diff --git "a/exp/log/log-train-2022-04-28-06-39-03-6" "b/exp/log/log-train-2022-04-28-06-39-03-6"
new file mode 100644--- /dev/null
+++ "b/exp/log/log-train-2022-04-28-06-39-03-6"
@@ -0,0 +1,3784 @@
+2022-04-28 06:39:03,125 INFO [train.py:827] (6/8) Training started
+2022-04-28 06:39:03,125 INFO [train.py:837] (6/8) Device: cuda:6
+2022-04-28 06:39:03,161 INFO [train.py:846] (6/8) {'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] (6/8) About to create model
+2022-04-28 06:39:03,691 INFO [train.py:852] (6/8) Number of model parameters: 118129516
+2022-04-28 06:39:09,695 INFO [train.py:858] (6/8) Using DDP
+2022-04-28 06:39:10,515 INFO [asr_datamodule.py:391] (6/8) About to get train-clean-100 cuts
+2022-04-28 06:39:17,003 INFO [asr_datamodule.py:398] (6/8) About to get train-clean-360 cuts
+2022-04-28 06:39:41,860 INFO [asr_datamodule.py:405] (6/8) About to get train-other-500 cuts
+2022-04-28 06:40:23,310 INFO [asr_datamodule.py:209] (6/8) Enable MUSAN
+2022-04-28 06:40:23,310 INFO [asr_datamodule.py:210] (6/8) About to get Musan cuts
+2022-04-28 06:40:24,577 INFO [asr_datamodule.py:238] (6/8) Enable SpecAugment
+2022-04-28 06:40:24,577 INFO [asr_datamodule.py:239] (6/8) Time warp factor: 80
+2022-04-28 06:40:24,577 INFO [asr_datamodule.py:251] (6/8) Num frame mask: 10
+2022-04-28 06:40:24,577 INFO [asr_datamodule.py:264] (6/8) About to create train dataset
+2022-04-28 06:40:24,577 INFO [asr_datamodule.py:292] (6/8) Using BucketingSampler.
+2022-04-28 06:40:29,051 INFO [asr_datamodule.py:308] (6/8) About to create train dataloader
+2022-04-28 06:40:29,051 INFO [asr_datamodule.py:412] (6/8) About to get dev-clean cuts
+2022-04-28 06:40:29,315 INFO [asr_datamodule.py:417] (6/8) About to get dev-other cuts
+2022-04-28 06:40:29,444 INFO [asr_datamodule.py:339] (6/8) About to create dev dataset
+2022-04-28 06:40:29,454 INFO [asr_datamodule.py:358] (6/8) About to create dev dataloader
+2022-04-28 06:40:29,455 INFO [train.py:987] (6/8) 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] (6/8) Reducer buckets have been rebuilt in this iteration.
+2022-04-28 06:41:17,064 INFO [train.py:763] (6/8) Epoch 0, batch 0, loss[loss=0.6847, simple_loss=1.369, pruned_loss=7.136, over 7297.00 frames.], tot_loss[loss=0.6847, simple_loss=1.369, pruned_loss=7.136, over 7297.00 frames.], batch size: 17, lr: 3.00e-03
+2022-04-28 06:42:23,565 INFO [train.py:763] (6/8) Epoch 0, batch 50, loss[loss=0.4922, simple_loss=0.9844, pruned_loss=6.678, over 7148.00 frames.], tot_loss[loss=0.5718, simple_loss=1.144, pruned_loss=6.961, over 324141.85 frames.], batch size: 19, lr: 3.00e-03
+2022-04-28 06:43:30,338 INFO [train.py:763] (6/8) Epoch 0, batch 100, loss[loss=0.4016, simple_loss=0.8031, pruned_loss=6.652, over 7004.00 frames.], tot_loss[loss=0.5118, simple_loss=1.024, pruned_loss=6.876, over 566163.62 frames.], batch size: 16, lr: 3.00e-03
+2022-04-28 06:44:37,579 INFO [train.py:763] (6/8) Epoch 0, batch 150, loss[loss=0.366, simple_loss=0.732, pruned_loss=6.65, over 7018.00 frames.], tot_loss[loss=0.4777, simple_loss=0.9555, pruned_loss=6.859, over 758105.89 frames.], batch size: 16, lr: 3.00e-03
+2022-04-28 06:45:44,959 INFO [train.py:763] (6/8) Epoch 0, batch 200, loss[loss=0.4478, simple_loss=0.8955, pruned_loss=6.861, over 7301.00 frames.], tot_loss[loss=0.4526, simple_loss=0.9051, pruned_loss=6.828, over 908133.15 frames.], batch size: 25, lr: 3.00e-03
+2022-04-28 06:46:50,981 INFO [train.py:763] (6/8) Epoch 0, batch 250, loss[loss=0.4261, simple_loss=0.8521, pruned_loss=6.831, over 7316.00 frames.], tot_loss[loss=0.4365, simple_loss=0.873, pruned_loss=6.793, over 1018264.53 frames.], batch size: 21, lr: 3.00e-03
+2022-04-28 06:47:58,726 INFO [train.py:763] (6/8) Epoch 0, batch 300, loss[loss=0.3929, simple_loss=0.7859, pruned_loss=6.714, over 7287.00 frames.], tot_loss[loss=0.4243, simple_loss=0.8487, pruned_loss=6.761, over 1109938.09 frames.], batch size: 25, lr: 3.00e-03
+2022-04-28 06:49:06,198 INFO [train.py:763] (6/8) Epoch 0, batch 350, loss[loss=0.3677, simple_loss=0.7354, pruned_loss=6.631, over 7253.00 frames.], tot_loss[loss=0.4139, simple_loss=0.8277, pruned_loss=6.727, over 1178924.48 frames.], batch size: 19, lr: 3.00e-03
+2022-04-28 06:50:12,118 INFO [train.py:763] (6/8) Epoch 0, batch 400, loss[loss=0.3834, simple_loss=0.7668, pruned_loss=6.657, over 7409.00 frames.], tot_loss[loss=0.4048, simple_loss=0.8096, pruned_loss=6.704, over 1231744.66 frames.], batch size: 21, lr: 3.00e-03
+2022-04-28 06:51:17,804 INFO [train.py:763] (6/8) Epoch 0, batch 450, loss[loss=0.3577, simple_loss=0.7153, pruned_loss=6.721, over 7405.00 frames.], tot_loss[loss=0.3918, simple_loss=0.7835, pruned_loss=6.685, over 1268056.65 frames.], batch size: 21, lr: 2.99e-03
+2022-04-28 06:52:24,500 INFO [train.py:763] (6/8) Epoch 0, batch 500, loss[loss=0.3435, simple_loss=0.6871, pruned_loss=6.761, over 7204.00 frames.], tot_loss[loss=0.3753, simple_loss=0.7506, pruned_loss=6.672, over 1303694.99 frames.], batch size: 22, lr: 2.99e-03
+2022-04-28 06:53:29,999 INFO [train.py:763] (6/8) Epoch 0, batch 550, loss[loss=0.3374, simple_loss=0.6749, pruned_loss=6.733, over 7336.00 frames.], tot_loss[loss=0.3609, simple_loss=0.7219, pruned_loss=6.672, over 1329447.44 frames.], batch size: 22, lr: 2.99e-03
+2022-04-28 06:54:36,573 INFO [train.py:763] (6/8) Epoch 0, batch 600, loss[loss=0.2855, simple_loss=0.5711, pruned_loss=6.666, over 7106.00 frames.], tot_loss[loss=0.3452, simple_loss=0.6905, pruned_loss=6.664, over 1350747.85 frames.], batch size: 21, lr: 2.99e-03
+2022-04-28 06:55:42,125 INFO [train.py:763] (6/8) Epoch 0, batch 650, loss[loss=0.2237, simple_loss=0.4473, pruned_loss=6.449, over 6983.00 frames.], tot_loss[loss=0.3309, simple_loss=0.6618, pruned_loss=6.653, over 1369199.11 frames.], batch size: 16, lr: 2.99e-03
+2022-04-28 06:56:47,775 INFO [train.py:763] (6/8) Epoch 0, batch 700, loss[loss=0.2781, simple_loss=0.5563, pruned_loss=6.656, over 7196.00 frames.], tot_loss[loss=0.3164, simple_loss=0.6328, pruned_loss=6.635, over 1380324.83 frames.], batch size: 23, lr: 2.99e-03
+2022-04-28 06:57:54,486 INFO [train.py:763] (6/8) Epoch 0, batch 750, loss[loss=0.2086, simple_loss=0.4173, pruned_loss=6.375, over 7281.00 frames.], tot_loss[loss=0.3032, simple_loss=0.6065, pruned_loss=6.619, over 1391924.05 frames.], batch size: 17, lr: 2.98e-03
+2022-04-28 06:59:01,269 INFO [train.py:763] (6/8) Epoch 0, batch 800, loss[loss=0.2814, simple_loss=0.5627, pruned_loss=6.681, over 7111.00 frames.], tot_loss[loss=0.2937, simple_loss=0.5873, pruned_loss=6.613, over 1397300.71 frames.], batch size: 21, lr: 2.98e-03
+2022-04-28 07:00:07,437 INFO [train.py:763] (6/8) Epoch 0, batch 850, loss[loss=0.2697, simple_loss=0.5394, pruned_loss=6.634, over 7218.00 frames.], tot_loss[loss=0.2845, simple_loss=0.569, pruned_loss=6.599, over 1402963.18 frames.], batch size: 21, lr: 2.98e-03
+2022-04-28 07:01:13,428 INFO [train.py:763] (6/8) Epoch 0, batch 900, loss[loss=0.2583, simple_loss=0.5166, pruned_loss=6.667, over 7321.00 frames.], tot_loss[loss=0.2758, simple_loss=0.5515, pruned_loss=6.589, over 1407585.82 frames.], batch size: 21, lr: 2.98e-03
+2022-04-28 07:02:19,013 INFO [train.py:763] (6/8) Epoch 0, batch 950, loss[loss=0.2103, simple_loss=0.4206, pruned_loss=6.396, over 7420.00 frames.], tot_loss[loss=0.2693, simple_loss=0.5386, pruned_loss=6.584, over 1404809.15 frames.], batch size: 17, lr: 2.97e-03
+2022-04-28 07:03:26,142 INFO [train.py:763] (6/8) Epoch 0, batch 1000, loss[loss=0.2073, simple_loss=0.4147, pruned_loss=6.471, over 6998.00 frames.], tot_loss[loss=0.2635, simple_loss=0.527, pruned_loss=6.58, over 1405139.57 frames.], batch size: 16, lr: 2.97e-03
+2022-04-28 07:04:32,978 INFO [train.py:763] (6/8) Epoch 0, batch 1050, loss[loss=0.2131, simple_loss=0.4262, pruned_loss=6.486, over 7017.00 frames.], tot_loss[loss=0.2585, simple_loss=0.517, pruned_loss=6.578, over 1407929.99 frames.], batch size: 16, lr: 2.97e-03
+2022-04-28 07:05:39,531 INFO [train.py:763] (6/8) Epoch 0, batch 1100, loss[loss=0.2246, simple_loss=0.4491, pruned_loss=6.563, over 7203.00 frames.], tot_loss[loss=0.2536, simple_loss=0.5072, pruned_loss=6.581, over 1412141.16 frames.], batch size: 22, lr: 2.96e-03
+2022-04-28 07:06:46,912 INFO [train.py:763] (6/8) Epoch 0, batch 1150, loss[loss=0.2394, simple_loss=0.4788, pruned_loss=6.572, over 6940.00 frames.], tot_loss[loss=0.2479, simple_loss=0.4958, pruned_loss=6.576, over 1412444.18 frames.], batch size: 32, lr: 2.96e-03
+2022-04-28 07:07:52,784 INFO [train.py:763] (6/8) Epoch 0, batch 1200, loss[loss=0.2238, simple_loss=0.4476, pruned_loss=6.612, over 7141.00 frames.], tot_loss[loss=0.2436, simple_loss=0.4873, pruned_loss=6.578, over 1420104.27 frames.], batch size: 26, lr: 2.96e-03
+2022-04-28 07:08:58,131 INFO [train.py:763] (6/8) Epoch 0, batch 1250, loss[loss=0.2364, simple_loss=0.4727, pruned_loss=6.676, over 7375.00 frames.], tot_loss[loss=0.2402, simple_loss=0.4803, pruned_loss=6.579, over 1414147.38 frames.], batch size: 23, lr: 2.95e-03
+2022-04-28 07:10:04,044 INFO [train.py:763] (6/8) Epoch 0, batch 1300, loss[loss=0.2307, simple_loss=0.4613, pruned_loss=6.735, over 7299.00 frames.], tot_loss[loss=0.2362, simple_loss=0.4723, pruned_loss=6.584, over 1421760.39 frames.], batch size: 24, lr: 2.95e-03
+2022-04-28 07:11:09,800 INFO [train.py:763] (6/8) Epoch 0, batch 1350, loss[loss=0.2562, simple_loss=0.5124, pruned_loss=6.646, over 7141.00 frames.], tot_loss[loss=0.2326, simple_loss=0.4653, pruned_loss=6.58, over 1422938.85 frames.], batch size: 20, lr: 2.95e-03
+2022-04-28 07:12:15,115 INFO [train.py:763] (6/8) Epoch 0, batch 1400, loss[loss=0.2469, simple_loss=0.4937, pruned_loss=6.673, over 7294.00 frames.], tot_loss[loss=0.2319, simple_loss=0.4639, pruned_loss=6.592, over 1419768.78 frames.], batch size: 24, lr: 2.94e-03
+2022-04-28 07:13:21,018 INFO [train.py:763] (6/8) Epoch 0, batch 1450, loss[loss=0.1835, simple_loss=0.3669, pruned_loss=6.405, over 7128.00 frames.], tot_loss[loss=0.2284, simple_loss=0.4569, pruned_loss=6.585, over 1420386.89 frames.], batch size: 17, lr: 2.94e-03
+2022-04-28 07:14:26,712 INFO [train.py:763] (6/8) Epoch 0, batch 1500, loss[loss=0.2241, simple_loss=0.4481, pruned_loss=6.643, over 7319.00 frames.], tot_loss[loss=0.2258, simple_loss=0.4516, pruned_loss=6.58, over 1423301.52 frames.], batch size: 24, lr: 2.94e-03
+2022-04-28 07:15:32,249 INFO [train.py:763] (6/8) Epoch 0, batch 1550, loss[loss=0.2038, simple_loss=0.4077, pruned_loss=6.565, over 7099.00 frames.], tot_loss[loss=0.2234, simple_loss=0.4469, pruned_loss=6.579, over 1423485.47 frames.], batch size: 21, lr: 2.93e-03
+2022-04-28 07:16:38,328 INFO [train.py:763] (6/8) Epoch 0, batch 1600, loss[loss=0.2132, simple_loss=0.4263, pruned_loss=6.592, over 7326.00 frames.], tot_loss[loss=0.221, simple_loss=0.442, pruned_loss=6.57, over 1421284.40 frames.], batch size: 20, lr: 2.93e-03
+2022-04-28 07:17:45,342 INFO [train.py:763] (6/8) Epoch 0, batch 1650, loss[loss=0.2089, simple_loss=0.4178, pruned_loss=6.611, over 7165.00 frames.], tot_loss[loss=0.2192, simple_loss=0.4384, pruned_loss=6.568, over 1422848.37 frames.], batch size: 18, lr: 2.92e-03
+2022-04-28 07:18:51,997 INFO [train.py:763] (6/8) Epoch 0, batch 1700, loss[loss=0.2137, simple_loss=0.4274, pruned_loss=6.57, over 6446.00 frames.], tot_loss[loss=0.2177, simple_loss=0.4355, pruned_loss=6.57, over 1419108.85 frames.], batch size: 38, lr: 2.92e-03
+2022-04-28 07:19:58,697 INFO [train.py:763] (6/8) Epoch 0, batch 1750, loss[loss=0.2157, simple_loss=0.4315, pruned_loss=6.525, over 6380.00 frames.], tot_loss[loss=0.2147, simple_loss=0.4294, pruned_loss=6.568, over 1418472.39 frames.], batch size: 38, lr: 2.91e-03
+2022-04-28 07:21:06,367 INFO [train.py:763] (6/8) Epoch 0, batch 1800, loss[loss=0.2318, simple_loss=0.4636, pruned_loss=6.562, over 7055.00 frames.], tot_loss[loss=0.2132, simple_loss=0.4264, pruned_loss=6.569, over 1418544.03 frames.], batch size: 28, lr: 2.91e-03
+2022-04-28 07:22:12,424 INFO [train.py:763] (6/8) Epoch 0, batch 1850, loss[loss=0.2492, simple_loss=0.4984, pruned_loss=6.554, over 5058.00 frames.], tot_loss[loss=0.2113, simple_loss=0.4226, pruned_loss=6.567, over 1420512.91 frames.], batch size: 52, lr: 2.91e-03
+2022-04-28 07:23:18,957 INFO [train.py:763] (6/8) Epoch 0, batch 1900, loss[loss=0.2, simple_loss=0.3999, pruned_loss=6.602, over 7261.00 frames.], tot_loss[loss=0.2107, simple_loss=0.4213, pruned_loss=6.573, over 1420682.66 frames.], batch size: 19, lr: 2.90e-03
+2022-04-28 07:24:26,570 INFO [train.py:763] (6/8) Epoch 0, batch 1950, loss[loss=0.2167, simple_loss=0.4333, pruned_loss=6.604, over 7320.00 frames.], tot_loss[loss=0.2089, simple_loss=0.4179, pruned_loss=6.569, over 1422708.38 frames.], batch size: 21, lr: 2.90e-03
+2022-04-28 07:25:34,111 INFO [train.py:763] (6/8) Epoch 0, batch 2000, loss[loss=0.1712, simple_loss=0.3424, pruned_loss=6.35, over 6840.00 frames.], tot_loss[loss=0.2072, simple_loss=0.4144, pruned_loss=6.564, over 1423747.31 frames.], batch size: 15, lr: 2.89e-03
+2022-04-28 07:26:39,962 INFO [train.py:763] (6/8) Epoch 0, batch 2050, loss[loss=0.2214, simple_loss=0.4428, pruned_loss=6.619, over 7150.00 frames.], tot_loss[loss=0.2061, simple_loss=0.4122, pruned_loss=6.565, over 1421489.54 frames.], batch size: 26, lr: 2.89e-03
+2022-04-28 07:27:45,823 INFO [train.py:763] (6/8) Epoch 0, batch 2100, loss[loss=0.192, simple_loss=0.384, pruned_loss=6.404, over 7157.00 frames.], tot_loss[loss=0.2047, simple_loss=0.4095, pruned_loss=6.565, over 1418209.13 frames.], batch size: 18, lr: 2.88e-03
+2022-04-28 07:28:51,551 INFO [train.py:763] (6/8) Epoch 0, batch 2150, loss[loss=0.2224, simple_loss=0.4447, pruned_loss=6.608, over 7335.00 frames.], tot_loss[loss=0.2036, simple_loss=0.4071, pruned_loss=6.57, over 1422283.12 frames.], batch size: 22, lr: 2.88e-03
+2022-04-28 07:29:57,478 INFO [train.py:763] (6/8) Epoch 0, batch 2200, loss[loss=0.2318, simple_loss=0.4636, pruned_loss=6.716, over 7284.00 frames.], tot_loss[loss=0.2036, simple_loss=0.4072, pruned_loss=6.577, over 1421139.27 frames.], batch size: 25, lr: 2.87e-03
+2022-04-28 07:31:03,290 INFO [train.py:763] (6/8) Epoch 0, batch 2250, loss[loss=0.1957, simple_loss=0.3913, pruned_loss=6.682, over 7219.00 frames.], tot_loss[loss=0.203, simple_loss=0.4059, pruned_loss=6.579, over 1420822.56 frames.], batch size: 21, lr: 2.86e-03
+2022-04-28 07:32:08,990 INFO [train.py:763] (6/8) Epoch 0, batch 2300, loss[loss=0.1892, simple_loss=0.3784, pruned_loss=6.536, over 7256.00 frames.], tot_loss[loss=0.2027, simple_loss=0.4053, pruned_loss=6.579, over 1416328.35 frames.], batch size: 19, lr: 2.86e-03
+2022-04-28 07:33:14,408 INFO [train.py:763] (6/8) Epoch 0, batch 2350, loss[loss=0.2323, simple_loss=0.4646, pruned_loss=6.559, over 5085.00 frames.], tot_loss[loss=0.2017, simple_loss=0.4034, pruned_loss=6.584, over 1415813.52 frames.], batch size: 52, lr: 2.85e-03
+2022-04-28 07:34:20,289 INFO [train.py:763] (6/8) Epoch 0, batch 2400, loss[loss=0.1944, simple_loss=0.3888, pruned_loss=6.664, over 7437.00 frames.], tot_loss[loss=0.2009, simple_loss=0.4019, pruned_loss=6.583, over 1412455.20 frames.], batch size: 20, lr: 2.85e-03
+2022-04-28 07:35:25,717 INFO [train.py:763] (6/8) Epoch 0, batch 2450, loss[loss=0.2086, simple_loss=0.4172, pruned_loss=6.448, over 4725.00 frames.], tot_loss[loss=0.2004, simple_loss=0.4007, pruned_loss=6.582, over 1412801.50 frames.], batch size: 52, lr: 2.84e-03
+2022-04-28 07:36:32,809 INFO [train.py:763] (6/8) Epoch 0, batch 2500, loss[loss=0.2133, simple_loss=0.4267, pruned_loss=6.712, over 7320.00 frames.], tot_loss[loss=0.1995, simple_loss=0.3989, pruned_loss=6.58, over 1418123.33 frames.], batch size: 20, lr: 2.84e-03
+2022-04-28 07:37:40,457 INFO [train.py:763] (6/8) Epoch 0, batch 2550, loss[loss=0.1765, simple_loss=0.3529, pruned_loss=6.465, over 7419.00 frames.], tot_loss[loss=0.1997, simple_loss=0.3995, pruned_loss=6.59, over 1418781.15 frames.], batch size: 18, lr: 2.83e-03
+2022-04-28 07:38:46,545 INFO [train.py:763] (6/8) Epoch 0, batch 2600, loss[loss=0.2207, simple_loss=0.4415, pruned_loss=6.808, over 7236.00 frames.], tot_loss[loss=0.1989, simple_loss=0.3978, pruned_loss=6.594, over 1422480.88 frames.], batch size: 20, lr: 2.83e-03
+2022-04-28 07:39:52,336 INFO [train.py:763] (6/8) Epoch 0, batch 2650, loss[loss=0.1851, simple_loss=0.3703, pruned_loss=6.506, over 7235.00 frames.], tot_loss[loss=0.1976, simple_loss=0.3952, pruned_loss=6.592, over 1424080.10 frames.], batch size: 20, lr: 2.82e-03
+2022-04-28 07:40:58,208 INFO [train.py:763] (6/8) Epoch 0, batch 2700, loss[loss=0.2028, simple_loss=0.4056, pruned_loss=6.649, over 7144.00 frames.], tot_loss[loss=0.1971, simple_loss=0.3941, pruned_loss=6.592, over 1423125.16 frames.], batch size: 20, lr: 2.81e-03
+2022-04-28 07:42:03,318 INFO [train.py:763] (6/8) Epoch 0, batch 2750, loss[loss=0.1732, simple_loss=0.3464, pruned_loss=6.579, over 7321.00 frames.], tot_loss[loss=0.1969, simple_loss=0.3938, pruned_loss=6.598, over 1423539.88 frames.], batch size: 20, lr: 2.81e-03
+2022-04-28 07:43:09,987 INFO [train.py:763] (6/8) Epoch 0, batch 2800, loss[loss=0.1914, simple_loss=0.3828, pruned_loss=6.593, over 7149.00 frames.], tot_loss[loss=0.1965, simple_loss=0.3929, pruned_loss=6.6, over 1422023.17 frames.], batch size: 20, lr: 2.80e-03
+2022-04-28 07:44:16,867 INFO [train.py:763] (6/8) Epoch 0, batch 2850, loss[loss=0.1883, simple_loss=0.3767, pruned_loss=6.521, over 7368.00 frames.], tot_loss[loss=0.1955, simple_loss=0.3909, pruned_loss=6.601, over 1425173.99 frames.], batch size: 19, lr: 2.80e-03
+2022-04-28 07:45:22,338 INFO [train.py:763] (6/8) Epoch 0, batch 2900, loss[loss=0.2029, simple_loss=0.4059, pruned_loss=6.773, over 7313.00 frames.], tot_loss[loss=0.196, simple_loss=0.392, pruned_loss=6.608, over 1420421.67 frames.], batch size: 20, lr: 2.79e-03
+2022-04-28 07:46:27,655 INFO [train.py:763] (6/8) Epoch 0, batch 2950, loss[loss=0.188, simple_loss=0.376, pruned_loss=6.545, over 7182.00 frames.], tot_loss[loss=0.1944, simple_loss=0.3889, pruned_loss=6.603, over 1416274.50 frames.], batch size: 26, lr: 2.78e-03
+2022-04-28 07:47:32,890 INFO [train.py:763] (6/8) Epoch 0, batch 3000, loss[loss=0.3535, simple_loss=0.4102, pruned_loss=1.484, over 7293.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3877, pruned_loss=6.579, over 1420042.12 frames.], batch size: 17, lr: 2.78e-03
+2022-04-28 07:47:32,890 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-28 07:47:50,998 INFO [train.py:792] (6/8) Epoch 0, validation: loss=2.072, simple_loss=0.4419, pruned_loss=1.851, over 698248.00 frames.
+2022-04-28 07:48:57,676 INFO [train.py:763] (6/8) Epoch 0, batch 3050, loss[loss=0.3146, simple_loss=0.4375, pruned_loss=0.9583, over 6560.00 frames.], tot_loss[loss=0.2519, simple_loss=0.398, pruned_loss=5.395, over 1419410.56 frames.], batch size: 38, lr: 2.77e-03
+2022-04-28 07:50:04,085 INFO [train.py:763] (6/8) Epoch 0, batch 3100, loss[loss=0.2761, simple_loss=0.4333, pruned_loss=0.5947, over 7402.00 frames.], tot_loss[loss=0.2531, simple_loss=0.3935, pruned_loss=4.336, over 1425034.93 frames.], batch size: 21, lr: 2.77e-03
+2022-04-28 07:51:10,056 INFO [train.py:763] (6/8) Epoch 0, batch 3150, loss[loss=0.2222, simple_loss=0.3757, pruned_loss=0.3433, over 7417.00 frames.], tot_loss[loss=0.2481, simple_loss=0.3901, pruned_loss=3.463, over 1426560.64 frames.], batch size: 21, lr: 2.76e-03
+2022-04-28 07:52:16,820 INFO [train.py:763] (6/8) Epoch 0, batch 3200, loss[loss=0.2213, simple_loss=0.3851, pruned_loss=0.2874, over 7271.00 frames.], tot_loss[loss=0.2422, simple_loss=0.388, pruned_loss=2.77, over 1422748.80 frames.], batch size: 24, lr: 2.75e-03
+2022-04-28 07:53:24,323 INFO [train.py:763] (6/8) Epoch 0, batch 3250, loss[loss=0.216, simple_loss=0.3838, pruned_loss=0.2414, over 7145.00 frames.], tot_loss[loss=0.2366, simple_loss=0.3867, pruned_loss=2.214, over 1422504.67 frames.], batch size: 20, lr: 2.75e-03
+2022-04-28 07:54:30,949 INFO [train.py:763] (6/8) Epoch 0, batch 3300, loss[loss=0.231, simple_loss=0.4079, pruned_loss=0.2705, over 7369.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3869, pruned_loss=1.783, over 1418552.47 frames.], batch size: 23, lr: 2.74e-03
+2022-04-28 07:55:37,658 INFO [train.py:763] (6/8) Epoch 0, batch 3350, loss[loss=0.2226, simple_loss=0.3983, pruned_loss=0.2344, over 7266.00 frames.], tot_loss[loss=0.2281, simple_loss=0.3854, pruned_loss=1.433, over 1422946.61 frames.], batch size: 24, lr: 2.73e-03
+2022-04-28 07:56:43,237 INFO [train.py:763] (6/8) Epoch 0, batch 3400, loss[loss=0.1946, simple_loss=0.3507, pruned_loss=0.1928, over 7251.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3847, pruned_loss=1.162, over 1423416.60 frames.], batch size: 19, lr: 2.73e-03
+2022-04-28 07:57:49,073 INFO [train.py:763] (6/8) Epoch 0, batch 3450, loss[loss=0.2185, simple_loss=0.3946, pruned_loss=0.2119, over 7285.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3839, pruned_loss=0.9502, over 1423901.83 frames.], batch size: 25, lr: 2.72e-03
+2022-04-28 07:58:54,329 INFO [train.py:763] (6/8) Epoch 0, batch 3500, loss[loss=0.2365, simple_loss=0.4232, pruned_loss=0.2488, over 7164.00 frames.], tot_loss[loss=0.2191, simple_loss=0.3832, pruned_loss=0.784, over 1421641.57 frames.], batch size: 26, lr: 2.72e-03
+2022-04-28 08:00:00,010 INFO [train.py:763] (6/8) Epoch 0, batch 3550, loss[loss=0.2109, simple_loss=0.3888, pruned_loss=0.1655, over 7213.00 frames.], tot_loss[loss=0.216, simple_loss=0.3809, pruned_loss=0.6511, over 1422947.14 frames.], batch size: 21, lr: 2.71e-03
+2022-04-28 08:01:06,049 INFO [train.py:763] (6/8) Epoch 0, batch 3600, loss[loss=0.1846, simple_loss=0.3353, pruned_loss=0.1696, over 7025.00 frames.], tot_loss[loss=0.2133, simple_loss=0.3788, pruned_loss=0.5477, over 1420816.67 frames.], batch size: 16, lr: 2.70e-03
+2022-04-28 08:02:21,061 INFO [train.py:763] (6/8) Epoch 0, batch 3650, loss[loss=0.2219, simple_loss=0.4019, pruned_loss=0.2093, over 7211.00 frames.], tot_loss[loss=0.2117, simple_loss=0.378, pruned_loss=0.4668, over 1421092.68 frames.], batch size: 21, lr: 2.70e-03
+2022-04-28 08:04:03,467 INFO [train.py:763] (6/8) Epoch 0, batch 3700, loss[loss=0.2154, simple_loss=0.3941, pruned_loss=0.1832, over 6698.00 frames.], tot_loss[loss=0.2098, simple_loss=0.3765, pruned_loss=0.4016, over 1425367.15 frames.], batch size: 31, lr: 2.69e-03
+2022-04-28 08:05:34,890 INFO [train.py:763] (6/8) Epoch 0, batch 3750, loss[loss=0.1842, simple_loss=0.3389, pruned_loss=0.1477, over 7267.00 frames.], tot_loss[loss=0.2085, simple_loss=0.3757, pruned_loss=0.3527, over 1417794.93 frames.], batch size: 18, lr: 2.68e-03
+2022-04-28 08:06:40,597 INFO [train.py:763] (6/8) Epoch 0, batch 3800, loss[loss=0.1826, simple_loss=0.3372, pruned_loss=0.14, over 7123.00 frames.], tot_loss[loss=0.2068, simple_loss=0.3738, pruned_loss=0.3118, over 1418043.31 frames.], batch size: 17, lr: 2.68e-03
+2022-04-28 08:07:46,191 INFO [train.py:763] (6/8) Epoch 0, batch 3850, loss[loss=0.1796, simple_loss=0.3333, pruned_loss=0.1295, over 7130.00 frames.], tot_loss[loss=0.2057, simple_loss=0.373, pruned_loss=0.2798, over 1423300.22 frames.], batch size: 17, lr: 2.67e-03
+2022-04-28 08:08:52,447 INFO [train.py:763] (6/8) Epoch 0, batch 3900, loss[loss=0.1745, simple_loss=0.3229, pruned_loss=0.1301, over 7258.00 frames.], tot_loss[loss=0.2051, simple_loss=0.3727, pruned_loss=0.2556, over 1420845.55 frames.], batch size: 16, lr: 2.66e-03
+2022-04-28 08:09:58,860 INFO [train.py:763] (6/8) Epoch 0, batch 3950, loss[loss=0.1719, simple_loss=0.3185, pruned_loss=0.1262, over 6792.00 frames.], tot_loss[loss=0.2043, simple_loss=0.372, pruned_loss=0.2358, over 1418879.45 frames.], batch size: 15, lr: 2.66e-03
+2022-04-28 08:11:04,206 INFO [train.py:763] (6/8) Epoch 0, batch 4000, loss[loss=0.1984, simple_loss=0.3674, pruned_loss=0.1468, over 7314.00 frames.], tot_loss[loss=0.2033, simple_loss=0.3711, pruned_loss=0.2191, over 1421258.75 frames.], batch size: 21, lr: 2.65e-03
+2022-04-28 08:12:09,510 INFO [train.py:763] (6/8) Epoch 0, batch 4050, loss[loss=0.2017, simple_loss=0.3724, pruned_loss=0.1548, over 7025.00 frames.], tot_loss[loss=0.203, simple_loss=0.371, pruned_loss=0.2072, over 1421813.03 frames.], batch size: 28, lr: 2.64e-03
+2022-04-28 08:13:15,840 INFO [train.py:763] (6/8) Epoch 0, batch 4100, loss[loss=0.2004, simple_loss=0.3653, pruned_loss=0.1776, over 7260.00 frames.], tot_loss[loss=0.2018, simple_loss=0.3693, pruned_loss=0.1961, over 1421903.21 frames.], batch size: 19, lr: 2.64e-03
+2022-04-28 08:14:22,421 INFO [train.py:763] (6/8) Epoch 0, batch 4150, loss[loss=0.1763, simple_loss=0.3297, pruned_loss=0.1141, over 7062.00 frames.], tot_loss[loss=0.2015, simple_loss=0.3694, pruned_loss=0.1875, over 1426161.71 frames.], batch size: 18, lr: 2.63e-03
+2022-04-28 08:15:27,429 INFO [train.py:763] (6/8) Epoch 0, batch 4200, loss[loss=0.2238, simple_loss=0.4088, pruned_loss=0.1943, over 7206.00 frames.], tot_loss[loss=0.202, simple_loss=0.3705, pruned_loss=0.1821, over 1425590.18 frames.], batch size: 22, lr: 2.63e-03
+2022-04-28 08:16:32,484 INFO [train.py:763] (6/8) Epoch 0, batch 4250, loss[loss=0.2043, simple_loss=0.3744, pruned_loss=0.1706, over 7433.00 frames.], tot_loss[loss=0.2024, simple_loss=0.3716, pruned_loss=0.1783, over 1423612.75 frames.], batch size: 20, lr: 2.62e-03
+2022-04-28 08:17:38,266 INFO [train.py:763] (6/8) Epoch 0, batch 4300, loss[loss=0.2036, simple_loss=0.3753, pruned_loss=0.16, over 7069.00 frames.], tot_loss[loss=0.202, simple_loss=0.3711, pruned_loss=0.1736, over 1422863.93 frames.], batch size: 28, lr: 2.61e-03
+2022-04-28 08:18:43,771 INFO [train.py:763] (6/8) Epoch 0, batch 4350, loss[loss=0.1755, simple_loss=0.3283, pruned_loss=0.1129, over 7426.00 frames.], tot_loss[loss=0.2019, simple_loss=0.3711, pruned_loss=0.1701, over 1426502.45 frames.], batch size: 20, lr: 2.61e-03
+2022-04-28 08:19:48,917 INFO [train.py:763] (6/8) Epoch 0, batch 4400, loss[loss=0.183, simple_loss=0.3391, pruned_loss=0.1346, over 7288.00 frames.], tot_loss[loss=0.2021, simple_loss=0.3717, pruned_loss=0.1676, over 1424427.84 frames.], batch size: 18, lr: 2.60e-03
+2022-04-28 08:20:54,083 INFO [train.py:763] (6/8) Epoch 0, batch 4450, loss[loss=0.2014, simple_loss=0.3718, pruned_loss=0.1551, over 7430.00 frames.], tot_loss[loss=0.2021, simple_loss=0.372, pruned_loss=0.1648, over 1423720.99 frames.], batch size: 20, lr: 2.59e-03
+2022-04-28 08:21:59,572 INFO [train.py:763] (6/8) Epoch 0, batch 4500, loss[loss=0.2151, simple_loss=0.3941, pruned_loss=0.18, over 6335.00 frames.], tot_loss[loss=0.2021, simple_loss=0.3722, pruned_loss=0.1634, over 1413810.27 frames.], batch size: 37, lr: 2.59e-03
+2022-04-28 08:23:05,655 INFO [train.py:763] (6/8) Epoch 0, batch 4550, loss[loss=0.2246, simple_loss=0.4071, pruned_loss=0.2103, over 5110.00 frames.], tot_loss[loss=0.2023, simple_loss=0.3726, pruned_loss=0.1626, over 1394892.33 frames.], batch size: 52, lr: 2.58e-03
+2022-04-28 08:24:44,870 INFO [train.py:763] (6/8) Epoch 1, batch 0, loss[loss=0.2157, simple_loss=0.3969, pruned_loss=0.1724, over 7224.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3969, pruned_loss=0.1724, over 7224.00 frames.], batch size: 26, lr: 2.56e-03
+2022-04-28 08:25:50,519 INFO [train.py:763] (6/8) Epoch 1, batch 50, loss[loss=0.2153, simple_loss=0.3972, pruned_loss=0.167, over 7238.00 frames.], tot_loss[loss=0.1996, simple_loss=0.3678, pruned_loss=0.1568, over 312415.65 frames.], batch size: 20, lr: 2.55e-03
+2022-04-28 08:26:56,239 INFO [train.py:763] (6/8) Epoch 1, batch 100, loss[loss=0.1883, simple_loss=0.3511, pruned_loss=0.1279, over 7423.00 frames.], tot_loss[loss=0.1958, simple_loss=0.362, pruned_loss=0.1475, over 560384.75 frames.], batch size: 20, lr: 2.54e-03
+2022-04-28 08:28:01,398 INFO [train.py:763] (6/8) Epoch 1, batch 150, loss[loss=0.1831, simple_loss=0.3384, pruned_loss=0.1387, over 7330.00 frames.], tot_loss[loss=0.1955, simple_loss=0.3616, pruned_loss=0.1473, over 751245.11 frames.], batch size: 20, lr: 2.54e-03
+2022-04-28 08:29:06,950 INFO [train.py:763] (6/8) Epoch 1, batch 200, loss[loss=0.1973, simple_loss=0.3667, pruned_loss=0.1397, over 7164.00 frames.], tot_loss[loss=0.1956, simple_loss=0.3617, pruned_loss=0.1477, over 900541.92 frames.], batch size: 19, lr: 2.53e-03
+2022-04-28 08:30:12,406 INFO [train.py:763] (6/8) Epoch 1, batch 250, loss[loss=0.2106, simple_loss=0.392, pruned_loss=0.146, over 7385.00 frames.], tot_loss[loss=0.1967, simple_loss=0.3637, pruned_loss=0.1481, over 1015700.35 frames.], batch size: 23, lr: 2.53e-03
+2022-04-28 08:31:17,601 INFO [train.py:763] (6/8) Epoch 1, batch 300, loss[loss=0.1748, simple_loss=0.3257, pruned_loss=0.1197, over 7253.00 frames.], tot_loss[loss=0.1966, simple_loss=0.3638, pruned_loss=0.1468, over 1104941.54 frames.], batch size: 19, lr: 2.52e-03
+2022-04-28 08:32:23,180 INFO [train.py:763] (6/8) Epoch 1, batch 350, loss[loss=0.209, simple_loss=0.3855, pruned_loss=0.1631, over 7215.00 frames.], tot_loss[loss=0.1961, simple_loss=0.363, pruned_loss=0.1464, over 1174582.67 frames.], batch size: 21, lr: 2.51e-03
+2022-04-28 08:33:29,335 INFO [train.py:763] (6/8) Epoch 1, batch 400, loss[loss=0.2038, simple_loss=0.3805, pruned_loss=0.1358, over 7145.00 frames.], tot_loss[loss=0.1959, simple_loss=0.3628, pruned_loss=0.1455, over 1231260.26 frames.], batch size: 20, lr: 2.51e-03
+2022-04-28 08:34:36,148 INFO [train.py:763] (6/8) Epoch 1, batch 450, loss[loss=0.1955, simple_loss=0.3619, pruned_loss=0.1453, over 7160.00 frames.], tot_loss[loss=0.1965, simple_loss=0.3638, pruned_loss=0.1462, over 1276085.35 frames.], batch size: 19, lr: 2.50e-03
+2022-04-28 08:35:42,353 INFO [train.py:763] (6/8) Epoch 1, batch 500, loss[loss=0.1867, simple_loss=0.3467, pruned_loss=0.1339, over 7166.00 frames.], tot_loss[loss=0.1958, simple_loss=0.3627, pruned_loss=0.1446, over 1307549.85 frames.], batch size: 18, lr: 2.49e-03
+2022-04-28 08:36:48,850 INFO [train.py:763] (6/8) Epoch 1, batch 550, loss[loss=0.1842, simple_loss=0.3423, pruned_loss=0.1304, over 7366.00 frames.], tot_loss[loss=0.1958, simple_loss=0.3626, pruned_loss=0.1448, over 1332106.57 frames.], batch size: 19, lr: 2.49e-03
+2022-04-28 08:37:55,694 INFO [train.py:763] (6/8) Epoch 1, batch 600, loss[loss=0.2055, simple_loss=0.382, pruned_loss=0.1448, over 7375.00 frames.], tot_loss[loss=0.1957, simple_loss=0.3626, pruned_loss=0.1441, over 1353831.97 frames.], batch size: 23, lr: 2.48e-03
+2022-04-28 08:39:01,289 INFO [train.py:763] (6/8) Epoch 1, batch 650, loss[loss=0.163, simple_loss=0.3034, pruned_loss=0.1126, over 7276.00 frames.], tot_loss[loss=0.1943, simple_loss=0.3602, pruned_loss=0.1424, over 1368108.59 frames.], batch size: 18, lr: 2.48e-03
+2022-04-28 08:40:06,989 INFO [train.py:763] (6/8) Epoch 1, batch 700, loss[loss=0.2055, simple_loss=0.3761, pruned_loss=0.1748, over 4966.00 frames.], tot_loss[loss=0.1935, simple_loss=0.3587, pruned_loss=0.1412, over 1379561.64 frames.], batch size: 52, lr: 2.47e-03
+2022-04-28 08:41:12,402 INFO [train.py:763] (6/8) Epoch 1, batch 750, loss[loss=0.1948, simple_loss=0.3611, pruned_loss=0.142, over 7259.00 frames.], tot_loss[loss=0.193, simple_loss=0.3581, pruned_loss=0.1396, over 1390554.25 frames.], batch size: 19, lr: 2.46e-03
+2022-04-28 08:42:18,207 INFO [train.py:763] (6/8) Epoch 1, batch 800, loss[loss=0.1712, simple_loss=0.3208, pruned_loss=0.1078, over 7064.00 frames.], tot_loss[loss=0.1926, simple_loss=0.3573, pruned_loss=0.139, over 1399965.39 frames.], batch size: 18, lr: 2.46e-03
+2022-04-28 08:43:24,115 INFO [train.py:763] (6/8) Epoch 1, batch 850, loss[loss=0.1757, simple_loss=0.3303, pruned_loss=0.1057, over 7330.00 frames.], tot_loss[loss=0.1921, simple_loss=0.3565, pruned_loss=0.1384, over 1407670.66 frames.], batch size: 20, lr: 2.45e-03
+2022-04-28 08:44:29,825 INFO [train.py:763] (6/8) Epoch 1, batch 900, loss[loss=0.1726, simple_loss=0.3241, pruned_loss=0.1057, over 7426.00 frames.], tot_loss[loss=0.1923, simple_loss=0.3569, pruned_loss=0.138, over 1412400.03 frames.], batch size: 20, lr: 2.45e-03
+2022-04-28 08:45:35,252 INFO [train.py:763] (6/8) Epoch 1, batch 950, loss[loss=0.1723, simple_loss=0.3249, pruned_loss=0.09891, over 7270.00 frames.], tot_loss[loss=0.1925, simple_loss=0.3574, pruned_loss=0.1381, over 1415164.11 frames.], batch size: 19, lr: 2.44e-03
+2022-04-28 08:46:40,822 INFO [train.py:763] (6/8) Epoch 1, batch 1000, loss[loss=0.2181, simple_loss=0.4029, pruned_loss=0.1669, over 6948.00 frames.], tot_loss[loss=0.1917, simple_loss=0.3561, pruned_loss=0.1362, over 1416752.35 frames.], batch size: 32, lr: 2.43e-03
+2022-04-28 08:47:46,479 INFO [train.py:763] (6/8) Epoch 1, batch 1050, loss[loss=0.1735, simple_loss=0.3249, pruned_loss=0.1111, over 7438.00 frames.], tot_loss[loss=0.1908, simple_loss=0.3546, pruned_loss=0.1353, over 1419065.86 frames.], batch size: 20, lr: 2.43e-03
+2022-04-28 08:48:51,695 INFO [train.py:763] (6/8) Epoch 1, batch 1100, loss[loss=0.1766, simple_loss=0.3285, pruned_loss=0.1235, over 7164.00 frames.], tot_loss[loss=0.1908, simple_loss=0.3547, pruned_loss=0.1341, over 1419785.40 frames.], batch size: 18, lr: 2.42e-03
+2022-04-28 08:49:57,352 INFO [train.py:763] (6/8) Epoch 1, batch 1150, loss[loss=0.1789, simple_loss=0.3323, pruned_loss=0.1269, over 7238.00 frames.], tot_loss[loss=0.1897, simple_loss=0.3528, pruned_loss=0.133, over 1423983.44 frames.], batch size: 20, lr: 2.41e-03
+2022-04-28 08:51:02,492 INFO [train.py:763] (6/8) Epoch 1, batch 1200, loss[loss=0.1858, simple_loss=0.3475, pruned_loss=0.1204, over 7134.00 frames.], tot_loss[loss=0.1897, simple_loss=0.3528, pruned_loss=0.1325, over 1423942.20 frames.], batch size: 28, lr: 2.41e-03
+2022-04-28 08:52:07,810 INFO [train.py:763] (6/8) Epoch 1, batch 1250, loss[loss=0.1821, simple_loss=0.3393, pruned_loss=0.1244, over 7283.00 frames.], tot_loss[loss=0.1901, simple_loss=0.3537, pruned_loss=0.1328, over 1422994.39 frames.], batch size: 18, lr: 2.40e-03
+2022-04-28 08:53:12,960 INFO [train.py:763] (6/8) Epoch 1, batch 1300, loss[loss=0.2122, simple_loss=0.3937, pruned_loss=0.154, over 7215.00 frames.], tot_loss[loss=0.1904, simple_loss=0.3541, pruned_loss=0.1334, over 1417535.69 frames.], batch size: 21, lr: 2.40e-03
+2022-04-28 08:54:18,352 INFO [train.py:763] (6/8) Epoch 1, batch 1350, loss[loss=0.1757, simple_loss=0.3259, pruned_loss=0.1277, over 7275.00 frames.], tot_loss[loss=0.1892, simple_loss=0.3521, pruned_loss=0.1316, over 1421139.58 frames.], batch size: 17, lr: 2.39e-03
+2022-04-28 08:55:23,448 INFO [train.py:763] (6/8) Epoch 1, batch 1400, loss[loss=0.1952, simple_loss=0.3623, pruned_loss=0.1407, over 7224.00 frames.], tot_loss[loss=0.1903, simple_loss=0.354, pruned_loss=0.1329, over 1419741.88 frames.], batch size: 21, lr: 2.39e-03
+2022-04-28 08:56:28,949 INFO [train.py:763] (6/8) Epoch 1, batch 1450, loss[loss=0.3267, simple_loss=0.3726, pruned_loss=0.1404, over 7143.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3548, pruned_loss=0.1347, over 1423148.89 frames.], batch size: 26, lr: 2.38e-03
+2022-04-28 08:57:34,413 INFO [train.py:763] (6/8) Epoch 1, batch 1500, loss[loss=0.2969, simple_loss=0.3456, pruned_loss=0.1241, over 6479.00 frames.], tot_loss[loss=0.2374, simple_loss=0.3558, pruned_loss=0.1354, over 1423710.46 frames.], batch size: 38, lr: 2.37e-03
+2022-04-28 08:58:40,149 INFO [train.py:763] (6/8) Epoch 1, batch 1550, loss[loss=0.2713, simple_loss=0.3353, pruned_loss=0.1037, over 7437.00 frames.], tot_loss[loss=0.2551, simple_loss=0.3575, pruned_loss=0.1353, over 1427473.65 frames.], batch size: 20, lr: 2.37e-03
+2022-04-28 08:59:47,369 INFO [train.py:763] (6/8) Epoch 1, batch 1600, loss[loss=0.3121, simple_loss=0.3556, pruned_loss=0.1343, over 7164.00 frames.], tot_loss[loss=0.2667, simple_loss=0.3562, pruned_loss=0.1345, over 1425903.04 frames.], batch size: 18, lr: 2.36e-03
+2022-04-28 09:00:52,894 INFO [train.py:763] (6/8) Epoch 1, batch 1650, loss[loss=0.2499, simple_loss=0.3167, pruned_loss=0.0915, over 7422.00 frames.], tot_loss[loss=0.2762, simple_loss=0.3562, pruned_loss=0.1338, over 1427129.10 frames.], batch size: 20, lr: 2.36e-03
+2022-04-28 09:01:59,219 INFO [train.py:763] (6/8) Epoch 1, batch 1700, loss[loss=0.3429, simple_loss=0.3905, pruned_loss=0.1477, over 7413.00 frames.], tot_loss[loss=0.2822, simple_loss=0.3556, pruned_loss=0.1322, over 1424740.26 frames.], batch size: 21, lr: 2.35e-03
+2022-04-28 09:03:06,114 INFO [train.py:763] (6/8) Epoch 1, batch 1750, loss[loss=0.2571, simple_loss=0.3187, pruned_loss=0.09779, over 7291.00 frames.], tot_loss[loss=0.2901, simple_loss=0.358, pruned_loss=0.1327, over 1424315.63 frames.], batch size: 18, lr: 2.34e-03
+2022-04-28 09:04:13,395 INFO [train.py:763] (6/8) Epoch 1, batch 1800, loss[loss=0.2775, simple_loss=0.3268, pruned_loss=0.1141, over 7357.00 frames.], tot_loss[loss=0.2934, simple_loss=0.3576, pruned_loss=0.1315, over 1425704.77 frames.], batch size: 19, lr: 2.34e-03
+2022-04-28 09:05:20,643 INFO [train.py:763] (6/8) Epoch 1, batch 1850, loss[loss=0.3818, simple_loss=0.4026, pruned_loss=0.1805, over 7326.00 frames.], tot_loss[loss=0.2948, simple_loss=0.3563, pruned_loss=0.1298, over 1425410.65 frames.], batch size: 20, lr: 2.33e-03
+2022-04-28 09:06:26,266 INFO [train.py:763] (6/8) Epoch 1, batch 1900, loss[loss=0.2607, simple_loss=0.306, pruned_loss=0.1077, over 7001.00 frames.], tot_loss[loss=0.2971, simple_loss=0.3564, pruned_loss=0.129, over 1429252.94 frames.], batch size: 16, lr: 2.33e-03
+2022-04-28 09:07:32,798 INFO [train.py:763] (6/8) Epoch 1, batch 1950, loss[loss=0.2614, simple_loss=0.3265, pruned_loss=0.09819, over 7270.00 frames.], tot_loss[loss=0.2981, simple_loss=0.3561, pruned_loss=0.1279, over 1429809.69 frames.], batch size: 18, lr: 2.32e-03
+2022-04-28 09:08:38,162 INFO [train.py:763] (6/8) Epoch 1, batch 2000, loss[loss=0.3092, simple_loss=0.3735, pruned_loss=0.1224, over 7108.00 frames.], tot_loss[loss=0.299, simple_loss=0.3568, pruned_loss=0.1268, over 1423316.97 frames.], batch size: 21, lr: 2.32e-03
+2022-04-28 09:09:44,446 INFO [train.py:763] (6/8) Epoch 1, batch 2050, loss[loss=0.3073, simple_loss=0.3685, pruned_loss=0.123, over 7024.00 frames.], tot_loss[loss=0.2979, simple_loss=0.3553, pruned_loss=0.125, over 1424237.80 frames.], batch size: 28, lr: 2.31e-03
+2022-04-28 09:10:49,769 INFO [train.py:763] (6/8) Epoch 1, batch 2100, loss[loss=0.2589, simple_loss=0.3215, pruned_loss=0.09818, over 7404.00 frames.], tot_loss[loss=0.298, simple_loss=0.3552, pruned_loss=0.1241, over 1424783.07 frames.], batch size: 18, lr: 2.31e-03
+2022-04-28 09:11:55,403 INFO [train.py:763] (6/8) Epoch 1, batch 2150, loss[loss=0.3722, simple_loss=0.4109, pruned_loss=0.1667, over 7404.00 frames.], tot_loss[loss=0.298, simple_loss=0.3546, pruned_loss=0.1236, over 1423192.93 frames.], batch size: 21, lr: 2.30e-03
+2022-04-28 09:13:01,257 INFO [train.py:763] (6/8) Epoch 1, batch 2200, loss[loss=0.2644, simple_loss=0.3478, pruned_loss=0.09056, over 7116.00 frames.], tot_loss[loss=0.2977, simple_loss=0.3539, pruned_loss=0.123, over 1422787.09 frames.], batch size: 21, lr: 2.29e-03
+2022-04-28 09:14:06,870 INFO [train.py:763] (6/8) Epoch 1, batch 2250, loss[loss=0.3179, simple_loss=0.3718, pruned_loss=0.132, over 7213.00 frames.], tot_loss[loss=0.2976, simple_loss=0.3537, pruned_loss=0.1226, over 1423864.38 frames.], batch size: 21, lr: 2.29e-03
+2022-04-28 09:15:14,112 INFO [train.py:763] (6/8) Epoch 1, batch 2300, loss[loss=0.3087, simple_loss=0.3604, pruned_loss=0.1285, over 7212.00 frames.], tot_loss[loss=0.2976, simple_loss=0.3538, pruned_loss=0.1221, over 1425350.55 frames.], batch size: 22, lr: 2.28e-03
+2022-04-28 09:16:21,363 INFO [train.py:763] (6/8) Epoch 1, batch 2350, loss[loss=0.3638, simple_loss=0.4042, pruned_loss=0.1617, over 7241.00 frames.], tot_loss[loss=0.2984, simple_loss=0.3542, pruned_loss=0.1224, over 1423522.08 frames.], batch size: 20, lr: 2.28e-03
+2022-04-28 09:17:26,504 INFO [train.py:763] (6/8) Epoch 1, batch 2400, loss[loss=0.312, simple_loss=0.3757, pruned_loss=0.1242, over 7324.00 frames.], tot_loss[loss=0.297, simple_loss=0.3536, pruned_loss=0.1211, over 1423948.09 frames.], batch size: 21, lr: 2.27e-03
+2022-04-28 09:18:31,940 INFO [train.py:763] (6/8) Epoch 1, batch 2450, loss[loss=0.3086, simple_loss=0.3744, pruned_loss=0.1214, over 7321.00 frames.], tot_loss[loss=0.2972, simple_loss=0.354, pruned_loss=0.1208, over 1427732.65 frames.], batch size: 21, lr: 2.27e-03
+2022-04-28 09:19:37,100 INFO [train.py:763] (6/8) Epoch 1, batch 2500, loss[loss=0.3687, simple_loss=0.4158, pruned_loss=0.1608, over 7190.00 frames.], tot_loss[loss=0.2982, simple_loss=0.3547, pruned_loss=0.1214, over 1427748.48 frames.], batch size: 26, lr: 2.26e-03
+2022-04-28 09:20:43,300 INFO [train.py:763] (6/8) Epoch 1, batch 2550, loss[loss=0.282, simple_loss=0.3315, pruned_loss=0.1163, over 6995.00 frames.], tot_loss[loss=0.2989, simple_loss=0.3554, pruned_loss=0.1216, over 1427880.56 frames.], batch size: 16, lr: 2.26e-03
+2022-04-28 09:21:48,828 INFO [train.py:763] (6/8) Epoch 1, batch 2600, loss[loss=0.3388, simple_loss=0.3863, pruned_loss=0.1456, over 7148.00 frames.], tot_loss[loss=0.2969, simple_loss=0.3536, pruned_loss=0.1204, over 1429931.60 frames.], batch size: 26, lr: 2.25e-03
+2022-04-28 09:22:54,017 INFO [train.py:763] (6/8) Epoch 1, batch 2650, loss[loss=0.3494, simple_loss=0.3927, pruned_loss=0.153, over 6331.00 frames.], tot_loss[loss=0.2957, simple_loss=0.3528, pruned_loss=0.1195, over 1428530.21 frames.], batch size: 37, lr: 2.25e-03
+2022-04-28 09:24:00,481 INFO [train.py:763] (6/8) Epoch 1, batch 2700, loss[loss=0.3439, simple_loss=0.3813, pruned_loss=0.1533, over 6781.00 frames.], tot_loss[loss=0.2921, simple_loss=0.3498, pruned_loss=0.1173, over 1427759.94 frames.], batch size: 31, lr: 2.24e-03
+2022-04-28 09:25:06,556 INFO [train.py:763] (6/8) Epoch 1, batch 2750, loss[loss=0.3372, simple_loss=0.3875, pruned_loss=0.1435, over 7274.00 frames.], tot_loss[loss=0.2927, simple_loss=0.3503, pruned_loss=0.1177, over 1423218.31 frames.], batch size: 24, lr: 2.24e-03
+2022-04-28 09:26:12,251 INFO [train.py:763] (6/8) Epoch 1, batch 2800, loss[loss=0.3362, simple_loss=0.3943, pruned_loss=0.1391, over 7208.00 frames.], tot_loss[loss=0.2918, simple_loss=0.3505, pruned_loss=0.1167, over 1425947.48 frames.], batch size: 23, lr: 2.23e-03
+2022-04-28 09:27:17,546 INFO [train.py:763] (6/8) Epoch 1, batch 2850, loss[loss=0.2835, simple_loss=0.3506, pruned_loss=0.1082, over 7299.00 frames.], tot_loss[loss=0.2913, simple_loss=0.3502, pruned_loss=0.1163, over 1425804.86 frames.], batch size: 24, lr: 2.23e-03
+2022-04-28 09:28:22,522 INFO [train.py:763] (6/8) Epoch 1, batch 2900, loss[loss=0.3102, simple_loss=0.3797, pruned_loss=0.1203, over 7246.00 frames.], tot_loss[loss=0.2939, simple_loss=0.3525, pruned_loss=0.1177, over 1420964.47 frames.], batch size: 20, lr: 2.22e-03
+2022-04-28 09:29:27,937 INFO [train.py:763] (6/8) Epoch 1, batch 2950, loss[loss=0.3002, simple_loss=0.3598, pruned_loss=0.1203, over 7241.00 frames.], tot_loss[loss=0.2935, simple_loss=0.3524, pruned_loss=0.1173, over 1422225.32 frames.], batch size: 20, lr: 2.22e-03
+2022-04-28 09:30:33,554 INFO [train.py:763] (6/8) Epoch 1, batch 3000, loss[loss=0.2472, simple_loss=0.3053, pruned_loss=0.09454, over 7289.00 frames.], tot_loss[loss=0.2924, simple_loss=0.3515, pruned_loss=0.1167, over 1425305.87 frames.], batch size: 17, lr: 2.21e-03
+2022-04-28 09:30:33,555 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-28 09:30:49,512 INFO [train.py:792] (6/8) Epoch 1, validation: loss=0.217, simple_loss=0.3099, pruned_loss=0.06207, over 698248.00 frames.
+2022-04-28 09:31:55,884 INFO [train.py:763] (6/8) Epoch 1, batch 3050, loss[loss=0.2621, simple_loss=0.3159, pruned_loss=0.1042, over 7283.00 frames.], tot_loss[loss=0.2913, simple_loss=0.3506, pruned_loss=0.116, over 1421561.40 frames.], batch size: 18, lr: 2.20e-03
+2022-04-28 09:33:01,969 INFO [train.py:763] (6/8) Epoch 1, batch 3100, loss[loss=0.3519, simple_loss=0.386, pruned_loss=0.159, over 5167.00 frames.], tot_loss[loss=0.2922, simple_loss=0.3515, pruned_loss=0.1165, over 1421580.94 frames.], batch size: 52, lr: 2.20e-03
+2022-04-28 09:34:07,388 INFO [train.py:763] (6/8) Epoch 1, batch 3150, loss[loss=0.2851, simple_loss=0.3313, pruned_loss=0.1194, over 6785.00 frames.], tot_loss[loss=0.2906, simple_loss=0.3507, pruned_loss=0.1152, over 1423600.41 frames.], batch size: 15, lr: 2.19e-03
+2022-04-28 09:35:13,548 INFO [train.py:763] (6/8) Epoch 1, batch 3200, loss[loss=0.348, simple_loss=0.3867, pruned_loss=0.1546, over 5025.00 frames.], tot_loss[loss=0.2918, simple_loss=0.3517, pruned_loss=0.1159, over 1413087.32 frames.], batch size: 52, lr: 2.19e-03
+2022-04-28 09:36:19,398 INFO [train.py:763] (6/8) Epoch 1, batch 3250, loss[loss=0.3337, simple_loss=0.3869, pruned_loss=0.1403, over 7196.00 frames.], tot_loss[loss=0.2913, simple_loss=0.3517, pruned_loss=0.1155, over 1416020.91 frames.], batch size: 23, lr: 2.18e-03
+2022-04-28 09:37:26,023 INFO [train.py:763] (6/8) Epoch 1, batch 3300, loss[loss=0.273, simple_loss=0.3426, pruned_loss=0.1017, over 7198.00 frames.], tot_loss[loss=0.2895, simple_loss=0.3501, pruned_loss=0.1145, over 1421231.48 frames.], batch size: 22, lr: 2.18e-03
+2022-04-28 09:38:31,144 INFO [train.py:763] (6/8) Epoch 1, batch 3350, loss[loss=0.3172, simple_loss=0.3833, pruned_loss=0.1256, over 7211.00 frames.], tot_loss[loss=0.2902, simple_loss=0.3511, pruned_loss=0.1146, over 1423926.24 frames.], batch size: 26, lr: 2.18e-03
+2022-04-28 09:39:36,460 INFO [train.py:763] (6/8) Epoch 1, batch 3400, loss[loss=0.2824, simple_loss=0.3406, pruned_loss=0.1121, over 7116.00 frames.], tot_loss[loss=0.2892, simple_loss=0.3502, pruned_loss=0.1141, over 1425704.00 frames.], batch size: 17, lr: 2.17e-03
+2022-04-28 09:40:52,331 INFO [train.py:763] (6/8) Epoch 1, batch 3450, loss[loss=0.306, simple_loss=0.368, pruned_loss=0.122, over 7298.00 frames.], tot_loss[loss=0.2885, simple_loss=0.3501, pruned_loss=0.1135, over 1427769.04 frames.], batch size: 24, lr: 2.17e-03
+2022-04-28 09:41:59,072 INFO [train.py:763] (6/8) Epoch 1, batch 3500, loss[loss=0.3618, simple_loss=0.3831, pruned_loss=0.1702, over 6402.00 frames.], tot_loss[loss=0.2895, simple_loss=0.3504, pruned_loss=0.1143, over 1424803.14 frames.], batch size: 38, lr: 2.16e-03
+2022-04-28 09:43:05,806 INFO [train.py:763] (6/8) Epoch 1, batch 3550, loss[loss=0.264, simple_loss=0.3409, pruned_loss=0.09354, over 7315.00 frames.], tot_loss[loss=0.289, simple_loss=0.3497, pruned_loss=0.1141, over 1424593.48 frames.], batch size: 25, lr: 2.16e-03
+2022-04-28 09:44:12,974 INFO [train.py:763] (6/8) Epoch 1, batch 3600, loss[loss=0.2989, simple_loss=0.3619, pruned_loss=0.118, over 7234.00 frames.], tot_loss[loss=0.2893, simple_loss=0.3505, pruned_loss=0.1141, over 1425590.75 frames.], batch size: 20, lr: 2.15e-03
+2022-04-28 09:45:20,593 INFO [train.py:763] (6/8) Epoch 1, batch 3650, loss[loss=0.2669, simple_loss=0.3358, pruned_loss=0.09903, over 7230.00 frames.], tot_loss[loss=0.29, simple_loss=0.3509, pruned_loss=0.1146, over 1427354.35 frames.], batch size: 16, lr: 2.15e-03
+2022-04-28 09:46:27,979 INFO [train.py:763] (6/8) Epoch 1, batch 3700, loss[loss=0.2778, simple_loss=0.3463, pruned_loss=0.1047, over 7161.00 frames.], tot_loss[loss=0.2903, simple_loss=0.3515, pruned_loss=0.1145, over 1428975.40 frames.], batch size: 19, lr: 2.14e-03
+2022-04-28 09:47:33,416 INFO [train.py:763] (6/8) Epoch 1, batch 3750, loss[loss=0.3009, simple_loss=0.3708, pruned_loss=0.1155, over 7272.00 frames.], tot_loss[loss=0.2898, simple_loss=0.3515, pruned_loss=0.1141, over 1430211.10 frames.], batch size: 24, lr: 2.14e-03
+2022-04-28 09:48:38,890 INFO [train.py:763] (6/8) Epoch 1, batch 3800, loss[loss=0.2546, simple_loss=0.312, pruned_loss=0.09859, over 6797.00 frames.], tot_loss[loss=0.2882, simple_loss=0.3501, pruned_loss=0.1132, over 1429995.49 frames.], batch size: 15, lr: 2.13e-03
+2022-04-28 09:49:44,147 INFO [train.py:763] (6/8) Epoch 1, batch 3850, loss[loss=0.3846, simple_loss=0.419, pruned_loss=0.1751, over 7118.00 frames.], tot_loss[loss=0.2893, simple_loss=0.3513, pruned_loss=0.1136, over 1430993.18 frames.], batch size: 26, lr: 2.13e-03
+2022-04-28 09:50:49,546 INFO [train.py:763] (6/8) Epoch 1, batch 3900, loss[loss=0.3087, simple_loss=0.3749, pruned_loss=0.1212, over 7293.00 frames.], tot_loss[loss=0.2869, simple_loss=0.3497, pruned_loss=0.1121, over 1429986.37 frames.], batch size: 24, lr: 2.12e-03
+2022-04-28 09:51:55,500 INFO [train.py:763] (6/8) Epoch 1, batch 3950, loss[loss=0.267, simple_loss=0.3335, pruned_loss=0.1003, over 7108.00 frames.], tot_loss[loss=0.2852, simple_loss=0.3478, pruned_loss=0.1113, over 1428460.37 frames.], batch size: 21, lr: 2.12e-03
+2022-04-28 09:53:01,282 INFO [train.py:763] (6/8) Epoch 1, batch 4000, loss[loss=0.2619, simple_loss=0.3502, pruned_loss=0.08685, over 7210.00 frames.], tot_loss[loss=0.2843, simple_loss=0.3473, pruned_loss=0.1106, over 1428730.16 frames.], batch size: 22, lr: 2.11e-03
+2022-04-28 09:54:07,051 INFO [train.py:763] (6/8) Epoch 1, batch 4050, loss[loss=0.3235, simple_loss=0.378, pruned_loss=0.1345, over 6678.00 frames.], tot_loss[loss=0.2845, simple_loss=0.3476, pruned_loss=0.1107, over 1426758.81 frames.], batch size: 31, lr: 2.11e-03
+2022-04-28 09:55:12,318 INFO [train.py:763] (6/8) Epoch 1, batch 4100, loss[loss=0.2665, simple_loss=0.3445, pruned_loss=0.09421, over 7222.00 frames.], tot_loss[loss=0.2839, simple_loss=0.3475, pruned_loss=0.1101, over 1420880.32 frames.], batch size: 21, lr: 2.10e-03
+2022-04-28 09:56:17,394 INFO [train.py:763] (6/8) Epoch 1, batch 4150, loss[loss=0.3233, simple_loss=0.3774, pruned_loss=0.1346, over 6774.00 frames.], tot_loss[loss=0.2826, simple_loss=0.3465, pruned_loss=0.1094, over 1420368.40 frames.], batch size: 31, lr: 2.10e-03
+2022-04-28 09:57:22,846 INFO [train.py:763] (6/8) Epoch 1, batch 4200, loss[loss=0.2481, simple_loss=0.3158, pruned_loss=0.09019, over 7288.00 frames.], tot_loss[loss=0.2821, simple_loss=0.3458, pruned_loss=0.1092, over 1419506.74 frames.], batch size: 18, lr: 2.10e-03
+2022-04-28 09:58:27,893 INFO [train.py:763] (6/8) Epoch 1, batch 4250, loss[loss=0.2181, simple_loss=0.2879, pruned_loss=0.07417, over 7274.00 frames.], tot_loss[loss=0.2843, simple_loss=0.3473, pruned_loss=0.1107, over 1414607.66 frames.], batch size: 18, lr: 2.09e-03
+2022-04-28 09:59:34,355 INFO [train.py:763] (6/8) Epoch 1, batch 4300, loss[loss=0.3086, simple_loss=0.3676, pruned_loss=0.1248, over 7323.00 frames.], tot_loss[loss=0.2836, simple_loss=0.3469, pruned_loss=0.1101, over 1413059.00 frames.], batch size: 25, lr: 2.09e-03
+2022-04-28 10:00:39,972 INFO [train.py:763] (6/8) Epoch 1, batch 4350, loss[loss=0.2332, simple_loss=0.2948, pruned_loss=0.08582, over 6994.00 frames.], tot_loss[loss=0.2834, simple_loss=0.3467, pruned_loss=0.11, over 1413662.38 frames.], batch size: 16, lr: 2.08e-03
+2022-04-28 10:01:45,337 INFO [train.py:763] (6/8) Epoch 1, batch 4400, loss[loss=0.286, simple_loss=0.3503, pruned_loss=0.1109, over 7318.00 frames.], tot_loss[loss=0.284, simple_loss=0.3473, pruned_loss=0.1103, over 1407996.78 frames.], batch size: 21, lr: 2.08e-03
+2022-04-28 10:02:50,268 INFO [train.py:763] (6/8) Epoch 1, batch 4450, loss[loss=0.3648, simple_loss=0.4067, pruned_loss=0.1614, over 6372.00 frames.], tot_loss[loss=0.2857, simple_loss=0.3486, pruned_loss=0.1114, over 1400148.97 frames.], batch size: 38, lr: 2.07e-03
+2022-04-28 10:03:55,337 INFO [train.py:763] (6/8) Epoch 1, batch 4500, loss[loss=0.3073, simple_loss=0.3684, pruned_loss=0.1231, over 6212.00 frames.], tot_loss[loss=0.2846, simple_loss=0.3474, pruned_loss=0.1109, over 1385893.14 frames.], batch size: 37, lr: 2.07e-03
+2022-04-28 10:04:59,436 INFO [train.py:763] (6/8) Epoch 1, batch 4550, loss[loss=0.3542, simple_loss=0.394, pruned_loss=0.1572, over 5092.00 frames.], tot_loss[loss=0.2896, simple_loss=0.3508, pruned_loss=0.1142, over 1354056.21 frames.], batch size: 52, lr: 2.06e-03
+2022-04-28 10:06:27,052 INFO [train.py:763] (6/8) Epoch 2, batch 0, loss[loss=0.2757, simple_loss=0.3224, pruned_loss=0.1145, over 7280.00 frames.], tot_loss[loss=0.2757, simple_loss=0.3224, pruned_loss=0.1145, over 7280.00 frames.], batch size: 17, lr: 2.02e-03
+2022-04-28 10:07:33,521 INFO [train.py:763] (6/8) Epoch 2, batch 50, loss[loss=0.2804, simple_loss=0.3495, pruned_loss=0.1057, over 7283.00 frames.], tot_loss[loss=0.2874, simple_loss=0.3499, pruned_loss=0.1125, over 321241.17 frames.], batch size: 25, lr: 2.02e-03
+2022-04-28 10:08:39,204 INFO [train.py:763] (6/8) Epoch 2, batch 100, loss[loss=0.2724, simple_loss=0.3225, pruned_loss=0.1111, over 6998.00 frames.], tot_loss[loss=0.2813, simple_loss=0.3469, pruned_loss=0.1079, over 568512.86 frames.], batch size: 16, lr: 2.01e-03
+2022-04-28 10:09:45,125 INFO [train.py:763] (6/8) Epoch 2, batch 150, loss[loss=0.3489, simple_loss=0.4094, pruned_loss=0.1442, over 6826.00 frames.], tot_loss[loss=0.2756, simple_loss=0.3419, pruned_loss=0.1047, over 761177.59 frames.], batch size: 31, lr: 2.01e-03
+2022-04-28 10:10:50,700 INFO [train.py:763] (6/8) Epoch 2, batch 200, loss[loss=0.2109, simple_loss=0.2793, pruned_loss=0.07122, over 6849.00 frames.], tot_loss[loss=0.2753, simple_loss=0.341, pruned_loss=0.1048, over 900879.98 frames.], batch size: 15, lr: 2.00e-03
+2022-04-28 10:11:56,043 INFO [train.py:763] (6/8) Epoch 2, batch 250, loss[loss=0.294, simple_loss=0.3547, pruned_loss=0.1167, over 7359.00 frames.], tot_loss[loss=0.2757, simple_loss=0.3417, pruned_loss=0.1049, over 1011191.07 frames.], batch size: 19, lr: 2.00e-03
+2022-04-28 10:13:01,578 INFO [train.py:763] (6/8) Epoch 2, batch 300, loss[loss=0.2954, simple_loss=0.3742, pruned_loss=0.1083, over 6745.00 frames.], tot_loss[loss=0.277, simple_loss=0.3432, pruned_loss=0.1054, over 1101417.44 frames.], batch size: 31, lr: 2.00e-03
+2022-04-28 10:14:07,066 INFO [train.py:763] (6/8) Epoch 2, batch 350, loss[loss=0.2256, simple_loss=0.3161, pruned_loss=0.06751, over 7324.00 frames.], tot_loss[loss=0.277, simple_loss=0.3437, pruned_loss=0.1051, over 1172001.70 frames.], batch size: 21, lr: 1.99e-03
+2022-04-28 10:15:12,739 INFO [train.py:763] (6/8) Epoch 2, batch 400, loss[loss=0.2926, simple_loss=0.3542, pruned_loss=0.1155, over 7282.00 frames.], tot_loss[loss=0.2791, simple_loss=0.3449, pruned_loss=0.1067, over 1224064.91 frames.], batch size: 24, lr: 1.99e-03
+2022-04-28 10:16:17,708 INFO [train.py:763] (6/8) Epoch 2, batch 450, loss[loss=0.2731, simple_loss=0.3458, pruned_loss=0.1003, over 7205.00 frames.], tot_loss[loss=0.2802, simple_loss=0.3465, pruned_loss=0.107, over 1263835.46 frames.], batch size: 22, lr: 1.98e-03
+2022-04-28 10:17:41,020 INFO [train.py:763] (6/8) Epoch 2, batch 500, loss[loss=0.2747, simple_loss=0.335, pruned_loss=0.1072, over 7012.00 frames.], tot_loss[loss=0.2789, simple_loss=0.3456, pruned_loss=0.1061, over 1302332.95 frames.], batch size: 16, lr: 1.98e-03
+2022-04-28 10:19:24,495 INFO [train.py:763] (6/8) Epoch 2, batch 550, loss[loss=0.2363, simple_loss=0.3417, pruned_loss=0.06547, over 7224.00 frames.], tot_loss[loss=0.2768, simple_loss=0.3444, pruned_loss=0.1046, over 1331955.28 frames.], batch size: 21, lr: 1.98e-03
+2022-04-28 10:20:31,156 INFO [train.py:763] (6/8) Epoch 2, batch 600, loss[loss=0.3865, simple_loss=0.4372, pruned_loss=0.1679, over 7291.00 frames.], tot_loss[loss=0.2757, simple_loss=0.3434, pruned_loss=0.104, over 1353345.83 frames.], batch size: 25, lr: 1.97e-03
+2022-04-28 10:21:56,820 INFO [train.py:763] (6/8) Epoch 2, batch 650, loss[loss=0.2353, simple_loss=0.3182, pruned_loss=0.07618, over 7353.00 frames.], tot_loss[loss=0.2753, simple_loss=0.3432, pruned_loss=0.1037, over 1367251.10 frames.], batch size: 19, lr: 1.97e-03
+2022-04-28 10:23:03,993 INFO [train.py:763] (6/8) Epoch 2, batch 700, loss[loss=0.2449, simple_loss=0.336, pruned_loss=0.0769, over 7211.00 frames.], tot_loss[loss=0.2746, simple_loss=0.3425, pruned_loss=0.1033, over 1377529.58 frames.], batch size: 21, lr: 1.96e-03
+2022-04-28 10:24:09,350 INFO [train.py:763] (6/8) Epoch 2, batch 750, loss[loss=0.2649, simple_loss=0.3412, pruned_loss=0.09427, over 7208.00 frames.], tot_loss[loss=0.2756, simple_loss=0.3434, pruned_loss=0.1039, over 1391142.13 frames.], batch size: 23, lr: 1.96e-03
+2022-04-28 10:25:14,625 INFO [train.py:763] (6/8) Epoch 2, batch 800, loss[loss=0.3379, simple_loss=0.3945, pruned_loss=0.1406, over 7211.00 frames.], tot_loss[loss=0.2763, simple_loss=0.344, pruned_loss=0.1042, over 1401989.90 frames.], batch size: 23, lr: 1.96e-03
+2022-04-28 10:26:20,183 INFO [train.py:763] (6/8) Epoch 2, batch 850, loss[loss=0.341, simple_loss=0.3959, pruned_loss=0.1431, over 7304.00 frames.], tot_loss[loss=0.2749, simple_loss=0.3428, pruned_loss=0.1035, over 1409668.86 frames.], batch size: 25, lr: 1.95e-03
+2022-04-28 10:27:26,282 INFO [train.py:763] (6/8) Epoch 2, batch 900, loss[loss=0.2574, simple_loss=0.3389, pruned_loss=0.08795, over 7056.00 frames.], tot_loss[loss=0.276, simple_loss=0.3439, pruned_loss=0.104, over 1412331.11 frames.], batch size: 18, lr: 1.95e-03
+2022-04-28 10:28:31,602 INFO [train.py:763] (6/8) Epoch 2, batch 950, loss[loss=0.2622, simple_loss=0.3446, pruned_loss=0.08994, over 7144.00 frames.], tot_loss[loss=0.2748, simple_loss=0.3434, pruned_loss=0.1031, over 1417210.20 frames.], batch size: 20, lr: 1.94e-03
+2022-04-28 10:29:36,673 INFO [train.py:763] (6/8) Epoch 2, batch 1000, loss[loss=0.2608, simple_loss=0.3402, pruned_loss=0.09072, over 6731.00 frames.], tot_loss[loss=0.2763, simple_loss=0.3446, pruned_loss=0.104, over 1416915.62 frames.], batch size: 31, lr: 1.94e-03
+2022-04-28 10:30:41,996 INFO [train.py:763] (6/8) Epoch 2, batch 1050, loss[loss=0.1999, simple_loss=0.2789, pruned_loss=0.06047, over 7284.00 frames.], tot_loss[loss=0.2753, simple_loss=0.344, pruned_loss=0.1033, over 1414255.61 frames.], batch size: 18, lr: 1.94e-03
+2022-04-28 10:31:48,326 INFO [train.py:763] (6/8) Epoch 2, batch 1100, loss[loss=0.2552, simple_loss=0.3416, pruned_loss=0.08436, over 7221.00 frames.], tot_loss[loss=0.276, simple_loss=0.345, pruned_loss=0.1035, over 1419263.44 frames.], batch size: 21, lr: 1.93e-03
+2022-04-28 10:32:55,820 INFO [train.py:763] (6/8) Epoch 2, batch 1150, loss[loss=0.2839, simple_loss=0.336, pruned_loss=0.1159, over 7227.00 frames.], tot_loss[loss=0.2736, simple_loss=0.3425, pruned_loss=0.1024, over 1421243.29 frames.], batch size: 20, lr: 1.93e-03
+2022-04-28 10:34:03,565 INFO [train.py:763] (6/8) Epoch 2, batch 1200, loss[loss=0.2577, simple_loss=0.3312, pruned_loss=0.09212, over 7416.00 frames.], tot_loss[loss=0.2726, simple_loss=0.3417, pruned_loss=0.1018, over 1424224.86 frames.], batch size: 20, lr: 1.93e-03
+2022-04-28 10:35:11,227 INFO [train.py:763] (6/8) Epoch 2, batch 1250, loss[loss=0.3025, simple_loss=0.3554, pruned_loss=0.1248, over 7411.00 frames.], tot_loss[loss=0.2733, simple_loss=0.3415, pruned_loss=0.1025, over 1424684.90 frames.], batch size: 21, lr: 1.92e-03
+2022-04-28 10:36:17,316 INFO [train.py:763] (6/8) Epoch 2, batch 1300, loss[loss=0.2624, simple_loss=0.3378, pruned_loss=0.09347, over 7304.00 frames.], tot_loss[loss=0.2713, simple_loss=0.3402, pruned_loss=0.1012, over 1426500.69 frames.], batch size: 21, lr: 1.92e-03
+2022-04-28 10:37:22,341 INFO [train.py:763] (6/8) Epoch 2, batch 1350, loss[loss=0.2625, simple_loss=0.3308, pruned_loss=0.09713, over 7431.00 frames.], tot_loss[loss=0.2726, simple_loss=0.3416, pruned_loss=0.1019, over 1426428.70 frames.], batch size: 20, lr: 1.91e-03
+2022-04-28 10:38:27,404 INFO [train.py:763] (6/8) Epoch 2, batch 1400, loss[loss=0.2371, simple_loss=0.3129, pruned_loss=0.08067, over 7158.00 frames.], tot_loss[loss=0.2725, simple_loss=0.3416, pruned_loss=0.1017, over 1423768.86 frames.], batch size: 19, lr: 1.91e-03
+2022-04-28 10:39:32,823 INFO [train.py:763] (6/8) Epoch 2, batch 1450, loss[loss=0.2126, simple_loss=0.2878, pruned_loss=0.06872, over 7130.00 frames.], tot_loss[loss=0.2707, simple_loss=0.3401, pruned_loss=0.1006, over 1420767.87 frames.], batch size: 17, lr: 1.91e-03
+2022-04-28 10:40:38,391 INFO [train.py:763] (6/8) Epoch 2, batch 1500, loss[loss=0.2368, simple_loss=0.3281, pruned_loss=0.07276, over 7308.00 frames.], tot_loss[loss=0.2705, simple_loss=0.34, pruned_loss=0.1005, over 1419016.41 frames.], batch size: 21, lr: 1.90e-03
+2022-04-28 10:41:43,974 INFO [train.py:763] (6/8) Epoch 2, batch 1550, loss[loss=0.259, simple_loss=0.3368, pruned_loss=0.09064, over 7156.00 frames.], tot_loss[loss=0.2718, simple_loss=0.3409, pruned_loss=0.1014, over 1422990.63 frames.], batch size: 19, lr: 1.90e-03
+2022-04-28 10:42:49,543 INFO [train.py:763] (6/8) Epoch 2, batch 1600, loss[loss=0.2666, simple_loss=0.3337, pruned_loss=0.09976, over 7171.00 frames.], tot_loss[loss=0.2714, simple_loss=0.3405, pruned_loss=0.1012, over 1424568.16 frames.], batch size: 19, lr: 1.90e-03
+2022-04-28 10:43:56,348 INFO [train.py:763] (6/8) Epoch 2, batch 1650, loss[loss=0.2687, simple_loss=0.3456, pruned_loss=0.09593, over 7431.00 frames.], tot_loss[loss=0.2712, simple_loss=0.3403, pruned_loss=0.101, over 1426669.31 frames.], batch size: 20, lr: 1.89e-03
+2022-04-28 10:45:02,827 INFO [train.py:763] (6/8) Epoch 2, batch 1700, loss[loss=0.2833, simple_loss=0.3505, pruned_loss=0.108, over 7147.00 frames.], tot_loss[loss=0.2721, simple_loss=0.341, pruned_loss=0.1016, over 1416635.30 frames.], batch size: 20, lr: 1.89e-03
+2022-04-28 10:46:08,595 INFO [train.py:763] (6/8) Epoch 2, batch 1750, loss[loss=0.2061, simple_loss=0.3125, pruned_loss=0.04982, over 7237.00 frames.], tot_loss[loss=0.2698, simple_loss=0.3397, pruned_loss=0.09996, over 1423991.52 frames.], batch size: 20, lr: 1.88e-03
+2022-04-28 10:47:13,956 INFO [train.py:763] (6/8) Epoch 2, batch 1800, loss[loss=0.2559, simple_loss=0.3407, pruned_loss=0.08552, over 7113.00 frames.], tot_loss[loss=0.2703, simple_loss=0.3402, pruned_loss=0.1002, over 1417072.68 frames.], batch size: 21, lr: 1.88e-03
+2022-04-28 10:48:20,974 INFO [train.py:763] (6/8) Epoch 2, batch 1850, loss[loss=0.2861, simple_loss=0.3575, pruned_loss=0.1074, over 7411.00 frames.], tot_loss[loss=0.2689, simple_loss=0.3388, pruned_loss=0.09948, over 1419950.24 frames.], batch size: 21, lr: 1.88e-03
+2022-04-28 10:49:26,581 INFO [train.py:763] (6/8) Epoch 2, batch 1900, loss[loss=0.2638, simple_loss=0.3312, pruned_loss=0.09826, over 7160.00 frames.], tot_loss[loss=0.2698, simple_loss=0.3389, pruned_loss=0.1003, over 1418154.49 frames.], batch size: 18, lr: 1.87e-03
+2022-04-28 10:50:31,924 INFO [train.py:763] (6/8) Epoch 2, batch 1950, loss[loss=0.2936, simple_loss=0.3599, pruned_loss=0.1136, over 6870.00 frames.], tot_loss[loss=0.2687, simple_loss=0.3381, pruned_loss=0.09962, over 1419585.78 frames.], batch size: 31, lr: 1.87e-03
+2022-04-28 10:51:37,339 INFO [train.py:763] (6/8) Epoch 2, batch 2000, loss[loss=0.2515, simple_loss=0.3331, pruned_loss=0.08498, over 7147.00 frames.], tot_loss[loss=0.2675, simple_loss=0.3372, pruned_loss=0.09893, over 1424006.92 frames.], batch size: 19, lr: 1.87e-03
+2022-04-28 10:52:43,640 INFO [train.py:763] (6/8) Epoch 2, batch 2050, loss[loss=0.3441, simple_loss=0.3941, pruned_loss=0.147, over 4836.00 frames.], tot_loss[loss=0.2702, simple_loss=0.3397, pruned_loss=0.1003, over 1423370.45 frames.], batch size: 52, lr: 1.86e-03
+2022-04-28 10:53:49,752 INFO [train.py:763] (6/8) Epoch 2, batch 2100, loss[loss=0.2847, simple_loss=0.3615, pruned_loss=0.1039, over 7317.00 frames.], tot_loss[loss=0.2697, simple_loss=0.3397, pruned_loss=0.09984, over 1425916.31 frames.], batch size: 21, lr: 1.86e-03
+2022-04-28 10:54:55,194 INFO [train.py:763] (6/8) Epoch 2, batch 2150, loss[loss=0.2657, simple_loss=0.3388, pruned_loss=0.09628, over 7226.00 frames.], tot_loss[loss=0.2689, simple_loss=0.3392, pruned_loss=0.09933, over 1427328.02 frames.], batch size: 20, lr: 1.86e-03
+2022-04-28 10:56:00,717 INFO [train.py:763] (6/8) Epoch 2, batch 2200, loss[loss=0.258, simple_loss=0.337, pruned_loss=0.0895, over 7138.00 frames.], tot_loss[loss=0.2681, simple_loss=0.3382, pruned_loss=0.09902, over 1425602.81 frames.], batch size: 20, lr: 1.85e-03
+2022-04-28 10:57:05,940 INFO [train.py:763] (6/8) Epoch 2, batch 2250, loss[loss=0.2773, simple_loss=0.3516, pruned_loss=0.1015, over 7323.00 frames.], tot_loss[loss=0.2662, simple_loss=0.3371, pruned_loss=0.09768, over 1424972.37 frames.], batch size: 20, lr: 1.85e-03
+2022-04-28 10:58:11,386 INFO [train.py:763] (6/8) Epoch 2, batch 2300, loss[loss=0.2408, simple_loss=0.3118, pruned_loss=0.08489, over 7378.00 frames.], tot_loss[loss=0.2671, simple_loss=0.3373, pruned_loss=0.09845, over 1414088.82 frames.], batch size: 19, lr: 1.85e-03
+2022-04-28 10:59:16,568 INFO [train.py:763] (6/8) Epoch 2, batch 2350, loss[loss=0.3249, simple_loss=0.3606, pruned_loss=0.1446, over 7252.00 frames.], tot_loss[loss=0.2665, simple_loss=0.3368, pruned_loss=0.09813, over 1415637.77 frames.], batch size: 19, lr: 1.84e-03
+2022-04-28 11:00:21,742 INFO [train.py:763] (6/8) Epoch 2, batch 2400, loss[loss=0.2169, simple_loss=0.2967, pruned_loss=0.06852, over 7258.00 frames.], tot_loss[loss=0.266, simple_loss=0.3367, pruned_loss=0.09767, over 1418730.22 frames.], batch size: 19, lr: 1.84e-03
+2022-04-28 11:01:26,805 INFO [train.py:763] (6/8) Epoch 2, batch 2450, loss[loss=0.3359, simple_loss=0.3877, pruned_loss=0.1421, over 7237.00 frames.], tot_loss[loss=0.2664, simple_loss=0.3374, pruned_loss=0.09771, over 1416773.42 frames.], batch size: 20, lr: 1.84e-03
+2022-04-28 11:02:32,498 INFO [train.py:763] (6/8) Epoch 2, batch 2500, loss[loss=0.2713, simple_loss=0.3443, pruned_loss=0.09909, over 7152.00 frames.], tot_loss[loss=0.2673, simple_loss=0.3377, pruned_loss=0.09842, over 1414335.41 frames.], batch size: 19, lr: 1.83e-03
+2022-04-28 11:03:38,315 INFO [train.py:763] (6/8) Epoch 2, batch 2550, loss[loss=0.252, simple_loss=0.3255, pruned_loss=0.08924, over 7220.00 frames.], tot_loss[loss=0.2667, simple_loss=0.3368, pruned_loss=0.09834, over 1413970.50 frames.], batch size: 21, lr: 1.83e-03
+2022-04-28 11:04:44,223 INFO [train.py:763] (6/8) Epoch 2, batch 2600, loss[loss=0.2557, simple_loss=0.3333, pruned_loss=0.08901, over 7275.00 frames.], tot_loss[loss=0.2645, simple_loss=0.3355, pruned_loss=0.09677, over 1419922.67 frames.], batch size: 18, lr: 1.83e-03
+2022-04-28 11:05:50,141 INFO [train.py:763] (6/8) Epoch 2, batch 2650, loss[loss=0.2731, simple_loss=0.347, pruned_loss=0.09956, over 7319.00 frames.], tot_loss[loss=0.2637, simple_loss=0.335, pruned_loss=0.09618, over 1419642.00 frames.], batch size: 20, lr: 1.82e-03
+2022-04-28 11:06:55,498 INFO [train.py:763] (6/8) Epoch 2, batch 2700, loss[loss=0.2657, simple_loss=0.321, pruned_loss=0.1052, over 7062.00 frames.], tot_loss[loss=0.2642, simple_loss=0.3357, pruned_loss=0.09638, over 1420525.20 frames.], batch size: 18, lr: 1.82e-03
+2022-04-28 11:08:01,955 INFO [train.py:763] (6/8) Epoch 2, batch 2750, loss[loss=0.2785, simple_loss=0.3531, pruned_loss=0.102, over 7187.00 frames.], tot_loss[loss=0.2653, simple_loss=0.3365, pruned_loss=0.0971, over 1419320.98 frames.], batch size: 26, lr: 1.82e-03
+2022-04-28 11:09:07,552 INFO [train.py:763] (6/8) Epoch 2, batch 2800, loss[loss=0.3214, simple_loss=0.3677, pruned_loss=0.1376, over 5137.00 frames.], tot_loss[loss=0.264, simple_loss=0.3358, pruned_loss=0.09614, over 1419037.63 frames.], batch size: 52, lr: 1.81e-03
+2022-04-28 11:10:13,396 INFO [train.py:763] (6/8) Epoch 2, batch 2850, loss[loss=0.2301, simple_loss=0.3231, pruned_loss=0.0685, over 7210.00 frames.], tot_loss[loss=0.2616, simple_loss=0.334, pruned_loss=0.09463, over 1421091.80 frames.], batch size: 21, lr: 1.81e-03
+2022-04-28 11:11:19,196 INFO [train.py:763] (6/8) Epoch 2, batch 2900, loss[loss=0.2843, simple_loss=0.3469, pruned_loss=0.1109, over 6428.00 frames.], tot_loss[loss=0.2614, simple_loss=0.3338, pruned_loss=0.09453, over 1416954.72 frames.], batch size: 37, lr: 1.81e-03
+2022-04-28 11:12:24,871 INFO [train.py:763] (6/8) Epoch 2, batch 2950, loss[loss=0.2572, simple_loss=0.3439, pruned_loss=0.0853, over 7161.00 frames.], tot_loss[loss=0.2622, simple_loss=0.335, pruned_loss=0.0947, over 1416858.56 frames.], batch size: 26, lr: 1.80e-03
+2022-04-28 11:13:30,379 INFO [train.py:763] (6/8) Epoch 2, batch 3000, loss[loss=0.2421, simple_loss=0.3241, pruned_loss=0.0801, over 7329.00 frames.], tot_loss[loss=0.2624, simple_loss=0.3352, pruned_loss=0.09478, over 1419569.21 frames.], batch size: 22, lr: 1.80e-03
+2022-04-28 11:13:30,380 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-28 11:13:45,774 INFO [train.py:792] (6/8) Epoch 2, validation: loss=0.2017, simple_loss=0.3052, pruned_loss=0.04915, over 698248.00 frames.
+2022-04-28 11:14:51,527 INFO [train.py:763] (6/8) Epoch 2, batch 3050, loss[loss=0.2265, simple_loss=0.3115, pruned_loss=0.07075, over 7410.00 frames.], tot_loss[loss=0.2629, simple_loss=0.3356, pruned_loss=0.09514, over 1425140.77 frames.], batch size: 21, lr: 1.80e-03
+2022-04-28 11:15:57,117 INFO [train.py:763] (6/8) Epoch 2, batch 3100, loss[loss=0.2187, simple_loss=0.2865, pruned_loss=0.07547, over 7271.00 frames.], tot_loss[loss=0.2621, simple_loss=0.3346, pruned_loss=0.09478, over 1428572.45 frames.], batch size: 18, lr: 1.79e-03
+2022-04-28 11:17:02,759 INFO [train.py:763] (6/8) Epoch 2, batch 3150, loss[loss=0.3215, simple_loss=0.388, pruned_loss=0.1275, over 7212.00 frames.], tot_loss[loss=0.2609, simple_loss=0.3333, pruned_loss=0.09422, over 1422710.66 frames.], batch size: 21, lr: 1.79e-03
+2022-04-28 11:18:08,973 INFO [train.py:763] (6/8) Epoch 2, batch 3200, loss[loss=0.2835, simple_loss=0.3548, pruned_loss=0.1061, over 7370.00 frames.], tot_loss[loss=0.2632, simple_loss=0.336, pruned_loss=0.09525, over 1425789.19 frames.], batch size: 23, lr: 1.79e-03
+2022-04-28 11:19:14,937 INFO [train.py:763] (6/8) Epoch 2, batch 3250, loss[loss=0.2314, simple_loss=0.3113, pruned_loss=0.07577, over 7170.00 frames.], tot_loss[loss=0.2633, simple_loss=0.3361, pruned_loss=0.09528, over 1427470.30 frames.], batch size: 19, lr: 1.79e-03
+2022-04-28 11:20:20,954 INFO [train.py:763] (6/8) Epoch 2, batch 3300, loss[loss=0.301, simple_loss=0.3688, pruned_loss=0.1166, over 7136.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3357, pruned_loss=0.09486, over 1429594.03 frames.], batch size: 26, lr: 1.78e-03
+2022-04-28 11:21:25,810 INFO [train.py:763] (6/8) Epoch 2, batch 3350, loss[loss=0.2852, simple_loss=0.3552, pruned_loss=0.1076, over 7278.00 frames.], tot_loss[loss=0.264, simple_loss=0.3368, pruned_loss=0.09557, over 1426953.28 frames.], batch size: 18, lr: 1.78e-03
+2022-04-28 11:22:30,853 INFO [train.py:763] (6/8) Epoch 2, batch 3400, loss[loss=0.2195, simple_loss=0.2994, pruned_loss=0.06983, over 7394.00 frames.], tot_loss[loss=0.2641, simple_loss=0.3373, pruned_loss=0.0955, over 1424939.93 frames.], batch size: 18, lr: 1.78e-03
+2022-04-28 11:23:36,219 INFO [train.py:763] (6/8) Epoch 2, batch 3450, loss[loss=0.1863, simple_loss=0.2766, pruned_loss=0.04802, over 7256.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3356, pruned_loss=0.09489, over 1420890.05 frames.], batch size: 19, lr: 1.77e-03
+2022-04-28 11:24:41,581 INFO [train.py:763] (6/8) Epoch 2, batch 3500, loss[loss=0.3002, simple_loss=0.3757, pruned_loss=0.1123, over 7286.00 frames.], tot_loss[loss=0.2621, simple_loss=0.3348, pruned_loss=0.09467, over 1422136.85 frames.], batch size: 25, lr: 1.77e-03
+2022-04-28 11:25:47,027 INFO [train.py:763] (6/8) Epoch 2, batch 3550, loss[loss=0.2791, simple_loss=0.3544, pruned_loss=0.1019, over 7222.00 frames.], tot_loss[loss=0.2623, simple_loss=0.3351, pruned_loss=0.09478, over 1421060.81 frames.], batch size: 21, lr: 1.77e-03
+2022-04-28 11:26:52,371 INFO [train.py:763] (6/8) Epoch 2, batch 3600, loss[loss=0.2589, simple_loss=0.3273, pruned_loss=0.09524, over 7267.00 frames.], tot_loss[loss=0.2614, simple_loss=0.3339, pruned_loss=0.09446, over 1422069.17 frames.], batch size: 24, lr: 1.76e-03
+2022-04-28 11:27:57,956 INFO [train.py:763] (6/8) Epoch 2, batch 3650, loss[loss=0.2925, simple_loss=0.3603, pruned_loss=0.1123, over 7378.00 frames.], tot_loss[loss=0.2595, simple_loss=0.3325, pruned_loss=0.09328, over 1421945.10 frames.], batch size: 23, lr: 1.76e-03
+2022-04-28 11:29:03,181 INFO [train.py:763] (6/8) Epoch 2, batch 3700, loss[loss=0.2405, simple_loss=0.3083, pruned_loss=0.08638, over 7421.00 frames.], tot_loss[loss=0.2591, simple_loss=0.3322, pruned_loss=0.09296, over 1418496.12 frames.], batch size: 18, lr: 1.76e-03
+2022-04-28 11:30:08,701 INFO [train.py:763] (6/8) Epoch 2, batch 3750, loss[loss=0.2412, simple_loss=0.3105, pruned_loss=0.08599, over 7286.00 frames.], tot_loss[loss=0.257, simple_loss=0.3307, pruned_loss=0.09161, over 1424116.89 frames.], batch size: 18, lr: 1.76e-03
+2022-04-28 11:31:14,666 INFO [train.py:763] (6/8) Epoch 2, batch 3800, loss[loss=0.2676, simple_loss=0.3375, pruned_loss=0.09889, over 7169.00 frames.], tot_loss[loss=0.2572, simple_loss=0.3308, pruned_loss=0.09179, over 1424393.34 frames.], batch size: 18, lr: 1.75e-03
+2022-04-28 11:32:20,653 INFO [train.py:763] (6/8) Epoch 2, batch 3850, loss[loss=0.2789, simple_loss=0.3528, pruned_loss=0.1025, over 7340.00 frames.], tot_loss[loss=0.2583, simple_loss=0.3313, pruned_loss=0.09265, over 1422974.53 frames.], batch size: 22, lr: 1.75e-03
+2022-04-28 11:33:26,579 INFO [train.py:763] (6/8) Epoch 2, batch 3900, loss[loss=0.2398, simple_loss=0.3304, pruned_loss=0.07458, over 7326.00 frames.], tot_loss[loss=0.2583, simple_loss=0.3316, pruned_loss=0.09245, over 1424687.83 frames.], batch size: 20, lr: 1.75e-03
+2022-04-28 11:34:31,996 INFO [train.py:763] (6/8) Epoch 2, batch 3950, loss[loss=0.2552, simple_loss=0.3309, pruned_loss=0.08976, over 7321.00 frames.], tot_loss[loss=0.2577, simple_loss=0.3314, pruned_loss=0.09203, over 1421605.29 frames.], batch size: 21, lr: 1.74e-03
+2022-04-28 11:35:37,606 INFO [train.py:763] (6/8) Epoch 2, batch 4000, loss[loss=0.2775, simple_loss=0.3452, pruned_loss=0.1048, over 7340.00 frames.], tot_loss[loss=0.2583, simple_loss=0.3318, pruned_loss=0.09241, over 1426086.29 frames.], batch size: 22, lr: 1.74e-03
+2022-04-28 11:36:44,081 INFO [train.py:763] (6/8) Epoch 2, batch 4050, loss[loss=0.3397, simple_loss=0.3962, pruned_loss=0.1416, over 7450.00 frames.], tot_loss[loss=0.2579, simple_loss=0.3313, pruned_loss=0.09225, over 1426354.90 frames.], batch size: 20, lr: 1.74e-03
+2022-04-28 11:37:49,244 INFO [train.py:763] (6/8) Epoch 2, batch 4100, loss[loss=0.2455, simple_loss=0.317, pruned_loss=0.087, over 7069.00 frames.], tot_loss[loss=0.2593, simple_loss=0.3325, pruned_loss=0.09302, over 1416568.31 frames.], batch size: 18, lr: 1.73e-03
+2022-04-28 11:38:54,190 INFO [train.py:763] (6/8) Epoch 2, batch 4150, loss[loss=0.2307, simple_loss=0.3203, pruned_loss=0.07058, over 7103.00 frames.], tot_loss[loss=0.2588, simple_loss=0.3326, pruned_loss=0.09256, over 1420944.00 frames.], batch size: 21, lr: 1.73e-03
+2022-04-28 11:40:00,867 INFO [train.py:763] (6/8) Epoch 2, batch 4200, loss[loss=0.3344, simple_loss=0.399, pruned_loss=0.1349, over 7036.00 frames.], tot_loss[loss=0.2587, simple_loss=0.3321, pruned_loss=0.09269, over 1421892.04 frames.], batch size: 28, lr: 1.73e-03
+2022-04-28 11:41:07,992 INFO [train.py:763] (6/8) Epoch 2, batch 4250, loss[loss=0.2758, simple_loss=0.3586, pruned_loss=0.09647, over 7194.00 frames.], tot_loss[loss=0.2573, simple_loss=0.331, pruned_loss=0.0918, over 1421926.21 frames.], batch size: 22, lr: 1.73e-03
+2022-04-28 11:42:14,759 INFO [train.py:763] (6/8) Epoch 2, batch 4300, loss[loss=0.2002, simple_loss=0.2854, pruned_loss=0.05748, over 7452.00 frames.], tot_loss[loss=0.2572, simple_loss=0.3315, pruned_loss=0.09147, over 1424636.35 frames.], batch size: 19, lr: 1.72e-03
+2022-04-28 11:43:21,902 INFO [train.py:763] (6/8) Epoch 2, batch 4350, loss[loss=0.2576, simple_loss=0.3386, pruned_loss=0.08832, over 7141.00 frames.], tot_loss[loss=0.2558, simple_loss=0.3303, pruned_loss=0.09068, over 1425492.93 frames.], batch size: 20, lr: 1.72e-03
+2022-04-28 11:44:27,746 INFO [train.py:763] (6/8) Epoch 2, batch 4400, loss[loss=0.2754, simple_loss=0.3535, pruned_loss=0.09863, over 7327.00 frames.], tot_loss[loss=0.2565, simple_loss=0.3307, pruned_loss=0.09117, over 1419742.06 frames.], batch size: 25, lr: 1.72e-03
+2022-04-28 11:45:33,251 INFO [train.py:763] (6/8) Epoch 2, batch 4450, loss[loss=0.262, simple_loss=0.3488, pruned_loss=0.08762, over 7338.00 frames.], tot_loss[loss=0.2591, simple_loss=0.3331, pruned_loss=0.09257, over 1412366.19 frames.], batch size: 22, lr: 1.71e-03
+2022-04-28 11:46:38,448 INFO [train.py:763] (6/8) Epoch 2, batch 4500, loss[loss=0.2387, simple_loss=0.3276, pruned_loss=0.0749, over 7123.00 frames.], tot_loss[loss=0.2595, simple_loss=0.3333, pruned_loss=0.09282, over 1406390.03 frames.], batch size: 21, lr: 1.71e-03
+2022-04-28 11:47:42,634 INFO [train.py:763] (6/8) Epoch 2, batch 4550, loss[loss=0.2639, simple_loss=0.342, pruned_loss=0.0929, over 6194.00 frames.], tot_loss[loss=0.2632, simple_loss=0.3365, pruned_loss=0.09502, over 1378210.46 frames.], batch size: 37, lr: 1.71e-03
+2022-04-28 11:49:10,865 INFO [train.py:763] (6/8) Epoch 3, batch 0, loss[loss=0.2639, simple_loss=0.3436, pruned_loss=0.09215, over 7191.00 frames.], tot_loss[loss=0.2639, simple_loss=0.3436, pruned_loss=0.09215, over 7191.00 frames.], batch size: 23, lr: 1.66e-03
+2022-04-28 11:50:17,406 INFO [train.py:763] (6/8) Epoch 3, batch 50, loss[loss=0.2112, simple_loss=0.2961, pruned_loss=0.06311, over 7276.00 frames.], tot_loss[loss=0.2565, simple_loss=0.3297, pruned_loss=0.09163, over 317596.52 frames.], batch size: 17, lr: 1.66e-03
+2022-04-28 11:51:23,922 INFO [train.py:763] (6/8) Epoch 3, batch 100, loss[loss=0.2367, simple_loss=0.3029, pruned_loss=0.08526, over 7261.00 frames.], tot_loss[loss=0.2497, simple_loss=0.3249, pruned_loss=0.0872, over 564523.47 frames.], batch size: 17, lr: 1.65e-03
+2022-04-28 11:52:29,497 INFO [train.py:763] (6/8) Epoch 3, batch 150, loss[loss=0.2639, simple_loss=0.3435, pruned_loss=0.09213, over 7325.00 frames.], tot_loss[loss=0.2491, simple_loss=0.3246, pruned_loss=0.08682, over 755216.76 frames.], batch size: 22, lr: 1.65e-03
+2022-04-28 11:53:34,976 INFO [train.py:763] (6/8) Epoch 3, batch 200, loss[loss=0.2695, simple_loss=0.3436, pruned_loss=0.09766, over 7209.00 frames.], tot_loss[loss=0.2492, simple_loss=0.326, pruned_loss=0.08622, over 904108.32 frames.], batch size: 23, lr: 1.65e-03
+2022-04-28 11:54:40,984 INFO [train.py:763] (6/8) Epoch 3, batch 250, loss[loss=0.2215, simple_loss=0.3091, pruned_loss=0.06696, over 7346.00 frames.], tot_loss[loss=0.2503, simple_loss=0.3272, pruned_loss=0.08668, over 1016824.20 frames.], batch size: 22, lr: 1.64e-03
+2022-04-28 11:55:46,610 INFO [train.py:763] (6/8) Epoch 3, batch 300, loss[loss=0.257, simple_loss=0.3475, pruned_loss=0.08324, over 7355.00 frames.], tot_loss[loss=0.25, simple_loss=0.3272, pruned_loss=0.08642, over 1110847.99 frames.], batch size: 23, lr: 1.64e-03
+2022-04-28 11:56:52,029 INFO [train.py:763] (6/8) Epoch 3, batch 350, loss[loss=0.2465, simple_loss=0.3307, pruned_loss=0.08116, over 7322.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3274, pruned_loss=0.08683, over 1181820.52 frames.], batch size: 21, lr: 1.64e-03
+2022-04-28 11:57:57,850 INFO [train.py:763] (6/8) Epoch 3, batch 400, loss[loss=0.2407, simple_loss=0.3253, pruned_loss=0.07808, over 7233.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3269, pruned_loss=0.08729, over 1232865.18 frames.], batch size: 20, lr: 1.64e-03
+2022-04-28 11:59:03,271 INFO [train.py:763] (6/8) Epoch 3, batch 450, loss[loss=0.2884, simple_loss=0.3682, pruned_loss=0.1043, over 7148.00 frames.], tot_loss[loss=0.2496, simple_loss=0.3264, pruned_loss=0.08637, over 1274482.01 frames.], batch size: 20, lr: 1.63e-03
+2022-04-28 12:00:09,023 INFO [train.py:763] (6/8) Epoch 3, batch 500, loss[loss=0.2693, simple_loss=0.3402, pruned_loss=0.09915, over 7155.00 frames.], tot_loss[loss=0.253, simple_loss=0.3291, pruned_loss=0.0884, over 1303506.58 frames.], batch size: 19, lr: 1.63e-03
+2022-04-28 12:01:14,928 INFO [train.py:763] (6/8) Epoch 3, batch 550, loss[loss=0.2513, simple_loss=0.3235, pruned_loss=0.08955, over 7148.00 frames.], tot_loss[loss=0.2533, simple_loss=0.329, pruned_loss=0.08876, over 1329080.07 frames.], batch size: 18, lr: 1.63e-03
+2022-04-28 12:02:20,845 INFO [train.py:763] (6/8) Epoch 3, batch 600, loss[loss=0.3217, simple_loss=0.3765, pruned_loss=0.1335, over 6359.00 frames.], tot_loss[loss=0.2522, simple_loss=0.3278, pruned_loss=0.08826, over 1346635.96 frames.], batch size: 38, lr: 1.63e-03
+2022-04-28 12:03:27,787 INFO [train.py:763] (6/8) Epoch 3, batch 650, loss[loss=0.2496, simple_loss=0.3319, pruned_loss=0.08365, over 7431.00 frames.], tot_loss[loss=0.2527, simple_loss=0.3282, pruned_loss=0.08858, over 1367163.69 frames.], batch size: 20, lr: 1.62e-03
+2022-04-28 12:04:35,119 INFO [train.py:763] (6/8) Epoch 3, batch 700, loss[loss=0.2448, simple_loss=0.3236, pruned_loss=0.08302, over 7300.00 frames.], tot_loss[loss=0.2515, simple_loss=0.3273, pruned_loss=0.08782, over 1383787.95 frames.], batch size: 24, lr: 1.62e-03
+2022-04-28 12:05:41,311 INFO [train.py:763] (6/8) Epoch 3, batch 750, loss[loss=0.2955, simple_loss=0.3638, pruned_loss=0.1136, over 7292.00 frames.], tot_loss[loss=0.2509, simple_loss=0.3269, pruned_loss=0.08745, over 1392381.89 frames.], batch size: 24, lr: 1.62e-03
+2022-04-28 12:06:46,993 INFO [train.py:763] (6/8) Epoch 3, batch 800, loss[loss=0.2251, simple_loss=0.3086, pruned_loss=0.07081, over 7259.00 frames.], tot_loss[loss=0.2511, simple_loss=0.3269, pruned_loss=0.08765, over 1396435.07 frames.], batch size: 19, lr: 1.62e-03
+2022-04-28 12:07:53,460 INFO [train.py:763] (6/8) Epoch 3, batch 850, loss[loss=0.2123, simple_loss=0.3041, pruned_loss=0.06025, over 7063.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3267, pruned_loss=0.08691, over 1406328.77 frames.], batch size: 18, lr: 1.61e-03
+2022-04-28 12:09:00,228 INFO [train.py:763] (6/8) Epoch 3, batch 900, loss[loss=0.2777, simple_loss=0.3468, pruned_loss=0.1043, over 7104.00 frames.], tot_loss[loss=0.249, simple_loss=0.3258, pruned_loss=0.08613, over 1413843.30 frames.], batch size: 21, lr: 1.61e-03
+2022-04-28 12:10:06,546 INFO [train.py:763] (6/8) Epoch 3, batch 950, loss[loss=0.2736, simple_loss=0.3375, pruned_loss=0.1048, over 7165.00 frames.], tot_loss[loss=0.2485, simple_loss=0.3257, pruned_loss=0.08565, over 1419317.55 frames.], batch size: 26, lr: 1.61e-03
+2022-04-28 12:11:12,752 INFO [train.py:763] (6/8) Epoch 3, batch 1000, loss[loss=0.2317, simple_loss=0.3082, pruned_loss=0.07761, over 7266.00 frames.], tot_loss[loss=0.2487, simple_loss=0.3253, pruned_loss=0.08605, over 1420376.91 frames.], batch size: 18, lr: 1.61e-03
+2022-04-28 12:12:18,815 INFO [train.py:763] (6/8) Epoch 3, batch 1050, loss[loss=0.339, simple_loss=0.3874, pruned_loss=0.1453, over 6856.00 frames.], tot_loss[loss=0.2489, simple_loss=0.3259, pruned_loss=0.08591, over 1419266.23 frames.], batch size: 31, lr: 1.60e-03
+2022-04-28 12:13:24,399 INFO [train.py:763] (6/8) Epoch 3, batch 1100, loss[loss=0.2292, simple_loss=0.3136, pruned_loss=0.07246, over 7405.00 frames.], tot_loss[loss=0.2498, simple_loss=0.327, pruned_loss=0.0863, over 1419851.51 frames.], batch size: 21, lr: 1.60e-03
+2022-04-28 12:14:28,838 INFO [train.py:763] (6/8) Epoch 3, batch 1150, loss[loss=0.2578, simple_loss=0.3397, pruned_loss=0.08802, over 7328.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3281, pruned_loss=0.08652, over 1417855.20 frames.], batch size: 21, lr: 1.60e-03
+2022-04-28 12:15:35,088 INFO [train.py:763] (6/8) Epoch 3, batch 1200, loss[loss=0.2309, simple_loss=0.3188, pruned_loss=0.07151, over 7319.00 frames.], tot_loss[loss=0.2513, simple_loss=0.329, pruned_loss=0.08682, over 1415621.48 frames.], batch size: 21, lr: 1.60e-03
+2022-04-28 12:16:40,632 INFO [train.py:763] (6/8) Epoch 3, batch 1250, loss[loss=0.2494, simple_loss=0.3069, pruned_loss=0.09592, over 6792.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3289, pruned_loss=0.0874, over 1414372.11 frames.], batch size: 15, lr: 1.59e-03
+2022-04-28 12:17:46,146 INFO [train.py:763] (6/8) Epoch 3, batch 1300, loss[loss=0.2595, simple_loss=0.341, pruned_loss=0.08899, over 7222.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3282, pruned_loss=0.08725, over 1417711.22 frames.], batch size: 23, lr: 1.59e-03
+2022-04-28 12:18:51,891 INFO [train.py:763] (6/8) Epoch 3, batch 1350, loss[loss=0.2301, simple_loss=0.3192, pruned_loss=0.07051, over 7236.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3272, pruned_loss=0.08701, over 1416670.19 frames.], batch size: 20, lr: 1.59e-03
+2022-04-28 12:19:57,903 INFO [train.py:763] (6/8) Epoch 3, batch 1400, loss[loss=0.2633, simple_loss=0.3481, pruned_loss=0.08928, over 7210.00 frames.], tot_loss[loss=0.2499, simple_loss=0.3265, pruned_loss=0.08667, over 1419474.97 frames.], batch size: 22, lr: 1.59e-03
+2022-04-28 12:21:03,063 INFO [train.py:763] (6/8) Epoch 3, batch 1450, loss[loss=0.2538, simple_loss=0.3276, pruned_loss=0.09, over 7298.00 frames.], tot_loss[loss=0.2503, simple_loss=0.3273, pruned_loss=0.08667, over 1420890.52 frames.], batch size: 24, lr: 1.59e-03
+2022-04-28 12:22:08,503 INFO [train.py:763] (6/8) Epoch 3, batch 1500, loss[loss=0.2516, simple_loss=0.3232, pruned_loss=0.08999, over 7293.00 frames.], tot_loss[loss=0.2507, simple_loss=0.3271, pruned_loss=0.08716, over 1417559.28 frames.], batch size: 24, lr: 1.58e-03
+2022-04-28 12:23:14,003 INFO [train.py:763] (6/8) Epoch 3, batch 1550, loss[loss=0.3152, simple_loss=0.3603, pruned_loss=0.135, over 4920.00 frames.], tot_loss[loss=0.2516, simple_loss=0.3277, pruned_loss=0.08771, over 1416098.68 frames.], batch size: 52, lr: 1.58e-03
+2022-04-28 12:24:20,150 INFO [train.py:763] (6/8) Epoch 3, batch 1600, loss[loss=0.2742, simple_loss=0.3409, pruned_loss=0.1038, over 7296.00 frames.], tot_loss[loss=0.2526, simple_loss=0.3286, pruned_loss=0.08824, over 1413402.78 frames.], batch size: 25, lr: 1.58e-03
+2022-04-28 12:25:26,870 INFO [train.py:763] (6/8) Epoch 3, batch 1650, loss[loss=0.245, simple_loss=0.3139, pruned_loss=0.08807, over 7319.00 frames.], tot_loss[loss=0.251, simple_loss=0.3274, pruned_loss=0.08725, over 1415270.19 frames.], batch size: 20, lr: 1.58e-03
+2022-04-28 12:26:34,040 INFO [train.py:763] (6/8) Epoch 3, batch 1700, loss[loss=0.2859, simple_loss=0.3628, pruned_loss=0.1045, over 7155.00 frames.], tot_loss[loss=0.252, simple_loss=0.3289, pruned_loss=0.08758, over 1418963.02 frames.], batch size: 20, lr: 1.57e-03
+2022-04-28 12:27:40,152 INFO [train.py:763] (6/8) Epoch 3, batch 1750, loss[loss=0.2622, simple_loss=0.3262, pruned_loss=0.09911, over 7203.00 frames.], tot_loss[loss=0.2516, simple_loss=0.3287, pruned_loss=0.08727, over 1418727.74 frames.], batch size: 22, lr: 1.57e-03
+2022-04-28 12:28:45,189 INFO [train.py:763] (6/8) Epoch 3, batch 1800, loss[loss=0.2826, simple_loss=0.3502, pruned_loss=0.1075, over 7224.00 frames.], tot_loss[loss=0.252, simple_loss=0.3295, pruned_loss=0.08727, over 1420824.24 frames.], batch size: 21, lr: 1.57e-03
+2022-04-28 12:29:50,461 INFO [train.py:763] (6/8) Epoch 3, batch 1850, loss[loss=0.208, simple_loss=0.2896, pruned_loss=0.06326, over 7143.00 frames.], tot_loss[loss=0.2521, simple_loss=0.3297, pruned_loss=0.0872, over 1419895.03 frames.], batch size: 17, lr: 1.57e-03
+2022-04-28 12:30:57,335 INFO [train.py:763] (6/8) Epoch 3, batch 1900, loss[loss=0.3416, simple_loss=0.373, pruned_loss=0.1551, over 7159.00 frames.], tot_loss[loss=0.2531, simple_loss=0.33, pruned_loss=0.08807, over 1422788.80 frames.], batch size: 19, lr: 1.56e-03
+2022-04-28 12:32:03,220 INFO [train.py:763] (6/8) Epoch 3, batch 1950, loss[loss=0.3028, simple_loss=0.3576, pruned_loss=0.124, over 6572.00 frames.], tot_loss[loss=0.2527, simple_loss=0.33, pruned_loss=0.08773, over 1427844.76 frames.], batch size: 38, lr: 1.56e-03
+2022-04-28 12:33:17,864 INFO [train.py:763] (6/8) Epoch 3, batch 2000, loss[loss=0.2894, simple_loss=0.353, pruned_loss=0.1129, over 7125.00 frames.], tot_loss[loss=0.252, simple_loss=0.3293, pruned_loss=0.08738, over 1425033.59 frames.], batch size: 21, lr: 1.56e-03
+2022-04-28 12:35:10,049 INFO [train.py:763] (6/8) Epoch 3, batch 2050, loss[loss=0.2631, simple_loss=0.3304, pruned_loss=0.09797, over 6772.00 frames.], tot_loss[loss=0.2529, simple_loss=0.3298, pruned_loss=0.08802, over 1422024.49 frames.], batch size: 31, lr: 1.56e-03
+2022-04-28 12:36:15,499 INFO [train.py:763] (6/8) Epoch 3, batch 2100, loss[loss=0.2786, simple_loss=0.3514, pruned_loss=0.1029, over 7329.00 frames.], tot_loss[loss=0.251, simple_loss=0.3282, pruned_loss=0.08692, over 1419890.43 frames.], batch size: 21, lr: 1.56e-03
+2022-04-28 12:37:29,642 INFO [train.py:763] (6/8) Epoch 3, batch 2150, loss[loss=0.2738, simple_loss=0.3448, pruned_loss=0.1014, over 7333.00 frames.], tot_loss[loss=0.2491, simple_loss=0.3267, pruned_loss=0.08575, over 1422742.99 frames.], batch size: 22, lr: 1.55e-03
+2022-04-28 12:38:44,758 INFO [train.py:763] (6/8) Epoch 3, batch 2200, loss[loss=0.2607, simple_loss=0.3448, pruned_loss=0.08828, over 7223.00 frames.], tot_loss[loss=0.2476, simple_loss=0.3254, pruned_loss=0.0849, over 1425118.90 frames.], batch size: 21, lr: 1.55e-03
+2022-04-28 12:40:02,468 INFO [train.py:763] (6/8) Epoch 3, batch 2250, loss[loss=0.3035, simple_loss=0.3511, pruned_loss=0.128, over 4747.00 frames.], tot_loss[loss=0.2469, simple_loss=0.3255, pruned_loss=0.08413, over 1426197.77 frames.], batch size: 52, lr: 1.55e-03
+2022-04-28 12:41:07,754 INFO [train.py:763] (6/8) Epoch 3, batch 2300, loss[loss=0.2311, simple_loss=0.3199, pruned_loss=0.07116, over 7157.00 frames.], tot_loss[loss=0.2462, simple_loss=0.325, pruned_loss=0.08374, over 1429519.32 frames.], batch size: 19, lr: 1.55e-03
+2022-04-28 12:42:14,642 INFO [train.py:763] (6/8) Epoch 3, batch 2350, loss[loss=0.2399, simple_loss=0.325, pruned_loss=0.07741, over 7327.00 frames.], tot_loss[loss=0.2463, simple_loss=0.325, pruned_loss=0.08379, over 1431042.01 frames.], batch size: 20, lr: 1.54e-03
+2022-04-28 12:43:19,981 INFO [train.py:763] (6/8) Epoch 3, batch 2400, loss[loss=0.2562, simple_loss=0.3306, pruned_loss=0.09095, over 7282.00 frames.], tot_loss[loss=0.2485, simple_loss=0.3272, pruned_loss=0.08495, over 1433141.49 frames.], batch size: 25, lr: 1.54e-03
+2022-04-28 12:44:25,916 INFO [train.py:763] (6/8) Epoch 3, batch 2450, loss[loss=0.2409, simple_loss=0.316, pruned_loss=0.0829, over 7378.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3265, pruned_loss=0.08451, over 1435950.59 frames.], batch size: 23, lr: 1.54e-03
+2022-04-28 12:45:31,562 INFO [train.py:763] (6/8) Epoch 3, batch 2500, loss[loss=0.2242, simple_loss=0.3073, pruned_loss=0.07057, over 7148.00 frames.], tot_loss[loss=0.2479, simple_loss=0.326, pruned_loss=0.08493, over 1434625.75 frames.], batch size: 19, lr: 1.54e-03
+2022-04-28 12:46:36,899 INFO [train.py:763] (6/8) Epoch 3, batch 2550, loss[loss=0.2475, simple_loss=0.3147, pruned_loss=0.09018, over 7412.00 frames.], tot_loss[loss=0.248, simple_loss=0.3258, pruned_loss=0.08513, over 1425422.82 frames.], batch size: 18, lr: 1.54e-03
+2022-04-28 12:47:42,410 INFO [train.py:763] (6/8) Epoch 3, batch 2600, loss[loss=0.2077, simple_loss=0.2961, pruned_loss=0.05968, over 7237.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3274, pruned_loss=0.08673, over 1425473.81 frames.], batch size: 20, lr: 1.53e-03
+2022-04-28 12:48:47,823 INFO [train.py:763] (6/8) Epoch 3, batch 2650, loss[loss=0.2503, simple_loss=0.3061, pruned_loss=0.09727, over 7005.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3275, pruned_loss=0.08671, over 1418640.25 frames.], batch size: 16, lr: 1.53e-03
+2022-04-28 12:49:52,902 INFO [train.py:763] (6/8) Epoch 3, batch 2700, loss[loss=0.1904, simple_loss=0.271, pruned_loss=0.05486, over 6786.00 frames.], tot_loss[loss=0.2491, simple_loss=0.3269, pruned_loss=0.08568, over 1417331.11 frames.], batch size: 15, lr: 1.53e-03
+2022-04-28 12:50:58,281 INFO [train.py:763] (6/8) Epoch 3, batch 2750, loss[loss=0.2391, simple_loss=0.3132, pruned_loss=0.08246, over 7257.00 frames.], tot_loss[loss=0.2476, simple_loss=0.3259, pruned_loss=0.08468, over 1420912.32 frames.], batch size: 19, lr: 1.53e-03
+2022-04-28 12:52:03,627 INFO [train.py:763] (6/8) Epoch 3, batch 2800, loss[loss=0.2283, simple_loss=0.3118, pruned_loss=0.07237, over 7161.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3237, pruned_loss=0.08335, over 1423671.47 frames.], batch size: 19, lr: 1.53e-03
+2022-04-28 12:53:09,249 INFO [train.py:763] (6/8) Epoch 3, batch 2850, loss[loss=0.3075, simple_loss=0.3615, pruned_loss=0.1267, over 5202.00 frames.], tot_loss[loss=0.2448, simple_loss=0.3235, pruned_loss=0.08302, over 1423088.63 frames.], batch size: 53, lr: 1.52e-03
+2022-04-28 12:54:14,537 INFO [train.py:763] (6/8) Epoch 3, batch 2900, loss[loss=0.2748, simple_loss=0.3401, pruned_loss=0.1048, over 6700.00 frames.], tot_loss[loss=0.2446, simple_loss=0.3232, pruned_loss=0.08297, over 1423913.19 frames.], batch size: 31, lr: 1.52e-03
+2022-04-28 12:55:20,288 INFO [train.py:763] (6/8) Epoch 3, batch 2950, loss[loss=0.2364, simple_loss=0.3187, pruned_loss=0.07701, over 7027.00 frames.], tot_loss[loss=0.2445, simple_loss=0.3236, pruned_loss=0.08276, over 1427577.96 frames.], batch size: 28, lr: 1.52e-03
+2022-04-28 12:56:25,612 INFO [train.py:763] (6/8) Epoch 3, batch 3000, loss[loss=0.2514, simple_loss=0.3413, pruned_loss=0.08076, over 7147.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3243, pruned_loss=0.08299, over 1426113.51 frames.], batch size: 20, lr: 1.52e-03
+2022-04-28 12:56:25,613 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-28 12:56:40,878 INFO [train.py:792] (6/8) Epoch 3, validation: loss=0.1917, simple_loss=0.2967, pruned_loss=0.04336, over 698248.00 frames.
+2022-04-28 12:57:46,624 INFO [train.py:763] (6/8) Epoch 3, batch 3050, loss[loss=0.2291, simple_loss=0.3139, pruned_loss=0.07209, over 7124.00 frames.], tot_loss[loss=0.245, simple_loss=0.3239, pruned_loss=0.08304, over 1421409.31 frames.], batch size: 21, lr: 1.51e-03
+2022-04-28 12:58:52,514 INFO [train.py:763] (6/8) Epoch 3, batch 3100, loss[loss=0.2453, simple_loss=0.3313, pruned_loss=0.0797, over 7301.00 frames.], tot_loss[loss=0.2436, simple_loss=0.3228, pruned_loss=0.0822, over 1417229.22 frames.], batch size: 24, lr: 1.51e-03
+2022-04-28 12:59:58,117 INFO [train.py:763] (6/8) Epoch 3, batch 3150, loss[loss=0.2632, simple_loss=0.3421, pruned_loss=0.09219, over 7319.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3217, pruned_loss=0.08172, over 1421969.43 frames.], batch size: 25, lr: 1.51e-03
+2022-04-28 13:01:03,463 INFO [train.py:763] (6/8) Epoch 3, batch 3200, loss[loss=0.1869, simple_loss=0.2707, pruned_loss=0.05155, over 7075.00 frames.], tot_loss[loss=0.242, simple_loss=0.3209, pruned_loss=0.08153, over 1423221.57 frames.], batch size: 18, lr: 1.51e-03
+2022-04-28 13:02:09,453 INFO [train.py:763] (6/8) Epoch 3, batch 3250, loss[loss=0.2642, simple_loss=0.3342, pruned_loss=0.09716, over 7261.00 frames.], tot_loss[loss=0.2437, simple_loss=0.3225, pruned_loss=0.08249, over 1423907.45 frames.], batch size: 19, lr: 1.51e-03
+2022-04-28 13:03:16,232 INFO [train.py:763] (6/8) Epoch 3, batch 3300, loss[loss=0.2665, simple_loss=0.3495, pruned_loss=0.09172, over 7211.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3238, pruned_loss=0.083, over 1422022.08 frames.], batch size: 23, lr: 1.50e-03
+2022-04-28 13:04:22,928 INFO [train.py:763] (6/8) Epoch 3, batch 3350, loss[loss=0.3036, simple_loss=0.362, pruned_loss=0.1226, over 6475.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3226, pruned_loss=0.08255, over 1420442.01 frames.], batch size: 38, lr: 1.50e-03
+2022-04-28 13:05:28,643 INFO [train.py:763] (6/8) Epoch 3, batch 3400, loss[loss=0.2248, simple_loss=0.2973, pruned_loss=0.0762, over 6999.00 frames.], tot_loss[loss=0.2435, simple_loss=0.3226, pruned_loss=0.08217, over 1421113.23 frames.], batch size: 16, lr: 1.50e-03
+2022-04-28 13:06:35,008 INFO [train.py:763] (6/8) Epoch 3, batch 3450, loss[loss=0.2445, simple_loss=0.3167, pruned_loss=0.08614, over 7167.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3211, pruned_loss=0.0818, over 1426012.94 frames.], batch size: 18, lr: 1.50e-03
+2022-04-28 13:07:42,193 INFO [train.py:763] (6/8) Epoch 3, batch 3500, loss[loss=0.2411, simple_loss=0.3269, pruned_loss=0.07767, over 7370.00 frames.], tot_loss[loss=0.2413, simple_loss=0.3203, pruned_loss=0.08119, over 1428098.23 frames.], batch size: 23, lr: 1.50e-03
+2022-04-28 13:08:48,565 INFO [train.py:763] (6/8) Epoch 3, batch 3550, loss[loss=0.2325, simple_loss=0.3135, pruned_loss=0.07579, over 7279.00 frames.], tot_loss[loss=0.2427, simple_loss=0.3213, pruned_loss=0.082, over 1429275.81 frames.], batch size: 24, lr: 1.49e-03
+2022-04-28 13:09:55,527 INFO [train.py:763] (6/8) Epoch 3, batch 3600, loss[loss=0.1884, simple_loss=0.2662, pruned_loss=0.05528, over 7009.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3222, pruned_loss=0.08284, over 1428273.27 frames.], batch size: 16, lr: 1.49e-03
+2022-04-28 13:11:02,051 INFO [train.py:763] (6/8) Epoch 3, batch 3650, loss[loss=0.2615, simple_loss=0.3211, pruned_loss=0.1009, over 7144.00 frames.], tot_loss[loss=0.2445, simple_loss=0.323, pruned_loss=0.08298, over 1428574.52 frames.], batch size: 17, lr: 1.49e-03
+2022-04-28 13:12:07,905 INFO [train.py:763] (6/8) Epoch 3, batch 3700, loss[loss=0.2389, simple_loss=0.3112, pruned_loss=0.08327, over 7003.00 frames.], tot_loss[loss=0.2441, simple_loss=0.323, pruned_loss=0.08261, over 1427851.41 frames.], batch size: 16, lr: 1.49e-03
+2022-04-28 13:13:15,361 INFO [train.py:763] (6/8) Epoch 3, batch 3750, loss[loss=0.269, simple_loss=0.3496, pruned_loss=0.09422, over 7427.00 frames.], tot_loss[loss=0.2424, simple_loss=0.3215, pruned_loss=0.08162, over 1426305.18 frames.], batch size: 20, lr: 1.49e-03
+2022-04-28 13:14:22,358 INFO [train.py:763] (6/8) Epoch 3, batch 3800, loss[loss=0.2218, simple_loss=0.303, pruned_loss=0.07032, over 7060.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3212, pruned_loss=0.0817, over 1422592.52 frames.], batch size: 18, lr: 1.48e-03
+2022-04-28 13:15:29,712 INFO [train.py:763] (6/8) Epoch 3, batch 3850, loss[loss=0.1805, simple_loss=0.2555, pruned_loss=0.05277, over 7409.00 frames.], tot_loss[loss=0.2408, simple_loss=0.3202, pruned_loss=0.08076, over 1426330.71 frames.], batch size: 18, lr: 1.48e-03
+2022-04-28 13:16:35,238 INFO [train.py:763] (6/8) Epoch 3, batch 3900, loss[loss=0.3477, simple_loss=0.3941, pruned_loss=0.1506, over 5207.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3217, pruned_loss=0.08205, over 1427577.01 frames.], batch size: 52, lr: 1.48e-03
+2022-04-28 13:17:41,253 INFO [train.py:763] (6/8) Epoch 3, batch 3950, loss[loss=0.2006, simple_loss=0.2821, pruned_loss=0.05957, over 6786.00 frames.], tot_loss[loss=0.2431, simple_loss=0.3215, pruned_loss=0.0823, over 1425774.89 frames.], batch size: 15, lr: 1.48e-03
+2022-04-28 13:18:46,788 INFO [train.py:763] (6/8) Epoch 3, batch 4000, loss[loss=0.2553, simple_loss=0.3375, pruned_loss=0.08653, over 7230.00 frames.], tot_loss[loss=0.2444, simple_loss=0.3226, pruned_loss=0.08308, over 1418781.04 frames.], batch size: 21, lr: 1.48e-03
+2022-04-28 13:19:52,131 INFO [train.py:763] (6/8) Epoch 3, batch 4050, loss[loss=0.2614, simple_loss=0.3472, pruned_loss=0.08777, over 7414.00 frames.], tot_loss[loss=0.2436, simple_loss=0.322, pruned_loss=0.08258, over 1420278.48 frames.], batch size: 21, lr: 1.47e-03
+2022-04-28 13:20:58,244 INFO [train.py:763] (6/8) Epoch 3, batch 4100, loss[loss=0.2622, simple_loss=0.3364, pruned_loss=0.094, over 6371.00 frames.], tot_loss[loss=0.2435, simple_loss=0.3222, pruned_loss=0.0824, over 1421808.68 frames.], batch size: 37, lr: 1.47e-03
+2022-04-28 13:22:04,071 INFO [train.py:763] (6/8) Epoch 3, batch 4150, loss[loss=0.2225, simple_loss=0.2966, pruned_loss=0.07417, over 6992.00 frames.], tot_loss[loss=0.2418, simple_loss=0.321, pruned_loss=0.08135, over 1423969.89 frames.], batch size: 16, lr: 1.47e-03
+2022-04-28 13:23:11,045 INFO [train.py:763] (6/8) Epoch 3, batch 4200, loss[loss=0.2582, simple_loss=0.33, pruned_loss=0.09325, over 7160.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3213, pruned_loss=0.082, over 1421591.31 frames.], batch size: 19, lr: 1.47e-03
+2022-04-28 13:24:18,324 INFO [train.py:763] (6/8) Epoch 3, batch 4250, loss[loss=0.2299, simple_loss=0.314, pruned_loss=0.0729, over 7362.00 frames.], tot_loss[loss=0.242, simple_loss=0.3204, pruned_loss=0.08185, over 1413985.80 frames.], batch size: 19, lr: 1.47e-03
+2022-04-28 13:25:24,089 INFO [train.py:763] (6/8) Epoch 3, batch 4300, loss[loss=0.2639, simple_loss=0.3344, pruned_loss=0.09672, over 7350.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3181, pruned_loss=0.08075, over 1412903.89 frames.], batch size: 19, lr: 1.47e-03
+2022-04-28 13:26:29,896 INFO [train.py:763] (6/8) Epoch 3, batch 4350, loss[loss=0.2493, simple_loss=0.3387, pruned_loss=0.07995, over 6553.00 frames.], tot_loss[loss=0.2378, simple_loss=0.316, pruned_loss=0.07982, over 1411430.78 frames.], batch size: 38, lr: 1.46e-03
+2022-04-28 13:27:35,681 INFO [train.py:763] (6/8) Epoch 3, batch 4400, loss[loss=0.2292, simple_loss=0.3134, pruned_loss=0.07252, over 7075.00 frames.], tot_loss[loss=0.2379, simple_loss=0.316, pruned_loss=0.07984, over 1409471.51 frames.], batch size: 18, lr: 1.46e-03
+2022-04-28 13:28:41,564 INFO [train.py:763] (6/8) Epoch 3, batch 4450, loss[loss=0.2554, simple_loss=0.3423, pruned_loss=0.08425, over 7384.00 frames.], tot_loss[loss=0.2372, simple_loss=0.3154, pruned_loss=0.07946, over 1402098.95 frames.], batch size: 23, lr: 1.46e-03
+2022-04-28 13:29:46,951 INFO [train.py:763] (6/8) Epoch 3, batch 4500, loss[loss=0.2865, simple_loss=0.3707, pruned_loss=0.1011, over 6441.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3159, pruned_loss=0.08014, over 1396078.53 frames.], batch size: 38, lr: 1.46e-03
+2022-04-28 13:30:51,040 INFO [train.py:763] (6/8) Epoch 3, batch 4550, loss[loss=0.3019, simple_loss=0.3679, pruned_loss=0.1179, over 5082.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3203, pruned_loss=0.08278, over 1361919.76 frames.], batch size: 53, lr: 1.46e-03
+2022-04-28 13:32:20,244 INFO [train.py:763] (6/8) Epoch 4, batch 0, loss[loss=0.2469, simple_loss=0.3382, pruned_loss=0.07784, over 7216.00 frames.], tot_loss[loss=0.2469, simple_loss=0.3382, pruned_loss=0.07784, over 7216.00 frames.], batch size: 23, lr: 1.40e-03
+2022-04-28 13:33:26,514 INFO [train.py:763] (6/8) Epoch 4, batch 50, loss[loss=0.2473, simple_loss=0.3373, pruned_loss=0.07869, over 7337.00 frames.], tot_loss[loss=0.2444, simple_loss=0.3224, pruned_loss=0.08322, over 320613.30 frames.], batch size: 22, lr: 1.40e-03
+2022-04-28 13:34:31,941 INFO [train.py:763] (6/8) Epoch 4, batch 100, loss[loss=0.2512, simple_loss=0.3349, pruned_loss=0.08372, over 7331.00 frames.], tot_loss[loss=0.242, simple_loss=0.3228, pruned_loss=0.08061, over 567065.49 frames.], batch size: 22, lr: 1.40e-03
+2022-04-28 13:35:37,420 INFO [train.py:763] (6/8) Epoch 4, batch 150, loss[loss=0.312, simple_loss=0.3748, pruned_loss=0.1246, over 4831.00 frames.], tot_loss[loss=0.2407, simple_loss=0.3218, pruned_loss=0.07973, over 755952.70 frames.], batch size: 52, lr: 1.40e-03
+2022-04-28 13:36:43,014 INFO [train.py:763] (6/8) Epoch 4, batch 200, loss[loss=0.2289, simple_loss=0.3209, pruned_loss=0.06842, over 7155.00 frames.], tot_loss[loss=0.2417, simple_loss=0.3222, pruned_loss=0.08056, over 904580.81 frames.], batch size: 19, lr: 1.40e-03
+2022-04-28 13:37:49,018 INFO [train.py:763] (6/8) Epoch 4, batch 250, loss[loss=0.2373, simple_loss=0.3297, pruned_loss=0.07247, over 7352.00 frames.], tot_loss[loss=0.2422, simple_loss=0.3237, pruned_loss=0.08034, over 1021817.57 frames.], batch size: 22, lr: 1.39e-03
+2022-04-28 13:38:55,657 INFO [train.py:763] (6/8) Epoch 4, batch 300, loss[loss=0.2177, simple_loss=0.288, pruned_loss=0.07376, over 7277.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3206, pruned_loss=0.07895, over 1113736.68 frames.], batch size: 17, lr: 1.39e-03
+2022-04-28 13:40:02,794 INFO [train.py:763] (6/8) Epoch 4, batch 350, loss[loss=0.1985, simple_loss=0.2803, pruned_loss=0.05834, over 7162.00 frames.], tot_loss[loss=0.2384, simple_loss=0.3196, pruned_loss=0.07858, over 1181458.45 frames.], batch size: 19, lr: 1.39e-03
+2022-04-28 13:41:09,483 INFO [train.py:763] (6/8) Epoch 4, batch 400, loss[loss=0.2644, simple_loss=0.34, pruned_loss=0.09434, over 7101.00 frames.], tot_loss[loss=0.2383, simple_loss=0.3195, pruned_loss=0.07857, over 1232575.53 frames.], batch size: 28, lr: 1.39e-03
+2022-04-28 13:42:15,466 INFO [train.py:763] (6/8) Epoch 4, batch 450, loss[loss=0.2374, simple_loss=0.3173, pruned_loss=0.07877, over 7090.00 frames.], tot_loss[loss=0.2384, simple_loss=0.3195, pruned_loss=0.07866, over 1274049.17 frames.], batch size: 28, lr: 1.39e-03
+2022-04-28 13:43:21,272 INFO [train.py:763] (6/8) Epoch 4, batch 500, loss[loss=0.2325, simple_loss=0.3241, pruned_loss=0.07047, over 7325.00 frames.], tot_loss[loss=0.237, simple_loss=0.3183, pruned_loss=0.07782, over 1309796.52 frames.], batch size: 21, lr: 1.39e-03
+2022-04-28 13:44:28,337 INFO [train.py:763] (6/8) Epoch 4, batch 550, loss[loss=0.2288, simple_loss=0.3149, pruned_loss=0.07132, over 6598.00 frames.], tot_loss[loss=0.237, simple_loss=0.3183, pruned_loss=0.07782, over 1334170.36 frames.], batch size: 31, lr: 1.38e-03
+2022-04-28 13:45:33,792 INFO [train.py:763] (6/8) Epoch 4, batch 600, loss[loss=0.2433, simple_loss=0.311, pruned_loss=0.08781, over 6994.00 frames.], tot_loss[loss=0.2365, simple_loss=0.3172, pruned_loss=0.07792, over 1355846.63 frames.], batch size: 16, lr: 1.38e-03
+2022-04-28 13:46:39,058 INFO [train.py:763] (6/8) Epoch 4, batch 650, loss[loss=0.2321, simple_loss=0.3191, pruned_loss=0.0725, over 7321.00 frames.], tot_loss[loss=0.237, simple_loss=0.3175, pruned_loss=0.0782, over 1370477.16 frames.], batch size: 20, lr: 1.38e-03
+2022-04-28 13:47:44,006 INFO [train.py:763] (6/8) Epoch 4, batch 700, loss[loss=0.2321, simple_loss=0.3388, pruned_loss=0.06266, over 7303.00 frames.], tot_loss[loss=0.2376, simple_loss=0.3185, pruned_loss=0.07841, over 1381084.57 frames.], batch size: 25, lr: 1.38e-03
+2022-04-28 13:48:49,480 INFO [train.py:763] (6/8) Epoch 4, batch 750, loss[loss=0.2569, simple_loss=0.3296, pruned_loss=0.09209, over 7064.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3185, pruned_loss=0.07858, over 1386514.89 frames.], batch size: 18, lr: 1.38e-03
+2022-04-28 13:49:55,004 INFO [train.py:763] (6/8) Epoch 4, batch 800, loss[loss=0.2083, simple_loss=0.2863, pruned_loss=0.06516, over 7057.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3163, pruned_loss=0.07749, over 1397255.79 frames.], batch size: 18, lr: 1.38e-03
+2022-04-28 13:50:59,967 INFO [train.py:763] (6/8) Epoch 4, batch 850, loss[loss=0.2203, simple_loss=0.2989, pruned_loss=0.07088, over 7072.00 frames.], tot_loss[loss=0.2356, simple_loss=0.316, pruned_loss=0.07758, over 1395070.54 frames.], batch size: 18, lr: 1.37e-03
+2022-04-28 13:52:05,757 INFO [train.py:763] (6/8) Epoch 4, batch 900, loss[loss=0.2329, simple_loss=0.327, pruned_loss=0.06936, over 7318.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3165, pruned_loss=0.07766, over 1401841.41 frames.], batch size: 21, lr: 1.37e-03
+2022-04-28 13:53:12,272 INFO [train.py:763] (6/8) Epoch 4, batch 950, loss[loss=0.2679, simple_loss=0.3412, pruned_loss=0.09733, over 6980.00 frames.], tot_loss[loss=0.2364, simple_loss=0.317, pruned_loss=0.07788, over 1405889.92 frames.], batch size: 28, lr: 1.37e-03
+2022-04-28 13:54:19,422 INFO [train.py:763] (6/8) Epoch 4, batch 1000, loss[loss=0.2406, simple_loss=0.3254, pruned_loss=0.07789, over 7057.00 frames.], tot_loss[loss=0.2353, simple_loss=0.3161, pruned_loss=0.07725, over 1410771.09 frames.], batch size: 18, lr: 1.37e-03
+2022-04-28 13:55:24,902 INFO [train.py:763] (6/8) Epoch 4, batch 1050, loss[loss=0.2702, simple_loss=0.3499, pruned_loss=0.0953, over 7275.00 frames.], tot_loss[loss=0.2366, simple_loss=0.3175, pruned_loss=0.07791, over 1416301.41 frames.], batch size: 24, lr: 1.37e-03
+2022-04-28 13:56:29,982 INFO [train.py:763] (6/8) Epoch 4, batch 1100, loss[loss=0.2608, simple_loss=0.3382, pruned_loss=0.09176, over 6329.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3193, pruned_loss=0.07949, over 1411974.85 frames.], batch size: 37, lr: 1.37e-03
+2022-04-28 13:57:36,087 INFO [train.py:763] (6/8) Epoch 4, batch 1150, loss[loss=0.2619, simple_loss=0.3323, pruned_loss=0.09573, over 7428.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3207, pruned_loss=0.08005, over 1415186.48 frames.], batch size: 20, lr: 1.36e-03
+2022-04-28 13:58:41,145 INFO [train.py:763] (6/8) Epoch 4, batch 1200, loss[loss=0.2324, simple_loss=0.3141, pruned_loss=0.07534, over 6500.00 frames.], tot_loss[loss=0.2382, simple_loss=0.3185, pruned_loss=0.07891, over 1417336.80 frames.], batch size: 38, lr: 1.36e-03
+2022-04-28 13:59:46,360 INFO [train.py:763] (6/8) Epoch 4, batch 1250, loss[loss=0.2465, simple_loss=0.3201, pruned_loss=0.08642, over 7251.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3173, pruned_loss=0.07848, over 1413500.50 frames.], batch size: 19, lr: 1.36e-03
+2022-04-28 14:00:51,531 INFO [train.py:763] (6/8) Epoch 4, batch 1300, loss[loss=0.2159, simple_loss=0.3077, pruned_loss=0.06212, over 7333.00 frames.], tot_loss[loss=0.2376, simple_loss=0.3181, pruned_loss=0.07856, over 1416673.46 frames.], batch size: 20, lr: 1.36e-03
+2022-04-28 14:01:57,423 INFO [train.py:763] (6/8) Epoch 4, batch 1350, loss[loss=0.2111, simple_loss=0.2927, pruned_loss=0.06477, over 7134.00 frames.], tot_loss[loss=0.2374, simple_loss=0.3179, pruned_loss=0.07847, over 1423474.17 frames.], batch size: 17, lr: 1.36e-03
+2022-04-28 14:03:02,790 INFO [train.py:763] (6/8) Epoch 4, batch 1400, loss[loss=0.2523, simple_loss=0.3355, pruned_loss=0.0845, over 7230.00 frames.], tot_loss[loss=0.2382, simple_loss=0.3188, pruned_loss=0.07884, over 1418987.91 frames.], batch size: 20, lr: 1.36e-03
+2022-04-28 14:04:07,965 INFO [train.py:763] (6/8) Epoch 4, batch 1450, loss[loss=0.1778, simple_loss=0.2538, pruned_loss=0.05089, over 6997.00 frames.], tot_loss[loss=0.2387, simple_loss=0.3191, pruned_loss=0.07915, over 1419516.16 frames.], batch size: 16, lr: 1.35e-03
+2022-04-28 14:05:14,092 INFO [train.py:763] (6/8) Epoch 4, batch 1500, loss[loss=0.2141, simple_loss=0.3061, pruned_loss=0.06098, over 7328.00 frames.], tot_loss[loss=0.2375, simple_loss=0.3179, pruned_loss=0.07853, over 1422975.06 frames.], batch size: 20, lr: 1.35e-03
+2022-04-28 14:06:19,711 INFO [train.py:763] (6/8) Epoch 4, batch 1550, loss[loss=0.2321, simple_loss=0.3201, pruned_loss=0.07211, over 7375.00 frames.], tot_loss[loss=0.2355, simple_loss=0.3164, pruned_loss=0.07733, over 1425390.19 frames.], batch size: 23, lr: 1.35e-03
+2022-04-28 14:07:24,979 INFO [train.py:763] (6/8) Epoch 4, batch 1600, loss[loss=0.2458, simple_loss=0.336, pruned_loss=0.07782, over 7290.00 frames.], tot_loss[loss=0.2352, simple_loss=0.3165, pruned_loss=0.077, over 1424401.77 frames.], batch size: 25, lr: 1.35e-03
+2022-04-28 14:08:30,207 INFO [train.py:763] (6/8) Epoch 4, batch 1650, loss[loss=0.2536, simple_loss=0.3338, pruned_loss=0.08666, over 7117.00 frames.], tot_loss[loss=0.2345, simple_loss=0.316, pruned_loss=0.07645, over 1422527.51 frames.], batch size: 21, lr: 1.35e-03
+2022-04-28 14:09:35,801 INFO [train.py:763] (6/8) Epoch 4, batch 1700, loss[loss=0.2655, simple_loss=0.3455, pruned_loss=0.09272, over 7343.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3147, pruned_loss=0.0754, over 1424538.48 frames.], batch size: 22, lr: 1.35e-03
+2022-04-28 14:10:42,771 INFO [train.py:763] (6/8) Epoch 4, batch 1750, loss[loss=0.2289, simple_loss=0.3258, pruned_loss=0.06596, over 7296.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3139, pruned_loss=0.07524, over 1423971.77 frames.], batch size: 24, lr: 1.34e-03
+2022-04-28 14:11:49,094 INFO [train.py:763] (6/8) Epoch 4, batch 1800, loss[loss=0.2476, simple_loss=0.3433, pruned_loss=0.07592, over 7318.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3145, pruned_loss=0.07528, over 1426460.84 frames.], batch size: 21, lr: 1.34e-03
+2022-04-28 14:12:54,650 INFO [train.py:763] (6/8) Epoch 4, batch 1850, loss[loss=0.2592, simple_loss=0.3344, pruned_loss=0.09197, over 6334.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3159, pruned_loss=0.07624, over 1426896.49 frames.], batch size: 38, lr: 1.34e-03
+2022-04-28 14:13:59,951 INFO [train.py:763] (6/8) Epoch 4, batch 1900, loss[loss=0.2494, simple_loss=0.3352, pruned_loss=0.08183, over 7102.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3168, pruned_loss=0.07653, over 1427758.53 frames.], batch size: 21, lr: 1.34e-03
+2022-04-28 14:15:05,368 INFO [train.py:763] (6/8) Epoch 4, batch 1950, loss[loss=0.228, simple_loss=0.3056, pruned_loss=0.07523, over 7144.00 frames.], tot_loss[loss=0.2353, simple_loss=0.3168, pruned_loss=0.07686, over 1428022.74 frames.], batch size: 18, lr: 1.34e-03
+2022-04-28 14:16:10,983 INFO [train.py:763] (6/8) Epoch 4, batch 2000, loss[loss=0.2339, simple_loss=0.3175, pruned_loss=0.07517, over 7330.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3155, pruned_loss=0.07615, over 1424330.12 frames.], batch size: 25, lr: 1.34e-03
+2022-04-28 14:17:16,771 INFO [train.py:763] (6/8) Epoch 4, batch 2050, loss[loss=0.2666, simple_loss=0.3549, pruned_loss=0.08918, over 7290.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3151, pruned_loss=0.07592, over 1429346.60 frames.], batch size: 24, lr: 1.34e-03
+2022-04-28 14:18:22,260 INFO [train.py:763] (6/8) Epoch 4, batch 2100, loss[loss=0.2381, simple_loss=0.3095, pruned_loss=0.08333, over 7410.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3143, pruned_loss=0.07522, over 1432895.39 frames.], batch size: 18, lr: 1.33e-03
+2022-04-28 14:19:27,875 INFO [train.py:763] (6/8) Epoch 4, batch 2150, loss[loss=0.2152, simple_loss=0.2857, pruned_loss=0.07231, over 7063.00 frames.], tot_loss[loss=0.2336, simple_loss=0.3158, pruned_loss=0.07572, over 1431112.97 frames.], batch size: 18, lr: 1.33e-03
+2022-04-28 14:20:34,208 INFO [train.py:763] (6/8) Epoch 4, batch 2200, loss[loss=0.2459, simple_loss=0.3415, pruned_loss=0.07516, over 7352.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3158, pruned_loss=0.07603, over 1432817.99 frames.], batch size: 22, lr: 1.33e-03
+2022-04-28 14:21:39,761 INFO [train.py:763] (6/8) Epoch 4, batch 2250, loss[loss=0.2902, simple_loss=0.3673, pruned_loss=0.1066, over 7376.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3156, pruned_loss=0.07609, over 1430636.70 frames.], batch size: 23, lr: 1.33e-03
+2022-04-28 14:22:45,299 INFO [train.py:763] (6/8) Epoch 4, batch 2300, loss[loss=0.1907, simple_loss=0.2713, pruned_loss=0.05507, over 7278.00 frames.], tot_loss[loss=0.2346, simple_loss=0.3162, pruned_loss=0.07648, over 1429712.21 frames.], batch size: 17, lr: 1.33e-03
+2022-04-28 14:23:50,803 INFO [train.py:763] (6/8) Epoch 4, batch 2350, loss[loss=0.1832, simple_loss=0.2627, pruned_loss=0.05184, over 7407.00 frames.], tot_loss[loss=0.2351, simple_loss=0.3168, pruned_loss=0.07672, over 1433127.63 frames.], batch size: 18, lr: 1.33e-03
+2022-04-28 14:24:56,455 INFO [train.py:763] (6/8) Epoch 4, batch 2400, loss[loss=0.2267, simple_loss=0.3246, pruned_loss=0.06438, over 7216.00 frames.], tot_loss[loss=0.2341, simple_loss=0.316, pruned_loss=0.07609, over 1434481.98 frames.], batch size: 21, lr: 1.32e-03
+2022-04-28 14:26:01,952 INFO [train.py:763] (6/8) Epoch 4, batch 2450, loss[loss=0.1959, simple_loss=0.2825, pruned_loss=0.05465, over 7286.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3156, pruned_loss=0.07557, over 1434199.44 frames.], batch size: 18, lr: 1.32e-03
+2022-04-28 14:27:09,069 INFO [train.py:763] (6/8) Epoch 4, batch 2500, loss[loss=0.2582, simple_loss=0.3462, pruned_loss=0.08511, over 7202.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3143, pruned_loss=0.07509, over 1431901.74 frames.], batch size: 22, lr: 1.32e-03
+2022-04-28 14:28:14,998 INFO [train.py:763] (6/8) Epoch 4, batch 2550, loss[loss=0.2249, simple_loss=0.3115, pruned_loss=0.06909, over 7140.00 frames.], tot_loss[loss=0.2317, simple_loss=0.314, pruned_loss=0.07467, over 1432399.66 frames.], batch size: 20, lr: 1.32e-03
+2022-04-28 14:29:20,357 INFO [train.py:763] (6/8) Epoch 4, batch 2600, loss[loss=0.2287, simple_loss=0.3147, pruned_loss=0.07137, over 7329.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3148, pruned_loss=0.07508, over 1430764.92 frames.], batch size: 21, lr: 1.32e-03
+2022-04-28 14:30:26,098 INFO [train.py:763] (6/8) Epoch 4, batch 2650, loss[loss=0.1865, simple_loss=0.2714, pruned_loss=0.05086, over 7016.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3142, pruned_loss=0.07449, over 1429496.50 frames.], batch size: 16, lr: 1.32e-03
+2022-04-28 14:31:31,707 INFO [train.py:763] (6/8) Epoch 4, batch 2700, loss[loss=0.237, simple_loss=0.3183, pruned_loss=0.07784, over 7283.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3136, pruned_loss=0.07434, over 1432232.01 frames.], batch size: 18, lr: 1.32e-03
+2022-04-28 14:32:38,238 INFO [train.py:763] (6/8) Epoch 4, batch 2750, loss[loss=0.2355, simple_loss=0.3121, pruned_loss=0.07948, over 7367.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3138, pruned_loss=0.07441, over 1432516.93 frames.], batch size: 19, lr: 1.31e-03
+2022-04-28 14:33:43,920 INFO [train.py:763] (6/8) Epoch 4, batch 2800, loss[loss=0.2003, simple_loss=0.2744, pruned_loss=0.06304, over 7129.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3128, pruned_loss=0.07403, over 1432801.00 frames.], batch size: 17, lr: 1.31e-03
+2022-04-28 14:34:49,328 INFO [train.py:763] (6/8) Epoch 4, batch 2850, loss[loss=0.2361, simple_loss=0.327, pruned_loss=0.07261, over 6722.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3137, pruned_loss=0.07465, over 1430612.06 frames.], batch size: 31, lr: 1.31e-03
+2022-04-28 14:35:56,026 INFO [train.py:763] (6/8) Epoch 4, batch 2900, loss[loss=0.2197, simple_loss=0.3297, pruned_loss=0.05485, over 7300.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3148, pruned_loss=0.07484, over 1429912.40 frames.], batch size: 24, lr: 1.31e-03
+2022-04-28 14:37:01,946 INFO [train.py:763] (6/8) Epoch 4, batch 2950, loss[loss=0.216, simple_loss=0.3004, pruned_loss=0.0658, over 7333.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3139, pruned_loss=0.07411, over 1430156.56 frames.], batch size: 22, lr: 1.31e-03
+2022-04-28 14:38:07,794 INFO [train.py:763] (6/8) Epoch 4, batch 3000, loss[loss=0.2643, simple_loss=0.3455, pruned_loss=0.09154, over 7154.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3133, pruned_loss=0.07411, over 1425867.14 frames.], batch size: 26, lr: 1.31e-03
+2022-04-28 14:38:07,795 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-28 14:38:23,245 INFO [train.py:792] (6/8) Epoch 4, validation: loss=0.1809, simple_loss=0.2865, pruned_loss=0.03766, over 698248.00 frames.
+2022-04-28 14:39:28,676 INFO [train.py:763] (6/8) Epoch 4, batch 3050, loss[loss=0.2289, simple_loss=0.3154, pruned_loss=0.07118, over 7209.00 frames.], tot_loss[loss=0.2311, simple_loss=0.314, pruned_loss=0.0741, over 1429742.65 frames.], batch size: 22, lr: 1.31e-03
+2022-04-28 14:40:34,113 INFO [train.py:763] (6/8) Epoch 4, batch 3100, loss[loss=0.2274, simple_loss=0.3114, pruned_loss=0.07169, over 7223.00 frames.], tot_loss[loss=0.2314, simple_loss=0.314, pruned_loss=0.07438, over 1428544.59 frames.], batch size: 20, lr: 1.30e-03
+2022-04-28 14:41:39,920 INFO [train.py:763] (6/8) Epoch 4, batch 3150, loss[loss=0.2646, simple_loss=0.3442, pruned_loss=0.09248, over 7288.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3141, pruned_loss=0.07446, over 1428882.31 frames.], batch size: 25, lr: 1.30e-03
+2022-04-28 14:42:46,507 INFO [train.py:763] (6/8) Epoch 4, batch 3200, loss[loss=0.2023, simple_loss=0.2947, pruned_loss=0.05497, over 7345.00 frames.], tot_loss[loss=0.231, simple_loss=0.3138, pruned_loss=0.07406, over 1429985.77 frames.], batch size: 19, lr: 1.30e-03
+2022-04-28 14:43:52,417 INFO [train.py:763] (6/8) Epoch 4, batch 3250, loss[loss=0.202, simple_loss=0.28, pruned_loss=0.06194, over 7171.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3137, pruned_loss=0.07392, over 1428376.64 frames.], batch size: 18, lr: 1.30e-03
+2022-04-28 14:44:57,966 INFO [train.py:763] (6/8) Epoch 4, batch 3300, loss[loss=0.2368, simple_loss=0.3214, pruned_loss=0.07611, over 7141.00 frames.], tot_loss[loss=0.232, simple_loss=0.3144, pruned_loss=0.07474, over 1423394.07 frames.], batch size: 26, lr: 1.30e-03
+2022-04-28 14:46:03,556 INFO [train.py:763] (6/8) Epoch 4, batch 3350, loss[loss=0.2575, simple_loss=0.3356, pruned_loss=0.0897, over 7118.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3141, pruned_loss=0.07404, over 1426566.56 frames.], batch size: 21, lr: 1.30e-03
+2022-04-28 14:47:08,815 INFO [train.py:763] (6/8) Epoch 4, batch 3400, loss[loss=0.2329, simple_loss=0.3141, pruned_loss=0.07583, over 7227.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3146, pruned_loss=0.07463, over 1428594.01 frames.], batch size: 20, lr: 1.30e-03
+2022-04-28 14:48:14,159 INFO [train.py:763] (6/8) Epoch 4, batch 3450, loss[loss=0.2024, simple_loss=0.2973, pruned_loss=0.05374, over 7201.00 frames.], tot_loss[loss=0.231, simple_loss=0.3135, pruned_loss=0.07421, over 1428183.31 frames.], batch size: 23, lr: 1.29e-03
+2022-04-28 14:49:37,446 INFO [train.py:763] (6/8) Epoch 4, batch 3500, loss[loss=0.237, simple_loss=0.3199, pruned_loss=0.077, over 7327.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3146, pruned_loss=0.0744, over 1430233.96 frames.], batch size: 20, lr: 1.29e-03
+2022-04-28 14:50:52,147 INFO [train.py:763] (6/8) Epoch 4, batch 3550, loss[loss=0.2322, simple_loss=0.3287, pruned_loss=0.06781, over 7416.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3141, pruned_loss=0.07454, over 1424933.60 frames.], batch size: 21, lr: 1.29e-03
+2022-04-28 14:51:57,846 INFO [train.py:763] (6/8) Epoch 4, batch 3600, loss[loss=0.2057, simple_loss=0.2942, pruned_loss=0.05857, over 7268.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3148, pruned_loss=0.07517, over 1421619.62 frames.], batch size: 19, lr: 1.29e-03
+2022-04-28 14:53:23,232 INFO [train.py:763] (6/8) Epoch 4, batch 3650, loss[loss=0.2348, simple_loss=0.3203, pruned_loss=0.07469, over 6783.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3156, pruned_loss=0.07534, over 1415690.61 frames.], batch size: 31, lr: 1.29e-03
+2022-04-28 14:54:39,014 INFO [train.py:763] (6/8) Epoch 4, batch 3700, loss[loss=0.2297, simple_loss=0.3074, pruned_loss=0.076, over 7149.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3134, pruned_loss=0.07452, over 1419344.90 frames.], batch size: 18, lr: 1.29e-03
+2022-04-28 14:55:53,486 INFO [train.py:763] (6/8) Epoch 4, batch 3750, loss[loss=0.1935, simple_loss=0.2829, pruned_loss=0.05199, over 6837.00 frames.], tot_loss[loss=0.232, simple_loss=0.3141, pruned_loss=0.07494, over 1419633.64 frames.], batch size: 15, lr: 1.29e-03
+2022-04-28 14:56:59,177 INFO [train.py:763] (6/8) Epoch 4, batch 3800, loss[loss=0.1812, simple_loss=0.2692, pruned_loss=0.04664, over 7278.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3137, pruned_loss=0.07431, over 1421010.13 frames.], batch size: 18, lr: 1.28e-03
+2022-04-28 14:58:05,505 INFO [train.py:763] (6/8) Epoch 4, batch 3850, loss[loss=0.2464, simple_loss=0.3297, pruned_loss=0.08153, over 7407.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3132, pruned_loss=0.07428, over 1421199.80 frames.], batch size: 21, lr: 1.28e-03
+2022-04-28 14:59:11,126 INFO [train.py:763] (6/8) Epoch 4, batch 3900, loss[loss=0.1927, simple_loss=0.2789, pruned_loss=0.05327, over 7157.00 frames.], tot_loss[loss=0.231, simple_loss=0.313, pruned_loss=0.07452, over 1417845.32 frames.], batch size: 18, lr: 1.28e-03
+2022-04-28 15:00:16,494 INFO [train.py:763] (6/8) Epoch 4, batch 3950, loss[loss=0.2505, simple_loss=0.3324, pruned_loss=0.08435, over 7418.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3134, pruned_loss=0.07492, over 1414818.21 frames.], batch size: 21, lr: 1.28e-03
+2022-04-28 15:01:21,855 INFO [train.py:763] (6/8) Epoch 4, batch 4000, loss[loss=0.2068, simple_loss=0.3087, pruned_loss=0.05246, over 7434.00 frames.], tot_loss[loss=0.2305, simple_loss=0.3132, pruned_loss=0.07392, over 1417246.87 frames.], batch size: 20, lr: 1.28e-03
+2022-04-28 15:02:27,539 INFO [train.py:763] (6/8) Epoch 4, batch 4050, loss[loss=0.2429, simple_loss=0.321, pruned_loss=0.08241, over 7217.00 frames.], tot_loss[loss=0.23, simple_loss=0.313, pruned_loss=0.07356, over 1419473.29 frames.], batch size: 21, lr: 1.28e-03
+2022-04-28 15:03:34,098 INFO [train.py:763] (6/8) Epoch 4, batch 4100, loss[loss=0.195, simple_loss=0.2842, pruned_loss=0.05288, over 7267.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3145, pruned_loss=0.07386, over 1416478.35 frames.], batch size: 18, lr: 1.28e-03
+2022-04-28 15:04:40,950 INFO [train.py:763] (6/8) Epoch 4, batch 4150, loss[loss=0.1891, simple_loss=0.291, pruned_loss=0.04364, over 7197.00 frames.], tot_loss[loss=0.231, simple_loss=0.3147, pruned_loss=0.0736, over 1415312.49 frames.], batch size: 22, lr: 1.27e-03
+2022-04-28 15:05:47,259 INFO [train.py:763] (6/8) Epoch 4, batch 4200, loss[loss=0.2151, simple_loss=0.2907, pruned_loss=0.06973, over 7143.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3155, pruned_loss=0.07465, over 1413410.88 frames.], batch size: 17, lr: 1.27e-03
+2022-04-28 15:06:53,142 INFO [train.py:763] (6/8) Epoch 4, batch 4250, loss[loss=0.2303, simple_loss=0.3116, pruned_loss=0.07453, over 7450.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3158, pruned_loss=0.07493, over 1414838.50 frames.], batch size: 19, lr: 1.27e-03
+2022-04-28 15:07:59,508 INFO [train.py:763] (6/8) Epoch 4, batch 4300, loss[loss=0.2547, simple_loss=0.3381, pruned_loss=0.08563, over 7144.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3163, pruned_loss=0.07528, over 1414978.50 frames.], batch size: 20, lr: 1.27e-03
+2022-04-28 15:09:04,574 INFO [train.py:763] (6/8) Epoch 4, batch 4350, loss[loss=0.2529, simple_loss=0.341, pruned_loss=0.08239, over 7410.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3163, pruned_loss=0.07497, over 1413946.33 frames.], batch size: 21, lr: 1.27e-03
+2022-04-28 15:10:09,735 INFO [train.py:763] (6/8) Epoch 4, batch 4400, loss[loss=0.2085, simple_loss=0.3079, pruned_loss=0.05451, over 7264.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3157, pruned_loss=0.07447, over 1408904.85 frames.], batch size: 19, lr: 1.27e-03
+2022-04-28 15:11:14,751 INFO [train.py:763] (6/8) Epoch 4, batch 4450, loss[loss=0.247, simple_loss=0.3249, pruned_loss=0.08458, over 6777.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3161, pruned_loss=0.075, over 1402480.96 frames.], batch size: 31, lr: 1.27e-03
+2022-04-28 15:12:19,725 INFO [train.py:763] (6/8) Epoch 4, batch 4500, loss[loss=0.2592, simple_loss=0.3361, pruned_loss=0.09116, over 4996.00 frames.], tot_loss[loss=0.2355, simple_loss=0.3185, pruned_loss=0.0762, over 1392132.78 frames.], batch size: 54, lr: 1.27e-03
+2022-04-28 15:13:25,333 INFO [train.py:763] (6/8) Epoch 4, batch 4550, loss[loss=0.2617, simple_loss=0.3254, pruned_loss=0.09903, over 5343.00 frames.], tot_loss[loss=0.2413, simple_loss=0.322, pruned_loss=0.08032, over 1337434.40 frames.], batch size: 53, lr: 1.26e-03
+2022-04-28 15:14:53,620 INFO [train.py:763] (6/8) Epoch 5, batch 0, loss[loss=0.2183, simple_loss=0.2981, pruned_loss=0.06928, over 7155.00 frames.], tot_loss[loss=0.2183, simple_loss=0.2981, pruned_loss=0.06928, over 7155.00 frames.], batch size: 19, lr: 1.21e-03
+2022-04-28 15:15:59,881 INFO [train.py:763] (6/8) Epoch 5, batch 50, loss[loss=0.2626, simple_loss=0.3275, pruned_loss=0.09881, over 4898.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3106, pruned_loss=0.07123, over 318399.27 frames.], batch size: 52, lr: 1.21e-03
+2022-04-28 15:17:05,485 INFO [train.py:763] (6/8) Epoch 5, batch 100, loss[loss=0.2052, simple_loss=0.2936, pruned_loss=0.0584, over 7140.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3132, pruned_loss=0.07163, over 560698.94 frames.], batch size: 20, lr: 1.21e-03
+2022-04-28 15:18:11,204 INFO [train.py:763] (6/8) Epoch 5, batch 150, loss[loss=0.242, simple_loss=0.3287, pruned_loss=0.0777, over 6678.00 frames.], tot_loss[loss=0.2276, simple_loss=0.312, pruned_loss=0.07158, over 749399.36 frames.], batch size: 31, lr: 1.21e-03
+2022-04-28 15:19:17,539 INFO [train.py:763] (6/8) Epoch 5, batch 200, loss[loss=0.2074, simple_loss=0.2866, pruned_loss=0.06404, over 7419.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3101, pruned_loss=0.07013, over 898930.88 frames.], batch size: 18, lr: 1.21e-03
+2022-04-28 15:20:23,020 INFO [train.py:763] (6/8) Epoch 5, batch 250, loss[loss=0.2497, simple_loss=0.3304, pruned_loss=0.08444, over 7323.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3105, pruned_loss=0.07, over 1019279.20 frames.], batch size: 22, lr: 1.21e-03
+2022-04-28 15:21:29,013 INFO [train.py:763] (6/8) Epoch 5, batch 300, loss[loss=0.2177, simple_loss=0.3106, pruned_loss=0.06235, over 7228.00 frames.], tot_loss[loss=0.225, simple_loss=0.3103, pruned_loss=0.06979, over 1111890.04 frames.], batch size: 20, lr: 1.21e-03
+2022-04-28 15:22:35,198 INFO [train.py:763] (6/8) Epoch 5, batch 350, loss[loss=0.2009, simple_loss=0.2947, pruned_loss=0.05356, over 7322.00 frames.], tot_loss[loss=0.2239, simple_loss=0.3095, pruned_loss=0.06913, over 1185718.03 frames.], batch size: 20, lr: 1.20e-03
+2022-04-28 15:23:40,935 INFO [train.py:763] (6/8) Epoch 5, batch 400, loss[loss=0.2196, simple_loss=0.3075, pruned_loss=0.06583, over 7379.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3106, pruned_loss=0.07029, over 1236993.37 frames.], batch size: 23, lr: 1.20e-03
+2022-04-28 15:24:46,897 INFO [train.py:763] (6/8) Epoch 5, batch 450, loss[loss=0.1934, simple_loss=0.2791, pruned_loss=0.05378, over 7232.00 frames.], tot_loss[loss=0.2255, simple_loss=0.3104, pruned_loss=0.07035, over 1280029.90 frames.], batch size: 16, lr: 1.20e-03
+2022-04-28 15:25:52,439 INFO [train.py:763] (6/8) Epoch 5, batch 500, loss[loss=0.2861, simple_loss=0.3515, pruned_loss=0.1103, over 5189.00 frames.], tot_loss[loss=0.2262, simple_loss=0.311, pruned_loss=0.0707, over 1310620.87 frames.], batch size: 53, lr: 1.20e-03
+2022-04-28 15:26:57,644 INFO [train.py:763] (6/8) Epoch 5, batch 550, loss[loss=0.2598, simple_loss=0.3451, pruned_loss=0.08728, over 6626.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3111, pruned_loss=0.07105, over 1334175.12 frames.], batch size: 38, lr: 1.20e-03
+2022-04-28 15:28:04,520 INFO [train.py:763] (6/8) Epoch 5, batch 600, loss[loss=0.2263, simple_loss=0.3228, pruned_loss=0.06494, over 7145.00 frames.], tot_loss[loss=0.225, simple_loss=0.3094, pruned_loss=0.07029, over 1352923.22 frames.], batch size: 20, lr: 1.20e-03
+2022-04-28 15:29:09,668 INFO [train.py:763] (6/8) Epoch 5, batch 650, loss[loss=0.1966, simple_loss=0.2956, pruned_loss=0.04881, over 7416.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3095, pruned_loss=0.07053, over 1367283.90 frames.], batch size: 21, lr: 1.20e-03
+2022-04-28 15:30:15,011 INFO [train.py:763] (6/8) Epoch 5, batch 700, loss[loss=0.2021, simple_loss=0.2805, pruned_loss=0.06186, over 7242.00 frames.], tot_loss[loss=0.2243, simple_loss=0.309, pruned_loss=0.06984, over 1379933.18 frames.], batch size: 16, lr: 1.20e-03
+2022-04-28 15:31:20,300 INFO [train.py:763] (6/8) Epoch 5, batch 750, loss[loss=0.2439, simple_loss=0.3315, pruned_loss=0.07814, over 7229.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3103, pruned_loss=0.07048, over 1389333.91 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:32:25,892 INFO [train.py:763] (6/8) Epoch 5, batch 800, loss[loss=0.2536, simple_loss=0.3386, pruned_loss=0.08432, over 7220.00 frames.], tot_loss[loss=0.225, simple_loss=0.3098, pruned_loss=0.07016, over 1399648.53 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:33:31,215 INFO [train.py:763] (6/8) Epoch 5, batch 850, loss[loss=0.2389, simple_loss=0.3274, pruned_loss=0.07521, over 7194.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3106, pruned_loss=0.07047, over 1404327.08 frames.], batch size: 23, lr: 1.19e-03
+2022-04-28 15:34:36,544 INFO [train.py:763] (6/8) Epoch 5, batch 900, loss[loss=0.2015, simple_loss=0.2915, pruned_loss=0.05572, over 7414.00 frames.], tot_loss[loss=0.2266, simple_loss=0.311, pruned_loss=0.07116, over 1405794.61 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:35:42,333 INFO [train.py:763] (6/8) Epoch 5, batch 950, loss[loss=0.1955, simple_loss=0.2804, pruned_loss=0.05532, over 7125.00 frames.], tot_loss[loss=0.2264, simple_loss=0.3109, pruned_loss=0.07092, over 1406612.44 frames.], batch size: 17, lr: 1.19e-03
+2022-04-28 15:36:47,763 INFO [train.py:763] (6/8) Epoch 5, batch 1000, loss[loss=0.2199, simple_loss=0.316, pruned_loss=0.06192, over 7402.00 frames.], tot_loss[loss=0.227, simple_loss=0.3113, pruned_loss=0.07131, over 1408985.18 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:37:53,892 INFO [train.py:763] (6/8) Epoch 5, batch 1050, loss[loss=0.201, simple_loss=0.2942, pruned_loss=0.05383, over 7327.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3113, pruned_loss=0.07177, over 1414019.55 frames.], batch size: 20, lr: 1.19e-03
+2022-04-28 15:39:10,233 INFO [train.py:763] (6/8) Epoch 5, batch 1100, loss[loss=0.2237, simple_loss=0.3158, pruned_loss=0.06577, over 7325.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3111, pruned_loss=0.0716, over 1409094.51 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:40:16,806 INFO [train.py:763] (6/8) Epoch 5, batch 1150, loss[loss=0.191, simple_loss=0.2843, pruned_loss=0.0488, over 7160.00 frames.], tot_loss[loss=0.2263, simple_loss=0.311, pruned_loss=0.07084, over 1414410.09 frames.], batch size: 20, lr: 1.19e-03
+2022-04-28 15:41:22,503 INFO [train.py:763] (6/8) Epoch 5, batch 1200, loss[loss=0.2105, simple_loss=0.2914, pruned_loss=0.0648, over 7179.00 frames.], tot_loss[loss=0.2257, simple_loss=0.3103, pruned_loss=0.07053, over 1414654.60 frames.], batch size: 26, lr: 1.18e-03
+2022-04-28 15:42:28,995 INFO [train.py:763] (6/8) Epoch 5, batch 1250, loss[loss=0.2302, simple_loss=0.3254, pruned_loss=0.06747, over 7139.00 frames.], tot_loss[loss=0.2264, simple_loss=0.3109, pruned_loss=0.07091, over 1413530.12 frames.], batch size: 20, lr: 1.18e-03
+2022-04-28 15:43:36,003 INFO [train.py:763] (6/8) Epoch 5, batch 1300, loss[loss=0.2372, simple_loss=0.3158, pruned_loss=0.07931, over 7359.00 frames.], tot_loss[loss=0.225, simple_loss=0.3093, pruned_loss=0.07034, over 1411682.71 frames.], batch size: 19, lr: 1.18e-03
+2022-04-28 15:44:42,296 INFO [train.py:763] (6/8) Epoch 5, batch 1350, loss[loss=0.2702, simple_loss=0.3584, pruned_loss=0.09099, over 7060.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3091, pruned_loss=0.07009, over 1415219.21 frames.], batch size: 28, lr: 1.18e-03
+2022-04-28 15:45:48,505 INFO [train.py:763] (6/8) Epoch 5, batch 1400, loss[loss=0.2247, simple_loss=0.3083, pruned_loss=0.07054, over 7331.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3088, pruned_loss=0.06973, over 1418431.51 frames.], batch size: 20, lr: 1.18e-03
+2022-04-28 15:46:53,766 INFO [train.py:763] (6/8) Epoch 5, batch 1450, loss[loss=0.2411, simple_loss=0.3258, pruned_loss=0.07821, over 7435.00 frames.], tot_loss[loss=0.2243, simple_loss=0.3088, pruned_loss=0.06992, over 1419671.50 frames.], batch size: 20, lr: 1.18e-03
+2022-04-28 15:47:59,050 INFO [train.py:763] (6/8) Epoch 5, batch 1500, loss[loss=0.2214, simple_loss=0.301, pruned_loss=0.07092, over 7149.00 frames.], tot_loss[loss=0.2243, simple_loss=0.3088, pruned_loss=0.06992, over 1419870.92 frames.], batch size: 20, lr: 1.18e-03
+2022-04-28 15:49:04,609 INFO [train.py:763] (6/8) Epoch 5, batch 1550, loss[loss=0.1846, simple_loss=0.2649, pruned_loss=0.05216, over 7279.00 frames.], tot_loss[loss=0.224, simple_loss=0.3091, pruned_loss=0.06942, over 1421567.65 frames.], batch size: 17, lr: 1.18e-03
+2022-04-28 15:50:09,901 INFO [train.py:763] (6/8) Epoch 5, batch 1600, loss[loss=0.2345, simple_loss=0.3091, pruned_loss=0.07993, over 7428.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3083, pruned_loss=0.06913, over 1414868.95 frames.], batch size: 20, lr: 1.17e-03
+2022-04-28 15:51:15,389 INFO [train.py:763] (6/8) Epoch 5, batch 1650, loss[loss=0.2516, simple_loss=0.3394, pruned_loss=0.08189, over 7299.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3078, pruned_loss=0.06859, over 1415333.61 frames.], batch size: 25, lr: 1.17e-03
+2022-04-28 15:52:21,516 INFO [train.py:763] (6/8) Epoch 5, batch 1700, loss[loss=0.2456, simple_loss=0.3258, pruned_loss=0.08267, over 7213.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3085, pruned_loss=0.06935, over 1414139.37 frames.], batch size: 22, lr: 1.17e-03
+2022-04-28 15:53:26,979 INFO [train.py:763] (6/8) Epoch 5, batch 1750, loss[loss=0.2007, simple_loss=0.2771, pruned_loss=0.06217, over 7280.00 frames.], tot_loss[loss=0.2241, simple_loss=0.309, pruned_loss=0.06956, over 1411083.24 frames.], batch size: 18, lr: 1.17e-03
+2022-04-28 15:54:32,247 INFO [train.py:763] (6/8) Epoch 5, batch 1800, loss[loss=0.2456, simple_loss=0.3212, pruned_loss=0.08497, over 5296.00 frames.], tot_loss[loss=0.2241, simple_loss=0.3091, pruned_loss=0.06955, over 1412389.29 frames.], batch size: 52, lr: 1.17e-03
+2022-04-28 15:55:37,878 INFO [train.py:763] (6/8) Epoch 5, batch 1850, loss[loss=0.2182, simple_loss=0.3068, pruned_loss=0.06486, over 7162.00 frames.], tot_loss[loss=0.224, simple_loss=0.3088, pruned_loss=0.06961, over 1416685.51 frames.], batch size: 18, lr: 1.17e-03
+2022-04-28 15:56:43,279 INFO [train.py:763] (6/8) Epoch 5, batch 1900, loss[loss=0.1919, simple_loss=0.272, pruned_loss=0.05587, over 7146.00 frames.], tot_loss[loss=0.2235, simple_loss=0.309, pruned_loss=0.06904, over 1416101.74 frames.], batch size: 17, lr: 1.17e-03
+2022-04-28 15:57:48,605 INFO [train.py:763] (6/8) Epoch 5, batch 1950, loss[loss=0.2336, simple_loss=0.3337, pruned_loss=0.06677, over 7111.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3094, pruned_loss=0.06892, over 1420203.43 frames.], batch size: 21, lr: 1.17e-03
+2022-04-28 15:58:54,744 INFO [train.py:763] (6/8) Epoch 5, batch 2000, loss[loss=0.2136, simple_loss=0.2892, pruned_loss=0.06901, over 7257.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3092, pruned_loss=0.06922, over 1423398.85 frames.], batch size: 18, lr: 1.17e-03
+2022-04-28 15:59:59,955 INFO [train.py:763] (6/8) Epoch 5, batch 2050, loss[loss=0.2231, simple_loss=0.3156, pruned_loss=0.06526, over 7021.00 frames.], tot_loss[loss=0.2237, simple_loss=0.3093, pruned_loss=0.06906, over 1423138.75 frames.], batch size: 28, lr: 1.16e-03
+2022-04-28 16:01:06,585 INFO [train.py:763] (6/8) Epoch 5, batch 2100, loss[loss=0.2517, simple_loss=0.3312, pruned_loss=0.08611, over 6159.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3092, pruned_loss=0.06899, over 1424685.29 frames.], batch size: 37, lr: 1.16e-03
+2022-04-28 16:02:12,119 INFO [train.py:763] (6/8) Epoch 5, batch 2150, loss[loss=0.221, simple_loss=0.2944, pruned_loss=0.07376, over 7143.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3085, pruned_loss=0.06864, over 1429954.09 frames.], batch size: 20, lr: 1.16e-03
+2022-04-28 16:03:17,459 INFO [train.py:763] (6/8) Epoch 5, batch 2200, loss[loss=0.2326, simple_loss=0.3184, pruned_loss=0.07339, over 7130.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3092, pruned_loss=0.06958, over 1426002.92 frames.], batch size: 20, lr: 1.16e-03
+2022-04-28 16:04:22,915 INFO [train.py:763] (6/8) Epoch 5, batch 2250, loss[loss=0.199, simple_loss=0.29, pruned_loss=0.05396, over 7368.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3098, pruned_loss=0.07002, over 1424929.59 frames.], batch size: 19, lr: 1.16e-03
+2022-04-28 16:05:29,059 INFO [train.py:763] (6/8) Epoch 5, batch 2300, loss[loss=0.2322, simple_loss=0.3142, pruned_loss=0.07513, over 7288.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3096, pruned_loss=0.07046, over 1421994.05 frames.], batch size: 24, lr: 1.16e-03
+2022-04-28 16:06:35,244 INFO [train.py:763] (6/8) Epoch 5, batch 2350, loss[loss=0.2257, simple_loss=0.3165, pruned_loss=0.06744, over 7219.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3095, pruned_loss=0.07065, over 1421347.45 frames.], batch size: 21, lr: 1.16e-03
+2022-04-28 16:07:41,477 INFO [train.py:763] (6/8) Epoch 5, batch 2400, loss[loss=0.2019, simple_loss=0.286, pruned_loss=0.05888, over 7335.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3087, pruned_loss=0.07043, over 1421880.24 frames.], batch size: 20, lr: 1.16e-03
+2022-04-28 16:08:47,666 INFO [train.py:763] (6/8) Epoch 5, batch 2450, loss[loss=0.2078, simple_loss=0.289, pruned_loss=0.0633, over 7191.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3076, pruned_loss=0.06971, over 1421474.52 frames.], batch size: 16, lr: 1.16e-03
+2022-04-28 16:09:52,954 INFO [train.py:763] (6/8) Epoch 5, batch 2500, loss[loss=0.2121, simple_loss=0.2983, pruned_loss=0.06297, over 7329.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3079, pruned_loss=0.06955, over 1421121.70 frames.], batch size: 22, lr: 1.15e-03
+2022-04-28 16:10:59,312 INFO [train.py:763] (6/8) Epoch 5, batch 2550, loss[loss=0.1929, simple_loss=0.2709, pruned_loss=0.05743, over 6816.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3075, pruned_loss=0.06935, over 1422904.42 frames.], batch size: 15, lr: 1.15e-03
+2022-04-28 16:12:05,356 INFO [train.py:763] (6/8) Epoch 5, batch 2600, loss[loss=0.2556, simple_loss=0.349, pruned_loss=0.08112, over 7336.00 frames.], tot_loss[loss=0.223, simple_loss=0.3076, pruned_loss=0.06916, over 1425881.34 frames.], batch size: 21, lr: 1.15e-03
+2022-04-28 16:13:10,884 INFO [train.py:763] (6/8) Epoch 5, batch 2650, loss[loss=0.2204, simple_loss=0.3145, pruned_loss=0.06313, over 7298.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3088, pruned_loss=0.06936, over 1424060.04 frames.], batch size: 25, lr: 1.15e-03
+2022-04-28 16:14:16,439 INFO [train.py:763] (6/8) Epoch 5, batch 2700, loss[loss=0.1711, simple_loss=0.2579, pruned_loss=0.04222, over 7254.00 frames.], tot_loss[loss=0.2228, simple_loss=0.308, pruned_loss=0.06878, over 1426614.12 frames.], batch size: 16, lr: 1.15e-03
+2022-04-28 16:15:15,069 INFO [train.py:763] (6/8) Epoch 5, batch 2750, loss[loss=0.2593, simple_loss=0.3379, pruned_loss=0.09036, over 7233.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3089, pruned_loss=0.06931, over 1424048.16 frames.], batch size: 20, lr: 1.15e-03
+2022-04-28 16:16:11,917 INFO [train.py:763] (6/8) Epoch 5, batch 2800, loss[loss=0.2042, simple_loss=0.2979, pruned_loss=0.05526, over 7272.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3087, pruned_loss=0.06927, over 1421898.24 frames.], batch size: 18, lr: 1.15e-03
+2022-04-28 16:17:08,599 INFO [train.py:763] (6/8) Epoch 5, batch 2850, loss[loss=0.1707, simple_loss=0.2536, pruned_loss=0.04383, over 7275.00 frames.], tot_loss[loss=0.2236, simple_loss=0.309, pruned_loss=0.06905, over 1419515.19 frames.], batch size: 17, lr: 1.15e-03
+2022-04-28 16:18:06,437 INFO [train.py:763] (6/8) Epoch 5, batch 2900, loss[loss=0.2341, simple_loss=0.3184, pruned_loss=0.07489, over 6758.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3091, pruned_loss=0.06897, over 1420897.98 frames.], batch size: 31, lr: 1.15e-03
+2022-04-28 16:19:04,270 INFO [train.py:763] (6/8) Epoch 5, batch 2950, loss[loss=0.1868, simple_loss=0.2734, pruned_loss=0.05011, over 7142.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3082, pruned_loss=0.06881, over 1420596.13 frames.], batch size: 20, lr: 1.14e-03
+2022-04-28 16:19:58,152 INFO [train.py:763] (6/8) Epoch 5, batch 3000, loss[loss=0.2043, simple_loss=0.2955, pruned_loss=0.05655, over 7237.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3085, pruned_loss=0.06852, over 1420615.46 frames.], batch size: 20, lr: 1.14e-03
+2022-04-28 16:19:58,153 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-28 16:20:13,356 INFO [train.py:792] (6/8) Epoch 5, validation: loss=0.1791, simple_loss=0.2847, pruned_loss=0.03677, over 698248.00 frames.
+2022-04-28 16:21:19,341 INFO [train.py:763] (6/8) Epoch 5, batch 3050, loss[loss=0.2619, simple_loss=0.341, pruned_loss=0.09137, over 7193.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3077, pruned_loss=0.06857, over 1426300.00 frames.], batch size: 23, lr: 1.14e-03
+2022-04-28 16:22:24,940 INFO [train.py:763] (6/8) Epoch 5, batch 3100, loss[loss=0.2151, simple_loss=0.3221, pruned_loss=0.05406, over 7332.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3061, pruned_loss=0.0681, over 1423807.10 frames.], batch size: 22, lr: 1.14e-03
+2022-04-28 16:23:30,172 INFO [train.py:763] (6/8) Epoch 5, batch 3150, loss[loss=0.2192, simple_loss=0.3095, pruned_loss=0.06446, over 7207.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3075, pruned_loss=0.06775, over 1424452.59 frames.], batch size: 23, lr: 1.14e-03
+2022-04-28 16:24:36,690 INFO [train.py:763] (6/8) Epoch 5, batch 3200, loss[loss=0.2359, simple_loss=0.313, pruned_loss=0.07946, over 7227.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3083, pruned_loss=0.06855, over 1425451.39 frames.], batch size: 21, lr: 1.14e-03
+2022-04-28 16:25:42,635 INFO [train.py:763] (6/8) Epoch 5, batch 3250, loss[loss=0.2172, simple_loss=0.3064, pruned_loss=0.06406, over 7361.00 frames.], tot_loss[loss=0.224, simple_loss=0.3095, pruned_loss=0.06926, over 1425557.84 frames.], batch size: 19, lr: 1.14e-03
+2022-04-28 16:26:48,950 INFO [train.py:763] (6/8) Epoch 5, batch 3300, loss[loss=0.2288, simple_loss=0.3056, pruned_loss=0.07604, over 7204.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3098, pruned_loss=0.06896, over 1421633.17 frames.], batch size: 23, lr: 1.14e-03
+2022-04-28 16:27:54,261 INFO [train.py:763] (6/8) Epoch 5, batch 3350, loss[loss=0.2097, simple_loss=0.2847, pruned_loss=0.06737, over 7257.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3087, pruned_loss=0.0686, over 1425979.45 frames.], batch size: 19, lr: 1.14e-03
+2022-04-28 16:28:59,514 INFO [train.py:763] (6/8) Epoch 5, batch 3400, loss[loss=0.2748, simple_loss=0.3504, pruned_loss=0.09958, over 7286.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3082, pruned_loss=0.06864, over 1424828.32 frames.], batch size: 24, lr: 1.14e-03
+2022-04-28 16:30:05,195 INFO [train.py:763] (6/8) Epoch 5, batch 3450, loss[loss=0.2483, simple_loss=0.3389, pruned_loss=0.07885, over 7417.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3096, pruned_loss=0.06936, over 1427404.42 frames.], batch size: 21, lr: 1.13e-03
+2022-04-28 16:31:11,006 INFO [train.py:763] (6/8) Epoch 5, batch 3500, loss[loss=0.2565, simple_loss=0.3464, pruned_loss=0.08334, over 7204.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3087, pruned_loss=0.06917, over 1424021.31 frames.], batch size: 22, lr: 1.13e-03
+2022-04-28 16:32:16,131 INFO [train.py:763] (6/8) Epoch 5, batch 3550, loss[loss=0.2708, simple_loss=0.346, pruned_loss=0.09781, over 7322.00 frames.], tot_loss[loss=0.222, simple_loss=0.3074, pruned_loss=0.06831, over 1427077.57 frames.], batch size: 21, lr: 1.13e-03
+2022-04-28 16:33:21,409 INFO [train.py:763] (6/8) Epoch 5, batch 3600, loss[loss=0.2084, simple_loss=0.2886, pruned_loss=0.06413, over 7170.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3074, pruned_loss=0.06838, over 1428898.67 frames.], batch size: 18, lr: 1.13e-03
+2022-04-28 16:34:27,151 INFO [train.py:763] (6/8) Epoch 5, batch 3650, loss[loss=0.2075, simple_loss=0.2965, pruned_loss=0.05921, over 7409.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3071, pruned_loss=0.06793, over 1428143.08 frames.], batch size: 21, lr: 1.13e-03
+2022-04-28 16:35:34,112 INFO [train.py:763] (6/8) Epoch 5, batch 3700, loss[loss=0.2163, simple_loss=0.3016, pruned_loss=0.06555, over 7227.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3067, pruned_loss=0.06769, over 1426219.01 frames.], batch size: 20, lr: 1.13e-03
+2022-04-28 16:36:39,374 INFO [train.py:763] (6/8) Epoch 5, batch 3750, loss[loss=0.239, simple_loss=0.3221, pruned_loss=0.07797, over 7369.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3075, pruned_loss=0.06847, over 1423541.71 frames.], batch size: 23, lr: 1.13e-03
+2022-04-28 16:37:46,345 INFO [train.py:763] (6/8) Epoch 5, batch 3800, loss[loss=0.2409, simple_loss=0.3328, pruned_loss=0.07444, over 7236.00 frames.], tot_loss[loss=0.222, simple_loss=0.3069, pruned_loss=0.06852, over 1418760.42 frames.], batch size: 20, lr: 1.13e-03
+2022-04-28 16:38:51,771 INFO [train.py:763] (6/8) Epoch 5, batch 3850, loss[loss=0.1999, simple_loss=0.292, pruned_loss=0.05388, over 7436.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3086, pruned_loss=0.06906, over 1419434.04 frames.], batch size: 20, lr: 1.13e-03
+2022-04-28 16:39:57,101 INFO [train.py:763] (6/8) Epoch 5, batch 3900, loss[loss=0.2195, simple_loss=0.3048, pruned_loss=0.06709, over 7409.00 frames.], tot_loss[loss=0.2239, simple_loss=0.3092, pruned_loss=0.06927, over 1423971.89 frames.], batch size: 18, lr: 1.13e-03
+2022-04-28 16:41:04,044 INFO [train.py:763] (6/8) Epoch 5, batch 3950, loss[loss=0.2475, simple_loss=0.3331, pruned_loss=0.08093, over 7295.00 frames.], tot_loss[loss=0.2217, simple_loss=0.3072, pruned_loss=0.06814, over 1423186.86 frames.], batch size: 24, lr: 1.12e-03
+2022-04-28 16:42:10,958 INFO [train.py:763] (6/8) Epoch 5, batch 4000, loss[loss=0.2349, simple_loss=0.324, pruned_loss=0.07283, over 7200.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3073, pruned_loss=0.06778, over 1426211.00 frames.], batch size: 23, lr: 1.12e-03
+2022-04-28 16:43:18,250 INFO [train.py:763] (6/8) Epoch 5, batch 4050, loss[loss=0.2855, simple_loss=0.3632, pruned_loss=0.1039, over 7267.00 frames.], tot_loss[loss=0.2212, simple_loss=0.3075, pruned_loss=0.06749, over 1427525.88 frames.], batch size: 24, lr: 1.12e-03
+2022-04-28 16:44:25,536 INFO [train.py:763] (6/8) Epoch 5, batch 4100, loss[loss=0.2268, simple_loss=0.3019, pruned_loss=0.07584, over 7413.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3065, pruned_loss=0.06761, over 1428107.57 frames.], batch size: 18, lr: 1.12e-03
+2022-04-28 16:45:32,378 INFO [train.py:763] (6/8) Epoch 5, batch 4150, loss[loss=0.2545, simple_loss=0.3308, pruned_loss=0.0891, over 6790.00 frames.], tot_loss[loss=0.2189, simple_loss=0.3043, pruned_loss=0.06677, over 1427583.06 frames.], batch size: 31, lr: 1.12e-03
+2022-04-28 16:46:39,134 INFO [train.py:763] (6/8) Epoch 5, batch 4200, loss[loss=0.227, simple_loss=0.3189, pruned_loss=0.06757, over 7109.00 frames.], tot_loss[loss=0.2184, simple_loss=0.3037, pruned_loss=0.06658, over 1428757.27 frames.], batch size: 21, lr: 1.12e-03
+2022-04-28 16:47:45,473 INFO [train.py:763] (6/8) Epoch 5, batch 4250, loss[loss=0.2211, simple_loss=0.3142, pruned_loss=0.06404, over 7381.00 frames.], tot_loss[loss=0.2188, simple_loss=0.3038, pruned_loss=0.06689, over 1429451.15 frames.], batch size: 23, lr: 1.12e-03
+2022-04-28 16:48:52,197 INFO [train.py:763] (6/8) Epoch 5, batch 4300, loss[loss=0.1987, simple_loss=0.2877, pruned_loss=0.05488, over 7065.00 frames.], tot_loss[loss=0.219, simple_loss=0.3043, pruned_loss=0.06689, over 1425203.43 frames.], batch size: 18, lr: 1.12e-03
+2022-04-28 16:49:59,889 INFO [train.py:763] (6/8) Epoch 5, batch 4350, loss[loss=0.241, simple_loss=0.3278, pruned_loss=0.07712, over 7229.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3033, pruned_loss=0.06596, over 1424922.84 frames.], batch size: 21, lr: 1.12e-03
+2022-04-28 16:51:07,556 INFO [train.py:763] (6/8) Epoch 5, batch 4400, loss[loss=0.216, simple_loss=0.304, pruned_loss=0.06399, over 7434.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3023, pruned_loss=0.06529, over 1422634.60 frames.], batch size: 20, lr: 1.12e-03
+2022-04-28 16:52:13,250 INFO [train.py:763] (6/8) Epoch 5, batch 4450, loss[loss=0.2224, simple_loss=0.2992, pruned_loss=0.07283, over 7289.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3034, pruned_loss=0.06609, over 1409817.38 frames.], batch size: 17, lr: 1.11e-03
+2022-04-28 16:53:19,251 INFO [train.py:763] (6/8) Epoch 5, batch 4500, loss[loss=0.2434, simple_loss=0.3182, pruned_loss=0.0843, over 7232.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3012, pruned_loss=0.0659, over 1408970.51 frames.], batch size: 20, lr: 1.11e-03
+2022-04-28 16:54:23,900 INFO [train.py:763] (6/8) Epoch 5, batch 4550, loss[loss=0.2923, simple_loss=0.3744, pruned_loss=0.1051, over 5387.00 frames.], tot_loss[loss=0.222, simple_loss=0.305, pruned_loss=0.06948, over 1360550.07 frames.], batch size: 52, lr: 1.11e-03
+2022-04-28 16:55:51,899 INFO [train.py:763] (6/8) Epoch 6, batch 0, loss[loss=0.2097, simple_loss=0.2892, pruned_loss=0.06513, over 7407.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2892, pruned_loss=0.06513, over 7407.00 frames.], batch size: 18, lr: 1.07e-03
+2022-04-28 16:56:58,101 INFO [train.py:763] (6/8) Epoch 6, batch 50, loss[loss=0.1864, simple_loss=0.2841, pruned_loss=0.04439, over 7397.00 frames.], tot_loss[loss=0.2124, simple_loss=0.2998, pruned_loss=0.06255, over 322499.02 frames.], batch size: 18, lr: 1.07e-03
+2022-04-28 16:58:04,028 INFO [train.py:763] (6/8) Epoch 6, batch 100, loss[loss=0.1905, simple_loss=0.2847, pruned_loss=0.04816, over 7151.00 frames.], tot_loss[loss=0.2135, simple_loss=0.3008, pruned_loss=0.06315, over 566510.92 frames.], batch size: 19, lr: 1.06e-03
+2022-04-28 16:59:09,770 INFO [train.py:763] (6/8) Epoch 6, batch 150, loss[loss=0.2013, simple_loss=0.2942, pruned_loss=0.05415, over 7168.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3031, pruned_loss=0.06386, over 756604.46 frames.], batch size: 19, lr: 1.06e-03
+2022-04-28 17:00:15,500 INFO [train.py:763] (6/8) Epoch 6, batch 200, loss[loss=0.195, simple_loss=0.3005, pruned_loss=0.04476, over 7375.00 frames.], tot_loss[loss=0.2157, simple_loss=0.303, pruned_loss=0.06421, over 906701.88 frames.], batch size: 23, lr: 1.06e-03
+2022-04-28 17:01:29,829 INFO [train.py:763] (6/8) Epoch 6, batch 250, loss[loss=0.2245, simple_loss=0.3214, pruned_loss=0.06384, over 7136.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3046, pruned_loss=0.06527, over 1020935.40 frames.], batch size: 20, lr: 1.06e-03
+2022-04-28 17:02:45,515 INFO [train.py:763] (6/8) Epoch 6, batch 300, loss[loss=0.2051, simple_loss=0.2827, pruned_loss=0.06378, over 6816.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3055, pruned_loss=0.06591, over 1107141.74 frames.], batch size: 15, lr: 1.06e-03
+2022-04-28 17:03:59,807 INFO [train.py:763] (6/8) Epoch 6, batch 350, loss[loss=0.2129, simple_loss=0.3062, pruned_loss=0.05981, over 7108.00 frames.], tot_loss[loss=0.2184, simple_loss=0.3054, pruned_loss=0.06572, over 1177620.29 frames.], batch size: 21, lr: 1.06e-03
+2022-04-28 17:05:05,099 INFO [train.py:763] (6/8) Epoch 6, batch 400, loss[loss=0.1652, simple_loss=0.2555, pruned_loss=0.03746, over 7166.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3047, pruned_loss=0.06508, over 1230230.12 frames.], batch size: 18, lr: 1.06e-03
+2022-04-28 17:06:20,584 INFO [train.py:763] (6/8) Epoch 6, batch 450, loss[loss=0.1958, simple_loss=0.2902, pruned_loss=0.0507, over 7364.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3047, pruned_loss=0.06506, over 1276326.85 frames.], batch size: 19, lr: 1.06e-03
+2022-04-28 17:07:44,117 INFO [train.py:763] (6/8) Epoch 6, batch 500, loss[loss=0.2204, simple_loss=0.3023, pruned_loss=0.0692, over 6491.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3051, pruned_loss=0.06551, over 1305546.07 frames.], batch size: 38, lr: 1.06e-03
+2022-04-28 17:08:59,115 INFO [train.py:763] (6/8) Epoch 6, batch 550, loss[loss=0.2286, simple_loss=0.3189, pruned_loss=0.06917, over 7118.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3044, pruned_loss=0.06487, over 1330416.55 frames.], batch size: 21, lr: 1.06e-03
+2022-04-28 17:10:13,646 INFO [train.py:763] (6/8) Epoch 6, batch 600, loss[loss=0.2417, simple_loss=0.3312, pruned_loss=0.07612, over 7099.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3055, pruned_loss=0.06545, over 1349080.04 frames.], batch size: 28, lr: 1.06e-03
+2022-04-28 17:11:19,492 INFO [train.py:763] (6/8) Epoch 6, batch 650, loss[loss=0.2565, simple_loss=0.3282, pruned_loss=0.09245, over 5115.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3041, pruned_loss=0.06458, over 1365266.91 frames.], batch size: 54, lr: 1.05e-03
+2022-04-28 17:12:25,223 INFO [train.py:763] (6/8) Epoch 6, batch 700, loss[loss=0.1967, simple_loss=0.2783, pruned_loss=0.05751, over 7157.00 frames.], tot_loss[loss=0.2169, simple_loss=0.3043, pruned_loss=0.06477, over 1379362.74 frames.], batch size: 18, lr: 1.05e-03
+2022-04-28 17:13:31,499 INFO [train.py:763] (6/8) Epoch 6, batch 750, loss[loss=0.2313, simple_loss=0.3163, pruned_loss=0.0732, over 6755.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3032, pruned_loss=0.06396, over 1392732.28 frames.], batch size: 31, lr: 1.05e-03
+2022-04-28 17:14:37,094 INFO [train.py:763] (6/8) Epoch 6, batch 800, loss[loss=0.1786, simple_loss=0.2857, pruned_loss=0.03578, over 7322.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3021, pruned_loss=0.06385, over 1392632.73 frames.], batch size: 20, lr: 1.05e-03
+2022-04-28 17:15:43,494 INFO [train.py:763] (6/8) Epoch 6, batch 850, loss[loss=0.2462, simple_loss=0.338, pruned_loss=0.07717, over 7287.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3026, pruned_loss=0.06407, over 1399387.23 frames.], batch size: 24, lr: 1.05e-03
+2022-04-28 17:16:48,959 INFO [train.py:763] (6/8) Epoch 6, batch 900, loss[loss=0.2485, simple_loss=0.3462, pruned_loss=0.07543, over 7366.00 frames.], tot_loss[loss=0.216, simple_loss=0.3031, pruned_loss=0.06447, over 1404324.03 frames.], batch size: 23, lr: 1.05e-03
+2022-04-28 17:17:54,047 INFO [train.py:763] (6/8) Epoch 6, batch 950, loss[loss=0.2357, simple_loss=0.3235, pruned_loss=0.07389, over 7377.00 frames.], tot_loss[loss=0.218, simple_loss=0.3051, pruned_loss=0.06545, over 1408359.11 frames.], batch size: 23, lr: 1.05e-03
+2022-04-28 17:18:59,568 INFO [train.py:763] (6/8) Epoch 6, batch 1000, loss[loss=0.2113, simple_loss=0.312, pruned_loss=0.05532, over 7394.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3039, pruned_loss=0.06517, over 1408794.23 frames.], batch size: 23, lr: 1.05e-03
+2022-04-28 17:20:06,064 INFO [train.py:763] (6/8) Epoch 6, batch 1050, loss[loss=0.1927, simple_loss=0.2787, pruned_loss=0.05337, over 7165.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3026, pruned_loss=0.06415, over 1415623.08 frames.], batch size: 19, lr: 1.05e-03
+2022-04-28 17:21:12,155 INFO [train.py:763] (6/8) Epoch 6, batch 1100, loss[loss=0.236, simple_loss=0.331, pruned_loss=0.07049, over 7307.00 frames.], tot_loss[loss=0.2158, simple_loss=0.303, pruned_loss=0.06431, over 1419886.84 frames.], batch size: 25, lr: 1.05e-03
+2022-04-28 17:22:18,728 INFO [train.py:763] (6/8) Epoch 6, batch 1150, loss[loss=0.1731, simple_loss=0.2681, pruned_loss=0.03909, over 7152.00 frames.], tot_loss[loss=0.2157, simple_loss=0.303, pruned_loss=0.06419, over 1418080.60 frames.], batch size: 17, lr: 1.05e-03
+2022-04-28 17:23:26,114 INFO [train.py:763] (6/8) Epoch 6, batch 1200, loss[loss=0.2188, simple_loss=0.2894, pruned_loss=0.07411, over 7215.00 frames.], tot_loss[loss=0.216, simple_loss=0.3031, pruned_loss=0.06444, over 1413092.66 frames.], batch size: 16, lr: 1.04e-03
+2022-04-28 17:24:33,317 INFO [train.py:763] (6/8) Epoch 6, batch 1250, loss[loss=0.2122, simple_loss=0.3113, pruned_loss=0.05655, over 7221.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3022, pruned_loss=0.06416, over 1414027.81 frames.], batch size: 20, lr: 1.04e-03
+2022-04-28 17:25:39,228 INFO [train.py:763] (6/8) Epoch 6, batch 1300, loss[loss=0.1848, simple_loss=0.2593, pruned_loss=0.0551, over 7283.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3019, pruned_loss=0.06368, over 1414885.84 frames.], batch size: 17, lr: 1.04e-03
+2022-04-28 17:26:44,445 INFO [train.py:763] (6/8) Epoch 6, batch 1350, loss[loss=0.2366, simple_loss=0.3281, pruned_loss=0.07253, over 7424.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3023, pruned_loss=0.06364, over 1420456.64 frames.], batch size: 21, lr: 1.04e-03
+2022-04-28 17:27:49,619 INFO [train.py:763] (6/8) Epoch 6, batch 1400, loss[loss=0.1994, simple_loss=0.2858, pruned_loss=0.05654, over 7173.00 frames.], tot_loss[loss=0.2162, simple_loss=0.3033, pruned_loss=0.06451, over 1418685.30 frames.], batch size: 19, lr: 1.04e-03
+2022-04-28 17:28:55,364 INFO [train.py:763] (6/8) Epoch 6, batch 1450, loss[loss=0.2355, simple_loss=0.3262, pruned_loss=0.07234, over 6713.00 frames.], tot_loss[loss=0.2159, simple_loss=0.303, pruned_loss=0.06439, over 1418423.86 frames.], batch size: 31, lr: 1.04e-03
+2022-04-28 17:30:00,749 INFO [train.py:763] (6/8) Epoch 6, batch 1500, loss[loss=0.1976, simple_loss=0.2937, pruned_loss=0.05073, over 7420.00 frames.], tot_loss[loss=0.2151, simple_loss=0.3022, pruned_loss=0.064, over 1422138.28 frames.], batch size: 21, lr: 1.04e-03
+2022-04-28 17:31:05,971 INFO [train.py:763] (6/8) Epoch 6, batch 1550, loss[loss=0.2126, simple_loss=0.3089, pruned_loss=0.05815, over 7203.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3028, pruned_loss=0.06441, over 1415934.94 frames.], batch size: 26, lr: 1.04e-03
+2022-04-28 17:32:11,544 INFO [train.py:763] (6/8) Epoch 6, batch 1600, loss[loss=0.2186, simple_loss=0.3129, pruned_loss=0.06212, over 7107.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3029, pruned_loss=0.06405, over 1422486.16 frames.], batch size: 21, lr: 1.04e-03
+2022-04-28 17:33:16,938 INFO [train.py:763] (6/8) Epoch 6, batch 1650, loss[loss=0.1862, simple_loss=0.2786, pruned_loss=0.04686, over 7454.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3022, pruned_loss=0.0641, over 1417739.51 frames.], batch size: 19, lr: 1.04e-03
+2022-04-28 17:34:24,125 INFO [train.py:763] (6/8) Epoch 6, batch 1700, loss[loss=0.2268, simple_loss=0.3127, pruned_loss=0.07048, over 7226.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3013, pruned_loss=0.0639, over 1416283.14 frames.], batch size: 22, lr: 1.04e-03
+2022-04-28 17:35:30,122 INFO [train.py:763] (6/8) Epoch 6, batch 1750, loss[loss=0.2209, simple_loss=0.3141, pruned_loss=0.06385, over 7336.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3018, pruned_loss=0.06427, over 1412197.84 frames.], batch size: 22, lr: 1.04e-03
+2022-04-28 17:36:35,230 INFO [train.py:763] (6/8) Epoch 6, batch 1800, loss[loss=0.2232, simple_loss=0.3131, pruned_loss=0.06671, over 7265.00 frames.], tot_loss[loss=0.2159, simple_loss=0.303, pruned_loss=0.06441, over 1414716.03 frames.], batch size: 25, lr: 1.03e-03
+2022-04-28 17:37:41,014 INFO [train.py:763] (6/8) Epoch 6, batch 1850, loss[loss=0.1729, simple_loss=0.2674, pruned_loss=0.03923, over 7002.00 frames.], tot_loss[loss=0.2158, simple_loss=0.303, pruned_loss=0.06428, over 1417398.54 frames.], batch size: 16, lr: 1.03e-03
+2022-04-28 17:38:46,203 INFO [train.py:763] (6/8) Epoch 6, batch 1900, loss[loss=0.1751, simple_loss=0.2647, pruned_loss=0.04278, over 7065.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3019, pruned_loss=0.06386, over 1414284.22 frames.], batch size: 18, lr: 1.03e-03
+2022-04-28 17:39:52,707 INFO [train.py:763] (6/8) Epoch 6, batch 1950, loss[loss=0.231, simple_loss=0.3048, pruned_loss=0.07861, over 7275.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3019, pruned_loss=0.06463, over 1418232.50 frames.], batch size: 18, lr: 1.03e-03
+2022-04-28 17:40:59,183 INFO [train.py:763] (6/8) Epoch 6, batch 2000, loss[loss=0.2497, simple_loss=0.3266, pruned_loss=0.08638, over 7268.00 frames.], tot_loss[loss=0.216, simple_loss=0.3024, pruned_loss=0.06483, over 1418140.78 frames.], batch size: 25, lr: 1.03e-03
+2022-04-28 17:42:06,098 INFO [train.py:763] (6/8) Epoch 6, batch 2050, loss[loss=0.2127, simple_loss=0.3046, pruned_loss=0.06046, over 7295.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3024, pruned_loss=0.06424, over 1414645.26 frames.], batch size: 24, lr: 1.03e-03
+2022-04-28 17:43:12,554 INFO [train.py:763] (6/8) Epoch 6, batch 2100, loss[loss=0.186, simple_loss=0.2713, pruned_loss=0.05034, over 7005.00 frames.], tot_loss[loss=0.216, simple_loss=0.3029, pruned_loss=0.06455, over 1417704.61 frames.], batch size: 16, lr: 1.03e-03
+2022-04-28 17:44:19,365 INFO [train.py:763] (6/8) Epoch 6, batch 2150, loss[loss=0.1908, simple_loss=0.287, pruned_loss=0.04725, over 7410.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3032, pruned_loss=0.06404, over 1422952.83 frames.], batch size: 21, lr: 1.03e-03
+2022-04-28 17:45:25,696 INFO [train.py:763] (6/8) Epoch 6, batch 2200, loss[loss=0.1915, simple_loss=0.2668, pruned_loss=0.05807, over 7136.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3027, pruned_loss=0.06429, over 1422033.79 frames.], batch size: 17, lr: 1.03e-03
+2022-04-28 17:46:32,105 INFO [train.py:763] (6/8) Epoch 6, batch 2250, loss[loss=0.2059, simple_loss=0.2848, pruned_loss=0.0635, over 7293.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3035, pruned_loss=0.06491, over 1417553.31 frames.], batch size: 17, lr: 1.03e-03
+2022-04-28 17:47:38,687 INFO [train.py:763] (6/8) Epoch 6, batch 2300, loss[loss=0.2283, simple_loss=0.3158, pruned_loss=0.07046, over 7210.00 frames.], tot_loss[loss=0.216, simple_loss=0.3029, pruned_loss=0.06453, over 1420328.29 frames.], batch size: 23, lr: 1.03e-03
+2022-04-28 17:48:44,944 INFO [train.py:763] (6/8) Epoch 6, batch 2350, loss[loss=0.2197, simple_loss=0.3147, pruned_loss=0.06238, over 7406.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3025, pruned_loss=0.06448, over 1418497.45 frames.], batch size: 21, lr: 1.02e-03
+2022-04-28 17:49:50,856 INFO [train.py:763] (6/8) Epoch 6, batch 2400, loss[loss=0.1607, simple_loss=0.251, pruned_loss=0.03516, over 7264.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3018, pruned_loss=0.06397, over 1421905.23 frames.], batch size: 18, lr: 1.02e-03
+2022-04-28 17:50:56,974 INFO [train.py:763] (6/8) Epoch 6, batch 2450, loss[loss=0.2485, simple_loss=0.3332, pruned_loss=0.08191, over 7416.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3024, pruned_loss=0.06441, over 1418298.66 frames.], batch size: 21, lr: 1.02e-03
+2022-04-28 17:52:02,803 INFO [train.py:763] (6/8) Epoch 6, batch 2500, loss[loss=0.2715, simple_loss=0.3543, pruned_loss=0.09434, over 7321.00 frames.], tot_loss[loss=0.2162, simple_loss=0.303, pruned_loss=0.06473, over 1418510.07 frames.], batch size: 21, lr: 1.02e-03
+2022-04-28 17:53:08,649 INFO [train.py:763] (6/8) Epoch 6, batch 2550, loss[loss=0.2467, simple_loss=0.3265, pruned_loss=0.08343, over 7429.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3029, pruned_loss=0.06412, over 1424483.04 frames.], batch size: 20, lr: 1.02e-03
+2022-04-28 17:54:14,769 INFO [train.py:763] (6/8) Epoch 6, batch 2600, loss[loss=0.1983, simple_loss=0.2754, pruned_loss=0.06058, over 7170.00 frames.], tot_loss[loss=0.216, simple_loss=0.3031, pruned_loss=0.06448, over 1418337.40 frames.], batch size: 18, lr: 1.02e-03
+2022-04-28 17:55:21,085 INFO [train.py:763] (6/8) Epoch 6, batch 2650, loss[loss=0.1984, simple_loss=0.2841, pruned_loss=0.05635, over 7163.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3027, pruned_loss=0.06437, over 1417056.27 frames.], batch size: 18, lr: 1.02e-03
+2022-04-28 17:56:26,533 INFO [train.py:763] (6/8) Epoch 6, batch 2700, loss[loss=0.1988, simple_loss=0.282, pruned_loss=0.05783, over 6862.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3029, pruned_loss=0.0643, over 1419034.42 frames.], batch size: 15, lr: 1.02e-03
+2022-04-28 17:57:32,630 INFO [train.py:763] (6/8) Epoch 6, batch 2750, loss[loss=0.206, simple_loss=0.2821, pruned_loss=0.06497, over 7414.00 frames.], tot_loss[loss=0.2147, simple_loss=0.3023, pruned_loss=0.06352, over 1419554.38 frames.], batch size: 18, lr: 1.02e-03
+2022-04-28 17:58:39,122 INFO [train.py:763] (6/8) Epoch 6, batch 2800, loss[loss=0.1593, simple_loss=0.2486, pruned_loss=0.03496, over 7001.00 frames.], tot_loss[loss=0.2133, simple_loss=0.3006, pruned_loss=0.06306, over 1418219.48 frames.], batch size: 16, lr: 1.02e-03
+2022-04-28 17:59:46,088 INFO [train.py:763] (6/8) Epoch 6, batch 2850, loss[loss=0.2239, simple_loss=0.3031, pruned_loss=0.07239, over 7321.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2998, pruned_loss=0.06314, over 1422788.86 frames.], batch size: 21, lr: 1.02e-03
+2022-04-28 18:00:52,209 INFO [train.py:763] (6/8) Epoch 6, batch 2900, loss[loss=0.242, simple_loss=0.316, pruned_loss=0.08397, over 5259.00 frames.], tot_loss[loss=0.2135, simple_loss=0.3001, pruned_loss=0.06348, over 1424674.71 frames.], batch size: 53, lr: 1.02e-03
+2022-04-28 18:01:57,563 INFO [train.py:763] (6/8) Epoch 6, batch 2950, loss[loss=0.285, simple_loss=0.3597, pruned_loss=0.1051, over 7308.00 frames.], tot_loss[loss=0.215, simple_loss=0.3016, pruned_loss=0.06426, over 1424273.71 frames.], batch size: 25, lr: 1.01e-03
+2022-04-28 18:03:03,562 INFO [train.py:763] (6/8) Epoch 6, batch 3000, loss[loss=0.2517, simple_loss=0.3301, pruned_loss=0.08661, over 7256.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3021, pruned_loss=0.06426, over 1426549.83 frames.], batch size: 26, lr: 1.01e-03
+2022-04-28 18:03:03,563 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-28 18:03:18,817 INFO [train.py:792] (6/8) Epoch 6, validation: loss=0.1749, simple_loss=0.2793, pruned_loss=0.03525, over 698248.00 frames.
+2022-04-28 18:04:24,349 INFO [train.py:763] (6/8) Epoch 6, batch 3050, loss[loss=0.2505, simple_loss=0.338, pruned_loss=0.08144, over 7112.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3023, pruned_loss=0.06418, over 1427648.77 frames.], batch size: 26, lr: 1.01e-03
+2022-04-28 18:05:30,297 INFO [train.py:763] (6/8) Epoch 6, batch 3100, loss[loss=0.2363, simple_loss=0.3191, pruned_loss=0.07677, over 7164.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3036, pruned_loss=0.06477, over 1425028.31 frames.], batch size: 26, lr: 1.01e-03
+2022-04-28 18:06:36,922 INFO [train.py:763] (6/8) Epoch 6, batch 3150, loss[loss=0.2133, simple_loss=0.3074, pruned_loss=0.05955, over 7081.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3032, pruned_loss=0.06421, over 1428130.61 frames.], batch size: 28, lr: 1.01e-03
+2022-04-28 18:07:42,734 INFO [train.py:763] (6/8) Epoch 6, batch 3200, loss[loss=0.2429, simple_loss=0.3329, pruned_loss=0.07642, over 7343.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3046, pruned_loss=0.0648, over 1423784.21 frames.], batch size: 22, lr: 1.01e-03
+2022-04-28 18:08:48,609 INFO [train.py:763] (6/8) Epoch 6, batch 3250, loss[loss=0.2206, simple_loss=0.3115, pruned_loss=0.0648, over 7029.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3031, pruned_loss=0.06395, over 1423854.54 frames.], batch size: 28, lr: 1.01e-03
+2022-04-28 18:09:54,857 INFO [train.py:763] (6/8) Epoch 6, batch 3300, loss[loss=0.2337, simple_loss=0.3248, pruned_loss=0.07133, over 7146.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3038, pruned_loss=0.06406, over 1418911.24 frames.], batch size: 20, lr: 1.01e-03
+2022-04-28 18:11:00,642 INFO [train.py:763] (6/8) Epoch 6, batch 3350, loss[loss=0.2001, simple_loss=0.2865, pruned_loss=0.05679, over 7149.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3033, pruned_loss=0.06393, over 1420466.44 frames.], batch size: 19, lr: 1.01e-03
+2022-04-28 18:12:05,975 INFO [train.py:763] (6/8) Epoch 6, batch 3400, loss[loss=0.2195, simple_loss=0.3152, pruned_loss=0.06195, over 7121.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3037, pruned_loss=0.06401, over 1423097.02 frames.], batch size: 21, lr: 1.01e-03
+2022-04-28 18:13:11,472 INFO [train.py:763] (6/8) Epoch 6, batch 3450, loss[loss=0.2152, simple_loss=0.3048, pruned_loss=0.0628, over 7283.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3037, pruned_loss=0.0639, over 1420513.34 frames.], batch size: 24, lr: 1.01e-03
+2022-04-28 18:14:16,747 INFO [train.py:763] (6/8) Epoch 6, batch 3500, loss[loss=0.2781, simple_loss=0.3676, pruned_loss=0.0943, over 7214.00 frames.], tot_loss[loss=0.2158, simple_loss=0.304, pruned_loss=0.06386, over 1422579.53 frames.], batch size: 21, lr: 1.01e-03
+2022-04-28 18:15:22,308 INFO [train.py:763] (6/8) Epoch 6, batch 3550, loss[loss=0.2372, simple_loss=0.3292, pruned_loss=0.07262, over 7386.00 frames.], tot_loss[loss=0.2151, simple_loss=0.303, pruned_loss=0.06362, over 1424139.48 frames.], batch size: 23, lr: 1.01e-03
+2022-04-28 18:16:27,536 INFO [train.py:763] (6/8) Epoch 6, batch 3600, loss[loss=0.2025, simple_loss=0.3174, pruned_loss=0.04381, over 7222.00 frames.], tot_loss[loss=0.2147, simple_loss=0.303, pruned_loss=0.06323, over 1425549.54 frames.], batch size: 21, lr: 1.00e-03
+2022-04-28 18:17:32,793 INFO [train.py:763] (6/8) Epoch 6, batch 3650, loss[loss=0.22, simple_loss=0.3073, pruned_loss=0.06635, over 7089.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3021, pruned_loss=0.06258, over 1421487.07 frames.], batch size: 28, lr: 1.00e-03
+2022-04-28 18:18:39,444 INFO [train.py:763] (6/8) Epoch 6, batch 3700, loss[loss=0.204, simple_loss=0.2977, pruned_loss=0.05512, over 7438.00 frames.], tot_loss[loss=0.2133, simple_loss=0.3015, pruned_loss=0.06255, over 1423204.04 frames.], batch size: 20, lr: 1.00e-03
+2022-04-28 18:19:44,875 INFO [train.py:763] (6/8) Epoch 6, batch 3750, loss[loss=0.274, simple_loss=0.352, pruned_loss=0.09797, over 5003.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3023, pruned_loss=0.06304, over 1423549.14 frames.], batch size: 52, lr: 1.00e-03
+2022-04-28 18:20:50,223 INFO [train.py:763] (6/8) Epoch 6, batch 3800, loss[loss=0.2158, simple_loss=0.2922, pruned_loss=0.06971, over 7355.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3023, pruned_loss=0.06362, over 1420898.30 frames.], batch size: 19, lr: 1.00e-03
+2022-04-28 18:21:56,432 INFO [train.py:763] (6/8) Epoch 6, batch 3850, loss[loss=0.1879, simple_loss=0.2713, pruned_loss=0.05221, over 7150.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3011, pruned_loss=0.06375, over 1424279.26 frames.], batch size: 17, lr: 1.00e-03
+2022-04-28 18:23:02,744 INFO [train.py:763] (6/8) Epoch 6, batch 3900, loss[loss=0.1766, simple_loss=0.2663, pruned_loss=0.04344, over 7159.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3012, pruned_loss=0.06415, over 1425008.91 frames.], batch size: 18, lr: 1.00e-03
+2022-04-28 18:24:08,630 INFO [train.py:763] (6/8) Epoch 6, batch 3950, loss[loss=0.23, simple_loss=0.331, pruned_loss=0.06453, over 7323.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3011, pruned_loss=0.06367, over 1426796.05 frames.], batch size: 22, lr: 9.99e-04
+2022-04-28 18:25:14,072 INFO [train.py:763] (6/8) Epoch 6, batch 4000, loss[loss=0.2383, simple_loss=0.321, pruned_loss=0.0778, over 6717.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3004, pruned_loss=0.06303, over 1431139.75 frames.], batch size: 31, lr: 9.98e-04
+2022-04-28 18:26:19,668 INFO [train.py:763] (6/8) Epoch 6, batch 4050, loss[loss=0.2298, simple_loss=0.3107, pruned_loss=0.07443, over 7148.00 frames.], tot_loss[loss=0.2138, simple_loss=0.3008, pruned_loss=0.0634, over 1430001.71 frames.], batch size: 18, lr: 9.98e-04
+2022-04-28 18:27:25,537 INFO [train.py:763] (6/8) Epoch 6, batch 4100, loss[loss=0.2089, simple_loss=0.3052, pruned_loss=0.05632, over 7104.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3017, pruned_loss=0.06407, over 1425325.42 frames.], batch size: 21, lr: 9.97e-04
+2022-04-28 18:28:32,063 INFO [train.py:763] (6/8) Epoch 6, batch 4150, loss[loss=0.2545, simple_loss=0.3298, pruned_loss=0.08965, over 7207.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3022, pruned_loss=0.06431, over 1425241.70 frames.], batch size: 23, lr: 9.96e-04
+2022-04-28 18:29:37,834 INFO [train.py:763] (6/8) Epoch 6, batch 4200, loss[loss=0.1976, simple_loss=0.277, pruned_loss=0.0591, over 7275.00 frames.], tot_loss[loss=0.2144, simple_loss=0.3015, pruned_loss=0.0637, over 1427329.60 frames.], batch size: 17, lr: 9.95e-04
+2022-04-28 18:30:43,251 INFO [train.py:763] (6/8) Epoch 6, batch 4250, loss[loss=0.1947, simple_loss=0.292, pruned_loss=0.04869, over 7437.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3013, pruned_loss=0.06355, over 1422468.14 frames.], batch size: 20, lr: 9.95e-04
+2022-04-28 18:31:48,768 INFO [train.py:763] (6/8) Epoch 6, batch 4300, loss[loss=0.2057, simple_loss=0.3079, pruned_loss=0.05172, over 7227.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3026, pruned_loss=0.06397, over 1417014.21 frames.], batch size: 20, lr: 9.94e-04
+2022-04-28 18:32:54,887 INFO [train.py:763] (6/8) Epoch 6, batch 4350, loss[loss=0.2242, simple_loss=0.3148, pruned_loss=0.06678, over 6502.00 frames.], tot_loss[loss=0.2134, simple_loss=0.3011, pruned_loss=0.06284, over 1410280.97 frames.], batch size: 38, lr: 9.93e-04
+2022-04-28 18:34:00,637 INFO [train.py:763] (6/8) Epoch 6, batch 4400, loss[loss=0.2233, simple_loss=0.3151, pruned_loss=0.06569, over 6758.00 frames.], tot_loss[loss=0.213, simple_loss=0.3006, pruned_loss=0.06266, over 1411844.24 frames.], batch size: 31, lr: 9.92e-04
+2022-04-28 18:35:07,352 INFO [train.py:763] (6/8) Epoch 6, batch 4450, loss[loss=0.2188, simple_loss=0.3162, pruned_loss=0.06074, over 7203.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3014, pruned_loss=0.06291, over 1407336.35 frames.], batch size: 22, lr: 9.92e-04
+2022-04-28 18:36:23,322 INFO [train.py:763] (6/8) Epoch 6, batch 4500, loss[loss=0.2142, simple_loss=0.3113, pruned_loss=0.05852, over 7214.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3014, pruned_loss=0.06289, over 1404380.55 frames.], batch size: 22, lr: 9.91e-04
+2022-04-28 18:37:28,330 INFO [train.py:763] (6/8) Epoch 6, batch 4550, loss[loss=0.2891, simple_loss=0.3581, pruned_loss=0.1101, over 5049.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3035, pruned_loss=0.06402, over 1389758.97 frames.], batch size: 53, lr: 9.90e-04
+2022-04-28 18:38:57,445 INFO [train.py:763] (6/8) Epoch 7, batch 0, loss[loss=0.228, simple_loss=0.3157, pruned_loss=0.07019, over 7348.00 frames.], tot_loss[loss=0.228, simple_loss=0.3157, pruned_loss=0.07019, over 7348.00 frames.], batch size: 22, lr: 9.49e-04
+2022-04-28 18:40:02,642 INFO [train.py:763] (6/8) Epoch 7, batch 50, loss[loss=0.1902, simple_loss=0.2687, pruned_loss=0.05589, over 7129.00 frames.], tot_loss[loss=0.2112, simple_loss=0.3017, pruned_loss=0.06038, over 320487.31 frames.], batch size: 17, lr: 9.48e-04
+2022-04-28 18:41:07,852 INFO [train.py:763] (6/8) Epoch 7, batch 100, loss[loss=0.2063, simple_loss=0.2884, pruned_loss=0.06205, over 7308.00 frames.], tot_loss[loss=0.2109, simple_loss=0.3013, pruned_loss=0.0602, over 568678.30 frames.], batch size: 25, lr: 9.48e-04
+2022-04-28 18:42:13,274 INFO [train.py:763] (6/8) Epoch 7, batch 150, loss[loss=0.2216, simple_loss=0.3207, pruned_loss=0.06129, over 7123.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2985, pruned_loss=0.05952, over 757943.58 frames.], batch size: 21, lr: 9.47e-04
+2022-04-28 18:43:19,111 INFO [train.py:763] (6/8) Epoch 7, batch 200, loss[loss=0.1842, simple_loss=0.2844, pruned_loss=0.04202, over 7217.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2999, pruned_loss=0.06043, over 906231.25 frames.], batch size: 22, lr: 9.46e-04
+2022-04-28 18:44:24,615 INFO [train.py:763] (6/8) Epoch 7, batch 250, loss[loss=0.2056, simple_loss=0.2986, pruned_loss=0.05629, over 7122.00 frames.], tot_loss[loss=0.2103, simple_loss=0.3001, pruned_loss=0.06022, over 1019486.88 frames.], batch size: 21, lr: 9.46e-04
+2022-04-28 18:45:29,825 INFO [train.py:763] (6/8) Epoch 7, batch 300, loss[loss=0.2282, simple_loss=0.3097, pruned_loss=0.07339, over 7065.00 frames.], tot_loss[loss=0.2108, simple_loss=0.3002, pruned_loss=0.06066, over 1105544.78 frames.], batch size: 18, lr: 9.45e-04
+2022-04-28 18:46:35,550 INFO [train.py:763] (6/8) Epoch 7, batch 350, loss[loss=0.215, simple_loss=0.3173, pruned_loss=0.05638, over 7110.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2996, pruned_loss=0.0607, over 1177728.78 frames.], batch size: 21, lr: 9.44e-04
+2022-04-28 18:47:40,825 INFO [train.py:763] (6/8) Epoch 7, batch 400, loss[loss=0.2697, simple_loss=0.3315, pruned_loss=0.1039, over 5005.00 frames.], tot_loss[loss=0.2124, simple_loss=0.3014, pruned_loss=0.06167, over 1230576.25 frames.], batch size: 52, lr: 9.43e-04
+2022-04-28 18:48:46,398 INFO [train.py:763] (6/8) Epoch 7, batch 450, loss[loss=0.1639, simple_loss=0.2518, pruned_loss=0.03805, over 7190.00 frames.], tot_loss[loss=0.2117, simple_loss=0.3005, pruned_loss=0.06148, over 1271997.03 frames.], batch size: 16, lr: 9.43e-04
+2022-04-28 18:49:51,766 INFO [train.py:763] (6/8) Epoch 7, batch 500, loss[loss=0.2273, simple_loss=0.3076, pruned_loss=0.07349, over 7208.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2997, pruned_loss=0.06156, over 1304772.97 frames.], batch size: 23, lr: 9.42e-04
+2022-04-28 18:50:57,362 INFO [train.py:763] (6/8) Epoch 7, batch 550, loss[loss=0.2141, simple_loss=0.2984, pruned_loss=0.06489, over 7213.00 frames.], tot_loss[loss=0.211, simple_loss=0.2995, pruned_loss=0.06124, over 1332195.24 frames.], batch size: 23, lr: 9.41e-04
+2022-04-28 18:52:02,637 INFO [train.py:763] (6/8) Epoch 7, batch 600, loss[loss=0.242, simple_loss=0.3312, pruned_loss=0.07645, over 7221.00 frames.], tot_loss[loss=0.2115, simple_loss=0.3005, pruned_loss=0.06128, over 1352587.08 frames.], batch size: 21, lr: 9.41e-04
+2022-04-28 18:53:08,464 INFO [train.py:763] (6/8) Epoch 7, batch 650, loss[loss=0.2514, simple_loss=0.3215, pruned_loss=0.09063, over 7267.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2994, pruned_loss=0.06043, over 1368165.76 frames.], batch size: 19, lr: 9.40e-04
+2022-04-28 18:54:13,819 INFO [train.py:763] (6/8) Epoch 7, batch 700, loss[loss=0.2654, simple_loss=0.3262, pruned_loss=0.1023, over 4827.00 frames.], tot_loss[loss=0.2111, simple_loss=0.3005, pruned_loss=0.06085, over 1376157.46 frames.], batch size: 53, lr: 9.39e-04
+2022-04-28 18:55:19,520 INFO [train.py:763] (6/8) Epoch 7, batch 750, loss[loss=0.201, simple_loss=0.2943, pruned_loss=0.0539, over 7348.00 frames.], tot_loss[loss=0.2106, simple_loss=0.3, pruned_loss=0.06059, over 1385250.71 frames.], batch size: 19, lr: 9.39e-04
+2022-04-28 18:56:26,154 INFO [train.py:763] (6/8) Epoch 7, batch 800, loss[loss=0.2287, simple_loss=0.3163, pruned_loss=0.07056, over 6440.00 frames.], tot_loss[loss=0.2121, simple_loss=0.3015, pruned_loss=0.06135, over 1390506.14 frames.], batch size: 37, lr: 9.38e-04
+2022-04-28 18:57:33,317 INFO [train.py:763] (6/8) Epoch 7, batch 850, loss[loss=0.1632, simple_loss=0.2531, pruned_loss=0.03663, over 7416.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2984, pruned_loss=0.05992, over 1399351.85 frames.], batch size: 18, lr: 9.37e-04
+2022-04-28 18:58:40,266 INFO [train.py:763] (6/8) Epoch 7, batch 900, loss[loss=0.2648, simple_loss=0.3507, pruned_loss=0.08942, over 6898.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2979, pruned_loss=0.06048, over 1398539.68 frames.], batch size: 31, lr: 9.36e-04
+2022-04-28 18:59:46,948 INFO [train.py:763] (6/8) Epoch 7, batch 950, loss[loss=0.1854, simple_loss=0.2849, pruned_loss=0.04298, over 7248.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2985, pruned_loss=0.06061, over 1404095.88 frames.], batch size: 20, lr: 9.36e-04
+2022-04-28 19:00:52,053 INFO [train.py:763] (6/8) Epoch 7, batch 1000, loss[loss=0.2282, simple_loss=0.3267, pruned_loss=0.06487, over 7224.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2991, pruned_loss=0.06059, over 1408461.79 frames.], batch size: 21, lr: 9.35e-04
+2022-04-28 19:01:58,585 INFO [train.py:763] (6/8) Epoch 7, batch 1050, loss[loss=0.2036, simple_loss=0.2995, pruned_loss=0.05383, over 7145.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2997, pruned_loss=0.06084, over 1406248.00 frames.], batch size: 17, lr: 9.34e-04
+2022-04-28 19:03:05,229 INFO [train.py:763] (6/8) Epoch 7, batch 1100, loss[loss=0.2389, simple_loss=0.3216, pruned_loss=0.0781, over 7203.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2982, pruned_loss=0.06023, over 1410488.14 frames.], batch size: 22, lr: 9.34e-04
+2022-04-28 19:04:11,931 INFO [train.py:763] (6/8) Epoch 7, batch 1150, loss[loss=0.2802, simple_loss=0.3473, pruned_loss=0.1066, over 5068.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2999, pruned_loss=0.06079, over 1415974.62 frames.], batch size: 52, lr: 9.33e-04
+2022-04-28 19:05:18,440 INFO [train.py:763] (6/8) Epoch 7, batch 1200, loss[loss=0.1967, simple_loss=0.2934, pruned_loss=0.05001, over 7143.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2987, pruned_loss=0.0604, over 1419598.22 frames.], batch size: 20, lr: 9.32e-04
+2022-04-28 19:06:24,032 INFO [train.py:763] (6/8) Epoch 7, batch 1250, loss[loss=0.1861, simple_loss=0.2615, pruned_loss=0.05535, over 7285.00 frames.], tot_loss[loss=0.209, simple_loss=0.2975, pruned_loss=0.06026, over 1418792.69 frames.], batch size: 18, lr: 9.32e-04
+2022-04-28 19:07:30,159 INFO [train.py:763] (6/8) Epoch 7, batch 1300, loss[loss=0.2159, simple_loss=0.3088, pruned_loss=0.06147, over 7159.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2988, pruned_loss=0.06072, over 1415723.98 frames.], batch size: 20, lr: 9.31e-04
+2022-04-28 19:08:35,482 INFO [train.py:763] (6/8) Epoch 7, batch 1350, loss[loss=0.2316, simple_loss=0.3094, pruned_loss=0.07692, over 7160.00 frames.], tot_loss[loss=0.2109, simple_loss=0.2993, pruned_loss=0.06123, over 1415097.25 frames.], batch size: 19, lr: 9.30e-04
+2022-04-28 19:09:41,320 INFO [train.py:763] (6/8) Epoch 7, batch 1400, loss[loss=0.2046, simple_loss=0.2941, pruned_loss=0.05756, over 7295.00 frames.], tot_loss[loss=0.21, simple_loss=0.2992, pruned_loss=0.0604, over 1416363.76 frames.], batch size: 18, lr: 9.30e-04
+2022-04-28 19:10:48,153 INFO [train.py:763] (6/8) Epoch 7, batch 1450, loss[loss=0.2221, simple_loss=0.299, pruned_loss=0.07257, over 7172.00 frames.], tot_loss[loss=0.21, simple_loss=0.2991, pruned_loss=0.06045, over 1415954.91 frames.], batch size: 18, lr: 9.29e-04
+2022-04-28 19:11:54,401 INFO [train.py:763] (6/8) Epoch 7, batch 1500, loss[loss=0.2042, simple_loss=0.272, pruned_loss=0.06819, over 7416.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2974, pruned_loss=0.05993, over 1416270.00 frames.], batch size: 18, lr: 9.28e-04
+2022-04-28 19:12:59,478 INFO [train.py:763] (6/8) Epoch 7, batch 1550, loss[loss=0.2357, simple_loss=0.3218, pruned_loss=0.07479, over 7210.00 frames.], tot_loss[loss=0.209, simple_loss=0.2981, pruned_loss=0.05993, over 1421046.12 frames.], batch size: 22, lr: 9.28e-04
+2022-04-28 19:14:04,515 INFO [train.py:763] (6/8) Epoch 7, batch 1600, loss[loss=0.2425, simple_loss=0.3311, pruned_loss=0.07701, over 6305.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2989, pruned_loss=0.06013, over 1421279.67 frames.], batch size: 38, lr: 9.27e-04
+2022-04-28 19:15:09,644 INFO [train.py:763] (6/8) Epoch 7, batch 1650, loss[loss=0.1923, simple_loss=0.2901, pruned_loss=0.04726, over 7285.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2985, pruned_loss=0.05983, over 1419477.42 frames.], batch size: 24, lr: 9.26e-04
+2022-04-28 19:16:15,862 INFO [train.py:763] (6/8) Epoch 7, batch 1700, loss[loss=0.2002, simple_loss=0.2972, pruned_loss=0.05153, over 7313.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2979, pruned_loss=0.05936, over 1420269.50 frames.], batch size: 21, lr: 9.26e-04
+2022-04-28 19:17:22,179 INFO [train.py:763] (6/8) Epoch 7, batch 1750, loss[loss=0.2202, simple_loss=0.3127, pruned_loss=0.06382, over 7329.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2984, pruned_loss=0.06013, over 1422076.25 frames.], batch size: 22, lr: 9.25e-04
+2022-04-28 19:18:45,819 INFO [train.py:763] (6/8) Epoch 7, batch 1800, loss[loss=0.2174, simple_loss=0.3172, pruned_loss=0.05877, over 7337.00 frames.], tot_loss[loss=0.2082, simple_loss=0.297, pruned_loss=0.05971, over 1422908.48 frames.], batch size: 22, lr: 9.24e-04
+2022-04-28 19:19:59,993 INFO [train.py:763] (6/8) Epoch 7, batch 1850, loss[loss=0.224, simple_loss=0.3232, pruned_loss=0.06237, over 7237.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2986, pruned_loss=0.06062, over 1424913.45 frames.], batch size: 20, lr: 9.24e-04
+2022-04-28 19:21:23,372 INFO [train.py:763] (6/8) Epoch 7, batch 1900, loss[loss=0.229, simple_loss=0.3065, pruned_loss=0.07578, over 7284.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2973, pruned_loss=0.0602, over 1422842.06 frames.], batch size: 25, lr: 9.23e-04
+2022-04-28 19:22:40,069 INFO [train.py:763] (6/8) Epoch 7, batch 1950, loss[loss=0.1892, simple_loss=0.2708, pruned_loss=0.05378, over 7007.00 frames.], tot_loss[loss=0.2083, simple_loss=0.297, pruned_loss=0.05978, over 1427006.92 frames.], batch size: 16, lr: 9.22e-04
+2022-04-28 19:23:47,454 INFO [train.py:763] (6/8) Epoch 7, batch 2000, loss[loss=0.2374, simple_loss=0.3267, pruned_loss=0.07407, over 7116.00 frames.], tot_loss[loss=0.208, simple_loss=0.2968, pruned_loss=0.05964, over 1427466.10 frames.], batch size: 21, lr: 9.22e-04
+2022-04-28 19:25:02,870 INFO [train.py:763] (6/8) Epoch 7, batch 2050, loss[loss=0.2266, simple_loss=0.3015, pruned_loss=0.07584, over 5280.00 frames.], tot_loss[loss=0.2084, simple_loss=0.297, pruned_loss=0.05985, over 1422408.39 frames.], batch size: 52, lr: 9.21e-04
+2022-04-28 19:26:07,944 INFO [train.py:763] (6/8) Epoch 7, batch 2100, loss[loss=0.184, simple_loss=0.2804, pruned_loss=0.04377, over 7231.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2976, pruned_loss=0.06013, over 1419284.56 frames.], batch size: 20, lr: 9.20e-04
+2022-04-28 19:27:22,248 INFO [train.py:763] (6/8) Epoch 7, batch 2150, loss[loss=0.2137, simple_loss=0.3048, pruned_loss=0.06131, over 7196.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2976, pruned_loss=0.05987, over 1420089.67 frames.], batch size: 22, lr: 9.20e-04
+2022-04-28 19:28:27,689 INFO [train.py:763] (6/8) Epoch 7, batch 2200, loss[loss=0.2079, simple_loss=0.3019, pruned_loss=0.05694, over 7294.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2961, pruned_loss=0.05925, over 1417713.42 frames.], batch size: 24, lr: 9.19e-04
+2022-04-28 19:29:32,844 INFO [train.py:763] (6/8) Epoch 7, batch 2250, loss[loss=0.2559, simple_loss=0.3365, pruned_loss=0.08768, over 7218.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2962, pruned_loss=0.05979, over 1412940.37 frames.], batch size: 23, lr: 9.18e-04
+2022-04-28 19:30:38,171 INFO [train.py:763] (6/8) Epoch 7, batch 2300, loss[loss=0.1762, simple_loss=0.2656, pruned_loss=0.04344, over 7403.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2963, pruned_loss=0.05969, over 1413404.12 frames.], batch size: 18, lr: 9.18e-04
+2022-04-28 19:31:43,914 INFO [train.py:763] (6/8) Epoch 7, batch 2350, loss[loss=0.2216, simple_loss=0.3059, pruned_loss=0.06865, over 7061.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2977, pruned_loss=0.06063, over 1413427.29 frames.], batch size: 18, lr: 9.17e-04
+2022-04-28 19:32:50,594 INFO [train.py:763] (6/8) Epoch 7, batch 2400, loss[loss=0.187, simple_loss=0.275, pruned_loss=0.04948, over 7259.00 frames.], tot_loss[loss=0.208, simple_loss=0.2967, pruned_loss=0.0597, over 1417415.80 frames.], batch size: 19, lr: 9.16e-04
+2022-04-28 19:33:55,904 INFO [train.py:763] (6/8) Epoch 7, batch 2450, loss[loss=0.2125, simple_loss=0.3063, pruned_loss=0.0593, over 7287.00 frames.], tot_loss[loss=0.208, simple_loss=0.2964, pruned_loss=0.0598, over 1423502.00 frames.], batch size: 24, lr: 9.16e-04
+2022-04-28 19:35:01,303 INFO [train.py:763] (6/8) Epoch 7, batch 2500, loss[loss=0.266, simple_loss=0.347, pruned_loss=0.09255, over 7321.00 frames.], tot_loss[loss=0.209, simple_loss=0.2975, pruned_loss=0.06028, over 1422278.27 frames.], batch size: 21, lr: 9.15e-04
+2022-04-28 19:36:06,927 INFO [train.py:763] (6/8) Epoch 7, batch 2550, loss[loss=0.173, simple_loss=0.2655, pruned_loss=0.04024, over 7362.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2962, pruned_loss=0.05997, over 1426093.30 frames.], batch size: 19, lr: 9.14e-04
+2022-04-28 19:37:12,484 INFO [train.py:763] (6/8) Epoch 7, batch 2600, loss[loss=0.2248, simple_loss=0.3005, pruned_loss=0.07448, over 6821.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2962, pruned_loss=0.05981, over 1426149.33 frames.], batch size: 15, lr: 9.14e-04
+2022-04-28 19:38:17,715 INFO [train.py:763] (6/8) Epoch 7, batch 2650, loss[loss=0.2256, simple_loss=0.3201, pruned_loss=0.06559, over 7121.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2964, pruned_loss=0.05931, over 1426671.43 frames.], batch size: 21, lr: 9.13e-04
+2022-04-28 19:39:23,651 INFO [train.py:763] (6/8) Epoch 7, batch 2700, loss[loss=0.1841, simple_loss=0.2629, pruned_loss=0.05267, over 6811.00 frames.], tot_loss[loss=0.207, simple_loss=0.2957, pruned_loss=0.05913, over 1429088.34 frames.], batch size: 15, lr: 9.12e-04
+2022-04-28 19:40:30,720 INFO [train.py:763] (6/8) Epoch 7, batch 2750, loss[loss=0.1758, simple_loss=0.2561, pruned_loss=0.04769, over 6999.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2953, pruned_loss=0.059, over 1428096.53 frames.], batch size: 16, lr: 9.12e-04
+2022-04-28 19:41:36,689 INFO [train.py:763] (6/8) Epoch 7, batch 2800, loss[loss=0.2445, simple_loss=0.3215, pruned_loss=0.08374, over 7144.00 frames.], tot_loss[loss=0.2074, simple_loss=0.296, pruned_loss=0.05942, over 1429044.89 frames.], batch size: 20, lr: 9.11e-04
+2022-04-28 19:42:43,487 INFO [train.py:763] (6/8) Epoch 7, batch 2850, loss[loss=0.1819, simple_loss=0.2874, pruned_loss=0.03814, over 7207.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2964, pruned_loss=0.05952, over 1426760.24 frames.], batch size: 22, lr: 9.11e-04
+2022-04-28 19:43:49,334 INFO [train.py:763] (6/8) Epoch 7, batch 2900, loss[loss=0.1622, simple_loss=0.2402, pruned_loss=0.04207, over 7130.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2968, pruned_loss=0.05943, over 1426573.05 frames.], batch size: 17, lr: 9.10e-04
+2022-04-28 19:44:55,757 INFO [train.py:763] (6/8) Epoch 7, batch 2950, loss[loss=0.1969, simple_loss=0.2798, pruned_loss=0.05702, over 7065.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2971, pruned_loss=0.06015, over 1425374.75 frames.], batch size: 18, lr: 9.09e-04
+2022-04-28 19:46:01,160 INFO [train.py:763] (6/8) Epoch 7, batch 3000, loss[loss=0.2674, simple_loss=0.3361, pruned_loss=0.09934, over 5183.00 frames.], tot_loss[loss=0.209, simple_loss=0.2977, pruned_loss=0.06022, over 1422345.17 frames.], batch size: 52, lr: 9.09e-04
+2022-04-28 19:46:01,161 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-28 19:46:16,423 INFO [train.py:792] (6/8) Epoch 7, validation: loss=0.1713, simple_loss=0.2754, pruned_loss=0.03361, over 698248.00 frames.
+2022-04-28 19:47:23,040 INFO [train.py:763] (6/8) Epoch 7, batch 3050, loss[loss=0.2268, simple_loss=0.3218, pruned_loss=0.06583, over 6579.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2977, pruned_loss=0.06024, over 1415218.05 frames.], batch size: 38, lr: 9.08e-04
+2022-04-28 19:48:28,735 INFO [train.py:763] (6/8) Epoch 7, batch 3100, loss[loss=0.2087, simple_loss=0.2965, pruned_loss=0.06042, over 7260.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2973, pruned_loss=0.05979, over 1419553.07 frames.], batch size: 19, lr: 9.07e-04
+2022-04-28 19:49:34,316 INFO [train.py:763] (6/8) Epoch 7, batch 3150, loss[loss=0.1983, simple_loss=0.2864, pruned_loss=0.05514, over 7418.00 frames.], tot_loss[loss=0.207, simple_loss=0.2959, pruned_loss=0.05904, over 1420690.00 frames.], batch size: 20, lr: 9.07e-04
+2022-04-28 19:50:39,920 INFO [train.py:763] (6/8) Epoch 7, batch 3200, loss[loss=0.186, simple_loss=0.2836, pruned_loss=0.04424, over 7428.00 frames.], tot_loss[loss=0.206, simple_loss=0.2953, pruned_loss=0.05838, over 1424212.20 frames.], batch size: 20, lr: 9.06e-04
+2022-04-28 19:51:45,168 INFO [train.py:763] (6/8) Epoch 7, batch 3250, loss[loss=0.2202, simple_loss=0.3153, pruned_loss=0.06252, over 7063.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2969, pruned_loss=0.05932, over 1422928.78 frames.], batch size: 28, lr: 9.05e-04
+2022-04-28 19:52:50,676 INFO [train.py:763] (6/8) Epoch 7, batch 3300, loss[loss=0.2215, simple_loss=0.3109, pruned_loss=0.06601, over 6685.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2967, pruned_loss=0.05957, over 1421834.09 frames.], batch size: 31, lr: 9.05e-04
+2022-04-28 19:53:56,158 INFO [train.py:763] (6/8) Epoch 7, batch 3350, loss[loss=0.1882, simple_loss=0.2834, pruned_loss=0.04651, over 7428.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2968, pruned_loss=0.05942, over 1419957.89 frames.], batch size: 20, lr: 9.04e-04
+2022-04-28 19:55:01,743 INFO [train.py:763] (6/8) Epoch 7, batch 3400, loss[loss=0.2232, simple_loss=0.3165, pruned_loss=0.06495, over 6804.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2975, pruned_loss=0.05968, over 1417384.65 frames.], batch size: 31, lr: 9.04e-04
+2022-04-28 19:56:08,386 INFO [train.py:763] (6/8) Epoch 7, batch 3450, loss[loss=0.1945, simple_loss=0.2731, pruned_loss=0.05792, over 7412.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2989, pruned_loss=0.06038, over 1420418.72 frames.], batch size: 18, lr: 9.03e-04
+2022-04-28 19:57:15,789 INFO [train.py:763] (6/8) Epoch 7, batch 3500, loss[loss=0.2208, simple_loss=0.3137, pruned_loss=0.064, over 7381.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2995, pruned_loss=0.06036, over 1419802.97 frames.], batch size: 23, lr: 9.02e-04
+2022-04-28 19:58:22,787 INFO [train.py:763] (6/8) Epoch 7, batch 3550, loss[loss=0.2101, simple_loss=0.2992, pruned_loss=0.06047, over 7260.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2991, pruned_loss=0.05963, over 1421759.14 frames.], batch size: 19, lr: 9.02e-04
+2022-04-28 19:59:29,958 INFO [train.py:763] (6/8) Epoch 7, batch 3600, loss[loss=0.1836, simple_loss=0.2673, pruned_loss=0.05, over 7286.00 frames.], tot_loss[loss=0.2085, simple_loss=0.298, pruned_loss=0.05946, over 1420162.20 frames.], batch size: 17, lr: 9.01e-04
+2022-04-28 20:00:37,039 INFO [train.py:763] (6/8) Epoch 7, batch 3650, loss[loss=0.1722, simple_loss=0.2725, pruned_loss=0.03601, over 7421.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2987, pruned_loss=0.06, over 1414823.17 frames.], batch size: 21, lr: 9.01e-04
+2022-04-28 20:01:42,542 INFO [train.py:763] (6/8) Epoch 7, batch 3700, loss[loss=0.2135, simple_loss=0.303, pruned_loss=0.06203, over 7222.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2974, pruned_loss=0.05913, over 1419167.00 frames.], batch size: 21, lr: 9.00e-04
+2022-04-28 20:02:49,192 INFO [train.py:763] (6/8) Epoch 7, batch 3750, loss[loss=0.1804, simple_loss=0.2743, pruned_loss=0.04326, over 7161.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2964, pruned_loss=0.0585, over 1416854.11 frames.], batch size: 19, lr: 8.99e-04
+2022-04-28 20:03:54,763 INFO [train.py:763] (6/8) Epoch 7, batch 3800, loss[loss=0.2113, simple_loss=0.3025, pruned_loss=0.06011, over 7300.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2977, pruned_loss=0.05889, over 1419939.31 frames.], batch size: 24, lr: 8.99e-04
+2022-04-28 20:05:00,515 INFO [train.py:763] (6/8) Epoch 7, batch 3850, loss[loss=0.2325, simple_loss=0.3378, pruned_loss=0.06362, over 7221.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2977, pruned_loss=0.05857, over 1418062.63 frames.], batch size: 21, lr: 8.98e-04
+2022-04-28 20:06:06,737 INFO [train.py:763] (6/8) Epoch 7, batch 3900, loss[loss=0.198, simple_loss=0.2977, pruned_loss=0.04917, over 7435.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2961, pruned_loss=0.05845, over 1422054.50 frames.], batch size: 20, lr: 8.97e-04
+2022-04-28 20:07:13,249 INFO [train.py:763] (6/8) Epoch 7, batch 3950, loss[loss=0.1904, simple_loss=0.2797, pruned_loss=0.05061, over 7436.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2949, pruned_loss=0.05781, over 1425806.74 frames.], batch size: 17, lr: 8.97e-04
+2022-04-28 20:08:18,738 INFO [train.py:763] (6/8) Epoch 7, batch 4000, loss[loss=0.2245, simple_loss=0.3197, pruned_loss=0.06464, over 7154.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2964, pruned_loss=0.05845, over 1423962.77 frames.], batch size: 20, lr: 8.96e-04
+2022-04-28 20:09:23,870 INFO [train.py:763] (6/8) Epoch 7, batch 4050, loss[loss=0.1925, simple_loss=0.2879, pruned_loss=0.04856, over 7423.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2957, pruned_loss=0.05827, over 1426683.87 frames.], batch size: 21, lr: 8.96e-04
+2022-04-28 20:10:29,414 INFO [train.py:763] (6/8) Epoch 7, batch 4100, loss[loss=0.1609, simple_loss=0.2444, pruned_loss=0.0387, over 7268.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2963, pruned_loss=0.05854, over 1419977.13 frames.], batch size: 17, lr: 8.95e-04
+2022-04-28 20:11:34,142 INFO [train.py:763] (6/8) Epoch 7, batch 4150, loss[loss=0.1935, simple_loss=0.2995, pruned_loss=0.04371, over 7335.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2962, pruned_loss=0.05834, over 1412483.11 frames.], batch size: 22, lr: 8.94e-04
+2022-04-28 20:12:39,367 INFO [train.py:763] (6/8) Epoch 7, batch 4200, loss[loss=0.1846, simple_loss=0.283, pruned_loss=0.04311, over 7151.00 frames.], tot_loss[loss=0.207, simple_loss=0.297, pruned_loss=0.05852, over 1415146.36 frames.], batch size: 20, lr: 8.94e-04
+2022-04-28 20:13:44,890 INFO [train.py:763] (6/8) Epoch 7, batch 4250, loss[loss=0.2034, simple_loss=0.3122, pruned_loss=0.04731, over 7202.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2966, pruned_loss=0.0581, over 1419532.23 frames.], batch size: 22, lr: 8.93e-04
+2022-04-28 20:14:50,389 INFO [train.py:763] (6/8) Epoch 7, batch 4300, loss[loss=0.2031, simple_loss=0.2934, pruned_loss=0.05643, over 7321.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2961, pruned_loss=0.05849, over 1417158.50 frames.], batch size: 21, lr: 8.93e-04
+2022-04-28 20:15:55,685 INFO [train.py:763] (6/8) Epoch 7, batch 4350, loss[loss=0.2012, simple_loss=0.2997, pruned_loss=0.05132, over 7112.00 frames.], tot_loss[loss=0.206, simple_loss=0.2953, pruned_loss=0.0584, over 1413417.07 frames.], batch size: 21, lr: 8.92e-04
+2022-04-28 20:17:01,820 INFO [train.py:763] (6/8) Epoch 7, batch 4400, loss[loss=0.2203, simple_loss=0.3141, pruned_loss=0.06323, over 7106.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2942, pruned_loss=0.05807, over 1416101.37 frames.], batch size: 28, lr: 8.91e-04
+2022-04-28 20:18:09,019 INFO [train.py:763] (6/8) Epoch 7, batch 4450, loss[loss=0.1799, simple_loss=0.2757, pruned_loss=0.04209, over 7332.00 frames.], tot_loss[loss=0.2051, simple_loss=0.294, pruned_loss=0.05807, over 1416055.04 frames.], batch size: 20, lr: 8.91e-04
+2022-04-28 20:19:16,395 INFO [train.py:763] (6/8) Epoch 7, batch 4500, loss[loss=0.2086, simple_loss=0.2983, pruned_loss=0.05947, over 7161.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2936, pruned_loss=0.05779, over 1413752.75 frames.], batch size: 18, lr: 8.90e-04
+2022-04-28 20:20:24,252 INFO [train.py:763] (6/8) Epoch 7, batch 4550, loss[loss=0.1612, simple_loss=0.2489, pruned_loss=0.03674, over 7266.00 frames.], tot_loss[loss=0.206, simple_loss=0.2938, pruned_loss=0.0591, over 1396257.79 frames.], batch size: 17, lr: 8.90e-04
+2022-04-28 20:21:52,806 INFO [train.py:763] (6/8) Epoch 8, batch 0, loss[loss=0.2018, simple_loss=0.2956, pruned_loss=0.05396, over 7180.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2956, pruned_loss=0.05396, over 7180.00 frames.], batch size: 23, lr: 8.54e-04
+2022-04-28 20:22:58,562 INFO [train.py:763] (6/8) Epoch 8, batch 50, loss[loss=0.2189, simple_loss=0.3048, pruned_loss=0.06648, over 7111.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2977, pruned_loss=0.05736, over 319353.86 frames.], batch size: 28, lr: 8.53e-04
+2022-04-28 20:24:03,945 INFO [train.py:763] (6/8) Epoch 8, batch 100, loss[loss=0.1892, simple_loss=0.2864, pruned_loss=0.046, over 7240.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2941, pruned_loss=0.05469, over 566330.34 frames.], batch size: 20, lr: 8.53e-04
+2022-04-28 20:25:10,130 INFO [train.py:763] (6/8) Epoch 8, batch 150, loss[loss=0.2202, simple_loss=0.3131, pruned_loss=0.06366, over 5218.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2949, pruned_loss=0.05636, over 753870.48 frames.], batch size: 52, lr: 8.52e-04
+2022-04-28 20:26:16,006 INFO [train.py:763] (6/8) Epoch 8, batch 200, loss[loss=0.2211, simple_loss=0.3156, pruned_loss=0.06332, over 7203.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2944, pruned_loss=0.05598, over 903110.88 frames.], batch size: 22, lr: 8.51e-04
+2022-04-28 20:27:21,275 INFO [train.py:763] (6/8) Epoch 8, batch 250, loss[loss=0.2181, simple_loss=0.3033, pruned_loss=0.06646, over 7435.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2946, pruned_loss=0.05623, over 1019610.47 frames.], batch size: 20, lr: 8.51e-04
+2022-04-28 20:28:27,035 INFO [train.py:763] (6/8) Epoch 8, batch 300, loss[loss=0.2019, simple_loss=0.298, pruned_loss=0.05288, over 7335.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2958, pruned_loss=0.0568, over 1105120.90 frames.], batch size: 22, lr: 8.50e-04
+2022-04-28 20:29:32,798 INFO [train.py:763] (6/8) Epoch 8, batch 350, loss[loss=0.1972, simple_loss=0.289, pruned_loss=0.05274, over 7163.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2934, pruned_loss=0.05551, over 1178670.52 frames.], batch size: 19, lr: 8.50e-04
+2022-04-28 20:30:38,286 INFO [train.py:763] (6/8) Epoch 8, batch 400, loss[loss=0.1795, simple_loss=0.2648, pruned_loss=0.04708, over 7131.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2942, pruned_loss=0.05633, over 1237650.59 frames.], batch size: 17, lr: 8.49e-04
+2022-04-28 20:31:43,713 INFO [train.py:763] (6/8) Epoch 8, batch 450, loss[loss=0.2017, simple_loss=0.2916, pruned_loss=0.05588, over 7264.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2935, pruned_loss=0.05613, over 1278266.35 frames.], batch size: 19, lr: 8.49e-04
+2022-04-28 20:32:50,563 INFO [train.py:763] (6/8) Epoch 8, batch 500, loss[loss=0.1615, simple_loss=0.2603, pruned_loss=0.03138, over 7406.00 frames.], tot_loss[loss=0.204, simple_loss=0.2947, pruned_loss=0.05664, over 1310933.45 frames.], batch size: 18, lr: 8.48e-04
+2022-04-28 20:33:57,713 INFO [train.py:763] (6/8) Epoch 8, batch 550, loss[loss=0.1725, simple_loss=0.2615, pruned_loss=0.0417, over 7055.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2932, pruned_loss=0.05559, over 1338644.71 frames.], batch size: 18, lr: 8.48e-04
+2022-04-28 20:35:03,800 INFO [train.py:763] (6/8) Epoch 8, batch 600, loss[loss=0.1965, simple_loss=0.2777, pruned_loss=0.05758, over 7080.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2931, pruned_loss=0.05591, over 1360115.01 frames.], batch size: 18, lr: 8.47e-04
+2022-04-28 20:36:09,110 INFO [train.py:763] (6/8) Epoch 8, batch 650, loss[loss=0.1845, simple_loss=0.2724, pruned_loss=0.04824, over 7357.00 frames.], tot_loss[loss=0.202, simple_loss=0.2929, pruned_loss=0.05559, over 1373047.92 frames.], batch size: 19, lr: 8.46e-04
+2022-04-28 20:37:14,560 INFO [train.py:763] (6/8) Epoch 8, batch 700, loss[loss=0.1873, simple_loss=0.287, pruned_loss=0.04379, over 7427.00 frames.], tot_loss[loss=0.202, simple_loss=0.2929, pruned_loss=0.0556, over 1385602.68 frames.], batch size: 20, lr: 8.46e-04
+2022-04-28 20:38:20,315 INFO [train.py:763] (6/8) Epoch 8, batch 750, loss[loss=0.1593, simple_loss=0.2412, pruned_loss=0.03869, over 7166.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2933, pruned_loss=0.05601, over 1389674.07 frames.], batch size: 18, lr: 8.45e-04
+2022-04-28 20:39:25,914 INFO [train.py:763] (6/8) Epoch 8, batch 800, loss[loss=0.222, simple_loss=0.3123, pruned_loss=0.06583, over 7392.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2937, pruned_loss=0.05648, over 1396449.49 frames.], batch size: 23, lr: 8.45e-04
+2022-04-28 20:40:32,530 INFO [train.py:763] (6/8) Epoch 8, batch 850, loss[loss=0.2064, simple_loss=0.3078, pruned_loss=0.05248, over 7323.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2944, pruned_loss=0.05716, over 1401674.89 frames.], batch size: 21, lr: 8.44e-04
+2022-04-28 20:41:39,528 INFO [train.py:763] (6/8) Epoch 8, batch 900, loss[loss=0.2303, simple_loss=0.316, pruned_loss=0.07227, over 7225.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2932, pruned_loss=0.05612, over 1411085.45 frames.], batch size: 21, lr: 8.44e-04
+2022-04-28 20:42:46,674 INFO [train.py:763] (6/8) Epoch 8, batch 950, loss[loss=0.199, simple_loss=0.2934, pruned_loss=0.05231, over 7335.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2934, pruned_loss=0.05609, over 1408654.20 frames.], batch size: 20, lr: 8.43e-04
+2022-04-28 20:43:53,794 INFO [train.py:763] (6/8) Epoch 8, batch 1000, loss[loss=0.229, simple_loss=0.3148, pruned_loss=0.07155, over 7430.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2928, pruned_loss=0.05582, over 1413398.31 frames.], batch size: 20, lr: 8.43e-04
+2022-04-28 20:45:00,938 INFO [train.py:763] (6/8) Epoch 8, batch 1050, loss[loss=0.1936, simple_loss=0.2851, pruned_loss=0.05102, over 7259.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2933, pruned_loss=0.05619, over 1417136.08 frames.], batch size: 19, lr: 8.42e-04
+2022-04-28 20:46:07,161 INFO [train.py:763] (6/8) Epoch 8, batch 1100, loss[loss=0.1713, simple_loss=0.2628, pruned_loss=0.03993, over 7283.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2939, pruned_loss=0.05599, over 1420255.62 frames.], batch size: 17, lr: 8.41e-04
+2022-04-28 20:47:12,901 INFO [train.py:763] (6/8) Epoch 8, batch 1150, loss[loss=0.2263, simple_loss=0.3151, pruned_loss=0.06873, over 7283.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2933, pruned_loss=0.05579, over 1420992.33 frames.], batch size: 25, lr: 8.41e-04
+2022-04-28 20:48:18,242 INFO [train.py:763] (6/8) Epoch 8, batch 1200, loss[loss=0.1754, simple_loss=0.2721, pruned_loss=0.03937, over 7424.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2932, pruned_loss=0.0555, over 1421436.68 frames.], batch size: 20, lr: 8.40e-04
+2022-04-28 20:49:23,429 INFO [train.py:763] (6/8) Epoch 8, batch 1250, loss[loss=0.2022, simple_loss=0.2867, pruned_loss=0.05887, over 6773.00 frames.], tot_loss[loss=0.2011, simple_loss=0.292, pruned_loss=0.05513, over 1416957.63 frames.], batch size: 15, lr: 8.40e-04
+2022-04-28 20:50:29,922 INFO [train.py:763] (6/8) Epoch 8, batch 1300, loss[loss=0.235, simple_loss=0.3305, pruned_loss=0.06973, over 7157.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2932, pruned_loss=0.05578, over 1413454.01 frames.], batch size: 19, lr: 8.39e-04
+2022-04-28 20:51:37,150 INFO [train.py:763] (6/8) Epoch 8, batch 1350, loss[loss=0.1952, simple_loss=0.2894, pruned_loss=0.05055, over 7436.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2935, pruned_loss=0.05601, over 1418301.16 frames.], batch size: 20, lr: 8.39e-04
+2022-04-28 20:52:43,213 INFO [train.py:763] (6/8) Epoch 8, batch 1400, loss[loss=0.2057, simple_loss=0.2995, pruned_loss=0.05593, over 7232.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2929, pruned_loss=0.05599, over 1415081.44 frames.], batch size: 21, lr: 8.38e-04
+2022-04-28 20:53:48,899 INFO [train.py:763] (6/8) Epoch 8, batch 1450, loss[loss=0.2069, simple_loss=0.3049, pruned_loss=0.0545, over 7319.00 frames.], tot_loss[loss=0.2027, simple_loss=0.293, pruned_loss=0.05617, over 1420041.30 frames.], batch size: 21, lr: 8.38e-04
+2022-04-28 20:54:55,524 INFO [train.py:763] (6/8) Epoch 8, batch 1500, loss[loss=0.219, simple_loss=0.3062, pruned_loss=0.06588, over 7230.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2931, pruned_loss=0.05583, over 1422786.03 frames.], batch size: 20, lr: 8.37e-04
+2022-04-28 20:56:02,361 INFO [train.py:763] (6/8) Epoch 8, batch 1550, loss[loss=0.2076, simple_loss=0.2941, pruned_loss=0.06057, over 7200.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2935, pruned_loss=0.05654, over 1421825.98 frames.], batch size: 22, lr: 8.37e-04
+2022-04-28 20:57:08,584 INFO [train.py:763] (6/8) Epoch 8, batch 1600, loss[loss=0.1776, simple_loss=0.2673, pruned_loss=0.04399, over 7059.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2934, pruned_loss=0.05637, over 1420485.68 frames.], batch size: 18, lr: 8.36e-04
+2022-04-28 20:58:15,581 INFO [train.py:763] (6/8) Epoch 8, batch 1650, loss[loss=0.1996, simple_loss=0.2987, pruned_loss=0.05027, over 7126.00 frames.], tot_loss[loss=0.203, simple_loss=0.2933, pruned_loss=0.05632, over 1422207.14 frames.], batch size: 21, lr: 8.35e-04
+2022-04-28 20:59:22,337 INFO [train.py:763] (6/8) Epoch 8, batch 1700, loss[loss=0.1954, simple_loss=0.2968, pruned_loss=0.047, over 7145.00 frames.], tot_loss[loss=0.204, simple_loss=0.2947, pruned_loss=0.05661, over 1421004.38 frames.], batch size: 20, lr: 8.35e-04
+2022-04-28 21:00:28,779 INFO [train.py:763] (6/8) Epoch 8, batch 1750, loss[loss=0.1695, simple_loss=0.2644, pruned_loss=0.03724, over 7317.00 frames.], tot_loss[loss=0.2033, simple_loss=0.294, pruned_loss=0.05631, over 1422286.42 frames.], batch size: 21, lr: 8.34e-04
+2022-04-28 21:01:33,981 INFO [train.py:763] (6/8) Epoch 8, batch 1800, loss[loss=0.225, simple_loss=0.3187, pruned_loss=0.06562, over 7241.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2937, pruned_loss=0.05625, over 1419321.14 frames.], batch size: 20, lr: 8.34e-04
+2022-04-28 21:02:39,283 INFO [train.py:763] (6/8) Epoch 8, batch 1850, loss[loss=0.1929, simple_loss=0.2874, pruned_loss=0.04922, over 7236.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2955, pruned_loss=0.0564, over 1422039.07 frames.], batch size: 20, lr: 8.33e-04
+2022-04-28 21:03:44,674 INFO [train.py:763] (6/8) Epoch 8, batch 1900, loss[loss=0.1903, simple_loss=0.2783, pruned_loss=0.0512, over 7154.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2954, pruned_loss=0.05652, over 1420133.99 frames.], batch size: 19, lr: 8.33e-04
+2022-04-28 21:04:50,207 INFO [train.py:763] (6/8) Epoch 8, batch 1950, loss[loss=0.2035, simple_loss=0.3015, pruned_loss=0.05273, over 7113.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2946, pruned_loss=0.05634, over 1421267.50 frames.], batch size: 21, lr: 8.32e-04
+2022-04-28 21:05:55,503 INFO [train.py:763] (6/8) Epoch 8, batch 2000, loss[loss=0.1936, simple_loss=0.2883, pruned_loss=0.04942, over 7306.00 frames.], tot_loss[loss=0.202, simple_loss=0.2934, pruned_loss=0.05534, over 1422035.15 frames.], batch size: 24, lr: 8.32e-04
+2022-04-28 21:07:00,731 INFO [train.py:763] (6/8) Epoch 8, batch 2050, loss[loss=0.1679, simple_loss=0.248, pruned_loss=0.04384, over 7283.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2935, pruned_loss=0.05597, over 1421789.53 frames.], batch size: 17, lr: 8.31e-04
+2022-04-28 21:08:05,937 INFO [train.py:763] (6/8) Epoch 8, batch 2100, loss[loss=0.1837, simple_loss=0.2751, pruned_loss=0.04615, over 7259.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2928, pruned_loss=0.05523, over 1423428.70 frames.], batch size: 19, lr: 8.31e-04
+2022-04-28 21:09:08,025 INFO [train.py:763] (6/8) Epoch 8, batch 2150, loss[loss=0.1827, simple_loss=0.273, pruned_loss=0.0462, over 7066.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2928, pruned_loss=0.05488, over 1425818.00 frames.], batch size: 18, lr: 8.30e-04
+2022-04-28 21:10:14,558 INFO [train.py:763] (6/8) Epoch 8, batch 2200, loss[loss=0.2264, simple_loss=0.2964, pruned_loss=0.07818, over 7266.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2925, pruned_loss=0.05532, over 1423888.36 frames.], batch size: 17, lr: 8.30e-04
+2022-04-28 21:11:21,398 INFO [train.py:763] (6/8) Epoch 8, batch 2250, loss[loss=0.1719, simple_loss=0.2612, pruned_loss=0.0413, over 7156.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2923, pruned_loss=0.055, over 1424658.16 frames.], batch size: 18, lr: 8.29e-04
+2022-04-28 21:12:26,809 INFO [train.py:763] (6/8) Epoch 8, batch 2300, loss[loss=0.1974, simple_loss=0.2864, pruned_loss=0.0542, over 7144.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2925, pruned_loss=0.05515, over 1425402.38 frames.], batch size: 20, lr: 8.29e-04
+2022-04-28 21:13:32,127 INFO [train.py:763] (6/8) Epoch 8, batch 2350, loss[loss=0.2122, simple_loss=0.3164, pruned_loss=0.05401, over 6890.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2931, pruned_loss=0.05573, over 1424318.71 frames.], batch size: 31, lr: 8.28e-04
+2022-04-28 21:14:37,451 INFO [train.py:763] (6/8) Epoch 8, batch 2400, loss[loss=0.19, simple_loss=0.2786, pruned_loss=0.05075, over 7279.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2928, pruned_loss=0.05584, over 1425111.40 frames.], batch size: 18, lr: 8.28e-04
+2022-04-28 21:15:42,879 INFO [train.py:763] (6/8) Epoch 8, batch 2450, loss[loss=0.1697, simple_loss=0.2592, pruned_loss=0.04013, over 7410.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2924, pruned_loss=0.05538, over 1426233.09 frames.], batch size: 18, lr: 8.27e-04
+2022-04-28 21:16:48,165 INFO [train.py:763] (6/8) Epoch 8, batch 2500, loss[loss=0.2158, simple_loss=0.3215, pruned_loss=0.0551, over 7199.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2931, pruned_loss=0.05579, over 1424362.87 frames.], batch size: 22, lr: 8.27e-04
+2022-04-28 21:17:53,464 INFO [train.py:763] (6/8) Epoch 8, batch 2550, loss[loss=0.1687, simple_loss=0.2608, pruned_loss=0.03834, over 7149.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2924, pruned_loss=0.05574, over 1421650.45 frames.], batch size: 17, lr: 8.26e-04
+2022-04-28 21:18:58,785 INFO [train.py:763] (6/8) Epoch 8, batch 2600, loss[loss=0.2203, simple_loss=0.3135, pruned_loss=0.06353, over 7378.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2939, pruned_loss=0.05641, over 1418162.00 frames.], batch size: 23, lr: 8.25e-04
+2022-04-28 21:20:03,880 INFO [train.py:763] (6/8) Epoch 8, batch 2650, loss[loss=0.2661, simple_loss=0.3359, pruned_loss=0.09813, over 4654.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2933, pruned_loss=0.05622, over 1416667.98 frames.], batch size: 53, lr: 8.25e-04
+2022-04-28 21:21:09,315 INFO [train.py:763] (6/8) Epoch 8, batch 2700, loss[loss=0.2262, simple_loss=0.3193, pruned_loss=0.06656, over 7338.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2942, pruned_loss=0.05605, over 1418522.85 frames.], batch size: 22, lr: 8.24e-04
+2022-04-28 21:22:14,616 INFO [train.py:763] (6/8) Epoch 8, batch 2750, loss[loss=0.2027, simple_loss=0.2991, pruned_loss=0.05312, over 7326.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2943, pruned_loss=0.0561, over 1423387.92 frames.], batch size: 20, lr: 8.24e-04
+2022-04-28 21:23:20,617 INFO [train.py:763] (6/8) Epoch 8, batch 2800, loss[loss=0.2178, simple_loss=0.3112, pruned_loss=0.06223, over 7207.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2946, pruned_loss=0.05616, over 1426262.43 frames.], batch size: 22, lr: 8.23e-04
+2022-04-28 21:24:26,774 INFO [train.py:763] (6/8) Epoch 8, batch 2850, loss[loss=0.2073, simple_loss=0.2879, pruned_loss=0.06332, over 7150.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2931, pruned_loss=0.05516, over 1429116.48 frames.], batch size: 19, lr: 8.23e-04
+2022-04-28 21:25:32,045 INFO [train.py:763] (6/8) Epoch 8, batch 2900, loss[loss=0.2047, simple_loss=0.2933, pruned_loss=0.05808, over 7312.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2934, pruned_loss=0.05534, over 1427780.40 frames.], batch size: 21, lr: 8.22e-04
+2022-04-28 21:26:37,471 INFO [train.py:763] (6/8) Epoch 8, batch 2950, loss[loss=0.1895, simple_loss=0.2784, pruned_loss=0.0503, over 7278.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2943, pruned_loss=0.0562, over 1424469.55 frames.], batch size: 18, lr: 8.22e-04
+2022-04-28 21:27:43,086 INFO [train.py:763] (6/8) Epoch 8, batch 3000, loss[loss=0.2011, simple_loss=0.2982, pruned_loss=0.05202, over 7277.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2936, pruned_loss=0.05612, over 1422664.01 frames.], batch size: 24, lr: 8.21e-04
+2022-04-28 21:27:43,087 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-28 21:27:58,489 INFO [train.py:792] (6/8) Epoch 8, validation: loss=0.1715, simple_loss=0.2766, pruned_loss=0.03324, over 698248.00 frames.
+2022-04-28 21:29:04,152 INFO [train.py:763] (6/8) Epoch 8, batch 3050, loss[loss=0.1839, simple_loss=0.2845, pruned_loss=0.04161, over 7332.00 frames.], tot_loss[loss=0.2026, simple_loss=0.293, pruned_loss=0.05611, over 1419287.00 frames.], batch size: 20, lr: 8.21e-04
+2022-04-28 21:30:09,332 INFO [train.py:763] (6/8) Epoch 8, batch 3100, loss[loss=0.2255, simple_loss=0.3101, pruned_loss=0.07044, over 6764.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2955, pruned_loss=0.05738, over 1413891.20 frames.], batch size: 31, lr: 8.20e-04
+2022-04-28 21:31:14,877 INFO [train.py:763] (6/8) Epoch 8, batch 3150, loss[loss=0.1733, simple_loss=0.2637, pruned_loss=0.04147, over 7158.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2936, pruned_loss=0.05639, over 1417359.10 frames.], batch size: 19, lr: 8.20e-04
+2022-04-28 21:32:20,535 INFO [train.py:763] (6/8) Epoch 8, batch 3200, loss[loss=0.2147, simple_loss=0.3069, pruned_loss=0.06127, over 7161.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2932, pruned_loss=0.05576, over 1421571.28 frames.], batch size: 20, lr: 8.19e-04
+2022-04-28 21:33:34,632 INFO [train.py:763] (6/8) Epoch 8, batch 3250, loss[loss=0.2668, simple_loss=0.3442, pruned_loss=0.09467, over 5241.00 frames.], tot_loss[loss=0.2032, simple_loss=0.294, pruned_loss=0.05616, over 1419755.48 frames.], batch size: 53, lr: 8.19e-04
+2022-04-28 21:34:51,672 INFO [train.py:763] (6/8) Epoch 8, batch 3300, loss[loss=0.2165, simple_loss=0.3119, pruned_loss=0.06059, over 7206.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2936, pruned_loss=0.05596, over 1420282.17 frames.], batch size: 22, lr: 8.18e-04
+2022-04-28 21:36:05,889 INFO [train.py:763] (6/8) Epoch 8, batch 3350, loss[loss=0.2041, simple_loss=0.2958, pruned_loss=0.0562, over 7261.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2933, pruned_loss=0.05576, over 1423734.04 frames.], batch size: 19, lr: 8.18e-04
+2022-04-28 21:37:39,079 INFO [train.py:763] (6/8) Epoch 8, batch 3400, loss[loss=0.1805, simple_loss=0.2801, pruned_loss=0.04047, over 6711.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2946, pruned_loss=0.05653, over 1421661.70 frames.], batch size: 31, lr: 8.17e-04
+2022-04-28 21:38:45,186 INFO [train.py:763] (6/8) Epoch 8, batch 3450, loss[loss=0.1895, simple_loss=0.2798, pruned_loss=0.04963, over 7394.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2941, pruned_loss=0.05606, over 1424283.65 frames.], batch size: 18, lr: 8.17e-04
+2022-04-28 21:40:00,475 INFO [train.py:763] (6/8) Epoch 8, batch 3500, loss[loss=0.2018, simple_loss=0.297, pruned_loss=0.05329, over 7156.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2936, pruned_loss=0.05595, over 1425482.47 frames.], batch size: 19, lr: 8.16e-04
+2022-04-28 21:41:15,118 INFO [train.py:763] (6/8) Epoch 8, batch 3550, loss[loss=0.1752, simple_loss=0.2583, pruned_loss=0.04606, over 7163.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2927, pruned_loss=0.05593, over 1427256.37 frames.], batch size: 18, lr: 8.16e-04
+2022-04-28 21:42:20,513 INFO [train.py:763] (6/8) Epoch 8, batch 3600, loss[loss=0.1501, simple_loss=0.2438, pruned_loss=0.02818, over 7302.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2929, pruned_loss=0.05582, over 1425217.37 frames.], batch size: 18, lr: 8.15e-04
+2022-04-28 21:43:26,013 INFO [train.py:763] (6/8) Epoch 8, batch 3650, loss[loss=0.1817, simple_loss=0.2657, pruned_loss=0.04882, over 7125.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2924, pruned_loss=0.05567, over 1426637.97 frames.], batch size: 17, lr: 8.15e-04
+2022-04-28 21:44:39,931 INFO [train.py:763] (6/8) Epoch 8, batch 3700, loss[loss=0.2248, simple_loss=0.3053, pruned_loss=0.07211, over 7269.00 frames.], tot_loss[loss=0.203, simple_loss=0.2935, pruned_loss=0.05621, over 1427094.24 frames.], batch size: 25, lr: 8.14e-04
+2022-04-28 21:45:45,263 INFO [train.py:763] (6/8) Epoch 8, batch 3750, loss[loss=0.1629, simple_loss=0.2538, pruned_loss=0.03601, over 7433.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2944, pruned_loss=0.05662, over 1426139.28 frames.], batch size: 20, lr: 8.14e-04
+2022-04-28 21:46:51,550 INFO [train.py:763] (6/8) Epoch 8, batch 3800, loss[loss=0.2095, simple_loss=0.2908, pruned_loss=0.06414, over 7398.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2943, pruned_loss=0.05643, over 1429181.84 frames.], batch size: 18, lr: 8.13e-04
+2022-04-28 21:47:57,463 INFO [train.py:763] (6/8) Epoch 8, batch 3850, loss[loss=0.1622, simple_loss=0.2569, pruned_loss=0.03376, over 7302.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2943, pruned_loss=0.05633, over 1430539.67 frames.], batch size: 17, lr: 8.13e-04
+2022-04-28 21:49:03,317 INFO [train.py:763] (6/8) Epoch 8, batch 3900, loss[loss=0.2253, simple_loss=0.3081, pruned_loss=0.07127, over 4997.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2949, pruned_loss=0.05618, over 1427488.15 frames.], batch size: 52, lr: 8.12e-04
+2022-04-28 21:50:08,722 INFO [train.py:763] (6/8) Epoch 8, batch 3950, loss[loss=0.2342, simple_loss=0.3205, pruned_loss=0.07391, over 6721.00 frames.], tot_loss[loss=0.2029, simple_loss=0.294, pruned_loss=0.05591, over 1427878.81 frames.], batch size: 31, lr: 8.12e-04
+2022-04-28 21:51:14,836 INFO [train.py:763] (6/8) Epoch 8, batch 4000, loss[loss=0.1929, simple_loss=0.2966, pruned_loss=0.04461, over 7222.00 frames.], tot_loss[loss=0.203, simple_loss=0.2943, pruned_loss=0.05581, over 1427191.78 frames.], batch size: 21, lr: 8.11e-04
+2022-04-28 21:52:21,992 INFO [train.py:763] (6/8) Epoch 8, batch 4050, loss[loss=0.1572, simple_loss=0.2545, pruned_loss=0.02989, over 7426.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2928, pruned_loss=0.05571, over 1426278.55 frames.], batch size: 18, lr: 8.11e-04
+2022-04-28 21:53:28,736 INFO [train.py:763] (6/8) Epoch 8, batch 4100, loss[loss=0.1774, simple_loss=0.2665, pruned_loss=0.04412, over 7137.00 frames.], tot_loss[loss=0.2012, simple_loss=0.292, pruned_loss=0.05518, over 1426930.80 frames.], batch size: 17, lr: 8.10e-04
+2022-04-28 21:54:34,090 INFO [train.py:763] (6/8) Epoch 8, batch 4150, loss[loss=0.1967, simple_loss=0.2941, pruned_loss=0.04961, over 7066.00 frames.], tot_loss[loss=0.201, simple_loss=0.2918, pruned_loss=0.05511, over 1422704.21 frames.], batch size: 28, lr: 8.10e-04
+2022-04-28 21:55:39,790 INFO [train.py:763] (6/8) Epoch 8, batch 4200, loss[loss=0.206, simple_loss=0.3001, pruned_loss=0.05593, over 7333.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2912, pruned_loss=0.05494, over 1423774.62 frames.], batch size: 20, lr: 8.09e-04
+2022-04-28 21:56:45,197 INFO [train.py:763] (6/8) Epoch 8, batch 4250, loss[loss=0.18, simple_loss=0.2707, pruned_loss=0.04469, over 7143.00 frames.], tot_loss[loss=0.2009, simple_loss=0.291, pruned_loss=0.05545, over 1419436.20 frames.], batch size: 17, lr: 8.09e-04
+2022-04-28 21:57:50,932 INFO [train.py:763] (6/8) Epoch 8, batch 4300, loss[loss=0.1889, simple_loss=0.2959, pruned_loss=0.04093, over 7413.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2905, pruned_loss=0.05525, over 1414297.77 frames.], batch size: 21, lr: 8.08e-04
+2022-04-28 21:58:56,622 INFO [train.py:763] (6/8) Epoch 8, batch 4350, loss[loss=0.1785, simple_loss=0.264, pruned_loss=0.04648, over 7290.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2904, pruned_loss=0.05501, over 1420279.56 frames.], batch size: 17, lr: 8.08e-04
+2022-04-28 22:00:02,323 INFO [train.py:763] (6/8) Epoch 8, batch 4400, loss[loss=0.2324, simple_loss=0.3239, pruned_loss=0.07046, over 7103.00 frames.], tot_loss[loss=0.2, simple_loss=0.29, pruned_loss=0.05503, over 1417578.32 frames.], batch size: 28, lr: 8.07e-04
+2022-04-28 22:01:09,662 INFO [train.py:763] (6/8) Epoch 8, batch 4450, loss[loss=0.2018, simple_loss=0.2942, pruned_loss=0.05471, over 7039.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2887, pruned_loss=0.05505, over 1413389.60 frames.], batch size: 28, lr: 8.07e-04
+2022-04-28 22:02:15,955 INFO [train.py:763] (6/8) Epoch 8, batch 4500, loss[loss=0.2204, simple_loss=0.3086, pruned_loss=0.06613, over 6999.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2894, pruned_loss=0.05575, over 1394789.17 frames.], batch size: 28, lr: 8.07e-04
+2022-04-28 22:03:19,881 INFO [train.py:763] (6/8) Epoch 8, batch 4550, loss[loss=0.2298, simple_loss=0.3199, pruned_loss=0.06989, over 6272.00 frames.], tot_loss[loss=0.2064, simple_loss=0.295, pruned_loss=0.05888, over 1355375.76 frames.], batch size: 37, lr: 8.06e-04
+2022-04-28 22:04:39,799 INFO [train.py:763] (6/8) Epoch 9, batch 0, loss[loss=0.1766, simple_loss=0.2736, pruned_loss=0.03973, over 7417.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2736, pruned_loss=0.03973, over 7417.00 frames.], batch size: 21, lr: 7.75e-04
+2022-04-28 22:05:45,913 INFO [train.py:763] (6/8) Epoch 9, batch 50, loss[loss=0.2038, simple_loss=0.2972, pruned_loss=0.05521, over 7222.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2905, pruned_loss=0.05543, over 321792.01 frames.], batch size: 23, lr: 7.74e-04
+2022-04-28 22:06:51,598 INFO [train.py:763] (6/8) Epoch 9, batch 100, loss[loss=0.2537, simple_loss=0.3301, pruned_loss=0.08864, over 5115.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2914, pruned_loss=0.05623, over 557788.97 frames.], batch size: 53, lr: 7.74e-04
+2022-04-28 22:07:57,286 INFO [train.py:763] (6/8) Epoch 9, batch 150, loss[loss=0.1906, simple_loss=0.2783, pruned_loss=0.05142, over 7439.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2904, pruned_loss=0.05431, over 751721.17 frames.], batch size: 20, lr: 7.73e-04
+2022-04-28 22:09:03,721 INFO [train.py:763] (6/8) Epoch 9, batch 200, loss[loss=0.1858, simple_loss=0.2784, pruned_loss=0.04665, over 7427.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2897, pruned_loss=0.05364, over 899244.82 frames.], batch size: 20, lr: 7.73e-04
+2022-04-28 22:10:10,400 INFO [train.py:763] (6/8) Epoch 9, batch 250, loss[loss=0.2107, simple_loss=0.2901, pruned_loss=0.06564, over 7168.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2918, pruned_loss=0.05482, over 1011766.75 frames.], batch size: 18, lr: 7.72e-04
+2022-04-28 22:11:16,230 INFO [train.py:763] (6/8) Epoch 9, batch 300, loss[loss=0.1935, simple_loss=0.2926, pruned_loss=0.04715, over 7322.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2913, pruned_loss=0.05407, over 1104927.41 frames.], batch size: 20, lr: 7.72e-04
+2022-04-28 22:12:21,604 INFO [train.py:763] (6/8) Epoch 9, batch 350, loss[loss=0.1758, simple_loss=0.2821, pruned_loss=0.03472, over 7194.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2913, pruned_loss=0.05406, over 1173394.70 frames.], batch size: 23, lr: 7.71e-04
+2022-04-28 22:13:26,945 INFO [train.py:763] (6/8) Epoch 9, batch 400, loss[loss=0.1976, simple_loss=0.2951, pruned_loss=0.04999, over 7182.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2922, pruned_loss=0.054, over 1222513.11 frames.], batch size: 26, lr: 7.71e-04
+2022-04-28 22:14:32,127 INFO [train.py:763] (6/8) Epoch 9, batch 450, loss[loss=0.2126, simple_loss=0.3039, pruned_loss=0.06068, over 6287.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2926, pruned_loss=0.05383, over 1260617.53 frames.], batch size: 37, lr: 7.71e-04
+2022-04-28 22:15:37,760 INFO [train.py:763] (6/8) Epoch 9, batch 500, loss[loss=0.2086, simple_loss=0.2835, pruned_loss=0.06682, over 7171.00 frames.], tot_loss[loss=0.2005, simple_loss=0.293, pruned_loss=0.05403, over 1296676.76 frames.], batch size: 19, lr: 7.70e-04
+2022-04-28 22:16:43,394 INFO [train.py:763] (6/8) Epoch 9, batch 550, loss[loss=0.187, simple_loss=0.2726, pruned_loss=0.05065, over 7136.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2925, pruned_loss=0.05392, over 1324636.24 frames.], batch size: 17, lr: 7.70e-04
+2022-04-28 22:17:49,464 INFO [train.py:763] (6/8) Epoch 9, batch 600, loss[loss=0.1753, simple_loss=0.2608, pruned_loss=0.04488, over 7284.00 frames.], tot_loss[loss=0.201, simple_loss=0.2927, pruned_loss=0.05461, over 1346170.17 frames.], batch size: 18, lr: 7.69e-04
+2022-04-28 22:18:54,919 INFO [train.py:763] (6/8) Epoch 9, batch 650, loss[loss=0.2248, simple_loss=0.3164, pruned_loss=0.06659, over 7181.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2929, pruned_loss=0.05448, over 1362724.21 frames.], batch size: 26, lr: 7.69e-04
+2022-04-28 22:20:00,490 INFO [train.py:763] (6/8) Epoch 9, batch 700, loss[loss=0.1891, simple_loss=0.2916, pruned_loss=0.04331, over 7334.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2924, pruned_loss=0.05425, over 1377202.71 frames.], batch size: 25, lr: 7.68e-04
+2022-04-28 22:21:06,843 INFO [train.py:763] (6/8) Epoch 9, batch 750, loss[loss=0.2122, simple_loss=0.2844, pruned_loss=0.07002, over 7436.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2918, pruned_loss=0.05416, over 1387069.75 frames.], batch size: 20, lr: 7.68e-04
+2022-04-28 22:22:12,200 INFO [train.py:763] (6/8) Epoch 9, batch 800, loss[loss=0.2056, simple_loss=0.2973, pruned_loss=0.05696, over 7290.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2914, pruned_loss=0.0544, over 1394121.36 frames.], batch size: 24, lr: 7.67e-04
+2022-04-28 22:23:17,413 INFO [train.py:763] (6/8) Epoch 9, batch 850, loss[loss=0.2273, simple_loss=0.313, pruned_loss=0.07087, over 6396.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2914, pruned_loss=0.05423, over 1396817.24 frames.], batch size: 37, lr: 7.67e-04
+2022-04-28 22:24:22,757 INFO [train.py:763] (6/8) Epoch 9, batch 900, loss[loss=0.1953, simple_loss=0.3013, pruned_loss=0.04463, over 7306.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2915, pruned_loss=0.05435, over 1406706.03 frames.], batch size: 21, lr: 7.66e-04
+2022-04-28 22:25:27,954 INFO [train.py:763] (6/8) Epoch 9, batch 950, loss[loss=0.21, simple_loss=0.3088, pruned_loss=0.0556, over 7201.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2919, pruned_loss=0.05468, over 1406267.43 frames.], batch size: 26, lr: 7.66e-04
+2022-04-28 22:26:34,039 INFO [train.py:763] (6/8) Epoch 9, batch 1000, loss[loss=0.1695, simple_loss=0.2685, pruned_loss=0.03523, over 7323.00 frames.], tot_loss[loss=0.1995, simple_loss=0.291, pruned_loss=0.054, over 1413548.71 frames.], batch size: 20, lr: 7.66e-04
+2022-04-28 22:27:40,364 INFO [train.py:763] (6/8) Epoch 9, batch 1050, loss[loss=0.2262, simple_loss=0.3319, pruned_loss=0.06026, over 7035.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2905, pruned_loss=0.05351, over 1415611.59 frames.], batch size: 28, lr: 7.65e-04
+2022-04-28 22:28:46,002 INFO [train.py:763] (6/8) Epoch 9, batch 1100, loss[loss=0.2097, simple_loss=0.3067, pruned_loss=0.05636, over 7051.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2917, pruned_loss=0.05372, over 1416063.83 frames.], batch size: 28, lr: 7.65e-04
+2022-04-28 22:29:52,331 INFO [train.py:763] (6/8) Epoch 9, batch 1150, loss[loss=0.2061, simple_loss=0.3027, pruned_loss=0.05476, over 7329.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2916, pruned_loss=0.0537, over 1420776.14 frames.], batch size: 20, lr: 7.64e-04
+2022-04-28 22:30:57,646 INFO [train.py:763] (6/8) Epoch 9, batch 1200, loss[loss=0.2222, simple_loss=0.3127, pruned_loss=0.06585, over 7201.00 frames.], tot_loss[loss=0.2, simple_loss=0.2921, pruned_loss=0.05396, over 1420001.39 frames.], batch size: 23, lr: 7.64e-04
+2022-04-28 22:32:04,444 INFO [train.py:763] (6/8) Epoch 9, batch 1250, loss[loss=0.1955, simple_loss=0.2775, pruned_loss=0.05675, over 7270.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2918, pruned_loss=0.05425, over 1418694.21 frames.], batch size: 17, lr: 7.63e-04
+2022-04-28 22:33:11,157 INFO [train.py:763] (6/8) Epoch 9, batch 1300, loss[loss=0.1681, simple_loss=0.2458, pruned_loss=0.04524, over 7004.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2907, pruned_loss=0.05425, over 1417215.80 frames.], batch size: 16, lr: 7.63e-04
+2022-04-28 22:34:16,572 INFO [train.py:763] (6/8) Epoch 9, batch 1350, loss[loss=0.1996, simple_loss=0.3008, pruned_loss=0.04919, over 7309.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2911, pruned_loss=0.05453, over 1415551.01 frames.], batch size: 21, lr: 7.62e-04
+2022-04-28 22:35:21,720 INFO [train.py:763] (6/8) Epoch 9, batch 1400, loss[loss=0.1853, simple_loss=0.2748, pruned_loss=0.04791, over 7119.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2915, pruned_loss=0.05435, over 1418817.32 frames.], batch size: 21, lr: 7.62e-04
+2022-04-28 22:36:27,461 INFO [train.py:763] (6/8) Epoch 9, batch 1450, loss[loss=0.1901, simple_loss=0.2771, pruned_loss=0.05157, over 7285.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2911, pruned_loss=0.05406, over 1420185.99 frames.], batch size: 25, lr: 7.62e-04
+2022-04-28 22:37:33,362 INFO [train.py:763] (6/8) Epoch 9, batch 1500, loss[loss=0.2139, simple_loss=0.3005, pruned_loss=0.06369, over 5000.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2913, pruned_loss=0.05398, over 1415796.12 frames.], batch size: 52, lr: 7.61e-04
+2022-04-28 22:38:38,709 INFO [train.py:763] (6/8) Epoch 9, batch 1550, loss[loss=0.1668, simple_loss=0.2668, pruned_loss=0.03339, over 7370.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2914, pruned_loss=0.05355, over 1419068.30 frames.], batch size: 19, lr: 7.61e-04
+2022-04-28 22:39:43,990 INFO [train.py:763] (6/8) Epoch 9, batch 1600, loss[loss=0.2094, simple_loss=0.3006, pruned_loss=0.05912, over 7258.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2915, pruned_loss=0.05349, over 1417573.66 frames.], batch size: 19, lr: 7.60e-04
+2022-04-28 22:40:50,098 INFO [train.py:763] (6/8) Epoch 9, batch 1650, loss[loss=0.1872, simple_loss=0.2845, pruned_loss=0.04496, over 7403.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2908, pruned_loss=0.05319, over 1415328.18 frames.], batch size: 21, lr: 7.60e-04
+2022-04-28 22:41:56,342 INFO [train.py:763] (6/8) Epoch 9, batch 1700, loss[loss=0.2266, simple_loss=0.3261, pruned_loss=0.06353, over 7296.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2907, pruned_loss=0.05345, over 1413846.37 frames.], batch size: 24, lr: 7.59e-04
+2022-04-28 22:43:01,519 INFO [train.py:763] (6/8) Epoch 9, batch 1750, loss[loss=0.1579, simple_loss=0.248, pruned_loss=0.03392, over 7238.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2915, pruned_loss=0.05458, over 1406059.10 frames.], batch size: 16, lr: 7.59e-04
+2022-04-28 22:44:07,087 INFO [train.py:763] (6/8) Epoch 9, batch 1800, loss[loss=0.2111, simple_loss=0.2915, pruned_loss=0.06538, over 7363.00 frames.], tot_loss[loss=0.2, simple_loss=0.2913, pruned_loss=0.05437, over 1410736.41 frames.], batch size: 19, lr: 7.59e-04
+2022-04-28 22:45:14,105 INFO [train.py:763] (6/8) Epoch 9, batch 1850, loss[loss=0.1842, simple_loss=0.2701, pruned_loss=0.04913, over 7357.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2914, pruned_loss=0.05492, over 1411603.15 frames.], batch size: 19, lr: 7.58e-04
+2022-04-28 22:46:21,655 INFO [train.py:763] (6/8) Epoch 9, batch 1900, loss[loss=0.2148, simple_loss=0.2951, pruned_loss=0.06724, over 7275.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2905, pruned_loss=0.05416, over 1416151.37 frames.], batch size: 18, lr: 7.58e-04
+2022-04-28 22:47:28,655 INFO [train.py:763] (6/8) Epoch 9, batch 1950, loss[loss=0.2061, simple_loss=0.3189, pruned_loss=0.04669, over 7196.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2898, pruned_loss=0.05359, over 1414953.79 frames.], batch size: 23, lr: 7.57e-04
+2022-04-28 22:48:34,057 INFO [train.py:763] (6/8) Epoch 9, batch 2000, loss[loss=0.1777, simple_loss=0.2759, pruned_loss=0.0398, over 7231.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2887, pruned_loss=0.05299, over 1417925.42 frames.], batch size: 20, lr: 7.57e-04
+2022-04-28 22:49:39,700 INFO [train.py:763] (6/8) Epoch 9, batch 2050, loss[loss=0.1822, simple_loss=0.2823, pruned_loss=0.04102, over 7194.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2886, pruned_loss=0.05288, over 1419579.64 frames.], batch size: 23, lr: 7.56e-04
+2022-04-28 22:50:45,165 INFO [train.py:763] (6/8) Epoch 9, batch 2100, loss[loss=0.194, simple_loss=0.2863, pruned_loss=0.0509, over 7149.00 frames.], tot_loss[loss=0.1963, simple_loss=0.288, pruned_loss=0.05225, over 1424462.39 frames.], batch size: 20, lr: 7.56e-04
+2022-04-28 22:51:50,838 INFO [train.py:763] (6/8) Epoch 9, batch 2150, loss[loss=0.1537, simple_loss=0.2479, pruned_loss=0.02979, over 7399.00 frames.], tot_loss[loss=0.1947, simple_loss=0.287, pruned_loss=0.05124, over 1426683.70 frames.], batch size: 18, lr: 7.56e-04
+2022-04-28 22:52:56,059 INFO [train.py:763] (6/8) Epoch 9, batch 2200, loss[loss=0.1648, simple_loss=0.266, pruned_loss=0.03179, over 6628.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2882, pruned_loss=0.05177, over 1427203.76 frames.], batch size: 38, lr: 7.55e-04
+2022-04-28 22:54:01,588 INFO [train.py:763] (6/8) Epoch 9, batch 2250, loss[loss=0.1787, simple_loss=0.2736, pruned_loss=0.04191, over 7322.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2878, pruned_loss=0.05163, over 1429217.46 frames.], batch size: 21, lr: 7.55e-04
+2022-04-28 22:55:07,221 INFO [train.py:763] (6/8) Epoch 9, batch 2300, loss[loss=0.1896, simple_loss=0.2941, pruned_loss=0.04256, over 7140.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2884, pruned_loss=0.05201, over 1426505.68 frames.], batch size: 20, lr: 7.54e-04
+2022-04-28 22:56:13,148 INFO [train.py:763] (6/8) Epoch 9, batch 2350, loss[loss=0.1937, simple_loss=0.2922, pruned_loss=0.04759, over 7217.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2878, pruned_loss=0.05225, over 1423908.15 frames.], batch size: 22, lr: 7.54e-04
+2022-04-28 22:57:18,361 INFO [train.py:763] (6/8) Epoch 9, batch 2400, loss[loss=0.1575, simple_loss=0.2518, pruned_loss=0.0316, over 7278.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2882, pruned_loss=0.05203, over 1426153.85 frames.], batch size: 18, lr: 7.53e-04
+2022-04-28 22:58:24,895 INFO [train.py:763] (6/8) Epoch 9, batch 2450, loss[loss=0.1713, simple_loss=0.2615, pruned_loss=0.04059, over 7061.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2887, pruned_loss=0.05196, over 1429219.95 frames.], batch size: 18, lr: 7.53e-04
+2022-04-28 22:59:30,588 INFO [train.py:763] (6/8) Epoch 9, batch 2500, loss[loss=0.1815, simple_loss=0.2826, pruned_loss=0.04018, over 7321.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2883, pruned_loss=0.05211, over 1427773.83 frames.], batch size: 21, lr: 7.53e-04
+2022-04-28 23:00:35,850 INFO [train.py:763] (6/8) Epoch 9, batch 2550, loss[loss=0.2156, simple_loss=0.3072, pruned_loss=0.06196, over 7227.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2885, pruned_loss=0.05266, over 1425822.76 frames.], batch size: 21, lr: 7.52e-04
+2022-04-28 23:01:42,063 INFO [train.py:763] (6/8) Epoch 9, batch 2600, loss[loss=0.2356, simple_loss=0.315, pruned_loss=0.07812, over 7138.00 frames.], tot_loss[loss=0.1975, simple_loss=0.289, pruned_loss=0.05297, over 1429630.08 frames.], batch size: 26, lr: 7.52e-04
+2022-04-28 23:02:47,160 INFO [train.py:763] (6/8) Epoch 9, batch 2650, loss[loss=0.2076, simple_loss=0.3038, pruned_loss=0.05569, over 7326.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2903, pruned_loss=0.05354, over 1424926.58 frames.], batch size: 22, lr: 7.51e-04
+2022-04-28 23:03:53,451 INFO [train.py:763] (6/8) Epoch 9, batch 2700, loss[loss=0.2327, simple_loss=0.3214, pruned_loss=0.07201, over 6907.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2891, pruned_loss=0.05311, over 1426574.12 frames.], batch size: 31, lr: 7.51e-04
+2022-04-28 23:04:58,885 INFO [train.py:763] (6/8) Epoch 9, batch 2750, loss[loss=0.1914, simple_loss=0.286, pruned_loss=0.04836, over 6876.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2883, pruned_loss=0.05292, over 1424055.06 frames.], batch size: 32, lr: 7.50e-04
+2022-04-28 23:06:04,505 INFO [train.py:763] (6/8) Epoch 9, batch 2800, loss[loss=0.2265, simple_loss=0.3189, pruned_loss=0.06699, over 7382.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2879, pruned_loss=0.0526, over 1428717.95 frames.], batch size: 23, lr: 7.50e-04
+2022-04-28 23:07:09,872 INFO [train.py:763] (6/8) Epoch 9, batch 2850, loss[loss=0.2427, simple_loss=0.3333, pruned_loss=0.07605, over 7344.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2888, pruned_loss=0.05301, over 1426662.33 frames.], batch size: 22, lr: 7.50e-04
+2022-04-28 23:08:15,556 INFO [train.py:763] (6/8) Epoch 9, batch 2900, loss[loss=0.2161, simple_loss=0.3126, pruned_loss=0.05979, over 7109.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2882, pruned_loss=0.05242, over 1426308.23 frames.], batch size: 21, lr: 7.49e-04
+2022-04-28 23:09:22,055 INFO [train.py:763] (6/8) Epoch 9, batch 2950, loss[loss=0.1744, simple_loss=0.2715, pruned_loss=0.03868, over 7285.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2879, pruned_loss=0.05254, over 1426168.50 frames.], batch size: 18, lr: 7.49e-04
+2022-04-28 23:10:29,030 INFO [train.py:763] (6/8) Epoch 9, batch 3000, loss[loss=0.1559, simple_loss=0.2475, pruned_loss=0.03217, over 7292.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2879, pruned_loss=0.05278, over 1425885.49 frames.], batch size: 17, lr: 7.48e-04
+2022-04-28 23:10:29,031 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-28 23:10:44,553 INFO [train.py:792] (6/8) Epoch 9, validation: loss=0.1713, simple_loss=0.276, pruned_loss=0.03324, over 698248.00 frames.
+2022-04-28 23:11:50,378 INFO [train.py:763] (6/8) Epoch 9, batch 3050, loss[loss=0.1939, simple_loss=0.2873, pruned_loss=0.05024, over 7152.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2884, pruned_loss=0.05292, over 1425669.18 frames.], batch size: 19, lr: 7.48e-04
+2022-04-28 23:12:55,856 INFO [train.py:763] (6/8) Epoch 9, batch 3100, loss[loss=0.1871, simple_loss=0.2935, pruned_loss=0.04035, over 7111.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2882, pruned_loss=0.05235, over 1428855.91 frames.], batch size: 21, lr: 7.47e-04
+2022-04-28 23:14:01,346 INFO [train.py:763] (6/8) Epoch 9, batch 3150, loss[loss=0.1896, simple_loss=0.2835, pruned_loss=0.04781, over 7319.00 frames.], tot_loss[loss=0.1962, simple_loss=0.288, pruned_loss=0.05225, over 1424945.02 frames.], batch size: 21, lr: 7.47e-04
+2022-04-28 23:15:07,616 INFO [train.py:763] (6/8) Epoch 9, batch 3200, loss[loss=0.2198, simple_loss=0.3047, pruned_loss=0.06749, over 7238.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2876, pruned_loss=0.05188, over 1425475.26 frames.], batch size: 20, lr: 7.47e-04
+2022-04-28 23:16:13,887 INFO [train.py:763] (6/8) Epoch 9, batch 3250, loss[loss=0.2102, simple_loss=0.3123, pruned_loss=0.05404, over 7411.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2889, pruned_loss=0.05268, over 1426425.32 frames.], batch size: 21, lr: 7.46e-04
+2022-04-28 23:17:19,392 INFO [train.py:763] (6/8) Epoch 9, batch 3300, loss[loss=0.2157, simple_loss=0.3136, pruned_loss=0.05893, over 7198.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2893, pruned_loss=0.05266, over 1428335.84 frames.], batch size: 22, lr: 7.46e-04
+2022-04-28 23:18:25,154 INFO [train.py:763] (6/8) Epoch 9, batch 3350, loss[loss=0.2287, simple_loss=0.3191, pruned_loss=0.06911, over 7206.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2889, pruned_loss=0.0521, over 1428933.05 frames.], batch size: 23, lr: 7.45e-04
+2022-04-28 23:19:31,231 INFO [train.py:763] (6/8) Epoch 9, batch 3400, loss[loss=0.158, simple_loss=0.2468, pruned_loss=0.03462, over 7292.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2893, pruned_loss=0.0525, over 1425010.75 frames.], batch size: 17, lr: 7.45e-04
+2022-04-28 23:20:36,538 INFO [train.py:763] (6/8) Epoch 9, batch 3450, loss[loss=0.1931, simple_loss=0.2902, pruned_loss=0.04805, over 7318.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2893, pruned_loss=0.05254, over 1423856.96 frames.], batch size: 24, lr: 7.45e-04
+2022-04-28 23:21:42,132 INFO [train.py:763] (6/8) Epoch 9, batch 3500, loss[loss=0.2016, simple_loss=0.3072, pruned_loss=0.04799, over 7418.00 frames.], tot_loss[loss=0.1973, simple_loss=0.29, pruned_loss=0.05227, over 1424447.62 frames.], batch size: 21, lr: 7.44e-04
+2022-04-28 23:22:49,854 INFO [train.py:763] (6/8) Epoch 9, batch 3550, loss[loss=0.2163, simple_loss=0.3001, pruned_loss=0.06622, over 7080.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2888, pruned_loss=0.0521, over 1427097.76 frames.], batch size: 28, lr: 7.44e-04
+2022-04-28 23:23:55,517 INFO [train.py:763] (6/8) Epoch 9, batch 3600, loss[loss=0.2171, simple_loss=0.3064, pruned_loss=0.06388, over 7052.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2878, pruned_loss=0.05177, over 1427264.62 frames.], batch size: 28, lr: 7.43e-04
+2022-04-28 23:25:02,073 INFO [train.py:763] (6/8) Epoch 9, batch 3650, loss[loss=0.1621, simple_loss=0.2576, pruned_loss=0.03328, over 7061.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2875, pruned_loss=0.05193, over 1423036.72 frames.], batch size: 18, lr: 7.43e-04
+2022-04-28 23:26:07,308 INFO [train.py:763] (6/8) Epoch 9, batch 3700, loss[loss=0.1612, simple_loss=0.2475, pruned_loss=0.03744, over 7284.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2878, pruned_loss=0.05202, over 1425657.35 frames.], batch size: 17, lr: 7.43e-04
+2022-04-28 23:27:12,606 INFO [train.py:763] (6/8) Epoch 9, batch 3750, loss[loss=0.1987, simple_loss=0.2957, pruned_loss=0.05087, over 7165.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2888, pruned_loss=0.05229, over 1427679.31 frames.], batch size: 19, lr: 7.42e-04
+2022-04-28 23:28:17,825 INFO [train.py:763] (6/8) Epoch 9, batch 3800, loss[loss=0.2005, simple_loss=0.2925, pruned_loss=0.05426, over 7428.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2888, pruned_loss=0.05232, over 1426656.87 frames.], batch size: 20, lr: 7.42e-04
+2022-04-28 23:29:23,011 INFO [train.py:763] (6/8) Epoch 9, batch 3850, loss[loss=0.1592, simple_loss=0.2595, pruned_loss=0.02944, over 7062.00 frames.], tot_loss[loss=0.197, simple_loss=0.2895, pruned_loss=0.05223, over 1425768.44 frames.], batch size: 18, lr: 7.41e-04
+2022-04-28 23:30:28,555 INFO [train.py:763] (6/8) Epoch 9, batch 3900, loss[loss=0.1981, simple_loss=0.2829, pruned_loss=0.05669, over 7156.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2892, pruned_loss=0.05199, over 1426861.06 frames.], batch size: 19, lr: 7.41e-04
+2022-04-28 23:31:35,178 INFO [train.py:763] (6/8) Epoch 9, batch 3950, loss[loss=0.2256, simple_loss=0.3033, pruned_loss=0.07397, over 5130.00 frames.], tot_loss[loss=0.197, simple_loss=0.2892, pruned_loss=0.05235, over 1420467.40 frames.], batch size: 54, lr: 7.41e-04
+2022-04-28 23:32:42,032 INFO [train.py:763] (6/8) Epoch 9, batch 4000, loss[loss=0.2022, simple_loss=0.2854, pruned_loss=0.05948, over 7262.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2894, pruned_loss=0.05249, over 1421216.23 frames.], batch size: 19, lr: 7.40e-04
+2022-04-28 23:33:47,289 INFO [train.py:763] (6/8) Epoch 9, batch 4050, loss[loss=0.1568, simple_loss=0.2543, pruned_loss=0.02966, over 7138.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2885, pruned_loss=0.05235, over 1422279.93 frames.], batch size: 17, lr: 7.40e-04
+2022-04-28 23:34:53,528 INFO [train.py:763] (6/8) Epoch 9, batch 4100, loss[loss=0.1857, simple_loss=0.2931, pruned_loss=0.03913, over 7317.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2881, pruned_loss=0.05168, over 1424421.51 frames.], batch size: 21, lr: 7.39e-04
+2022-04-28 23:35:59,484 INFO [train.py:763] (6/8) Epoch 9, batch 4150, loss[loss=0.1511, simple_loss=0.2504, pruned_loss=0.02587, over 7402.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2874, pruned_loss=0.0512, over 1425123.22 frames.], batch size: 18, lr: 7.39e-04
+2022-04-28 23:37:04,703 INFO [train.py:763] (6/8) Epoch 9, batch 4200, loss[loss=0.2021, simple_loss=0.2895, pruned_loss=0.0573, over 7270.00 frames.], tot_loss[loss=0.1958, simple_loss=0.288, pruned_loss=0.05181, over 1427021.41 frames.], batch size: 24, lr: 7.39e-04
+2022-04-28 23:38:10,598 INFO [train.py:763] (6/8) Epoch 9, batch 4250, loss[loss=0.1838, simple_loss=0.2669, pruned_loss=0.05032, over 7284.00 frames.], tot_loss[loss=0.1968, simple_loss=0.289, pruned_loss=0.05235, over 1422942.17 frames.], batch size: 17, lr: 7.38e-04
+2022-04-28 23:39:16,465 INFO [train.py:763] (6/8) Epoch 9, batch 4300, loss[loss=0.1969, simple_loss=0.2987, pruned_loss=0.04752, over 7269.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2894, pruned_loss=0.0524, over 1415806.50 frames.], batch size: 24, lr: 7.38e-04
+2022-04-28 23:40:22,492 INFO [train.py:763] (6/8) Epoch 9, batch 4350, loss[loss=0.2509, simple_loss=0.3355, pruned_loss=0.08315, over 4867.00 frames.], tot_loss[loss=0.198, simple_loss=0.2902, pruned_loss=0.05285, over 1405931.22 frames.], batch size: 52, lr: 7.37e-04
+2022-04-28 23:41:28,473 INFO [train.py:763] (6/8) Epoch 9, batch 4400, loss[loss=0.2018, simple_loss=0.3095, pruned_loss=0.047, over 7211.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2914, pruned_loss=0.054, over 1409277.38 frames.], batch size: 22, lr: 7.37e-04
+2022-04-28 23:42:35,222 INFO [train.py:763] (6/8) Epoch 9, batch 4450, loss[loss=0.2423, simple_loss=0.3286, pruned_loss=0.078, over 4928.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2924, pruned_loss=0.05497, over 1394055.24 frames.], batch size: 52, lr: 7.37e-04
+2022-04-28 23:43:41,393 INFO [train.py:763] (6/8) Epoch 9, batch 4500, loss[loss=0.2001, simple_loss=0.2972, pruned_loss=0.05148, over 7136.00 frames.], tot_loss[loss=0.1999, simple_loss=0.291, pruned_loss=0.05444, over 1391661.36 frames.], batch size: 20, lr: 7.36e-04
+2022-04-28 23:44:47,992 INFO [train.py:763] (6/8) Epoch 9, batch 4550, loss[loss=0.2213, simple_loss=0.3171, pruned_loss=0.06274, over 7144.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2912, pruned_loss=0.0551, over 1372226.29 frames.], batch size: 26, lr: 7.36e-04
+2022-04-28 23:46:26,285 INFO [train.py:763] (6/8) Epoch 10, batch 0, loss[loss=0.2401, simple_loss=0.3228, pruned_loss=0.07868, over 7417.00 frames.], tot_loss[loss=0.2401, simple_loss=0.3228, pruned_loss=0.07868, over 7417.00 frames.], batch size: 20, lr: 7.08e-04
+2022-04-28 23:47:32,326 INFO [train.py:763] (6/8) Epoch 10, batch 50, loss[loss=0.1978, simple_loss=0.2836, pruned_loss=0.05604, over 7431.00 frames.], tot_loss[loss=0.1952, simple_loss=0.29, pruned_loss=0.05018, over 322431.29 frames.], batch size: 20, lr: 7.08e-04
+2022-04-28 23:48:38,947 INFO [train.py:763] (6/8) Epoch 10, batch 100, loss[loss=0.1515, simple_loss=0.2387, pruned_loss=0.03212, over 7275.00 frames.], tot_loss[loss=0.1944, simple_loss=0.289, pruned_loss=0.04988, over 566683.95 frames.], batch size: 18, lr: 7.08e-04
+2022-04-28 23:49:55,134 INFO [train.py:763] (6/8) Epoch 10, batch 150, loss[loss=0.1926, simple_loss=0.2821, pruned_loss=0.05153, over 6766.00 frames.], tot_loss[loss=0.1968, simple_loss=0.291, pruned_loss=0.05126, over 760061.70 frames.], batch size: 15, lr: 7.07e-04
+2022-04-28 23:51:18,547 INFO [train.py:763] (6/8) Epoch 10, batch 200, loss[loss=0.1649, simple_loss=0.2597, pruned_loss=0.03501, over 7424.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2896, pruned_loss=0.05067, over 907594.77 frames.], batch size: 18, lr: 7.07e-04
+2022-04-28 23:52:32,863 INFO [train.py:763] (6/8) Epoch 10, batch 250, loss[loss=0.1911, simple_loss=0.2851, pruned_loss=0.0485, over 6310.00 frames.], tot_loss[loss=0.195, simple_loss=0.2886, pruned_loss=0.05069, over 1023107.68 frames.], batch size: 37, lr: 7.06e-04
+2022-04-28 23:53:48,227 INFO [train.py:763] (6/8) Epoch 10, batch 300, loss[loss=0.2354, simple_loss=0.3131, pruned_loss=0.07882, over 5335.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2872, pruned_loss=0.04993, over 1114227.25 frames.], batch size: 52, lr: 7.06e-04
+2022-04-28 23:54:53,618 INFO [train.py:763] (6/8) Epoch 10, batch 350, loss[loss=0.2174, simple_loss=0.2933, pruned_loss=0.07073, over 6760.00 frames.], tot_loss[loss=0.194, simple_loss=0.2873, pruned_loss=0.0504, over 1186883.46 frames.], batch size: 31, lr: 7.06e-04
+2022-04-28 23:56:17,501 INFO [train.py:763] (6/8) Epoch 10, batch 400, loss[loss=0.1774, simple_loss=0.2743, pruned_loss=0.04024, over 7416.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2869, pruned_loss=0.05021, over 1240673.80 frames.], batch size: 20, lr: 7.05e-04
+2022-04-28 23:57:23,253 INFO [train.py:763] (6/8) Epoch 10, batch 450, loss[loss=0.1968, simple_loss=0.285, pruned_loss=0.05427, over 7246.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2854, pruned_loss=0.04984, over 1280457.04 frames.], batch size: 20, lr: 7.05e-04
+2022-04-28 23:58:37,639 INFO [train.py:763] (6/8) Epoch 10, batch 500, loss[loss=0.1984, simple_loss=0.29, pruned_loss=0.05339, over 7322.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2847, pruned_loss=0.04955, over 1314920.71 frames.], batch size: 20, lr: 7.04e-04
+2022-04-28 23:59:42,724 INFO [train.py:763] (6/8) Epoch 10, batch 550, loss[loss=0.1719, simple_loss=0.2637, pruned_loss=0.04008, over 7076.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2853, pruned_loss=0.04977, over 1340113.96 frames.], batch size: 18, lr: 7.04e-04
+2022-04-29 00:00:47,813 INFO [train.py:763] (6/8) Epoch 10, batch 600, loss[loss=0.1594, simple_loss=0.2469, pruned_loss=0.03596, over 7001.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2863, pruned_loss=0.05026, over 1359649.30 frames.], batch size: 16, lr: 7.04e-04
+2022-04-29 00:01:53,008 INFO [train.py:763] (6/8) Epoch 10, batch 650, loss[loss=0.1768, simple_loss=0.2547, pruned_loss=0.04943, over 7139.00 frames.], tot_loss[loss=0.195, simple_loss=0.2872, pruned_loss=0.05139, over 1364063.94 frames.], batch size: 17, lr: 7.03e-04
+2022-04-29 00:02:58,037 INFO [train.py:763] (6/8) Epoch 10, batch 700, loss[loss=0.1794, simple_loss=0.2641, pruned_loss=0.04729, over 7216.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2873, pruned_loss=0.05127, over 1374732.73 frames.], batch size: 16, lr: 7.03e-04
+2022-04-29 00:04:03,195 INFO [train.py:763] (6/8) Epoch 10, batch 750, loss[loss=0.1961, simple_loss=0.2997, pruned_loss=0.04624, over 7139.00 frames.], tot_loss[loss=0.195, simple_loss=0.2875, pruned_loss=0.05125, over 1381996.22 frames.], batch size: 20, lr: 7.03e-04
+2022-04-29 00:05:08,474 INFO [train.py:763] (6/8) Epoch 10, batch 800, loss[loss=0.2177, simple_loss=0.3049, pruned_loss=0.06528, over 7162.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2876, pruned_loss=0.05127, over 1393884.02 frames.], batch size: 26, lr: 7.02e-04
+2022-04-29 00:06:13,826 INFO [train.py:763] (6/8) Epoch 10, batch 850, loss[loss=0.19, simple_loss=0.2898, pruned_loss=0.04511, over 7330.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2872, pruned_loss=0.05099, over 1398280.45 frames.], batch size: 20, lr: 7.02e-04
+2022-04-29 00:07:19,244 INFO [train.py:763] (6/8) Epoch 10, batch 900, loss[loss=0.166, simple_loss=0.2602, pruned_loss=0.03592, over 7430.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2867, pruned_loss=0.05106, over 1406855.77 frames.], batch size: 20, lr: 7.02e-04
+2022-04-29 00:08:24,542 INFO [train.py:763] (6/8) Epoch 10, batch 950, loss[loss=0.1702, simple_loss=0.271, pruned_loss=0.03469, over 6995.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2868, pruned_loss=0.05137, over 1408629.32 frames.], batch size: 16, lr: 7.01e-04
+2022-04-29 00:09:29,921 INFO [train.py:763] (6/8) Epoch 10, batch 1000, loss[loss=0.2096, simple_loss=0.3026, pruned_loss=0.05824, over 7289.00 frames.], tot_loss[loss=0.1947, simple_loss=0.287, pruned_loss=0.05118, over 1413353.02 frames.], batch size: 25, lr: 7.01e-04
+2022-04-29 00:10:35,518 INFO [train.py:763] (6/8) Epoch 10, batch 1050, loss[loss=0.1954, simple_loss=0.2794, pruned_loss=0.05574, over 7261.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2882, pruned_loss=0.052, over 1408354.42 frames.], batch size: 19, lr: 7.00e-04
+2022-04-29 00:11:41,111 INFO [train.py:763] (6/8) Epoch 10, batch 1100, loss[loss=0.1595, simple_loss=0.2547, pruned_loss=0.03214, over 7153.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2877, pruned_loss=0.05133, over 1412676.99 frames.], batch size: 18, lr: 7.00e-04
+2022-04-29 00:12:46,586 INFO [train.py:763] (6/8) Epoch 10, batch 1150, loss[loss=0.2014, simple_loss=0.2884, pruned_loss=0.05724, over 7065.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2873, pruned_loss=0.05127, over 1416144.26 frames.], batch size: 18, lr: 7.00e-04
+2022-04-29 00:13:53,260 INFO [train.py:763] (6/8) Epoch 10, batch 1200, loss[loss=0.1545, simple_loss=0.249, pruned_loss=0.03002, over 7190.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2857, pruned_loss=0.05073, over 1419456.90 frames.], batch size: 16, lr: 6.99e-04
+2022-04-29 00:14:58,981 INFO [train.py:763] (6/8) Epoch 10, batch 1250, loss[loss=0.165, simple_loss=0.2551, pruned_loss=0.03741, over 7147.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2847, pruned_loss=0.04981, over 1423184.38 frames.], batch size: 17, lr: 6.99e-04
+2022-04-29 00:16:04,764 INFO [train.py:763] (6/8) Epoch 10, batch 1300, loss[loss=0.186, simple_loss=0.2914, pruned_loss=0.04032, over 7310.00 frames.], tot_loss[loss=0.1924, simple_loss=0.285, pruned_loss=0.04993, over 1420106.81 frames.], batch size: 21, lr: 6.99e-04
+2022-04-29 00:17:11,851 INFO [train.py:763] (6/8) Epoch 10, batch 1350, loss[loss=0.1911, simple_loss=0.2889, pruned_loss=0.0467, over 7314.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2865, pruned_loss=0.05034, over 1422996.53 frames.], batch size: 21, lr: 6.98e-04
+2022-04-29 00:18:18,357 INFO [train.py:763] (6/8) Epoch 10, batch 1400, loss[loss=0.1641, simple_loss=0.2608, pruned_loss=0.03371, over 7147.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2859, pruned_loss=0.04961, over 1426435.49 frames.], batch size: 19, lr: 6.98e-04
+2022-04-29 00:19:25,281 INFO [train.py:763] (6/8) Epoch 10, batch 1450, loss[loss=0.144, simple_loss=0.2421, pruned_loss=0.02295, over 7283.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2857, pruned_loss=0.04929, over 1427382.75 frames.], batch size: 17, lr: 6.97e-04
+2022-04-29 00:20:30,751 INFO [train.py:763] (6/8) Epoch 10, batch 1500, loss[loss=0.1832, simple_loss=0.2856, pruned_loss=0.04039, over 7051.00 frames.], tot_loss[loss=0.1923, simple_loss=0.286, pruned_loss=0.04932, over 1424723.10 frames.], batch size: 28, lr: 6.97e-04
+2022-04-29 00:21:36,430 INFO [train.py:763] (6/8) Epoch 10, batch 1550, loss[loss=0.1781, simple_loss=0.2728, pruned_loss=0.0417, over 7427.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2865, pruned_loss=0.04964, over 1423420.60 frames.], batch size: 20, lr: 6.97e-04
+2022-04-29 00:22:41,608 INFO [train.py:763] (6/8) Epoch 10, batch 1600, loss[loss=0.2294, simple_loss=0.301, pruned_loss=0.07891, over 6716.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2862, pruned_loss=0.04974, over 1418541.76 frames.], batch size: 31, lr: 6.96e-04
+2022-04-29 00:23:47,729 INFO [train.py:763] (6/8) Epoch 10, batch 1650, loss[loss=0.1655, simple_loss=0.2557, pruned_loss=0.0376, over 6784.00 frames.], tot_loss[loss=0.192, simple_loss=0.2849, pruned_loss=0.04954, over 1418459.90 frames.], batch size: 15, lr: 6.96e-04
+2022-04-29 00:24:52,737 INFO [train.py:763] (6/8) Epoch 10, batch 1700, loss[loss=0.165, simple_loss=0.2512, pruned_loss=0.03943, over 7264.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2863, pruned_loss=0.05029, over 1417760.74 frames.], batch size: 16, lr: 6.96e-04
+2022-04-29 00:25:58,398 INFO [train.py:763] (6/8) Epoch 10, batch 1750, loss[loss=0.1737, simple_loss=0.2803, pruned_loss=0.03356, over 7119.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2846, pruned_loss=0.0496, over 1414783.76 frames.], batch size: 21, lr: 6.95e-04
+2022-04-29 00:27:03,889 INFO [train.py:763] (6/8) Epoch 10, batch 1800, loss[loss=0.2334, simple_loss=0.3136, pruned_loss=0.07656, over 5496.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2846, pruned_loss=0.04979, over 1414207.64 frames.], batch size: 52, lr: 6.95e-04
+2022-04-29 00:28:10,810 INFO [train.py:763] (6/8) Epoch 10, batch 1850, loss[loss=0.1905, simple_loss=0.2793, pruned_loss=0.0508, over 6588.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2844, pruned_loss=0.04943, over 1418524.98 frames.], batch size: 38, lr: 6.95e-04
+2022-04-29 00:29:17,824 INFO [train.py:763] (6/8) Epoch 10, batch 1900, loss[loss=0.1932, simple_loss=0.2884, pruned_loss=0.04895, over 7315.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2846, pruned_loss=0.04942, over 1422701.96 frames.], batch size: 21, lr: 6.94e-04
+2022-04-29 00:30:24,814 INFO [train.py:763] (6/8) Epoch 10, batch 1950, loss[loss=0.2149, simple_loss=0.3114, pruned_loss=0.0592, over 7353.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2842, pruned_loss=0.04898, over 1421728.78 frames.], batch size: 19, lr: 6.94e-04
+2022-04-29 00:31:31,796 INFO [train.py:763] (6/8) Epoch 10, batch 2000, loss[loss=0.2007, simple_loss=0.2919, pruned_loss=0.05473, over 7161.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2846, pruned_loss=0.04893, over 1423161.86 frames.], batch size: 18, lr: 6.93e-04
+2022-04-29 00:32:38,662 INFO [train.py:763] (6/8) Epoch 10, batch 2050, loss[loss=0.164, simple_loss=0.2497, pruned_loss=0.03915, over 7281.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2837, pruned_loss=0.04871, over 1424831.84 frames.], batch size: 17, lr: 6.93e-04
+2022-04-29 00:33:45,456 INFO [train.py:763] (6/8) Epoch 10, batch 2100, loss[loss=0.1786, simple_loss=0.28, pruned_loss=0.03857, over 7378.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2837, pruned_loss=0.04846, over 1424216.65 frames.], batch size: 23, lr: 6.93e-04
+2022-04-29 00:35:01,072 INFO [train.py:763] (6/8) Epoch 10, batch 2150, loss[loss=0.1993, simple_loss=0.2901, pruned_loss=0.05427, over 7163.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2845, pruned_loss=0.04862, over 1424524.17 frames.], batch size: 18, lr: 6.92e-04
+2022-04-29 00:36:06,566 INFO [train.py:763] (6/8) Epoch 10, batch 2200, loss[loss=0.1968, simple_loss=0.2952, pruned_loss=0.04917, over 7239.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2851, pruned_loss=0.04935, over 1421858.16 frames.], batch size: 20, lr: 6.92e-04
+2022-04-29 00:37:11,927 INFO [train.py:763] (6/8) Epoch 10, batch 2250, loss[loss=0.185, simple_loss=0.2891, pruned_loss=0.04044, over 7335.00 frames.], tot_loss[loss=0.193, simple_loss=0.2865, pruned_loss=0.04972, over 1425024.23 frames.], batch size: 22, lr: 6.92e-04
+2022-04-29 00:38:17,411 INFO [train.py:763] (6/8) Epoch 10, batch 2300, loss[loss=0.2102, simple_loss=0.3038, pruned_loss=0.05829, over 7130.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2856, pruned_loss=0.04975, over 1425675.99 frames.], batch size: 26, lr: 6.91e-04
+2022-04-29 00:39:22,703 INFO [train.py:763] (6/8) Epoch 10, batch 2350, loss[loss=0.1998, simple_loss=0.2894, pruned_loss=0.05508, over 6852.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2849, pruned_loss=0.04921, over 1428334.30 frames.], batch size: 31, lr: 6.91e-04
+2022-04-29 00:40:27,867 INFO [train.py:763] (6/8) Epoch 10, batch 2400, loss[loss=0.1912, simple_loss=0.2915, pruned_loss=0.04544, over 7315.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2862, pruned_loss=0.0498, over 1422710.67 frames.], batch size: 21, lr: 6.91e-04
+2022-04-29 00:41:33,301 INFO [train.py:763] (6/8) Epoch 10, batch 2450, loss[loss=0.189, simple_loss=0.2766, pruned_loss=0.0507, over 7019.00 frames.], tot_loss[loss=0.192, simple_loss=0.285, pruned_loss=0.04955, over 1423381.00 frames.], batch size: 16, lr: 6.90e-04
+2022-04-29 00:42:38,514 INFO [train.py:763] (6/8) Epoch 10, batch 2500, loss[loss=0.177, simple_loss=0.2637, pruned_loss=0.04518, over 7152.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2856, pruned_loss=0.04957, over 1422803.70 frames.], batch size: 19, lr: 6.90e-04
+2022-04-29 00:43:44,256 INFO [train.py:763] (6/8) Epoch 10, batch 2550, loss[loss=0.1967, simple_loss=0.2711, pruned_loss=0.06111, over 6803.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2849, pruned_loss=0.0495, over 1426762.98 frames.], batch size: 15, lr: 6.90e-04
+2022-04-29 00:44:51,068 INFO [train.py:763] (6/8) Epoch 10, batch 2600, loss[loss=0.1975, simple_loss=0.293, pruned_loss=0.05096, over 7366.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2854, pruned_loss=0.0499, over 1428231.74 frames.], batch size: 23, lr: 6.89e-04
+2022-04-29 00:45:56,183 INFO [train.py:763] (6/8) Epoch 10, batch 2650, loss[loss=0.1635, simple_loss=0.2506, pruned_loss=0.03819, over 6997.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2864, pruned_loss=0.05031, over 1423385.57 frames.], batch size: 16, lr: 6.89e-04
+2022-04-29 00:47:01,613 INFO [train.py:763] (6/8) Epoch 10, batch 2700, loss[loss=0.191, simple_loss=0.2892, pruned_loss=0.04643, over 7417.00 frames.], tot_loss[loss=0.1935, simple_loss=0.287, pruned_loss=0.04998, over 1426189.39 frames.], batch size: 21, lr: 6.89e-04
+2022-04-29 00:48:08,166 INFO [train.py:763] (6/8) Epoch 10, batch 2750, loss[loss=0.1888, simple_loss=0.2792, pruned_loss=0.04917, over 7270.00 frames.], tot_loss[loss=0.1923, simple_loss=0.285, pruned_loss=0.04982, over 1425056.86 frames.], batch size: 18, lr: 6.88e-04
+2022-04-29 00:49:13,513 INFO [train.py:763] (6/8) Epoch 10, batch 2800, loss[loss=0.1885, simple_loss=0.2855, pruned_loss=0.04573, over 7177.00 frames.], tot_loss[loss=0.1923, simple_loss=0.285, pruned_loss=0.04979, over 1423861.20 frames.], batch size: 19, lr: 6.88e-04
+2022-04-29 00:50:19,053 INFO [train.py:763] (6/8) Epoch 10, batch 2850, loss[loss=0.1574, simple_loss=0.2525, pruned_loss=0.03112, over 7318.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2842, pruned_loss=0.04931, over 1424203.29 frames.], batch size: 21, lr: 6.87e-04
+2022-04-29 00:51:24,559 INFO [train.py:763] (6/8) Epoch 10, batch 2900, loss[loss=0.2347, simple_loss=0.3253, pruned_loss=0.07211, over 7203.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2851, pruned_loss=0.04954, over 1426559.26 frames.], batch size: 23, lr: 6.87e-04
+2022-04-29 00:52:30,308 INFO [train.py:763] (6/8) Epoch 10, batch 2950, loss[loss=0.1899, simple_loss=0.2868, pruned_loss=0.04654, over 7212.00 frames.], tot_loss[loss=0.1921, simple_loss=0.286, pruned_loss=0.04907, over 1423843.90 frames.], batch size: 22, lr: 6.87e-04
+2022-04-29 00:53:36,009 INFO [train.py:763] (6/8) Epoch 10, batch 3000, loss[loss=0.1431, simple_loss=0.234, pruned_loss=0.02608, over 7159.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2863, pruned_loss=0.04955, over 1422368.82 frames.], batch size: 18, lr: 6.86e-04
+2022-04-29 00:53:36,010 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 00:53:51,272 INFO [train.py:792] (6/8) Epoch 10, validation: loss=0.1689, simple_loss=0.2722, pruned_loss=0.03283, over 698248.00 frames.
+2022-04-29 00:54:57,776 INFO [train.py:763] (6/8) Epoch 10, batch 3050, loss[loss=0.2209, simple_loss=0.3199, pruned_loss=0.06091, over 7160.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2859, pruned_loss=0.04952, over 1427093.89 frames.], batch size: 26, lr: 6.86e-04
+2022-04-29 00:56:03,625 INFO [train.py:763] (6/8) Epoch 10, batch 3100, loss[loss=0.1728, simple_loss=0.2694, pruned_loss=0.0381, over 7398.00 frames.], tot_loss[loss=0.194, simple_loss=0.2871, pruned_loss=0.05047, over 1424782.12 frames.], batch size: 18, lr: 6.86e-04
+2022-04-29 00:57:10,795 INFO [train.py:763] (6/8) Epoch 10, batch 3150, loss[loss=0.1819, simple_loss=0.2755, pruned_loss=0.04416, over 7286.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2859, pruned_loss=0.04987, over 1427234.85 frames.], batch size: 18, lr: 6.85e-04
+2022-04-29 00:58:16,973 INFO [train.py:763] (6/8) Epoch 10, batch 3200, loss[loss=0.1756, simple_loss=0.2785, pruned_loss=0.03637, over 7167.00 frames.], tot_loss[loss=0.1922, simple_loss=0.285, pruned_loss=0.04969, over 1429304.73 frames.], batch size: 18, lr: 6.85e-04
+2022-04-29 00:59:22,562 INFO [train.py:763] (6/8) Epoch 10, batch 3250, loss[loss=0.1981, simple_loss=0.2722, pruned_loss=0.06202, over 7066.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2853, pruned_loss=0.04998, over 1430886.35 frames.], batch size: 18, lr: 6.85e-04
+2022-04-29 01:00:29,377 INFO [train.py:763] (6/8) Epoch 10, batch 3300, loss[loss=0.216, simple_loss=0.3181, pruned_loss=0.05694, over 6433.00 frames.], tot_loss[loss=0.1943, simple_loss=0.287, pruned_loss=0.05078, over 1429307.34 frames.], batch size: 38, lr: 6.84e-04
+2022-04-29 01:01:36,448 INFO [train.py:763] (6/8) Epoch 10, batch 3350, loss[loss=0.1999, simple_loss=0.2803, pruned_loss=0.05977, over 7115.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2865, pruned_loss=0.05052, over 1424384.29 frames.], batch size: 21, lr: 6.84e-04
+2022-04-29 01:02:41,923 INFO [train.py:763] (6/8) Epoch 10, batch 3400, loss[loss=0.1658, simple_loss=0.2524, pruned_loss=0.03956, over 6995.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2872, pruned_loss=0.05121, over 1421699.32 frames.], batch size: 16, lr: 6.84e-04
+2022-04-29 01:03:47,416 INFO [train.py:763] (6/8) Epoch 10, batch 3450, loss[loss=0.1846, simple_loss=0.272, pruned_loss=0.04858, over 7134.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2874, pruned_loss=0.051, over 1424272.08 frames.], batch size: 21, lr: 6.83e-04
+2022-04-29 01:04:52,723 INFO [train.py:763] (6/8) Epoch 10, batch 3500, loss[loss=0.1687, simple_loss=0.2549, pruned_loss=0.04125, over 7414.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2866, pruned_loss=0.05048, over 1425144.85 frames.], batch size: 18, lr: 6.83e-04
+2022-04-29 01:05:58,213 INFO [train.py:763] (6/8) Epoch 10, batch 3550, loss[loss=0.2107, simple_loss=0.3085, pruned_loss=0.05643, over 6383.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2866, pruned_loss=0.05063, over 1423838.36 frames.], batch size: 37, lr: 6.83e-04
+2022-04-29 01:07:03,433 INFO [train.py:763] (6/8) Epoch 10, batch 3600, loss[loss=0.1953, simple_loss=0.2908, pruned_loss=0.04987, over 6089.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2871, pruned_loss=0.05119, over 1418815.39 frames.], batch size: 37, lr: 6.82e-04
+2022-04-29 01:08:09,035 INFO [train.py:763] (6/8) Epoch 10, batch 3650, loss[loss=0.204, simple_loss=0.3013, pruned_loss=0.05331, over 7123.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2861, pruned_loss=0.05059, over 1422434.04 frames.], batch size: 21, lr: 6.82e-04
+2022-04-29 01:09:14,319 INFO [train.py:763] (6/8) Epoch 10, batch 3700, loss[loss=0.2382, simple_loss=0.3268, pruned_loss=0.07485, over 7132.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2868, pruned_loss=0.05079, over 1418969.76 frames.], batch size: 21, lr: 6.82e-04
+2022-04-29 01:10:20,282 INFO [train.py:763] (6/8) Epoch 10, batch 3750, loss[loss=0.1982, simple_loss=0.2868, pruned_loss=0.05479, over 7424.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2881, pruned_loss=0.0507, over 1424714.66 frames.], batch size: 20, lr: 6.81e-04
+2022-04-29 01:11:26,043 INFO [train.py:763] (6/8) Epoch 10, batch 3800, loss[loss=0.2074, simple_loss=0.2994, pruned_loss=0.05771, over 7314.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2874, pruned_loss=0.05061, over 1422580.74 frames.], batch size: 24, lr: 6.81e-04
+2022-04-29 01:12:32,918 INFO [train.py:763] (6/8) Epoch 10, batch 3850, loss[loss=0.243, simple_loss=0.3289, pruned_loss=0.07859, over 7210.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2876, pruned_loss=0.05092, over 1426553.44 frames.], batch size: 22, lr: 6.81e-04
+2022-04-29 01:13:40,344 INFO [train.py:763] (6/8) Epoch 10, batch 3900, loss[loss=0.1949, simple_loss=0.2954, pruned_loss=0.04718, over 7379.00 frames.], tot_loss[loss=0.1943, simple_loss=0.287, pruned_loss=0.05078, over 1427657.89 frames.], batch size: 23, lr: 6.80e-04
+2022-04-29 01:14:47,718 INFO [train.py:763] (6/8) Epoch 10, batch 3950, loss[loss=0.2007, simple_loss=0.2984, pruned_loss=0.05146, over 7433.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2857, pruned_loss=0.05034, over 1427422.75 frames.], batch size: 20, lr: 6.80e-04
+2022-04-29 01:15:53,614 INFO [train.py:763] (6/8) Epoch 10, batch 4000, loss[loss=0.1834, simple_loss=0.2791, pruned_loss=0.04381, over 7235.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2864, pruned_loss=0.05088, over 1418186.42 frames.], batch size: 21, lr: 6.80e-04
+2022-04-29 01:17:00,543 INFO [train.py:763] (6/8) Epoch 10, batch 4050, loss[loss=0.1914, simple_loss=0.2862, pruned_loss=0.04826, over 7216.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2869, pruned_loss=0.05077, over 1417823.68 frames.], batch size: 22, lr: 6.79e-04
+2022-04-29 01:18:07,364 INFO [train.py:763] (6/8) Epoch 10, batch 4100, loss[loss=0.1953, simple_loss=0.2821, pruned_loss=0.05422, over 7196.00 frames.], tot_loss[loss=0.1942, simple_loss=0.287, pruned_loss=0.05073, over 1417766.95 frames.], batch size: 22, lr: 6.79e-04
+2022-04-29 01:19:14,031 INFO [train.py:763] (6/8) Epoch 10, batch 4150, loss[loss=0.2055, simple_loss=0.3035, pruned_loss=0.0537, over 6698.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2875, pruned_loss=0.05071, over 1415207.71 frames.], batch size: 31, lr: 6.79e-04
+2022-04-29 01:20:19,808 INFO [train.py:763] (6/8) Epoch 10, batch 4200, loss[loss=0.199, simple_loss=0.2936, pruned_loss=0.0522, over 7042.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2879, pruned_loss=0.05088, over 1415834.49 frames.], batch size: 28, lr: 6.78e-04
+2022-04-29 01:21:26,030 INFO [train.py:763] (6/8) Epoch 10, batch 4250, loss[loss=0.2442, simple_loss=0.3152, pruned_loss=0.08659, over 4739.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2863, pruned_loss=0.05025, over 1414803.80 frames.], batch size: 52, lr: 6.78e-04
+2022-04-29 01:22:31,076 INFO [train.py:763] (6/8) Epoch 10, batch 4300, loss[loss=0.2223, simple_loss=0.3068, pruned_loss=0.06893, over 5014.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2873, pruned_loss=0.0509, over 1411233.17 frames.], batch size: 52, lr: 6.78e-04
+2022-04-29 01:23:36,198 INFO [train.py:763] (6/8) Epoch 10, batch 4350, loss[loss=0.1759, simple_loss=0.2774, pruned_loss=0.03718, over 7230.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2874, pruned_loss=0.05096, over 1410717.92 frames.], batch size: 20, lr: 6.77e-04
+2022-04-29 01:24:41,260 INFO [train.py:763] (6/8) Epoch 10, batch 4400, loss[loss=0.2015, simple_loss=0.2995, pruned_loss=0.05172, over 7213.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2878, pruned_loss=0.05081, over 1415632.72 frames.], batch size: 22, lr: 6.77e-04
+2022-04-29 01:25:46,578 INFO [train.py:763] (6/8) Epoch 10, batch 4450, loss[loss=0.1719, simple_loss=0.2601, pruned_loss=0.04189, over 7242.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2897, pruned_loss=0.05197, over 1418859.13 frames.], batch size: 20, lr: 6.77e-04
+2022-04-29 01:26:52,302 INFO [train.py:763] (6/8) Epoch 10, batch 4500, loss[loss=0.2452, simple_loss=0.3265, pruned_loss=0.08198, over 5197.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2913, pruned_loss=0.05271, over 1410941.36 frames.], batch size: 52, lr: 6.76e-04
+2022-04-29 01:27:57,103 INFO [train.py:763] (6/8) Epoch 10, batch 4550, loss[loss=0.2282, simple_loss=0.3102, pruned_loss=0.0731, over 5009.00 frames.], tot_loss[loss=0.2023, simple_loss=0.294, pruned_loss=0.05534, over 1347627.22 frames.], batch size: 53, lr: 6.76e-04
+2022-04-29 01:29:26,057 INFO [train.py:763] (6/8) Epoch 11, batch 0, loss[loss=0.1945, simple_loss=0.292, pruned_loss=0.04853, over 7413.00 frames.], tot_loss[loss=0.1945, simple_loss=0.292, pruned_loss=0.04853, over 7413.00 frames.], batch size: 21, lr: 6.52e-04
+2022-04-29 01:30:32,267 INFO [train.py:763] (6/8) Epoch 11, batch 50, loss[loss=0.2163, simple_loss=0.3049, pruned_loss=0.0639, over 4815.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2863, pruned_loss=0.05003, over 319014.97 frames.], batch size: 54, lr: 6.52e-04
+2022-04-29 01:31:38,423 INFO [train.py:763] (6/8) Epoch 11, batch 100, loss[loss=0.1795, simple_loss=0.2824, pruned_loss=0.03831, over 6435.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2848, pruned_loss=0.0498, over 558631.87 frames.], batch size: 38, lr: 6.51e-04
+2022-04-29 01:32:44,338 INFO [train.py:763] (6/8) Epoch 11, batch 150, loss[loss=0.1929, simple_loss=0.28, pruned_loss=0.05289, over 7297.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2871, pruned_loss=0.05057, over 748720.15 frames.], batch size: 17, lr: 6.51e-04
+2022-04-29 01:33:50,251 INFO [train.py:763] (6/8) Epoch 11, batch 200, loss[loss=0.2303, simple_loss=0.3195, pruned_loss=0.07056, over 7201.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2878, pruned_loss=0.05101, over 895571.23 frames.], batch size: 22, lr: 6.51e-04
+2022-04-29 01:34:55,810 INFO [train.py:763] (6/8) Epoch 11, batch 250, loss[loss=0.2102, simple_loss=0.3015, pruned_loss=0.05949, over 6698.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2871, pruned_loss=0.05009, over 1013737.17 frames.], batch size: 31, lr: 6.50e-04
+2022-04-29 01:36:01,208 INFO [train.py:763] (6/8) Epoch 11, batch 300, loss[loss=0.2174, simple_loss=0.3034, pruned_loss=0.06567, over 7193.00 frames.], tot_loss[loss=0.1931, simple_loss=0.287, pruned_loss=0.04965, over 1098190.36 frames.], batch size: 22, lr: 6.50e-04
+2022-04-29 01:37:06,909 INFO [train.py:763] (6/8) Epoch 11, batch 350, loss[loss=0.1814, simple_loss=0.2783, pruned_loss=0.04227, over 7336.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2859, pruned_loss=0.04894, over 1164278.62 frames.], batch size: 22, lr: 6.50e-04
+2022-04-29 01:38:12,680 INFO [train.py:763] (6/8) Epoch 11, batch 400, loss[loss=0.1923, simple_loss=0.2886, pruned_loss=0.04805, over 7338.00 frames.], tot_loss[loss=0.1911, simple_loss=0.285, pruned_loss=0.04859, over 1219533.37 frames.], batch size: 22, lr: 6.49e-04
+2022-04-29 01:39:18,308 INFO [train.py:763] (6/8) Epoch 11, batch 450, loss[loss=0.1824, simple_loss=0.2913, pruned_loss=0.0368, over 7155.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2845, pruned_loss=0.04805, over 1268018.41 frames.], batch size: 19, lr: 6.49e-04
+2022-04-29 01:40:24,056 INFO [train.py:763] (6/8) Epoch 11, batch 500, loss[loss=0.2422, simple_loss=0.343, pruned_loss=0.07068, over 7376.00 frames.], tot_loss[loss=0.191, simple_loss=0.285, pruned_loss=0.04854, over 1302151.36 frames.], batch size: 23, lr: 6.49e-04
+2022-04-29 01:41:30,081 INFO [train.py:763] (6/8) Epoch 11, batch 550, loss[loss=0.1896, simple_loss=0.2919, pruned_loss=0.04365, over 7403.00 frames.], tot_loss[loss=0.1904, simple_loss=0.284, pruned_loss=0.04838, over 1328250.99 frames.], batch size: 21, lr: 6.48e-04
+2022-04-29 01:42:36,720 INFO [train.py:763] (6/8) Epoch 11, batch 600, loss[loss=0.1851, simple_loss=0.2893, pruned_loss=0.04043, over 7340.00 frames.], tot_loss[loss=0.191, simple_loss=0.2843, pruned_loss=0.04881, over 1347374.76 frames.], batch size: 22, lr: 6.48e-04
+2022-04-29 01:43:44,065 INFO [train.py:763] (6/8) Epoch 11, batch 650, loss[loss=0.2055, simple_loss=0.3012, pruned_loss=0.05493, over 7381.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2838, pruned_loss=0.04856, over 1368478.16 frames.], batch size: 23, lr: 6.48e-04
+2022-04-29 01:44:51,068 INFO [train.py:763] (6/8) Epoch 11, batch 700, loss[loss=0.1965, simple_loss=0.2867, pruned_loss=0.05313, over 7270.00 frames.], tot_loss[loss=0.19, simple_loss=0.2837, pruned_loss=0.04814, over 1379822.28 frames.], batch size: 24, lr: 6.47e-04
+2022-04-29 01:45:57,538 INFO [train.py:763] (6/8) Epoch 11, batch 750, loss[loss=0.1832, simple_loss=0.2809, pruned_loss=0.0427, over 7330.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2841, pruned_loss=0.04822, over 1385915.66 frames.], batch size: 20, lr: 6.47e-04
+2022-04-29 01:47:03,479 INFO [train.py:763] (6/8) Epoch 11, batch 800, loss[loss=0.152, simple_loss=0.2381, pruned_loss=0.03295, over 7402.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2838, pruned_loss=0.04858, over 1398537.69 frames.], batch size: 18, lr: 6.47e-04
+2022-04-29 01:48:08,964 INFO [train.py:763] (6/8) Epoch 11, batch 850, loss[loss=0.2142, simple_loss=0.3022, pruned_loss=0.06306, over 6828.00 frames.], tot_loss[loss=0.1913, simple_loss=0.285, pruned_loss=0.0488, over 1402829.23 frames.], batch size: 31, lr: 6.46e-04
+2022-04-29 01:49:14,829 INFO [train.py:763] (6/8) Epoch 11, batch 900, loss[loss=0.2053, simple_loss=0.3003, pruned_loss=0.05513, over 7337.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2846, pruned_loss=0.04881, over 1406905.61 frames.], batch size: 22, lr: 6.46e-04
+2022-04-29 01:50:20,644 INFO [train.py:763] (6/8) Epoch 11, batch 950, loss[loss=0.1739, simple_loss=0.2679, pruned_loss=0.03997, over 7426.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2849, pruned_loss=0.04866, over 1412504.28 frames.], batch size: 20, lr: 6.46e-04
+2022-04-29 01:51:27,138 INFO [train.py:763] (6/8) Epoch 11, batch 1000, loss[loss=0.1804, simple_loss=0.2775, pruned_loss=0.04162, over 7156.00 frames.], tot_loss[loss=0.192, simple_loss=0.2858, pruned_loss=0.04916, over 1415863.75 frames.], batch size: 19, lr: 6.46e-04
+2022-04-29 01:52:32,494 INFO [train.py:763] (6/8) Epoch 11, batch 1050, loss[loss=0.1794, simple_loss=0.265, pruned_loss=0.04692, over 7421.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2863, pruned_loss=0.04926, over 1416039.47 frames.], batch size: 17, lr: 6.45e-04
+2022-04-29 01:53:38,689 INFO [train.py:763] (6/8) Epoch 11, batch 1100, loss[loss=0.1859, simple_loss=0.2771, pruned_loss=0.04732, over 7156.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2872, pruned_loss=0.04967, over 1418962.54 frames.], batch size: 19, lr: 6.45e-04
+2022-04-29 01:54:45,799 INFO [train.py:763] (6/8) Epoch 11, batch 1150, loss[loss=0.2146, simple_loss=0.2969, pruned_loss=0.06609, over 4803.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2866, pruned_loss=0.04962, over 1421581.08 frames.], batch size: 52, lr: 6.45e-04
+2022-04-29 01:55:51,998 INFO [train.py:763] (6/8) Epoch 11, batch 1200, loss[loss=0.1824, simple_loss=0.2899, pruned_loss=0.03748, over 7114.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2866, pruned_loss=0.04928, over 1424000.92 frames.], batch size: 21, lr: 6.44e-04
+2022-04-29 01:56:57,805 INFO [train.py:763] (6/8) Epoch 11, batch 1250, loss[loss=0.1863, simple_loss=0.2645, pruned_loss=0.05406, over 6990.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2853, pruned_loss=0.04903, over 1425452.53 frames.], batch size: 16, lr: 6.44e-04
+2022-04-29 01:58:03,704 INFO [train.py:763] (6/8) Epoch 11, batch 1300, loss[loss=0.1916, simple_loss=0.2947, pruned_loss=0.04421, over 7327.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2847, pruned_loss=0.04848, over 1427596.31 frames.], batch size: 20, lr: 6.44e-04
+2022-04-29 01:59:10,168 INFO [train.py:763] (6/8) Epoch 11, batch 1350, loss[loss=0.1748, simple_loss=0.2883, pruned_loss=0.03062, over 7313.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2851, pruned_loss=0.04876, over 1423997.56 frames.], batch size: 21, lr: 6.43e-04
+2022-04-29 02:00:15,528 INFO [train.py:763] (6/8) Epoch 11, batch 1400, loss[loss=0.1792, simple_loss=0.2848, pruned_loss=0.03679, over 7315.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2845, pruned_loss=0.04852, over 1420602.50 frames.], batch size: 21, lr: 6.43e-04
+2022-04-29 02:01:21,167 INFO [train.py:763] (6/8) Epoch 11, batch 1450, loss[loss=0.1745, simple_loss=0.2729, pruned_loss=0.03799, over 7067.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2856, pruned_loss=0.04914, over 1421990.05 frames.], batch size: 18, lr: 6.43e-04
+2022-04-29 02:02:28,460 INFO [train.py:763] (6/8) Epoch 11, batch 1500, loss[loss=0.2208, simple_loss=0.308, pruned_loss=0.06676, over 7192.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2844, pruned_loss=0.04834, over 1425586.90 frames.], batch size: 23, lr: 6.42e-04
+2022-04-29 02:03:33,960 INFO [train.py:763] (6/8) Epoch 11, batch 1550, loss[loss=0.1835, simple_loss=0.2838, pruned_loss=0.04165, over 7244.00 frames.], tot_loss[loss=0.1904, simple_loss=0.284, pruned_loss=0.04846, over 1424653.42 frames.], batch size: 20, lr: 6.42e-04
+2022-04-29 02:04:39,636 INFO [train.py:763] (6/8) Epoch 11, batch 1600, loss[loss=0.1746, simple_loss=0.268, pruned_loss=0.04059, over 7356.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2847, pruned_loss=0.04893, over 1425020.15 frames.], batch size: 19, lr: 6.42e-04
+2022-04-29 02:06:04,017 INFO [train.py:763] (6/8) Epoch 11, batch 1650, loss[loss=0.1919, simple_loss=0.2914, pruned_loss=0.0462, over 7396.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2852, pruned_loss=0.0491, over 1425979.15 frames.], batch size: 23, lr: 6.42e-04
+2022-04-29 02:07:17,967 INFO [train.py:763] (6/8) Epoch 11, batch 1700, loss[loss=0.2283, simple_loss=0.3287, pruned_loss=0.06399, over 7222.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2857, pruned_loss=0.04866, over 1427076.52 frames.], batch size: 21, lr: 6.41e-04
+2022-04-29 02:08:33,275 INFO [train.py:763] (6/8) Epoch 11, batch 1750, loss[loss=0.1982, simple_loss=0.2912, pruned_loss=0.05259, over 7174.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2859, pruned_loss=0.0486, over 1427487.83 frames.], batch size: 26, lr: 6.41e-04
+2022-04-29 02:09:47,987 INFO [train.py:763] (6/8) Epoch 11, batch 1800, loss[loss=0.1697, simple_loss=0.257, pruned_loss=0.04123, over 7000.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2845, pruned_loss=0.04792, over 1427275.25 frames.], batch size: 16, lr: 6.41e-04
+2022-04-29 02:11:03,172 INFO [train.py:763] (6/8) Epoch 11, batch 1850, loss[loss=0.1892, simple_loss=0.28, pruned_loss=0.04925, over 7141.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2839, pruned_loss=0.04789, over 1426626.08 frames.], batch size: 26, lr: 6.40e-04
+2022-04-29 02:12:18,083 INFO [train.py:763] (6/8) Epoch 11, batch 1900, loss[loss=0.1887, simple_loss=0.2827, pruned_loss=0.04734, over 7425.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2835, pruned_loss=0.04783, over 1428909.54 frames.], batch size: 20, lr: 6.40e-04
+2022-04-29 02:13:32,353 INFO [train.py:763] (6/8) Epoch 11, batch 1950, loss[loss=0.1925, simple_loss=0.2746, pruned_loss=0.0552, over 6972.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2835, pruned_loss=0.0479, over 1427249.59 frames.], batch size: 16, lr: 6.40e-04
+2022-04-29 02:14:38,126 INFO [train.py:763] (6/8) Epoch 11, batch 2000, loss[loss=0.2081, simple_loss=0.2958, pruned_loss=0.06021, over 6338.00 frames.], tot_loss[loss=0.19, simple_loss=0.2836, pruned_loss=0.04814, over 1425227.15 frames.], batch size: 37, lr: 6.39e-04
+2022-04-29 02:15:44,448 INFO [train.py:763] (6/8) Epoch 11, batch 2050, loss[loss=0.2084, simple_loss=0.3054, pruned_loss=0.0557, over 7396.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2834, pruned_loss=0.04854, over 1422734.76 frames.], batch size: 23, lr: 6.39e-04
+2022-04-29 02:16:50,752 INFO [train.py:763] (6/8) Epoch 11, batch 2100, loss[loss=0.1823, simple_loss=0.2782, pruned_loss=0.04318, over 6823.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2839, pruned_loss=0.04874, over 1427153.58 frames.], batch size: 31, lr: 6.39e-04
+2022-04-29 02:17:57,124 INFO [train.py:763] (6/8) Epoch 11, batch 2150, loss[loss=0.1959, simple_loss=0.2761, pruned_loss=0.05789, over 6807.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2835, pruned_loss=0.04856, over 1422359.85 frames.], batch size: 15, lr: 6.38e-04
+2022-04-29 02:19:03,273 INFO [train.py:763] (6/8) Epoch 11, batch 2200, loss[loss=0.2073, simple_loss=0.3032, pruned_loss=0.05576, over 7424.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2831, pruned_loss=0.04838, over 1426822.44 frames.], batch size: 20, lr: 6.38e-04
+2022-04-29 02:20:09,540 INFO [train.py:763] (6/8) Epoch 11, batch 2250, loss[loss=0.1703, simple_loss=0.2638, pruned_loss=0.03842, over 7137.00 frames.], tot_loss[loss=0.19, simple_loss=0.2832, pruned_loss=0.04844, over 1426324.83 frames.], batch size: 17, lr: 6.38e-04
+2022-04-29 02:21:16,308 INFO [train.py:763] (6/8) Epoch 11, batch 2300, loss[loss=0.191, simple_loss=0.2711, pruned_loss=0.05549, over 7350.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2843, pruned_loss=0.04925, over 1424719.64 frames.], batch size: 19, lr: 6.38e-04
+2022-04-29 02:22:22,095 INFO [train.py:763] (6/8) Epoch 11, batch 2350, loss[loss=0.2114, simple_loss=0.2996, pruned_loss=0.06164, over 7277.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2836, pruned_loss=0.04887, over 1426201.44 frames.], batch size: 24, lr: 6.37e-04
+2022-04-29 02:23:28,148 INFO [train.py:763] (6/8) Epoch 11, batch 2400, loss[loss=0.1818, simple_loss=0.2874, pruned_loss=0.0381, over 7117.00 frames.], tot_loss[loss=0.191, simple_loss=0.2844, pruned_loss=0.04883, over 1428060.57 frames.], batch size: 21, lr: 6.37e-04
+2022-04-29 02:24:33,628 INFO [train.py:763] (6/8) Epoch 11, batch 2450, loss[loss=0.2105, simple_loss=0.3004, pruned_loss=0.06024, over 7235.00 frames.], tot_loss[loss=0.1911, simple_loss=0.285, pruned_loss=0.04857, over 1426521.81 frames.], batch size: 20, lr: 6.37e-04
+2022-04-29 02:25:39,228 INFO [train.py:763] (6/8) Epoch 11, batch 2500, loss[loss=0.1922, simple_loss=0.2751, pruned_loss=0.05463, over 7071.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2848, pruned_loss=0.04871, over 1424958.36 frames.], batch size: 18, lr: 6.36e-04
+2022-04-29 02:26:45,647 INFO [train.py:763] (6/8) Epoch 11, batch 2550, loss[loss=0.1647, simple_loss=0.2565, pruned_loss=0.03645, over 7273.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2852, pruned_loss=0.04877, over 1428003.71 frames.], batch size: 17, lr: 6.36e-04
+2022-04-29 02:27:50,868 INFO [train.py:763] (6/8) Epoch 11, batch 2600, loss[loss=0.209, simple_loss=0.308, pruned_loss=0.05494, over 7262.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2852, pruned_loss=0.04865, over 1422303.40 frames.], batch size: 24, lr: 6.36e-04
+2022-04-29 02:28:56,396 INFO [train.py:763] (6/8) Epoch 11, batch 2650, loss[loss=0.1771, simple_loss=0.2653, pruned_loss=0.04446, over 7252.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2859, pruned_loss=0.04888, over 1419141.14 frames.], batch size: 19, lr: 6.36e-04
+2022-04-29 02:30:03,349 INFO [train.py:763] (6/8) Epoch 11, batch 2700, loss[loss=0.1857, simple_loss=0.2802, pruned_loss=0.0456, over 7283.00 frames.], tot_loss[loss=0.19, simple_loss=0.2844, pruned_loss=0.04784, over 1422977.24 frames.], batch size: 25, lr: 6.35e-04
+2022-04-29 02:31:08,822 INFO [train.py:763] (6/8) Epoch 11, batch 2750, loss[loss=0.2125, simple_loss=0.3061, pruned_loss=0.05952, over 7436.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2841, pruned_loss=0.04757, over 1426155.13 frames.], batch size: 20, lr: 6.35e-04
+2022-04-29 02:32:14,649 INFO [train.py:763] (6/8) Epoch 11, batch 2800, loss[loss=0.2199, simple_loss=0.3212, pruned_loss=0.05931, over 7111.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2846, pruned_loss=0.04805, over 1426914.58 frames.], batch size: 21, lr: 6.35e-04
+2022-04-29 02:33:21,115 INFO [train.py:763] (6/8) Epoch 11, batch 2850, loss[loss=0.1753, simple_loss=0.2768, pruned_loss=0.03689, over 7318.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2834, pruned_loss=0.04794, over 1429002.34 frames.], batch size: 21, lr: 6.34e-04
+2022-04-29 02:34:28,408 INFO [train.py:763] (6/8) Epoch 11, batch 2900, loss[loss=0.203, simple_loss=0.3048, pruned_loss=0.05057, over 7282.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2856, pruned_loss=0.04887, over 1424905.19 frames.], batch size: 24, lr: 6.34e-04
+2022-04-29 02:35:35,072 INFO [train.py:763] (6/8) Epoch 11, batch 2950, loss[loss=0.1654, simple_loss=0.2631, pruned_loss=0.03386, over 7218.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2849, pruned_loss=0.04906, over 1420303.27 frames.], batch size: 21, lr: 6.34e-04
+2022-04-29 02:36:40,645 INFO [train.py:763] (6/8) Epoch 11, batch 3000, loss[loss=0.1935, simple_loss=0.2866, pruned_loss=0.05022, over 7316.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2842, pruned_loss=0.0486, over 1421615.63 frames.], batch size: 25, lr: 6.33e-04
+2022-04-29 02:36:40,645 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 02:36:55,964 INFO [train.py:792] (6/8) Epoch 11, validation: loss=0.1677, simple_loss=0.2702, pruned_loss=0.03262, over 698248.00 frames.
+2022-04-29 02:38:01,325 INFO [train.py:763] (6/8) Epoch 11, batch 3050, loss[loss=0.1924, simple_loss=0.2923, pruned_loss=0.04625, over 7377.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2853, pruned_loss=0.04879, over 1419783.51 frames.], batch size: 23, lr: 6.33e-04
+2022-04-29 02:39:06,999 INFO [train.py:763] (6/8) Epoch 11, batch 3100, loss[loss=0.166, simple_loss=0.2703, pruned_loss=0.03084, over 7325.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2845, pruned_loss=0.04789, over 1421741.43 frames.], batch size: 20, lr: 6.33e-04
+2022-04-29 02:40:14,525 INFO [train.py:763] (6/8) Epoch 11, batch 3150, loss[loss=0.2096, simple_loss=0.3007, pruned_loss=0.05924, over 7398.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2844, pruned_loss=0.04774, over 1423913.43 frames.], batch size: 23, lr: 6.33e-04
+2022-04-29 02:41:19,858 INFO [train.py:763] (6/8) Epoch 11, batch 3200, loss[loss=0.1969, simple_loss=0.2984, pruned_loss=0.04769, over 7119.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2846, pruned_loss=0.04782, over 1423556.62 frames.], batch size: 21, lr: 6.32e-04
+2022-04-29 02:42:26,204 INFO [train.py:763] (6/8) Epoch 11, batch 3250, loss[loss=0.1948, simple_loss=0.3021, pruned_loss=0.04377, over 7424.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2845, pruned_loss=0.04746, over 1425022.25 frames.], batch size: 21, lr: 6.32e-04
+2022-04-29 02:43:31,318 INFO [train.py:763] (6/8) Epoch 11, batch 3300, loss[loss=0.1739, simple_loss=0.2535, pruned_loss=0.0472, over 6993.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2851, pruned_loss=0.04777, over 1425283.79 frames.], batch size: 16, lr: 6.32e-04
+2022-04-29 02:44:36,750 INFO [train.py:763] (6/8) Epoch 11, batch 3350, loss[loss=0.1783, simple_loss=0.2692, pruned_loss=0.04365, over 7277.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2852, pruned_loss=0.04749, over 1425680.26 frames.], batch size: 18, lr: 6.31e-04
+2022-04-29 02:45:42,397 INFO [train.py:763] (6/8) Epoch 11, batch 3400, loss[loss=0.2251, simple_loss=0.3079, pruned_loss=0.07111, over 6507.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2848, pruned_loss=0.04773, over 1421010.96 frames.], batch size: 38, lr: 6.31e-04
+2022-04-29 02:46:49,567 INFO [train.py:763] (6/8) Epoch 11, batch 3450, loss[loss=0.2034, simple_loss=0.2922, pruned_loss=0.05733, over 7117.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2837, pruned_loss=0.04771, over 1418022.79 frames.], batch size: 21, lr: 6.31e-04
+2022-04-29 02:47:56,125 INFO [train.py:763] (6/8) Epoch 11, batch 3500, loss[loss=0.1893, simple_loss=0.2943, pruned_loss=0.04215, over 7315.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2836, pruned_loss=0.04749, over 1424080.83 frames.], batch size: 21, lr: 6.31e-04
+2022-04-29 02:49:02,251 INFO [train.py:763] (6/8) Epoch 11, batch 3550, loss[loss=0.1617, simple_loss=0.2526, pruned_loss=0.03545, over 7001.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2839, pruned_loss=0.04775, over 1422797.41 frames.], batch size: 16, lr: 6.30e-04
+2022-04-29 02:50:08,012 INFO [train.py:763] (6/8) Epoch 11, batch 3600, loss[loss=0.1975, simple_loss=0.2929, pruned_loss=0.051, over 7227.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2841, pruned_loss=0.04729, over 1424574.98 frames.], batch size: 20, lr: 6.30e-04
+2022-04-29 02:51:13,360 INFO [train.py:763] (6/8) Epoch 11, batch 3650, loss[loss=0.1638, simple_loss=0.2672, pruned_loss=0.03022, over 7424.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2852, pruned_loss=0.04782, over 1424177.95 frames.], batch size: 20, lr: 6.30e-04
+2022-04-29 02:52:20,067 INFO [train.py:763] (6/8) Epoch 11, batch 3700, loss[loss=0.2169, simple_loss=0.3065, pruned_loss=0.06363, over 6782.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2844, pruned_loss=0.04762, over 1421328.42 frames.], batch size: 31, lr: 6.29e-04
+2022-04-29 02:53:25,481 INFO [train.py:763] (6/8) Epoch 11, batch 3750, loss[loss=0.1847, simple_loss=0.2819, pruned_loss=0.04375, over 7365.00 frames.], tot_loss[loss=0.189, simple_loss=0.2834, pruned_loss=0.04734, over 1425356.61 frames.], batch size: 23, lr: 6.29e-04
+2022-04-29 02:54:30,952 INFO [train.py:763] (6/8) Epoch 11, batch 3800, loss[loss=0.1877, simple_loss=0.2908, pruned_loss=0.04225, over 7184.00 frames.], tot_loss[loss=0.1885, simple_loss=0.283, pruned_loss=0.04704, over 1428011.98 frames.], batch size: 26, lr: 6.29e-04
+2022-04-29 02:55:36,108 INFO [train.py:763] (6/8) Epoch 11, batch 3850, loss[loss=0.1833, simple_loss=0.2909, pruned_loss=0.03784, over 7115.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2837, pruned_loss=0.04724, over 1428430.55 frames.], batch size: 21, lr: 6.29e-04
+2022-04-29 02:56:41,385 INFO [train.py:763] (6/8) Epoch 11, batch 3900, loss[loss=0.165, simple_loss=0.2615, pruned_loss=0.03419, over 7432.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2834, pruned_loss=0.04714, over 1429106.69 frames.], batch size: 20, lr: 6.28e-04
+2022-04-29 02:57:46,960 INFO [train.py:763] (6/8) Epoch 11, batch 3950, loss[loss=0.2043, simple_loss=0.3035, pruned_loss=0.05253, over 7234.00 frames.], tot_loss[loss=0.189, simple_loss=0.2832, pruned_loss=0.04734, over 1431142.52 frames.], batch size: 20, lr: 6.28e-04
+2022-04-29 02:58:52,092 INFO [train.py:763] (6/8) Epoch 11, batch 4000, loss[loss=0.1944, simple_loss=0.2949, pruned_loss=0.04698, over 7421.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2839, pruned_loss=0.04765, over 1425888.31 frames.], batch size: 21, lr: 6.28e-04
+2022-04-29 02:59:57,357 INFO [train.py:763] (6/8) Epoch 11, batch 4050, loss[loss=0.2014, simple_loss=0.2854, pruned_loss=0.05869, over 7417.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2838, pruned_loss=0.04787, over 1424515.45 frames.], batch size: 20, lr: 6.27e-04
+2022-04-29 03:01:03,191 INFO [train.py:763] (6/8) Epoch 11, batch 4100, loss[loss=0.2327, simple_loss=0.3121, pruned_loss=0.07664, over 7328.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2835, pruned_loss=0.04792, over 1421897.88 frames.], batch size: 20, lr: 6.27e-04
+2022-04-29 03:02:08,283 INFO [train.py:763] (6/8) Epoch 11, batch 4150, loss[loss=0.196, simple_loss=0.2862, pruned_loss=0.05286, over 7229.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2835, pruned_loss=0.04798, over 1422530.60 frames.], batch size: 20, lr: 6.27e-04
+2022-04-29 03:03:14,697 INFO [train.py:763] (6/8) Epoch 11, batch 4200, loss[loss=0.1711, simple_loss=0.2697, pruned_loss=0.03631, over 7333.00 frames.], tot_loss[loss=0.1907, simple_loss=0.284, pruned_loss=0.04866, over 1421717.80 frames.], batch size: 22, lr: 6.27e-04
+2022-04-29 03:04:21,493 INFO [train.py:763] (6/8) Epoch 11, batch 4250, loss[loss=0.1664, simple_loss=0.2595, pruned_loss=0.03662, over 7428.00 frames.], tot_loss[loss=0.1896, simple_loss=0.283, pruned_loss=0.04811, over 1424618.24 frames.], batch size: 18, lr: 6.26e-04
+2022-04-29 03:05:27,594 INFO [train.py:763] (6/8) Epoch 11, batch 4300, loss[loss=0.1776, simple_loss=0.2824, pruned_loss=0.03646, over 7234.00 frames.], tot_loss[loss=0.1889, simple_loss=0.282, pruned_loss=0.04785, over 1418064.52 frames.], batch size: 20, lr: 6.26e-04
+2022-04-29 03:06:35,255 INFO [train.py:763] (6/8) Epoch 11, batch 4350, loss[loss=0.2066, simple_loss=0.3054, pruned_loss=0.05388, over 7209.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2803, pruned_loss=0.04707, over 1419605.25 frames.], batch size: 22, lr: 6.26e-04
+2022-04-29 03:07:41,465 INFO [train.py:763] (6/8) Epoch 11, batch 4400, loss[loss=0.1913, simple_loss=0.2804, pruned_loss=0.05117, over 7316.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2801, pruned_loss=0.04662, over 1417767.32 frames.], batch size: 21, lr: 6.25e-04
+2022-04-29 03:08:47,765 INFO [train.py:763] (6/8) Epoch 11, batch 4450, loss[loss=0.2093, simple_loss=0.2972, pruned_loss=0.06069, over 6285.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2794, pruned_loss=0.04683, over 1405682.76 frames.], batch size: 37, lr: 6.25e-04
+2022-04-29 03:09:54,260 INFO [train.py:763] (6/8) Epoch 11, batch 4500, loss[loss=0.1714, simple_loss=0.2736, pruned_loss=0.03462, over 6577.00 frames.], tot_loss[loss=0.1879, simple_loss=0.28, pruned_loss=0.04791, over 1389418.55 frames.], batch size: 37, lr: 6.25e-04
+2022-04-29 03:10:59,881 INFO [train.py:763] (6/8) Epoch 11, batch 4550, loss[loss=0.2249, simple_loss=0.3064, pruned_loss=0.07177, over 4751.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2823, pruned_loss=0.04992, over 1348775.19 frames.], batch size: 52, lr: 6.25e-04
+2022-04-29 03:12:38,230 INFO [train.py:763] (6/8) Epoch 12, batch 0, loss[loss=0.1846, simple_loss=0.2834, pruned_loss=0.04288, over 7157.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2834, pruned_loss=0.04288, over 7157.00 frames.], batch size: 20, lr: 6.03e-04
+2022-04-29 03:13:44,624 INFO [train.py:763] (6/8) Epoch 12, batch 50, loss[loss=0.1817, simple_loss=0.2808, pruned_loss=0.04134, over 7236.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2836, pruned_loss=0.04716, over 318213.32 frames.], batch size: 20, lr: 6.03e-04
+2022-04-29 03:14:50,402 INFO [train.py:763] (6/8) Epoch 12, batch 100, loss[loss=0.1959, simple_loss=0.291, pruned_loss=0.05041, over 7172.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2821, pruned_loss=0.0452, over 564657.48 frames.], batch size: 23, lr: 6.03e-04
+2022-04-29 03:15:56,442 INFO [train.py:763] (6/8) Epoch 12, batch 150, loss[loss=0.1633, simple_loss=0.2638, pruned_loss=0.03138, over 7143.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2841, pruned_loss=0.04647, over 753840.63 frames.], batch size: 20, lr: 6.03e-04
+2022-04-29 03:17:02,808 INFO [train.py:763] (6/8) Epoch 12, batch 200, loss[loss=0.189, simple_loss=0.2938, pruned_loss=0.04208, over 7150.00 frames.], tot_loss[loss=0.1887, simple_loss=0.284, pruned_loss=0.04669, over 900671.17 frames.], batch size: 20, lr: 6.02e-04
+2022-04-29 03:18:09,056 INFO [train.py:763] (6/8) Epoch 12, batch 250, loss[loss=0.1794, simple_loss=0.2666, pruned_loss=0.04611, over 6850.00 frames.], tot_loss[loss=0.189, simple_loss=0.2841, pruned_loss=0.04693, over 1014309.23 frames.], batch size: 15, lr: 6.02e-04
+2022-04-29 03:19:15,283 INFO [train.py:763] (6/8) Epoch 12, batch 300, loss[loss=0.2207, simple_loss=0.3198, pruned_loss=0.0608, over 7137.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2844, pruned_loss=0.04723, over 1104320.55 frames.], batch size: 20, lr: 6.02e-04
+2022-04-29 03:20:20,575 INFO [train.py:763] (6/8) Epoch 12, batch 350, loss[loss=0.1795, simple_loss=0.2837, pruned_loss=0.03764, over 7023.00 frames.], tot_loss[loss=0.1894, simple_loss=0.285, pruned_loss=0.04692, over 1176549.56 frames.], batch size: 28, lr: 6.01e-04
+2022-04-29 03:21:26,174 INFO [train.py:763] (6/8) Epoch 12, batch 400, loss[loss=0.153, simple_loss=0.2536, pruned_loss=0.02625, over 7359.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2844, pruned_loss=0.04694, over 1233489.45 frames.], batch size: 19, lr: 6.01e-04
+2022-04-29 03:22:31,838 INFO [train.py:763] (6/8) Epoch 12, batch 450, loss[loss=0.161, simple_loss=0.2694, pruned_loss=0.02631, over 7325.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2834, pruned_loss=0.04689, over 1276999.74 frames.], batch size: 21, lr: 6.01e-04
+2022-04-29 03:23:38,040 INFO [train.py:763] (6/8) Epoch 12, batch 500, loss[loss=0.1988, simple_loss=0.2953, pruned_loss=0.05114, over 6438.00 frames.], tot_loss[loss=0.1863, simple_loss=0.281, pruned_loss=0.04584, over 1311239.57 frames.], batch size: 38, lr: 6.01e-04
+2022-04-29 03:24:43,946 INFO [train.py:763] (6/8) Epoch 12, batch 550, loss[loss=0.2375, simple_loss=0.3275, pruned_loss=0.07376, over 7391.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2814, pruned_loss=0.04582, over 1333808.61 frames.], batch size: 23, lr: 6.00e-04
+2022-04-29 03:25:49,965 INFO [train.py:763] (6/8) Epoch 12, batch 600, loss[loss=0.1714, simple_loss=0.2554, pruned_loss=0.04367, over 6782.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2801, pruned_loss=0.04574, over 1347689.04 frames.], batch size: 15, lr: 6.00e-04
+2022-04-29 03:26:55,897 INFO [train.py:763] (6/8) Epoch 12, batch 650, loss[loss=0.1818, simple_loss=0.2733, pruned_loss=0.0452, over 7267.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2805, pruned_loss=0.04562, over 1366603.65 frames.], batch size: 18, lr: 6.00e-04
+2022-04-29 03:28:02,298 INFO [train.py:763] (6/8) Epoch 12, batch 700, loss[loss=0.1928, simple_loss=0.2781, pruned_loss=0.05382, over 6825.00 frames.], tot_loss[loss=0.187, simple_loss=0.2816, pruned_loss=0.04616, over 1383348.95 frames.], batch size: 15, lr: 6.00e-04
+2022-04-29 03:29:08,000 INFO [train.py:763] (6/8) Epoch 12, batch 750, loss[loss=0.2346, simple_loss=0.3147, pruned_loss=0.07721, over 7192.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2828, pruned_loss=0.04649, over 1395678.59 frames.], batch size: 23, lr: 5.99e-04
+2022-04-29 03:30:14,229 INFO [train.py:763] (6/8) Epoch 12, batch 800, loss[loss=0.2099, simple_loss=0.3005, pruned_loss=0.05959, over 7202.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2827, pruned_loss=0.04631, over 1405350.58 frames.], batch size: 22, lr: 5.99e-04
+2022-04-29 03:31:20,653 INFO [train.py:763] (6/8) Epoch 12, batch 850, loss[loss=0.1644, simple_loss=0.2398, pruned_loss=0.04452, over 7134.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2834, pruned_loss=0.04675, over 1412168.20 frames.], batch size: 17, lr: 5.99e-04
+2022-04-29 03:32:27,844 INFO [train.py:763] (6/8) Epoch 12, batch 900, loss[loss=0.1842, simple_loss=0.2926, pruned_loss=0.03795, over 7336.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2817, pruned_loss=0.04596, over 1414922.33 frames.], batch size: 20, lr: 5.99e-04
+2022-04-29 03:33:44,141 INFO [train.py:763] (6/8) Epoch 12, batch 950, loss[loss=0.1766, simple_loss=0.2813, pruned_loss=0.03599, over 7219.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2822, pruned_loss=0.04609, over 1414968.09 frames.], batch size: 26, lr: 5.98e-04
+2022-04-29 03:34:49,708 INFO [train.py:763] (6/8) Epoch 12, batch 1000, loss[loss=0.2063, simple_loss=0.2904, pruned_loss=0.06104, over 6507.00 frames.], tot_loss[loss=0.188, simple_loss=0.283, pruned_loss=0.04653, over 1415864.70 frames.], batch size: 38, lr: 5.98e-04
+2022-04-29 03:35:56,176 INFO [train.py:763] (6/8) Epoch 12, batch 1050, loss[loss=0.2103, simple_loss=0.2935, pruned_loss=0.06352, over 7252.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2824, pruned_loss=0.04692, over 1416641.14 frames.], batch size: 19, lr: 5.98e-04
+2022-04-29 03:37:02,341 INFO [train.py:763] (6/8) Epoch 12, batch 1100, loss[loss=0.2008, simple_loss=0.301, pruned_loss=0.05035, over 7390.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2821, pruned_loss=0.0464, over 1422567.37 frames.], batch size: 23, lr: 5.97e-04
+2022-04-29 03:38:08,857 INFO [train.py:763] (6/8) Epoch 12, batch 1150, loss[loss=0.1898, simple_loss=0.2906, pruned_loss=0.04447, over 7324.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2823, pruned_loss=0.0463, over 1426085.90 frames.], batch size: 20, lr: 5.97e-04
+2022-04-29 03:39:15,160 INFO [train.py:763] (6/8) Epoch 12, batch 1200, loss[loss=0.2115, simple_loss=0.3077, pruned_loss=0.0577, over 4629.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2827, pruned_loss=0.04646, over 1422280.38 frames.], batch size: 53, lr: 5.97e-04
+2022-04-29 03:40:21,633 INFO [train.py:763] (6/8) Epoch 12, batch 1250, loss[loss=0.1762, simple_loss=0.2794, pruned_loss=0.03646, over 7153.00 frames.], tot_loss[loss=0.1885, simple_loss=0.283, pruned_loss=0.04696, over 1419221.51 frames.], batch size: 19, lr: 5.97e-04
+2022-04-29 03:41:28,267 INFO [train.py:763] (6/8) Epoch 12, batch 1300, loss[loss=0.1428, simple_loss=0.2379, pruned_loss=0.02392, over 7071.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2818, pruned_loss=0.04633, over 1419181.14 frames.], batch size: 18, lr: 5.96e-04
+2022-04-29 03:42:33,927 INFO [train.py:763] (6/8) Epoch 12, batch 1350, loss[loss=0.1999, simple_loss=0.2904, pruned_loss=0.0547, over 4840.00 frames.], tot_loss[loss=0.188, simple_loss=0.2827, pruned_loss=0.0467, over 1416190.63 frames.], batch size: 54, lr: 5.96e-04
+2022-04-29 03:43:39,829 INFO [train.py:763] (6/8) Epoch 12, batch 1400, loss[loss=0.1978, simple_loss=0.2917, pruned_loss=0.05192, over 7303.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2827, pruned_loss=0.04715, over 1415224.49 frames.], batch size: 25, lr: 5.96e-04
+2022-04-29 03:44:45,267 INFO [train.py:763] (6/8) Epoch 12, batch 1450, loss[loss=0.1868, simple_loss=0.2792, pruned_loss=0.04719, over 7319.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2826, pruned_loss=0.04686, over 1413779.26 frames.], batch size: 21, lr: 5.96e-04
+2022-04-29 03:45:51,849 INFO [train.py:763] (6/8) Epoch 12, batch 1500, loss[loss=0.2287, simple_loss=0.3218, pruned_loss=0.06777, over 7209.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2823, pruned_loss=0.04657, over 1417443.13 frames.], batch size: 23, lr: 5.95e-04
+2022-04-29 03:46:59,222 INFO [train.py:763] (6/8) Epoch 12, batch 1550, loss[loss=0.2077, simple_loss=0.3048, pruned_loss=0.05528, over 7050.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2821, pruned_loss=0.0465, over 1419343.94 frames.], batch size: 28, lr: 5.95e-04
+2022-04-29 03:48:05,684 INFO [train.py:763] (6/8) Epoch 12, batch 1600, loss[loss=0.2102, simple_loss=0.311, pruned_loss=0.05467, over 7306.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2823, pruned_loss=0.04673, over 1418446.19 frames.], batch size: 25, lr: 5.95e-04
+2022-04-29 03:49:11,829 INFO [train.py:763] (6/8) Epoch 12, batch 1650, loss[loss=0.1958, simple_loss=0.2945, pruned_loss=0.04856, over 7301.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2815, pruned_loss=0.04611, over 1421561.41 frames.], batch size: 24, lr: 5.95e-04
+2022-04-29 03:50:17,595 INFO [train.py:763] (6/8) Epoch 12, batch 1700, loss[loss=0.1644, simple_loss=0.2466, pruned_loss=0.04108, over 7124.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2815, pruned_loss=0.04612, over 1417671.08 frames.], batch size: 17, lr: 5.94e-04
+2022-04-29 03:51:23,277 INFO [train.py:763] (6/8) Epoch 12, batch 1750, loss[loss=0.2116, simple_loss=0.3033, pruned_loss=0.05989, over 7146.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2805, pruned_loss=0.04587, over 1420982.31 frames.], batch size: 26, lr: 5.94e-04
+2022-04-29 03:52:29,190 INFO [train.py:763] (6/8) Epoch 12, batch 1800, loss[loss=0.1669, simple_loss=0.2522, pruned_loss=0.04076, over 7012.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2801, pruned_loss=0.04583, over 1426723.34 frames.], batch size: 16, lr: 5.94e-04
+2022-04-29 03:53:35,392 INFO [train.py:763] (6/8) Epoch 12, batch 1850, loss[loss=0.2067, simple_loss=0.3049, pruned_loss=0.05422, over 7324.00 frames.], tot_loss[loss=0.1857, simple_loss=0.28, pruned_loss=0.0457, over 1427250.31 frames.], batch size: 22, lr: 5.94e-04
+2022-04-29 03:54:41,558 INFO [train.py:763] (6/8) Epoch 12, batch 1900, loss[loss=0.1726, simple_loss=0.2739, pruned_loss=0.03563, over 7229.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2808, pruned_loss=0.04585, over 1428441.10 frames.], batch size: 20, lr: 5.93e-04
+2022-04-29 03:55:47,354 INFO [train.py:763] (6/8) Epoch 12, batch 1950, loss[loss=0.1844, simple_loss=0.263, pruned_loss=0.05288, over 7282.00 frames.], tot_loss[loss=0.1852, simple_loss=0.28, pruned_loss=0.04515, over 1428663.94 frames.], batch size: 17, lr: 5.93e-04
+2022-04-29 03:56:53,847 INFO [train.py:763] (6/8) Epoch 12, batch 2000, loss[loss=0.1781, simple_loss=0.2649, pruned_loss=0.04565, over 7013.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2793, pruned_loss=0.04498, over 1427718.90 frames.], batch size: 16, lr: 5.93e-04
+2022-04-29 03:57:59,764 INFO [train.py:763] (6/8) Epoch 12, batch 2050, loss[loss=0.1588, simple_loss=0.254, pruned_loss=0.03176, over 7154.00 frames.], tot_loss[loss=0.1846, simple_loss=0.279, pruned_loss=0.04513, over 1421125.27 frames.], batch size: 19, lr: 5.93e-04
+2022-04-29 03:59:05,460 INFO [train.py:763] (6/8) Epoch 12, batch 2100, loss[loss=0.1691, simple_loss=0.2644, pruned_loss=0.0369, over 7158.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2798, pruned_loss=0.04558, over 1421124.98 frames.], batch size: 19, lr: 5.92e-04
+2022-04-29 04:00:11,332 INFO [train.py:763] (6/8) Epoch 12, batch 2150, loss[loss=0.1631, simple_loss=0.25, pruned_loss=0.03807, over 7285.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2807, pruned_loss=0.04597, over 1421407.11 frames.], batch size: 18, lr: 5.92e-04
+2022-04-29 04:01:17,166 INFO [train.py:763] (6/8) Epoch 12, batch 2200, loss[loss=0.1752, simple_loss=0.2695, pruned_loss=0.04043, over 7333.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2808, pruned_loss=0.04611, over 1422181.61 frames.], batch size: 20, lr: 5.92e-04
+2022-04-29 04:02:23,228 INFO [train.py:763] (6/8) Epoch 12, batch 2250, loss[loss=0.2012, simple_loss=0.2932, pruned_loss=0.05459, over 7087.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2808, pruned_loss=0.04638, over 1420773.87 frames.], batch size: 28, lr: 5.91e-04
+2022-04-29 04:03:29,737 INFO [train.py:763] (6/8) Epoch 12, batch 2300, loss[loss=0.2026, simple_loss=0.2982, pruned_loss=0.05347, over 7118.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2813, pruned_loss=0.04651, over 1424280.65 frames.], batch size: 21, lr: 5.91e-04
+2022-04-29 04:04:36,296 INFO [train.py:763] (6/8) Epoch 12, batch 2350, loss[loss=0.1788, simple_loss=0.2753, pruned_loss=0.04115, over 7157.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2822, pruned_loss=0.04667, over 1425396.56 frames.], batch size: 19, lr: 5.91e-04
+2022-04-29 04:05:42,056 INFO [train.py:763] (6/8) Epoch 12, batch 2400, loss[loss=0.1575, simple_loss=0.2468, pruned_loss=0.03408, over 7133.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2822, pruned_loss=0.04668, over 1425486.98 frames.], batch size: 17, lr: 5.91e-04
+2022-04-29 04:06:47,904 INFO [train.py:763] (6/8) Epoch 12, batch 2450, loss[loss=0.1781, simple_loss=0.282, pruned_loss=0.03708, over 7215.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2819, pruned_loss=0.04612, over 1424617.56 frames.], batch size: 21, lr: 5.90e-04
+2022-04-29 04:07:54,991 INFO [train.py:763] (6/8) Epoch 12, batch 2500, loss[loss=0.1845, simple_loss=0.2718, pruned_loss=0.04862, over 7290.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2825, pruned_loss=0.04623, over 1425724.81 frames.], batch size: 18, lr: 5.90e-04
+2022-04-29 04:09:01,287 INFO [train.py:763] (6/8) Epoch 12, batch 2550, loss[loss=0.1604, simple_loss=0.2511, pruned_loss=0.03492, over 7318.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2832, pruned_loss=0.04676, over 1428155.38 frames.], batch size: 16, lr: 5.90e-04
+2022-04-29 04:10:08,042 INFO [train.py:763] (6/8) Epoch 12, batch 2600, loss[loss=0.1775, simple_loss=0.2548, pruned_loss=0.0501, over 7187.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2829, pruned_loss=0.04693, over 1425001.56 frames.], batch size: 16, lr: 5.90e-04
+2022-04-29 04:11:13,667 INFO [train.py:763] (6/8) Epoch 12, batch 2650, loss[loss=0.1517, simple_loss=0.2372, pruned_loss=0.03312, over 6994.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2835, pruned_loss=0.04694, over 1422453.47 frames.], batch size: 16, lr: 5.89e-04
+2022-04-29 04:12:19,606 INFO [train.py:763] (6/8) Epoch 12, batch 2700, loss[loss=0.148, simple_loss=0.2366, pruned_loss=0.02973, over 7001.00 frames.], tot_loss[loss=0.188, simple_loss=0.2827, pruned_loss=0.04663, over 1423869.75 frames.], batch size: 16, lr: 5.89e-04
+2022-04-29 04:13:25,132 INFO [train.py:763] (6/8) Epoch 12, batch 2750, loss[loss=0.1831, simple_loss=0.283, pruned_loss=0.04155, over 7114.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2822, pruned_loss=0.04642, over 1421303.72 frames.], batch size: 21, lr: 5.89e-04
+2022-04-29 04:14:30,847 INFO [train.py:763] (6/8) Epoch 12, batch 2800, loss[loss=0.1617, simple_loss=0.2554, pruned_loss=0.03397, over 7140.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2836, pruned_loss=0.04696, over 1420867.46 frames.], batch size: 17, lr: 5.89e-04
+2022-04-29 04:15:37,565 INFO [train.py:763] (6/8) Epoch 12, batch 2850, loss[loss=0.198, simple_loss=0.2861, pruned_loss=0.05498, over 7394.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2836, pruned_loss=0.04686, over 1427053.54 frames.], batch size: 23, lr: 5.88e-04
+2022-04-29 04:16:43,209 INFO [train.py:763] (6/8) Epoch 12, batch 2900, loss[loss=0.1532, simple_loss=0.2481, pruned_loss=0.02915, over 7355.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2845, pruned_loss=0.04714, over 1425009.30 frames.], batch size: 19, lr: 5.88e-04
+2022-04-29 04:17:49,208 INFO [train.py:763] (6/8) Epoch 12, batch 2950, loss[loss=0.187, simple_loss=0.2892, pruned_loss=0.04238, over 7118.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2828, pruned_loss=0.04625, over 1426315.61 frames.], batch size: 21, lr: 5.88e-04
+2022-04-29 04:18:54,868 INFO [train.py:763] (6/8) Epoch 12, batch 3000, loss[loss=0.1399, simple_loss=0.2284, pruned_loss=0.02576, over 7266.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2819, pruned_loss=0.04642, over 1427168.19 frames.], batch size: 17, lr: 5.88e-04
+2022-04-29 04:18:54,869 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 04:19:10,344 INFO [train.py:792] (6/8) Epoch 12, validation: loss=0.1673, simple_loss=0.27, pruned_loss=0.03225, over 698248.00 frames.
+2022-04-29 04:20:16,219 INFO [train.py:763] (6/8) Epoch 12, batch 3050, loss[loss=0.1473, simple_loss=0.2396, pruned_loss=0.0275, over 7156.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2806, pruned_loss=0.04624, over 1427641.06 frames.], batch size: 17, lr: 5.87e-04
+2022-04-29 04:21:32,116 INFO [train.py:763] (6/8) Epoch 12, batch 3100, loss[loss=0.193, simple_loss=0.2889, pruned_loss=0.04854, over 7102.00 frames.], tot_loss[loss=0.186, simple_loss=0.2799, pruned_loss=0.04603, over 1427015.41 frames.], batch size: 21, lr: 5.87e-04
+2022-04-29 04:22:37,475 INFO [train.py:763] (6/8) Epoch 12, batch 3150, loss[loss=0.2319, simple_loss=0.3264, pruned_loss=0.06875, over 7269.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2809, pruned_loss=0.04591, over 1424804.56 frames.], batch size: 25, lr: 5.87e-04
+2022-04-29 04:23:52,370 INFO [train.py:763] (6/8) Epoch 12, batch 3200, loss[loss=0.247, simple_loss=0.327, pruned_loss=0.08349, over 5025.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2818, pruned_loss=0.04575, over 1426014.39 frames.], batch size: 52, lr: 5.87e-04
+2022-04-29 04:25:17,145 INFO [train.py:763] (6/8) Epoch 12, batch 3250, loss[loss=0.1668, simple_loss=0.2549, pruned_loss=0.03937, over 7288.00 frames.], tot_loss[loss=0.186, simple_loss=0.2808, pruned_loss=0.04556, over 1428540.57 frames.], batch size: 17, lr: 5.86e-04
+2022-04-29 04:26:23,035 INFO [train.py:763] (6/8) Epoch 12, batch 3300, loss[loss=0.1672, simple_loss=0.2665, pruned_loss=0.03393, over 7329.00 frames.], tot_loss[loss=0.187, simple_loss=0.2816, pruned_loss=0.04618, over 1428272.50 frames.], batch size: 20, lr: 5.86e-04
+2022-04-29 04:27:37,933 INFO [train.py:763] (6/8) Epoch 12, batch 3350, loss[loss=0.1707, simple_loss=0.2541, pruned_loss=0.04367, over 7007.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2817, pruned_loss=0.04649, over 1421695.27 frames.], batch size: 16, lr: 5.86e-04
+2022-04-29 04:29:03,559 INFO [train.py:763] (6/8) Epoch 12, batch 3400, loss[loss=0.1951, simple_loss=0.2895, pruned_loss=0.05035, over 7374.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2823, pruned_loss=0.04654, over 1425394.16 frames.], batch size: 23, lr: 5.86e-04
+2022-04-29 04:30:18,601 INFO [train.py:763] (6/8) Epoch 12, batch 3450, loss[loss=0.1752, simple_loss=0.255, pruned_loss=0.04765, over 7427.00 frames.], tot_loss[loss=0.188, simple_loss=0.2821, pruned_loss=0.04695, over 1414458.14 frames.], batch size: 18, lr: 5.85e-04
+2022-04-29 04:31:24,822 INFO [train.py:763] (6/8) Epoch 12, batch 3500, loss[loss=0.2165, simple_loss=0.3101, pruned_loss=0.06142, over 6674.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2822, pruned_loss=0.04624, over 1416275.02 frames.], batch size: 31, lr: 5.85e-04
+2022-04-29 04:32:31,886 INFO [train.py:763] (6/8) Epoch 12, batch 3550, loss[loss=0.1579, simple_loss=0.247, pruned_loss=0.03438, over 6991.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2814, pruned_loss=0.04585, over 1421344.28 frames.], batch size: 16, lr: 5.85e-04
+2022-04-29 04:33:38,542 INFO [train.py:763] (6/8) Epoch 12, batch 3600, loss[loss=0.1712, simple_loss=0.2616, pruned_loss=0.04034, over 7300.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2814, pruned_loss=0.04581, over 1421586.64 frames.], batch size: 18, lr: 5.85e-04
+2022-04-29 04:34:44,021 INFO [train.py:763] (6/8) Epoch 12, batch 3650, loss[loss=0.1996, simple_loss=0.2994, pruned_loss=0.04993, over 7409.00 frames.], tot_loss[loss=0.1872, simple_loss=0.282, pruned_loss=0.04616, over 1424297.54 frames.], batch size: 21, lr: 5.84e-04
+2022-04-29 04:35:49,779 INFO [train.py:763] (6/8) Epoch 12, batch 3700, loss[loss=0.2123, simple_loss=0.2969, pruned_loss=0.06388, over 7268.00 frames.], tot_loss[loss=0.1868, simple_loss=0.281, pruned_loss=0.04626, over 1424905.34 frames.], batch size: 19, lr: 5.84e-04
+2022-04-29 04:36:55,385 INFO [train.py:763] (6/8) Epoch 12, batch 3750, loss[loss=0.1898, simple_loss=0.2956, pruned_loss=0.04202, over 7414.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2812, pruned_loss=0.04629, over 1424848.09 frames.], batch size: 21, lr: 5.84e-04
+2022-04-29 04:38:01,437 INFO [train.py:763] (6/8) Epoch 12, batch 3800, loss[loss=0.1895, simple_loss=0.2891, pruned_loss=0.04502, over 7006.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2814, pruned_loss=0.04617, over 1428468.84 frames.], batch size: 28, lr: 5.84e-04
+2022-04-29 04:39:06,795 INFO [train.py:763] (6/8) Epoch 12, batch 3850, loss[loss=0.2408, simple_loss=0.3228, pruned_loss=0.07941, over 7196.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2829, pruned_loss=0.04638, over 1425984.33 frames.], batch size: 22, lr: 5.83e-04
+2022-04-29 04:40:13,134 INFO [train.py:763] (6/8) Epoch 12, batch 3900, loss[loss=0.2011, simple_loss=0.295, pruned_loss=0.05365, over 7289.00 frames.], tot_loss[loss=0.186, simple_loss=0.2809, pruned_loss=0.04554, over 1424436.43 frames.], batch size: 24, lr: 5.83e-04
+2022-04-29 04:41:18,537 INFO [train.py:763] (6/8) Epoch 12, batch 3950, loss[loss=0.1784, simple_loss=0.2952, pruned_loss=0.03076, over 7204.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2816, pruned_loss=0.04557, over 1422955.30 frames.], batch size: 23, lr: 5.83e-04
+2022-04-29 04:42:24,202 INFO [train.py:763] (6/8) Epoch 12, batch 4000, loss[loss=0.1492, simple_loss=0.2358, pruned_loss=0.03132, over 7134.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2815, pruned_loss=0.04554, over 1422570.25 frames.], batch size: 17, lr: 5.83e-04
+2022-04-29 04:43:29,491 INFO [train.py:763] (6/8) Epoch 12, batch 4050, loss[loss=0.1613, simple_loss=0.2601, pruned_loss=0.03128, over 7237.00 frames.], tot_loss[loss=0.186, simple_loss=0.2812, pruned_loss=0.04535, over 1423805.85 frames.], batch size: 20, lr: 5.82e-04
+2022-04-29 04:44:35,697 INFO [train.py:763] (6/8) Epoch 12, batch 4100, loss[loss=0.1842, simple_loss=0.284, pruned_loss=0.04217, over 7147.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2808, pruned_loss=0.0458, over 1423845.06 frames.], batch size: 20, lr: 5.82e-04
+2022-04-29 04:45:41,164 INFO [train.py:763] (6/8) Epoch 12, batch 4150, loss[loss=0.1734, simple_loss=0.2643, pruned_loss=0.04126, over 7437.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2812, pruned_loss=0.04583, over 1418612.89 frames.], batch size: 20, lr: 5.82e-04
+2022-04-29 04:46:48,357 INFO [train.py:763] (6/8) Epoch 12, batch 4200, loss[loss=0.1814, simple_loss=0.2803, pruned_loss=0.04125, over 7153.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2795, pruned_loss=0.04534, over 1420896.12 frames.], batch size: 20, lr: 5.82e-04
+2022-04-29 04:47:54,429 INFO [train.py:763] (6/8) Epoch 12, batch 4250, loss[loss=0.2009, simple_loss=0.287, pruned_loss=0.0574, over 7140.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2796, pruned_loss=0.04548, over 1417954.73 frames.], batch size: 26, lr: 5.81e-04
+2022-04-29 04:49:00,805 INFO [train.py:763] (6/8) Epoch 12, batch 4300, loss[loss=0.1873, simple_loss=0.2768, pruned_loss=0.04894, over 7415.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2804, pruned_loss=0.04624, over 1415569.23 frames.], batch size: 20, lr: 5.81e-04
+2022-04-29 04:50:06,809 INFO [train.py:763] (6/8) Epoch 12, batch 4350, loss[loss=0.1542, simple_loss=0.2503, pruned_loss=0.02903, over 7017.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2804, pruned_loss=0.0464, over 1410506.30 frames.], batch size: 16, lr: 5.81e-04
+2022-04-29 04:51:13,415 INFO [train.py:763] (6/8) Epoch 12, batch 4400, loss[loss=0.2427, simple_loss=0.333, pruned_loss=0.07622, over 5012.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2792, pruned_loss=0.04553, over 1409881.85 frames.], batch size: 52, lr: 5.81e-04
+2022-04-29 04:52:19,271 INFO [train.py:763] (6/8) Epoch 12, batch 4450, loss[loss=0.2314, simple_loss=0.3327, pruned_loss=0.06501, over 7291.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2788, pruned_loss=0.04515, over 1407831.76 frames.], batch size: 24, lr: 5.81e-04
+2022-04-29 04:53:25,183 INFO [train.py:763] (6/8) Epoch 12, batch 4500, loss[loss=0.194, simple_loss=0.2887, pruned_loss=0.04965, over 7414.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2801, pruned_loss=0.04606, over 1388676.77 frames.], batch size: 21, lr: 5.80e-04
+2022-04-29 04:54:31,141 INFO [train.py:763] (6/8) Epoch 12, batch 4550, loss[loss=0.234, simple_loss=0.3276, pruned_loss=0.07022, over 5444.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2831, pruned_loss=0.04794, over 1353215.75 frames.], batch size: 52, lr: 5.80e-04
+2022-04-29 04:56:09,896 INFO [train.py:763] (6/8) Epoch 13, batch 0, loss[loss=0.2039, simple_loss=0.3017, pruned_loss=0.05309, over 7369.00 frames.], tot_loss[loss=0.2039, simple_loss=0.3017, pruned_loss=0.05309, over 7369.00 frames.], batch size: 23, lr: 5.61e-04
+2022-04-29 04:57:15,972 INFO [train.py:763] (6/8) Epoch 13, batch 50, loss[loss=0.2524, simple_loss=0.3293, pruned_loss=0.08778, over 7126.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2764, pruned_loss=0.04437, over 322252.25 frames.], batch size: 21, lr: 5.61e-04
+2022-04-29 04:58:22,264 INFO [train.py:763] (6/8) Epoch 13, batch 100, loss[loss=0.2173, simple_loss=0.3123, pruned_loss=0.06121, over 7147.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2791, pruned_loss=0.04416, over 572067.67 frames.], batch size: 20, lr: 5.61e-04
+2022-04-29 04:59:28,142 INFO [train.py:763] (6/8) Epoch 13, batch 150, loss[loss=0.1646, simple_loss=0.2495, pruned_loss=0.03981, over 6985.00 frames.], tot_loss[loss=0.182, simple_loss=0.2771, pruned_loss=0.04342, over 762385.20 frames.], batch size: 16, lr: 5.61e-04
+2022-04-29 05:00:33,586 INFO [train.py:763] (6/8) Epoch 13, batch 200, loss[loss=0.1674, simple_loss=0.2795, pruned_loss=0.0277, over 7189.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2777, pruned_loss=0.0439, over 909581.35 frames.], batch size: 22, lr: 5.60e-04
+2022-04-29 05:01:39,403 INFO [train.py:763] (6/8) Epoch 13, batch 250, loss[loss=0.2189, simple_loss=0.3171, pruned_loss=0.06029, over 7195.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2786, pruned_loss=0.04432, over 1025330.09 frames.], batch size: 22, lr: 5.60e-04
+2022-04-29 05:02:44,824 INFO [train.py:763] (6/8) Epoch 13, batch 300, loss[loss=0.1605, simple_loss=0.2595, pruned_loss=0.03077, over 7409.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2804, pruned_loss=0.04463, over 1111797.37 frames.], batch size: 21, lr: 5.60e-04
+2022-04-29 05:03:50,337 INFO [train.py:763] (6/8) Epoch 13, batch 350, loss[loss=0.1802, simple_loss=0.288, pruned_loss=0.03622, over 7431.00 frames.], tot_loss[loss=0.184, simple_loss=0.2791, pruned_loss=0.0444, over 1179788.00 frames.], batch size: 20, lr: 5.60e-04
+2022-04-29 05:04:55,875 INFO [train.py:763] (6/8) Epoch 13, batch 400, loss[loss=0.1844, simple_loss=0.2779, pruned_loss=0.0454, over 6998.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2792, pruned_loss=0.04465, over 1230089.36 frames.], batch size: 28, lr: 5.59e-04
+2022-04-29 05:06:01,970 INFO [train.py:763] (6/8) Epoch 13, batch 450, loss[loss=0.2079, simple_loss=0.3054, pruned_loss=0.05521, over 6393.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2807, pruned_loss=0.0449, over 1272085.23 frames.], batch size: 37, lr: 5.59e-04
+2022-04-29 05:07:07,986 INFO [train.py:763] (6/8) Epoch 13, batch 500, loss[loss=0.242, simple_loss=0.3242, pruned_loss=0.07988, over 7066.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2806, pruned_loss=0.0451, over 1299152.66 frames.], batch size: 28, lr: 5.59e-04
+2022-04-29 05:08:13,590 INFO [train.py:763] (6/8) Epoch 13, batch 550, loss[loss=0.1974, simple_loss=0.293, pruned_loss=0.05089, over 6366.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2803, pruned_loss=0.04496, over 1325425.74 frames.], batch size: 38, lr: 5.59e-04
+2022-04-29 05:09:19,619 INFO [train.py:763] (6/8) Epoch 13, batch 600, loss[loss=0.2121, simple_loss=0.3103, pruned_loss=0.05696, over 7324.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2802, pruned_loss=0.0452, over 1347736.23 frames.], batch size: 21, lr: 5.59e-04
+2022-04-29 05:10:25,764 INFO [train.py:763] (6/8) Epoch 13, batch 650, loss[loss=0.1695, simple_loss=0.2648, pruned_loss=0.03708, over 7065.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2805, pruned_loss=0.04513, over 1360424.07 frames.], batch size: 18, lr: 5.58e-04
+2022-04-29 05:11:32,550 INFO [train.py:763] (6/8) Epoch 13, batch 700, loss[loss=0.1486, simple_loss=0.2446, pruned_loss=0.02634, over 7275.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2797, pruned_loss=0.04457, over 1375888.13 frames.], batch size: 18, lr: 5.58e-04
+2022-04-29 05:12:37,746 INFO [train.py:763] (6/8) Epoch 13, batch 750, loss[loss=0.2176, simple_loss=0.31, pruned_loss=0.06258, over 7202.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2798, pruned_loss=0.04445, over 1382549.35 frames.], batch size: 23, lr: 5.58e-04
+2022-04-29 05:13:44,377 INFO [train.py:763] (6/8) Epoch 13, batch 800, loss[loss=0.1841, simple_loss=0.2831, pruned_loss=0.04252, over 7335.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2802, pruned_loss=0.04451, over 1391835.01 frames.], batch size: 25, lr: 5.58e-04
+2022-04-29 05:14:50,892 INFO [train.py:763] (6/8) Epoch 13, batch 850, loss[loss=0.1655, simple_loss=0.2642, pruned_loss=0.03344, over 7225.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2799, pruned_loss=0.04453, over 1400689.30 frames.], batch size: 21, lr: 5.57e-04
+2022-04-29 05:15:57,549 INFO [train.py:763] (6/8) Epoch 13, batch 900, loss[loss=0.1685, simple_loss=0.2614, pruned_loss=0.03785, over 7162.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2808, pruned_loss=0.04512, over 1404228.38 frames.], batch size: 18, lr: 5.57e-04
+2022-04-29 05:17:04,247 INFO [train.py:763] (6/8) Epoch 13, batch 950, loss[loss=0.1807, simple_loss=0.2849, pruned_loss=0.03831, over 7222.00 frames.], tot_loss[loss=0.185, simple_loss=0.2806, pruned_loss=0.04473, over 1404836.86 frames.], batch size: 21, lr: 5.57e-04
+2022-04-29 05:18:11,094 INFO [train.py:763] (6/8) Epoch 13, batch 1000, loss[loss=0.2207, simple_loss=0.3007, pruned_loss=0.07033, over 7213.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2804, pruned_loss=0.04486, over 1411658.56 frames.], batch size: 22, lr: 5.57e-04
+2022-04-29 05:19:17,016 INFO [train.py:763] (6/8) Epoch 13, batch 1050, loss[loss=0.1801, simple_loss=0.2897, pruned_loss=0.03527, over 7411.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2797, pruned_loss=0.04464, over 1411582.19 frames.], batch size: 21, lr: 5.56e-04
+2022-04-29 05:20:22,746 INFO [train.py:763] (6/8) Epoch 13, batch 1100, loss[loss=0.2079, simple_loss=0.2967, pruned_loss=0.05956, over 6623.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2789, pruned_loss=0.04415, over 1410519.65 frames.], batch size: 31, lr: 5.56e-04
+2022-04-29 05:21:28,696 INFO [train.py:763] (6/8) Epoch 13, batch 1150, loss[loss=0.2216, simple_loss=0.3124, pruned_loss=0.06539, over 7333.00 frames.], tot_loss[loss=0.185, simple_loss=0.2804, pruned_loss=0.04482, over 1410679.95 frames.], batch size: 22, lr: 5.56e-04
+2022-04-29 05:22:34,609 INFO [train.py:763] (6/8) Epoch 13, batch 1200, loss[loss=0.2498, simple_loss=0.3237, pruned_loss=0.08795, over 5278.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2804, pruned_loss=0.0451, over 1410677.37 frames.], batch size: 53, lr: 5.56e-04
+2022-04-29 05:23:40,301 INFO [train.py:763] (6/8) Epoch 13, batch 1250, loss[loss=0.1992, simple_loss=0.2826, pruned_loss=0.05792, over 7434.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2812, pruned_loss=0.04527, over 1414739.57 frames.], batch size: 20, lr: 5.56e-04
+2022-04-29 05:24:45,577 INFO [train.py:763] (6/8) Epoch 13, batch 1300, loss[loss=0.182, simple_loss=0.2789, pruned_loss=0.04252, over 7262.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2813, pruned_loss=0.04488, over 1418479.52 frames.], batch size: 19, lr: 5.55e-04
+2022-04-29 05:25:51,459 INFO [train.py:763] (6/8) Epoch 13, batch 1350, loss[loss=0.1648, simple_loss=0.2542, pruned_loss=0.0377, over 7278.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2807, pruned_loss=0.04505, over 1422270.70 frames.], batch size: 18, lr: 5.55e-04
+2022-04-29 05:26:57,108 INFO [train.py:763] (6/8) Epoch 13, batch 1400, loss[loss=0.1582, simple_loss=0.2516, pruned_loss=0.03237, over 7162.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2808, pruned_loss=0.04537, over 1418200.59 frames.], batch size: 18, lr: 5.55e-04
+2022-04-29 05:28:02,592 INFO [train.py:763] (6/8) Epoch 13, batch 1450, loss[loss=0.1562, simple_loss=0.2436, pruned_loss=0.0344, over 7284.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2806, pruned_loss=0.04506, over 1421482.57 frames.], batch size: 17, lr: 5.55e-04
+2022-04-29 05:29:08,109 INFO [train.py:763] (6/8) Epoch 13, batch 1500, loss[loss=0.1941, simple_loss=0.283, pruned_loss=0.05263, over 7296.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2791, pruned_loss=0.04433, over 1423012.28 frames.], batch size: 17, lr: 5.54e-04
+2022-04-29 05:30:14,046 INFO [train.py:763] (6/8) Epoch 13, batch 1550, loss[loss=0.2043, simple_loss=0.3047, pruned_loss=0.05191, over 6285.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2803, pruned_loss=0.04507, over 1417596.98 frames.], batch size: 37, lr: 5.54e-04
+2022-04-29 05:31:19,482 INFO [train.py:763] (6/8) Epoch 13, batch 1600, loss[loss=0.1827, simple_loss=0.2864, pruned_loss=0.0395, over 7414.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2805, pruned_loss=0.04487, over 1416731.53 frames.], batch size: 21, lr: 5.54e-04
+2022-04-29 05:32:25,609 INFO [train.py:763] (6/8) Epoch 13, batch 1650, loss[loss=0.1975, simple_loss=0.2844, pruned_loss=0.05531, over 7229.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2819, pruned_loss=0.04583, over 1418933.87 frames.], batch size: 20, lr: 5.54e-04
+2022-04-29 05:33:31,239 INFO [train.py:763] (6/8) Epoch 13, batch 1700, loss[loss=0.1845, simple_loss=0.279, pruned_loss=0.04499, over 6423.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2817, pruned_loss=0.04584, over 1418441.41 frames.], batch size: 38, lr: 5.54e-04
+2022-04-29 05:34:36,781 INFO [train.py:763] (6/8) Epoch 13, batch 1750, loss[loss=0.1575, simple_loss=0.2565, pruned_loss=0.02923, over 7277.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2801, pruned_loss=0.04508, over 1421731.20 frames.], batch size: 17, lr: 5.53e-04
+2022-04-29 05:35:42,703 INFO [train.py:763] (6/8) Epoch 13, batch 1800, loss[loss=0.1715, simple_loss=0.2694, pruned_loss=0.03684, over 7141.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2794, pruned_loss=0.04502, over 1426083.32 frames.], batch size: 20, lr: 5.53e-04
+2022-04-29 05:36:48,186 INFO [train.py:763] (6/8) Epoch 13, batch 1850, loss[loss=0.1762, simple_loss=0.2784, pruned_loss=0.03704, over 7288.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2799, pruned_loss=0.04527, over 1425909.90 frames.], batch size: 25, lr: 5.53e-04
+2022-04-29 05:37:54,119 INFO [train.py:763] (6/8) Epoch 13, batch 1900, loss[loss=0.1879, simple_loss=0.2802, pruned_loss=0.04779, over 6265.00 frames.], tot_loss[loss=0.1851, simple_loss=0.28, pruned_loss=0.04509, over 1421051.33 frames.], batch size: 37, lr: 5.53e-04
+2022-04-29 05:39:00,729 INFO [train.py:763] (6/8) Epoch 13, batch 1950, loss[loss=0.1887, simple_loss=0.2873, pruned_loss=0.0451, over 7261.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2811, pruned_loss=0.04537, over 1421977.65 frames.], batch size: 19, lr: 5.52e-04
+2022-04-29 05:40:07,433 INFO [train.py:763] (6/8) Epoch 13, batch 2000, loss[loss=0.1788, simple_loss=0.286, pruned_loss=0.0358, over 7338.00 frames.], tot_loss[loss=0.185, simple_loss=0.2805, pruned_loss=0.04473, over 1423218.03 frames.], batch size: 22, lr: 5.52e-04
+2022-04-29 05:41:13,026 INFO [train.py:763] (6/8) Epoch 13, batch 2050, loss[loss=0.2118, simple_loss=0.308, pruned_loss=0.05784, over 7385.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2794, pruned_loss=0.04402, over 1424496.17 frames.], batch size: 23, lr: 5.52e-04
+2022-04-29 05:42:18,154 INFO [train.py:763] (6/8) Epoch 13, batch 2100, loss[loss=0.1975, simple_loss=0.2917, pruned_loss=0.05158, over 7237.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2799, pruned_loss=0.04391, over 1424322.61 frames.], batch size: 20, lr: 5.52e-04
+2022-04-29 05:43:24,243 INFO [train.py:763] (6/8) Epoch 13, batch 2150, loss[loss=0.1978, simple_loss=0.2946, pruned_loss=0.05053, over 7171.00 frames.], tot_loss[loss=0.183, simple_loss=0.2792, pruned_loss=0.04343, over 1426942.69 frames.], batch size: 26, lr: 5.52e-04
+2022-04-29 05:44:29,758 INFO [train.py:763] (6/8) Epoch 13, batch 2200, loss[loss=0.1538, simple_loss=0.2526, pruned_loss=0.02753, over 7432.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2793, pruned_loss=0.04329, over 1425797.84 frames.], batch size: 20, lr: 5.51e-04
+2022-04-29 05:45:35,368 INFO [train.py:763] (6/8) Epoch 13, batch 2250, loss[loss=0.1701, simple_loss=0.2615, pruned_loss=0.03936, over 7236.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2788, pruned_loss=0.04352, over 1427362.28 frames.], batch size: 20, lr: 5.51e-04
+2022-04-29 05:46:41,461 INFO [train.py:763] (6/8) Epoch 13, batch 2300, loss[loss=0.1888, simple_loss=0.2869, pruned_loss=0.04533, over 7047.00 frames.], tot_loss[loss=0.1822, simple_loss=0.278, pruned_loss=0.04317, over 1427651.44 frames.], batch size: 28, lr: 5.51e-04
+2022-04-29 05:47:46,895 INFO [train.py:763] (6/8) Epoch 13, batch 2350, loss[loss=0.2201, simple_loss=0.3065, pruned_loss=0.06686, over 5018.00 frames.], tot_loss[loss=0.183, simple_loss=0.2788, pruned_loss=0.04357, over 1427501.64 frames.], batch size: 53, lr: 5.51e-04
+2022-04-29 05:48:52,769 INFO [train.py:763] (6/8) Epoch 13, batch 2400, loss[loss=0.1716, simple_loss=0.2586, pruned_loss=0.04234, over 7269.00 frames.], tot_loss[loss=0.1822, simple_loss=0.278, pruned_loss=0.04322, over 1429160.88 frames.], batch size: 17, lr: 5.50e-04
+2022-04-29 05:49:58,373 INFO [train.py:763] (6/8) Epoch 13, batch 2450, loss[loss=0.1983, simple_loss=0.2965, pruned_loss=0.05001, over 6838.00 frames.], tot_loss[loss=0.183, simple_loss=0.279, pruned_loss=0.04353, over 1431673.03 frames.], batch size: 31, lr: 5.50e-04
+2022-04-29 05:51:03,651 INFO [train.py:763] (6/8) Epoch 13, batch 2500, loss[loss=0.1374, simple_loss=0.2348, pruned_loss=0.02002, over 7286.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2801, pruned_loss=0.04439, over 1427827.94 frames.], batch size: 17, lr: 5.50e-04
+2022-04-29 05:52:08,892 INFO [train.py:763] (6/8) Epoch 13, batch 2550, loss[loss=0.1751, simple_loss=0.2773, pruned_loss=0.0364, over 7287.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2805, pruned_loss=0.04458, over 1423052.57 frames.], batch size: 25, lr: 5.50e-04
+2022-04-29 05:53:14,609 INFO [train.py:763] (6/8) Epoch 13, batch 2600, loss[loss=0.1959, simple_loss=0.299, pruned_loss=0.04641, over 7414.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2807, pruned_loss=0.0449, over 1418991.96 frames.], batch size: 21, lr: 5.50e-04
+2022-04-29 05:54:20,021 INFO [train.py:763] (6/8) Epoch 13, batch 2650, loss[loss=0.2149, simple_loss=0.3088, pruned_loss=0.06051, over 7118.00 frames.], tot_loss[loss=0.185, simple_loss=0.2803, pruned_loss=0.04486, over 1418405.70 frames.], batch size: 21, lr: 5.49e-04
+2022-04-29 05:55:25,829 INFO [train.py:763] (6/8) Epoch 13, batch 2700, loss[loss=0.1625, simple_loss=0.2556, pruned_loss=0.03463, over 6998.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2788, pruned_loss=0.04391, over 1423429.92 frames.], batch size: 16, lr: 5.49e-04
+2022-04-29 05:56:31,326 INFO [train.py:763] (6/8) Epoch 13, batch 2750, loss[loss=0.183, simple_loss=0.2703, pruned_loss=0.04787, over 7292.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2787, pruned_loss=0.04404, over 1428579.93 frames.], batch size: 24, lr: 5.49e-04
+2022-04-29 05:57:36,855 INFO [train.py:763] (6/8) Epoch 13, batch 2800, loss[loss=0.173, simple_loss=0.2674, pruned_loss=0.03928, over 7120.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2785, pruned_loss=0.04404, over 1427024.88 frames.], batch size: 17, lr: 5.49e-04
+2022-04-29 05:58:42,725 INFO [train.py:763] (6/8) Epoch 13, batch 2850, loss[loss=0.1888, simple_loss=0.2816, pruned_loss=0.04798, over 7409.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2783, pruned_loss=0.04452, over 1428272.84 frames.], batch size: 21, lr: 5.48e-04
+2022-04-29 05:59:48,437 INFO [train.py:763] (6/8) Epoch 13, batch 2900, loss[loss=0.1998, simple_loss=0.3081, pruned_loss=0.04574, over 7115.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2783, pruned_loss=0.04401, over 1429139.30 frames.], batch size: 21, lr: 5.48e-04
+2022-04-29 06:00:53,880 INFO [train.py:763] (6/8) Epoch 13, batch 2950, loss[loss=0.2341, simple_loss=0.3258, pruned_loss=0.07123, over 7189.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2788, pruned_loss=0.04365, over 1430480.65 frames.], batch size: 23, lr: 5.48e-04
+2022-04-29 06:01:59,747 INFO [train.py:763] (6/8) Epoch 13, batch 3000, loss[loss=0.1998, simple_loss=0.3045, pruned_loss=0.04752, over 7320.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2779, pruned_loss=0.0436, over 1431272.19 frames.], batch size: 24, lr: 5.48e-04
+2022-04-29 06:01:59,748 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 06:02:15,158 INFO [train.py:792] (6/8) Epoch 13, validation: loss=0.1677, simple_loss=0.2714, pruned_loss=0.03198, over 698248.00 frames.
+2022-04-29 06:03:21,968 INFO [train.py:763] (6/8) Epoch 13, batch 3050, loss[loss=0.1679, simple_loss=0.2602, pruned_loss=0.03781, over 7258.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2788, pruned_loss=0.04377, over 1431296.36 frames.], batch size: 17, lr: 5.48e-04
+2022-04-29 06:04:29,183 INFO [train.py:763] (6/8) Epoch 13, batch 3100, loss[loss=0.1952, simple_loss=0.2978, pruned_loss=0.0463, over 7185.00 frames.], tot_loss[loss=0.1835, simple_loss=0.279, pruned_loss=0.04399, over 1431355.82 frames.], batch size: 23, lr: 5.47e-04
+2022-04-29 06:05:35,705 INFO [train.py:763] (6/8) Epoch 13, batch 3150, loss[loss=0.2289, simple_loss=0.309, pruned_loss=0.07445, over 5129.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2774, pruned_loss=0.04284, over 1430073.88 frames.], batch size: 52, lr: 5.47e-04
+2022-04-29 06:06:41,346 INFO [train.py:763] (6/8) Epoch 13, batch 3200, loss[loss=0.2014, simple_loss=0.2962, pruned_loss=0.05326, over 7337.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2776, pruned_loss=0.04296, over 1429282.83 frames.], batch size: 22, lr: 5.47e-04
+2022-04-29 06:07:46,884 INFO [train.py:763] (6/8) Epoch 13, batch 3250, loss[loss=0.2099, simple_loss=0.3087, pruned_loss=0.0555, over 7208.00 frames.], tot_loss[loss=0.1822, simple_loss=0.278, pruned_loss=0.0432, over 1426336.44 frames.], batch size: 26, lr: 5.47e-04
+2022-04-29 06:08:52,447 INFO [train.py:763] (6/8) Epoch 13, batch 3300, loss[loss=0.1698, simple_loss=0.2648, pruned_loss=0.03737, over 7161.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2784, pruned_loss=0.04372, over 1424024.96 frames.], batch size: 18, lr: 5.46e-04
+2022-04-29 06:09:57,828 INFO [train.py:763] (6/8) Epoch 13, batch 3350, loss[loss=0.1557, simple_loss=0.248, pruned_loss=0.03168, over 7416.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2782, pruned_loss=0.0436, over 1425674.13 frames.], batch size: 18, lr: 5.46e-04
+2022-04-29 06:11:03,349 INFO [train.py:763] (6/8) Epoch 13, batch 3400, loss[loss=0.1958, simple_loss=0.3019, pruned_loss=0.04487, over 7158.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2787, pruned_loss=0.04386, over 1425994.19 frames.], batch size: 18, lr: 5.46e-04
+2022-04-29 06:12:10,254 INFO [train.py:763] (6/8) Epoch 13, batch 3450, loss[loss=0.1865, simple_loss=0.2851, pruned_loss=0.04398, over 7117.00 frames.], tot_loss[loss=0.184, simple_loss=0.2795, pruned_loss=0.04428, over 1424687.98 frames.], batch size: 21, lr: 5.46e-04
+2022-04-29 06:13:16,584 INFO [train.py:763] (6/8) Epoch 13, batch 3500, loss[loss=0.2021, simple_loss=0.3045, pruned_loss=0.04985, over 7336.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2787, pruned_loss=0.04411, over 1426425.70 frames.], batch size: 22, lr: 5.46e-04
+2022-04-29 06:14:22,080 INFO [train.py:763] (6/8) Epoch 13, batch 3550, loss[loss=0.1712, simple_loss=0.2706, pruned_loss=0.03589, over 7321.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2791, pruned_loss=0.04408, over 1426439.97 frames.], batch size: 21, lr: 5.45e-04
+2022-04-29 06:15:27,779 INFO [train.py:763] (6/8) Epoch 13, batch 3600, loss[loss=0.1606, simple_loss=0.2534, pruned_loss=0.03393, over 7350.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2777, pruned_loss=0.04382, over 1429999.30 frames.], batch size: 19, lr: 5.45e-04
+2022-04-29 06:16:33,708 INFO [train.py:763] (6/8) Epoch 13, batch 3650, loss[loss=0.1966, simple_loss=0.2715, pruned_loss=0.06087, over 7230.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2779, pruned_loss=0.04417, over 1429608.33 frames.], batch size: 20, lr: 5.45e-04
+2022-04-29 06:17:39,183 INFO [train.py:763] (6/8) Epoch 13, batch 3700, loss[loss=0.2054, simple_loss=0.3072, pruned_loss=0.05183, over 7312.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2788, pruned_loss=0.04437, over 1421708.76 frames.], batch size: 24, lr: 5.45e-04
+2022-04-29 06:18:44,837 INFO [train.py:763] (6/8) Epoch 13, batch 3750, loss[loss=0.2106, simple_loss=0.2849, pruned_loss=0.06814, over 4807.00 frames.], tot_loss[loss=0.184, simple_loss=0.2793, pruned_loss=0.04437, over 1419819.80 frames.], batch size: 52, lr: 5.45e-04
+2022-04-29 06:19:51,471 INFO [train.py:763] (6/8) Epoch 13, batch 3800, loss[loss=0.1544, simple_loss=0.2361, pruned_loss=0.03631, over 7018.00 frames.], tot_loss[loss=0.184, simple_loss=0.2792, pruned_loss=0.04437, over 1419104.09 frames.], batch size: 16, lr: 5.44e-04
+2022-04-29 06:20:57,072 INFO [train.py:763] (6/8) Epoch 13, batch 3850, loss[loss=0.177, simple_loss=0.2701, pruned_loss=0.04193, over 7189.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2793, pruned_loss=0.04445, over 1420297.08 frames.], batch size: 22, lr: 5.44e-04
+2022-04-29 06:22:02,334 INFO [train.py:763] (6/8) Epoch 13, batch 3900, loss[loss=0.2047, simple_loss=0.3034, pruned_loss=0.05298, over 7318.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2799, pruned_loss=0.04471, over 1421864.53 frames.], batch size: 21, lr: 5.44e-04
+2022-04-29 06:23:08,134 INFO [train.py:763] (6/8) Epoch 13, batch 3950, loss[loss=0.2308, simple_loss=0.3142, pruned_loss=0.0737, over 5191.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2789, pruned_loss=0.04427, over 1420290.76 frames.], batch size: 53, lr: 5.44e-04
+2022-04-29 06:24:13,271 INFO [train.py:763] (6/8) Epoch 13, batch 4000, loss[loss=0.2028, simple_loss=0.2926, pruned_loss=0.05654, over 7334.00 frames.], tot_loss[loss=0.185, simple_loss=0.2804, pruned_loss=0.04483, over 1422133.37 frames.], batch size: 22, lr: 5.43e-04
+2022-04-29 06:25:19,013 INFO [train.py:763] (6/8) Epoch 13, batch 4050, loss[loss=0.1685, simple_loss=0.2549, pruned_loss=0.04105, over 7167.00 frames.], tot_loss[loss=0.1836, simple_loss=0.279, pruned_loss=0.04413, over 1423901.03 frames.], batch size: 16, lr: 5.43e-04
+2022-04-29 06:26:24,354 INFO [train.py:763] (6/8) Epoch 13, batch 4100, loss[loss=0.1866, simple_loss=0.283, pruned_loss=0.0451, over 6787.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2784, pruned_loss=0.04426, over 1421162.33 frames.], batch size: 31, lr: 5.43e-04
+2022-04-29 06:27:29,933 INFO [train.py:763] (6/8) Epoch 13, batch 4150, loss[loss=0.1712, simple_loss=0.2688, pruned_loss=0.03674, over 7218.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2774, pruned_loss=0.0434, over 1420022.38 frames.], batch size: 21, lr: 5.43e-04
+2022-04-29 06:28:36,037 INFO [train.py:763] (6/8) Epoch 13, batch 4200, loss[loss=0.1924, simple_loss=0.2686, pruned_loss=0.05809, over 7297.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2765, pruned_loss=0.04288, over 1421839.29 frames.], batch size: 17, lr: 5.43e-04
+2022-04-29 06:29:41,278 INFO [train.py:763] (6/8) Epoch 13, batch 4250, loss[loss=0.2171, simple_loss=0.3104, pruned_loss=0.0619, over 6440.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2771, pruned_loss=0.04319, over 1415597.02 frames.], batch size: 38, lr: 5.42e-04
+2022-04-29 06:30:47,745 INFO [train.py:763] (6/8) Epoch 13, batch 4300, loss[loss=0.2091, simple_loss=0.3034, pruned_loss=0.05738, over 7213.00 frames.], tot_loss[loss=0.1826, simple_loss=0.278, pruned_loss=0.04363, over 1411411.89 frames.], batch size: 21, lr: 5.42e-04
+2022-04-29 06:31:53,160 INFO [train.py:763] (6/8) Epoch 13, batch 4350, loss[loss=0.1467, simple_loss=0.2303, pruned_loss=0.03158, over 7212.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2786, pruned_loss=0.04406, over 1408276.66 frames.], batch size: 16, lr: 5.42e-04
+2022-04-29 06:33:10,016 INFO [train.py:763] (6/8) Epoch 13, batch 4400, loss[loss=0.1867, simple_loss=0.272, pruned_loss=0.05073, over 7147.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2782, pruned_loss=0.04399, over 1401442.28 frames.], batch size: 20, lr: 5.42e-04
+2022-04-29 06:34:14,931 INFO [train.py:763] (6/8) Epoch 13, batch 4450, loss[loss=0.2037, simple_loss=0.2913, pruned_loss=0.0581, over 4868.00 frames.], tot_loss[loss=0.1836, simple_loss=0.279, pruned_loss=0.04416, over 1391890.40 frames.], batch size: 52, lr: 5.42e-04
+2022-04-29 06:35:30,494 INFO [train.py:763] (6/8) Epoch 13, batch 4500, loss[loss=0.2059, simple_loss=0.2988, pruned_loss=0.05651, over 4963.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2803, pruned_loss=0.04512, over 1375916.46 frames.], batch size: 54, lr: 5.41e-04
+2022-04-29 06:36:35,408 INFO [train.py:763] (6/8) Epoch 13, batch 4550, loss[loss=0.2017, simple_loss=0.2915, pruned_loss=0.0559, over 6739.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2804, pruned_loss=0.04534, over 1365716.98 frames.], batch size: 31, lr: 5.41e-04
+2022-04-29 06:38:13,964 INFO [train.py:763] (6/8) Epoch 14, batch 0, loss[loss=0.1956, simple_loss=0.2952, pruned_loss=0.04803, over 7091.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2952, pruned_loss=0.04803, over 7091.00 frames.], batch size: 28, lr: 5.25e-04
+2022-04-29 06:39:20,774 INFO [train.py:763] (6/8) Epoch 14, batch 50, loss[loss=0.24, simple_loss=0.319, pruned_loss=0.08047, over 4879.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2791, pruned_loss=0.04307, over 321499.61 frames.], batch size: 52, lr: 5.24e-04
+2022-04-29 06:40:45,785 INFO [train.py:763] (6/8) Epoch 14, batch 100, loss[loss=0.1998, simple_loss=0.2923, pruned_loss=0.0536, over 7163.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2799, pruned_loss=0.04385, over 568443.55 frames.], batch size: 18, lr: 5.24e-04
+2022-04-29 06:41:59,832 INFO [train.py:763] (6/8) Epoch 14, batch 150, loss[loss=0.1642, simple_loss=0.2763, pruned_loss=0.02602, over 7114.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2816, pruned_loss=0.04401, over 758969.82 frames.], batch size: 21, lr: 5.24e-04
+2022-04-29 06:43:06,516 INFO [train.py:763] (6/8) Epoch 14, batch 200, loss[loss=0.2053, simple_loss=0.3045, pruned_loss=0.05304, over 7324.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2821, pruned_loss=0.0444, over 903055.43 frames.], batch size: 20, lr: 5.24e-04
+2022-04-29 06:44:23,225 INFO [train.py:763] (6/8) Epoch 14, batch 250, loss[loss=0.2104, simple_loss=0.3066, pruned_loss=0.05708, over 6114.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2812, pruned_loss=0.04464, over 1019494.18 frames.], batch size: 37, lr: 5.24e-04
+2022-04-29 06:45:48,393 INFO [train.py:763] (6/8) Epoch 14, batch 300, loss[loss=0.1499, simple_loss=0.2396, pruned_loss=0.03012, over 7116.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2785, pruned_loss=0.04329, over 1109282.41 frames.], batch size: 17, lr: 5.23e-04
+2022-04-29 06:46:55,903 INFO [train.py:763] (6/8) Epoch 14, batch 350, loss[loss=0.1296, simple_loss=0.2159, pruned_loss=0.02169, over 6788.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2779, pruned_loss=0.04349, over 1171847.60 frames.], batch size: 15, lr: 5.23e-04
+2022-04-29 06:48:03,003 INFO [train.py:763] (6/8) Epoch 14, batch 400, loss[loss=0.2048, simple_loss=0.3055, pruned_loss=0.05201, over 7140.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2776, pruned_loss=0.04368, over 1227481.68 frames.], batch size: 20, lr: 5.23e-04
+2022-04-29 06:49:01,687 INFO [train.py:763] (6/8) Epoch 14, batch 450, loss[loss=0.1898, simple_loss=0.2756, pruned_loss=0.05199, over 7153.00 frames.], tot_loss[loss=0.1815, simple_loss=0.277, pruned_loss=0.04297, over 1271932.91 frames.], batch size: 19, lr: 5.23e-04
+2022-04-29 06:50:05,440 INFO [train.py:763] (6/8) Epoch 14, batch 500, loss[loss=0.1832, simple_loss=0.2809, pruned_loss=0.04279, over 7424.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2774, pruned_loss=0.043, over 1304732.16 frames.], batch size: 20, lr: 5.23e-04
+2022-04-29 06:51:07,461 INFO [train.py:763] (6/8) Epoch 14, batch 550, loss[loss=0.156, simple_loss=0.2614, pruned_loss=0.02527, over 7290.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2759, pruned_loss=0.04242, over 1333669.64 frames.], batch size: 18, lr: 5.22e-04
+2022-04-29 06:52:12,673 INFO [train.py:763] (6/8) Epoch 14, batch 600, loss[loss=0.1668, simple_loss=0.2766, pruned_loss=0.02848, over 7236.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2753, pruned_loss=0.04187, over 1356079.02 frames.], batch size: 20, lr: 5.22e-04
+2022-04-29 06:53:18,168 INFO [train.py:763] (6/8) Epoch 14, batch 650, loss[loss=0.1656, simple_loss=0.2722, pruned_loss=0.0295, over 7330.00 frames.], tot_loss[loss=0.1801, simple_loss=0.276, pruned_loss=0.04209, over 1370779.35 frames.], batch size: 22, lr: 5.22e-04
+2022-04-29 06:54:23,432 INFO [train.py:763] (6/8) Epoch 14, batch 700, loss[loss=0.1716, simple_loss=0.2631, pruned_loss=0.04001, over 7323.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2764, pruned_loss=0.042, over 1383215.64 frames.], batch size: 20, lr: 5.22e-04
+2022-04-29 06:55:28,866 INFO [train.py:763] (6/8) Epoch 14, batch 750, loss[loss=0.2085, simple_loss=0.3102, pruned_loss=0.05339, over 7347.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2765, pruned_loss=0.04189, over 1391493.88 frames.], batch size: 22, lr: 5.22e-04
+2022-04-29 06:56:34,179 INFO [train.py:763] (6/8) Epoch 14, batch 800, loss[loss=0.1864, simple_loss=0.2829, pruned_loss=0.04498, over 7338.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2771, pruned_loss=0.04229, over 1398895.32 frames.], batch size: 22, lr: 5.21e-04
+2022-04-29 06:57:40,708 INFO [train.py:763] (6/8) Epoch 14, batch 850, loss[loss=0.1664, simple_loss=0.2609, pruned_loss=0.03591, over 7143.00 frames.], tot_loss[loss=0.181, simple_loss=0.2772, pruned_loss=0.04243, over 1401835.40 frames.], batch size: 17, lr: 5.21e-04
+2022-04-29 06:58:46,055 INFO [train.py:763] (6/8) Epoch 14, batch 900, loss[loss=0.2045, simple_loss=0.298, pruned_loss=0.05552, over 7261.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2772, pruned_loss=0.04263, over 1397080.96 frames.], batch size: 19, lr: 5.21e-04
+2022-04-29 06:59:51,294 INFO [train.py:763] (6/8) Epoch 14, batch 950, loss[loss=0.1712, simple_loss=0.2712, pruned_loss=0.03558, over 7335.00 frames.], tot_loss[loss=0.1818, simple_loss=0.278, pruned_loss=0.04275, over 1406002.73 frames.], batch size: 22, lr: 5.21e-04
+2022-04-29 07:00:56,958 INFO [train.py:763] (6/8) Epoch 14, batch 1000, loss[loss=0.2319, simple_loss=0.3122, pruned_loss=0.07583, over 7008.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2786, pruned_loss=0.04323, over 1407585.67 frames.], batch size: 28, lr: 5.21e-04
+2022-04-29 07:02:02,198 INFO [train.py:763] (6/8) Epoch 14, batch 1050, loss[loss=0.148, simple_loss=0.2478, pruned_loss=0.02407, over 7276.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2774, pruned_loss=0.04264, over 1413550.09 frames.], batch size: 18, lr: 5.20e-04
+2022-04-29 07:03:07,570 INFO [train.py:763] (6/8) Epoch 14, batch 1100, loss[loss=0.1731, simple_loss=0.2556, pruned_loss=0.04527, over 7288.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2782, pruned_loss=0.0431, over 1418389.73 frames.], batch size: 17, lr: 5.20e-04
+2022-04-29 07:04:13,189 INFO [train.py:763] (6/8) Epoch 14, batch 1150, loss[loss=0.1853, simple_loss=0.2834, pruned_loss=0.04358, over 7420.00 frames.], tot_loss[loss=0.181, simple_loss=0.2768, pruned_loss=0.04257, over 1422820.00 frames.], batch size: 21, lr: 5.20e-04
+2022-04-29 07:05:18,949 INFO [train.py:763] (6/8) Epoch 14, batch 1200, loss[loss=0.1783, simple_loss=0.2725, pruned_loss=0.04203, over 7427.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2771, pruned_loss=0.04285, over 1424068.77 frames.], batch size: 20, lr: 5.20e-04
+2022-04-29 07:06:24,247 INFO [train.py:763] (6/8) Epoch 14, batch 1250, loss[loss=0.1626, simple_loss=0.2628, pruned_loss=0.03116, over 7356.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2774, pruned_loss=0.0426, over 1427479.67 frames.], batch size: 19, lr: 5.20e-04
+2022-04-29 07:07:29,934 INFO [train.py:763] (6/8) Epoch 14, batch 1300, loss[loss=0.1969, simple_loss=0.2955, pruned_loss=0.04921, over 6431.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2772, pruned_loss=0.04255, over 1420385.00 frames.], batch size: 38, lr: 5.19e-04
+2022-04-29 07:08:35,855 INFO [train.py:763] (6/8) Epoch 14, batch 1350, loss[loss=0.1675, simple_loss=0.2632, pruned_loss=0.03589, over 6999.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2775, pruned_loss=0.04281, over 1421611.87 frames.], batch size: 16, lr: 5.19e-04
+2022-04-29 07:09:40,888 INFO [train.py:763] (6/8) Epoch 14, batch 1400, loss[loss=0.1855, simple_loss=0.2821, pruned_loss=0.04449, over 7293.00 frames.], tot_loss[loss=0.1806, simple_loss=0.276, pruned_loss=0.04257, over 1421106.92 frames.], batch size: 24, lr: 5.19e-04
+2022-04-29 07:10:46,114 INFO [train.py:763] (6/8) Epoch 14, batch 1450, loss[loss=0.1946, simple_loss=0.3003, pruned_loss=0.04445, over 7392.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2764, pruned_loss=0.04274, over 1418829.70 frames.], batch size: 23, lr: 5.19e-04
+2022-04-29 07:11:52,457 INFO [train.py:763] (6/8) Epoch 14, batch 1500, loss[loss=0.1703, simple_loss=0.2707, pruned_loss=0.03497, over 7144.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2772, pruned_loss=0.04304, over 1412852.87 frames.], batch size: 20, lr: 5.19e-04
+2022-04-29 07:12:59,677 INFO [train.py:763] (6/8) Epoch 14, batch 1550, loss[loss=0.198, simple_loss=0.2968, pruned_loss=0.04964, over 7109.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2769, pruned_loss=0.04285, over 1417129.15 frames.], batch size: 21, lr: 5.18e-04
+2022-04-29 07:14:06,937 INFO [train.py:763] (6/8) Epoch 14, batch 1600, loss[loss=0.2186, simple_loss=0.3138, pruned_loss=0.06175, over 7415.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2766, pruned_loss=0.04244, over 1419295.04 frames.], batch size: 21, lr: 5.18e-04
+2022-04-29 07:15:13,440 INFO [train.py:763] (6/8) Epoch 14, batch 1650, loss[loss=0.1953, simple_loss=0.2962, pruned_loss=0.04724, over 7225.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2763, pruned_loss=0.04245, over 1424376.22 frames.], batch size: 23, lr: 5.18e-04
+2022-04-29 07:16:19,627 INFO [train.py:763] (6/8) Epoch 14, batch 1700, loss[loss=0.1832, simple_loss=0.2847, pruned_loss=0.04085, over 7294.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2754, pruned_loss=0.042, over 1428006.32 frames.], batch size: 25, lr: 5.18e-04
+2022-04-29 07:17:25,762 INFO [train.py:763] (6/8) Epoch 14, batch 1750, loss[loss=0.1828, simple_loss=0.2884, pruned_loss=0.03857, over 7094.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2762, pruned_loss=0.04235, over 1431316.99 frames.], batch size: 28, lr: 5.18e-04
+2022-04-29 07:18:30,998 INFO [train.py:763] (6/8) Epoch 14, batch 1800, loss[loss=0.163, simple_loss=0.2501, pruned_loss=0.03798, over 7289.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2763, pruned_loss=0.0423, over 1428174.62 frames.], batch size: 17, lr: 5.17e-04
+2022-04-29 07:19:36,653 INFO [train.py:763] (6/8) Epoch 14, batch 1850, loss[loss=0.1481, simple_loss=0.2465, pruned_loss=0.02483, over 7159.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2763, pruned_loss=0.04236, over 1432324.10 frames.], batch size: 18, lr: 5.17e-04
+2022-04-29 07:20:42,277 INFO [train.py:763] (6/8) Epoch 14, batch 1900, loss[loss=0.1694, simple_loss=0.2759, pruned_loss=0.03152, over 7113.00 frames.], tot_loss[loss=0.181, simple_loss=0.2766, pruned_loss=0.04268, over 1431949.39 frames.], batch size: 21, lr: 5.17e-04
+2022-04-29 07:21:47,863 INFO [train.py:763] (6/8) Epoch 14, batch 1950, loss[loss=0.2175, simple_loss=0.3172, pruned_loss=0.05885, over 7263.00 frames.], tot_loss[loss=0.181, simple_loss=0.2765, pruned_loss=0.04268, over 1432105.76 frames.], batch size: 18, lr: 5.17e-04
+2022-04-29 07:22:53,275 INFO [train.py:763] (6/8) Epoch 14, batch 2000, loss[loss=0.2036, simple_loss=0.3042, pruned_loss=0.05146, over 6438.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2761, pruned_loss=0.04255, over 1428176.57 frames.], batch size: 38, lr: 5.17e-04
+2022-04-29 07:23:58,402 INFO [train.py:763] (6/8) Epoch 14, batch 2050, loss[loss=0.1872, simple_loss=0.2945, pruned_loss=0.04001, over 7323.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2762, pruned_loss=0.04266, over 1429502.15 frames.], batch size: 25, lr: 5.16e-04
+2022-04-29 07:25:03,742 INFO [train.py:763] (6/8) Epoch 14, batch 2100, loss[loss=0.1451, simple_loss=0.239, pruned_loss=0.02557, over 7413.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2759, pruned_loss=0.04286, over 1424219.93 frames.], batch size: 18, lr: 5.16e-04
+2022-04-29 07:26:09,020 INFO [train.py:763] (6/8) Epoch 14, batch 2150, loss[loss=0.1961, simple_loss=0.3001, pruned_loss=0.04601, over 7181.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2756, pruned_loss=0.04237, over 1421480.04 frames.], batch size: 22, lr: 5.16e-04
+2022-04-29 07:27:14,558 INFO [train.py:763] (6/8) Epoch 14, batch 2200, loss[loss=0.1923, simple_loss=0.2906, pruned_loss=0.04704, over 7420.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2769, pruned_loss=0.04287, over 1420932.55 frames.], batch size: 20, lr: 5.16e-04
+2022-04-29 07:28:19,752 INFO [train.py:763] (6/8) Epoch 14, batch 2250, loss[loss=0.1775, simple_loss=0.2968, pruned_loss=0.0291, over 7056.00 frames.], tot_loss[loss=0.181, simple_loss=0.2768, pruned_loss=0.04262, over 1421201.40 frames.], batch size: 28, lr: 5.16e-04
+2022-04-29 07:29:24,986 INFO [train.py:763] (6/8) Epoch 14, batch 2300, loss[loss=0.1764, simple_loss=0.2608, pruned_loss=0.04596, over 6831.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2772, pruned_loss=0.04259, over 1420980.80 frames.], batch size: 15, lr: 5.15e-04
+2022-04-29 07:30:30,168 INFO [train.py:763] (6/8) Epoch 14, batch 2350, loss[loss=0.1778, simple_loss=0.2591, pruned_loss=0.04832, over 7410.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2765, pruned_loss=0.0422, over 1423980.83 frames.], batch size: 18, lr: 5.15e-04
+2022-04-29 07:31:35,493 INFO [train.py:763] (6/8) Epoch 14, batch 2400, loss[loss=0.1445, simple_loss=0.249, pruned_loss=0.02002, over 7398.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2776, pruned_loss=0.04274, over 1422084.91 frames.], batch size: 18, lr: 5.15e-04
+2022-04-29 07:32:40,931 INFO [train.py:763] (6/8) Epoch 14, batch 2450, loss[loss=0.1754, simple_loss=0.2779, pruned_loss=0.03644, over 7409.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2774, pruned_loss=0.04254, over 1423682.51 frames.], batch size: 21, lr: 5.15e-04
+2022-04-29 07:33:46,241 INFO [train.py:763] (6/8) Epoch 14, batch 2500, loss[loss=0.1825, simple_loss=0.2982, pruned_loss=0.03342, over 7324.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2789, pruned_loss=0.04339, over 1425413.57 frames.], batch size: 21, lr: 5.15e-04
+2022-04-29 07:34:51,432 INFO [train.py:763] (6/8) Epoch 14, batch 2550, loss[loss=0.1652, simple_loss=0.2673, pruned_loss=0.03157, over 7165.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2786, pruned_loss=0.04358, over 1427557.20 frames.], batch size: 18, lr: 5.14e-04
+2022-04-29 07:35:56,548 INFO [train.py:763] (6/8) Epoch 14, batch 2600, loss[loss=0.193, simple_loss=0.2981, pruned_loss=0.04392, over 7199.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2794, pruned_loss=0.04379, over 1421011.35 frames.], batch size: 23, lr: 5.14e-04
+2022-04-29 07:37:01,621 INFO [train.py:763] (6/8) Epoch 14, batch 2650, loss[loss=0.2061, simple_loss=0.2901, pruned_loss=0.06109, over 7293.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2782, pruned_loss=0.0431, over 1421923.59 frames.], batch size: 25, lr: 5.14e-04
+2022-04-29 07:38:06,936 INFO [train.py:763] (6/8) Epoch 14, batch 2700, loss[loss=0.1993, simple_loss=0.302, pruned_loss=0.04828, over 7315.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2787, pruned_loss=0.04299, over 1424005.59 frames.], batch size: 21, lr: 5.14e-04
+2022-04-29 07:39:12,134 INFO [train.py:763] (6/8) Epoch 14, batch 2750, loss[loss=0.1826, simple_loss=0.2774, pruned_loss=0.04392, over 7287.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2788, pruned_loss=0.04307, over 1424822.52 frames.], batch size: 24, lr: 5.14e-04
+2022-04-29 07:40:17,444 INFO [train.py:763] (6/8) Epoch 14, batch 2800, loss[loss=0.192, simple_loss=0.2844, pruned_loss=0.04978, over 7148.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2783, pruned_loss=0.04308, over 1427959.29 frames.], batch size: 20, lr: 5.14e-04
+2022-04-29 07:41:22,762 INFO [train.py:763] (6/8) Epoch 14, batch 2850, loss[loss=0.1664, simple_loss=0.2609, pruned_loss=0.03596, over 6786.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2784, pruned_loss=0.04298, over 1428246.28 frames.], batch size: 15, lr: 5.13e-04
+2022-04-29 07:42:28,526 INFO [train.py:763] (6/8) Epoch 14, batch 2900, loss[loss=0.1835, simple_loss=0.2826, pruned_loss=0.0422, over 7387.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2781, pruned_loss=0.04331, over 1423292.59 frames.], batch size: 23, lr: 5.13e-04
+2022-04-29 07:43:34,056 INFO [train.py:763] (6/8) Epoch 14, batch 2950, loss[loss=0.1644, simple_loss=0.2523, pruned_loss=0.03831, over 7432.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2779, pruned_loss=0.04326, over 1424239.27 frames.], batch size: 20, lr: 5.13e-04
+2022-04-29 07:44:39,582 INFO [train.py:763] (6/8) Epoch 14, batch 3000, loss[loss=0.1878, simple_loss=0.292, pruned_loss=0.04185, over 7157.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2774, pruned_loss=0.04315, over 1422596.13 frames.], batch size: 19, lr: 5.13e-04
+2022-04-29 07:44:39,583 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 07:44:54,980 INFO [train.py:792] (6/8) Epoch 14, validation: loss=0.1687, simple_loss=0.2708, pruned_loss=0.03331, over 698248.00 frames.
+2022-04-29 07:46:00,331 INFO [train.py:763] (6/8) Epoch 14, batch 3050, loss[loss=0.1846, simple_loss=0.2698, pruned_loss=0.04967, over 6756.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2783, pruned_loss=0.04334, over 1425823.26 frames.], batch size: 15, lr: 5.13e-04
+2022-04-29 07:47:05,876 INFO [train.py:763] (6/8) Epoch 14, batch 3100, loss[loss=0.1628, simple_loss=0.2699, pruned_loss=0.02783, over 7325.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2794, pruned_loss=0.04391, over 1421349.83 frames.], batch size: 20, lr: 5.12e-04
+2022-04-29 07:48:12,214 INFO [train.py:763] (6/8) Epoch 14, batch 3150, loss[loss=0.1506, simple_loss=0.248, pruned_loss=0.02661, over 7275.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2788, pruned_loss=0.04322, over 1426671.78 frames.], batch size: 17, lr: 5.12e-04
+2022-04-29 07:49:18,810 INFO [train.py:763] (6/8) Epoch 14, batch 3200, loss[loss=0.1885, simple_loss=0.2963, pruned_loss=0.04031, over 7074.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2784, pruned_loss=0.04337, over 1426956.26 frames.], batch size: 28, lr: 5.12e-04
+2022-04-29 07:50:24,261 INFO [train.py:763] (6/8) Epoch 14, batch 3250, loss[loss=0.2181, simple_loss=0.3039, pruned_loss=0.06619, over 7075.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2777, pruned_loss=0.04303, over 1427455.82 frames.], batch size: 18, lr: 5.12e-04
+2022-04-29 07:51:29,740 INFO [train.py:763] (6/8) Epoch 14, batch 3300, loss[loss=0.1702, simple_loss=0.2477, pruned_loss=0.04632, over 7281.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2772, pruned_loss=0.04284, over 1426804.05 frames.], batch size: 17, lr: 5.12e-04
+2022-04-29 07:52:35,058 INFO [train.py:763] (6/8) Epoch 14, batch 3350, loss[loss=0.191, simple_loss=0.3036, pruned_loss=0.03922, over 7208.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2776, pruned_loss=0.04292, over 1426774.78 frames.], batch size: 23, lr: 5.11e-04
+2022-04-29 07:53:40,779 INFO [train.py:763] (6/8) Epoch 14, batch 3400, loss[loss=0.1585, simple_loss=0.2606, pruned_loss=0.02822, over 7219.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2781, pruned_loss=0.04288, over 1423823.19 frames.], batch size: 21, lr: 5.11e-04
+2022-04-29 07:54:45,992 INFO [train.py:763] (6/8) Epoch 14, batch 3450, loss[loss=0.1813, simple_loss=0.2796, pruned_loss=0.04151, over 7055.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2788, pruned_loss=0.04329, over 1420874.57 frames.], batch size: 28, lr: 5.11e-04
+2022-04-29 07:55:51,603 INFO [train.py:763] (6/8) Epoch 14, batch 3500, loss[loss=0.2143, simple_loss=0.3109, pruned_loss=0.05885, over 7132.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2782, pruned_loss=0.04295, over 1426112.88 frames.], batch size: 26, lr: 5.11e-04
+2022-04-29 07:56:57,023 INFO [train.py:763] (6/8) Epoch 14, batch 3550, loss[loss=0.1717, simple_loss=0.2743, pruned_loss=0.03456, over 7231.00 frames.], tot_loss[loss=0.1829, simple_loss=0.279, pruned_loss=0.04342, over 1427427.43 frames.], batch size: 20, lr: 5.11e-04
+2022-04-29 07:58:03,510 INFO [train.py:763] (6/8) Epoch 14, batch 3600, loss[loss=0.2262, simple_loss=0.3111, pruned_loss=0.0707, over 7333.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2785, pruned_loss=0.04363, over 1423457.47 frames.], batch size: 21, lr: 5.11e-04
+2022-04-29 07:59:08,918 INFO [train.py:763] (6/8) Epoch 14, batch 3650, loss[loss=0.2071, simple_loss=0.2978, pruned_loss=0.05823, over 7256.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2784, pruned_loss=0.04303, over 1423948.02 frames.], batch size: 19, lr: 5.10e-04
+2022-04-29 08:00:14,236 INFO [train.py:763] (6/8) Epoch 14, batch 3700, loss[loss=0.1816, simple_loss=0.2721, pruned_loss=0.0456, over 7438.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2788, pruned_loss=0.04334, over 1421014.17 frames.], batch size: 20, lr: 5.10e-04
+2022-04-29 08:01:19,995 INFO [train.py:763] (6/8) Epoch 14, batch 3750, loss[loss=0.2062, simple_loss=0.3061, pruned_loss=0.05319, over 5046.00 frames.], tot_loss[loss=0.1823, simple_loss=0.278, pruned_loss=0.0433, over 1422863.97 frames.], batch size: 52, lr: 5.10e-04
+2022-04-29 08:02:27,064 INFO [train.py:763] (6/8) Epoch 14, batch 3800, loss[loss=0.1677, simple_loss=0.252, pruned_loss=0.04175, over 7061.00 frames.], tot_loss[loss=0.183, simple_loss=0.2787, pruned_loss=0.04367, over 1425471.62 frames.], batch size: 18, lr: 5.10e-04
+2022-04-29 08:03:33,861 INFO [train.py:763] (6/8) Epoch 14, batch 3850, loss[loss=0.1548, simple_loss=0.2536, pruned_loss=0.02798, over 7241.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2786, pruned_loss=0.04308, over 1427954.70 frames.], batch size: 20, lr: 5.10e-04
+2022-04-29 08:04:40,266 INFO [train.py:763] (6/8) Epoch 14, batch 3900, loss[loss=0.1541, simple_loss=0.2526, pruned_loss=0.02777, over 7249.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2777, pruned_loss=0.04238, over 1426578.19 frames.], batch size: 19, lr: 5.09e-04
+2022-04-29 08:05:46,539 INFO [train.py:763] (6/8) Epoch 14, batch 3950, loss[loss=0.1778, simple_loss=0.2732, pruned_loss=0.04114, over 7348.00 frames.], tot_loss[loss=0.181, simple_loss=0.2771, pruned_loss=0.04247, over 1422231.73 frames.], batch size: 19, lr: 5.09e-04
+2022-04-29 08:06:52,812 INFO [train.py:763] (6/8) Epoch 14, batch 4000, loss[loss=0.1871, simple_loss=0.2898, pruned_loss=0.04222, over 7216.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2768, pruned_loss=0.0421, over 1423041.57 frames.], batch size: 21, lr: 5.09e-04
+2022-04-29 08:07:57,994 INFO [train.py:763] (6/8) Epoch 14, batch 4050, loss[loss=0.1712, simple_loss=0.2698, pruned_loss=0.03633, over 7226.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2774, pruned_loss=0.04213, over 1427232.62 frames.], batch size: 21, lr: 5.09e-04
+2022-04-29 08:09:03,253 INFO [train.py:763] (6/8) Epoch 14, batch 4100, loss[loss=0.1839, simple_loss=0.2883, pruned_loss=0.03974, over 7208.00 frames.], tot_loss[loss=0.181, simple_loss=0.2773, pruned_loss=0.04236, over 1419584.03 frames.], batch size: 23, lr: 5.09e-04
+2022-04-29 08:10:08,499 INFO [train.py:763] (6/8) Epoch 14, batch 4150, loss[loss=0.209, simple_loss=0.3058, pruned_loss=0.05616, over 5132.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2779, pruned_loss=0.04295, over 1413189.81 frames.], batch size: 52, lr: 5.08e-04
+2022-04-29 08:11:13,733 INFO [train.py:763] (6/8) Epoch 14, batch 4200, loss[loss=0.1981, simple_loss=0.2966, pruned_loss=0.04981, over 7229.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2771, pruned_loss=0.04286, over 1411665.14 frames.], batch size: 20, lr: 5.08e-04
+2022-04-29 08:12:19,795 INFO [train.py:763] (6/8) Epoch 14, batch 4250, loss[loss=0.1659, simple_loss=0.2548, pruned_loss=0.03853, over 7069.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2769, pruned_loss=0.0429, over 1409634.59 frames.], batch size: 18, lr: 5.08e-04
+2022-04-29 08:13:25,929 INFO [train.py:763] (6/8) Epoch 14, batch 4300, loss[loss=0.1709, simple_loss=0.2584, pruned_loss=0.04171, over 6795.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2771, pruned_loss=0.04296, over 1404841.98 frames.], batch size: 15, lr: 5.08e-04
+2022-04-29 08:14:30,947 INFO [train.py:763] (6/8) Epoch 14, batch 4350, loss[loss=0.1719, simple_loss=0.2724, pruned_loss=0.0357, over 7317.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2774, pruned_loss=0.04321, over 1407994.23 frames.], batch size: 21, lr: 5.08e-04
+2022-04-29 08:15:37,008 INFO [train.py:763] (6/8) Epoch 14, batch 4400, loss[loss=0.1722, simple_loss=0.2748, pruned_loss=0.03482, over 7140.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2765, pruned_loss=0.0426, over 1410708.52 frames.], batch size: 19, lr: 5.08e-04
+2022-04-29 08:16:42,730 INFO [train.py:763] (6/8) Epoch 14, batch 4450, loss[loss=0.1561, simple_loss=0.2487, pruned_loss=0.03174, over 7170.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2746, pruned_loss=0.04216, over 1403396.05 frames.], batch size: 18, lr: 5.07e-04
+2022-04-29 08:17:47,612 INFO [train.py:763] (6/8) Epoch 14, batch 4500, loss[loss=0.1712, simple_loss=0.2662, pruned_loss=0.03812, over 7070.00 frames.], tot_loss[loss=0.1809, simple_loss=0.276, pruned_loss=0.04293, over 1394572.51 frames.], batch size: 18, lr: 5.07e-04
+2022-04-29 08:18:51,945 INFO [train.py:763] (6/8) Epoch 14, batch 4550, loss[loss=0.22, simple_loss=0.305, pruned_loss=0.06753, over 5317.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2769, pruned_loss=0.04365, over 1366856.68 frames.], batch size: 52, lr: 5.07e-04
+2022-04-29 08:20:20,834 INFO [train.py:763] (6/8) Epoch 15, batch 0, loss[loss=0.1831, simple_loss=0.2881, pruned_loss=0.0391, over 7291.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2881, pruned_loss=0.0391, over 7291.00 frames.], batch size: 24, lr: 4.92e-04
+2022-04-29 08:21:27,547 INFO [train.py:763] (6/8) Epoch 15, batch 50, loss[loss=0.1651, simple_loss=0.2602, pruned_loss=0.03495, over 7408.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2762, pruned_loss=0.04139, over 320856.68 frames.], batch size: 18, lr: 4.92e-04
+2022-04-29 08:22:33,715 INFO [train.py:763] (6/8) Epoch 15, batch 100, loss[loss=0.1823, simple_loss=0.2794, pruned_loss=0.04266, over 7337.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2744, pruned_loss=0.04048, over 564200.18 frames.], batch size: 20, lr: 4.92e-04
+2022-04-29 08:23:40,400 INFO [train.py:763] (6/8) Epoch 15, batch 150, loss[loss=0.1813, simple_loss=0.2854, pruned_loss=0.03856, over 7145.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2756, pruned_loss=0.04142, over 754263.57 frames.], batch size: 20, lr: 4.92e-04
+2022-04-29 08:24:46,768 INFO [train.py:763] (6/8) Epoch 15, batch 200, loss[loss=0.1841, simple_loss=0.2849, pruned_loss=0.04162, over 7116.00 frames.], tot_loss[loss=0.1802, simple_loss=0.276, pruned_loss=0.04215, over 897302.42 frames.], batch size: 21, lr: 4.91e-04
+2022-04-29 08:25:52,228 INFO [train.py:763] (6/8) Epoch 15, batch 250, loss[loss=0.1938, simple_loss=0.2891, pruned_loss=0.04925, over 7158.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2763, pruned_loss=0.0421, over 1014092.58 frames.], batch size: 19, lr: 4.91e-04
+2022-04-29 08:26:57,840 INFO [train.py:763] (6/8) Epoch 15, batch 300, loss[loss=0.2135, simple_loss=0.3047, pruned_loss=0.06111, over 7167.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2756, pruned_loss=0.04184, over 1108818.77 frames.], batch size: 19, lr: 4.91e-04
+2022-04-29 08:28:03,218 INFO [train.py:763] (6/8) Epoch 15, batch 350, loss[loss=0.1861, simple_loss=0.2586, pruned_loss=0.05682, over 7287.00 frames.], tot_loss[loss=0.1803, simple_loss=0.276, pruned_loss=0.04233, over 1180107.90 frames.], batch size: 18, lr: 4.91e-04
+2022-04-29 08:29:08,691 INFO [train.py:763] (6/8) Epoch 15, batch 400, loss[loss=0.1694, simple_loss=0.2639, pruned_loss=0.03742, over 7268.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2765, pruned_loss=0.04236, over 1234930.70 frames.], batch size: 19, lr: 4.91e-04
+2022-04-29 08:30:14,240 INFO [train.py:763] (6/8) Epoch 15, batch 450, loss[loss=0.1682, simple_loss=0.2653, pruned_loss=0.03559, over 7427.00 frames.], tot_loss[loss=0.181, simple_loss=0.2774, pruned_loss=0.04232, over 1281657.37 frames.], batch size: 20, lr: 4.91e-04
+2022-04-29 08:31:19,821 INFO [train.py:763] (6/8) Epoch 15, batch 500, loss[loss=0.1781, simple_loss=0.2811, pruned_loss=0.03756, over 7208.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2782, pruned_loss=0.04259, over 1318329.41 frames.], batch size: 23, lr: 4.90e-04
+2022-04-29 08:32:25,946 INFO [train.py:763] (6/8) Epoch 15, batch 550, loss[loss=0.1409, simple_loss=0.2446, pruned_loss=0.01857, over 7271.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2762, pruned_loss=0.04163, over 1345518.27 frames.], batch size: 18, lr: 4.90e-04
+2022-04-29 08:33:31,110 INFO [train.py:763] (6/8) Epoch 15, batch 600, loss[loss=0.1675, simple_loss=0.2598, pruned_loss=0.03763, over 7158.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2751, pruned_loss=0.04104, over 1361494.52 frames.], batch size: 19, lr: 4.90e-04
+2022-04-29 08:34:36,400 INFO [train.py:763] (6/8) Epoch 15, batch 650, loss[loss=0.2044, simple_loss=0.3019, pruned_loss=0.05349, over 6316.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2758, pruned_loss=0.04122, over 1373480.50 frames.], batch size: 37, lr: 4.90e-04
+2022-04-29 08:35:42,060 INFO [train.py:763] (6/8) Epoch 15, batch 700, loss[loss=0.1598, simple_loss=0.2748, pruned_loss=0.02243, over 7090.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2749, pruned_loss=0.04075, over 1386140.06 frames.], batch size: 28, lr: 4.90e-04
+2022-04-29 08:36:47,194 INFO [train.py:763] (6/8) Epoch 15, batch 750, loss[loss=0.1583, simple_loss=0.2532, pruned_loss=0.03168, over 7162.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2747, pruned_loss=0.04069, over 1396060.58 frames.], batch size: 19, lr: 4.89e-04
+2022-04-29 08:37:53,215 INFO [train.py:763] (6/8) Epoch 15, batch 800, loss[loss=0.164, simple_loss=0.2624, pruned_loss=0.03278, over 7267.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2749, pruned_loss=0.04078, over 1403464.91 frames.], batch size: 19, lr: 4.89e-04
+2022-04-29 08:39:00,105 INFO [train.py:763] (6/8) Epoch 15, batch 850, loss[loss=0.1659, simple_loss=0.2737, pruned_loss=0.02904, over 7145.00 frames.], tot_loss[loss=0.178, simple_loss=0.2751, pruned_loss=0.04044, over 1405631.77 frames.], batch size: 20, lr: 4.89e-04
+2022-04-29 08:40:05,804 INFO [train.py:763] (6/8) Epoch 15, batch 900, loss[loss=0.168, simple_loss=0.2565, pruned_loss=0.03979, over 7352.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2751, pruned_loss=0.04068, over 1404283.82 frames.], batch size: 19, lr: 4.89e-04
+2022-04-29 08:41:11,040 INFO [train.py:763] (6/8) Epoch 15, batch 950, loss[loss=0.2024, simple_loss=0.2788, pruned_loss=0.06299, over 7434.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2744, pruned_loss=0.04091, over 1407689.46 frames.], batch size: 20, lr: 4.89e-04
+2022-04-29 08:42:16,443 INFO [train.py:763] (6/8) Epoch 15, batch 1000, loss[loss=0.1918, simple_loss=0.2949, pruned_loss=0.04435, over 7306.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2742, pruned_loss=0.04079, over 1412945.95 frames.], batch size: 25, lr: 4.89e-04
+2022-04-29 08:43:21,671 INFO [train.py:763] (6/8) Epoch 15, batch 1050, loss[loss=0.1564, simple_loss=0.2615, pruned_loss=0.0256, over 7334.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2751, pruned_loss=0.04101, over 1417895.72 frames.], batch size: 20, lr: 4.88e-04
+2022-04-29 08:44:28,814 INFO [train.py:763] (6/8) Epoch 15, batch 1100, loss[loss=0.1849, simple_loss=0.2729, pruned_loss=0.04844, over 7355.00 frames.], tot_loss[loss=0.1787, simple_loss=0.275, pruned_loss=0.04124, over 1420968.43 frames.], batch size: 19, lr: 4.88e-04
+2022-04-29 08:45:35,101 INFO [train.py:763] (6/8) Epoch 15, batch 1150, loss[loss=0.2148, simple_loss=0.307, pruned_loss=0.06128, over 5129.00 frames.], tot_loss[loss=0.178, simple_loss=0.2741, pruned_loss=0.04095, over 1422203.14 frames.], batch size: 52, lr: 4.88e-04
+2022-04-29 08:46:40,374 INFO [train.py:763] (6/8) Epoch 15, batch 1200, loss[loss=0.1742, simple_loss=0.2723, pruned_loss=0.03802, over 7103.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2741, pruned_loss=0.04106, over 1419029.98 frames.], batch size: 21, lr: 4.88e-04
+2022-04-29 08:47:45,861 INFO [train.py:763] (6/8) Epoch 15, batch 1250, loss[loss=0.1539, simple_loss=0.2371, pruned_loss=0.03534, over 6783.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2738, pruned_loss=0.04123, over 1420145.46 frames.], batch size: 15, lr: 4.88e-04
+2022-04-29 08:48:51,150 INFO [train.py:763] (6/8) Epoch 15, batch 1300, loss[loss=0.1713, simple_loss=0.2829, pruned_loss=0.02988, over 7214.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2749, pruned_loss=0.04113, over 1425963.85 frames.], batch size: 22, lr: 4.88e-04
+2022-04-29 08:49:56,771 INFO [train.py:763] (6/8) Epoch 15, batch 1350, loss[loss=0.1732, simple_loss=0.2652, pruned_loss=0.04061, over 7154.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2755, pruned_loss=0.0416, over 1418299.77 frames.], batch size: 19, lr: 4.87e-04
+2022-04-29 08:51:13,201 INFO [train.py:763] (6/8) Epoch 15, batch 1400, loss[loss=0.1833, simple_loss=0.2815, pruned_loss=0.04253, over 7333.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2759, pruned_loss=0.04181, over 1417094.64 frames.], batch size: 22, lr: 4.87e-04
+2022-04-29 08:52:20,210 INFO [train.py:763] (6/8) Epoch 15, batch 1450, loss[loss=0.2107, simple_loss=0.3126, pruned_loss=0.05438, over 7413.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2755, pruned_loss=0.04157, over 1422762.51 frames.], batch size: 21, lr: 4.87e-04
+2022-04-29 08:53:25,689 INFO [train.py:763] (6/8) Epoch 15, batch 1500, loss[loss=0.1867, simple_loss=0.2834, pruned_loss=0.04501, over 7169.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2766, pruned_loss=0.04216, over 1422535.74 frames.], batch size: 23, lr: 4.87e-04
+2022-04-29 08:54:40,090 INFO [train.py:763] (6/8) Epoch 15, batch 1550, loss[loss=0.1575, simple_loss=0.2457, pruned_loss=0.03464, over 7214.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2765, pruned_loss=0.04171, over 1420856.11 frames.], batch size: 16, lr: 4.87e-04
+2022-04-29 08:56:03,996 INFO [train.py:763] (6/8) Epoch 15, batch 1600, loss[loss=0.1852, simple_loss=0.2699, pruned_loss=0.05025, over 6859.00 frames.], tot_loss[loss=0.1806, simple_loss=0.277, pruned_loss=0.04213, over 1422992.09 frames.], batch size: 15, lr: 4.87e-04
+2022-04-29 08:57:19,956 INFO [train.py:763] (6/8) Epoch 15, batch 1650, loss[loss=0.1666, simple_loss=0.2713, pruned_loss=0.03093, over 7151.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2765, pruned_loss=0.042, over 1424358.54 frames.], batch size: 20, lr: 4.86e-04
+2022-04-29 08:58:25,682 INFO [train.py:763] (6/8) Epoch 15, batch 1700, loss[loss=0.1424, simple_loss=0.2367, pruned_loss=0.02407, over 7407.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2756, pruned_loss=0.04146, over 1424787.82 frames.], batch size: 18, lr: 4.86e-04
+2022-04-29 08:59:40,116 INFO [train.py:763] (6/8) Epoch 15, batch 1750, loss[loss=0.1821, simple_loss=0.2869, pruned_loss=0.03863, over 7380.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2756, pruned_loss=0.04139, over 1424316.98 frames.], batch size: 23, lr: 4.86e-04
+2022-04-29 09:00:47,097 INFO [train.py:763] (6/8) Epoch 15, batch 1800, loss[loss=0.158, simple_loss=0.2465, pruned_loss=0.03478, over 7352.00 frames.], tot_loss[loss=0.179, simple_loss=0.2755, pruned_loss=0.04122, over 1423020.80 frames.], batch size: 19, lr: 4.86e-04
+2022-04-29 09:02:11,305 INFO [train.py:763] (6/8) Epoch 15, batch 1850, loss[loss=0.1769, simple_loss=0.2849, pruned_loss=0.03441, over 7150.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2746, pruned_loss=0.0411, over 1425706.83 frames.], batch size: 20, lr: 4.86e-04
+2022-04-29 09:03:16,749 INFO [train.py:763] (6/8) Epoch 15, batch 1900, loss[loss=0.1937, simple_loss=0.305, pruned_loss=0.0412, over 7295.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2749, pruned_loss=0.04133, over 1429385.36 frames.], batch size: 25, lr: 4.86e-04
+2022-04-29 09:04:23,832 INFO [train.py:763] (6/8) Epoch 15, batch 1950, loss[loss=0.1868, simple_loss=0.2919, pruned_loss=0.04078, over 7198.00 frames.], tot_loss[loss=0.1797, simple_loss=0.276, pruned_loss=0.04167, over 1429981.03 frames.], batch size: 23, lr: 4.85e-04
+2022-04-29 09:05:29,698 INFO [train.py:763] (6/8) Epoch 15, batch 2000, loss[loss=0.2505, simple_loss=0.3241, pruned_loss=0.08842, over 4870.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2769, pruned_loss=0.04211, over 1423211.83 frames.], batch size: 52, lr: 4.85e-04
+2022-04-29 09:06:36,280 INFO [train.py:763] (6/8) Epoch 15, batch 2050, loss[loss=0.165, simple_loss=0.2717, pruned_loss=0.02916, over 6311.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2779, pruned_loss=0.04258, over 1421760.85 frames.], batch size: 37, lr: 4.85e-04
+2022-04-29 09:07:41,965 INFO [train.py:763] (6/8) Epoch 15, batch 2100, loss[loss=0.1648, simple_loss=0.2655, pruned_loss=0.03207, over 7117.00 frames.], tot_loss[loss=0.1803, simple_loss=0.277, pruned_loss=0.0418, over 1422421.84 frames.], batch size: 21, lr: 4.85e-04
+2022-04-29 09:08:48,745 INFO [train.py:763] (6/8) Epoch 15, batch 2150, loss[loss=0.1687, simple_loss=0.2681, pruned_loss=0.03462, over 7258.00 frames.], tot_loss[loss=0.1804, simple_loss=0.277, pruned_loss=0.04192, over 1417414.67 frames.], batch size: 19, lr: 4.85e-04
+2022-04-29 09:09:53,840 INFO [train.py:763] (6/8) Epoch 15, batch 2200, loss[loss=0.1872, simple_loss=0.2941, pruned_loss=0.04015, over 7208.00 frames.], tot_loss[loss=0.1805, simple_loss=0.277, pruned_loss=0.04204, over 1414155.35 frames.], batch size: 22, lr: 4.84e-04
+2022-04-29 09:10:59,457 INFO [train.py:763] (6/8) Epoch 15, batch 2250, loss[loss=0.2038, simple_loss=0.305, pruned_loss=0.05123, over 7415.00 frames.], tot_loss[loss=0.1799, simple_loss=0.276, pruned_loss=0.04187, over 1416039.77 frames.], batch size: 21, lr: 4.84e-04
+2022-04-29 09:12:05,742 INFO [train.py:763] (6/8) Epoch 15, batch 2300, loss[loss=0.1961, simple_loss=0.2923, pruned_loss=0.04994, over 7216.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2756, pruned_loss=0.04163, over 1417967.83 frames.], batch size: 23, lr: 4.84e-04
+2022-04-29 09:13:13,276 INFO [train.py:763] (6/8) Epoch 15, batch 2350, loss[loss=0.1919, simple_loss=0.2877, pruned_loss=0.04803, over 7316.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2756, pruned_loss=0.04163, over 1421124.12 frames.], batch size: 25, lr: 4.84e-04
+2022-04-29 09:14:19,341 INFO [train.py:763] (6/8) Epoch 15, batch 2400, loss[loss=0.2078, simple_loss=0.3041, pruned_loss=0.05572, over 7299.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2763, pruned_loss=0.04208, over 1425148.93 frames.], batch size: 25, lr: 4.84e-04
+2022-04-29 09:15:24,435 INFO [train.py:763] (6/8) Epoch 15, batch 2450, loss[loss=0.1883, simple_loss=0.287, pruned_loss=0.04482, over 6798.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2771, pruned_loss=0.04226, over 1424007.52 frames.], batch size: 31, lr: 4.84e-04
+2022-04-29 09:16:31,204 INFO [train.py:763] (6/8) Epoch 15, batch 2500, loss[loss=0.1599, simple_loss=0.2634, pruned_loss=0.02816, over 7211.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2766, pruned_loss=0.04181, over 1426682.73 frames.], batch size: 21, lr: 4.83e-04
+2022-04-29 09:17:37,402 INFO [train.py:763] (6/8) Epoch 15, batch 2550, loss[loss=0.1649, simple_loss=0.2709, pruned_loss=0.02947, over 7145.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2755, pruned_loss=0.04146, over 1423028.00 frames.], batch size: 20, lr: 4.83e-04
+2022-04-29 09:18:44,540 INFO [train.py:763] (6/8) Epoch 15, batch 2600, loss[loss=0.169, simple_loss=0.2771, pruned_loss=0.03046, over 7355.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2754, pruned_loss=0.04144, over 1421813.58 frames.], batch size: 19, lr: 4.83e-04
+2022-04-29 09:19:51,211 INFO [train.py:763] (6/8) Epoch 15, batch 2650, loss[loss=0.1864, simple_loss=0.2841, pruned_loss=0.04434, over 7387.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2752, pruned_loss=0.04156, over 1422765.90 frames.], batch size: 23, lr: 4.83e-04
+2022-04-29 09:20:56,494 INFO [train.py:763] (6/8) Epoch 15, batch 2700, loss[loss=0.1905, simple_loss=0.2856, pruned_loss=0.04773, over 7182.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2757, pruned_loss=0.04189, over 1418816.03 frames.], batch size: 26, lr: 4.83e-04
+2022-04-29 09:22:02,818 INFO [train.py:763] (6/8) Epoch 15, batch 2750, loss[loss=0.2042, simple_loss=0.2914, pruned_loss=0.05855, over 7279.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2758, pruned_loss=0.0419, over 1423065.51 frames.], batch size: 18, lr: 4.83e-04
+2022-04-29 09:23:10,086 INFO [train.py:763] (6/8) Epoch 15, batch 2800, loss[loss=0.1979, simple_loss=0.3068, pruned_loss=0.04455, over 7214.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2762, pruned_loss=0.04165, over 1425209.11 frames.], batch size: 21, lr: 4.82e-04
+2022-04-29 09:24:17,266 INFO [train.py:763] (6/8) Epoch 15, batch 2850, loss[loss=0.1697, simple_loss=0.2652, pruned_loss=0.03709, over 7158.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2763, pruned_loss=0.04149, over 1425038.19 frames.], batch size: 18, lr: 4.82e-04
+2022-04-29 09:25:24,201 INFO [train.py:763] (6/8) Epoch 15, batch 2900, loss[loss=0.1565, simple_loss=0.2495, pruned_loss=0.03176, over 7174.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2756, pruned_loss=0.041, over 1427606.85 frames.], batch size: 18, lr: 4.82e-04
+2022-04-29 09:26:29,783 INFO [train.py:763] (6/8) Epoch 15, batch 2950, loss[loss=0.1831, simple_loss=0.2838, pruned_loss=0.04124, over 7323.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2758, pruned_loss=0.04087, over 1423739.09 frames.], batch size: 22, lr: 4.82e-04
+2022-04-29 09:27:35,049 INFO [train.py:763] (6/8) Epoch 15, batch 3000, loss[loss=0.1519, simple_loss=0.2503, pruned_loss=0.02675, over 7403.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2762, pruned_loss=0.04108, over 1427760.36 frames.], batch size: 21, lr: 4.82e-04
+2022-04-29 09:27:35,050 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 09:27:50,493 INFO [train.py:792] (6/8) Epoch 15, validation: loss=0.1668, simple_loss=0.2684, pruned_loss=0.03254, over 698248.00 frames.
+2022-04-29 09:28:57,622 INFO [train.py:763] (6/8) Epoch 15, batch 3050, loss[loss=0.1593, simple_loss=0.2492, pruned_loss=0.03471, over 7423.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2762, pruned_loss=0.04139, over 1426135.48 frames.], batch size: 18, lr: 4.82e-04
+2022-04-29 09:30:04,541 INFO [train.py:763] (6/8) Epoch 15, batch 3100, loss[loss=0.2099, simple_loss=0.3026, pruned_loss=0.05861, over 7215.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2767, pruned_loss=0.04186, over 1426448.00 frames.], batch size: 23, lr: 4.81e-04
+2022-04-29 09:31:11,567 INFO [train.py:763] (6/8) Epoch 15, batch 3150, loss[loss=0.1596, simple_loss=0.2504, pruned_loss=0.0344, over 7146.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2766, pruned_loss=0.04187, over 1424116.40 frames.], batch size: 18, lr: 4.81e-04
+2022-04-29 09:32:29,195 INFO [train.py:763] (6/8) Epoch 15, batch 3200, loss[loss=0.1696, simple_loss=0.2642, pruned_loss=0.03746, over 7295.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2766, pruned_loss=0.04163, over 1424219.88 frames.], batch size: 24, lr: 4.81e-04
+2022-04-29 09:33:36,695 INFO [train.py:763] (6/8) Epoch 15, batch 3250, loss[loss=0.1988, simple_loss=0.2885, pruned_loss=0.05457, over 7318.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2755, pruned_loss=0.04132, over 1425380.43 frames.], batch size: 21, lr: 4.81e-04
+2022-04-29 09:34:43,460 INFO [train.py:763] (6/8) Epoch 15, batch 3300, loss[loss=0.196, simple_loss=0.2949, pruned_loss=0.04852, over 7308.00 frames.], tot_loss[loss=0.1794, simple_loss=0.276, pruned_loss=0.04145, over 1429112.00 frames.], batch size: 25, lr: 4.81e-04
+2022-04-29 09:35:50,326 INFO [train.py:763] (6/8) Epoch 15, batch 3350, loss[loss=0.1952, simple_loss=0.2958, pruned_loss=0.04725, over 7236.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2767, pruned_loss=0.0418, over 1431455.29 frames.], batch size: 20, lr: 4.81e-04
+2022-04-29 09:36:57,532 INFO [train.py:763] (6/8) Epoch 15, batch 3400, loss[loss=0.2055, simple_loss=0.3007, pruned_loss=0.05513, over 7056.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2768, pruned_loss=0.04211, over 1428683.15 frames.], batch size: 28, lr: 4.80e-04
+2022-04-29 09:38:05,031 INFO [train.py:763] (6/8) Epoch 15, batch 3450, loss[loss=0.1725, simple_loss=0.2643, pruned_loss=0.04031, over 7352.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2761, pruned_loss=0.04184, over 1430377.06 frames.], batch size: 19, lr: 4.80e-04
+2022-04-29 09:39:11,459 INFO [train.py:763] (6/8) Epoch 15, batch 3500, loss[loss=0.1623, simple_loss=0.274, pruned_loss=0.02534, over 7314.00 frames.], tot_loss[loss=0.1797, simple_loss=0.276, pruned_loss=0.04173, over 1429037.25 frames.], batch size: 21, lr: 4.80e-04
+2022-04-29 09:40:16,436 INFO [train.py:763] (6/8) Epoch 15, batch 3550, loss[loss=0.228, simple_loss=0.3264, pruned_loss=0.06474, over 7195.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2769, pruned_loss=0.042, over 1425015.88 frames.], batch size: 26, lr: 4.80e-04
+2022-04-29 09:41:21,621 INFO [train.py:763] (6/8) Epoch 15, batch 3600, loss[loss=0.2238, simple_loss=0.327, pruned_loss=0.06032, over 7317.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2767, pruned_loss=0.04157, over 1426734.83 frames.], batch size: 21, lr: 4.80e-04
+2022-04-29 09:42:26,934 INFO [train.py:763] (6/8) Epoch 15, batch 3650, loss[loss=0.1833, simple_loss=0.265, pruned_loss=0.0508, over 7271.00 frames.], tot_loss[loss=0.18, simple_loss=0.2768, pruned_loss=0.04157, over 1426745.46 frames.], batch size: 18, lr: 4.80e-04
+2022-04-29 09:43:33,157 INFO [train.py:763] (6/8) Epoch 15, batch 3700, loss[loss=0.1583, simple_loss=0.2497, pruned_loss=0.03341, over 6770.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2765, pruned_loss=0.04149, over 1423516.89 frames.], batch size: 15, lr: 4.79e-04
+2022-04-29 09:44:39,841 INFO [train.py:763] (6/8) Epoch 15, batch 3750, loss[loss=0.2021, simple_loss=0.3084, pruned_loss=0.04792, over 7325.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2761, pruned_loss=0.0416, over 1421655.51 frames.], batch size: 25, lr: 4.79e-04
+2022-04-29 09:45:46,801 INFO [train.py:763] (6/8) Epoch 15, batch 3800, loss[loss=0.156, simple_loss=0.254, pruned_loss=0.02906, over 7134.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2762, pruned_loss=0.04181, over 1425458.67 frames.], batch size: 17, lr: 4.79e-04
+2022-04-29 09:46:53,784 INFO [train.py:763] (6/8) Epoch 15, batch 3850, loss[loss=0.1775, simple_loss=0.2621, pruned_loss=0.04645, over 7278.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2763, pruned_loss=0.04237, over 1421729.58 frames.], batch size: 18, lr: 4.79e-04
+2022-04-29 09:48:00,486 INFO [train.py:763] (6/8) Epoch 15, batch 3900, loss[loss=0.1806, simple_loss=0.2819, pruned_loss=0.03961, over 7217.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2764, pruned_loss=0.04227, over 1423261.88 frames.], batch size: 21, lr: 4.79e-04
+2022-04-29 09:49:06,579 INFO [train.py:763] (6/8) Epoch 15, batch 3950, loss[loss=0.1757, simple_loss=0.2737, pruned_loss=0.03884, over 7232.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2768, pruned_loss=0.04256, over 1422523.08 frames.], batch size: 20, lr: 4.79e-04
+2022-04-29 09:50:13,630 INFO [train.py:763] (6/8) Epoch 15, batch 4000, loss[loss=0.1967, simple_loss=0.3018, pruned_loss=0.04584, over 7325.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2775, pruned_loss=0.04254, over 1420140.13 frames.], batch size: 21, lr: 4.79e-04
+2022-04-29 09:51:19,316 INFO [train.py:763] (6/8) Epoch 15, batch 4050, loss[loss=0.1679, simple_loss=0.2623, pruned_loss=0.03678, over 7162.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2769, pruned_loss=0.04244, over 1418433.53 frames.], batch size: 18, lr: 4.78e-04
+2022-04-29 09:52:24,923 INFO [train.py:763] (6/8) Epoch 15, batch 4100, loss[loss=0.1765, simple_loss=0.2689, pruned_loss=0.04201, over 7177.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2756, pruned_loss=0.04186, over 1423458.83 frames.], batch size: 18, lr: 4.78e-04
+2022-04-29 09:53:30,117 INFO [train.py:763] (6/8) Epoch 15, batch 4150, loss[loss=0.1631, simple_loss=0.2581, pruned_loss=0.03409, over 7090.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2758, pruned_loss=0.04197, over 1418657.30 frames.], batch size: 28, lr: 4.78e-04
+2022-04-29 09:54:36,367 INFO [train.py:763] (6/8) Epoch 15, batch 4200, loss[loss=0.1747, simple_loss=0.254, pruned_loss=0.04763, over 7007.00 frames.], tot_loss[loss=0.1792, simple_loss=0.275, pruned_loss=0.04171, over 1417644.95 frames.], batch size: 16, lr: 4.78e-04
+2022-04-29 09:55:43,511 INFO [train.py:763] (6/8) Epoch 15, batch 4250, loss[loss=0.1671, simple_loss=0.2574, pruned_loss=0.03837, over 7168.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2737, pruned_loss=0.04133, over 1416628.41 frames.], batch size: 18, lr: 4.78e-04
+2022-04-29 09:56:48,664 INFO [train.py:763] (6/8) Epoch 15, batch 4300, loss[loss=0.2085, simple_loss=0.3062, pruned_loss=0.05543, over 6666.00 frames.], tot_loss[loss=0.178, simple_loss=0.2736, pruned_loss=0.04121, over 1411955.21 frames.], batch size: 31, lr: 4.78e-04
+2022-04-29 09:57:53,960 INFO [train.py:763] (6/8) Epoch 15, batch 4350, loss[loss=0.191, simple_loss=0.2749, pruned_loss=0.05361, over 7162.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2736, pruned_loss=0.04095, over 1415544.77 frames.], batch size: 18, lr: 4.77e-04
+2022-04-29 09:59:00,610 INFO [train.py:763] (6/8) Epoch 15, batch 4400, loss[loss=0.1616, simple_loss=0.2663, pruned_loss=0.0285, over 7116.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2739, pruned_loss=0.04073, over 1415453.28 frames.], batch size: 21, lr: 4.77e-04
+2022-04-29 10:00:06,759 INFO [train.py:763] (6/8) Epoch 15, batch 4450, loss[loss=0.1927, simple_loss=0.2857, pruned_loss=0.04979, over 7201.00 frames.], tot_loss[loss=0.1777, simple_loss=0.274, pruned_loss=0.04066, over 1410767.46 frames.], batch size: 22, lr: 4.77e-04
+2022-04-29 10:01:11,553 INFO [train.py:763] (6/8) Epoch 15, batch 4500, loss[loss=0.1452, simple_loss=0.2242, pruned_loss=0.03304, over 7146.00 frames.], tot_loss[loss=0.1777, simple_loss=0.274, pruned_loss=0.04068, over 1401652.94 frames.], batch size: 17, lr: 4.77e-04
+2022-04-29 10:02:15,684 INFO [train.py:763] (6/8) Epoch 15, batch 4550, loss[loss=0.2363, simple_loss=0.3159, pruned_loss=0.07835, over 4856.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2777, pruned_loss=0.04343, over 1349149.16 frames.], batch size: 52, lr: 4.77e-04
+2022-04-29 10:03:53,500 INFO [train.py:763] (6/8) Epoch 16, batch 0, loss[loss=0.1772, simple_loss=0.272, pruned_loss=0.04124, over 7445.00 frames.], tot_loss[loss=0.1772, simple_loss=0.272, pruned_loss=0.04124, over 7445.00 frames.], batch size: 22, lr: 4.63e-04
+2022-04-29 10:04:59,094 INFO [train.py:763] (6/8) Epoch 16, batch 50, loss[loss=0.1944, simple_loss=0.2836, pruned_loss=0.05263, over 7324.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2801, pruned_loss=0.04422, over 317602.03 frames.], batch size: 21, lr: 4.63e-04
+2022-04-29 10:06:04,342 INFO [train.py:763] (6/8) Epoch 16, batch 100, loss[loss=0.1833, simple_loss=0.2903, pruned_loss=0.03812, over 7162.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2779, pruned_loss=0.04284, over 559779.17 frames.], batch size: 20, lr: 4.63e-04
+2022-04-29 10:07:09,683 INFO [train.py:763] (6/8) Epoch 16, batch 150, loss[loss=0.148, simple_loss=0.2373, pruned_loss=0.0294, over 7016.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2757, pruned_loss=0.04165, over 747364.48 frames.], batch size: 16, lr: 4.63e-04
+2022-04-29 10:08:15,068 INFO [train.py:763] (6/8) Epoch 16, batch 200, loss[loss=0.1735, simple_loss=0.267, pruned_loss=0.04004, over 7128.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2781, pruned_loss=0.04257, over 896513.07 frames.], batch size: 17, lr: 4.63e-04
+2022-04-29 10:09:20,556 INFO [train.py:763] (6/8) Epoch 16, batch 250, loss[loss=0.1937, simple_loss=0.2864, pruned_loss=0.05053, over 7262.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2777, pruned_loss=0.04196, over 1015773.28 frames.], batch size: 19, lr: 4.63e-04
+2022-04-29 10:10:25,854 INFO [train.py:763] (6/8) Epoch 16, batch 300, loss[loss=0.1885, simple_loss=0.2759, pruned_loss=0.05054, over 7059.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2781, pruned_loss=0.04152, over 1100847.11 frames.], batch size: 18, lr: 4.62e-04
+2022-04-29 10:11:32,066 INFO [train.py:763] (6/8) Epoch 16, batch 350, loss[loss=0.1398, simple_loss=0.2361, pruned_loss=0.02175, over 6785.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2771, pruned_loss=0.04128, over 1171320.78 frames.], batch size: 15, lr: 4.62e-04
+2022-04-29 10:12:37,996 INFO [train.py:763] (6/8) Epoch 16, batch 400, loss[loss=0.1805, simple_loss=0.2741, pruned_loss=0.04348, over 5429.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2769, pruned_loss=0.04098, over 1227972.21 frames.], batch size: 52, lr: 4.62e-04
+2022-04-29 10:13:43,447 INFO [train.py:763] (6/8) Epoch 16, batch 450, loss[loss=0.1891, simple_loss=0.2824, pruned_loss=0.04789, over 7373.00 frames.], tot_loss[loss=0.1795, simple_loss=0.277, pruned_loss=0.04097, over 1268855.83 frames.], batch size: 19, lr: 4.62e-04
+2022-04-29 10:14:49,057 INFO [train.py:763] (6/8) Epoch 16, batch 500, loss[loss=0.1647, simple_loss=0.255, pruned_loss=0.03723, over 7159.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2765, pruned_loss=0.04123, over 1301522.85 frames.], batch size: 18, lr: 4.62e-04
+2022-04-29 10:15:54,721 INFO [train.py:763] (6/8) Epoch 16, batch 550, loss[loss=0.1817, simple_loss=0.2593, pruned_loss=0.05202, over 7134.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2759, pruned_loss=0.04166, over 1326613.05 frames.], batch size: 17, lr: 4.62e-04
+2022-04-29 10:17:00,205 INFO [train.py:763] (6/8) Epoch 16, batch 600, loss[loss=0.1877, simple_loss=0.2772, pruned_loss=0.04911, over 7155.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2762, pruned_loss=0.04205, over 1341427.59 frames.], batch size: 28, lr: 4.62e-04
+2022-04-29 10:18:05,532 INFO [train.py:763] (6/8) Epoch 16, batch 650, loss[loss=0.1815, simple_loss=0.2865, pruned_loss=0.0383, over 7328.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2764, pruned_loss=0.04194, over 1359740.09 frames.], batch size: 20, lr: 4.61e-04
+2022-04-29 10:19:10,731 INFO [train.py:763] (6/8) Epoch 16, batch 700, loss[loss=0.1785, simple_loss=0.2706, pruned_loss=0.04321, over 7258.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2774, pruned_loss=0.04244, over 1366889.56 frames.], batch size: 19, lr: 4.61e-04
+2022-04-29 10:20:16,741 INFO [train.py:763] (6/8) Epoch 16, batch 750, loss[loss=0.1912, simple_loss=0.2912, pruned_loss=0.04556, over 7146.00 frames.], tot_loss[loss=0.181, simple_loss=0.2774, pruned_loss=0.04232, over 1375185.09 frames.], batch size: 20, lr: 4.61e-04
+2022-04-29 10:21:21,859 INFO [train.py:763] (6/8) Epoch 16, batch 800, loss[loss=0.1534, simple_loss=0.2516, pruned_loss=0.02758, over 7163.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2762, pruned_loss=0.04168, over 1386496.13 frames.], batch size: 19, lr: 4.61e-04
+2022-04-29 10:22:27,309 INFO [train.py:763] (6/8) Epoch 16, batch 850, loss[loss=0.1965, simple_loss=0.2926, pruned_loss=0.05019, over 6377.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2753, pruned_loss=0.04178, over 1394404.17 frames.], batch size: 38, lr: 4.61e-04
+2022-04-29 10:23:32,970 INFO [train.py:763] (6/8) Epoch 16, batch 900, loss[loss=0.1716, simple_loss=0.2767, pruned_loss=0.03321, over 7325.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2751, pruned_loss=0.04162, over 1406167.91 frames.], batch size: 20, lr: 4.61e-04
+2022-04-29 10:24:38,492 INFO [train.py:763] (6/8) Epoch 16, batch 950, loss[loss=0.1422, simple_loss=0.227, pruned_loss=0.02872, over 7146.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2754, pruned_loss=0.04112, over 1411270.46 frames.], batch size: 17, lr: 4.60e-04
+2022-04-29 10:25:44,699 INFO [train.py:763] (6/8) Epoch 16, batch 1000, loss[loss=0.1916, simple_loss=0.2888, pruned_loss=0.04716, over 7118.00 frames.], tot_loss[loss=0.179, simple_loss=0.2758, pruned_loss=0.04115, over 1415825.59 frames.], batch size: 21, lr: 4.60e-04
+2022-04-29 10:26:51,177 INFO [train.py:763] (6/8) Epoch 16, batch 1050, loss[loss=0.1763, simple_loss=0.2861, pruned_loss=0.03328, over 7345.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2749, pruned_loss=0.04093, over 1420120.96 frames.], batch size: 22, lr: 4.60e-04
+2022-04-29 10:27:57,455 INFO [train.py:763] (6/8) Epoch 16, batch 1100, loss[loss=0.1794, simple_loss=0.2809, pruned_loss=0.03895, over 7288.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2752, pruned_loss=0.0407, over 1420603.01 frames.], batch size: 24, lr: 4.60e-04
+2022-04-29 10:29:02,474 INFO [train.py:763] (6/8) Epoch 16, batch 1150, loss[loss=0.1892, simple_loss=0.2975, pruned_loss=0.04043, over 7306.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2751, pruned_loss=0.04037, over 1422345.50 frames.], batch size: 24, lr: 4.60e-04
+2022-04-29 10:30:08,053 INFO [train.py:763] (6/8) Epoch 16, batch 1200, loss[loss=0.2417, simple_loss=0.3293, pruned_loss=0.07706, over 7295.00 frames.], tot_loss[loss=0.178, simple_loss=0.275, pruned_loss=0.04044, over 1419958.09 frames.], batch size: 25, lr: 4.60e-04
+2022-04-29 10:31:13,266 INFO [train.py:763] (6/8) Epoch 16, batch 1250, loss[loss=0.1631, simple_loss=0.2548, pruned_loss=0.03573, over 7271.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2752, pruned_loss=0.04095, over 1415113.07 frames.], batch size: 18, lr: 4.60e-04
+2022-04-29 10:32:19,088 INFO [train.py:763] (6/8) Epoch 16, batch 1300, loss[loss=0.1982, simple_loss=0.3061, pruned_loss=0.04514, over 7349.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2751, pruned_loss=0.04069, over 1413679.47 frames.], batch size: 22, lr: 4.59e-04
+2022-04-29 10:33:25,849 INFO [train.py:763] (6/8) Epoch 16, batch 1350, loss[loss=0.1409, simple_loss=0.235, pruned_loss=0.02338, over 7003.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2752, pruned_loss=0.0405, over 1418932.65 frames.], batch size: 16, lr: 4.59e-04
+2022-04-29 10:34:32,889 INFO [train.py:763] (6/8) Epoch 16, batch 1400, loss[loss=0.1856, simple_loss=0.2893, pruned_loss=0.041, over 7143.00 frames.], tot_loss[loss=0.177, simple_loss=0.2738, pruned_loss=0.0401, over 1420430.24 frames.], batch size: 20, lr: 4.59e-04
+2022-04-29 10:35:38,353 INFO [train.py:763] (6/8) Epoch 16, batch 1450, loss[loss=0.1948, simple_loss=0.2969, pruned_loss=0.04629, over 7344.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2741, pruned_loss=0.04027, over 1419125.97 frames.], batch size: 22, lr: 4.59e-04
+2022-04-29 10:36:43,999 INFO [train.py:763] (6/8) Epoch 16, batch 1500, loss[loss=0.142, simple_loss=0.2339, pruned_loss=0.02511, over 7253.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2722, pruned_loss=0.03966, over 1424722.98 frames.], batch size: 19, lr: 4.59e-04
+2022-04-29 10:37:49,279 INFO [train.py:763] (6/8) Epoch 16, batch 1550, loss[loss=0.1687, simple_loss=0.2745, pruned_loss=0.03146, over 7215.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2725, pruned_loss=0.03987, over 1422381.92 frames.], batch size: 21, lr: 4.59e-04
+2022-04-29 10:38:55,270 INFO [train.py:763] (6/8) Epoch 16, batch 1600, loss[loss=0.1651, simple_loss=0.2686, pruned_loss=0.03083, over 7429.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2733, pruned_loss=0.03969, over 1426607.59 frames.], batch size: 20, lr: 4.58e-04
+2022-04-29 10:40:00,455 INFO [train.py:763] (6/8) Epoch 16, batch 1650, loss[loss=0.1628, simple_loss=0.2685, pruned_loss=0.02852, over 7408.00 frames.], tot_loss[loss=0.177, simple_loss=0.2741, pruned_loss=0.03991, over 1429378.52 frames.], batch size: 21, lr: 4.58e-04
+2022-04-29 10:41:05,543 INFO [train.py:763] (6/8) Epoch 16, batch 1700, loss[loss=0.2317, simple_loss=0.3148, pruned_loss=0.07425, over 5428.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2747, pruned_loss=0.04022, over 1423300.00 frames.], batch size: 52, lr: 4.58e-04
+2022-04-29 10:42:10,602 INFO [train.py:763] (6/8) Epoch 16, batch 1750, loss[loss=0.2157, simple_loss=0.3057, pruned_loss=0.06282, over 7391.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2756, pruned_loss=0.04095, over 1415392.04 frames.], batch size: 23, lr: 4.58e-04
+2022-04-29 10:43:15,525 INFO [train.py:763] (6/8) Epoch 16, batch 1800, loss[loss=0.1683, simple_loss=0.274, pruned_loss=0.0313, over 7187.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2756, pruned_loss=0.04057, over 1416090.55 frames.], batch size: 23, lr: 4.58e-04
+2022-04-29 10:44:20,686 INFO [train.py:763] (6/8) Epoch 16, batch 1850, loss[loss=0.1885, simple_loss=0.2857, pruned_loss=0.04562, over 6395.00 frames.], tot_loss[loss=0.1788, simple_loss=0.276, pruned_loss=0.0408, over 1417081.24 frames.], batch size: 38, lr: 4.58e-04
+2022-04-29 10:45:26,188 INFO [train.py:763] (6/8) Epoch 16, batch 1900, loss[loss=0.1821, simple_loss=0.2704, pruned_loss=0.04692, over 7437.00 frames.], tot_loss[loss=0.1791, simple_loss=0.276, pruned_loss=0.04107, over 1420977.54 frames.], batch size: 20, lr: 4.58e-04
+2022-04-29 10:46:31,348 INFO [train.py:763] (6/8) Epoch 16, batch 1950, loss[loss=0.1717, simple_loss=0.2712, pruned_loss=0.03611, over 7318.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2751, pruned_loss=0.0404, over 1422909.92 frames.], batch size: 21, lr: 4.57e-04
+2022-04-29 10:47:36,630 INFO [train.py:763] (6/8) Epoch 16, batch 2000, loss[loss=0.159, simple_loss=0.2599, pruned_loss=0.02903, over 7251.00 frames.], tot_loss[loss=0.1787, simple_loss=0.276, pruned_loss=0.04069, over 1424643.87 frames.], batch size: 19, lr: 4.57e-04
+2022-04-29 10:48:44,157 INFO [train.py:763] (6/8) Epoch 16, batch 2050, loss[loss=0.1678, simple_loss=0.2562, pruned_loss=0.03971, over 7420.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2747, pruned_loss=0.04057, over 1428822.47 frames.], batch size: 18, lr: 4.57e-04
+2022-04-29 10:49:51,121 INFO [train.py:763] (6/8) Epoch 16, batch 2100, loss[loss=0.1606, simple_loss=0.2705, pruned_loss=0.02538, over 7414.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2755, pruned_loss=0.04069, over 1428870.72 frames.], batch size: 21, lr: 4.57e-04
+2022-04-29 10:50:57,995 INFO [train.py:763] (6/8) Epoch 16, batch 2150, loss[loss=0.1783, simple_loss=0.2869, pruned_loss=0.03483, over 7362.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2755, pruned_loss=0.04075, over 1425729.73 frames.], batch size: 19, lr: 4.57e-04
+2022-04-29 10:52:04,710 INFO [train.py:763] (6/8) Epoch 16, batch 2200, loss[loss=0.1451, simple_loss=0.2511, pruned_loss=0.01949, over 7325.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2752, pruned_loss=0.04054, over 1422634.11 frames.], batch size: 22, lr: 4.57e-04
+2022-04-29 10:53:10,676 INFO [train.py:763] (6/8) Epoch 16, batch 2250, loss[loss=0.1684, simple_loss=0.2768, pruned_loss=0.02999, over 7413.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2755, pruned_loss=0.04072, over 1425608.91 frames.], batch size: 21, lr: 4.56e-04
+2022-04-29 10:54:16,235 INFO [train.py:763] (6/8) Epoch 16, batch 2300, loss[loss=0.1848, simple_loss=0.2904, pruned_loss=0.03957, over 7285.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2752, pruned_loss=0.04061, over 1424546.72 frames.], batch size: 24, lr: 4.56e-04
+2022-04-29 10:55:22,550 INFO [train.py:763] (6/8) Epoch 16, batch 2350, loss[loss=0.2072, simple_loss=0.3039, pruned_loss=0.05523, over 7390.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2746, pruned_loss=0.04047, over 1427455.81 frames.], batch size: 23, lr: 4.56e-04
+2022-04-29 10:56:28,626 INFO [train.py:763] (6/8) Epoch 16, batch 2400, loss[loss=0.1601, simple_loss=0.2552, pruned_loss=0.03247, over 6984.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2737, pruned_loss=0.04048, over 1424794.06 frames.], batch size: 16, lr: 4.56e-04
+2022-04-29 10:57:34,946 INFO [train.py:763] (6/8) Epoch 16, batch 2450, loss[loss=0.2126, simple_loss=0.3039, pruned_loss=0.06067, over 7345.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2732, pruned_loss=0.04029, over 1424471.97 frames.], batch size: 22, lr: 4.56e-04
+2022-04-29 10:58:41,532 INFO [train.py:763] (6/8) Epoch 16, batch 2500, loss[loss=0.1876, simple_loss=0.2968, pruned_loss=0.03913, over 7228.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2725, pruned_loss=0.0399, over 1424441.92 frames.], batch size: 21, lr: 4.56e-04
+2022-04-29 10:59:48,423 INFO [train.py:763] (6/8) Epoch 16, batch 2550, loss[loss=0.1829, simple_loss=0.2859, pruned_loss=0.03992, over 7221.00 frames.], tot_loss[loss=0.1756, simple_loss=0.272, pruned_loss=0.03966, over 1419917.45 frames.], batch size: 21, lr: 4.56e-04
+2022-04-29 11:00:54,060 INFO [train.py:763] (6/8) Epoch 16, batch 2600, loss[loss=0.1954, simple_loss=0.291, pruned_loss=0.04994, over 7084.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2735, pruned_loss=0.04001, over 1423383.77 frames.], batch size: 28, lr: 4.55e-04
+2022-04-29 11:01:59,325 INFO [train.py:763] (6/8) Epoch 16, batch 2650, loss[loss=0.1728, simple_loss=0.2728, pruned_loss=0.03637, over 7362.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2744, pruned_loss=0.04043, over 1421737.47 frames.], batch size: 19, lr: 4.55e-04
+2022-04-29 11:03:04,683 INFO [train.py:763] (6/8) Epoch 16, batch 2700, loss[loss=0.2294, simple_loss=0.3178, pruned_loss=0.07048, over 7334.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2734, pruned_loss=0.03997, over 1424047.05 frames.], batch size: 22, lr: 4.55e-04
+2022-04-29 11:04:10,095 INFO [train.py:763] (6/8) Epoch 16, batch 2750, loss[loss=0.1597, simple_loss=0.2629, pruned_loss=0.02825, over 7166.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2725, pruned_loss=0.03967, over 1423162.92 frames.], batch size: 19, lr: 4.55e-04
+2022-04-29 11:05:15,590 INFO [train.py:763] (6/8) Epoch 16, batch 2800, loss[loss=0.2349, simple_loss=0.3281, pruned_loss=0.07086, over 5163.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2725, pruned_loss=0.03965, over 1422301.87 frames.], batch size: 55, lr: 4.55e-04
+2022-04-29 11:06:20,606 INFO [train.py:763] (6/8) Epoch 16, batch 2850, loss[loss=0.1814, simple_loss=0.2937, pruned_loss=0.03457, over 7315.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2735, pruned_loss=0.03978, over 1421547.69 frames.], batch size: 21, lr: 4.55e-04
+2022-04-29 11:07:35,854 INFO [train.py:763] (6/8) Epoch 16, batch 2900, loss[loss=0.1538, simple_loss=0.255, pruned_loss=0.02634, over 7228.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2733, pruned_loss=0.03972, over 1417919.26 frames.], batch size: 20, lr: 4.55e-04
+2022-04-29 11:08:42,410 INFO [train.py:763] (6/8) Epoch 16, batch 2950, loss[loss=0.1539, simple_loss=0.257, pruned_loss=0.02542, over 7276.00 frames.], tot_loss[loss=0.177, simple_loss=0.2739, pruned_loss=0.04005, over 1418204.32 frames.], batch size: 18, lr: 4.54e-04
+2022-04-29 11:09:49,127 INFO [train.py:763] (6/8) Epoch 16, batch 3000, loss[loss=0.1622, simple_loss=0.2739, pruned_loss=0.02528, over 7148.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2741, pruned_loss=0.04034, over 1423022.48 frames.], batch size: 20, lr: 4.54e-04
+2022-04-29 11:09:49,128 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 11:10:05,042 INFO [train.py:792] (6/8) Epoch 16, validation: loss=0.1677, simple_loss=0.2693, pruned_loss=0.03309, over 698248.00 frames.
+2022-04-29 11:11:10,310 INFO [train.py:763] (6/8) Epoch 16, batch 3050, loss[loss=0.1731, simple_loss=0.2743, pruned_loss=0.03591, over 6476.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2735, pruned_loss=0.04012, over 1422999.89 frames.], batch size: 38, lr: 4.54e-04
+2022-04-29 11:12:42,601 INFO [train.py:763] (6/8) Epoch 16, batch 3100, loss[loss=0.1858, simple_loss=0.2826, pruned_loss=0.04454, over 7321.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2736, pruned_loss=0.04044, over 1419802.21 frames.], batch size: 25, lr: 4.54e-04
+2022-04-29 11:13:48,022 INFO [train.py:763] (6/8) Epoch 16, batch 3150, loss[loss=0.1802, simple_loss=0.2721, pruned_loss=0.04412, over 7325.00 frames.], tot_loss[loss=0.1777, simple_loss=0.274, pruned_loss=0.04072, over 1418548.10 frames.], batch size: 20, lr: 4.54e-04
+2022-04-29 11:15:03,460 INFO [train.py:763] (6/8) Epoch 16, batch 3200, loss[loss=0.1535, simple_loss=0.251, pruned_loss=0.02799, over 7356.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2746, pruned_loss=0.04105, over 1418238.69 frames.], batch size: 19, lr: 4.54e-04
+2022-04-29 11:16:27,103 INFO [train.py:763] (6/8) Epoch 16, batch 3250, loss[loss=0.1886, simple_loss=0.2736, pruned_loss=0.05174, over 7078.00 frames.], tot_loss[loss=0.1785, simple_loss=0.275, pruned_loss=0.04102, over 1423554.42 frames.], batch size: 18, lr: 4.54e-04
+2022-04-29 11:17:32,422 INFO [train.py:763] (6/8) Epoch 16, batch 3300, loss[loss=0.1893, simple_loss=0.284, pruned_loss=0.04734, over 7148.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2757, pruned_loss=0.04129, over 1424976.86 frames.], batch size: 19, lr: 4.53e-04
+2022-04-29 11:18:47,355 INFO [train.py:763] (6/8) Epoch 16, batch 3350, loss[loss=0.1723, simple_loss=0.2866, pruned_loss=0.02901, over 7337.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2766, pruned_loss=0.04126, over 1425983.38 frames.], batch size: 22, lr: 4.53e-04
+2022-04-29 11:19:54,001 INFO [train.py:763] (6/8) Epoch 16, batch 3400, loss[loss=0.1681, simple_loss=0.2769, pruned_loss=0.02965, over 7144.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2762, pruned_loss=0.04097, over 1422556.63 frames.], batch size: 20, lr: 4.53e-04
+2022-04-29 11:21:00,497 INFO [train.py:763] (6/8) Epoch 16, batch 3450, loss[loss=0.1582, simple_loss=0.2567, pruned_loss=0.0298, over 7331.00 frames.], tot_loss[loss=0.1775, simple_loss=0.274, pruned_loss=0.04051, over 1423688.94 frames.], batch size: 20, lr: 4.53e-04
+2022-04-29 11:22:05,837 INFO [train.py:763] (6/8) Epoch 16, batch 3500, loss[loss=0.179, simple_loss=0.278, pruned_loss=0.04004, over 7203.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2736, pruned_loss=0.04067, over 1423150.44 frames.], batch size: 22, lr: 4.53e-04
+2022-04-29 11:23:11,000 INFO [train.py:763] (6/8) Epoch 16, batch 3550, loss[loss=0.1713, simple_loss=0.2736, pruned_loss=0.03448, over 7439.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2744, pruned_loss=0.04065, over 1426306.39 frames.], batch size: 22, lr: 4.53e-04
+2022-04-29 11:24:16,266 INFO [train.py:763] (6/8) Epoch 16, batch 3600, loss[loss=0.1555, simple_loss=0.2468, pruned_loss=0.03216, over 7285.00 frames.], tot_loss[loss=0.178, simple_loss=0.2747, pruned_loss=0.04065, over 1426802.39 frames.], batch size: 18, lr: 4.52e-04
+2022-04-29 11:25:21,853 INFO [train.py:763] (6/8) Epoch 16, batch 3650, loss[loss=0.1807, simple_loss=0.2842, pruned_loss=0.0386, over 7305.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2736, pruned_loss=0.04026, over 1430949.26 frames.], batch size: 21, lr: 4.52e-04
+2022-04-29 11:26:27,136 INFO [train.py:763] (6/8) Epoch 16, batch 3700, loss[loss=0.1707, simple_loss=0.2725, pruned_loss=0.03447, over 7149.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2733, pruned_loss=0.03991, over 1431146.43 frames.], batch size: 20, lr: 4.52e-04
+2022-04-29 11:27:34,287 INFO [train.py:763] (6/8) Epoch 16, batch 3750, loss[loss=0.1989, simple_loss=0.3054, pruned_loss=0.04626, over 6314.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2741, pruned_loss=0.04017, over 1428457.27 frames.], batch size: 38, lr: 4.52e-04
+2022-04-29 11:28:40,553 INFO [train.py:763] (6/8) Epoch 16, batch 3800, loss[loss=0.1731, simple_loss=0.2655, pruned_loss=0.0403, over 6407.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2749, pruned_loss=0.04004, over 1427088.81 frames.], batch size: 38, lr: 4.52e-04
+2022-04-29 11:29:46,871 INFO [train.py:763] (6/8) Epoch 16, batch 3850, loss[loss=0.1464, simple_loss=0.2409, pruned_loss=0.02598, over 6992.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2749, pruned_loss=0.03987, over 1426291.40 frames.], batch size: 16, lr: 4.52e-04
+2022-04-29 11:30:53,557 INFO [train.py:763] (6/8) Epoch 16, batch 3900, loss[loss=0.1697, simple_loss=0.2683, pruned_loss=0.03553, over 7204.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2734, pruned_loss=0.03983, over 1428479.27 frames.], batch size: 22, lr: 4.52e-04
+2022-04-29 11:32:00,329 INFO [train.py:763] (6/8) Epoch 16, batch 3950, loss[loss=0.1986, simple_loss=0.2907, pruned_loss=0.05322, over 7187.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2741, pruned_loss=0.04022, over 1428025.98 frames.], batch size: 23, lr: 4.51e-04
+2022-04-29 11:33:05,770 INFO [train.py:763] (6/8) Epoch 16, batch 4000, loss[loss=0.1514, simple_loss=0.25, pruned_loss=0.02644, over 7274.00 frames.], tot_loss[loss=0.1774, simple_loss=0.274, pruned_loss=0.04038, over 1428006.78 frames.], batch size: 18, lr: 4.51e-04
+2022-04-29 11:34:12,299 INFO [train.py:763] (6/8) Epoch 16, batch 4050, loss[loss=0.19, simple_loss=0.2932, pruned_loss=0.04336, over 6822.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2746, pruned_loss=0.04094, over 1423896.00 frames.], batch size: 31, lr: 4.51e-04
+2022-04-29 11:35:18,253 INFO [train.py:763] (6/8) Epoch 16, batch 4100, loss[loss=0.1735, simple_loss=0.2855, pruned_loss=0.03072, over 6639.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2754, pruned_loss=0.04091, over 1423627.46 frames.], batch size: 38, lr: 4.51e-04
+2022-04-29 11:36:24,675 INFO [train.py:763] (6/8) Epoch 16, batch 4150, loss[loss=0.1481, simple_loss=0.2437, pruned_loss=0.02627, over 7129.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2742, pruned_loss=0.04049, over 1422779.33 frames.], batch size: 17, lr: 4.51e-04
+2022-04-29 11:37:30,202 INFO [train.py:763] (6/8) Epoch 16, batch 4200, loss[loss=0.2038, simple_loss=0.3046, pruned_loss=0.05151, over 7154.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2745, pruned_loss=0.0406, over 1421805.70 frames.], batch size: 26, lr: 4.51e-04
+2022-04-29 11:38:36,632 INFO [train.py:763] (6/8) Epoch 16, batch 4250, loss[loss=0.1698, simple_loss=0.2643, pruned_loss=0.03769, over 7282.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2747, pruned_loss=0.04031, over 1423480.61 frames.], batch size: 18, lr: 4.51e-04
+2022-04-29 11:39:43,734 INFO [train.py:763] (6/8) Epoch 16, batch 4300, loss[loss=0.1667, simple_loss=0.2582, pruned_loss=0.03754, over 7067.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2735, pruned_loss=0.04013, over 1422206.46 frames.], batch size: 18, lr: 4.50e-04
+2022-04-29 11:40:49,812 INFO [train.py:763] (6/8) Epoch 16, batch 4350, loss[loss=0.1609, simple_loss=0.2633, pruned_loss=0.02928, over 7165.00 frames.], tot_loss[loss=0.1773, simple_loss=0.274, pruned_loss=0.04026, over 1421682.73 frames.], batch size: 18, lr: 4.50e-04
+2022-04-29 11:41:55,140 INFO [train.py:763] (6/8) Epoch 16, batch 4400, loss[loss=0.1655, simple_loss=0.2727, pruned_loss=0.0292, over 7210.00 frames.], tot_loss[loss=0.1773, simple_loss=0.274, pruned_loss=0.0403, over 1419523.28 frames.], batch size: 21, lr: 4.50e-04
+2022-04-29 11:43:00,290 INFO [train.py:763] (6/8) Epoch 16, batch 4450, loss[loss=0.153, simple_loss=0.2439, pruned_loss=0.03109, over 7139.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2741, pruned_loss=0.04002, over 1415786.73 frames.], batch size: 17, lr: 4.50e-04
+2022-04-29 11:44:06,065 INFO [train.py:763] (6/8) Epoch 16, batch 4500, loss[loss=0.1949, simple_loss=0.2889, pruned_loss=0.05046, over 7232.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2732, pruned_loss=0.04016, over 1416191.07 frames.], batch size: 20, lr: 4.50e-04
+2022-04-29 11:45:13,648 INFO [train.py:763] (6/8) Epoch 16, batch 4550, loss[loss=0.1867, simple_loss=0.285, pruned_loss=0.04421, over 4993.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2731, pruned_loss=0.04104, over 1381755.46 frames.], batch size: 52, lr: 4.50e-04
+2022-04-29 11:46:42,224 INFO [train.py:763] (6/8) Epoch 17, batch 0, loss[loss=0.1842, simple_loss=0.2892, pruned_loss=0.03962, over 7232.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2892, pruned_loss=0.03962, over 7232.00 frames.], batch size: 20, lr: 4.38e-04
+2022-04-29 11:47:48,728 INFO [train.py:763] (6/8) Epoch 17, batch 50, loss[loss=0.1699, simple_loss=0.2549, pruned_loss=0.04248, over 6983.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2727, pruned_loss=0.03908, over 323573.32 frames.], batch size: 16, lr: 4.38e-04
+2022-04-29 11:48:54,535 INFO [train.py:763] (6/8) Epoch 17, batch 100, loss[loss=0.1626, simple_loss=0.258, pruned_loss=0.03355, over 7151.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2733, pruned_loss=0.03849, over 565932.19 frames.], batch size: 18, lr: 4.37e-04
+2022-04-29 11:50:00,286 INFO [train.py:763] (6/8) Epoch 17, batch 150, loss[loss=0.1849, simple_loss=0.2727, pruned_loss=0.04849, over 7150.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2752, pruned_loss=0.03928, over 753211.91 frames.], batch size: 20, lr: 4.37e-04
+2022-04-29 11:51:07,236 INFO [train.py:763] (6/8) Epoch 17, batch 200, loss[loss=0.1872, simple_loss=0.2803, pruned_loss=0.04708, over 7159.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2752, pruned_loss=0.03965, over 904775.91 frames.], batch size: 18, lr: 4.37e-04
+2022-04-29 11:52:14,163 INFO [train.py:763] (6/8) Epoch 17, batch 250, loss[loss=0.1686, simple_loss=0.273, pruned_loss=0.03206, over 6829.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2746, pruned_loss=0.03939, over 1022475.21 frames.], batch size: 31, lr: 4.37e-04
+2022-04-29 11:53:19,801 INFO [train.py:763] (6/8) Epoch 17, batch 300, loss[loss=0.1842, simple_loss=0.2861, pruned_loss=0.04118, over 7094.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2755, pruned_loss=0.03954, over 1106263.77 frames.], batch size: 28, lr: 4.37e-04
+2022-04-29 11:54:25,514 INFO [train.py:763] (6/8) Epoch 17, batch 350, loss[loss=0.166, simple_loss=0.2796, pruned_loss=0.02623, over 7330.00 frames.], tot_loss[loss=0.1755, simple_loss=0.273, pruned_loss=0.03901, over 1174658.14 frames.], batch size: 22, lr: 4.37e-04
+2022-04-29 11:55:31,574 INFO [train.py:763] (6/8) Epoch 17, batch 400, loss[loss=0.1737, simple_loss=0.2587, pruned_loss=0.04438, over 6816.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2737, pruned_loss=0.03903, over 1233966.59 frames.], batch size: 15, lr: 4.37e-04
+2022-04-29 11:56:37,254 INFO [train.py:763] (6/8) Epoch 17, batch 450, loss[loss=0.1787, simple_loss=0.2747, pruned_loss=0.04138, over 7215.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2742, pruned_loss=0.03922, over 1276898.24 frames.], batch size: 22, lr: 4.36e-04
+2022-04-29 11:57:42,949 INFO [train.py:763] (6/8) Epoch 17, batch 500, loss[loss=0.1622, simple_loss=0.2719, pruned_loss=0.02632, over 7343.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2737, pruned_loss=0.03905, over 1313593.55 frames.], batch size: 22, lr: 4.36e-04
+2022-04-29 11:58:48,661 INFO [train.py:763] (6/8) Epoch 17, batch 550, loss[loss=0.1615, simple_loss=0.2642, pruned_loss=0.02938, over 7129.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2737, pruned_loss=0.03884, over 1339647.27 frames.], batch size: 17, lr: 4.36e-04
+2022-04-29 11:59:54,501 INFO [train.py:763] (6/8) Epoch 17, batch 600, loss[loss=0.1691, simple_loss=0.2768, pruned_loss=0.0307, over 6162.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2755, pruned_loss=0.03978, over 1356857.58 frames.], batch size: 37, lr: 4.36e-04
+2022-04-29 12:01:00,142 INFO [train.py:763] (6/8) Epoch 17, batch 650, loss[loss=0.2054, simple_loss=0.2905, pruned_loss=0.06017, over 5130.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2755, pruned_loss=0.03992, over 1369485.43 frames.], batch size: 54, lr: 4.36e-04
+2022-04-29 12:02:07,664 INFO [train.py:763] (6/8) Epoch 17, batch 700, loss[loss=0.1689, simple_loss=0.2769, pruned_loss=0.03042, over 7317.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2747, pruned_loss=0.03955, over 1380844.96 frames.], batch size: 21, lr: 4.36e-04
+2022-04-29 12:03:15,583 INFO [train.py:763] (6/8) Epoch 17, batch 750, loss[loss=0.1323, simple_loss=0.2276, pruned_loss=0.01849, over 7423.00 frames.], tot_loss[loss=0.1754, simple_loss=0.273, pruned_loss=0.03889, over 1391325.04 frames.], batch size: 18, lr: 4.36e-04
+2022-04-29 12:04:22,598 INFO [train.py:763] (6/8) Epoch 17, batch 800, loss[loss=0.189, simple_loss=0.2957, pruned_loss=0.04114, over 7323.00 frames.], tot_loss[loss=0.175, simple_loss=0.2728, pruned_loss=0.03861, over 1403743.39 frames.], batch size: 21, lr: 4.36e-04
+2022-04-29 12:05:28,621 INFO [train.py:763] (6/8) Epoch 17, batch 850, loss[loss=0.1902, simple_loss=0.2808, pruned_loss=0.04977, over 7417.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2721, pruned_loss=0.03859, over 1407921.61 frames.], batch size: 21, lr: 4.35e-04
+2022-04-29 12:06:34,120 INFO [train.py:763] (6/8) Epoch 17, batch 900, loss[loss=0.1869, simple_loss=0.2832, pruned_loss=0.04525, over 7207.00 frames.], tot_loss[loss=0.1753, simple_loss=0.273, pruned_loss=0.03878, over 1408535.63 frames.], batch size: 22, lr: 4.35e-04
+2022-04-29 12:07:40,038 INFO [train.py:763] (6/8) Epoch 17, batch 950, loss[loss=0.1715, simple_loss=0.2778, pruned_loss=0.03262, over 7257.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2736, pruned_loss=0.03911, over 1411239.58 frames.], batch size: 19, lr: 4.35e-04
+2022-04-29 12:08:46,313 INFO [train.py:763] (6/8) Epoch 17, batch 1000, loss[loss=0.1891, simple_loss=0.2935, pruned_loss=0.0423, over 7316.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2728, pruned_loss=0.03908, over 1415503.92 frames.], batch size: 24, lr: 4.35e-04
+2022-04-29 12:09:52,069 INFO [train.py:763] (6/8) Epoch 17, batch 1050, loss[loss=0.1575, simple_loss=0.2421, pruned_loss=0.03644, over 7285.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2721, pruned_loss=0.03863, over 1417792.05 frames.], batch size: 17, lr: 4.35e-04
+2022-04-29 12:10:57,974 INFO [train.py:763] (6/8) Epoch 17, batch 1100, loss[loss=0.2137, simple_loss=0.3042, pruned_loss=0.06157, over 7299.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2727, pruned_loss=0.03912, over 1420734.59 frames.], batch size: 25, lr: 4.35e-04
+2022-04-29 12:12:04,950 INFO [train.py:763] (6/8) Epoch 17, batch 1150, loss[loss=0.1888, simple_loss=0.2873, pruned_loss=0.04519, over 7377.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2727, pruned_loss=0.03935, over 1419703.67 frames.], batch size: 23, lr: 4.35e-04
+2022-04-29 12:13:12,221 INFO [train.py:763] (6/8) Epoch 17, batch 1200, loss[loss=0.1619, simple_loss=0.2541, pruned_loss=0.03486, over 7281.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2727, pruned_loss=0.03912, over 1417379.30 frames.], batch size: 18, lr: 4.34e-04
+2022-04-29 12:14:19,346 INFO [train.py:763] (6/8) Epoch 17, batch 1250, loss[loss=0.1572, simple_loss=0.261, pruned_loss=0.02671, over 7412.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2729, pruned_loss=0.03936, over 1419343.94 frames.], batch size: 21, lr: 4.34e-04
+2022-04-29 12:15:25,213 INFO [train.py:763] (6/8) Epoch 17, batch 1300, loss[loss=0.1968, simple_loss=0.2988, pruned_loss=0.04735, over 7149.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2727, pruned_loss=0.0393, over 1419793.87 frames.], batch size: 26, lr: 4.34e-04
+2022-04-29 12:16:30,497 INFO [train.py:763] (6/8) Epoch 17, batch 1350, loss[loss=0.1467, simple_loss=0.2334, pruned_loss=0.02998, over 7006.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2727, pruned_loss=0.03931, over 1422630.75 frames.], batch size: 16, lr: 4.34e-04
+2022-04-29 12:17:36,086 INFO [train.py:763] (6/8) Epoch 17, batch 1400, loss[loss=0.2076, simple_loss=0.3125, pruned_loss=0.05133, over 7108.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2734, pruned_loss=0.03904, over 1424504.04 frames.], batch size: 21, lr: 4.34e-04
+2022-04-29 12:18:41,489 INFO [train.py:763] (6/8) Epoch 17, batch 1450, loss[loss=0.1758, simple_loss=0.2809, pruned_loss=0.03532, over 7149.00 frames.], tot_loss[loss=0.1763, simple_loss=0.274, pruned_loss=0.03932, over 1421993.59 frames.], batch size: 20, lr: 4.34e-04
+2022-04-29 12:19:47,540 INFO [train.py:763] (6/8) Epoch 17, batch 1500, loss[loss=0.1776, simple_loss=0.2748, pruned_loss=0.04017, over 7277.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2739, pruned_loss=0.0396, over 1413714.48 frames.], batch size: 25, lr: 4.34e-04
+2022-04-29 12:20:53,498 INFO [train.py:763] (6/8) Epoch 17, batch 1550, loss[loss=0.1507, simple_loss=0.2522, pruned_loss=0.02463, over 7149.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2728, pruned_loss=0.03908, over 1421219.01 frames.], batch size: 19, lr: 4.33e-04
+2022-04-29 12:21:59,197 INFO [train.py:763] (6/8) Epoch 17, batch 1600, loss[loss=0.1867, simple_loss=0.2795, pruned_loss=0.04694, over 7432.00 frames.], tot_loss[loss=0.1758, simple_loss=0.273, pruned_loss=0.03931, over 1421887.79 frames.], batch size: 20, lr: 4.33e-04
+2022-04-29 12:23:04,505 INFO [train.py:763] (6/8) Epoch 17, batch 1650, loss[loss=0.1855, simple_loss=0.2728, pruned_loss=0.04906, over 7274.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2747, pruned_loss=0.03968, over 1421506.78 frames.], batch size: 17, lr: 4.33e-04
+2022-04-29 12:24:09,905 INFO [train.py:763] (6/8) Epoch 17, batch 1700, loss[loss=0.1646, simple_loss=0.2507, pruned_loss=0.03923, over 7348.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2744, pruned_loss=0.03965, over 1424227.49 frames.], batch size: 19, lr: 4.33e-04
+2022-04-29 12:25:15,255 INFO [train.py:763] (6/8) Epoch 17, batch 1750, loss[loss=0.1718, simple_loss=0.2732, pruned_loss=0.03518, over 7317.00 frames.], tot_loss[loss=0.1766, simple_loss=0.274, pruned_loss=0.03958, over 1424753.47 frames.], batch size: 21, lr: 4.33e-04
+2022-04-29 12:26:20,537 INFO [train.py:763] (6/8) Epoch 17, batch 1800, loss[loss=0.1884, simple_loss=0.291, pruned_loss=0.04286, over 7237.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2736, pruned_loss=0.03972, over 1429472.51 frames.], batch size: 20, lr: 4.33e-04
+2022-04-29 12:27:26,285 INFO [train.py:763] (6/8) Epoch 17, batch 1850, loss[loss=0.1754, simple_loss=0.2698, pruned_loss=0.04046, over 5003.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2723, pruned_loss=0.03965, over 1428017.91 frames.], batch size: 52, lr: 4.33e-04
+2022-04-29 12:28:31,344 INFO [train.py:763] (6/8) Epoch 17, batch 1900, loss[loss=0.171, simple_loss=0.2748, pruned_loss=0.03356, over 7322.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2732, pruned_loss=0.03958, over 1428376.44 frames.], batch size: 21, lr: 4.33e-04
+2022-04-29 12:29:36,731 INFO [train.py:763] (6/8) Epoch 17, batch 1950, loss[loss=0.1809, simple_loss=0.2977, pruned_loss=0.03205, over 7322.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2744, pruned_loss=0.03988, over 1425195.84 frames.], batch size: 21, lr: 4.32e-04
+2022-04-29 12:30:42,617 INFO [train.py:763] (6/8) Epoch 17, batch 2000, loss[loss=0.1843, simple_loss=0.27, pruned_loss=0.04936, over 4981.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2734, pruned_loss=0.03954, over 1425617.83 frames.], batch size: 52, lr: 4.32e-04
+2022-04-29 12:31:59,162 INFO [train.py:763] (6/8) Epoch 17, batch 2050, loss[loss=0.1732, simple_loss=0.2817, pruned_loss=0.03237, over 7122.00 frames.], tot_loss[loss=0.1761, simple_loss=0.273, pruned_loss=0.03964, over 1421641.82 frames.], batch size: 21, lr: 4.32e-04
+2022-04-29 12:33:04,691 INFO [train.py:763] (6/8) Epoch 17, batch 2100, loss[loss=0.1997, simple_loss=0.305, pruned_loss=0.0472, over 6749.00 frames.], tot_loss[loss=0.177, simple_loss=0.274, pruned_loss=0.03996, over 1417084.55 frames.], batch size: 31, lr: 4.32e-04
+2022-04-29 12:34:11,565 INFO [train.py:763] (6/8) Epoch 17, batch 2150, loss[loss=0.1702, simple_loss=0.28, pruned_loss=0.0302, over 7221.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2736, pruned_loss=0.03988, over 1419262.05 frames.], batch size: 21, lr: 4.32e-04
+2022-04-29 12:35:18,272 INFO [train.py:763] (6/8) Epoch 17, batch 2200, loss[loss=0.1521, simple_loss=0.2376, pruned_loss=0.03332, over 7251.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2733, pruned_loss=0.03975, over 1421538.93 frames.], batch size: 16, lr: 4.32e-04
+2022-04-29 12:36:23,942 INFO [train.py:763] (6/8) Epoch 17, batch 2250, loss[loss=0.1464, simple_loss=0.2372, pruned_loss=0.02779, over 7012.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2721, pruned_loss=0.03921, over 1424866.43 frames.], batch size: 16, lr: 4.32e-04
+2022-04-29 12:37:31,405 INFO [train.py:763] (6/8) Epoch 17, batch 2300, loss[loss=0.1685, simple_loss=0.2701, pruned_loss=0.03349, over 7140.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2728, pruned_loss=0.03924, over 1427441.81 frames.], batch size: 20, lr: 4.31e-04
+2022-04-29 12:38:38,624 INFO [train.py:763] (6/8) Epoch 17, batch 2350, loss[loss=0.1945, simple_loss=0.2976, pruned_loss=0.04572, over 7150.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2727, pruned_loss=0.03928, over 1427069.21 frames.], batch size: 26, lr: 4.31e-04
+2022-04-29 12:39:44,064 INFO [train.py:763] (6/8) Epoch 17, batch 2400, loss[loss=0.1952, simple_loss=0.3007, pruned_loss=0.04489, over 6550.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2731, pruned_loss=0.03932, over 1425769.95 frames.], batch size: 38, lr: 4.31e-04
+2022-04-29 12:40:49,291 INFO [train.py:763] (6/8) Epoch 17, batch 2450, loss[loss=0.16, simple_loss=0.2557, pruned_loss=0.03211, over 7157.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2725, pruned_loss=0.03914, over 1426876.03 frames.], batch size: 19, lr: 4.31e-04
+2022-04-29 12:41:54,334 INFO [train.py:763] (6/8) Epoch 17, batch 2500, loss[loss=0.1661, simple_loss=0.2647, pruned_loss=0.03372, over 7116.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2744, pruned_loss=0.04021, over 1419960.21 frames.], batch size: 21, lr: 4.31e-04
+2022-04-29 12:42:59,731 INFO [train.py:763] (6/8) Epoch 17, batch 2550, loss[loss=0.1532, simple_loss=0.2603, pruned_loss=0.02309, over 7324.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2738, pruned_loss=0.03984, over 1420265.88 frames.], batch size: 21, lr: 4.31e-04
+2022-04-29 12:44:04,851 INFO [train.py:763] (6/8) Epoch 17, batch 2600, loss[loss=0.1539, simple_loss=0.2399, pruned_loss=0.034, over 6808.00 frames.], tot_loss[loss=0.177, simple_loss=0.274, pruned_loss=0.04002, over 1419830.56 frames.], batch size: 15, lr: 4.31e-04
+2022-04-29 12:45:10,702 INFO [train.py:763] (6/8) Epoch 17, batch 2650, loss[loss=0.1552, simple_loss=0.2516, pruned_loss=0.02941, over 7361.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2738, pruned_loss=0.03984, over 1420733.20 frames.], batch size: 19, lr: 4.31e-04
+2022-04-29 12:46:17,008 INFO [train.py:763] (6/8) Epoch 17, batch 2700, loss[loss=0.1457, simple_loss=0.2324, pruned_loss=0.02955, over 7290.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2731, pruned_loss=0.03966, over 1420562.67 frames.], batch size: 18, lr: 4.30e-04
+2022-04-29 12:47:22,080 INFO [train.py:763] (6/8) Epoch 17, batch 2750, loss[loss=0.1937, simple_loss=0.2922, pruned_loss=0.04763, over 7129.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2727, pruned_loss=0.03941, over 1419077.96 frames.], batch size: 20, lr: 4.30e-04
+2022-04-29 12:48:28,898 INFO [train.py:763] (6/8) Epoch 17, batch 2800, loss[loss=0.1725, simple_loss=0.2831, pruned_loss=0.03094, over 7305.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2722, pruned_loss=0.03926, over 1418064.67 frames.], batch size: 21, lr: 4.30e-04
+2022-04-29 12:49:34,425 INFO [train.py:763] (6/8) Epoch 17, batch 2850, loss[loss=0.2146, simple_loss=0.3053, pruned_loss=0.06196, over 7299.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2718, pruned_loss=0.03863, over 1421109.18 frames.], batch size: 25, lr: 4.30e-04
+2022-04-29 12:50:39,888 INFO [train.py:763] (6/8) Epoch 17, batch 2900, loss[loss=0.1772, simple_loss=0.2753, pruned_loss=0.03951, over 7203.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2717, pruned_loss=0.03876, over 1423415.36 frames.], batch size: 22, lr: 4.30e-04
+2022-04-29 12:51:46,364 INFO [train.py:763] (6/8) Epoch 17, batch 2950, loss[loss=0.1652, simple_loss=0.2654, pruned_loss=0.03254, over 6352.00 frames.], tot_loss[loss=0.175, simple_loss=0.2723, pruned_loss=0.03884, over 1420387.56 frames.], batch size: 37, lr: 4.30e-04
+2022-04-29 12:52:52,643 INFO [train.py:763] (6/8) Epoch 17, batch 3000, loss[loss=0.1772, simple_loss=0.2898, pruned_loss=0.03233, over 7307.00 frames.], tot_loss[loss=0.1753, simple_loss=0.273, pruned_loss=0.0388, over 1420093.71 frames.], batch size: 25, lr: 4.30e-04
+2022-04-29 12:52:52,644 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 12:53:07,981 INFO [train.py:792] (6/8) Epoch 17, validation: loss=0.167, simple_loss=0.268, pruned_loss=0.03296, over 698248.00 frames.
+2022-04-29 12:54:13,323 INFO [train.py:763] (6/8) Epoch 17, batch 3050, loss[loss=0.1725, simple_loss=0.2714, pruned_loss=0.03681, over 7107.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2728, pruned_loss=0.03879, over 1418370.22 frames.], batch size: 21, lr: 4.29e-04
+2022-04-29 12:55:18,436 INFO [train.py:763] (6/8) Epoch 17, batch 3100, loss[loss=0.1583, simple_loss=0.2528, pruned_loss=0.03196, over 7230.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2733, pruned_loss=0.03895, over 1419761.73 frames.], batch size: 20, lr: 4.29e-04
+2022-04-29 12:56:23,981 INFO [train.py:763] (6/8) Epoch 17, batch 3150, loss[loss=0.1766, simple_loss=0.2708, pruned_loss=0.0412, over 7250.00 frames.], tot_loss[loss=0.175, simple_loss=0.2727, pruned_loss=0.03865, over 1422023.24 frames.], batch size: 19, lr: 4.29e-04
+2022-04-29 12:57:29,298 INFO [train.py:763] (6/8) Epoch 17, batch 3200, loss[loss=0.1934, simple_loss=0.2877, pruned_loss=0.04959, over 6731.00 frames.], tot_loss[loss=0.175, simple_loss=0.2724, pruned_loss=0.03878, over 1420331.75 frames.], batch size: 31, lr: 4.29e-04
+2022-04-29 12:58:34,633 INFO [train.py:763] (6/8) Epoch 17, batch 3250, loss[loss=0.1948, simple_loss=0.2905, pruned_loss=0.04957, over 7380.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2721, pruned_loss=0.03856, over 1423004.18 frames.], batch size: 23, lr: 4.29e-04
+2022-04-29 12:59:42,207 INFO [train.py:763] (6/8) Epoch 17, batch 3300, loss[loss=0.1481, simple_loss=0.2434, pruned_loss=0.02642, over 7159.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2712, pruned_loss=0.03827, over 1427264.34 frames.], batch size: 18, lr: 4.29e-04
+2022-04-29 13:00:47,854 INFO [train.py:763] (6/8) Epoch 17, batch 3350, loss[loss=0.1416, simple_loss=0.2329, pruned_loss=0.02521, over 7416.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2712, pruned_loss=0.03821, over 1426539.98 frames.], batch size: 18, lr: 4.29e-04
+2022-04-29 13:01:54,346 INFO [train.py:763] (6/8) Epoch 17, batch 3400, loss[loss=0.1987, simple_loss=0.3078, pruned_loss=0.04483, over 7388.00 frames.], tot_loss[loss=0.174, simple_loss=0.2716, pruned_loss=0.03821, over 1430435.01 frames.], batch size: 23, lr: 4.29e-04
+2022-04-29 13:02:59,885 INFO [train.py:763] (6/8) Epoch 17, batch 3450, loss[loss=0.1479, simple_loss=0.2415, pruned_loss=0.02718, over 7412.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2718, pruned_loss=0.03817, over 1430628.38 frames.], batch size: 18, lr: 4.28e-04
+2022-04-29 13:04:05,574 INFO [train.py:763] (6/8) Epoch 17, batch 3500, loss[loss=0.193, simple_loss=0.2995, pruned_loss=0.04326, over 6330.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2714, pruned_loss=0.03844, over 1432901.89 frames.], batch size: 38, lr: 4.28e-04
+2022-04-29 13:05:11,609 INFO [train.py:763] (6/8) Epoch 17, batch 3550, loss[loss=0.1937, simple_loss=0.2898, pruned_loss=0.04886, over 7209.00 frames.], tot_loss[loss=0.1755, simple_loss=0.273, pruned_loss=0.03897, over 1430852.91 frames.], batch size: 23, lr: 4.28e-04
+2022-04-29 13:06:17,364 INFO [train.py:763] (6/8) Epoch 17, batch 3600, loss[loss=0.1723, simple_loss=0.272, pruned_loss=0.03632, over 7206.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2728, pruned_loss=0.03903, over 1432138.59 frames.], batch size: 21, lr: 4.28e-04
+2022-04-29 13:07:22,978 INFO [train.py:763] (6/8) Epoch 17, batch 3650, loss[loss=0.1869, simple_loss=0.2967, pruned_loss=0.03855, over 7340.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2728, pruned_loss=0.03902, over 1422336.16 frames.], batch size: 22, lr: 4.28e-04
+2022-04-29 13:08:28,134 INFO [train.py:763] (6/8) Epoch 17, batch 3700, loss[loss=0.1664, simple_loss=0.2534, pruned_loss=0.03974, over 6984.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2736, pruned_loss=0.03943, over 1423621.29 frames.], batch size: 16, lr: 4.28e-04
+2022-04-29 13:09:33,327 INFO [train.py:763] (6/8) Epoch 17, batch 3750, loss[loss=0.1842, simple_loss=0.2861, pruned_loss=0.04115, over 7269.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2741, pruned_loss=0.03925, over 1426177.49 frames.], batch size: 25, lr: 4.28e-04
+2022-04-29 13:10:39,699 INFO [train.py:763] (6/8) Epoch 17, batch 3800, loss[loss=0.1591, simple_loss=0.2575, pruned_loss=0.03035, over 7357.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2739, pruned_loss=0.03966, over 1425909.46 frames.], batch size: 19, lr: 4.28e-04
+2022-04-29 13:11:45,019 INFO [train.py:763] (6/8) Epoch 17, batch 3850, loss[loss=0.1575, simple_loss=0.2476, pruned_loss=0.03367, over 7421.00 frames.], tot_loss[loss=0.1759, simple_loss=0.273, pruned_loss=0.03937, over 1424527.03 frames.], batch size: 18, lr: 4.27e-04
+2022-04-29 13:12:50,426 INFO [train.py:763] (6/8) Epoch 17, batch 3900, loss[loss=0.1609, simple_loss=0.27, pruned_loss=0.02592, over 7121.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2735, pruned_loss=0.03947, over 1420605.22 frames.], batch size: 21, lr: 4.27e-04
+2022-04-29 13:13:55,780 INFO [train.py:763] (6/8) Epoch 17, batch 3950, loss[loss=0.1941, simple_loss=0.3041, pruned_loss=0.04207, over 7079.00 frames.], tot_loss[loss=0.176, simple_loss=0.2731, pruned_loss=0.03948, over 1422172.95 frames.], batch size: 28, lr: 4.27e-04
+2022-04-29 13:15:01,136 INFO [train.py:763] (6/8) Epoch 17, batch 4000, loss[loss=0.1553, simple_loss=0.242, pruned_loss=0.03434, over 6850.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2733, pruned_loss=0.03984, over 1423101.04 frames.], batch size: 15, lr: 4.27e-04
+2022-04-29 13:16:06,982 INFO [train.py:763] (6/8) Epoch 17, batch 4050, loss[loss=0.212, simple_loss=0.2919, pruned_loss=0.0661, over 7053.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2734, pruned_loss=0.04024, over 1427221.39 frames.], batch size: 28, lr: 4.27e-04
+2022-04-29 13:17:12,351 INFO [train.py:763] (6/8) Epoch 17, batch 4100, loss[loss=0.1932, simple_loss=0.2949, pruned_loss=0.04577, over 7148.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2731, pruned_loss=0.04019, over 1423729.34 frames.], batch size: 20, lr: 4.27e-04
+2022-04-29 13:18:18,024 INFO [train.py:763] (6/8) Epoch 17, batch 4150, loss[loss=0.1678, simple_loss=0.2861, pruned_loss=0.02473, over 7325.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2736, pruned_loss=0.04039, over 1422455.86 frames.], batch size: 20, lr: 4.27e-04
+2022-04-29 13:19:24,069 INFO [train.py:763] (6/8) Epoch 17, batch 4200, loss[loss=0.142, simple_loss=0.2278, pruned_loss=0.02808, over 7431.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2722, pruned_loss=0.0398, over 1422180.20 frames.], batch size: 17, lr: 4.26e-04
+2022-04-29 13:20:29,204 INFO [train.py:763] (6/8) Epoch 17, batch 4250, loss[loss=0.1976, simple_loss=0.286, pruned_loss=0.05466, over 6865.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2727, pruned_loss=0.04012, over 1417956.05 frames.], batch size: 31, lr: 4.26e-04
+2022-04-29 13:21:35,162 INFO [train.py:763] (6/8) Epoch 17, batch 4300, loss[loss=0.1421, simple_loss=0.2401, pruned_loss=0.02203, over 6989.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2716, pruned_loss=0.03951, over 1418733.91 frames.], batch size: 16, lr: 4.26e-04
+2022-04-29 13:22:49,724 INFO [train.py:763] (6/8) Epoch 17, batch 4350, loss[loss=0.1818, simple_loss=0.2836, pruned_loss=0.04002, over 7218.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2713, pruned_loss=0.03955, over 1407126.04 frames.], batch size: 21, lr: 4.26e-04
+2022-04-29 13:23:54,553 INFO [train.py:763] (6/8) Epoch 17, batch 4400, loss[loss=0.1468, simple_loss=0.2386, pruned_loss=0.02744, over 7064.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2719, pruned_loss=0.03979, over 1400785.07 frames.], batch size: 18, lr: 4.26e-04
+2022-04-29 13:24:59,618 INFO [train.py:763] (6/8) Epoch 17, batch 4450, loss[loss=0.2206, simple_loss=0.3113, pruned_loss=0.06496, over 6265.00 frames.], tot_loss[loss=0.177, simple_loss=0.274, pruned_loss=0.04003, over 1393155.32 frames.], batch size: 37, lr: 4.26e-04
+2022-04-29 13:26:04,078 INFO [train.py:763] (6/8) Epoch 17, batch 4500, loss[loss=0.1392, simple_loss=0.2367, pruned_loss=0.02082, over 6986.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2749, pruned_loss=0.04048, over 1380371.70 frames.], batch size: 16, lr: 4.26e-04
+2022-04-29 13:27:09,435 INFO [train.py:763] (6/8) Epoch 17, batch 4550, loss[loss=0.1808, simple_loss=0.2811, pruned_loss=0.04025, over 7162.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2747, pruned_loss=0.04072, over 1371748.03 frames.], batch size: 19, lr: 4.26e-04
+2022-04-29 13:29:06,467 INFO [train.py:763] (6/8) Epoch 18, batch 0, loss[loss=0.1902, simple_loss=0.2832, pruned_loss=0.04863, over 7289.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2832, pruned_loss=0.04863, over 7289.00 frames.], batch size: 25, lr: 4.15e-04
+2022-04-29 13:30:22,088 INFO [train.py:763] (6/8) Epoch 18, batch 50, loss[loss=0.2013, simple_loss=0.2946, pruned_loss=0.05398, over 7345.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2721, pruned_loss=0.03964, over 324847.89 frames.], batch size: 22, lr: 4.15e-04
+2022-04-29 13:31:37,250 INFO [train.py:763] (6/8) Epoch 18, batch 100, loss[loss=0.1624, simple_loss=0.2687, pruned_loss=0.02802, over 7328.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2732, pruned_loss=0.03804, over 574103.59 frames.], batch size: 22, lr: 4.14e-04
+2022-04-29 13:32:51,553 INFO [train.py:763] (6/8) Epoch 18, batch 150, loss[loss=0.1573, simple_loss=0.2642, pruned_loss=0.02524, over 7220.00 frames.], tot_loss[loss=0.173, simple_loss=0.2714, pruned_loss=0.03728, over 763722.42 frames.], batch size: 21, lr: 4.14e-04
+2022-04-29 13:33:57,484 INFO [train.py:763] (6/8) Epoch 18, batch 200, loss[loss=0.1551, simple_loss=0.2483, pruned_loss=0.03092, over 7268.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2713, pruned_loss=0.03774, over 908836.18 frames.], batch size: 17, lr: 4.14e-04
+2022-04-29 13:35:11,769 INFO [train.py:763] (6/8) Epoch 18, batch 250, loss[loss=0.17, simple_loss=0.2734, pruned_loss=0.03333, over 6708.00 frames.], tot_loss[loss=0.174, simple_loss=0.2718, pruned_loss=0.03816, over 1024194.53 frames.], batch size: 31, lr: 4.14e-04
+2022-04-29 13:36:17,273 INFO [train.py:763] (6/8) Epoch 18, batch 300, loss[loss=0.1537, simple_loss=0.2527, pruned_loss=0.02735, over 7237.00 frames.], tot_loss[loss=0.174, simple_loss=0.272, pruned_loss=0.03801, over 1114554.30 frames.], batch size: 20, lr: 4.14e-04
+2022-04-29 13:37:24,208 INFO [train.py:763] (6/8) Epoch 18, batch 350, loss[loss=0.1836, simple_loss=0.2939, pruned_loss=0.0367, over 6749.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2709, pruned_loss=0.03771, over 1182168.46 frames.], batch size: 31, lr: 4.14e-04
+2022-04-29 13:38:31,275 INFO [train.py:763] (6/8) Epoch 18, batch 400, loss[loss=0.1773, simple_loss=0.2733, pruned_loss=0.0406, over 7064.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2725, pruned_loss=0.03849, over 1233938.05 frames.], batch size: 18, lr: 4.14e-04
+2022-04-29 13:39:38,719 INFO [train.py:763] (6/8) Epoch 18, batch 450, loss[loss=0.1708, simple_loss=0.2807, pruned_loss=0.03044, over 7341.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2728, pruned_loss=0.03853, over 1275598.07 frames.], batch size: 22, lr: 4.14e-04
+2022-04-29 13:40:45,467 INFO [train.py:763] (6/8) Epoch 18, batch 500, loss[loss=0.1493, simple_loss=0.2444, pruned_loss=0.02715, over 7127.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2729, pruned_loss=0.03872, over 1306387.85 frames.], batch size: 17, lr: 4.13e-04
+2022-04-29 13:41:52,280 INFO [train.py:763] (6/8) Epoch 18, batch 550, loss[loss=0.155, simple_loss=0.2436, pruned_loss=0.03323, over 7272.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2729, pruned_loss=0.03844, over 1335716.73 frames.], batch size: 17, lr: 4.13e-04
+2022-04-29 13:42:57,723 INFO [train.py:763] (6/8) Epoch 18, batch 600, loss[loss=0.1801, simple_loss=0.2667, pruned_loss=0.04677, over 7291.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2728, pruned_loss=0.03848, over 1356853.19 frames.], batch size: 18, lr: 4.13e-04
+2022-04-29 13:44:04,379 INFO [train.py:763] (6/8) Epoch 18, batch 650, loss[loss=0.1759, simple_loss=0.2849, pruned_loss=0.03351, over 7120.00 frames.], tot_loss[loss=0.1735, simple_loss=0.271, pruned_loss=0.03798, over 1375603.35 frames.], batch size: 21, lr: 4.13e-04
+2022-04-29 13:45:09,473 INFO [train.py:763] (6/8) Epoch 18, batch 700, loss[loss=0.195, simple_loss=0.2919, pruned_loss=0.04903, over 4872.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2721, pruned_loss=0.03843, over 1385808.99 frames.], batch size: 53, lr: 4.13e-04
+2022-04-29 13:46:15,216 INFO [train.py:763] (6/8) Epoch 18, batch 750, loss[loss=0.1454, simple_loss=0.2452, pruned_loss=0.02281, over 7149.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2708, pruned_loss=0.03769, over 1395096.92 frames.], batch size: 19, lr: 4.13e-04
+2022-04-29 13:47:20,149 INFO [train.py:763] (6/8) Epoch 18, batch 800, loss[loss=0.194, simple_loss=0.3006, pruned_loss=0.04372, over 6749.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2714, pruned_loss=0.03835, over 1397355.43 frames.], batch size: 31, lr: 4.13e-04
+2022-04-29 13:48:26,442 INFO [train.py:763] (6/8) Epoch 18, batch 850, loss[loss=0.1548, simple_loss=0.2391, pruned_loss=0.03532, over 7073.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2719, pruned_loss=0.03844, over 1405107.21 frames.], batch size: 18, lr: 4.13e-04
+2022-04-29 13:49:33,146 INFO [train.py:763] (6/8) Epoch 18, batch 900, loss[loss=0.2014, simple_loss=0.2851, pruned_loss=0.05879, over 6786.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2731, pruned_loss=0.03882, over 1410118.89 frames.], batch size: 15, lr: 4.12e-04
+2022-04-29 13:50:38,406 INFO [train.py:763] (6/8) Epoch 18, batch 950, loss[loss=0.1944, simple_loss=0.2923, pruned_loss=0.04824, over 7379.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2724, pruned_loss=0.03873, over 1413237.73 frames.], batch size: 23, lr: 4.12e-04
+2022-04-29 13:51:45,515 INFO [train.py:763] (6/8) Epoch 18, batch 1000, loss[loss=0.1793, simple_loss=0.2808, pruned_loss=0.03885, over 7137.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2726, pruned_loss=0.03856, over 1419880.48 frames.], batch size: 20, lr: 4.12e-04
+2022-04-29 13:52:52,992 INFO [train.py:763] (6/8) Epoch 18, batch 1050, loss[loss=0.184, simple_loss=0.2859, pruned_loss=0.04101, over 7309.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2721, pruned_loss=0.03877, over 1417650.70 frames.], batch size: 25, lr: 4.12e-04
+2022-04-29 13:53:58,531 INFO [train.py:763] (6/8) Epoch 18, batch 1100, loss[loss=0.1616, simple_loss=0.2632, pruned_loss=0.03004, over 7339.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2708, pruned_loss=0.03834, over 1418894.61 frames.], batch size: 20, lr: 4.12e-04
+2022-04-29 13:55:03,938 INFO [train.py:763] (6/8) Epoch 18, batch 1150, loss[loss=0.1751, simple_loss=0.2814, pruned_loss=0.03438, over 7303.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2707, pruned_loss=0.03795, over 1419502.93 frames.], batch size: 24, lr: 4.12e-04
+2022-04-29 13:56:09,833 INFO [train.py:763] (6/8) Epoch 18, batch 1200, loss[loss=0.1963, simple_loss=0.2736, pruned_loss=0.05951, over 5379.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2702, pruned_loss=0.03809, over 1415089.64 frames.], batch size: 53, lr: 4.12e-04
+2022-04-29 13:57:15,052 INFO [train.py:763] (6/8) Epoch 18, batch 1250, loss[loss=0.1733, simple_loss=0.2744, pruned_loss=0.03614, over 7118.00 frames.], tot_loss[loss=0.173, simple_loss=0.2702, pruned_loss=0.03792, over 1415179.37 frames.], batch size: 21, lr: 4.12e-04
+2022-04-29 13:58:20,085 INFO [train.py:763] (6/8) Epoch 18, batch 1300, loss[loss=0.1667, simple_loss=0.268, pruned_loss=0.03273, over 7157.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2712, pruned_loss=0.03781, over 1414466.10 frames.], batch size: 19, lr: 4.12e-04
+2022-04-29 13:59:25,400 INFO [train.py:763] (6/8) Epoch 18, batch 1350, loss[loss=0.21, simple_loss=0.3029, pruned_loss=0.05858, over 7104.00 frames.], tot_loss[loss=0.175, simple_loss=0.2727, pruned_loss=0.03868, over 1413267.04 frames.], batch size: 28, lr: 4.11e-04
+2022-04-29 14:00:32,448 INFO [train.py:763] (6/8) Epoch 18, batch 1400, loss[loss=0.1672, simple_loss=0.2675, pruned_loss=0.03347, over 7063.00 frames.], tot_loss[loss=0.175, simple_loss=0.2725, pruned_loss=0.03876, over 1411641.42 frames.], batch size: 18, lr: 4.11e-04
+2022-04-29 14:01:39,696 INFO [train.py:763] (6/8) Epoch 18, batch 1450, loss[loss=0.1725, simple_loss=0.2807, pruned_loss=0.0321, over 7319.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2727, pruned_loss=0.03875, over 1418500.68 frames.], batch size: 21, lr: 4.11e-04
+2022-04-29 14:02:45,984 INFO [train.py:763] (6/8) Epoch 18, batch 1500, loss[loss=0.1645, simple_loss=0.2576, pruned_loss=0.03567, over 7252.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2726, pruned_loss=0.03845, over 1421833.36 frames.], batch size: 19, lr: 4.11e-04
+2022-04-29 14:03:53,120 INFO [train.py:763] (6/8) Epoch 18, batch 1550, loss[loss=0.1828, simple_loss=0.281, pruned_loss=0.0423, over 7412.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2721, pruned_loss=0.03821, over 1424595.99 frames.], batch size: 21, lr: 4.11e-04
+2022-04-29 14:04:58,308 INFO [train.py:763] (6/8) Epoch 18, batch 1600, loss[loss=0.1833, simple_loss=0.2718, pruned_loss=0.04735, over 7212.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2721, pruned_loss=0.03836, over 1423579.65 frames.], batch size: 22, lr: 4.11e-04
+2022-04-29 14:06:03,988 INFO [train.py:763] (6/8) Epoch 18, batch 1650, loss[loss=0.1672, simple_loss=0.2635, pruned_loss=0.03548, over 7160.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2722, pruned_loss=0.03852, over 1422186.08 frames.], batch size: 18, lr: 4.11e-04
+2022-04-29 14:07:10,559 INFO [train.py:763] (6/8) Epoch 18, batch 1700, loss[loss=0.1907, simple_loss=0.272, pruned_loss=0.0547, over 7163.00 frames.], tot_loss[loss=0.175, simple_loss=0.2725, pruned_loss=0.03875, over 1422947.25 frames.], batch size: 18, lr: 4.11e-04
+2022-04-29 14:08:17,584 INFO [train.py:763] (6/8) Epoch 18, batch 1750, loss[loss=0.2011, simple_loss=0.2965, pruned_loss=0.05285, over 7148.00 frames.], tot_loss[loss=0.1766, simple_loss=0.274, pruned_loss=0.03962, over 1416377.87 frames.], batch size: 20, lr: 4.10e-04
+2022-04-29 14:09:24,695 INFO [train.py:763] (6/8) Epoch 18, batch 1800, loss[loss=0.1654, simple_loss=0.261, pruned_loss=0.03489, over 7257.00 frames.], tot_loss[loss=0.1769, simple_loss=0.275, pruned_loss=0.03941, over 1416538.02 frames.], batch size: 19, lr: 4.10e-04
+2022-04-29 14:10:32,230 INFO [train.py:763] (6/8) Epoch 18, batch 1850, loss[loss=0.1972, simple_loss=0.2972, pruned_loss=0.0486, over 7304.00 frames.], tot_loss[loss=0.1768, simple_loss=0.275, pruned_loss=0.03927, over 1422363.35 frames.], batch size: 24, lr: 4.10e-04
+2022-04-29 14:11:39,562 INFO [train.py:763] (6/8) Epoch 18, batch 1900, loss[loss=0.1876, simple_loss=0.2896, pruned_loss=0.04274, over 7072.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2745, pruned_loss=0.03935, over 1420543.05 frames.], batch size: 28, lr: 4.10e-04
+2022-04-29 14:12:46,674 INFO [train.py:763] (6/8) Epoch 18, batch 1950, loss[loss=0.1368, simple_loss=0.224, pruned_loss=0.02485, over 7001.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2749, pruned_loss=0.03943, over 1421112.56 frames.], batch size: 16, lr: 4.10e-04
+2022-04-29 14:13:51,991 INFO [train.py:763] (6/8) Epoch 18, batch 2000, loss[loss=0.1717, simple_loss=0.2713, pruned_loss=0.0361, over 7148.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2743, pruned_loss=0.03946, over 1424182.65 frames.], batch size: 20, lr: 4.10e-04
+2022-04-29 14:14:57,425 INFO [train.py:763] (6/8) Epoch 18, batch 2050, loss[loss=0.1909, simple_loss=0.2827, pruned_loss=0.04951, over 7305.00 frames.], tot_loss[loss=0.176, simple_loss=0.2736, pruned_loss=0.03924, over 1424343.52 frames.], batch size: 25, lr: 4.10e-04
+2022-04-29 14:16:02,571 INFO [train.py:763] (6/8) Epoch 18, batch 2100, loss[loss=0.1495, simple_loss=0.2422, pruned_loss=0.02837, over 7155.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2726, pruned_loss=0.03814, over 1424816.69 frames.], batch size: 19, lr: 4.10e-04
+2022-04-29 14:17:08,135 INFO [train.py:763] (6/8) Epoch 18, batch 2150, loss[loss=0.1875, simple_loss=0.2953, pruned_loss=0.03986, over 7217.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2726, pruned_loss=0.0386, over 1421624.69 frames.], batch size: 21, lr: 4.09e-04
+2022-04-29 14:18:13,399 INFO [train.py:763] (6/8) Epoch 18, batch 2200, loss[loss=0.18, simple_loss=0.2973, pruned_loss=0.03136, over 7445.00 frames.], tot_loss[loss=0.174, simple_loss=0.2716, pruned_loss=0.0382, over 1425868.94 frames.], batch size: 22, lr: 4.09e-04
+2022-04-29 14:19:18,571 INFO [train.py:763] (6/8) Epoch 18, batch 2250, loss[loss=0.1646, simple_loss=0.2632, pruned_loss=0.03301, over 6480.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2724, pruned_loss=0.0384, over 1424773.56 frames.], batch size: 37, lr: 4.09e-04
+2022-04-29 14:20:23,889 INFO [train.py:763] (6/8) Epoch 18, batch 2300, loss[loss=0.1875, simple_loss=0.2875, pruned_loss=0.04372, over 7372.00 frames.], tot_loss[loss=0.1742, simple_loss=0.272, pruned_loss=0.03818, over 1426501.00 frames.], batch size: 23, lr: 4.09e-04
+2022-04-29 14:21:28,908 INFO [train.py:763] (6/8) Epoch 18, batch 2350, loss[loss=0.1519, simple_loss=0.2407, pruned_loss=0.03152, over 7274.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2718, pruned_loss=0.03814, over 1423793.55 frames.], batch size: 17, lr: 4.09e-04
+2022-04-29 14:22:34,037 INFO [train.py:763] (6/8) Epoch 18, batch 2400, loss[loss=0.1685, simple_loss=0.2713, pruned_loss=0.03286, over 7150.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2725, pruned_loss=0.03838, over 1419871.17 frames.], batch size: 20, lr: 4.09e-04
+2022-04-29 14:23:41,078 INFO [train.py:763] (6/8) Epoch 18, batch 2450, loss[loss=0.1823, simple_loss=0.2779, pruned_loss=0.04328, over 7147.00 frames.], tot_loss[loss=0.1744, simple_loss=0.272, pruned_loss=0.03835, over 1422074.45 frames.], batch size: 20, lr: 4.09e-04
+2022-04-29 14:24:46,856 INFO [train.py:763] (6/8) Epoch 18, batch 2500, loss[loss=0.1882, simple_loss=0.2838, pruned_loss=0.04633, over 7154.00 frames.], tot_loss[loss=0.175, simple_loss=0.2721, pruned_loss=0.03889, over 1421445.67 frames.], batch size: 26, lr: 4.09e-04
+2022-04-29 14:25:51,852 INFO [train.py:763] (6/8) Epoch 18, batch 2550, loss[loss=0.1863, simple_loss=0.2828, pruned_loss=0.04494, over 7266.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2722, pruned_loss=0.03932, over 1421211.52 frames.], batch size: 24, lr: 4.08e-04
+2022-04-29 14:26:57,012 INFO [train.py:763] (6/8) Epoch 18, batch 2600, loss[loss=0.1589, simple_loss=0.2487, pruned_loss=0.03452, over 6992.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2728, pruned_loss=0.03927, over 1424605.93 frames.], batch size: 16, lr: 4.08e-04
+2022-04-29 14:28:02,332 INFO [train.py:763] (6/8) Epoch 18, batch 2650, loss[loss=0.1942, simple_loss=0.2906, pruned_loss=0.04896, over 7274.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2725, pruned_loss=0.039, over 1426853.30 frames.], batch size: 24, lr: 4.08e-04
+2022-04-29 14:29:08,135 INFO [train.py:763] (6/8) Epoch 18, batch 2700, loss[loss=0.1807, simple_loss=0.2917, pruned_loss=0.0348, over 7312.00 frames.], tot_loss[loss=0.174, simple_loss=0.2713, pruned_loss=0.03832, over 1430302.57 frames.], batch size: 25, lr: 4.08e-04
+2022-04-29 14:30:14,904 INFO [train.py:763] (6/8) Epoch 18, batch 2750, loss[loss=0.1598, simple_loss=0.2616, pruned_loss=0.02899, over 7413.00 frames.], tot_loss[loss=0.1746, simple_loss=0.272, pruned_loss=0.03862, over 1430282.30 frames.], batch size: 21, lr: 4.08e-04
+2022-04-29 14:31:21,338 INFO [train.py:763] (6/8) Epoch 18, batch 2800, loss[loss=0.1799, simple_loss=0.2768, pruned_loss=0.04153, over 7064.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2725, pruned_loss=0.03912, over 1431091.90 frames.], batch size: 18, lr: 4.08e-04
+2022-04-29 14:32:26,508 INFO [train.py:763] (6/8) Epoch 18, batch 2850, loss[loss=0.1682, simple_loss=0.2658, pruned_loss=0.03531, over 7159.00 frames.], tot_loss[loss=0.1745, simple_loss=0.272, pruned_loss=0.03849, over 1427901.72 frames.], batch size: 19, lr: 4.08e-04
+2022-04-29 14:33:31,781 INFO [train.py:763] (6/8) Epoch 18, batch 2900, loss[loss=0.1552, simple_loss=0.2599, pruned_loss=0.02522, over 7182.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2718, pruned_loss=0.03844, over 1425085.67 frames.], batch size: 26, lr: 4.08e-04
+2022-04-29 14:34:37,293 INFO [train.py:763] (6/8) Epoch 18, batch 2950, loss[loss=0.1387, simple_loss=0.2313, pruned_loss=0.02305, over 7271.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2719, pruned_loss=0.03835, over 1430640.78 frames.], batch size: 17, lr: 4.08e-04
+2022-04-29 14:35:43,264 INFO [train.py:763] (6/8) Epoch 18, batch 3000, loss[loss=0.1737, simple_loss=0.2759, pruned_loss=0.0358, over 5316.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2721, pruned_loss=0.03817, over 1431330.93 frames.], batch size: 52, lr: 4.07e-04
+2022-04-29 14:35:43,265 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 14:35:58,559 INFO [train.py:792] (6/8) Epoch 18, validation: loss=0.1668, simple_loss=0.2671, pruned_loss=0.03324, over 698248.00 frames.
+2022-04-29 14:37:05,449 INFO [train.py:763] (6/8) Epoch 18, batch 3050, loss[loss=0.1746, simple_loss=0.2716, pruned_loss=0.03882, over 7194.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2718, pruned_loss=0.03821, over 1432800.16 frames.], batch size: 23, lr: 4.07e-04
+2022-04-29 14:38:12,646 INFO [train.py:763] (6/8) Epoch 18, batch 3100, loss[loss=0.1655, simple_loss=0.2703, pruned_loss=0.03037, over 6512.00 frames.], tot_loss[loss=0.1744, simple_loss=0.272, pruned_loss=0.0384, over 1433786.82 frames.], batch size: 38, lr: 4.07e-04
+2022-04-29 14:39:19,393 INFO [train.py:763] (6/8) Epoch 18, batch 3150, loss[loss=0.1687, simple_loss=0.2574, pruned_loss=0.03995, over 7269.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2725, pruned_loss=0.0386, over 1431099.14 frames.], batch size: 18, lr: 4.07e-04
+2022-04-29 14:40:26,378 INFO [train.py:763] (6/8) Epoch 18, batch 3200, loss[loss=0.1636, simple_loss=0.2565, pruned_loss=0.03531, over 7163.00 frames.], tot_loss[loss=0.1742, simple_loss=0.272, pruned_loss=0.0382, over 1428874.20 frames.], batch size: 19, lr: 4.07e-04
+2022-04-29 14:41:32,520 INFO [train.py:763] (6/8) Epoch 18, batch 3250, loss[loss=0.1628, simple_loss=0.2546, pruned_loss=0.03557, over 7363.00 frames.], tot_loss[loss=0.175, simple_loss=0.273, pruned_loss=0.03851, over 1425773.48 frames.], batch size: 19, lr: 4.07e-04
+2022-04-29 14:42:37,743 INFO [train.py:763] (6/8) Epoch 18, batch 3300, loss[loss=0.1842, simple_loss=0.2871, pruned_loss=0.04062, over 6332.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2736, pruned_loss=0.03863, over 1425556.16 frames.], batch size: 37, lr: 4.07e-04
+2022-04-29 14:43:43,237 INFO [train.py:763] (6/8) Epoch 18, batch 3350, loss[loss=0.1852, simple_loss=0.2826, pruned_loss=0.04391, over 7113.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2727, pruned_loss=0.03835, over 1424534.64 frames.], batch size: 21, lr: 4.07e-04
+2022-04-29 14:44:48,484 INFO [train.py:763] (6/8) Epoch 18, batch 3400, loss[loss=0.1418, simple_loss=0.2386, pruned_loss=0.0225, over 7276.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2726, pruned_loss=0.03813, over 1424685.16 frames.], batch size: 18, lr: 4.06e-04
+2022-04-29 14:45:53,983 INFO [train.py:763] (6/8) Epoch 18, batch 3450, loss[loss=0.1531, simple_loss=0.2516, pruned_loss=0.02731, over 7354.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2713, pruned_loss=0.03784, over 1421624.11 frames.], batch size: 19, lr: 4.06e-04
+2022-04-29 14:46:59,198 INFO [train.py:763] (6/8) Epoch 18, batch 3500, loss[loss=0.1598, simple_loss=0.2582, pruned_loss=0.03064, over 7287.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2715, pruned_loss=0.0382, over 1423990.74 frames.], batch size: 18, lr: 4.06e-04
+2022-04-29 14:48:04,601 INFO [train.py:763] (6/8) Epoch 18, batch 3550, loss[loss=0.1616, simple_loss=0.2528, pruned_loss=0.03517, over 7142.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2716, pruned_loss=0.0384, over 1423822.15 frames.], batch size: 17, lr: 4.06e-04
+2022-04-29 14:49:09,818 INFO [train.py:763] (6/8) Epoch 18, batch 3600, loss[loss=0.1896, simple_loss=0.2829, pruned_loss=0.04819, over 7186.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2731, pruned_loss=0.03932, over 1421121.09 frames.], batch size: 23, lr: 4.06e-04
+2022-04-29 14:50:14,981 INFO [train.py:763] (6/8) Epoch 18, batch 3650, loss[loss=0.1768, simple_loss=0.2752, pruned_loss=0.03916, over 7320.00 frames.], tot_loss[loss=0.176, simple_loss=0.2732, pruned_loss=0.03934, over 1415122.38 frames.], batch size: 20, lr: 4.06e-04
+2022-04-29 14:51:20,201 INFO [train.py:763] (6/8) Epoch 18, batch 3700, loss[loss=0.1865, simple_loss=0.2808, pruned_loss=0.04612, over 7421.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2736, pruned_loss=0.03977, over 1416875.52 frames.], batch size: 21, lr: 4.06e-04
+2022-04-29 14:52:25,584 INFO [train.py:763] (6/8) Epoch 18, batch 3750, loss[loss=0.1804, simple_loss=0.2869, pruned_loss=0.03694, over 7390.00 frames.], tot_loss[loss=0.176, simple_loss=0.273, pruned_loss=0.03952, over 1412918.92 frames.], batch size: 23, lr: 4.06e-04
+2022-04-29 14:53:30,896 INFO [train.py:763] (6/8) Epoch 18, batch 3800, loss[loss=0.1533, simple_loss=0.2473, pruned_loss=0.02965, over 7369.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2727, pruned_loss=0.03909, over 1418688.92 frames.], batch size: 19, lr: 4.06e-04
+2022-04-29 14:54:36,412 INFO [train.py:763] (6/8) Epoch 18, batch 3850, loss[loss=0.1725, simple_loss=0.2527, pruned_loss=0.04621, over 7165.00 frames.], tot_loss[loss=0.1749, simple_loss=0.272, pruned_loss=0.03895, over 1417368.69 frames.], batch size: 18, lr: 4.05e-04
+2022-04-29 14:55:41,216 INFO [train.py:763] (6/8) Epoch 18, batch 3900, loss[loss=0.1787, simple_loss=0.2823, pruned_loss=0.03757, over 7108.00 frames.], tot_loss[loss=0.1748, simple_loss=0.272, pruned_loss=0.03881, over 1414429.10 frames.], batch size: 21, lr: 4.05e-04
+2022-04-29 14:56:46,301 INFO [train.py:763] (6/8) Epoch 18, batch 3950, loss[loss=0.1789, simple_loss=0.2756, pruned_loss=0.04115, over 7153.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2719, pruned_loss=0.03853, over 1416794.51 frames.], batch size: 18, lr: 4.05e-04
+2022-04-29 14:57:51,527 INFO [train.py:763] (6/8) Epoch 18, batch 4000, loss[loss=0.1867, simple_loss=0.2901, pruned_loss=0.0416, over 5723.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2722, pruned_loss=0.03841, over 1418146.93 frames.], batch size: 54, lr: 4.05e-04
+2022-04-29 14:58:57,193 INFO [train.py:763] (6/8) Epoch 18, batch 4050, loss[loss=0.1494, simple_loss=0.2404, pruned_loss=0.02922, over 6807.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2723, pruned_loss=0.03838, over 1416251.81 frames.], batch size: 15, lr: 4.05e-04
+2022-04-29 15:00:03,352 INFO [train.py:763] (6/8) Epoch 18, batch 4100, loss[loss=0.1948, simple_loss=0.2778, pruned_loss=0.05587, over 5395.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2725, pruned_loss=0.03849, over 1416497.12 frames.], batch size: 52, lr: 4.05e-04
+2022-04-29 15:01:09,077 INFO [train.py:763] (6/8) Epoch 18, batch 4150, loss[loss=0.1703, simple_loss=0.2611, pruned_loss=0.03975, over 7390.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2711, pruned_loss=0.0378, over 1421864.03 frames.], batch size: 23, lr: 4.05e-04
+2022-04-29 15:02:16,181 INFO [train.py:763] (6/8) Epoch 18, batch 4200, loss[loss=0.1758, simple_loss=0.2831, pruned_loss=0.03431, over 7201.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2712, pruned_loss=0.03788, over 1420360.47 frames.], batch size: 23, lr: 4.05e-04
+2022-04-29 15:03:23,611 INFO [train.py:763] (6/8) Epoch 18, batch 4250, loss[loss=0.1361, simple_loss=0.2315, pruned_loss=0.02034, over 6773.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2711, pruned_loss=0.03789, over 1419902.36 frames.], batch size: 15, lr: 4.04e-04
+2022-04-29 15:04:28,932 INFO [train.py:763] (6/8) Epoch 18, batch 4300, loss[loss=0.1868, simple_loss=0.2937, pruned_loss=0.03993, over 7124.00 frames.], tot_loss[loss=0.1744, simple_loss=0.272, pruned_loss=0.0384, over 1419778.32 frames.], batch size: 26, lr: 4.04e-04
+2022-04-29 15:05:35,080 INFO [train.py:763] (6/8) Epoch 18, batch 4350, loss[loss=0.1729, simple_loss=0.2672, pruned_loss=0.03927, over 7171.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2715, pruned_loss=0.03854, over 1417212.96 frames.], batch size: 18, lr: 4.04e-04
+2022-04-29 15:06:42,526 INFO [train.py:763] (6/8) Epoch 18, batch 4400, loss[loss=0.2069, simple_loss=0.3051, pruned_loss=0.05429, over 6447.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2709, pruned_loss=0.03837, over 1413750.61 frames.], batch size: 38, lr: 4.04e-04
+2022-04-29 15:07:48,953 INFO [train.py:763] (6/8) Epoch 18, batch 4450, loss[loss=0.1696, simple_loss=0.2527, pruned_loss=0.04321, over 7253.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2699, pruned_loss=0.03826, over 1408024.47 frames.], batch size: 16, lr: 4.04e-04
+2022-04-29 15:08:55,468 INFO [train.py:763] (6/8) Epoch 18, batch 4500, loss[loss=0.1641, simple_loss=0.2756, pruned_loss=0.02635, over 7143.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2715, pruned_loss=0.03912, over 1393637.92 frames.], batch size: 20, lr: 4.04e-04
+2022-04-29 15:10:01,721 INFO [train.py:763] (6/8) Epoch 18, batch 4550, loss[loss=0.1851, simple_loss=0.2815, pruned_loss=0.04433, over 6342.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2707, pruned_loss=0.03926, over 1367192.63 frames.], batch size: 37, lr: 4.04e-04
+2022-04-29 15:11:30,594 INFO [train.py:763] (6/8) Epoch 19, batch 0, loss[loss=0.1652, simple_loss=0.2662, pruned_loss=0.03209, over 7360.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2662, pruned_loss=0.03209, over 7360.00 frames.], batch size: 19, lr: 3.94e-04
+2022-04-29 15:12:36,740 INFO [train.py:763] (6/8) Epoch 19, batch 50, loss[loss=0.1517, simple_loss=0.2453, pruned_loss=0.029, over 7279.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2741, pruned_loss=0.03878, over 321416.92 frames.], batch size: 18, lr: 3.94e-04
+2022-04-29 15:13:42,680 INFO [train.py:763] (6/8) Epoch 19, batch 100, loss[loss=0.2156, simple_loss=0.3064, pruned_loss=0.06241, over 5475.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2719, pruned_loss=0.03801, over 566553.84 frames.], batch size: 53, lr: 3.94e-04
+2022-04-29 15:14:48,876 INFO [train.py:763] (6/8) Epoch 19, batch 150, loss[loss=0.1956, simple_loss=0.2977, pruned_loss=0.04673, over 7318.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2744, pruned_loss=0.0382, over 756434.00 frames.], batch size: 21, lr: 3.94e-04
+2022-04-29 15:15:54,342 INFO [train.py:763] (6/8) Epoch 19, batch 200, loss[loss=0.1635, simple_loss=0.2681, pruned_loss=0.02944, over 7335.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2732, pruned_loss=0.03761, over 903397.45 frames.], batch size: 22, lr: 3.93e-04
+2022-04-29 15:17:00,300 INFO [train.py:763] (6/8) Epoch 19, batch 250, loss[loss=0.177, simple_loss=0.2922, pruned_loss=0.03087, over 7347.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2719, pruned_loss=0.03774, over 1022652.46 frames.], batch size: 22, lr: 3.93e-04
+2022-04-29 15:18:06,655 INFO [train.py:763] (6/8) Epoch 19, batch 300, loss[loss=0.2118, simple_loss=0.2984, pruned_loss=0.06259, over 7201.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2728, pruned_loss=0.03785, over 1112132.26 frames.], batch size: 23, lr: 3.93e-04
+2022-04-29 15:19:12,754 INFO [train.py:763] (6/8) Epoch 19, batch 350, loss[loss=0.1478, simple_loss=0.255, pruned_loss=0.02027, over 7140.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2727, pruned_loss=0.03744, over 1184519.87 frames.], batch size: 20, lr: 3.93e-04
+2022-04-29 15:20:18,123 INFO [train.py:763] (6/8) Epoch 19, batch 400, loss[loss=0.1724, simple_loss=0.2747, pruned_loss=0.03503, over 7146.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2736, pruned_loss=0.03778, over 1237615.82 frames.], batch size: 20, lr: 3.93e-04
+2022-04-29 15:21:23,457 INFO [train.py:763] (6/8) Epoch 19, batch 450, loss[loss=0.1728, simple_loss=0.2747, pruned_loss=0.03544, over 7369.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2734, pruned_loss=0.0374, over 1274387.35 frames.], batch size: 23, lr: 3.93e-04
+2022-04-29 15:22:28,667 INFO [train.py:763] (6/8) Epoch 19, batch 500, loss[loss=0.1839, simple_loss=0.2915, pruned_loss=0.03819, over 7230.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2727, pruned_loss=0.03703, over 1306410.92 frames.], batch size: 21, lr: 3.93e-04
+2022-04-29 15:23:34,244 INFO [train.py:763] (6/8) Epoch 19, batch 550, loss[loss=0.1699, simple_loss=0.2808, pruned_loss=0.02949, over 6796.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2726, pruned_loss=0.0376, over 1332169.12 frames.], batch size: 31, lr: 3.93e-04
+2022-04-29 15:24:40,468 INFO [train.py:763] (6/8) Epoch 19, batch 600, loss[loss=0.145, simple_loss=0.2461, pruned_loss=0.02198, over 7161.00 frames.], tot_loss[loss=0.172, simple_loss=0.2703, pruned_loss=0.03686, over 1355337.79 frames.], batch size: 18, lr: 3.93e-04
+2022-04-29 15:25:45,943 INFO [train.py:763] (6/8) Epoch 19, batch 650, loss[loss=0.1649, simple_loss=0.2596, pruned_loss=0.03504, over 7160.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2701, pruned_loss=0.0371, over 1369301.39 frames.], batch size: 18, lr: 3.92e-04
+2022-04-29 15:26:51,171 INFO [train.py:763] (6/8) Epoch 19, batch 700, loss[loss=0.1408, simple_loss=0.2423, pruned_loss=0.01967, over 7226.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2712, pruned_loss=0.03724, over 1382793.70 frames.], batch size: 20, lr: 3.92e-04
+2022-04-29 15:27:56,785 INFO [train.py:763] (6/8) Epoch 19, batch 750, loss[loss=0.176, simple_loss=0.28, pruned_loss=0.03603, over 7308.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2706, pruned_loss=0.03733, over 1393616.28 frames.], batch size: 25, lr: 3.92e-04
+2022-04-29 15:29:03,458 INFO [train.py:763] (6/8) Epoch 19, batch 800, loss[loss=0.1419, simple_loss=0.2333, pruned_loss=0.02524, over 7411.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2707, pruned_loss=0.03746, over 1403075.64 frames.], batch size: 18, lr: 3.92e-04
+2022-04-29 15:30:19,518 INFO [train.py:763] (6/8) Epoch 19, batch 850, loss[loss=0.1906, simple_loss=0.2896, pruned_loss=0.0458, over 7007.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2713, pruned_loss=0.03785, over 1410965.92 frames.], batch size: 28, lr: 3.92e-04
+2022-04-29 15:31:25,290 INFO [train.py:763] (6/8) Epoch 19, batch 900, loss[loss=0.1922, simple_loss=0.2786, pruned_loss=0.05292, over 7358.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2703, pruned_loss=0.03741, over 1416086.54 frames.], batch size: 19, lr: 3.92e-04
+2022-04-29 15:32:30,747 INFO [train.py:763] (6/8) Epoch 19, batch 950, loss[loss=0.1748, simple_loss=0.2906, pruned_loss=0.02948, over 7239.00 frames.], tot_loss[loss=0.1728, simple_loss=0.271, pruned_loss=0.03732, over 1420341.39 frames.], batch size: 20, lr: 3.92e-04
+2022-04-29 15:33:36,033 INFO [train.py:763] (6/8) Epoch 19, batch 1000, loss[loss=0.1877, simple_loss=0.2907, pruned_loss=0.04238, over 7305.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2709, pruned_loss=0.0373, over 1420551.41 frames.], batch size: 24, lr: 3.92e-04
+2022-04-29 15:34:41,370 INFO [train.py:763] (6/8) Epoch 19, batch 1050, loss[loss=0.1617, simple_loss=0.26, pruned_loss=0.03165, over 7206.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2712, pruned_loss=0.03746, over 1420179.09 frames.], batch size: 22, lr: 3.92e-04
+2022-04-29 15:35:47,012 INFO [train.py:763] (6/8) Epoch 19, batch 1100, loss[loss=0.2156, simple_loss=0.3202, pruned_loss=0.05548, over 7200.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2712, pruned_loss=0.0377, over 1416504.84 frames.], batch size: 22, lr: 3.91e-04
+2022-04-29 15:36:52,332 INFO [train.py:763] (6/8) Epoch 19, batch 1150, loss[loss=0.1962, simple_loss=0.2915, pruned_loss=0.05046, over 7291.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2716, pruned_loss=0.03764, over 1419980.64 frames.], batch size: 24, lr: 3.91e-04
+2022-04-29 15:38:08,756 INFO [train.py:763] (6/8) Epoch 19, batch 1200, loss[loss=0.1702, simple_loss=0.2758, pruned_loss=0.03229, over 7328.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2705, pruned_loss=0.03747, over 1424469.91 frames.], batch size: 22, lr: 3.91e-04
+2022-04-29 15:39:14,191 INFO [train.py:763] (6/8) Epoch 19, batch 1250, loss[loss=0.1778, simple_loss=0.2634, pruned_loss=0.0461, over 7127.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2705, pruned_loss=0.03745, over 1424955.00 frames.], batch size: 17, lr: 3.91e-04
+2022-04-29 15:40:19,877 INFO [train.py:763] (6/8) Epoch 19, batch 1300, loss[loss=0.1715, simple_loss=0.2688, pruned_loss=0.03708, over 7109.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2704, pruned_loss=0.03758, over 1426909.16 frames.], batch size: 21, lr: 3.91e-04
+2022-04-29 15:41:25,080 INFO [train.py:763] (6/8) Epoch 19, batch 1350, loss[loss=0.1957, simple_loss=0.3004, pruned_loss=0.04551, over 7199.00 frames.], tot_loss[loss=0.1734, simple_loss=0.271, pruned_loss=0.03789, over 1428927.92 frames.], batch size: 22, lr: 3.91e-04
+2022-04-29 15:42:30,864 INFO [train.py:763] (6/8) Epoch 19, batch 1400, loss[loss=0.1828, simple_loss=0.2803, pruned_loss=0.04263, over 7152.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2713, pruned_loss=0.03809, over 1430806.15 frames.], batch size: 26, lr: 3.91e-04
+2022-04-29 15:43:46,246 INFO [train.py:763] (6/8) Epoch 19, batch 1450, loss[loss=0.1739, simple_loss=0.2775, pruned_loss=0.03515, over 7181.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2724, pruned_loss=0.03857, over 1429738.38 frames.], batch size: 26, lr: 3.91e-04
+2022-04-29 15:45:09,721 INFO [train.py:763] (6/8) Epoch 19, batch 1500, loss[loss=0.2189, simple_loss=0.3078, pruned_loss=0.06498, over 7384.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2728, pruned_loss=0.03873, over 1427758.31 frames.], batch size: 23, lr: 3.91e-04
+2022-04-29 15:46:15,427 INFO [train.py:763] (6/8) Epoch 19, batch 1550, loss[loss=0.18, simple_loss=0.273, pruned_loss=0.04349, over 7432.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2715, pruned_loss=0.03808, over 1429711.04 frames.], batch size: 20, lr: 3.91e-04
+2022-04-29 15:47:30,077 INFO [train.py:763] (6/8) Epoch 19, batch 1600, loss[loss=0.1844, simple_loss=0.29, pruned_loss=0.03937, over 7347.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2714, pruned_loss=0.03775, over 1424340.07 frames.], batch size: 22, lr: 3.90e-04
+2022-04-29 15:48:53,936 INFO [train.py:763] (6/8) Epoch 19, batch 1650, loss[loss=0.1619, simple_loss=0.2627, pruned_loss=0.03056, over 7180.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2718, pruned_loss=0.03798, over 1421423.46 frames.], batch size: 23, lr: 3.90e-04
+2022-04-29 15:50:08,828 INFO [train.py:763] (6/8) Epoch 19, batch 1700, loss[loss=0.1473, simple_loss=0.251, pruned_loss=0.02176, over 7156.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2721, pruned_loss=0.03789, over 1420769.60 frames.], batch size: 19, lr: 3.90e-04
+2022-04-29 15:51:14,401 INFO [train.py:763] (6/8) Epoch 19, batch 1750, loss[loss=0.1642, simple_loss=0.2747, pruned_loss=0.02682, over 7337.00 frames.], tot_loss[loss=0.1739, simple_loss=0.272, pruned_loss=0.03793, over 1425931.92 frames.], batch size: 22, lr: 3.90e-04
+2022-04-29 15:52:20,000 INFO [train.py:763] (6/8) Epoch 19, batch 1800, loss[loss=0.1783, simple_loss=0.281, pruned_loss=0.03784, over 7297.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2712, pruned_loss=0.03721, over 1425593.56 frames.], batch size: 25, lr: 3.90e-04
+2022-04-29 15:53:25,557 INFO [train.py:763] (6/8) Epoch 19, batch 1850, loss[loss=0.1483, simple_loss=0.2419, pruned_loss=0.02737, over 7070.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2708, pruned_loss=0.03708, over 1428242.42 frames.], batch size: 18, lr: 3.90e-04
+2022-04-29 15:54:30,871 INFO [train.py:763] (6/8) Epoch 19, batch 1900, loss[loss=0.1886, simple_loss=0.2864, pruned_loss=0.04536, over 7234.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2718, pruned_loss=0.03722, over 1428747.82 frames.], batch size: 20, lr: 3.90e-04
+2022-04-29 15:55:38,245 INFO [train.py:763] (6/8) Epoch 19, batch 1950, loss[loss=0.1876, simple_loss=0.2885, pruned_loss=0.04332, over 6454.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2711, pruned_loss=0.03713, over 1428861.38 frames.], batch size: 38, lr: 3.90e-04
+2022-04-29 15:56:45,559 INFO [train.py:763] (6/8) Epoch 19, batch 2000, loss[loss=0.1709, simple_loss=0.2792, pruned_loss=0.03129, over 7228.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2706, pruned_loss=0.03738, over 1429730.76 frames.], batch size: 20, lr: 3.90e-04
+2022-04-29 15:57:52,838 INFO [train.py:763] (6/8) Epoch 19, batch 2050, loss[loss=0.17, simple_loss=0.2724, pruned_loss=0.03376, over 7222.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2706, pruned_loss=0.03761, over 1429557.45 frames.], batch size: 21, lr: 3.89e-04
+2022-04-29 15:58:58,692 INFO [train.py:763] (6/8) Epoch 19, batch 2100, loss[loss=0.156, simple_loss=0.2531, pruned_loss=0.02946, over 7445.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2702, pruned_loss=0.03746, over 1431528.34 frames.], batch size: 20, lr: 3.89e-04
+2022-04-29 16:00:05,544 INFO [train.py:763] (6/8) Epoch 19, batch 2150, loss[loss=0.2043, simple_loss=0.3006, pruned_loss=0.05398, over 7214.00 frames.], tot_loss[loss=0.1732, simple_loss=0.271, pruned_loss=0.03773, over 1425677.63 frames.], batch size: 22, lr: 3.89e-04
+2022-04-29 16:01:11,304 INFO [train.py:763] (6/8) Epoch 19, batch 2200, loss[loss=0.1655, simple_loss=0.2604, pruned_loss=0.03533, over 6801.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2709, pruned_loss=0.0377, over 1420821.70 frames.], batch size: 15, lr: 3.89e-04
+2022-04-29 16:02:17,297 INFO [train.py:763] (6/8) Epoch 19, batch 2250, loss[loss=0.1633, simple_loss=0.2638, pruned_loss=0.03141, over 7158.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2703, pruned_loss=0.03754, over 1423323.19 frames.], batch size: 20, lr: 3.89e-04
+2022-04-29 16:03:23,076 INFO [train.py:763] (6/8) Epoch 19, batch 2300, loss[loss=0.1888, simple_loss=0.2813, pruned_loss=0.04811, over 7371.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2701, pruned_loss=0.03786, over 1423078.68 frames.], batch size: 23, lr: 3.89e-04
+2022-04-29 16:04:28,769 INFO [train.py:763] (6/8) Epoch 19, batch 2350, loss[loss=0.1757, simple_loss=0.2672, pruned_loss=0.04213, over 7318.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2708, pruned_loss=0.03791, over 1421977.33 frames.], batch size: 21, lr: 3.89e-04
+2022-04-29 16:05:34,129 INFO [train.py:763] (6/8) Epoch 19, batch 2400, loss[loss=0.1637, simple_loss=0.264, pruned_loss=0.03175, over 7418.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2701, pruned_loss=0.03778, over 1424025.57 frames.], batch size: 20, lr: 3.89e-04
+2022-04-29 16:06:39,695 INFO [train.py:763] (6/8) Epoch 19, batch 2450, loss[loss=0.1956, simple_loss=0.2939, pruned_loss=0.04859, over 7159.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2699, pruned_loss=0.03789, over 1426818.81 frames.], batch size: 28, lr: 3.89e-04
+2022-04-29 16:07:45,463 INFO [train.py:763] (6/8) Epoch 19, batch 2500, loss[loss=0.1928, simple_loss=0.2925, pruned_loss=0.04652, over 7167.00 frames.], tot_loss[loss=0.172, simple_loss=0.2691, pruned_loss=0.03749, over 1425675.37 frames.], batch size: 26, lr: 3.88e-04
+2022-04-29 16:08:50,997 INFO [train.py:763] (6/8) Epoch 19, batch 2550, loss[loss=0.1686, simple_loss=0.265, pruned_loss=0.03603, over 7329.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2694, pruned_loss=0.03774, over 1423719.30 frames.], batch size: 20, lr: 3.88e-04
+2022-04-29 16:09:56,809 INFO [train.py:763] (6/8) Epoch 19, batch 2600, loss[loss=0.2034, simple_loss=0.3012, pruned_loss=0.05274, over 6702.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2709, pruned_loss=0.0383, over 1425008.16 frames.], batch size: 31, lr: 3.88e-04
+2022-04-29 16:11:03,366 INFO [train.py:763] (6/8) Epoch 19, batch 2650, loss[loss=0.147, simple_loss=0.2369, pruned_loss=0.02855, over 7006.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2699, pruned_loss=0.03758, over 1426438.69 frames.], batch size: 16, lr: 3.88e-04
+2022-04-29 16:12:10,011 INFO [train.py:763] (6/8) Epoch 19, batch 2700, loss[loss=0.1856, simple_loss=0.2839, pruned_loss=0.0436, over 7388.00 frames.], tot_loss[loss=0.1719, simple_loss=0.269, pruned_loss=0.03741, over 1427014.77 frames.], batch size: 23, lr: 3.88e-04
+2022-04-29 16:13:17,139 INFO [train.py:763] (6/8) Epoch 19, batch 2750, loss[loss=0.1958, simple_loss=0.284, pruned_loss=0.05385, over 7198.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2697, pruned_loss=0.03737, over 1426173.41 frames.], batch size: 23, lr: 3.88e-04
+2022-04-29 16:14:22,706 INFO [train.py:763] (6/8) Epoch 19, batch 2800, loss[loss=0.1714, simple_loss=0.2669, pruned_loss=0.03798, over 7159.00 frames.], tot_loss[loss=0.1731, simple_loss=0.271, pruned_loss=0.03764, over 1430180.78 frames.], batch size: 18, lr: 3.88e-04
+2022-04-29 16:15:28,762 INFO [train.py:763] (6/8) Epoch 19, batch 2850, loss[loss=0.1785, simple_loss=0.2798, pruned_loss=0.03858, over 7411.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2711, pruned_loss=0.0376, over 1432025.92 frames.], batch size: 21, lr: 3.88e-04
+2022-04-29 16:16:34,848 INFO [train.py:763] (6/8) Epoch 19, batch 2900, loss[loss=0.1941, simple_loss=0.2907, pruned_loss=0.04879, over 7159.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2698, pruned_loss=0.03718, over 1427703.92 frames.], batch size: 26, lr: 3.88e-04
+2022-04-29 16:17:40,410 INFO [train.py:763] (6/8) Epoch 19, batch 2950, loss[loss=0.1714, simple_loss=0.2781, pruned_loss=0.03229, over 7243.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2705, pruned_loss=0.0374, over 1431538.81 frames.], batch size: 20, lr: 3.87e-04
+2022-04-29 16:18:45,957 INFO [train.py:763] (6/8) Epoch 19, batch 3000, loss[loss=0.1958, simple_loss=0.302, pruned_loss=0.04485, over 7379.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2715, pruned_loss=0.03744, over 1430793.77 frames.], batch size: 23, lr: 3.87e-04
+2022-04-29 16:18:45,958 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 16:19:01,554 INFO [train.py:792] (6/8) Epoch 19, validation: loss=0.1668, simple_loss=0.2663, pruned_loss=0.03363, over 698248.00 frames.
+2022-04-29 16:20:06,921 INFO [train.py:763] (6/8) Epoch 19, batch 3050, loss[loss=0.1597, simple_loss=0.2573, pruned_loss=0.03104, over 7157.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2706, pruned_loss=0.03744, over 1432282.49 frames.], batch size: 19, lr: 3.87e-04
+2022-04-29 16:21:12,182 INFO [train.py:763] (6/8) Epoch 19, batch 3100, loss[loss=0.1728, simple_loss=0.2804, pruned_loss=0.03264, over 7106.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2712, pruned_loss=0.03715, over 1432447.14 frames.], batch size: 21, lr: 3.87e-04
+2022-04-29 16:22:17,533 INFO [train.py:763] (6/8) Epoch 19, batch 3150, loss[loss=0.1607, simple_loss=0.2535, pruned_loss=0.0339, over 7286.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2719, pruned_loss=0.03752, over 1432887.66 frames.], batch size: 18, lr: 3.87e-04
+2022-04-29 16:23:23,021 INFO [train.py:763] (6/8) Epoch 19, batch 3200, loss[loss=0.1968, simple_loss=0.2895, pruned_loss=0.05203, over 6711.00 frames.], tot_loss[loss=0.173, simple_loss=0.2714, pruned_loss=0.03734, over 1432052.07 frames.], batch size: 31, lr: 3.87e-04
+2022-04-29 16:24:28,067 INFO [train.py:763] (6/8) Epoch 19, batch 3250, loss[loss=0.1476, simple_loss=0.2438, pruned_loss=0.0257, over 7071.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2711, pruned_loss=0.03734, over 1428561.55 frames.], batch size: 18, lr: 3.87e-04
+2022-04-29 16:25:34,720 INFO [train.py:763] (6/8) Epoch 19, batch 3300, loss[loss=0.1593, simple_loss=0.254, pruned_loss=0.03227, over 7139.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2706, pruned_loss=0.03729, over 1426935.56 frames.], batch size: 17, lr: 3.87e-04
+2022-04-29 16:26:41,822 INFO [train.py:763] (6/8) Epoch 19, batch 3350, loss[loss=0.1941, simple_loss=0.2958, pruned_loss=0.04621, over 7147.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2705, pruned_loss=0.03751, over 1427120.05 frames.], batch size: 20, lr: 3.87e-04
+2022-04-29 16:27:47,543 INFO [train.py:763] (6/8) Epoch 19, batch 3400, loss[loss=0.1389, simple_loss=0.2375, pruned_loss=0.02015, over 7281.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2708, pruned_loss=0.0378, over 1426455.61 frames.], batch size: 17, lr: 3.87e-04
+2022-04-29 16:28:53,016 INFO [train.py:763] (6/8) Epoch 19, batch 3450, loss[loss=0.1519, simple_loss=0.2607, pruned_loss=0.02153, over 7239.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2719, pruned_loss=0.03841, over 1425322.32 frames.], batch size: 20, lr: 3.86e-04
+2022-04-29 16:29:58,522 INFO [train.py:763] (6/8) Epoch 19, batch 3500, loss[loss=0.1439, simple_loss=0.2389, pruned_loss=0.02448, over 7265.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2717, pruned_loss=0.03821, over 1424118.81 frames.], batch size: 19, lr: 3.86e-04
+2022-04-29 16:31:03,661 INFO [train.py:763] (6/8) Epoch 19, batch 3550, loss[loss=0.1677, simple_loss=0.2761, pruned_loss=0.0297, over 7115.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2722, pruned_loss=0.03832, over 1427381.42 frames.], batch size: 21, lr: 3.86e-04
+2022-04-29 16:32:09,192 INFO [train.py:763] (6/8) Epoch 19, batch 3600, loss[loss=0.1732, simple_loss=0.2839, pruned_loss=0.03119, over 7192.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2711, pruned_loss=0.03803, over 1429335.00 frames.], batch size: 23, lr: 3.86e-04
+2022-04-29 16:33:15,438 INFO [train.py:763] (6/8) Epoch 19, batch 3650, loss[loss=0.1743, simple_loss=0.2904, pruned_loss=0.02907, over 7314.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2708, pruned_loss=0.03767, over 1430314.74 frames.], batch size: 21, lr: 3.86e-04
+2022-04-29 16:34:21,093 INFO [train.py:763] (6/8) Epoch 19, batch 3700, loss[loss=0.144, simple_loss=0.2463, pruned_loss=0.02081, over 7149.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2706, pruned_loss=0.03764, over 1432530.31 frames.], batch size: 18, lr: 3.86e-04
+2022-04-29 16:35:26,771 INFO [train.py:763] (6/8) Epoch 19, batch 3750, loss[loss=0.1993, simple_loss=0.2958, pruned_loss=0.05141, over 7098.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2706, pruned_loss=0.0378, over 1426017.76 frames.], batch size: 28, lr: 3.86e-04
+2022-04-29 16:36:32,308 INFO [train.py:763] (6/8) Epoch 19, batch 3800, loss[loss=0.1492, simple_loss=0.2504, pruned_loss=0.02401, over 7322.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2703, pruned_loss=0.03748, over 1421643.10 frames.], batch size: 20, lr: 3.86e-04
+2022-04-29 16:37:37,907 INFO [train.py:763] (6/8) Epoch 19, batch 3850, loss[loss=0.1516, simple_loss=0.2408, pruned_loss=0.03125, over 7275.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2699, pruned_loss=0.03745, over 1419513.63 frames.], batch size: 17, lr: 3.86e-04
+2022-04-29 16:38:44,167 INFO [train.py:763] (6/8) Epoch 19, batch 3900, loss[loss=0.1597, simple_loss=0.2598, pruned_loss=0.02982, over 7109.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2705, pruned_loss=0.03741, over 1417070.10 frames.], batch size: 21, lr: 3.85e-04
+2022-04-29 16:39:50,749 INFO [train.py:763] (6/8) Epoch 19, batch 3950, loss[loss=0.1692, simple_loss=0.2683, pruned_loss=0.03501, over 7335.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2699, pruned_loss=0.03736, over 1411370.30 frames.], batch size: 20, lr: 3.85e-04
+2022-04-29 16:40:57,113 INFO [train.py:763] (6/8) Epoch 19, batch 4000, loss[loss=0.1321, simple_loss=0.2355, pruned_loss=0.01439, over 7160.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2699, pruned_loss=0.03739, over 1408900.24 frames.], batch size: 18, lr: 3.85e-04
+2022-04-29 16:42:03,327 INFO [train.py:763] (6/8) Epoch 19, batch 4050, loss[loss=0.1516, simple_loss=0.2482, pruned_loss=0.02756, over 7327.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2697, pruned_loss=0.03718, over 1406637.80 frames.], batch size: 20, lr: 3.85e-04
+2022-04-29 16:43:09,190 INFO [train.py:763] (6/8) Epoch 19, batch 4100, loss[loss=0.1826, simple_loss=0.2694, pruned_loss=0.04791, over 7280.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2695, pruned_loss=0.03717, over 1407748.18 frames.], batch size: 18, lr: 3.85e-04
+2022-04-29 16:44:14,861 INFO [train.py:763] (6/8) Epoch 19, batch 4150, loss[loss=0.1532, simple_loss=0.2539, pruned_loss=0.02625, over 7057.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2686, pruned_loss=0.03691, over 1411056.89 frames.], batch size: 18, lr: 3.85e-04
+2022-04-29 16:45:20,204 INFO [train.py:763] (6/8) Epoch 19, batch 4200, loss[loss=0.1579, simple_loss=0.2411, pruned_loss=0.03734, over 6774.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2696, pruned_loss=0.03744, over 1406319.76 frames.], batch size: 15, lr: 3.85e-04
+2022-04-29 16:46:26,003 INFO [train.py:763] (6/8) Epoch 19, batch 4250, loss[loss=0.1804, simple_loss=0.2806, pruned_loss=0.04012, over 7191.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2682, pruned_loss=0.03703, over 1403181.70 frames.], batch size: 23, lr: 3.85e-04
+2022-04-29 16:47:31,496 INFO [train.py:763] (6/8) Epoch 19, batch 4300, loss[loss=0.1622, simple_loss=0.263, pruned_loss=0.03073, over 7225.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2686, pruned_loss=0.03692, over 1400939.57 frames.], batch size: 21, lr: 3.85e-04
+2022-04-29 16:48:37,209 INFO [train.py:763] (6/8) Epoch 19, batch 4350, loss[loss=0.1878, simple_loss=0.2722, pruned_loss=0.05165, over 5289.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2675, pruned_loss=0.03658, over 1404901.32 frames.], batch size: 53, lr: 3.84e-04
+2022-04-29 16:49:42,593 INFO [train.py:763] (6/8) Epoch 19, batch 4400, loss[loss=0.1835, simple_loss=0.2774, pruned_loss=0.04482, over 7159.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2678, pruned_loss=0.03677, over 1399504.49 frames.], batch size: 19, lr: 3.84e-04
+2022-04-29 16:50:47,789 INFO [train.py:763] (6/8) Epoch 19, batch 4450, loss[loss=0.1444, simple_loss=0.2339, pruned_loss=0.02741, over 7238.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2674, pruned_loss=0.03685, over 1390214.02 frames.], batch size: 16, lr: 3.84e-04
+2022-04-29 16:51:52,275 INFO [train.py:763] (6/8) Epoch 19, batch 4500, loss[loss=0.1907, simple_loss=0.2875, pruned_loss=0.04695, over 7201.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2697, pruned_loss=0.0375, over 1383095.72 frames.], batch size: 23, lr: 3.84e-04
+2022-04-29 16:52:57,055 INFO [train.py:763] (6/8) Epoch 19, batch 4550, loss[loss=0.1603, simple_loss=0.2611, pruned_loss=0.02979, over 6649.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2724, pruned_loss=0.03902, over 1338191.68 frames.], batch size: 38, lr: 3.84e-04
+2022-04-29 16:54:25,841 INFO [train.py:763] (6/8) Epoch 20, batch 0, loss[loss=0.157, simple_loss=0.2408, pruned_loss=0.03662, over 7002.00 frames.], tot_loss[loss=0.157, simple_loss=0.2408, pruned_loss=0.03662, over 7002.00 frames.], batch size: 16, lr: 3.75e-04
+2022-04-29 16:55:32,594 INFO [train.py:763] (6/8) Epoch 20, batch 50, loss[loss=0.1525, simple_loss=0.2591, pruned_loss=0.02294, over 6446.00 frames.], tot_loss[loss=0.171, simple_loss=0.2708, pruned_loss=0.0356, over 322586.32 frames.], batch size: 38, lr: 3.75e-04
+2022-04-29 16:56:38,005 INFO [train.py:763] (6/8) Epoch 20, batch 100, loss[loss=0.1439, simple_loss=0.2352, pruned_loss=0.02632, over 6814.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2698, pruned_loss=0.03479, over 566517.45 frames.], batch size: 15, lr: 3.75e-04
+2022-04-29 16:57:44,564 INFO [train.py:763] (6/8) Epoch 20, batch 150, loss[loss=0.1508, simple_loss=0.2402, pruned_loss=0.03068, over 7152.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2688, pruned_loss=0.03538, over 755886.48 frames.], batch size: 18, lr: 3.75e-04
+2022-04-29 16:58:49,752 INFO [train.py:763] (6/8) Epoch 20, batch 200, loss[loss=0.1661, simple_loss=0.2744, pruned_loss=0.02894, over 6826.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2713, pruned_loss=0.0367, over 901310.17 frames.], batch size: 31, lr: 3.75e-04
+2022-04-29 16:59:55,580 INFO [train.py:763] (6/8) Epoch 20, batch 250, loss[loss=0.1612, simple_loss=0.2579, pruned_loss=0.03219, over 7162.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2705, pruned_loss=0.03639, over 1013650.19 frames.], batch size: 19, lr: 3.75e-04
+2022-04-29 17:01:00,764 INFO [train.py:763] (6/8) Epoch 20, batch 300, loss[loss=0.1425, simple_loss=0.2426, pruned_loss=0.02122, over 7283.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2705, pruned_loss=0.03681, over 1102469.08 frames.], batch size: 18, lr: 3.75e-04
+2022-04-29 17:02:05,608 INFO [train.py:763] (6/8) Epoch 20, batch 350, loss[loss=0.1345, simple_loss=0.2337, pruned_loss=0.01767, over 7255.00 frames.], tot_loss[loss=0.172, simple_loss=0.2708, pruned_loss=0.03665, over 1170392.92 frames.], batch size: 19, lr: 3.74e-04
+2022-04-29 17:03:10,959 INFO [train.py:763] (6/8) Epoch 20, batch 400, loss[loss=0.1758, simple_loss=0.2741, pruned_loss=0.0388, over 7063.00 frames.], tot_loss[loss=0.1705, simple_loss=0.269, pruned_loss=0.03601, over 1229312.99 frames.], batch size: 18, lr: 3.74e-04
+2022-04-29 17:04:16,935 INFO [train.py:763] (6/8) Epoch 20, batch 450, loss[loss=0.1601, simple_loss=0.2506, pruned_loss=0.03483, over 7062.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2693, pruned_loss=0.03651, over 1272342.93 frames.], batch size: 18, lr: 3.74e-04
+2022-04-29 17:05:22,376 INFO [train.py:763] (6/8) Epoch 20, batch 500, loss[loss=0.1894, simple_loss=0.2892, pruned_loss=0.04485, over 6954.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2693, pruned_loss=0.03653, over 1310655.15 frames.], batch size: 28, lr: 3.74e-04
+2022-04-29 17:06:27,717 INFO [train.py:763] (6/8) Epoch 20, batch 550, loss[loss=0.1328, simple_loss=0.2191, pruned_loss=0.02327, over 7201.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2676, pruned_loss=0.03609, over 1337146.07 frames.], batch size: 16, lr: 3.74e-04
+2022-04-29 17:07:34,498 INFO [train.py:763] (6/8) Epoch 20, batch 600, loss[loss=0.1683, simple_loss=0.2796, pruned_loss=0.02846, over 7217.00 frames.], tot_loss[loss=0.17, simple_loss=0.2681, pruned_loss=0.03594, over 1356202.95 frames.], batch size: 22, lr: 3.74e-04
+2022-04-29 17:08:41,620 INFO [train.py:763] (6/8) Epoch 20, batch 650, loss[loss=0.1737, simple_loss=0.2658, pruned_loss=0.0408, over 7136.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2667, pruned_loss=0.03538, over 1370131.41 frames.], batch size: 17, lr: 3.74e-04
+2022-04-29 17:09:47,494 INFO [train.py:763] (6/8) Epoch 20, batch 700, loss[loss=0.183, simple_loss=0.2916, pruned_loss=0.0372, over 7227.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2679, pruned_loss=0.03574, over 1379774.94 frames.], batch size: 20, lr: 3.74e-04
+2022-04-29 17:10:53,619 INFO [train.py:763] (6/8) Epoch 20, batch 750, loss[loss=0.1565, simple_loss=0.2499, pruned_loss=0.0315, over 7397.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2686, pruned_loss=0.03624, over 1385707.05 frames.], batch size: 18, lr: 3.74e-04
+2022-04-29 17:11:58,917 INFO [train.py:763] (6/8) Epoch 20, batch 800, loss[loss=0.161, simple_loss=0.2527, pruned_loss=0.03465, over 7239.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2681, pruned_loss=0.03653, over 1384564.54 frames.], batch size: 20, lr: 3.73e-04
+2022-04-29 17:13:05,458 INFO [train.py:763] (6/8) Epoch 20, batch 850, loss[loss=0.2045, simple_loss=0.2975, pruned_loss=0.05575, over 7295.00 frames.], tot_loss[loss=0.17, simple_loss=0.2675, pruned_loss=0.03623, over 1391807.17 frames.], batch size: 25, lr: 3.73e-04
+2022-04-29 17:14:10,907 INFO [train.py:763] (6/8) Epoch 20, batch 900, loss[loss=0.1761, simple_loss=0.2817, pruned_loss=0.0352, over 7231.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2671, pruned_loss=0.03623, over 1400348.36 frames.], batch size: 20, lr: 3.73e-04
+2022-04-29 17:15:15,947 INFO [train.py:763] (6/8) Epoch 20, batch 950, loss[loss=0.1733, simple_loss=0.2732, pruned_loss=0.03672, over 7338.00 frames.], tot_loss[loss=0.17, simple_loss=0.2675, pruned_loss=0.03624, over 1406091.88 frames.], batch size: 22, lr: 3.73e-04
+2022-04-29 17:16:21,951 INFO [train.py:763] (6/8) Epoch 20, batch 1000, loss[loss=0.1907, simple_loss=0.2915, pruned_loss=0.04492, over 7195.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2685, pruned_loss=0.03662, over 1405876.81 frames.], batch size: 23, lr: 3.73e-04
+2022-04-29 17:17:26,878 INFO [train.py:763] (6/8) Epoch 20, batch 1050, loss[loss=0.1626, simple_loss=0.2762, pruned_loss=0.02454, over 7423.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2698, pruned_loss=0.03678, over 1406489.35 frames.], batch size: 21, lr: 3.73e-04
+2022-04-29 17:18:32,322 INFO [train.py:763] (6/8) Epoch 20, batch 1100, loss[loss=0.1741, simple_loss=0.2587, pruned_loss=0.04479, over 6798.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2695, pruned_loss=0.03685, over 1407467.23 frames.], batch size: 15, lr: 3.73e-04
+2022-04-29 17:19:37,615 INFO [train.py:763] (6/8) Epoch 20, batch 1150, loss[loss=0.1834, simple_loss=0.2874, pruned_loss=0.03974, over 7284.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2698, pruned_loss=0.03676, over 1412955.93 frames.], batch size: 24, lr: 3.73e-04
+2022-04-29 17:20:42,599 INFO [train.py:763] (6/8) Epoch 20, batch 1200, loss[loss=0.1911, simple_loss=0.2869, pruned_loss=0.04765, over 7266.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2709, pruned_loss=0.03692, over 1415774.12 frames.], batch size: 18, lr: 3.73e-04
+2022-04-29 17:21:47,932 INFO [train.py:763] (6/8) Epoch 20, batch 1250, loss[loss=0.1747, simple_loss=0.2825, pruned_loss=0.03344, over 7277.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2699, pruned_loss=0.03656, over 1418195.88 frames.], batch size: 24, lr: 3.73e-04
+2022-04-29 17:22:53,226 INFO [train.py:763] (6/8) Epoch 20, batch 1300, loss[loss=0.1771, simple_loss=0.2655, pruned_loss=0.04432, over 7075.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2694, pruned_loss=0.03666, over 1417442.04 frames.], batch size: 18, lr: 3.72e-04
+2022-04-29 17:23:59,019 INFO [train.py:763] (6/8) Epoch 20, batch 1350, loss[loss=0.1608, simple_loss=0.2629, pruned_loss=0.02937, over 7342.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2693, pruned_loss=0.03668, over 1424208.70 frames.], batch size: 22, lr: 3.72e-04
+2022-04-29 17:25:04,573 INFO [train.py:763] (6/8) Epoch 20, batch 1400, loss[loss=0.1793, simple_loss=0.2788, pruned_loss=0.03993, over 7376.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2701, pruned_loss=0.03701, over 1426250.50 frames.], batch size: 23, lr: 3.72e-04
+2022-04-29 17:26:11,038 INFO [train.py:763] (6/8) Epoch 20, batch 1450, loss[loss=0.1849, simple_loss=0.2734, pruned_loss=0.04818, over 5080.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2693, pruned_loss=0.03694, over 1421079.73 frames.], batch size: 52, lr: 3.72e-04
+2022-04-29 17:27:17,722 INFO [train.py:763] (6/8) Epoch 20, batch 1500, loss[loss=0.1579, simple_loss=0.2554, pruned_loss=0.0302, over 7337.00 frames.], tot_loss[loss=0.1722, simple_loss=0.27, pruned_loss=0.0372, over 1418619.17 frames.], batch size: 22, lr: 3.72e-04
+2022-04-29 17:28:24,677 INFO [train.py:763] (6/8) Epoch 20, batch 1550, loss[loss=0.1624, simple_loss=0.2609, pruned_loss=0.03195, over 6718.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2701, pruned_loss=0.03717, over 1420370.09 frames.], batch size: 31, lr: 3.72e-04
+2022-04-29 17:29:31,793 INFO [train.py:763] (6/8) Epoch 20, batch 1600, loss[loss=0.1744, simple_loss=0.2709, pruned_loss=0.03897, over 7346.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2711, pruned_loss=0.03701, over 1420850.59 frames.], batch size: 22, lr: 3.72e-04
+2022-04-29 17:30:38,862 INFO [train.py:763] (6/8) Epoch 20, batch 1650, loss[loss=0.171, simple_loss=0.2659, pruned_loss=0.0381, over 7331.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2708, pruned_loss=0.03698, over 1422007.19 frames.], batch size: 20, lr: 3.72e-04
+2022-04-29 17:31:46,138 INFO [train.py:763] (6/8) Epoch 20, batch 1700, loss[loss=0.173, simple_loss=0.2819, pruned_loss=0.03205, over 7338.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2703, pruned_loss=0.037, over 1422105.25 frames.], batch size: 22, lr: 3.72e-04
+2022-04-29 17:32:52,731 INFO [train.py:763] (6/8) Epoch 20, batch 1750, loss[loss=0.1722, simple_loss=0.2535, pruned_loss=0.04544, over 7413.00 frames.], tot_loss[loss=0.1718, simple_loss=0.27, pruned_loss=0.03675, over 1423074.67 frames.], batch size: 18, lr: 3.72e-04
+2022-04-29 17:33:59,658 INFO [train.py:763] (6/8) Epoch 20, batch 1800, loss[loss=0.2045, simple_loss=0.301, pruned_loss=0.05404, over 7201.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2689, pruned_loss=0.0364, over 1424567.53 frames.], batch size: 23, lr: 3.71e-04
+2022-04-29 17:35:06,943 INFO [train.py:763] (6/8) Epoch 20, batch 1850, loss[loss=0.1371, simple_loss=0.228, pruned_loss=0.02312, over 7408.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2692, pruned_loss=0.03667, over 1423478.23 frames.], batch size: 18, lr: 3.71e-04
+2022-04-29 17:36:12,560 INFO [train.py:763] (6/8) Epoch 20, batch 1900, loss[loss=0.1829, simple_loss=0.2708, pruned_loss=0.04755, over 7163.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2696, pruned_loss=0.03696, over 1424057.67 frames.], batch size: 19, lr: 3.71e-04
+2022-04-29 17:37:18,018 INFO [train.py:763] (6/8) Epoch 20, batch 1950, loss[loss=0.1546, simple_loss=0.2514, pruned_loss=0.0289, over 7260.00 frames.], tot_loss[loss=0.171, simple_loss=0.269, pruned_loss=0.03649, over 1427767.25 frames.], batch size: 19, lr: 3.71e-04
+2022-04-29 17:38:24,303 INFO [train.py:763] (6/8) Epoch 20, batch 2000, loss[loss=0.157, simple_loss=0.2652, pruned_loss=0.0244, over 6711.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2687, pruned_loss=0.03617, over 1424219.01 frames.], batch size: 31, lr: 3.71e-04
+2022-04-29 17:39:29,415 INFO [train.py:763] (6/8) Epoch 20, batch 2050, loss[loss=0.176, simple_loss=0.2746, pruned_loss=0.03873, over 7226.00 frames.], tot_loss[loss=0.1721, simple_loss=0.27, pruned_loss=0.03708, over 1423593.69 frames.], batch size: 21, lr: 3.71e-04
+2022-04-29 17:40:35,603 INFO [train.py:763] (6/8) Epoch 20, batch 2100, loss[loss=0.1512, simple_loss=0.2395, pruned_loss=0.03141, over 7071.00 frames.], tot_loss[loss=0.172, simple_loss=0.27, pruned_loss=0.03703, over 1422814.83 frames.], batch size: 18, lr: 3.71e-04
+2022-04-29 17:41:42,821 INFO [train.py:763] (6/8) Epoch 20, batch 2150, loss[loss=0.1386, simple_loss=0.2305, pruned_loss=0.02339, over 6825.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2712, pruned_loss=0.03758, over 1420862.79 frames.], batch size: 15, lr: 3.71e-04
+2022-04-29 17:42:48,994 INFO [train.py:763] (6/8) Epoch 20, batch 2200, loss[loss=0.1842, simple_loss=0.287, pruned_loss=0.0407, over 7211.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2702, pruned_loss=0.03705, over 1423305.96 frames.], batch size: 22, lr: 3.71e-04
+2022-04-29 17:43:54,362 INFO [train.py:763] (6/8) Epoch 20, batch 2250, loss[loss=0.1881, simple_loss=0.2896, pruned_loss=0.04329, over 7206.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2703, pruned_loss=0.03722, over 1424018.70 frames.], batch size: 22, lr: 3.71e-04
+2022-04-29 17:45:01,607 INFO [train.py:763] (6/8) Epoch 20, batch 2300, loss[loss=0.1979, simple_loss=0.2748, pruned_loss=0.06055, over 4908.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2691, pruned_loss=0.03706, over 1421842.21 frames.], batch size: 52, lr: 3.71e-04
+2022-04-29 17:46:08,269 INFO [train.py:763] (6/8) Epoch 20, batch 2350, loss[loss=0.1739, simple_loss=0.265, pruned_loss=0.04142, over 7308.00 frames.], tot_loss[loss=0.172, simple_loss=0.2696, pruned_loss=0.03714, over 1416377.03 frames.], batch size: 24, lr: 3.70e-04
+2022-04-29 17:47:15,537 INFO [train.py:763] (6/8) Epoch 20, batch 2400, loss[loss=0.181, simple_loss=0.2894, pruned_loss=0.03633, over 7204.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2697, pruned_loss=0.0369, over 1420351.73 frames.], batch size: 23, lr: 3.70e-04
+2022-04-29 17:48:22,425 INFO [train.py:763] (6/8) Epoch 20, batch 2450, loss[loss=0.1818, simple_loss=0.2736, pruned_loss=0.04503, over 7161.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2688, pruned_loss=0.03653, over 1421159.42 frames.], batch size: 19, lr: 3.70e-04
+2022-04-29 17:49:29,463 INFO [train.py:763] (6/8) Epoch 20, batch 2500, loss[loss=0.1625, simple_loss=0.2706, pruned_loss=0.02721, over 7412.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2687, pruned_loss=0.03642, over 1422012.99 frames.], batch size: 21, lr: 3.70e-04
+2022-04-29 17:50:36,139 INFO [train.py:763] (6/8) Epoch 20, batch 2550, loss[loss=0.176, simple_loss=0.2699, pruned_loss=0.0411, over 5116.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2698, pruned_loss=0.03704, over 1420053.88 frames.], batch size: 54, lr: 3.70e-04
+2022-04-29 17:51:41,445 INFO [train.py:763] (6/8) Epoch 20, batch 2600, loss[loss=0.1647, simple_loss=0.2597, pruned_loss=0.03489, over 7065.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2703, pruned_loss=0.03707, over 1420921.68 frames.], batch size: 18, lr: 3.70e-04
+2022-04-29 17:52:58,241 INFO [train.py:763] (6/8) Epoch 20, batch 2650, loss[loss=0.1802, simple_loss=0.2882, pruned_loss=0.0361, over 7335.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2711, pruned_loss=0.0376, over 1417654.89 frames.], batch size: 20, lr: 3.70e-04
+2022-04-29 17:54:04,062 INFO [train.py:763] (6/8) Epoch 20, batch 2700, loss[loss=0.1494, simple_loss=0.2409, pruned_loss=0.02896, over 7411.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2697, pruned_loss=0.03684, over 1420823.28 frames.], batch size: 18, lr: 3.70e-04
+2022-04-29 17:55:10,584 INFO [train.py:763] (6/8) Epoch 20, batch 2750, loss[loss=0.1713, simple_loss=0.2637, pruned_loss=0.03943, over 7152.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2697, pruned_loss=0.03687, over 1421966.89 frames.], batch size: 18, lr: 3.70e-04
+2022-04-29 17:56:15,902 INFO [train.py:763] (6/8) Epoch 20, batch 2800, loss[loss=0.1734, simple_loss=0.2688, pruned_loss=0.03901, over 7363.00 frames.], tot_loss[loss=0.171, simple_loss=0.2687, pruned_loss=0.03661, over 1425010.50 frames.], batch size: 23, lr: 3.70e-04
+2022-04-29 17:57:21,237 INFO [train.py:763] (6/8) Epoch 20, batch 2850, loss[loss=0.2219, simple_loss=0.3194, pruned_loss=0.06221, over 7199.00 frames.], tot_loss[loss=0.171, simple_loss=0.2685, pruned_loss=0.03671, over 1419320.90 frames.], batch size: 23, lr: 3.69e-04
+2022-04-29 17:58:26,460 INFO [train.py:763] (6/8) Epoch 20, batch 2900, loss[loss=0.193, simple_loss=0.2963, pruned_loss=0.04487, over 7068.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2685, pruned_loss=0.03679, over 1414758.31 frames.], batch size: 28, lr: 3.69e-04
+2022-04-29 17:59:31,729 INFO [train.py:763] (6/8) Epoch 20, batch 2950, loss[loss=0.1655, simple_loss=0.2663, pruned_loss=0.03239, over 7355.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2689, pruned_loss=0.03679, over 1412460.95 frames.], batch size: 19, lr: 3.69e-04
+2022-04-29 18:01:03,486 INFO [train.py:763] (6/8) Epoch 20, batch 3000, loss[loss=0.1793, simple_loss=0.2784, pruned_loss=0.04007, over 6878.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2684, pruned_loss=0.03692, over 1412321.56 frames.], batch size: 31, lr: 3.69e-04
+2022-04-29 18:01:03,487 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 18:01:18,758 INFO [train.py:792] (6/8) Epoch 20, validation: loss=0.1672, simple_loss=0.2663, pruned_loss=0.03407, over 698248.00 frames.
+2022-04-29 18:02:33,645 INFO [train.py:763] (6/8) Epoch 20, batch 3050, loss[loss=0.177, simple_loss=0.2688, pruned_loss=0.04263, over 7276.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2683, pruned_loss=0.03695, over 1413873.62 frames.], batch size: 18, lr: 3.69e-04
+2022-04-29 18:03:49,735 INFO [train.py:763] (6/8) Epoch 20, batch 3100, loss[loss=0.1636, simple_loss=0.262, pruned_loss=0.03262, over 7382.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2695, pruned_loss=0.03737, over 1413100.08 frames.], batch size: 23, lr: 3.69e-04
+2022-04-29 18:05:13,902 INFO [train.py:763] (6/8) Epoch 20, batch 3150, loss[loss=0.1972, simple_loss=0.2953, pruned_loss=0.04954, over 7284.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2692, pruned_loss=0.03732, over 1417517.63 frames.], batch size: 24, lr: 3.69e-04
+2022-04-29 18:06:18,923 INFO [train.py:763] (6/8) Epoch 20, batch 3200, loss[loss=0.1489, simple_loss=0.2477, pruned_loss=0.02501, over 7322.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2706, pruned_loss=0.03724, over 1422106.50 frames.], batch size: 21, lr: 3.69e-04
+2022-04-29 18:07:24,051 INFO [train.py:763] (6/8) Epoch 20, batch 3250, loss[loss=0.1658, simple_loss=0.2606, pruned_loss=0.03553, over 7065.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2706, pruned_loss=0.03716, over 1421112.17 frames.], batch size: 18, lr: 3.69e-04
+2022-04-29 18:08:29,712 INFO [train.py:763] (6/8) Epoch 20, batch 3300, loss[loss=0.1553, simple_loss=0.2486, pruned_loss=0.03098, over 7129.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2693, pruned_loss=0.03654, over 1422681.55 frames.], batch size: 17, lr: 3.69e-04
+2022-04-29 18:09:35,972 INFO [train.py:763] (6/8) Epoch 20, batch 3350, loss[loss=0.171, simple_loss=0.279, pruned_loss=0.03146, over 7233.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2693, pruned_loss=0.03619, over 1418217.81 frames.], batch size: 20, lr: 3.68e-04
+2022-04-29 18:10:42,811 INFO [train.py:763] (6/8) Epoch 20, batch 3400, loss[loss=0.1884, simple_loss=0.2808, pruned_loss=0.04801, over 6381.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2697, pruned_loss=0.03635, over 1416083.46 frames.], batch size: 37, lr: 3.68e-04
+2022-04-29 18:11:49,528 INFO [train.py:763] (6/8) Epoch 20, batch 3450, loss[loss=0.1824, simple_loss=0.2771, pruned_loss=0.04381, over 7316.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2702, pruned_loss=0.03709, over 1414388.37 frames.], batch size: 21, lr: 3.68e-04
+2022-04-29 18:12:54,739 INFO [train.py:763] (6/8) Epoch 20, batch 3500, loss[loss=0.1706, simple_loss=0.2758, pruned_loss=0.03275, over 7107.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2712, pruned_loss=0.03776, over 1410123.71 frames.], batch size: 28, lr: 3.68e-04
+2022-04-29 18:14:00,244 INFO [train.py:763] (6/8) Epoch 20, batch 3550, loss[loss=0.1461, simple_loss=0.231, pruned_loss=0.03057, over 7280.00 frames.], tot_loss[loss=0.172, simple_loss=0.2698, pruned_loss=0.03709, over 1413982.43 frames.], batch size: 17, lr: 3.68e-04
+2022-04-29 18:15:05,502 INFO [train.py:763] (6/8) Epoch 20, batch 3600, loss[loss=0.1619, simple_loss=0.2702, pruned_loss=0.0268, over 7367.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2699, pruned_loss=0.03668, over 1411954.02 frames.], batch size: 23, lr: 3.68e-04
+2022-04-29 18:16:10,760 INFO [train.py:763] (6/8) Epoch 20, batch 3650, loss[loss=0.1753, simple_loss=0.2807, pruned_loss=0.03489, over 7155.00 frames.], tot_loss[loss=0.171, simple_loss=0.2694, pruned_loss=0.03634, over 1413320.81 frames.], batch size: 26, lr: 3.68e-04
+2022-04-29 18:17:15,976 INFO [train.py:763] (6/8) Epoch 20, batch 3700, loss[loss=0.1619, simple_loss=0.2677, pruned_loss=0.02805, over 7305.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2695, pruned_loss=0.03618, over 1414752.49 frames.], batch size: 21, lr: 3.68e-04
+2022-04-29 18:18:22,132 INFO [train.py:763] (6/8) Epoch 20, batch 3750, loss[loss=0.1986, simple_loss=0.2919, pruned_loss=0.05266, over 7308.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2691, pruned_loss=0.03591, over 1417496.80 frames.], batch size: 25, lr: 3.68e-04
+2022-04-29 18:19:27,283 INFO [train.py:763] (6/8) Epoch 20, batch 3800, loss[loss=0.1806, simple_loss=0.2879, pruned_loss=0.03663, over 7149.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2686, pruned_loss=0.03587, over 1418355.05 frames.], batch size: 26, lr: 3.68e-04
+2022-04-29 18:20:33,281 INFO [train.py:763] (6/8) Epoch 20, batch 3850, loss[loss=0.1739, simple_loss=0.2749, pruned_loss=0.03648, over 7324.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2685, pruned_loss=0.03605, over 1419182.76 frames.], batch size: 20, lr: 3.68e-04
+2022-04-29 18:21:38,668 INFO [train.py:763] (6/8) Epoch 20, batch 3900, loss[loss=0.1821, simple_loss=0.2783, pruned_loss=0.04294, over 7254.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2687, pruned_loss=0.03603, over 1423087.39 frames.], batch size: 19, lr: 3.67e-04
+2022-04-29 18:22:44,412 INFO [train.py:763] (6/8) Epoch 20, batch 3950, loss[loss=0.1447, simple_loss=0.235, pruned_loss=0.02721, over 7396.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2699, pruned_loss=0.0366, over 1418611.34 frames.], batch size: 18, lr: 3.67e-04
+2022-04-29 18:23:51,278 INFO [train.py:763] (6/8) Epoch 20, batch 4000, loss[loss=0.163, simple_loss=0.2683, pruned_loss=0.02882, over 7356.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2698, pruned_loss=0.03619, over 1422497.62 frames.], batch size: 19, lr: 3.67e-04
+2022-04-29 18:24:58,615 INFO [train.py:763] (6/8) Epoch 20, batch 4050, loss[loss=0.2179, simple_loss=0.3035, pruned_loss=0.06612, over 4985.00 frames.], tot_loss[loss=0.17, simple_loss=0.2684, pruned_loss=0.03584, over 1419955.83 frames.], batch size: 53, lr: 3.67e-04
+2022-04-29 18:26:05,423 INFO [train.py:763] (6/8) Epoch 20, batch 4100, loss[loss=0.1633, simple_loss=0.2652, pruned_loss=0.03067, over 7221.00 frames.], tot_loss[loss=0.171, simple_loss=0.2693, pruned_loss=0.03637, over 1411332.21 frames.], batch size: 21, lr: 3.67e-04
+2022-04-29 18:27:10,993 INFO [train.py:763] (6/8) Epoch 20, batch 4150, loss[loss=0.1467, simple_loss=0.2469, pruned_loss=0.02325, over 7069.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2712, pruned_loss=0.03688, over 1412100.94 frames.], batch size: 18, lr: 3.67e-04
+2022-04-29 18:28:16,326 INFO [train.py:763] (6/8) Epoch 20, batch 4200, loss[loss=0.1663, simple_loss=0.2693, pruned_loss=0.03169, over 6902.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2709, pruned_loss=0.03681, over 1411766.11 frames.], batch size: 32, lr: 3.67e-04
+2022-04-29 18:29:32,312 INFO [train.py:763] (6/8) Epoch 20, batch 4250, loss[loss=0.1769, simple_loss=0.2764, pruned_loss=0.03867, over 7230.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2698, pruned_loss=0.03625, over 1416238.32 frames.], batch size: 21, lr: 3.67e-04
+2022-04-29 18:30:38,991 INFO [train.py:763] (6/8) Epoch 20, batch 4300, loss[loss=0.1724, simple_loss=0.2735, pruned_loss=0.0357, over 7288.00 frames.], tot_loss[loss=0.171, simple_loss=0.2695, pruned_loss=0.03622, over 1417156.27 frames.], batch size: 24, lr: 3.67e-04
+2022-04-29 18:31:45,009 INFO [train.py:763] (6/8) Epoch 20, batch 4350, loss[loss=0.1708, simple_loss=0.2728, pruned_loss=0.03443, over 7211.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2692, pruned_loss=0.03617, over 1417195.63 frames.], batch size: 21, lr: 3.67e-04
+2022-04-29 18:32:52,214 INFO [train.py:763] (6/8) Epoch 20, batch 4400, loss[loss=0.1823, simple_loss=0.2597, pruned_loss=0.05245, over 7156.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2689, pruned_loss=0.03578, over 1416306.97 frames.], batch size: 18, lr: 3.66e-04
+2022-04-29 18:33:58,454 INFO [train.py:763] (6/8) Epoch 20, batch 4450, loss[loss=0.1514, simple_loss=0.2458, pruned_loss=0.02847, over 7016.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2692, pruned_loss=0.03609, over 1408167.41 frames.], batch size: 16, lr: 3.66e-04
+2022-04-29 18:35:05,724 INFO [train.py:763] (6/8) Epoch 20, batch 4500, loss[loss=0.1477, simple_loss=0.2386, pruned_loss=0.02842, over 6994.00 frames.], tot_loss[loss=0.1705, simple_loss=0.269, pruned_loss=0.03605, over 1409800.42 frames.], batch size: 16, lr: 3.66e-04
+2022-04-29 18:36:13,271 INFO [train.py:763] (6/8) Epoch 20, batch 4550, loss[loss=0.1722, simple_loss=0.2743, pruned_loss=0.03507, over 5285.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2682, pruned_loss=0.03621, over 1394714.57 frames.], batch size: 52, lr: 3.66e-04
+2022-04-29 18:37:42,389 INFO [train.py:763] (6/8) Epoch 21, batch 0, loss[loss=0.1698, simple_loss=0.2754, pruned_loss=0.03214, over 7292.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2754, pruned_loss=0.03214, over 7292.00 frames.], batch size: 25, lr: 3.58e-04
+2022-04-29 18:38:48,214 INFO [train.py:763] (6/8) Epoch 21, batch 50, loss[loss=0.1438, simple_loss=0.2409, pruned_loss=0.02334, over 7163.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2719, pruned_loss=0.03729, over 317523.59 frames.], batch size: 18, lr: 3.58e-04
+2022-04-29 18:39:53,577 INFO [train.py:763] (6/8) Epoch 21, batch 100, loss[loss=0.1792, simple_loss=0.2917, pruned_loss=0.03339, over 7116.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2692, pruned_loss=0.03621, over 564319.64 frames.], batch size: 21, lr: 3.58e-04
+2022-04-29 18:41:00,343 INFO [train.py:763] (6/8) Epoch 21, batch 150, loss[loss=0.1881, simple_loss=0.2881, pruned_loss=0.04407, over 7313.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2684, pruned_loss=0.03602, over 753963.42 frames.], batch size: 21, lr: 3.58e-04
+2022-04-29 18:42:07,758 INFO [train.py:763] (6/8) Epoch 21, batch 200, loss[loss=0.1623, simple_loss=0.2643, pruned_loss=0.03015, over 7345.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2694, pruned_loss=0.03593, over 901553.85 frames.], batch size: 22, lr: 3.58e-04
+2022-04-29 18:43:14,305 INFO [train.py:763] (6/8) Epoch 21, batch 250, loss[loss=0.1502, simple_loss=0.2547, pruned_loss=0.02279, over 7249.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2691, pruned_loss=0.03609, over 1014515.78 frames.], batch size: 19, lr: 3.57e-04
+2022-04-29 18:44:19,573 INFO [train.py:763] (6/8) Epoch 21, batch 300, loss[loss=0.1712, simple_loss=0.263, pruned_loss=0.03973, over 7241.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2689, pruned_loss=0.0359, over 1106952.30 frames.], batch size: 20, lr: 3.57e-04
+2022-04-29 18:45:25,083 INFO [train.py:763] (6/8) Epoch 21, batch 350, loss[loss=0.1678, simple_loss=0.2772, pruned_loss=0.02918, over 7165.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2679, pruned_loss=0.03541, over 1176904.29 frames.], batch size: 19, lr: 3.57e-04
+2022-04-29 18:46:30,619 INFO [train.py:763] (6/8) Epoch 21, batch 400, loss[loss=0.2123, simple_loss=0.3142, pruned_loss=0.0552, over 7222.00 frames.], tot_loss[loss=0.1691, simple_loss=0.268, pruned_loss=0.0351, over 1230407.61 frames.], batch size: 21, lr: 3.57e-04
+2022-04-29 18:47:36,080 INFO [train.py:763] (6/8) Epoch 21, batch 450, loss[loss=0.199, simple_loss=0.2867, pruned_loss=0.05569, over 5022.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2674, pruned_loss=0.03518, over 1273955.39 frames.], batch size: 52, lr: 3.57e-04
+2022-04-29 18:48:41,850 INFO [train.py:763] (6/8) Epoch 21, batch 500, loss[loss=0.1955, simple_loss=0.2898, pruned_loss=0.05057, over 7295.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2682, pruned_loss=0.03528, over 1309488.06 frames.], batch size: 25, lr: 3.57e-04
+2022-04-29 18:49:47,436 INFO [train.py:763] (6/8) Epoch 21, batch 550, loss[loss=0.1563, simple_loss=0.2552, pruned_loss=0.02864, over 7435.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2688, pruned_loss=0.03534, over 1331974.56 frames.], batch size: 20, lr: 3.57e-04
+2022-04-29 18:50:53,642 INFO [train.py:763] (6/8) Epoch 21, batch 600, loss[loss=0.179, simple_loss=0.2928, pruned_loss=0.03266, over 7327.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2682, pruned_loss=0.03526, over 1353663.41 frames.], batch size: 22, lr: 3.57e-04
+2022-04-29 18:51:58,879 INFO [train.py:763] (6/8) Epoch 21, batch 650, loss[loss=0.1555, simple_loss=0.2644, pruned_loss=0.02326, over 7346.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2695, pruned_loss=0.03556, over 1370111.14 frames.], batch size: 22, lr: 3.57e-04
+2022-04-29 18:53:04,512 INFO [train.py:763] (6/8) Epoch 21, batch 700, loss[loss=0.1836, simple_loss=0.2776, pruned_loss=0.04478, over 7291.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2691, pruned_loss=0.03574, over 1378818.66 frames.], batch size: 25, lr: 3.57e-04
+2022-04-29 18:54:10,370 INFO [train.py:763] (6/8) Epoch 21, batch 750, loss[loss=0.165, simple_loss=0.262, pruned_loss=0.03397, over 7164.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2678, pruned_loss=0.03544, over 1387601.65 frames.], batch size: 18, lr: 3.57e-04
+2022-04-29 18:55:16,598 INFO [train.py:763] (6/8) Epoch 21, batch 800, loss[loss=0.1748, simple_loss=0.275, pruned_loss=0.03729, over 7274.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2681, pruned_loss=0.03554, over 1399791.27 frames.], batch size: 25, lr: 3.56e-04
+2022-04-29 18:56:22,305 INFO [train.py:763] (6/8) Epoch 21, batch 850, loss[loss=0.1429, simple_loss=0.2416, pruned_loss=0.02206, over 7407.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2676, pruned_loss=0.03538, over 1405320.25 frames.], batch size: 18, lr: 3.56e-04
+2022-04-29 18:57:27,452 INFO [train.py:763] (6/8) Epoch 21, batch 900, loss[loss=0.1973, simple_loss=0.3102, pruned_loss=0.04222, over 6392.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2671, pruned_loss=0.03539, over 1409724.53 frames.], batch size: 37, lr: 3.56e-04
+2022-04-29 18:58:32,840 INFO [train.py:763] (6/8) Epoch 21, batch 950, loss[loss=0.1391, simple_loss=0.2342, pruned_loss=0.02196, over 7277.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2669, pruned_loss=0.03541, over 1411759.53 frames.], batch size: 18, lr: 3.56e-04
+2022-04-29 18:59:38,150 INFO [train.py:763] (6/8) Epoch 21, batch 1000, loss[loss=0.1753, simple_loss=0.273, pruned_loss=0.03876, over 7140.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2681, pruned_loss=0.03581, over 1411892.85 frames.], batch size: 19, lr: 3.56e-04
+2022-04-29 19:00:44,772 INFO [train.py:763] (6/8) Epoch 21, batch 1050, loss[loss=0.1492, simple_loss=0.2601, pruned_loss=0.01918, over 7326.00 frames.], tot_loss[loss=0.169, simple_loss=0.267, pruned_loss=0.03555, over 1414985.45 frames.], batch size: 22, lr: 3.56e-04
+2022-04-29 19:01:50,755 INFO [train.py:763] (6/8) Epoch 21, batch 1100, loss[loss=0.175, simple_loss=0.2809, pruned_loss=0.03456, over 6430.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2676, pruned_loss=0.03596, over 1418750.67 frames.], batch size: 38, lr: 3.56e-04
+2022-04-29 19:02:56,409 INFO [train.py:763] (6/8) Epoch 21, batch 1150, loss[loss=0.1563, simple_loss=0.2566, pruned_loss=0.02805, over 7255.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2675, pruned_loss=0.03568, over 1419808.19 frames.], batch size: 19, lr: 3.56e-04
+2022-04-29 19:04:02,099 INFO [train.py:763] (6/8) Epoch 21, batch 1200, loss[loss=0.1741, simple_loss=0.2729, pruned_loss=0.03762, over 7294.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2675, pruned_loss=0.03574, over 1420576.09 frames.], batch size: 25, lr: 3.56e-04
+2022-04-29 19:05:07,721 INFO [train.py:763] (6/8) Epoch 21, batch 1250, loss[loss=0.1415, simple_loss=0.2298, pruned_loss=0.02657, over 6998.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2677, pruned_loss=0.03578, over 1420254.96 frames.], batch size: 16, lr: 3.56e-04
+2022-04-29 19:06:13,273 INFO [train.py:763] (6/8) Epoch 21, batch 1300, loss[loss=0.1588, simple_loss=0.2561, pruned_loss=0.03071, over 7163.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2671, pruned_loss=0.03571, over 1418397.31 frames.], batch size: 19, lr: 3.56e-04
+2022-04-29 19:07:19,457 INFO [train.py:763] (6/8) Epoch 21, batch 1350, loss[loss=0.1907, simple_loss=0.2871, pruned_loss=0.04718, over 7414.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2669, pruned_loss=0.03584, over 1422447.62 frames.], batch size: 21, lr: 3.55e-04
+2022-04-29 19:08:24,895 INFO [train.py:763] (6/8) Epoch 21, batch 1400, loss[loss=0.1789, simple_loss=0.296, pruned_loss=0.03087, over 7203.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2668, pruned_loss=0.03581, over 1419351.50 frames.], batch size: 22, lr: 3.55e-04
+2022-04-29 19:09:30,410 INFO [train.py:763] (6/8) Epoch 21, batch 1450, loss[loss=0.1852, simple_loss=0.2792, pruned_loss=0.04562, over 7433.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2667, pruned_loss=0.03555, over 1424510.70 frames.], batch size: 20, lr: 3.55e-04
+2022-04-29 19:10:36,219 INFO [train.py:763] (6/8) Epoch 21, batch 1500, loss[loss=0.1512, simple_loss=0.2612, pruned_loss=0.0206, over 7228.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2669, pruned_loss=0.03541, over 1426351.60 frames.], batch size: 20, lr: 3.55e-04
+2022-04-29 19:11:42,023 INFO [train.py:763] (6/8) Epoch 21, batch 1550, loss[loss=0.185, simple_loss=0.2822, pruned_loss=0.04391, over 7242.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2663, pruned_loss=0.03514, over 1429069.15 frames.], batch size: 20, lr: 3.55e-04
+2022-04-29 19:12:47,949 INFO [train.py:763] (6/8) Epoch 21, batch 1600, loss[loss=0.1363, simple_loss=0.2347, pruned_loss=0.0189, over 6751.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2663, pruned_loss=0.0352, over 1429890.54 frames.], batch size: 15, lr: 3.55e-04
+2022-04-29 19:13:54,884 INFO [train.py:763] (6/8) Epoch 21, batch 1650, loss[loss=0.189, simple_loss=0.2853, pruned_loss=0.04637, over 6763.00 frames.], tot_loss[loss=0.1689, simple_loss=0.267, pruned_loss=0.0354, over 1432185.15 frames.], batch size: 31, lr: 3.55e-04
+2022-04-29 19:15:01,800 INFO [train.py:763] (6/8) Epoch 21, batch 1700, loss[loss=0.1857, simple_loss=0.2933, pruned_loss=0.03906, over 7335.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2653, pruned_loss=0.0346, over 1435330.76 frames.], batch size: 22, lr: 3.55e-04
+2022-04-29 19:16:08,178 INFO [train.py:763] (6/8) Epoch 21, batch 1750, loss[loss=0.1692, simple_loss=0.2706, pruned_loss=0.03394, over 7225.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2658, pruned_loss=0.03463, over 1433864.95 frames.], batch size: 20, lr: 3.55e-04
+2022-04-29 19:17:14,204 INFO [train.py:763] (6/8) Epoch 21, batch 1800, loss[loss=0.1447, simple_loss=0.2384, pruned_loss=0.02554, over 7288.00 frames.], tot_loss[loss=0.168, simple_loss=0.2658, pruned_loss=0.03513, over 1429976.77 frames.], batch size: 17, lr: 3.55e-04
+2022-04-29 19:18:19,485 INFO [train.py:763] (6/8) Epoch 21, batch 1850, loss[loss=0.1702, simple_loss=0.2744, pruned_loss=0.03302, over 6394.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2657, pruned_loss=0.03519, over 1425785.83 frames.], batch size: 38, lr: 3.55e-04
+2022-04-29 19:19:25,205 INFO [train.py:763] (6/8) Epoch 21, batch 1900, loss[loss=0.1793, simple_loss=0.2734, pruned_loss=0.0426, over 5045.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2668, pruned_loss=0.03534, over 1423377.52 frames.], batch size: 52, lr: 3.54e-04
+2022-04-29 19:20:31,908 INFO [train.py:763] (6/8) Epoch 21, batch 1950, loss[loss=0.1553, simple_loss=0.2528, pruned_loss=0.0289, over 7289.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2674, pruned_loss=0.03567, over 1424344.09 frames.], batch size: 17, lr: 3.54e-04
+2022-04-29 19:21:37,667 INFO [train.py:763] (6/8) Epoch 21, batch 2000, loss[loss=0.1696, simple_loss=0.2703, pruned_loss=0.03446, over 7337.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2675, pruned_loss=0.03576, over 1427057.89 frames.], batch size: 20, lr: 3.54e-04
+2022-04-29 19:22:44,043 INFO [train.py:763] (6/8) Epoch 21, batch 2050, loss[loss=0.1443, simple_loss=0.2308, pruned_loss=0.02896, over 7280.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2677, pruned_loss=0.03604, over 1428151.35 frames.], batch size: 17, lr: 3.54e-04
+2022-04-29 19:23:50,504 INFO [train.py:763] (6/8) Epoch 21, batch 2100, loss[loss=0.142, simple_loss=0.2322, pruned_loss=0.02585, over 7418.00 frames.], tot_loss[loss=0.1699, simple_loss=0.268, pruned_loss=0.03594, over 1427213.31 frames.], batch size: 18, lr: 3.54e-04
+2022-04-29 19:24:56,273 INFO [train.py:763] (6/8) Epoch 21, batch 2150, loss[loss=0.161, simple_loss=0.2621, pruned_loss=0.02999, over 7159.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2677, pruned_loss=0.03602, over 1422886.17 frames.], batch size: 18, lr: 3.54e-04
+2022-04-29 19:26:02,249 INFO [train.py:763] (6/8) Epoch 21, batch 2200, loss[loss=0.1727, simple_loss=0.2669, pruned_loss=0.03924, over 7121.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2669, pruned_loss=0.0353, over 1425933.47 frames.], batch size: 21, lr: 3.54e-04
+2022-04-29 19:27:08,596 INFO [train.py:763] (6/8) Epoch 21, batch 2250, loss[loss=0.1497, simple_loss=0.2408, pruned_loss=0.02927, over 7274.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2676, pruned_loss=0.03572, over 1423819.66 frames.], batch size: 16, lr: 3.54e-04
+2022-04-29 19:28:14,989 INFO [train.py:763] (6/8) Epoch 21, batch 2300, loss[loss=0.214, simple_loss=0.3027, pruned_loss=0.06272, over 4984.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2676, pruned_loss=0.0353, over 1424926.70 frames.], batch size: 54, lr: 3.54e-04
+2022-04-29 19:29:21,493 INFO [train.py:763] (6/8) Epoch 21, batch 2350, loss[loss=0.1739, simple_loss=0.2812, pruned_loss=0.03333, over 6558.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2675, pruned_loss=0.03565, over 1427334.78 frames.], batch size: 38, lr: 3.54e-04
+2022-04-29 19:30:28,266 INFO [train.py:763] (6/8) Epoch 21, batch 2400, loss[loss=0.1485, simple_loss=0.2342, pruned_loss=0.03143, over 7133.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2665, pruned_loss=0.03564, over 1425987.61 frames.], batch size: 17, lr: 3.54e-04
+2022-04-29 19:31:33,883 INFO [train.py:763] (6/8) Epoch 21, batch 2450, loss[loss=0.1547, simple_loss=0.2463, pruned_loss=0.03161, over 7280.00 frames.], tot_loss[loss=0.169, simple_loss=0.2667, pruned_loss=0.03563, over 1424436.10 frames.], batch size: 17, lr: 3.54e-04
+2022-04-29 19:32:39,519 INFO [train.py:763] (6/8) Epoch 21, batch 2500, loss[loss=0.1709, simple_loss=0.2776, pruned_loss=0.03208, over 7409.00 frames.], tot_loss[loss=0.169, simple_loss=0.2666, pruned_loss=0.03567, over 1421989.95 frames.], batch size: 21, lr: 3.53e-04
+2022-04-29 19:33:46,127 INFO [train.py:763] (6/8) Epoch 21, batch 2550, loss[loss=0.1892, simple_loss=0.2824, pruned_loss=0.04801, over 7064.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2673, pruned_loss=0.03596, over 1420706.15 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:34:52,132 INFO [train.py:763] (6/8) Epoch 21, batch 2600, loss[loss=0.1657, simple_loss=0.2555, pruned_loss=0.03794, over 7157.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2685, pruned_loss=0.03615, over 1416925.01 frames.], batch size: 19, lr: 3.53e-04
+2022-04-29 19:35:58,117 INFO [train.py:763] (6/8) Epoch 21, batch 2650, loss[loss=0.1767, simple_loss=0.2755, pruned_loss=0.03894, over 7271.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2676, pruned_loss=0.03575, over 1420225.92 frames.], batch size: 19, lr: 3.53e-04
+2022-04-29 19:37:03,417 INFO [train.py:763] (6/8) Epoch 21, batch 2700, loss[loss=0.1419, simple_loss=0.2412, pruned_loss=0.02133, over 7164.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2676, pruned_loss=0.0355, over 1419314.20 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:38:08,438 INFO [train.py:763] (6/8) Epoch 21, batch 2750, loss[loss=0.1469, simple_loss=0.2446, pruned_loss=0.02458, over 7060.00 frames.], tot_loss[loss=0.1697, simple_loss=0.268, pruned_loss=0.03569, over 1419537.21 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:39:13,886 INFO [train.py:763] (6/8) Epoch 21, batch 2800, loss[loss=0.1768, simple_loss=0.2649, pruned_loss=0.04432, over 7272.00 frames.], tot_loss[loss=0.1697, simple_loss=0.268, pruned_loss=0.03565, over 1419953.40 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:40:19,369 INFO [train.py:763] (6/8) Epoch 21, batch 2850, loss[loss=0.1573, simple_loss=0.2496, pruned_loss=0.03244, over 7154.00 frames.], tot_loss[loss=0.17, simple_loss=0.2681, pruned_loss=0.03595, over 1418898.15 frames.], batch size: 19, lr: 3.53e-04
+2022-04-29 19:41:24,555 INFO [train.py:763] (6/8) Epoch 21, batch 2900, loss[loss=0.1768, simple_loss=0.2667, pruned_loss=0.04348, over 7164.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2678, pruned_loss=0.03587, over 1421351.21 frames.], batch size: 19, lr: 3.53e-04
+2022-04-29 19:42:30,256 INFO [train.py:763] (6/8) Epoch 21, batch 2950, loss[loss=0.154, simple_loss=0.265, pruned_loss=0.02156, over 7410.00 frames.], tot_loss[loss=0.17, simple_loss=0.2678, pruned_loss=0.03615, over 1421829.14 frames.], batch size: 21, lr: 3.53e-04
+2022-04-29 19:43:36,721 INFO [train.py:763] (6/8) Epoch 21, batch 3000, loss[loss=0.1822, simple_loss=0.2663, pruned_loss=0.04905, over 7150.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2685, pruned_loss=0.03635, over 1425881.70 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:43:36,722 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 19:43:52,055 INFO [train.py:792] (6/8) Epoch 21, validation: loss=0.1676, simple_loss=0.2672, pruned_loss=0.03398, over 698248.00 frames.
+2022-04-29 19:44:57,978 INFO [train.py:763] (6/8) Epoch 21, batch 3050, loss[loss=0.2054, simple_loss=0.3131, pruned_loss=0.04891, over 6967.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2687, pruned_loss=0.03648, over 1427756.31 frames.], batch size: 28, lr: 3.52e-04
+2022-04-29 19:46:03,954 INFO [train.py:763] (6/8) Epoch 21, batch 3100, loss[loss=0.1965, simple_loss=0.2847, pruned_loss=0.05414, over 5078.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2683, pruned_loss=0.03643, over 1428459.63 frames.], batch size: 52, lr: 3.52e-04
+2022-04-29 19:47:10,168 INFO [train.py:763] (6/8) Epoch 21, batch 3150, loss[loss=0.1794, simple_loss=0.2892, pruned_loss=0.03476, over 7417.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2677, pruned_loss=0.03578, over 1425774.92 frames.], batch size: 21, lr: 3.52e-04
+2022-04-29 19:48:15,889 INFO [train.py:763] (6/8) Epoch 21, batch 3200, loss[loss=0.1662, simple_loss=0.2665, pruned_loss=0.03292, over 7076.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2672, pruned_loss=0.03526, over 1426695.83 frames.], batch size: 18, lr: 3.52e-04
+2022-04-29 19:49:21,832 INFO [train.py:763] (6/8) Epoch 21, batch 3250, loss[loss=0.1698, simple_loss=0.2606, pruned_loss=0.03953, over 7003.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2687, pruned_loss=0.03572, over 1427643.33 frames.], batch size: 16, lr: 3.52e-04
+2022-04-29 19:50:27,809 INFO [train.py:763] (6/8) Epoch 21, batch 3300, loss[loss=0.1615, simple_loss=0.2594, pruned_loss=0.03174, over 7433.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2687, pruned_loss=0.0357, over 1430254.25 frames.], batch size: 20, lr: 3.52e-04
+2022-04-29 19:51:34,066 INFO [train.py:763] (6/8) Epoch 21, batch 3350, loss[loss=0.1622, simple_loss=0.2582, pruned_loss=0.03305, over 7366.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2693, pruned_loss=0.03614, over 1428740.83 frames.], batch size: 19, lr: 3.52e-04
+2022-04-29 19:52:40,238 INFO [train.py:763] (6/8) Epoch 21, batch 3400, loss[loss=0.1637, simple_loss=0.2584, pruned_loss=0.03452, over 7123.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2686, pruned_loss=0.03606, over 1425056.17 frames.], batch size: 17, lr: 3.52e-04
+2022-04-29 19:53:45,693 INFO [train.py:763] (6/8) Epoch 21, batch 3450, loss[loss=0.1782, simple_loss=0.2806, pruned_loss=0.03793, over 7344.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2692, pruned_loss=0.03623, over 1427112.17 frames.], batch size: 22, lr: 3.52e-04
+2022-04-29 19:54:51,960 INFO [train.py:763] (6/8) Epoch 21, batch 3500, loss[loss=0.1841, simple_loss=0.283, pruned_loss=0.04265, over 7328.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2686, pruned_loss=0.03627, over 1429592.40 frames.], batch size: 22, lr: 3.52e-04
+2022-04-29 19:55:58,078 INFO [train.py:763] (6/8) Epoch 21, batch 3550, loss[loss=0.183, simple_loss=0.2787, pruned_loss=0.04369, over 6748.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2699, pruned_loss=0.03683, over 1428420.32 frames.], batch size: 31, lr: 3.52e-04
+2022-04-29 19:57:04,821 INFO [train.py:763] (6/8) Epoch 21, batch 3600, loss[loss=0.1411, simple_loss=0.2391, pruned_loss=0.02154, over 7286.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2701, pruned_loss=0.03721, over 1423386.91 frames.], batch size: 17, lr: 3.51e-04
+2022-04-29 19:58:10,363 INFO [train.py:763] (6/8) Epoch 21, batch 3650, loss[loss=0.1834, simple_loss=0.2755, pruned_loss=0.04565, over 7375.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2706, pruned_loss=0.03706, over 1424538.39 frames.], batch size: 23, lr: 3.51e-04
+2022-04-29 19:59:15,684 INFO [train.py:763] (6/8) Epoch 21, batch 3700, loss[loss=0.1682, simple_loss=0.2688, pruned_loss=0.03383, over 7221.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2696, pruned_loss=0.03631, over 1426829.99 frames.], batch size: 21, lr: 3.51e-04
+2022-04-29 20:00:21,232 INFO [train.py:763] (6/8) Epoch 21, batch 3750, loss[loss=0.1443, simple_loss=0.2402, pruned_loss=0.02424, over 6983.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2689, pruned_loss=0.03616, over 1430382.52 frames.], batch size: 16, lr: 3.51e-04
+2022-04-29 20:01:26,921 INFO [train.py:763] (6/8) Epoch 21, batch 3800, loss[loss=0.1999, simple_loss=0.294, pruned_loss=0.05293, over 4910.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2687, pruned_loss=0.03647, over 1424288.92 frames.], batch size: 52, lr: 3.51e-04
+2022-04-29 20:02:32,251 INFO [train.py:763] (6/8) Epoch 21, batch 3850, loss[loss=0.1797, simple_loss=0.2785, pruned_loss=0.04052, over 7233.00 frames.], tot_loss[loss=0.171, simple_loss=0.2694, pruned_loss=0.03632, over 1427145.83 frames.], batch size: 20, lr: 3.51e-04
+2022-04-29 20:03:37,825 INFO [train.py:763] (6/8) Epoch 21, batch 3900, loss[loss=0.1643, simple_loss=0.2714, pruned_loss=0.02865, over 6574.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2682, pruned_loss=0.03533, over 1426931.63 frames.], batch size: 38, lr: 3.51e-04
+2022-04-29 20:04:43,336 INFO [train.py:763] (6/8) Epoch 21, batch 3950, loss[loss=0.1471, simple_loss=0.2444, pruned_loss=0.02492, over 7274.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2678, pruned_loss=0.03548, over 1425507.29 frames.], batch size: 17, lr: 3.51e-04
+2022-04-29 20:05:50,733 INFO [train.py:763] (6/8) Epoch 21, batch 4000, loss[loss=0.1708, simple_loss=0.2767, pruned_loss=0.03247, over 7310.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2685, pruned_loss=0.03582, over 1425678.95 frames.], batch size: 21, lr: 3.51e-04
+2022-04-29 20:06:57,086 INFO [train.py:763] (6/8) Epoch 21, batch 4050, loss[loss=0.1667, simple_loss=0.2613, pruned_loss=0.03611, over 7357.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2675, pruned_loss=0.03519, over 1424364.26 frames.], batch size: 19, lr: 3.51e-04
+2022-04-29 20:08:02,548 INFO [train.py:763] (6/8) Epoch 21, batch 4100, loss[loss=0.1412, simple_loss=0.25, pruned_loss=0.01618, over 7325.00 frames.], tot_loss[loss=0.1694, simple_loss=0.268, pruned_loss=0.03544, over 1425357.64 frames.], batch size: 20, lr: 3.51e-04
+2022-04-29 20:09:08,418 INFO [train.py:763] (6/8) Epoch 21, batch 4150, loss[loss=0.1717, simple_loss=0.2701, pruned_loss=0.03668, over 7060.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2675, pruned_loss=0.03551, over 1421035.61 frames.], batch size: 18, lr: 3.51e-04
+2022-04-29 20:10:23,430 INFO [train.py:763] (6/8) Epoch 21, batch 4200, loss[loss=0.1849, simple_loss=0.2805, pruned_loss=0.04461, over 7139.00 frames.], tot_loss[loss=0.169, simple_loss=0.2675, pruned_loss=0.03524, over 1416671.63 frames.], batch size: 20, lr: 3.50e-04
+2022-04-29 20:11:28,557 INFO [train.py:763] (6/8) Epoch 21, batch 4250, loss[loss=0.1738, simple_loss=0.2831, pruned_loss=0.03228, over 6886.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2689, pruned_loss=0.03566, over 1410533.76 frames.], batch size: 31, lr: 3.50e-04
+2022-04-29 20:12:34,520 INFO [train.py:763] (6/8) Epoch 21, batch 4300, loss[loss=0.1742, simple_loss=0.2735, pruned_loss=0.0375, over 7278.00 frames.], tot_loss[loss=0.17, simple_loss=0.2692, pruned_loss=0.03536, over 1411946.16 frames.], batch size: 24, lr: 3.50e-04
+2022-04-29 20:13:40,144 INFO [train.py:763] (6/8) Epoch 21, batch 4350, loss[loss=0.2028, simple_loss=0.3177, pruned_loss=0.04401, over 7336.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2701, pruned_loss=0.03547, over 1409056.08 frames.], batch size: 22, lr: 3.50e-04
+2022-04-29 20:14:45,324 INFO [train.py:763] (6/8) Epoch 21, batch 4400, loss[loss=0.1752, simple_loss=0.276, pruned_loss=0.03719, over 7094.00 frames.], tot_loss[loss=0.1706, simple_loss=0.27, pruned_loss=0.0356, over 1402930.01 frames.], batch size: 21, lr: 3.50e-04
+2022-04-29 20:15:50,789 INFO [train.py:763] (6/8) Epoch 21, batch 4450, loss[loss=0.1681, simple_loss=0.2786, pruned_loss=0.02877, over 7339.00 frames.], tot_loss[loss=0.171, simple_loss=0.2704, pruned_loss=0.03576, over 1399716.89 frames.], batch size: 22, lr: 3.50e-04
+2022-04-29 20:17:22,859 INFO [train.py:763] (6/8) Epoch 21, batch 4500, loss[loss=0.1949, simple_loss=0.2914, pruned_loss=0.04918, over 7051.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2721, pruned_loss=0.03708, over 1389921.34 frames.], batch size: 28, lr: 3.50e-04
+2022-04-29 20:18:27,310 INFO [train.py:763] (6/8) Epoch 21, batch 4550, loss[loss=0.1669, simple_loss=0.2643, pruned_loss=0.03469, over 5090.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2732, pruned_loss=0.03781, over 1347580.00 frames.], batch size: 52, lr: 3.50e-04
+2022-04-29 20:20:15,479 INFO [train.py:763] (6/8) Epoch 22, batch 0, loss[loss=0.1711, simple_loss=0.2645, pruned_loss=0.03886, over 6807.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2645, pruned_loss=0.03886, over 6807.00 frames.], batch size: 15, lr: 3.42e-04
+2022-04-29 20:21:30,526 INFO [train.py:763] (6/8) Epoch 22, batch 50, loss[loss=0.1433, simple_loss=0.2363, pruned_loss=0.02514, over 7154.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2655, pruned_loss=0.03488, over 319970.24 frames.], batch size: 19, lr: 3.42e-04
+2022-04-29 20:22:35,943 INFO [train.py:763] (6/8) Epoch 22, batch 100, loss[loss=0.1428, simple_loss=0.2353, pruned_loss=0.02511, over 7277.00 frames.], tot_loss[loss=0.168, simple_loss=0.2668, pruned_loss=0.03458, over 566119.79 frames.], batch size: 18, lr: 3.42e-04
+2022-04-29 20:23:41,422 INFO [train.py:763] (6/8) Epoch 22, batch 150, loss[loss=0.1647, simple_loss=0.2601, pruned_loss=0.03468, over 7281.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2692, pruned_loss=0.03499, over 753576.45 frames.], batch size: 24, lr: 3.42e-04
+2022-04-29 20:24:46,883 INFO [train.py:763] (6/8) Epoch 22, batch 200, loss[loss=0.1552, simple_loss=0.2579, pruned_loss=0.02622, over 6517.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2684, pruned_loss=0.03503, over 902668.03 frames.], batch size: 37, lr: 3.42e-04
+2022-04-29 20:25:52,443 INFO [train.py:763] (6/8) Epoch 22, batch 250, loss[loss=0.1691, simple_loss=0.2718, pruned_loss=0.03318, over 7206.00 frames.], tot_loss[loss=0.1697, simple_loss=0.269, pruned_loss=0.03518, over 1017723.01 frames.], batch size: 23, lr: 3.42e-04
+2022-04-29 20:26:58,034 INFO [train.py:763] (6/8) Epoch 22, batch 300, loss[loss=0.1729, simple_loss=0.2727, pruned_loss=0.0366, over 7158.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2683, pruned_loss=0.03543, over 1104337.96 frames.], batch size: 19, lr: 3.42e-04
+2022-04-29 20:28:05,354 INFO [train.py:763] (6/8) Epoch 22, batch 350, loss[loss=0.1571, simple_loss=0.2578, pruned_loss=0.0282, over 7340.00 frames.], tot_loss[loss=0.17, simple_loss=0.2685, pruned_loss=0.03578, over 1178853.10 frames.], batch size: 22, lr: 3.42e-04
+2022-04-29 20:29:12,806 INFO [train.py:763] (6/8) Epoch 22, batch 400, loss[loss=0.1689, simple_loss=0.2682, pruned_loss=0.03478, over 7211.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2685, pruned_loss=0.0359, over 1231266.97 frames.], batch size: 23, lr: 3.42e-04
+2022-04-29 20:30:18,164 INFO [train.py:763] (6/8) Epoch 22, batch 450, loss[loss=0.1915, simple_loss=0.29, pruned_loss=0.0465, over 7289.00 frames.], tot_loss[loss=0.1693, simple_loss=0.268, pruned_loss=0.03528, over 1271889.18 frames.], batch size: 24, lr: 3.42e-04
+2022-04-29 20:31:24,348 INFO [train.py:763] (6/8) Epoch 22, batch 500, loss[loss=0.1556, simple_loss=0.2489, pruned_loss=0.03121, over 7227.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2686, pruned_loss=0.03579, over 1307864.89 frames.], batch size: 16, lr: 3.41e-04
+2022-04-29 20:32:31,828 INFO [train.py:763] (6/8) Epoch 22, batch 550, loss[loss=0.1714, simple_loss=0.276, pruned_loss=0.03336, over 7293.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2681, pruned_loss=0.03573, over 1337472.11 frames.], batch size: 24, lr: 3.41e-04
+2022-04-29 20:33:39,039 INFO [train.py:763] (6/8) Epoch 22, batch 600, loss[loss=0.1774, simple_loss=0.2803, pruned_loss=0.03729, over 7104.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2688, pruned_loss=0.03622, over 1359464.95 frames.], batch size: 21, lr: 3.41e-04
+2022-04-29 20:34:44,744 INFO [train.py:763] (6/8) Epoch 22, batch 650, loss[loss=0.1523, simple_loss=0.2522, pruned_loss=0.02625, over 6728.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2684, pruned_loss=0.03586, over 1373808.35 frames.], batch size: 31, lr: 3.41e-04
+2022-04-29 20:35:51,885 INFO [train.py:763] (6/8) Epoch 22, batch 700, loss[loss=0.192, simple_loss=0.2919, pruned_loss=0.04606, over 5356.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2683, pruned_loss=0.03563, over 1381008.42 frames.], batch size: 54, lr: 3.41e-04
+2022-04-29 20:36:59,200 INFO [train.py:763] (6/8) Epoch 22, batch 750, loss[loss=0.1684, simple_loss=0.2679, pruned_loss=0.03444, over 7199.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2686, pruned_loss=0.03545, over 1391800.87 frames.], batch size: 23, lr: 3.41e-04
+2022-04-29 20:38:05,972 INFO [train.py:763] (6/8) Epoch 22, batch 800, loss[loss=0.1585, simple_loss=0.2527, pruned_loss=0.03211, over 7349.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2692, pruned_loss=0.03601, over 1396560.65 frames.], batch size: 19, lr: 3.41e-04
+2022-04-29 20:39:11,696 INFO [train.py:763] (6/8) Epoch 22, batch 850, loss[loss=0.1616, simple_loss=0.2629, pruned_loss=0.03011, over 7421.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2692, pruned_loss=0.03623, over 1405305.40 frames.], batch size: 20, lr: 3.41e-04
+2022-04-29 20:40:16,909 INFO [train.py:763] (6/8) Epoch 22, batch 900, loss[loss=0.1722, simple_loss=0.2751, pruned_loss=0.03466, over 7155.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2692, pruned_loss=0.03602, over 1409563.27 frames.], batch size: 19, lr: 3.41e-04
+2022-04-29 20:41:22,122 INFO [train.py:763] (6/8) Epoch 22, batch 950, loss[loss=0.1855, simple_loss=0.2883, pruned_loss=0.04137, over 7086.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2694, pruned_loss=0.03573, over 1411439.88 frames.], batch size: 28, lr: 3.41e-04
+2022-04-29 20:42:27,345 INFO [train.py:763] (6/8) Epoch 22, batch 1000, loss[loss=0.1533, simple_loss=0.2522, pruned_loss=0.0272, over 7359.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2692, pruned_loss=0.03548, over 1418534.15 frames.], batch size: 19, lr: 3.41e-04
+2022-04-29 20:43:32,806 INFO [train.py:763] (6/8) Epoch 22, batch 1050, loss[loss=0.188, simple_loss=0.2812, pruned_loss=0.04738, over 4856.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2685, pruned_loss=0.03528, over 1418880.47 frames.], batch size: 52, lr: 3.41e-04
+2022-04-29 20:44:37,789 INFO [train.py:763] (6/8) Epoch 22, batch 1100, loss[loss=0.1445, simple_loss=0.2431, pruned_loss=0.02292, over 7258.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2686, pruned_loss=0.03518, over 1418463.37 frames.], batch size: 17, lr: 3.40e-04
+2022-04-29 20:45:43,155 INFO [train.py:763] (6/8) Epoch 22, batch 1150, loss[loss=0.1599, simple_loss=0.257, pruned_loss=0.03139, over 7428.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2686, pruned_loss=0.03529, over 1422405.60 frames.], batch size: 20, lr: 3.40e-04
+2022-04-29 20:46:49,112 INFO [train.py:763] (6/8) Epoch 22, batch 1200, loss[loss=0.1368, simple_loss=0.2232, pruned_loss=0.02513, over 7290.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2685, pruned_loss=0.03496, over 1421197.00 frames.], batch size: 18, lr: 3.40e-04
+2022-04-29 20:47:55,636 INFO [train.py:763] (6/8) Epoch 22, batch 1250, loss[loss=0.1442, simple_loss=0.2368, pruned_loss=0.0258, over 7233.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2676, pruned_loss=0.03506, over 1424817.75 frames.], batch size: 16, lr: 3.40e-04
+2022-04-29 20:49:00,849 INFO [train.py:763] (6/8) Epoch 22, batch 1300, loss[loss=0.1889, simple_loss=0.2815, pruned_loss=0.04815, over 7203.00 frames.], tot_loss[loss=0.169, simple_loss=0.2676, pruned_loss=0.03515, over 1427443.55 frames.], batch size: 23, lr: 3.40e-04
+2022-04-29 20:50:07,454 INFO [train.py:763] (6/8) Epoch 22, batch 1350, loss[loss=0.1614, simple_loss=0.2511, pruned_loss=0.03588, over 7282.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2665, pruned_loss=0.03494, over 1428033.70 frames.], batch size: 18, lr: 3.40e-04
+2022-04-29 20:51:13,806 INFO [train.py:763] (6/8) Epoch 22, batch 1400, loss[loss=0.1803, simple_loss=0.282, pruned_loss=0.03932, over 7114.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2666, pruned_loss=0.03501, over 1428544.41 frames.], batch size: 21, lr: 3.40e-04
+2022-04-29 20:52:19,586 INFO [train.py:763] (6/8) Epoch 22, batch 1450, loss[loss=0.1507, simple_loss=0.2373, pruned_loss=0.03203, over 7405.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2669, pruned_loss=0.035, over 1422738.09 frames.], batch size: 18, lr: 3.40e-04
+2022-04-29 20:53:25,451 INFO [train.py:763] (6/8) Epoch 22, batch 1500, loss[loss=0.154, simple_loss=0.2607, pruned_loss=0.02363, over 7129.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2647, pruned_loss=0.03421, over 1423423.13 frames.], batch size: 28, lr: 3.40e-04
+2022-04-29 20:54:31,380 INFO [train.py:763] (6/8) Epoch 22, batch 1550, loss[loss=0.1636, simple_loss=0.2675, pruned_loss=0.02987, over 7355.00 frames.], tot_loss[loss=0.168, simple_loss=0.2661, pruned_loss=0.03494, over 1414288.41 frames.], batch size: 19, lr: 3.40e-04
+2022-04-29 20:55:37,832 INFO [train.py:763] (6/8) Epoch 22, batch 1600, loss[loss=0.2097, simple_loss=0.3042, pruned_loss=0.05764, over 7216.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2663, pruned_loss=0.03512, over 1412107.93 frames.], batch size: 21, lr: 3.40e-04
+2022-04-29 20:56:43,434 INFO [train.py:763] (6/8) Epoch 22, batch 1650, loss[loss=0.1937, simple_loss=0.2875, pruned_loss=0.04999, over 7350.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2665, pruned_loss=0.03504, over 1414935.31 frames.], batch size: 23, lr: 3.40e-04
+2022-04-29 20:57:48,936 INFO [train.py:763] (6/8) Epoch 22, batch 1700, loss[loss=0.1461, simple_loss=0.2434, pruned_loss=0.02444, over 7410.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2673, pruned_loss=0.03569, over 1416549.38 frames.], batch size: 18, lr: 3.39e-04
+2022-04-29 20:58:54,072 INFO [train.py:763] (6/8) Epoch 22, batch 1750, loss[loss=0.2139, simple_loss=0.3106, pruned_loss=0.05856, over 7168.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2686, pruned_loss=0.03586, over 1415021.79 frames.], batch size: 26, lr: 3.39e-04
+2022-04-29 20:59:59,909 INFO [train.py:763] (6/8) Epoch 22, batch 1800, loss[loss=0.1841, simple_loss=0.2835, pruned_loss=0.04233, over 4991.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2688, pruned_loss=0.03569, over 1411920.73 frames.], batch size: 52, lr: 3.39e-04
+2022-04-29 21:01:05,541 INFO [train.py:763] (6/8) Epoch 22, batch 1850, loss[loss=0.154, simple_loss=0.2508, pruned_loss=0.02854, over 7428.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2685, pruned_loss=0.03562, over 1417061.29 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:02:10,915 INFO [train.py:763] (6/8) Epoch 22, batch 1900, loss[loss=0.1821, simple_loss=0.2829, pruned_loss=0.04067, over 7154.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2678, pruned_loss=0.03553, over 1420402.16 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:03:17,154 INFO [train.py:763] (6/8) Epoch 22, batch 1950, loss[loss=0.1974, simple_loss=0.2948, pruned_loss=0.05002, over 7146.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2678, pruned_loss=0.03548, over 1417474.76 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:04:22,499 INFO [train.py:763] (6/8) Epoch 22, batch 2000, loss[loss=0.1628, simple_loss=0.26, pruned_loss=0.03285, over 7262.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2687, pruned_loss=0.03548, over 1421097.30 frames.], batch size: 19, lr: 3.39e-04
+2022-04-29 21:05:28,500 INFO [train.py:763] (6/8) Epoch 22, batch 2050, loss[loss=0.1754, simple_loss=0.2735, pruned_loss=0.0387, over 7231.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2686, pruned_loss=0.03508, over 1425143.33 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:06:35,603 INFO [train.py:763] (6/8) Epoch 22, batch 2100, loss[loss=0.1934, simple_loss=0.291, pruned_loss=0.0479, over 7199.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2681, pruned_loss=0.03503, over 1420440.89 frames.], batch size: 23, lr: 3.39e-04
+2022-04-29 21:07:42,148 INFO [train.py:763] (6/8) Epoch 22, batch 2150, loss[loss=0.1894, simple_loss=0.2715, pruned_loss=0.05362, over 7154.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2677, pruned_loss=0.03521, over 1421975.65 frames.], batch size: 19, lr: 3.39e-04
+2022-04-29 21:08:47,297 INFO [train.py:763] (6/8) Epoch 22, batch 2200, loss[loss=0.154, simple_loss=0.2644, pruned_loss=0.02177, over 7144.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2678, pruned_loss=0.03537, over 1417263.41 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:09:53,599 INFO [train.py:763] (6/8) Epoch 22, batch 2250, loss[loss=0.2289, simple_loss=0.314, pruned_loss=0.07186, over 7169.00 frames.], tot_loss[loss=0.1697, simple_loss=0.268, pruned_loss=0.03571, over 1412975.78 frames.], batch size: 19, lr: 3.39e-04
+2022-04-29 21:11:00,755 INFO [train.py:763] (6/8) Epoch 22, batch 2300, loss[loss=0.1699, simple_loss=0.2787, pruned_loss=0.03056, over 7307.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2668, pruned_loss=0.03512, over 1414357.45 frames.], batch size: 21, lr: 3.38e-04
+2022-04-29 21:12:07,677 INFO [train.py:763] (6/8) Epoch 22, batch 2350, loss[loss=0.1844, simple_loss=0.2902, pruned_loss=0.03934, over 7323.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2672, pruned_loss=0.0349, over 1416067.03 frames.], batch size: 22, lr: 3.38e-04
+2022-04-29 21:13:14,396 INFO [train.py:763] (6/8) Epoch 22, batch 2400, loss[loss=0.1748, simple_loss=0.2761, pruned_loss=0.03674, over 7311.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2681, pruned_loss=0.0353, over 1417937.02 frames.], batch size: 24, lr: 3.38e-04
+2022-04-29 21:14:19,604 INFO [train.py:763] (6/8) Epoch 22, batch 2450, loss[loss=0.1742, simple_loss=0.2797, pruned_loss=0.03436, over 7202.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2693, pruned_loss=0.0359, over 1421987.92 frames.], batch size: 22, lr: 3.38e-04
+2022-04-29 21:15:24,879 INFO [train.py:763] (6/8) Epoch 22, batch 2500, loss[loss=0.1787, simple_loss=0.2881, pruned_loss=0.03468, over 6401.00 frames.], tot_loss[loss=0.1698, simple_loss=0.268, pruned_loss=0.03581, over 1420384.52 frames.], batch size: 38, lr: 3.38e-04
+2022-04-29 21:16:30,045 INFO [train.py:763] (6/8) Epoch 22, batch 2550, loss[loss=0.1602, simple_loss=0.2565, pruned_loss=0.03202, over 7365.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2679, pruned_loss=0.03569, over 1421351.64 frames.], batch size: 23, lr: 3.38e-04
+2022-04-29 21:17:35,652 INFO [train.py:763] (6/8) Epoch 22, batch 2600, loss[loss=0.1437, simple_loss=0.2498, pruned_loss=0.01884, over 7336.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2678, pruned_loss=0.03553, over 1426031.03 frames.], batch size: 22, lr: 3.38e-04
+2022-04-29 21:18:41,157 INFO [train.py:763] (6/8) Epoch 22, batch 2650, loss[loss=0.2068, simple_loss=0.3034, pruned_loss=0.05509, over 7318.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2666, pruned_loss=0.03513, over 1423317.90 frames.], batch size: 25, lr: 3.38e-04
+2022-04-29 21:19:46,643 INFO [train.py:763] (6/8) Epoch 22, batch 2700, loss[loss=0.175, simple_loss=0.2725, pruned_loss=0.0388, over 7149.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2671, pruned_loss=0.03557, over 1423433.45 frames.], batch size: 19, lr: 3.38e-04
+2022-04-29 21:20:54,008 INFO [train.py:763] (6/8) Epoch 22, batch 2750, loss[loss=0.1657, simple_loss=0.2571, pruned_loss=0.03715, over 7154.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2671, pruned_loss=0.0359, over 1421187.83 frames.], batch size: 18, lr: 3.38e-04
+2022-04-29 21:22:00,025 INFO [train.py:763] (6/8) Epoch 22, batch 2800, loss[loss=0.1621, simple_loss=0.2481, pruned_loss=0.03799, over 7155.00 frames.], tot_loss[loss=0.17, simple_loss=0.2676, pruned_loss=0.03622, over 1421024.07 frames.], batch size: 18, lr: 3.38e-04
+2022-04-29 21:23:05,438 INFO [train.py:763] (6/8) Epoch 22, batch 2850, loss[loss=0.1778, simple_loss=0.2876, pruned_loss=0.03399, over 7108.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2669, pruned_loss=0.03571, over 1422257.18 frames.], batch size: 28, lr: 3.38e-04
+2022-04-29 21:24:10,664 INFO [train.py:763] (6/8) Epoch 22, batch 2900, loss[loss=0.1573, simple_loss=0.2676, pruned_loss=0.02348, over 7277.00 frames.], tot_loss[loss=0.1688, simple_loss=0.267, pruned_loss=0.03532, over 1423817.93 frames.], batch size: 25, lr: 3.37e-04
+2022-04-29 21:25:15,972 INFO [train.py:763] (6/8) Epoch 22, batch 2950, loss[loss=0.1764, simple_loss=0.2727, pruned_loss=0.04008, over 7203.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2676, pruned_loss=0.03568, over 1424363.30 frames.], batch size: 22, lr: 3.37e-04
+2022-04-29 21:26:20,974 INFO [train.py:763] (6/8) Epoch 22, batch 3000, loss[loss=0.1398, simple_loss=0.224, pruned_loss=0.0278, over 6986.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2666, pruned_loss=0.03488, over 1424213.58 frames.], batch size: 16, lr: 3.37e-04
+2022-04-29 21:26:20,975 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 21:26:36,379 INFO [train.py:792] (6/8) Epoch 22, validation: loss=0.1681, simple_loss=0.2667, pruned_loss=0.03474, over 698248.00 frames.
+2022-04-29 21:27:41,668 INFO [train.py:763] (6/8) Epoch 22, batch 3050, loss[loss=0.1742, simple_loss=0.2647, pruned_loss=0.04185, over 7170.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2663, pruned_loss=0.03503, over 1426352.64 frames.], batch size: 19, lr: 3.37e-04
+2022-04-29 21:28:58,462 INFO [train.py:763] (6/8) Epoch 22, batch 3100, loss[loss=0.164, simple_loss=0.2656, pruned_loss=0.03117, over 7235.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2653, pruned_loss=0.03473, over 1424775.42 frames.], batch size: 20, lr: 3.37e-04
+2022-04-29 21:30:03,942 INFO [train.py:763] (6/8) Epoch 22, batch 3150, loss[loss=0.1617, simple_loss=0.2655, pruned_loss=0.02895, over 7318.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2655, pruned_loss=0.03441, over 1426363.28 frames.], batch size: 20, lr: 3.37e-04
+2022-04-29 21:31:09,276 INFO [train.py:763] (6/8) Epoch 22, batch 3200, loss[loss=0.1602, simple_loss=0.2724, pruned_loss=0.02398, over 7123.00 frames.], tot_loss[loss=0.167, simple_loss=0.2653, pruned_loss=0.03439, over 1427210.66 frames.], batch size: 21, lr: 3.37e-04
+2022-04-29 21:32:14,550 INFO [train.py:763] (6/8) Epoch 22, batch 3250, loss[loss=0.1556, simple_loss=0.2709, pruned_loss=0.02013, over 6306.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2672, pruned_loss=0.03525, over 1422198.81 frames.], batch size: 37, lr: 3.37e-04
+2022-04-29 21:33:19,829 INFO [train.py:763] (6/8) Epoch 22, batch 3300, loss[loss=0.1858, simple_loss=0.2793, pruned_loss=0.04612, over 7286.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2671, pruned_loss=0.035, over 1422660.36 frames.], batch size: 24, lr: 3.37e-04
+2022-04-29 21:34:25,357 INFO [train.py:763] (6/8) Epoch 22, batch 3350, loss[loss=0.2156, simple_loss=0.3003, pruned_loss=0.06543, over 7140.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2659, pruned_loss=0.03489, over 1427166.64 frames.], batch size: 26, lr: 3.37e-04
+2022-04-29 21:35:30,551 INFO [train.py:763] (6/8) Epoch 22, batch 3400, loss[loss=0.161, simple_loss=0.2595, pruned_loss=0.0313, over 7156.00 frames.], tot_loss[loss=0.168, simple_loss=0.2659, pruned_loss=0.03511, over 1428560.59 frames.], batch size: 19, lr: 3.37e-04
+2022-04-29 21:36:36,032 INFO [train.py:763] (6/8) Epoch 22, batch 3450, loss[loss=0.1385, simple_loss=0.2252, pruned_loss=0.02595, over 6769.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2649, pruned_loss=0.03461, over 1429754.92 frames.], batch size: 15, lr: 3.37e-04
+2022-04-29 21:37:41,468 INFO [train.py:763] (6/8) Epoch 22, batch 3500, loss[loss=0.1556, simple_loss=0.2479, pruned_loss=0.03159, over 6849.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2649, pruned_loss=0.03421, over 1430966.40 frames.], batch size: 15, lr: 3.37e-04
+2022-04-29 21:38:46,763 INFO [train.py:763] (6/8) Epoch 22, batch 3550, loss[loss=0.1414, simple_loss=0.2324, pruned_loss=0.02518, over 7413.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2653, pruned_loss=0.03416, over 1431073.78 frames.], batch size: 18, lr: 3.36e-04
+2022-04-29 21:39:52,005 INFO [train.py:763] (6/8) Epoch 22, batch 3600, loss[loss=0.1624, simple_loss=0.2536, pruned_loss=0.03554, over 7275.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2665, pruned_loss=0.03463, over 1431921.39 frames.], batch size: 17, lr: 3.36e-04
+2022-04-29 21:40:57,417 INFO [train.py:763] (6/8) Epoch 22, batch 3650, loss[loss=0.1702, simple_loss=0.2718, pruned_loss=0.03433, over 6392.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2669, pruned_loss=0.03494, over 1431285.84 frames.], batch size: 38, lr: 3.36e-04
+2022-04-29 21:42:03,752 INFO [train.py:763] (6/8) Epoch 22, batch 3700, loss[loss=0.1677, simple_loss=0.2694, pruned_loss=0.03303, over 7159.00 frames.], tot_loss[loss=0.1684, simple_loss=0.267, pruned_loss=0.03494, over 1430073.11 frames.], batch size: 19, lr: 3.36e-04
+2022-04-29 21:43:09,192 INFO [train.py:763] (6/8) Epoch 22, batch 3750, loss[loss=0.1506, simple_loss=0.2454, pruned_loss=0.02784, over 7276.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2669, pruned_loss=0.03467, over 1428290.78 frames.], batch size: 17, lr: 3.36e-04
+2022-04-29 21:44:14,440 INFO [train.py:763] (6/8) Epoch 22, batch 3800, loss[loss=0.1754, simple_loss=0.2645, pruned_loss=0.04316, over 7361.00 frames.], tot_loss[loss=0.169, simple_loss=0.2676, pruned_loss=0.03525, over 1429524.84 frames.], batch size: 23, lr: 3.36e-04
+2022-04-29 21:45:19,892 INFO [train.py:763] (6/8) Epoch 22, batch 3850, loss[loss=0.1682, simple_loss=0.2765, pruned_loss=0.02994, over 7120.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2673, pruned_loss=0.03522, over 1430963.02 frames.], batch size: 28, lr: 3.36e-04
+2022-04-29 21:46:26,373 INFO [train.py:763] (6/8) Epoch 22, batch 3900, loss[loss=0.1731, simple_loss=0.2754, pruned_loss=0.03538, over 7448.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2672, pruned_loss=0.03518, over 1431570.31 frames.], batch size: 22, lr: 3.36e-04
+2022-04-29 21:47:31,493 INFO [train.py:763] (6/8) Epoch 22, batch 3950, loss[loss=0.1722, simple_loss=0.2636, pruned_loss=0.04044, over 7167.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2675, pruned_loss=0.03502, over 1430831.67 frames.], batch size: 19, lr: 3.36e-04
+2022-04-29 21:48:36,598 INFO [train.py:763] (6/8) Epoch 22, batch 4000, loss[loss=0.1523, simple_loss=0.2379, pruned_loss=0.03341, over 7279.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2668, pruned_loss=0.03466, over 1427287.29 frames.], batch size: 17, lr: 3.36e-04
+2022-04-29 21:49:42,511 INFO [train.py:763] (6/8) Epoch 22, batch 4050, loss[loss=0.159, simple_loss=0.2424, pruned_loss=0.0378, over 6815.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2678, pruned_loss=0.03515, over 1421734.05 frames.], batch size: 15, lr: 3.36e-04
+2022-04-29 21:50:49,119 INFO [train.py:763] (6/8) Epoch 22, batch 4100, loss[loss=0.1456, simple_loss=0.2459, pruned_loss=0.02267, over 6827.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2674, pruned_loss=0.03483, over 1418643.55 frames.], batch size: 15, lr: 3.36e-04
+2022-04-29 21:51:54,119 INFO [train.py:763] (6/8) Epoch 22, batch 4150, loss[loss=0.1492, simple_loss=0.2439, pruned_loss=0.02728, over 7312.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2675, pruned_loss=0.03451, over 1418367.68 frames.], batch size: 21, lr: 3.35e-04
+2022-04-29 21:52:59,301 INFO [train.py:763] (6/8) Epoch 22, batch 4200, loss[loss=0.15, simple_loss=0.2365, pruned_loss=0.03175, over 7412.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2683, pruned_loss=0.03501, over 1423003.59 frames.], batch size: 17, lr: 3.35e-04
+2022-04-29 21:54:05,492 INFO [train.py:763] (6/8) Epoch 22, batch 4250, loss[loss=0.1616, simple_loss=0.2628, pruned_loss=0.03024, over 7233.00 frames.], tot_loss[loss=0.1688, simple_loss=0.268, pruned_loss=0.03481, over 1424035.68 frames.], batch size: 20, lr: 3.35e-04
+2022-04-29 21:55:12,488 INFO [train.py:763] (6/8) Epoch 22, batch 4300, loss[loss=0.1394, simple_loss=0.2412, pruned_loss=0.01883, over 7158.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2666, pruned_loss=0.03453, over 1420973.66 frames.], batch size: 18, lr: 3.35e-04
+2022-04-29 21:56:19,757 INFO [train.py:763] (6/8) Epoch 22, batch 4350, loss[loss=0.143, simple_loss=0.2366, pruned_loss=0.0247, over 6840.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2657, pruned_loss=0.03401, over 1422363.88 frames.], batch size: 15, lr: 3.35e-04
+2022-04-29 21:57:26,791 INFO [train.py:763] (6/8) Epoch 22, batch 4400, loss[loss=0.1724, simple_loss=0.2595, pruned_loss=0.04268, over 7072.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2659, pruned_loss=0.03421, over 1419237.50 frames.], batch size: 18, lr: 3.35e-04
+2022-04-29 21:58:31,945 INFO [train.py:763] (6/8) Epoch 22, batch 4450, loss[loss=0.2095, simple_loss=0.3063, pruned_loss=0.0564, over 4816.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2664, pruned_loss=0.03447, over 1413019.81 frames.], batch size: 53, lr: 3.35e-04
+2022-04-29 21:59:36,919 INFO [train.py:763] (6/8) Epoch 22, batch 4500, loss[loss=0.1691, simple_loss=0.2625, pruned_loss=0.03789, over 7066.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2665, pruned_loss=0.03444, over 1412465.12 frames.], batch size: 18, lr: 3.35e-04
+2022-04-29 22:00:41,212 INFO [train.py:763] (6/8) Epoch 22, batch 4550, loss[loss=0.1915, simple_loss=0.2814, pruned_loss=0.0508, over 5117.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2701, pruned_loss=0.03685, over 1354385.29 frames.], batch size: 52, lr: 3.35e-04
+2022-04-29 22:02:00,634 INFO [train.py:763] (6/8) Epoch 23, batch 0, loss[loss=0.1525, simple_loss=0.2376, pruned_loss=0.03369, over 6802.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2376, pruned_loss=0.03369, over 6802.00 frames.], batch size: 15, lr: 3.28e-04
+2022-04-29 22:03:02,943 INFO [train.py:763] (6/8) Epoch 23, batch 50, loss[loss=0.155, simple_loss=0.252, pruned_loss=0.02901, over 7279.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2633, pruned_loss=0.0331, over 316994.30 frames.], batch size: 17, lr: 3.28e-04
+2022-04-29 22:04:05,009 INFO [train.py:763] (6/8) Epoch 23, batch 100, loss[loss=0.1835, simple_loss=0.2793, pruned_loss=0.04381, over 7324.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2643, pruned_loss=0.03292, over 567927.96 frames.], batch size: 20, lr: 3.28e-04
+2022-04-29 22:05:10,556 INFO [train.py:763] (6/8) Epoch 23, batch 150, loss[loss=0.1716, simple_loss=0.2766, pruned_loss=0.03332, over 7393.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2653, pruned_loss=0.03381, over 753860.87 frames.], batch size: 23, lr: 3.28e-04
+2022-04-29 22:06:15,912 INFO [train.py:763] (6/8) Epoch 23, batch 200, loss[loss=0.1686, simple_loss=0.2846, pruned_loss=0.02629, over 7200.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2666, pruned_loss=0.0345, over 904301.40 frames.], batch size: 22, lr: 3.28e-04
+2022-04-29 22:07:21,265 INFO [train.py:763] (6/8) Epoch 23, batch 250, loss[loss=0.1788, simple_loss=0.2814, pruned_loss=0.03806, over 7415.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2672, pruned_loss=0.03508, over 1015993.92 frames.], batch size: 21, lr: 3.28e-04
+2022-04-29 22:08:27,019 INFO [train.py:763] (6/8) Epoch 23, batch 300, loss[loss=0.1701, simple_loss=0.2774, pruned_loss=0.0314, over 7146.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2683, pruned_loss=0.03497, over 1107249.64 frames.], batch size: 20, lr: 3.27e-04
+2022-04-29 22:09:32,881 INFO [train.py:763] (6/8) Epoch 23, batch 350, loss[loss=0.167, simple_loss=0.2761, pruned_loss=0.02893, over 7318.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2681, pruned_loss=0.03474, over 1179289.05 frames.], batch size: 25, lr: 3.27e-04
+2022-04-29 22:10:38,046 INFO [train.py:763] (6/8) Epoch 23, batch 400, loss[loss=0.188, simple_loss=0.288, pruned_loss=0.04396, over 7296.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2671, pruned_loss=0.03484, over 1230249.15 frames.], batch size: 24, lr: 3.27e-04
+2022-04-29 22:11:43,826 INFO [train.py:763] (6/8) Epoch 23, batch 450, loss[loss=0.1427, simple_loss=0.2411, pruned_loss=0.0221, over 7145.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2674, pruned_loss=0.03474, over 1275651.52 frames.], batch size: 20, lr: 3.27e-04
+2022-04-29 22:12:49,136 INFO [train.py:763] (6/8) Epoch 23, batch 500, loss[loss=0.1554, simple_loss=0.2501, pruned_loss=0.03032, over 7354.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2672, pruned_loss=0.03468, over 1307552.60 frames.], batch size: 19, lr: 3.27e-04
+2022-04-29 22:13:54,753 INFO [train.py:763] (6/8) Epoch 23, batch 550, loss[loss=0.1762, simple_loss=0.2738, pruned_loss=0.03929, over 7194.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2671, pruned_loss=0.03462, over 1336237.85 frames.], batch size: 22, lr: 3.27e-04
+2022-04-29 22:15:00,602 INFO [train.py:763] (6/8) Epoch 23, batch 600, loss[loss=0.1821, simple_loss=0.2812, pruned_loss=0.04151, over 7356.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2664, pruned_loss=0.03469, over 1353445.54 frames.], batch size: 19, lr: 3.27e-04
+2022-04-29 22:16:06,055 INFO [train.py:763] (6/8) Epoch 23, batch 650, loss[loss=0.1584, simple_loss=0.2513, pruned_loss=0.03277, over 7356.00 frames.], tot_loss[loss=0.167, simple_loss=0.2655, pruned_loss=0.03428, over 1364343.90 frames.], batch size: 19, lr: 3.27e-04
+2022-04-29 22:17:12,011 INFO [train.py:763] (6/8) Epoch 23, batch 700, loss[loss=0.1792, simple_loss=0.282, pruned_loss=0.03816, over 7192.00 frames.], tot_loss[loss=0.1659, simple_loss=0.264, pruned_loss=0.03391, over 1381375.27 frames.], batch size: 26, lr: 3.27e-04
+2022-04-29 22:18:17,841 INFO [train.py:763] (6/8) Epoch 23, batch 750, loss[loss=0.1539, simple_loss=0.247, pruned_loss=0.03036, over 7011.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2646, pruned_loss=0.0339, over 1393223.89 frames.], batch size: 16, lr: 3.27e-04
+2022-04-29 22:19:23,433 INFO [train.py:763] (6/8) Epoch 23, batch 800, loss[loss=0.1578, simple_loss=0.2572, pruned_loss=0.02922, over 7256.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2646, pruned_loss=0.03395, over 1399965.42 frames.], batch size: 19, lr: 3.27e-04
+2022-04-29 22:20:28,945 INFO [train.py:763] (6/8) Epoch 23, batch 850, loss[loss=0.1789, simple_loss=0.2817, pruned_loss=0.03803, over 6595.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2641, pruned_loss=0.0338, over 1405629.37 frames.], batch size: 31, lr: 3.27e-04
+2022-04-29 22:21:34,332 INFO [train.py:763] (6/8) Epoch 23, batch 900, loss[loss=0.143, simple_loss=0.2395, pruned_loss=0.02323, over 7419.00 frames.], tot_loss[loss=0.166, simple_loss=0.2641, pruned_loss=0.03395, over 1410815.97 frames.], batch size: 20, lr: 3.27e-04
+2022-04-29 22:22:49,570 INFO [train.py:763] (6/8) Epoch 23, batch 950, loss[loss=0.156, simple_loss=0.2787, pruned_loss=0.01663, over 6462.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2636, pruned_loss=0.03338, over 1415266.51 frames.], batch size: 37, lr: 3.26e-04
+2022-04-29 22:23:55,240 INFO [train.py:763] (6/8) Epoch 23, batch 1000, loss[loss=0.1941, simple_loss=0.2947, pruned_loss=0.04672, over 7316.00 frames.], tot_loss[loss=0.1658, simple_loss=0.264, pruned_loss=0.03377, over 1417573.36 frames.], batch size: 21, lr: 3.26e-04
+2022-04-29 22:25:00,742 INFO [train.py:763] (6/8) Epoch 23, batch 1050, loss[loss=0.1845, simple_loss=0.2894, pruned_loss=0.03982, over 7238.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2651, pruned_loss=0.03415, over 1412741.91 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:26:07,029 INFO [train.py:763] (6/8) Epoch 23, batch 1100, loss[loss=0.179, simple_loss=0.2803, pruned_loss=0.03883, over 7147.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2653, pruned_loss=0.0343, over 1412323.32 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:27:12,600 INFO [train.py:763] (6/8) Epoch 23, batch 1150, loss[loss=0.1906, simple_loss=0.2896, pruned_loss=0.0458, over 6382.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2655, pruned_loss=0.03455, over 1415929.65 frames.], batch size: 38, lr: 3.26e-04
+2022-04-29 22:28:17,834 INFO [train.py:763] (6/8) Epoch 23, batch 1200, loss[loss=0.1446, simple_loss=0.2432, pruned_loss=0.02301, over 7162.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2661, pruned_loss=0.03448, over 1418699.17 frames.], batch size: 18, lr: 3.26e-04
+2022-04-29 22:29:23,309 INFO [train.py:763] (6/8) Epoch 23, batch 1250, loss[loss=0.1638, simple_loss=0.269, pruned_loss=0.02932, over 7328.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2655, pruned_loss=0.03441, over 1420043.15 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:30:28,894 INFO [train.py:763] (6/8) Epoch 23, batch 1300, loss[loss=0.178, simple_loss=0.278, pruned_loss=0.03903, over 6716.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2657, pruned_loss=0.03454, over 1421161.18 frames.], batch size: 31, lr: 3.26e-04
+2022-04-29 22:31:51,695 INFO [train.py:763] (6/8) Epoch 23, batch 1350, loss[loss=0.1494, simple_loss=0.2364, pruned_loss=0.03117, over 7417.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2662, pruned_loss=0.03456, over 1426296.49 frames.], batch size: 18, lr: 3.26e-04
+2022-04-29 22:32:57,245 INFO [train.py:763] (6/8) Epoch 23, batch 1400, loss[loss=0.2002, simple_loss=0.3054, pruned_loss=0.04745, over 7185.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2657, pruned_loss=0.03436, over 1424237.10 frames.], batch size: 26, lr: 3.26e-04
+2022-04-29 22:34:20,488 INFO [train.py:763] (6/8) Epoch 23, batch 1450, loss[loss=0.1651, simple_loss=0.2659, pruned_loss=0.03215, over 7146.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2662, pruned_loss=0.03428, over 1422681.96 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:35:53,303 INFO [train.py:763] (6/8) Epoch 23, batch 1500, loss[loss=0.1965, simple_loss=0.3012, pruned_loss=0.04586, over 7147.00 frames.], tot_loss[loss=0.167, simple_loss=0.2657, pruned_loss=0.03421, over 1421606.23 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:36:59,421 INFO [train.py:763] (6/8) Epoch 23, batch 1550, loss[loss=0.2039, simple_loss=0.3048, pruned_loss=0.05152, over 6761.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2664, pruned_loss=0.03439, over 1421284.10 frames.], batch size: 31, lr: 3.26e-04
+2022-04-29 22:38:04,560 INFO [train.py:763] (6/8) Epoch 23, batch 1600, loss[loss=0.1653, simple_loss=0.2693, pruned_loss=0.03063, over 7324.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2671, pruned_loss=0.03464, over 1422327.82 frames.], batch size: 20, lr: 3.25e-04
+2022-04-29 22:39:10,593 INFO [train.py:763] (6/8) Epoch 23, batch 1650, loss[loss=0.1666, simple_loss=0.2529, pruned_loss=0.04016, over 6862.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2674, pruned_loss=0.03492, over 1414338.56 frames.], batch size: 15, lr: 3.25e-04
+2022-04-29 22:40:17,829 INFO [train.py:763] (6/8) Epoch 23, batch 1700, loss[loss=0.1875, simple_loss=0.2981, pruned_loss=0.03841, over 7319.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2663, pruned_loss=0.03425, over 1417759.86 frames.], batch size: 21, lr: 3.25e-04
+2022-04-29 22:41:24,855 INFO [train.py:763] (6/8) Epoch 23, batch 1750, loss[loss=0.1556, simple_loss=0.2516, pruned_loss=0.02984, over 7071.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2671, pruned_loss=0.03469, over 1419649.54 frames.], batch size: 18, lr: 3.25e-04
+2022-04-29 22:42:30,372 INFO [train.py:763] (6/8) Epoch 23, batch 1800, loss[loss=0.1629, simple_loss=0.2655, pruned_loss=0.03022, over 7332.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2674, pruned_loss=0.03483, over 1420505.25 frames.], batch size: 22, lr: 3.25e-04
+2022-04-29 22:43:35,681 INFO [train.py:763] (6/8) Epoch 23, batch 1850, loss[loss=0.1645, simple_loss=0.2645, pruned_loss=0.03221, over 7306.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2679, pruned_loss=0.0349, over 1424359.22 frames.], batch size: 24, lr: 3.25e-04
+2022-04-29 22:44:41,104 INFO [train.py:763] (6/8) Epoch 23, batch 1900, loss[loss=0.1708, simple_loss=0.2825, pruned_loss=0.02957, over 7105.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2678, pruned_loss=0.03501, over 1422387.07 frames.], batch size: 28, lr: 3.25e-04
+2022-04-29 22:45:46,547 INFO [train.py:763] (6/8) Epoch 23, batch 1950, loss[loss=0.1758, simple_loss=0.2805, pruned_loss=0.03556, over 7124.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2684, pruned_loss=0.03521, over 1423511.91 frames.], batch size: 21, lr: 3.25e-04
+2022-04-29 22:46:52,101 INFO [train.py:763] (6/8) Epoch 23, batch 2000, loss[loss=0.2031, simple_loss=0.298, pruned_loss=0.05414, over 5092.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2686, pruned_loss=0.03543, over 1421213.73 frames.], batch size: 52, lr: 3.25e-04
+2022-04-29 22:47:58,955 INFO [train.py:763] (6/8) Epoch 23, batch 2050, loss[loss=0.1701, simple_loss=0.2664, pruned_loss=0.03691, over 7440.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2686, pruned_loss=0.03542, over 1421291.29 frames.], batch size: 20, lr: 3.25e-04
+2022-04-29 22:49:05,155 INFO [train.py:763] (6/8) Epoch 23, batch 2100, loss[loss=0.1757, simple_loss=0.2626, pruned_loss=0.04442, over 7016.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2683, pruned_loss=0.0354, over 1422956.64 frames.], batch size: 16, lr: 3.25e-04
+2022-04-29 22:50:10,654 INFO [train.py:763] (6/8) Epoch 23, batch 2150, loss[loss=0.2366, simple_loss=0.3156, pruned_loss=0.07881, over 5140.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2671, pruned_loss=0.0348, over 1420788.56 frames.], batch size: 52, lr: 3.25e-04
+2022-04-29 22:51:16,165 INFO [train.py:763] (6/8) Epoch 23, batch 2200, loss[loss=0.1457, simple_loss=0.2411, pruned_loss=0.02518, over 7138.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2668, pruned_loss=0.03468, over 1420186.03 frames.], batch size: 17, lr: 3.25e-04
+2022-04-29 22:52:21,334 INFO [train.py:763] (6/8) Epoch 23, batch 2250, loss[loss=0.1826, simple_loss=0.2862, pruned_loss=0.03948, over 7268.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2676, pruned_loss=0.03507, over 1410250.64 frames.], batch size: 25, lr: 3.24e-04
+2022-04-29 22:53:28,273 INFO [train.py:763] (6/8) Epoch 23, batch 2300, loss[loss=0.1555, simple_loss=0.2433, pruned_loss=0.03384, over 7299.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2671, pruned_loss=0.03485, over 1416942.08 frames.], batch size: 17, lr: 3.24e-04
+2022-04-29 22:54:34,466 INFO [train.py:763] (6/8) Epoch 23, batch 2350, loss[loss=0.1705, simple_loss=0.28, pruned_loss=0.03056, over 7343.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2673, pruned_loss=0.03466, over 1418083.96 frames.], batch size: 22, lr: 3.24e-04
+2022-04-29 22:55:39,751 INFO [train.py:763] (6/8) Epoch 23, batch 2400, loss[loss=0.1577, simple_loss=0.2463, pruned_loss=0.03452, over 6750.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2679, pruned_loss=0.03471, over 1420969.54 frames.], batch size: 15, lr: 3.24e-04
+2022-04-29 22:56:45,974 INFO [train.py:763] (6/8) Epoch 23, batch 2450, loss[loss=0.1924, simple_loss=0.2908, pruned_loss=0.04702, over 7235.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2676, pruned_loss=0.03481, over 1417308.69 frames.], batch size: 20, lr: 3.24e-04
+2022-04-29 22:57:51,399 INFO [train.py:763] (6/8) Epoch 23, batch 2500, loss[loss=0.1519, simple_loss=0.2531, pruned_loss=0.02533, over 7323.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2674, pruned_loss=0.03475, over 1417668.95 frames.], batch size: 21, lr: 3.24e-04
+2022-04-29 22:58:56,887 INFO [train.py:763] (6/8) Epoch 23, batch 2550, loss[loss=0.2062, simple_loss=0.2881, pruned_loss=0.06217, over 4933.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2671, pruned_loss=0.03499, over 1412874.38 frames.], batch size: 52, lr: 3.24e-04
+2022-04-29 23:00:02,922 INFO [train.py:763] (6/8) Epoch 23, batch 2600, loss[loss=0.1484, simple_loss=0.2445, pruned_loss=0.02613, over 7266.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2685, pruned_loss=0.03519, over 1416523.62 frames.], batch size: 18, lr: 3.24e-04
+2022-04-29 23:01:08,569 INFO [train.py:763] (6/8) Epoch 23, batch 2650, loss[loss=0.157, simple_loss=0.2702, pruned_loss=0.0219, over 7309.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2681, pruned_loss=0.03549, over 1416028.94 frames.], batch size: 21, lr: 3.24e-04
+2022-04-29 23:02:14,024 INFO [train.py:763] (6/8) Epoch 23, batch 2700, loss[loss=0.1661, simple_loss=0.2859, pruned_loss=0.02312, over 7336.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2683, pruned_loss=0.03545, over 1421347.36 frames.], batch size: 22, lr: 3.24e-04
+2022-04-29 23:03:19,900 INFO [train.py:763] (6/8) Epoch 23, batch 2750, loss[loss=0.1728, simple_loss=0.2737, pruned_loss=0.03598, over 7406.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2672, pruned_loss=0.03445, over 1424609.82 frames.], batch size: 21, lr: 3.24e-04
+2022-04-29 23:04:25,097 INFO [train.py:763] (6/8) Epoch 23, batch 2800, loss[loss=0.1624, simple_loss=0.2591, pruned_loss=0.0328, over 7228.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2685, pruned_loss=0.0348, over 1420625.14 frames.], batch size: 20, lr: 3.24e-04
+2022-04-29 23:05:30,275 INFO [train.py:763] (6/8) Epoch 23, batch 2850, loss[loss=0.1768, simple_loss=0.2738, pruned_loss=0.03984, over 7361.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2687, pruned_loss=0.03455, over 1420842.59 frames.], batch size: 19, lr: 3.24e-04
+2022-04-29 23:06:35,474 INFO [train.py:763] (6/8) Epoch 23, batch 2900, loss[loss=0.1623, simple_loss=0.2638, pruned_loss=0.03038, over 7304.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2684, pruned_loss=0.0343, over 1421230.09 frames.], batch size: 25, lr: 3.24e-04
+2022-04-29 23:07:40,685 INFO [train.py:763] (6/8) Epoch 23, batch 2950, loss[loss=0.1832, simple_loss=0.2686, pruned_loss=0.0489, over 7310.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2691, pruned_loss=0.03504, over 1425211.90 frames.], batch size: 17, lr: 3.23e-04
+2022-04-29 23:08:45,893 INFO [train.py:763] (6/8) Epoch 23, batch 3000, loss[loss=0.1699, simple_loss=0.2786, pruned_loss=0.0306, over 7125.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2687, pruned_loss=0.03496, over 1420969.33 frames.], batch size: 21, lr: 3.23e-04
+2022-04-29 23:08:45,894 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-29 23:09:01,228 INFO [train.py:792] (6/8) Epoch 23, validation: loss=0.1683, simple_loss=0.2665, pruned_loss=0.03509, over 698248.00 frames.
+2022-04-29 23:10:07,044 INFO [train.py:763] (6/8) Epoch 23, batch 3050, loss[loss=0.1579, simple_loss=0.2477, pruned_loss=0.03402, over 7277.00 frames.], tot_loss[loss=0.169, simple_loss=0.268, pruned_loss=0.03497, over 1416251.32 frames.], batch size: 18, lr: 3.23e-04
+2022-04-29 23:11:12,529 INFO [train.py:763] (6/8) Epoch 23, batch 3100, loss[loss=0.1605, simple_loss=0.2643, pruned_loss=0.02835, over 6730.00 frames.], tot_loss[loss=0.1682, simple_loss=0.267, pruned_loss=0.03467, over 1419606.93 frames.], batch size: 31, lr: 3.23e-04
+2022-04-29 23:12:19,060 INFO [train.py:763] (6/8) Epoch 23, batch 3150, loss[loss=0.1301, simple_loss=0.2235, pruned_loss=0.0184, over 6992.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2673, pruned_loss=0.03452, over 1420571.00 frames.], batch size: 16, lr: 3.23e-04
+2022-04-29 23:13:26,793 INFO [train.py:763] (6/8) Epoch 23, batch 3200, loss[loss=0.176, simple_loss=0.2794, pruned_loss=0.03624, over 7322.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2667, pruned_loss=0.03421, over 1425452.41 frames.], batch size: 21, lr: 3.23e-04
+2022-04-29 23:14:33,555 INFO [train.py:763] (6/8) Epoch 23, batch 3250, loss[loss=0.1543, simple_loss=0.2431, pruned_loss=0.03275, over 7152.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2667, pruned_loss=0.03443, over 1427731.46 frames.], batch size: 18, lr: 3.23e-04
+2022-04-29 23:15:38,819 INFO [train.py:763] (6/8) Epoch 23, batch 3300, loss[loss=0.1889, simple_loss=0.2886, pruned_loss=0.04455, over 7309.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2657, pruned_loss=0.03402, over 1427879.56 frames.], batch size: 24, lr: 3.23e-04
+2022-04-29 23:16:45,626 INFO [train.py:763] (6/8) Epoch 23, batch 3350, loss[loss=0.1783, simple_loss=0.2729, pruned_loss=0.04186, over 7313.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2663, pruned_loss=0.03463, over 1422921.72 frames.], batch size: 24, lr: 3.23e-04
+2022-04-29 23:17:51,525 INFO [train.py:763] (6/8) Epoch 23, batch 3400, loss[loss=0.166, simple_loss=0.2703, pruned_loss=0.03091, over 7352.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2666, pruned_loss=0.03456, over 1426891.98 frames.], batch size: 19, lr: 3.23e-04
+2022-04-29 23:18:56,728 INFO [train.py:763] (6/8) Epoch 23, batch 3450, loss[loss=0.169, simple_loss=0.2716, pruned_loss=0.03323, over 7349.00 frames.], tot_loss[loss=0.1679, simple_loss=0.267, pruned_loss=0.03443, over 1422958.92 frames.], batch size: 22, lr: 3.23e-04
+2022-04-29 23:20:02,253 INFO [train.py:763] (6/8) Epoch 23, batch 3500, loss[loss=0.1602, simple_loss=0.2562, pruned_loss=0.03208, over 7188.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2654, pruned_loss=0.03383, over 1421425.43 frames.], batch size: 16, lr: 3.23e-04
+2022-04-29 23:21:08,253 INFO [train.py:763] (6/8) Epoch 23, batch 3550, loss[loss=0.1722, simple_loss=0.2667, pruned_loss=0.03888, over 7111.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2652, pruned_loss=0.03407, over 1423048.73 frames.], batch size: 21, lr: 3.23e-04
+2022-04-29 23:22:13,614 INFO [train.py:763] (6/8) Epoch 23, batch 3600, loss[loss=0.1712, simple_loss=0.2795, pruned_loss=0.03144, over 7074.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2666, pruned_loss=0.03458, over 1421698.27 frames.], batch size: 18, lr: 3.22e-04
+2022-04-29 23:23:18,842 INFO [train.py:763] (6/8) Epoch 23, batch 3650, loss[loss=0.1707, simple_loss=0.2609, pruned_loss=0.04024, over 7361.00 frames.], tot_loss[loss=0.1679, simple_loss=0.267, pruned_loss=0.03441, over 1422312.43 frames.], batch size: 19, lr: 3.22e-04
+2022-04-29 23:24:24,044 INFO [train.py:763] (6/8) Epoch 23, batch 3700, loss[loss=0.1847, simple_loss=0.2857, pruned_loss=0.04181, over 6514.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2671, pruned_loss=0.03466, over 1419929.86 frames.], batch size: 38, lr: 3.22e-04
+2022-04-29 23:25:30,844 INFO [train.py:763] (6/8) Epoch 23, batch 3750, loss[loss=0.155, simple_loss=0.2545, pruned_loss=0.02779, over 7254.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2667, pruned_loss=0.03433, over 1421847.36 frames.], batch size: 18, lr: 3.22e-04
+2022-04-29 23:26:37,718 INFO [train.py:763] (6/8) Epoch 23, batch 3800, loss[loss=0.151, simple_loss=0.2511, pruned_loss=0.0255, over 7429.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2662, pruned_loss=0.03407, over 1423244.96 frames.], batch size: 20, lr: 3.22e-04
+2022-04-29 23:27:43,265 INFO [train.py:763] (6/8) Epoch 23, batch 3850, loss[loss=0.1895, simple_loss=0.2824, pruned_loss=0.04832, over 5250.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2662, pruned_loss=0.03425, over 1418772.70 frames.], batch size: 52, lr: 3.22e-04
+2022-04-29 23:28:48,635 INFO [train.py:763] (6/8) Epoch 23, batch 3900, loss[loss=0.1708, simple_loss=0.2682, pruned_loss=0.03665, over 6687.00 frames.], tot_loss[loss=0.1676, simple_loss=0.266, pruned_loss=0.03459, over 1415083.64 frames.], batch size: 31, lr: 3.22e-04
+2022-04-29 23:29:53,690 INFO [train.py:763] (6/8) Epoch 23, batch 3950, loss[loss=0.1544, simple_loss=0.2481, pruned_loss=0.03036, over 7148.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2663, pruned_loss=0.03411, over 1415633.84 frames.], batch size: 17, lr: 3.22e-04
+2022-04-29 23:30:59,588 INFO [train.py:763] (6/8) Epoch 23, batch 4000, loss[loss=0.2097, simple_loss=0.3018, pruned_loss=0.05881, over 7206.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2672, pruned_loss=0.03455, over 1413781.09 frames.], batch size: 22, lr: 3.22e-04
+2022-04-29 23:32:05,487 INFO [train.py:763] (6/8) Epoch 23, batch 4050, loss[loss=0.2065, simple_loss=0.2943, pruned_loss=0.05936, over 4675.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2668, pruned_loss=0.03452, over 1414527.50 frames.], batch size: 52, lr: 3.22e-04
+2022-04-29 23:33:10,719 INFO [train.py:763] (6/8) Epoch 23, batch 4100, loss[loss=0.1365, simple_loss=0.2302, pruned_loss=0.02143, over 7277.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2667, pruned_loss=0.03454, over 1414648.23 frames.], batch size: 18, lr: 3.22e-04
+2022-04-29 23:34:16,155 INFO [train.py:763] (6/8) Epoch 23, batch 4150, loss[loss=0.1457, simple_loss=0.2377, pruned_loss=0.02689, over 6986.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2661, pruned_loss=0.03439, over 1416179.79 frames.], batch size: 16, lr: 3.22e-04
+2022-04-29 23:35:21,253 INFO [train.py:763] (6/8) Epoch 23, batch 4200, loss[loss=0.1445, simple_loss=0.2347, pruned_loss=0.02713, over 7271.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2672, pruned_loss=0.0346, over 1417594.73 frames.], batch size: 18, lr: 3.22e-04
+2022-04-29 23:36:26,918 INFO [train.py:763] (6/8) Epoch 23, batch 4250, loss[loss=0.1927, simple_loss=0.2988, pruned_loss=0.04326, over 7383.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2677, pruned_loss=0.0349, over 1415871.83 frames.], batch size: 23, lr: 3.22e-04
+2022-04-29 23:37:32,235 INFO [train.py:763] (6/8) Epoch 23, batch 4300, loss[loss=0.1667, simple_loss=0.2595, pruned_loss=0.0369, over 7224.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2669, pruned_loss=0.03466, over 1415605.20 frames.], batch size: 16, lr: 3.21e-04
+2022-04-29 23:38:37,631 INFO [train.py:763] (6/8) Epoch 23, batch 4350, loss[loss=0.1878, simple_loss=0.2868, pruned_loss=0.04442, over 6775.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2672, pruned_loss=0.0348, over 1412944.00 frames.], batch size: 31, lr: 3.21e-04
+2022-04-29 23:39:43,232 INFO [train.py:763] (6/8) Epoch 23, batch 4400, loss[loss=0.1618, simple_loss=0.2686, pruned_loss=0.02746, over 6323.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2676, pruned_loss=0.03507, over 1406488.94 frames.], batch size: 37, lr: 3.21e-04
+2022-04-29 23:40:48,375 INFO [train.py:763] (6/8) Epoch 23, batch 4450, loss[loss=0.2032, simple_loss=0.3099, pruned_loss=0.04826, over 6509.00 frames.], tot_loss[loss=0.168, simple_loss=0.2667, pruned_loss=0.03465, over 1409775.29 frames.], batch size: 38, lr: 3.21e-04
+2022-04-29 23:41:53,045 INFO [train.py:763] (6/8) Epoch 23, batch 4500, loss[loss=0.1811, simple_loss=0.2781, pruned_loss=0.04202, over 6617.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2672, pruned_loss=0.03512, over 1398691.35 frames.], batch size: 38, lr: 3.21e-04
+2022-04-29 23:42:58,312 INFO [train.py:763] (6/8) Epoch 23, batch 4550, loss[loss=0.1817, simple_loss=0.2811, pruned_loss=0.04113, over 7301.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2674, pruned_loss=0.03547, over 1388873.20 frames.], batch size: 24, lr: 3.21e-04
+2022-04-29 23:44:17,936 INFO [train.py:763] (6/8) Epoch 24, batch 0, loss[loss=0.1758, simple_loss=0.2698, pruned_loss=0.04093, over 7076.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2698, pruned_loss=0.04093, over 7076.00 frames.], batch size: 18, lr: 3.15e-04
+2022-04-29 23:45:23,898 INFO [train.py:763] (6/8) Epoch 24, batch 50, loss[loss=0.1676, simple_loss=0.2707, pruned_loss=0.0323, over 7250.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2654, pruned_loss=0.03314, over 322061.20 frames.], batch size: 19, lr: 3.15e-04
+2022-04-29 23:46:30,364 INFO [train.py:763] (6/8) Epoch 24, batch 100, loss[loss=0.1812, simple_loss=0.2816, pruned_loss=0.0404, over 7323.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2656, pruned_loss=0.03331, over 569932.71 frames.], batch size: 20, lr: 3.15e-04
+2022-04-29 23:47:35,976 INFO [train.py:763] (6/8) Epoch 24, batch 150, loss[loss=0.1727, simple_loss=0.2771, pruned_loss=0.03414, over 7322.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2654, pruned_loss=0.03377, over 761032.92 frames.], batch size: 21, lr: 3.14e-04
+2022-04-29 23:48:41,596 INFO [train.py:763] (6/8) Epoch 24, batch 200, loss[loss=0.1373, simple_loss=0.2273, pruned_loss=0.02366, over 6775.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2659, pruned_loss=0.03395, over 906145.89 frames.], batch size: 15, lr: 3.14e-04
+2022-04-29 23:49:46,884 INFO [train.py:763] (6/8) Epoch 24, batch 250, loss[loss=0.1641, simple_loss=0.2719, pruned_loss=0.02817, over 7236.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2651, pruned_loss=0.03359, over 1017646.74 frames.], batch size: 20, lr: 3.14e-04
+2022-04-29 23:50:52,240 INFO [train.py:763] (6/8) Epoch 24, batch 300, loss[loss=0.171, simple_loss=0.2693, pruned_loss=0.0363, over 7163.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2663, pruned_loss=0.03413, over 1111933.10 frames.], batch size: 19, lr: 3.14e-04
+2022-04-29 23:51:57,522 INFO [train.py:763] (6/8) Epoch 24, batch 350, loss[loss=0.1784, simple_loss=0.2864, pruned_loss=0.03519, over 7208.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2667, pruned_loss=0.0344, over 1181699.56 frames.], batch size: 23, lr: 3.14e-04
+2022-04-29 23:53:03,347 INFO [train.py:763] (6/8) Epoch 24, batch 400, loss[loss=0.1463, simple_loss=0.2354, pruned_loss=0.02865, over 7225.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2662, pruned_loss=0.03406, over 1236286.58 frames.], batch size: 20, lr: 3.14e-04
+2022-04-29 23:54:08,679 INFO [train.py:763] (6/8) Epoch 24, batch 450, loss[loss=0.1637, simple_loss=0.2794, pruned_loss=0.02398, over 7083.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2653, pruned_loss=0.03393, over 1277511.43 frames.], batch size: 28, lr: 3.14e-04
+2022-04-29 23:55:14,252 INFO [train.py:763] (6/8) Epoch 24, batch 500, loss[loss=0.1598, simple_loss=0.2551, pruned_loss=0.03222, over 7167.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2648, pruned_loss=0.03399, over 1312463.51 frames.], batch size: 18, lr: 3.14e-04
+2022-04-29 23:56:20,428 INFO [train.py:763] (6/8) Epoch 24, batch 550, loss[loss=0.1665, simple_loss=0.2591, pruned_loss=0.03697, over 7164.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2649, pruned_loss=0.03366, over 1339517.19 frames.], batch size: 18, lr: 3.14e-04
+2022-04-29 23:57:26,721 INFO [train.py:763] (6/8) Epoch 24, batch 600, loss[loss=0.1793, simple_loss=0.2795, pruned_loss=0.03953, over 7211.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2653, pruned_loss=0.03391, over 1358914.08 frames.], batch size: 23, lr: 3.14e-04
+2022-04-29 23:58:32,106 INFO [train.py:763] (6/8) Epoch 24, batch 650, loss[loss=0.1381, simple_loss=0.2339, pruned_loss=0.02121, over 7289.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2644, pruned_loss=0.03388, over 1371420.39 frames.], batch size: 17, lr: 3.14e-04
+2022-04-29 23:59:38,744 INFO [train.py:763] (6/8) Epoch 24, batch 700, loss[loss=0.1449, simple_loss=0.238, pruned_loss=0.02595, over 6772.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2652, pruned_loss=0.03406, over 1387509.02 frames.], batch size: 15, lr: 3.14e-04
+2022-04-30 00:00:44,927 INFO [train.py:763] (6/8) Epoch 24, batch 750, loss[loss=0.1575, simple_loss=0.2618, pruned_loss=0.02655, over 7239.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2661, pruned_loss=0.03428, over 1399022.33 frames.], batch size: 20, lr: 3.14e-04
+2022-04-30 00:01:50,610 INFO [train.py:763] (6/8) Epoch 24, batch 800, loss[loss=0.1766, simple_loss=0.2744, pruned_loss=0.03937, over 7408.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2664, pruned_loss=0.03448, over 1406043.73 frames.], batch size: 21, lr: 3.14e-04
+2022-04-30 00:02:56,176 INFO [train.py:763] (6/8) Epoch 24, batch 850, loss[loss=0.1669, simple_loss=0.2708, pruned_loss=0.03152, over 7322.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2665, pruned_loss=0.0346, over 1407774.16 frames.], batch size: 21, lr: 3.13e-04
+2022-04-30 00:04:01,371 INFO [train.py:763] (6/8) Epoch 24, batch 900, loss[loss=0.1924, simple_loss=0.2934, pruned_loss=0.04568, over 7292.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2678, pruned_loss=0.03489, over 1409494.56 frames.], batch size: 25, lr: 3.13e-04
+2022-04-30 00:05:07,034 INFO [train.py:763] (6/8) Epoch 24, batch 950, loss[loss=0.2103, simple_loss=0.2966, pruned_loss=0.06201, over 4967.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2677, pruned_loss=0.03497, over 1403845.83 frames.], batch size: 52, lr: 3.13e-04
+2022-04-30 00:06:12,845 INFO [train.py:763] (6/8) Epoch 24, batch 1000, loss[loss=0.1688, simple_loss=0.2735, pruned_loss=0.03203, over 7409.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2673, pruned_loss=0.03477, over 1411428.25 frames.], batch size: 21, lr: 3.13e-04
+2022-04-30 00:07:18,487 INFO [train.py:763] (6/8) Epoch 24, batch 1050, loss[loss=0.14, simple_loss=0.246, pruned_loss=0.01704, over 7319.00 frames.], tot_loss[loss=0.168, simple_loss=0.2672, pruned_loss=0.03437, over 1418199.58 frames.], batch size: 20, lr: 3.13e-04
+2022-04-30 00:08:23,986 INFO [train.py:763] (6/8) Epoch 24, batch 1100, loss[loss=0.184, simple_loss=0.2853, pruned_loss=0.04132, over 7345.00 frames.], tot_loss[loss=0.1668, simple_loss=0.266, pruned_loss=0.03382, over 1420761.00 frames.], batch size: 22, lr: 3.13e-04
+2022-04-30 00:09:29,778 INFO [train.py:763] (6/8) Epoch 24, batch 1150, loss[loss=0.1847, simple_loss=0.2889, pruned_loss=0.04023, over 7197.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2661, pruned_loss=0.03385, over 1423341.29 frames.], batch size: 23, lr: 3.13e-04
+2022-04-30 00:10:35,401 INFO [train.py:763] (6/8) Epoch 24, batch 1200, loss[loss=0.1836, simple_loss=0.2815, pruned_loss=0.04285, over 7373.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2662, pruned_loss=0.03367, over 1422913.05 frames.], batch size: 23, lr: 3.13e-04
+2022-04-30 00:11:41,674 INFO [train.py:763] (6/8) Epoch 24, batch 1250, loss[loss=0.1555, simple_loss=0.2592, pruned_loss=0.02596, over 7148.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2666, pruned_loss=0.0342, over 1421245.46 frames.], batch size: 20, lr: 3.13e-04
+2022-04-30 00:12:47,622 INFO [train.py:763] (6/8) Epoch 24, batch 1300, loss[loss=0.1515, simple_loss=0.2476, pruned_loss=0.02768, over 7208.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2655, pruned_loss=0.034, over 1421164.26 frames.], batch size: 16, lr: 3.13e-04
+2022-04-30 00:13:53,405 INFO [train.py:763] (6/8) Epoch 24, batch 1350, loss[loss=0.1484, simple_loss=0.2564, pruned_loss=0.0202, over 6463.00 frames.], tot_loss[loss=0.166, simple_loss=0.2649, pruned_loss=0.03351, over 1420531.45 frames.], batch size: 38, lr: 3.13e-04
+2022-04-30 00:14:58,839 INFO [train.py:763] (6/8) Epoch 24, batch 1400, loss[loss=0.1407, simple_loss=0.2309, pruned_loss=0.02519, over 7287.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2663, pruned_loss=0.0338, over 1425769.71 frames.], batch size: 17, lr: 3.13e-04
+2022-04-30 00:16:04,294 INFO [train.py:763] (6/8) Epoch 24, batch 1450, loss[loss=0.1682, simple_loss=0.2763, pruned_loss=0.03009, over 7143.00 frames.], tot_loss[loss=0.167, simple_loss=0.266, pruned_loss=0.03394, over 1422209.45 frames.], batch size: 20, lr: 3.13e-04
+2022-04-30 00:17:11,226 INFO [train.py:763] (6/8) Epoch 24, batch 1500, loss[loss=0.1785, simple_loss=0.2879, pruned_loss=0.03458, over 6711.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2665, pruned_loss=0.03412, over 1421072.75 frames.], batch size: 31, lr: 3.13e-04
+2022-04-30 00:18:17,538 INFO [train.py:763] (6/8) Epoch 24, batch 1550, loss[loss=0.1322, simple_loss=0.2269, pruned_loss=0.01879, over 7281.00 frames.], tot_loss[loss=0.168, simple_loss=0.267, pruned_loss=0.03448, over 1422399.72 frames.], batch size: 18, lr: 3.12e-04
+2022-04-30 00:19:23,707 INFO [train.py:763] (6/8) Epoch 24, batch 1600, loss[loss=0.1496, simple_loss=0.25, pruned_loss=0.02454, over 6842.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2657, pruned_loss=0.03393, over 1421091.43 frames.], batch size: 15, lr: 3.12e-04
+2022-04-30 00:20:29,920 INFO [train.py:763] (6/8) Epoch 24, batch 1650, loss[loss=0.1634, simple_loss=0.2687, pruned_loss=0.02911, over 7236.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2663, pruned_loss=0.03425, over 1422175.59 frames.], batch size: 21, lr: 3.12e-04
+2022-04-30 00:21:35,724 INFO [train.py:763] (6/8) Epoch 24, batch 1700, loss[loss=0.1733, simple_loss=0.2608, pruned_loss=0.04296, over 7389.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2663, pruned_loss=0.03448, over 1420803.03 frames.], batch size: 23, lr: 3.12e-04
+2022-04-30 00:22:40,964 INFO [train.py:763] (6/8) Epoch 24, batch 1750, loss[loss=0.1587, simple_loss=0.2606, pruned_loss=0.02847, over 7127.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2667, pruned_loss=0.0346, over 1422704.00 frames.], batch size: 17, lr: 3.12e-04
+2022-04-30 00:23:47,087 INFO [train.py:763] (6/8) Epoch 24, batch 1800, loss[loss=0.1399, simple_loss=0.2281, pruned_loss=0.02586, over 7020.00 frames.], tot_loss[loss=0.1668, simple_loss=0.266, pruned_loss=0.0338, over 1423164.91 frames.], batch size: 16, lr: 3.12e-04
+2022-04-30 00:24:52,830 INFO [train.py:763] (6/8) Epoch 24, batch 1850, loss[loss=0.1447, simple_loss=0.2368, pruned_loss=0.02632, over 6872.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2655, pruned_loss=0.03376, over 1420148.27 frames.], batch size: 15, lr: 3.12e-04
+2022-04-30 00:26:09,446 INFO [train.py:763] (6/8) Epoch 24, batch 1900, loss[loss=0.1713, simple_loss=0.2693, pruned_loss=0.0367, over 7314.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2662, pruned_loss=0.03427, over 1422257.71 frames.], batch size: 25, lr: 3.12e-04
+2022-04-30 00:27:15,237 INFO [train.py:763] (6/8) Epoch 24, batch 1950, loss[loss=0.159, simple_loss=0.2567, pruned_loss=0.03062, over 7251.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2658, pruned_loss=0.03439, over 1423551.33 frames.], batch size: 19, lr: 3.12e-04
+2022-04-30 00:28:21,029 INFO [train.py:763] (6/8) Epoch 24, batch 2000, loss[loss=0.1623, simple_loss=0.2623, pruned_loss=0.03112, over 7149.00 frames.], tot_loss[loss=0.1668, simple_loss=0.265, pruned_loss=0.03433, over 1423730.25 frames.], batch size: 18, lr: 3.12e-04
+2022-04-30 00:29:27,148 INFO [train.py:763] (6/8) Epoch 24, batch 2050, loss[loss=0.1787, simple_loss=0.2802, pruned_loss=0.03859, over 7323.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2644, pruned_loss=0.03391, over 1426407.28 frames.], batch size: 21, lr: 3.12e-04
+2022-04-30 00:30:32,523 INFO [train.py:763] (6/8) Epoch 24, batch 2100, loss[loss=0.1688, simple_loss=0.278, pruned_loss=0.02978, over 7257.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2648, pruned_loss=0.03375, over 1423171.48 frames.], batch size: 19, lr: 3.12e-04
+2022-04-30 00:31:37,977 INFO [train.py:763] (6/8) Epoch 24, batch 2150, loss[loss=0.1768, simple_loss=0.2749, pruned_loss=0.03934, over 7433.00 frames.], tot_loss[loss=0.167, simple_loss=0.2658, pruned_loss=0.03408, over 1421715.78 frames.], batch size: 20, lr: 3.12e-04
+2022-04-30 00:32:43,334 INFO [train.py:763] (6/8) Epoch 24, batch 2200, loss[loss=0.1462, simple_loss=0.2392, pruned_loss=0.02665, over 6775.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2646, pruned_loss=0.03357, over 1420242.99 frames.], batch size: 15, lr: 3.12e-04
+2022-04-30 00:33:49,449 INFO [train.py:763] (6/8) Epoch 24, batch 2250, loss[loss=0.1593, simple_loss=0.2553, pruned_loss=0.0317, over 7070.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2648, pruned_loss=0.03368, over 1416187.37 frames.], batch size: 18, lr: 3.12e-04
+2022-04-30 00:34:55,319 INFO [train.py:763] (6/8) Epoch 24, batch 2300, loss[loss=0.1652, simple_loss=0.2476, pruned_loss=0.04144, over 7254.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2645, pruned_loss=0.03346, over 1417596.36 frames.], batch size: 16, lr: 3.11e-04
+2022-04-30 00:36:01,136 INFO [train.py:763] (6/8) Epoch 24, batch 2350, loss[loss=0.1584, simple_loss=0.2743, pruned_loss=0.02127, over 7319.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2645, pruned_loss=0.03364, over 1418076.06 frames.], batch size: 21, lr: 3.11e-04
+2022-04-30 00:37:06,714 INFO [train.py:763] (6/8) Epoch 24, batch 2400, loss[loss=0.1727, simple_loss=0.2691, pruned_loss=0.03817, over 7362.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2655, pruned_loss=0.03362, over 1423545.02 frames.], batch size: 19, lr: 3.11e-04
+2022-04-30 00:38:21,819 INFO [train.py:763] (6/8) Epoch 24, batch 2450, loss[loss=0.1436, simple_loss=0.2387, pruned_loss=0.02422, over 7139.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2661, pruned_loss=0.03367, over 1422559.00 frames.], batch size: 17, lr: 3.11e-04
+2022-04-30 00:39:27,188 INFO [train.py:763] (6/8) Epoch 24, batch 2500, loss[loss=0.169, simple_loss=0.2796, pruned_loss=0.02921, over 7425.00 frames.], tot_loss[loss=0.1668, simple_loss=0.266, pruned_loss=0.03378, over 1423002.29 frames.], batch size: 21, lr: 3.11e-04
+2022-04-30 00:40:32,705 INFO [train.py:763] (6/8) Epoch 24, batch 2550, loss[loss=0.1578, simple_loss=0.2619, pruned_loss=0.02688, over 7437.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2668, pruned_loss=0.03399, over 1423775.43 frames.], batch size: 20, lr: 3.11e-04
+2022-04-30 00:41:38,102 INFO [train.py:763] (6/8) Epoch 24, batch 2600, loss[loss=0.1708, simple_loss=0.2648, pruned_loss=0.03842, over 7118.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2669, pruned_loss=0.03432, over 1420635.41 frames.], batch size: 17, lr: 3.11e-04
+2022-04-30 00:42:43,680 INFO [train.py:763] (6/8) Epoch 24, batch 2650, loss[loss=0.1716, simple_loss=0.2571, pruned_loss=0.04304, over 7209.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2672, pruned_loss=0.03418, over 1422625.94 frames.], batch size: 22, lr: 3.11e-04
+2022-04-30 00:43:49,277 INFO [train.py:763] (6/8) Epoch 24, batch 2700, loss[loss=0.1618, simple_loss=0.2728, pruned_loss=0.02543, over 7059.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2661, pruned_loss=0.0335, over 1425493.87 frames.], batch size: 18, lr: 3.11e-04
+2022-04-30 00:44:54,694 INFO [train.py:763] (6/8) Epoch 24, batch 2750, loss[loss=0.1761, simple_loss=0.2702, pruned_loss=0.04096, over 7149.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2647, pruned_loss=0.03313, over 1421124.97 frames.], batch size: 20, lr: 3.11e-04
+2022-04-30 00:46:00,210 INFO [train.py:763] (6/8) Epoch 24, batch 2800, loss[loss=0.167, simple_loss=0.2669, pruned_loss=0.03357, over 7261.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2641, pruned_loss=0.0334, over 1421601.97 frames.], batch size: 19, lr: 3.11e-04
+2022-04-30 00:47:22,978 INFO [train.py:763] (6/8) Epoch 24, batch 2850, loss[loss=0.1671, simple_loss=0.272, pruned_loss=0.03104, over 7431.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2642, pruned_loss=0.03295, over 1419352.13 frames.], batch size: 20, lr: 3.11e-04
+2022-04-30 00:48:28,454 INFO [train.py:763] (6/8) Epoch 24, batch 2900, loss[loss=0.1678, simple_loss=0.2731, pruned_loss=0.03129, over 7213.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2651, pruned_loss=0.0331, over 1420440.42 frames.], batch size: 23, lr: 3.11e-04
+2022-04-30 00:49:52,269 INFO [train.py:763] (6/8) Epoch 24, batch 2950, loss[loss=0.1537, simple_loss=0.2602, pruned_loss=0.02363, over 7128.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2644, pruned_loss=0.03274, over 1426268.28 frames.], batch size: 21, lr: 3.11e-04
+2022-04-30 00:51:06,870 INFO [train.py:763] (6/8) Epoch 24, batch 3000, loss[loss=0.1655, simple_loss=0.2711, pruned_loss=0.02995, over 6812.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2636, pruned_loss=0.03278, over 1428883.14 frames.], batch size: 31, lr: 3.10e-04
+2022-04-30 00:51:06,871 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 00:51:22,143 INFO [train.py:792] (6/8) Epoch 24, validation: loss=0.1679, simple_loss=0.2653, pruned_loss=0.03523, over 698248.00 frames.
+2022-04-30 00:52:37,064 INFO [train.py:763] (6/8) Epoch 24, batch 3050, loss[loss=0.1533, simple_loss=0.2546, pruned_loss=0.02603, over 7112.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2632, pruned_loss=0.03263, over 1429659.06 frames.], batch size: 21, lr: 3.10e-04
+2022-04-30 00:53:42,763 INFO [train.py:763] (6/8) Epoch 24, batch 3100, loss[loss=0.1394, simple_loss=0.225, pruned_loss=0.02694, over 7202.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2621, pruned_loss=0.03234, over 1430948.20 frames.], batch size: 16, lr: 3.10e-04
+2022-04-30 00:54:48,076 INFO [train.py:763] (6/8) Epoch 24, batch 3150, loss[loss=0.1487, simple_loss=0.2472, pruned_loss=0.0251, over 7253.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2629, pruned_loss=0.03267, over 1432221.39 frames.], batch size: 19, lr: 3.10e-04
+2022-04-30 00:55:53,500 INFO [train.py:763] (6/8) Epoch 24, batch 3200, loss[loss=0.1873, simple_loss=0.2818, pruned_loss=0.0464, over 5202.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2625, pruned_loss=0.03233, over 1430738.85 frames.], batch size: 52, lr: 3.10e-04
+2022-04-30 00:56:59,244 INFO [train.py:763] (6/8) Epoch 24, batch 3250, loss[loss=0.1861, simple_loss=0.2808, pruned_loss=0.04569, over 7245.00 frames.], tot_loss[loss=0.165, simple_loss=0.2638, pruned_loss=0.03307, over 1429401.29 frames.], batch size: 20, lr: 3.10e-04
+2022-04-30 00:58:05,421 INFO [train.py:763] (6/8) Epoch 24, batch 3300, loss[loss=0.1641, simple_loss=0.2564, pruned_loss=0.03589, over 7161.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2644, pruned_loss=0.03327, over 1428174.46 frames.], batch size: 19, lr: 3.10e-04
+2022-04-30 00:59:11,084 INFO [train.py:763] (6/8) Epoch 24, batch 3350, loss[loss=0.1479, simple_loss=0.2472, pruned_loss=0.0243, over 7260.00 frames.], tot_loss[loss=0.1661, simple_loss=0.265, pruned_loss=0.03363, over 1424042.36 frames.], batch size: 19, lr: 3.10e-04
+2022-04-30 01:00:16,805 INFO [train.py:763] (6/8) Epoch 24, batch 3400, loss[loss=0.1459, simple_loss=0.2337, pruned_loss=0.02902, over 7283.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2647, pruned_loss=0.03353, over 1425700.56 frames.], batch size: 17, lr: 3.10e-04
+2022-04-30 01:01:22,329 INFO [train.py:763] (6/8) Epoch 24, batch 3450, loss[loss=0.166, simple_loss=0.2681, pruned_loss=0.03199, over 7196.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2648, pruned_loss=0.03395, over 1421909.30 frames.], batch size: 21, lr: 3.10e-04
+2022-04-30 01:02:27,653 INFO [train.py:763] (6/8) Epoch 24, batch 3500, loss[loss=0.1612, simple_loss=0.2434, pruned_loss=0.03947, over 7144.00 frames.], tot_loss[loss=0.1664, simple_loss=0.265, pruned_loss=0.03394, over 1423074.56 frames.], batch size: 17, lr: 3.10e-04
+2022-04-30 01:03:33,198 INFO [train.py:763] (6/8) Epoch 24, batch 3550, loss[loss=0.1736, simple_loss=0.2668, pruned_loss=0.0402, over 7329.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2654, pruned_loss=0.03401, over 1424983.49 frames.], batch size: 20, lr: 3.10e-04
+2022-04-30 01:04:38,401 INFO [train.py:763] (6/8) Epoch 24, batch 3600, loss[loss=0.1671, simple_loss=0.2682, pruned_loss=0.03296, over 7215.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2656, pruned_loss=0.03413, over 1423268.44 frames.], batch size: 23, lr: 3.10e-04
+2022-04-30 01:05:45,360 INFO [train.py:763] (6/8) Epoch 24, batch 3650, loss[loss=0.1658, simple_loss=0.2678, pruned_loss=0.03191, over 6676.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2654, pruned_loss=0.03391, over 1419394.18 frames.], batch size: 38, lr: 3.10e-04
+2022-04-30 01:06:51,868 INFO [train.py:763] (6/8) Epoch 24, batch 3700, loss[loss=0.1394, simple_loss=0.2357, pruned_loss=0.02156, over 7443.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2648, pruned_loss=0.03372, over 1422249.31 frames.], batch size: 20, lr: 3.10e-04
+2022-04-30 01:07:57,544 INFO [train.py:763] (6/8) Epoch 24, batch 3750, loss[loss=0.1875, simple_loss=0.2786, pruned_loss=0.04817, over 7366.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2648, pruned_loss=0.03378, over 1424391.42 frames.], batch size: 23, lr: 3.09e-04
+2022-04-30 01:09:02,952 INFO [train.py:763] (6/8) Epoch 24, batch 3800, loss[loss=0.2221, simple_loss=0.3125, pruned_loss=0.06585, over 5063.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2654, pruned_loss=0.0342, over 1422696.92 frames.], batch size: 52, lr: 3.09e-04
+2022-04-30 01:10:08,029 INFO [train.py:763] (6/8) Epoch 24, batch 3850, loss[loss=0.1371, simple_loss=0.226, pruned_loss=0.02413, over 7284.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2658, pruned_loss=0.03427, over 1422759.28 frames.], batch size: 18, lr: 3.09e-04
+2022-04-30 01:11:13,749 INFO [train.py:763] (6/8) Epoch 24, batch 3900, loss[loss=0.1492, simple_loss=0.2525, pruned_loss=0.02291, over 7261.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2662, pruned_loss=0.03404, over 1422057.08 frames.], batch size: 19, lr: 3.09e-04
+2022-04-30 01:12:19,229 INFO [train.py:763] (6/8) Epoch 24, batch 3950, loss[loss=0.1417, simple_loss=0.2283, pruned_loss=0.02757, over 7416.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2657, pruned_loss=0.03372, over 1424254.15 frames.], batch size: 18, lr: 3.09e-04
+2022-04-30 01:13:24,351 INFO [train.py:763] (6/8) Epoch 24, batch 4000, loss[loss=0.182, simple_loss=0.2855, pruned_loss=0.03928, over 7316.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2655, pruned_loss=0.03362, over 1424185.10 frames.], batch size: 21, lr: 3.09e-04
+2022-04-30 01:14:29,875 INFO [train.py:763] (6/8) Epoch 24, batch 4050, loss[loss=0.1398, simple_loss=0.243, pruned_loss=0.01826, over 7429.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2644, pruned_loss=0.03314, over 1422455.75 frames.], batch size: 20, lr: 3.09e-04
+2022-04-30 01:15:36,738 INFO [train.py:763] (6/8) Epoch 24, batch 4100, loss[loss=0.1862, simple_loss=0.2738, pruned_loss=0.04929, over 6360.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2646, pruned_loss=0.03325, over 1422491.77 frames.], batch size: 37, lr: 3.09e-04
+2022-04-30 01:16:43,523 INFO [train.py:763] (6/8) Epoch 24, batch 4150, loss[loss=0.1535, simple_loss=0.256, pruned_loss=0.02548, over 7226.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2648, pruned_loss=0.03331, over 1419167.59 frames.], batch size: 21, lr: 3.09e-04
+2022-04-30 01:17:50,169 INFO [train.py:763] (6/8) Epoch 24, batch 4200, loss[loss=0.1894, simple_loss=0.2909, pruned_loss=0.04394, over 7190.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2671, pruned_loss=0.034, over 1420003.75 frames.], batch size: 23, lr: 3.09e-04
+2022-04-30 01:18:56,572 INFO [train.py:763] (6/8) Epoch 24, batch 4250, loss[loss=0.1591, simple_loss=0.2706, pruned_loss=0.02377, over 6347.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2669, pruned_loss=0.03405, over 1414382.69 frames.], batch size: 37, lr: 3.09e-04
+2022-04-30 01:20:02,378 INFO [train.py:763] (6/8) Epoch 24, batch 4300, loss[loss=0.1622, simple_loss=0.2599, pruned_loss=0.03225, over 7161.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2669, pruned_loss=0.03442, over 1413859.15 frames.], batch size: 19, lr: 3.09e-04
+2022-04-30 01:21:09,419 INFO [train.py:763] (6/8) Epoch 24, batch 4350, loss[loss=0.1945, simple_loss=0.2984, pruned_loss=0.04529, over 7281.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2657, pruned_loss=0.03421, over 1414081.33 frames.], batch size: 25, lr: 3.09e-04
+2022-04-30 01:22:16,104 INFO [train.py:763] (6/8) Epoch 24, batch 4400, loss[loss=0.1715, simple_loss=0.2715, pruned_loss=0.03574, over 7284.00 frames.], tot_loss[loss=0.167, simple_loss=0.2661, pruned_loss=0.03391, over 1412625.40 frames.], batch size: 24, lr: 3.09e-04
+2022-04-30 01:23:21,723 INFO [train.py:763] (6/8) Epoch 24, batch 4450, loss[loss=0.1701, simple_loss=0.2812, pruned_loss=0.02954, over 7290.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2674, pruned_loss=0.03459, over 1403049.47 frames.], batch size: 25, lr: 3.09e-04
+2022-04-30 01:24:28,212 INFO [train.py:763] (6/8) Epoch 24, batch 4500, loss[loss=0.1835, simple_loss=0.2797, pruned_loss=0.04365, over 4813.00 frames.], tot_loss[loss=0.1698, simple_loss=0.269, pruned_loss=0.03527, over 1387954.95 frames.], batch size: 52, lr: 3.08e-04
+2022-04-30 01:25:32,953 INFO [train.py:763] (6/8) Epoch 24, batch 4550, loss[loss=0.1674, simple_loss=0.2712, pruned_loss=0.03179, over 5075.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2702, pruned_loss=0.03579, over 1350683.58 frames.], batch size: 52, lr: 3.08e-04
+2022-04-30 01:26:52,292 INFO [train.py:763] (6/8) Epoch 25, batch 0, loss[loss=0.1753, simple_loss=0.2762, pruned_loss=0.03713, over 7219.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2762, pruned_loss=0.03713, over 7219.00 frames.], batch size: 21, lr: 3.02e-04
+2022-04-30 01:27:58,472 INFO [train.py:763] (6/8) Epoch 25, batch 50, loss[loss=0.1824, simple_loss=0.2869, pruned_loss=0.03894, over 7316.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2637, pruned_loss=0.03238, over 323458.61 frames.], batch size: 21, lr: 3.02e-04
+2022-04-30 01:29:03,631 INFO [train.py:763] (6/8) Epoch 25, batch 100, loss[loss=0.1782, simple_loss=0.2727, pruned_loss=0.04181, over 4949.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2648, pruned_loss=0.03237, over 567162.17 frames.], batch size: 54, lr: 3.02e-04
+2022-04-30 01:30:08,884 INFO [train.py:763] (6/8) Epoch 25, batch 150, loss[loss=0.1566, simple_loss=0.2487, pruned_loss=0.03228, over 7268.00 frames.], tot_loss[loss=0.165, simple_loss=0.265, pruned_loss=0.03247, over 760869.03 frames.], batch size: 17, lr: 3.02e-04
+2022-04-30 01:31:14,497 INFO [train.py:763] (6/8) Epoch 25, batch 200, loss[loss=0.1841, simple_loss=0.28, pruned_loss=0.04406, over 7379.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2654, pruned_loss=0.03313, over 908708.55 frames.], batch size: 23, lr: 3.02e-04
+2022-04-30 01:32:20,362 INFO [train.py:763] (6/8) Epoch 25, batch 250, loss[loss=0.1753, simple_loss=0.2737, pruned_loss=0.03841, over 7185.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2663, pruned_loss=0.03344, over 1021211.22 frames.], batch size: 22, lr: 3.02e-04
+2022-04-30 01:33:26,238 INFO [train.py:763] (6/8) Epoch 25, batch 300, loss[loss=0.159, simple_loss=0.2603, pruned_loss=0.0289, over 7333.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2664, pruned_loss=0.03358, over 1107584.98 frames.], batch size: 20, lr: 3.02e-04
+2022-04-30 01:34:31,517 INFO [train.py:763] (6/8) Epoch 25, batch 350, loss[loss=0.1313, simple_loss=0.227, pruned_loss=0.01776, over 7170.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2645, pruned_loss=0.0331, over 1176881.80 frames.], batch size: 18, lr: 3.02e-04
+2022-04-30 01:35:36,790 INFO [train.py:763] (6/8) Epoch 25, batch 400, loss[loss=0.1332, simple_loss=0.2226, pruned_loss=0.02188, over 7408.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2635, pruned_loss=0.03252, over 1233886.88 frames.], batch size: 18, lr: 3.02e-04
+2022-04-30 01:36:42,355 INFO [train.py:763] (6/8) Epoch 25, batch 450, loss[loss=0.1714, simple_loss=0.2799, pruned_loss=0.03148, over 7423.00 frames.], tot_loss[loss=0.1634, simple_loss=0.263, pruned_loss=0.0319, over 1275113.99 frames.], batch size: 21, lr: 3.02e-04
+2022-04-30 01:37:47,503 INFO [train.py:763] (6/8) Epoch 25, batch 500, loss[loss=0.1742, simple_loss=0.2719, pruned_loss=0.03829, over 7372.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2637, pruned_loss=0.03256, over 1302986.58 frames.], batch size: 23, lr: 3.02e-04
+2022-04-30 01:38:52,815 INFO [train.py:763] (6/8) Epoch 25, batch 550, loss[loss=0.1704, simple_loss=0.2788, pruned_loss=0.03105, over 7240.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2623, pruned_loss=0.03201, over 1329914.56 frames.], batch size: 20, lr: 3.02e-04
+2022-04-30 01:39:58,987 INFO [train.py:763] (6/8) Epoch 25, batch 600, loss[loss=0.1574, simple_loss=0.2697, pruned_loss=0.02255, over 7080.00 frames.], tot_loss[loss=0.164, simple_loss=0.2634, pruned_loss=0.03234, over 1347993.12 frames.], batch size: 28, lr: 3.02e-04
+2022-04-30 01:41:04,681 INFO [train.py:763] (6/8) Epoch 25, batch 650, loss[loss=0.1626, simple_loss=0.2658, pruned_loss=0.02965, over 7331.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2623, pruned_loss=0.03221, over 1362296.27 frames.], batch size: 20, lr: 3.02e-04
+2022-04-30 01:42:10,709 INFO [train.py:763] (6/8) Epoch 25, batch 700, loss[loss=0.1938, simple_loss=0.2974, pruned_loss=0.04508, over 7141.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2624, pruned_loss=0.03229, over 1374934.56 frames.], batch size: 20, lr: 3.02e-04
+2022-04-30 01:43:16,098 INFO [train.py:763] (6/8) Epoch 25, batch 750, loss[loss=0.1564, simple_loss=0.2582, pruned_loss=0.02732, over 7426.00 frames.], tot_loss[loss=0.1641, simple_loss=0.263, pruned_loss=0.03257, over 1389860.21 frames.], batch size: 20, lr: 3.01e-04
+2022-04-30 01:44:20,964 INFO [train.py:763] (6/8) Epoch 25, batch 800, loss[loss=0.1822, simple_loss=0.3002, pruned_loss=0.03213, over 6694.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2644, pruned_loss=0.03332, over 1395049.14 frames.], batch size: 31, lr: 3.01e-04
+2022-04-30 01:45:26,282 INFO [train.py:763] (6/8) Epoch 25, batch 850, loss[loss=0.148, simple_loss=0.2541, pruned_loss=0.02101, over 7122.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2649, pruned_loss=0.03312, over 1405905.65 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:46:33,100 INFO [train.py:763] (6/8) Epoch 25, batch 900, loss[loss=0.1395, simple_loss=0.2283, pruned_loss=0.02536, over 7188.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2651, pruned_loss=0.03335, over 1406953.78 frames.], batch size: 16, lr: 3.01e-04
+2022-04-30 01:47:40,154 INFO [train.py:763] (6/8) Epoch 25, batch 950, loss[loss=0.1625, simple_loss=0.2513, pruned_loss=0.03687, over 7272.00 frames.], tot_loss[loss=0.1657, simple_loss=0.265, pruned_loss=0.03323, over 1413145.06 frames.], batch size: 17, lr: 3.01e-04
+2022-04-30 01:48:46,813 INFO [train.py:763] (6/8) Epoch 25, batch 1000, loss[loss=0.1838, simple_loss=0.2839, pruned_loss=0.04186, over 7118.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2649, pruned_loss=0.03299, over 1412152.30 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:49:52,614 INFO [train.py:763] (6/8) Epoch 25, batch 1050, loss[loss=0.1758, simple_loss=0.2673, pruned_loss=0.04213, over 4955.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2659, pruned_loss=0.03331, over 1412215.13 frames.], batch size: 52, lr: 3.01e-04
+2022-04-30 01:50:59,149 INFO [train.py:763] (6/8) Epoch 25, batch 1100, loss[loss=0.156, simple_loss=0.2554, pruned_loss=0.02835, over 7115.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2649, pruned_loss=0.0331, over 1413654.16 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:52:04,513 INFO [train.py:763] (6/8) Epoch 25, batch 1150, loss[loss=0.1794, simple_loss=0.2661, pruned_loss=0.04639, over 7379.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2647, pruned_loss=0.03309, over 1416768.23 frames.], batch size: 23, lr: 3.01e-04
+2022-04-30 01:53:10,909 INFO [train.py:763] (6/8) Epoch 25, batch 1200, loss[loss=0.1507, simple_loss=0.2432, pruned_loss=0.02911, over 7148.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2639, pruned_loss=0.03294, over 1420472.28 frames.], batch size: 17, lr: 3.01e-04
+2022-04-30 01:54:16,945 INFO [train.py:763] (6/8) Epoch 25, batch 1250, loss[loss=0.1665, simple_loss=0.27, pruned_loss=0.03151, over 7320.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2639, pruned_loss=0.03279, over 1422724.98 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:55:23,838 INFO [train.py:763] (6/8) Epoch 25, batch 1300, loss[loss=0.1372, simple_loss=0.2373, pruned_loss=0.01853, over 7434.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2634, pruned_loss=0.03248, over 1426093.06 frames.], batch size: 20, lr: 3.01e-04
+2022-04-30 01:56:30,414 INFO [train.py:763] (6/8) Epoch 25, batch 1350, loss[loss=0.1611, simple_loss=0.2696, pruned_loss=0.02636, over 7316.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2641, pruned_loss=0.03264, over 1426121.02 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:57:36,865 INFO [train.py:763] (6/8) Epoch 25, batch 1400, loss[loss=0.1536, simple_loss=0.2594, pruned_loss=0.02393, over 7329.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2647, pruned_loss=0.03289, over 1426044.48 frames.], batch size: 22, lr: 3.01e-04
+2022-04-30 01:58:42,309 INFO [train.py:763] (6/8) Epoch 25, batch 1450, loss[loss=0.1571, simple_loss=0.2501, pruned_loss=0.03206, over 6986.00 frames.], tot_loss[loss=0.1654, simple_loss=0.265, pruned_loss=0.03293, over 1428133.34 frames.], batch size: 16, lr: 3.01e-04
+2022-04-30 01:59:49,400 INFO [train.py:763] (6/8) Epoch 25, batch 1500, loss[loss=0.1722, simple_loss=0.2776, pruned_loss=0.0334, over 7230.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2646, pruned_loss=0.03301, over 1428003.14 frames.], batch size: 21, lr: 3.00e-04
+2022-04-30 02:00:55,047 INFO [train.py:763] (6/8) Epoch 25, batch 1550, loss[loss=0.1483, simple_loss=0.2353, pruned_loss=0.0307, over 7145.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2645, pruned_loss=0.03312, over 1427583.07 frames.], batch size: 17, lr: 3.00e-04
+2022-04-30 02:02:00,073 INFO [train.py:763] (6/8) Epoch 25, batch 1600, loss[loss=0.1834, simple_loss=0.2827, pruned_loss=0.0421, over 7151.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2662, pruned_loss=0.03347, over 1424805.69 frames.], batch size: 20, lr: 3.00e-04
+2022-04-30 02:03:05,634 INFO [train.py:763] (6/8) Epoch 25, batch 1650, loss[loss=0.1825, simple_loss=0.2752, pruned_loss=0.04484, over 7173.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2649, pruned_loss=0.03321, over 1426237.93 frames.], batch size: 28, lr: 3.00e-04
+2022-04-30 02:04:10,611 INFO [train.py:763] (6/8) Epoch 25, batch 1700, loss[loss=0.1694, simple_loss=0.2769, pruned_loss=0.0309, over 7323.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2651, pruned_loss=0.03312, over 1426374.99 frames.], batch size: 21, lr: 3.00e-04
+2022-04-30 02:05:15,842 INFO [train.py:763] (6/8) Epoch 25, batch 1750, loss[loss=0.1435, simple_loss=0.2305, pruned_loss=0.02828, over 7133.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2651, pruned_loss=0.03289, over 1425425.87 frames.], batch size: 17, lr: 3.00e-04
+2022-04-30 02:06:21,041 INFO [train.py:763] (6/8) Epoch 25, batch 1800, loss[loss=0.18, simple_loss=0.2776, pruned_loss=0.04124, over 7143.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2659, pruned_loss=0.03331, over 1421641.61 frames.], batch size: 20, lr: 3.00e-04
+2022-04-30 02:07:26,297 INFO [train.py:763] (6/8) Epoch 25, batch 1850, loss[loss=0.1842, simple_loss=0.283, pruned_loss=0.04267, over 7430.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2657, pruned_loss=0.03328, over 1422352.56 frames.], batch size: 20, lr: 3.00e-04
+2022-04-30 02:08:31,447 INFO [train.py:763] (6/8) Epoch 25, batch 1900, loss[loss=0.1567, simple_loss=0.2414, pruned_loss=0.03596, over 7126.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2656, pruned_loss=0.03288, over 1422640.89 frames.], batch size: 17, lr: 3.00e-04
+2022-04-30 02:09:36,778 INFO [train.py:763] (6/8) Epoch 25, batch 1950, loss[loss=0.1951, simple_loss=0.2946, pruned_loss=0.04775, over 5416.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2654, pruned_loss=0.03313, over 1421392.37 frames.], batch size: 53, lr: 3.00e-04
+2022-04-30 02:10:42,030 INFO [train.py:763] (6/8) Epoch 25, batch 2000, loss[loss=0.1565, simple_loss=0.2545, pruned_loss=0.02928, over 7159.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2648, pruned_loss=0.03299, over 1417248.96 frames.], batch size: 19, lr: 3.00e-04
+2022-04-30 02:11:47,949 INFO [train.py:763] (6/8) Epoch 25, batch 2050, loss[loss=0.1729, simple_loss=0.2721, pruned_loss=0.03691, over 7320.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2644, pruned_loss=0.03305, over 1418536.06 frames.], batch size: 20, lr: 3.00e-04
+2022-04-30 02:12:54,273 INFO [train.py:763] (6/8) Epoch 25, batch 2100, loss[loss=0.193, simple_loss=0.2854, pruned_loss=0.05028, over 7196.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2653, pruned_loss=0.03342, over 1418166.69 frames.], batch size: 22, lr: 3.00e-04
+2022-04-30 02:13:59,524 INFO [train.py:763] (6/8) Epoch 25, batch 2150, loss[loss=0.1455, simple_loss=0.2451, pruned_loss=0.02292, over 7161.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2665, pruned_loss=0.03349, over 1420682.62 frames.], batch size: 18, lr: 3.00e-04
+2022-04-30 02:15:05,525 INFO [train.py:763] (6/8) Epoch 25, batch 2200, loss[loss=0.1561, simple_loss=0.2609, pruned_loss=0.02562, over 7061.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2663, pruned_loss=0.03348, over 1422448.48 frames.], batch size: 28, lr: 3.00e-04
+2022-04-30 02:16:11,386 INFO [train.py:763] (6/8) Epoch 25, batch 2250, loss[loss=0.1818, simple_loss=0.2832, pruned_loss=0.04024, over 7395.00 frames.], tot_loss[loss=0.1663, simple_loss=0.266, pruned_loss=0.03337, over 1425306.89 frames.], batch size: 23, lr: 3.00e-04
+2022-04-30 02:17:16,594 INFO [train.py:763] (6/8) Epoch 25, batch 2300, loss[loss=0.1558, simple_loss=0.2506, pruned_loss=0.03047, over 7064.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2663, pruned_loss=0.03348, over 1425475.65 frames.], batch size: 18, lr: 2.99e-04
+2022-04-30 02:18:23,382 INFO [train.py:763] (6/8) Epoch 25, batch 2350, loss[loss=0.127, simple_loss=0.2238, pruned_loss=0.01507, over 7257.00 frames.], tot_loss[loss=0.1658, simple_loss=0.265, pruned_loss=0.03325, over 1425567.19 frames.], batch size: 19, lr: 2.99e-04
+2022-04-30 02:19:30,574 INFO [train.py:763] (6/8) Epoch 25, batch 2400, loss[loss=0.171, simple_loss=0.2786, pruned_loss=0.03176, over 7381.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2644, pruned_loss=0.03296, over 1423349.35 frames.], batch size: 23, lr: 2.99e-04
+2022-04-30 02:20:35,958 INFO [train.py:763] (6/8) Epoch 25, batch 2450, loss[loss=0.1645, simple_loss=0.2653, pruned_loss=0.03182, over 6746.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2651, pruned_loss=0.03328, over 1422095.37 frames.], batch size: 31, lr: 2.99e-04
+2022-04-30 02:21:42,823 INFO [train.py:763] (6/8) Epoch 25, batch 2500, loss[loss=0.1586, simple_loss=0.2607, pruned_loss=0.02826, over 7356.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2639, pruned_loss=0.03253, over 1424203.15 frames.], batch size: 19, lr: 2.99e-04
+2022-04-30 02:22:48,788 INFO [train.py:763] (6/8) Epoch 25, batch 2550, loss[loss=0.1669, simple_loss=0.2452, pruned_loss=0.04434, over 7415.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2636, pruned_loss=0.03255, over 1426671.30 frames.], batch size: 18, lr: 2.99e-04
+2022-04-30 02:23:56,379 INFO [train.py:763] (6/8) Epoch 25, batch 2600, loss[loss=0.1664, simple_loss=0.2626, pruned_loss=0.03514, over 7154.00 frames.], tot_loss[loss=0.1649, simple_loss=0.264, pruned_loss=0.03292, over 1424148.29 frames.], batch size: 19, lr: 2.99e-04
+2022-04-30 02:25:02,541 INFO [train.py:763] (6/8) Epoch 25, batch 2650, loss[loss=0.1798, simple_loss=0.2773, pruned_loss=0.04114, over 7047.00 frames.], tot_loss[loss=0.1659, simple_loss=0.265, pruned_loss=0.03334, over 1419618.26 frames.], batch size: 28, lr: 2.99e-04
+2022-04-30 02:26:07,758 INFO [train.py:763] (6/8) Epoch 25, batch 2700, loss[loss=0.1529, simple_loss=0.247, pruned_loss=0.02944, over 7257.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2648, pruned_loss=0.03312, over 1419925.44 frames.], batch size: 19, lr: 2.99e-04
+2022-04-30 02:27:12,940 INFO [train.py:763] (6/8) Epoch 25, batch 2750, loss[loss=0.1905, simple_loss=0.2788, pruned_loss=0.05113, over 7291.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2652, pruned_loss=0.03321, over 1413367.56 frames.], batch size: 25, lr: 2.99e-04
+2022-04-30 02:28:19,371 INFO [train.py:763] (6/8) Epoch 25, batch 2800, loss[loss=0.1501, simple_loss=0.2502, pruned_loss=0.02506, over 7281.00 frames.], tot_loss[loss=0.165, simple_loss=0.2645, pruned_loss=0.03277, over 1416700.89 frames.], batch size: 18, lr: 2.99e-04
+2022-04-30 02:29:24,930 INFO [train.py:763] (6/8) Epoch 25, batch 2850, loss[loss=0.1983, simple_loss=0.2868, pruned_loss=0.05487, over 7421.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2643, pruned_loss=0.03282, over 1412069.36 frames.], batch size: 21, lr: 2.99e-04
+2022-04-30 02:30:30,621 INFO [train.py:763] (6/8) Epoch 25, batch 2900, loss[loss=0.1474, simple_loss=0.2445, pruned_loss=0.02512, over 7157.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2638, pruned_loss=0.03278, over 1418110.66 frames.], batch size: 20, lr: 2.99e-04
+2022-04-30 02:31:35,886 INFO [train.py:763] (6/8) Epoch 25, batch 2950, loss[loss=0.153, simple_loss=0.2553, pruned_loss=0.02538, over 7331.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2644, pruned_loss=0.03314, over 1418343.56 frames.], batch size: 20, lr: 2.99e-04
+2022-04-30 02:32:41,162 INFO [train.py:763] (6/8) Epoch 25, batch 3000, loss[loss=0.1522, simple_loss=0.2626, pruned_loss=0.02085, over 6395.00 frames.], tot_loss[loss=0.1656, simple_loss=0.265, pruned_loss=0.03311, over 1422511.75 frames.], batch size: 37, lr: 2.99e-04
+2022-04-30 02:32:41,163 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 02:32:56,273 INFO [train.py:792] (6/8) Epoch 25, validation: loss=0.1697, simple_loss=0.2684, pruned_loss=0.03548, over 698248.00 frames.
+2022-04-30 02:34:02,074 INFO [train.py:763] (6/8) Epoch 25, batch 3050, loss[loss=0.1391, simple_loss=0.2449, pruned_loss=0.01669, over 7335.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2659, pruned_loss=0.03328, over 1421393.09 frames.], batch size: 22, lr: 2.99e-04
+2022-04-30 02:35:09,272 INFO [train.py:763] (6/8) Epoch 25, batch 3100, loss[loss=0.1649, simple_loss=0.264, pruned_loss=0.03293, over 7257.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2659, pruned_loss=0.03314, over 1419662.10 frames.], batch size: 19, lr: 2.98e-04
+2022-04-30 02:36:16,362 INFO [train.py:763] (6/8) Epoch 25, batch 3150, loss[loss=0.1271, simple_loss=0.2197, pruned_loss=0.01727, over 7152.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2661, pruned_loss=0.03339, over 1417854.34 frames.], batch size: 17, lr: 2.98e-04
+2022-04-30 02:37:22,259 INFO [train.py:763] (6/8) Epoch 25, batch 3200, loss[loss=0.1446, simple_loss=0.2444, pruned_loss=0.02237, over 7153.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2655, pruned_loss=0.03301, over 1420975.33 frames.], batch size: 19, lr: 2.98e-04
+2022-04-30 02:38:29,251 INFO [train.py:763] (6/8) Epoch 25, batch 3250, loss[loss=0.1485, simple_loss=0.2459, pruned_loss=0.02562, over 7278.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2641, pruned_loss=0.03254, over 1423726.99 frames.], batch size: 18, lr: 2.98e-04
+2022-04-30 02:39:35,796 INFO [train.py:763] (6/8) Epoch 25, batch 3300, loss[loss=0.1705, simple_loss=0.2794, pruned_loss=0.03078, over 7152.00 frames.], tot_loss[loss=0.1655, simple_loss=0.265, pruned_loss=0.03305, over 1417616.19 frames.], batch size: 26, lr: 2.98e-04
+2022-04-30 02:40:42,746 INFO [train.py:763] (6/8) Epoch 25, batch 3350, loss[loss=0.2043, simple_loss=0.3033, pruned_loss=0.05267, over 7326.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2645, pruned_loss=0.03303, over 1414236.37 frames.], batch size: 21, lr: 2.98e-04
+2022-04-30 02:41:49,872 INFO [train.py:763] (6/8) Epoch 25, batch 3400, loss[loss=0.1716, simple_loss=0.2805, pruned_loss=0.03131, over 6619.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2635, pruned_loss=0.0327, over 1419924.83 frames.], batch size: 38, lr: 2.98e-04
+2022-04-30 02:42:55,394 INFO [train.py:763] (6/8) Epoch 25, batch 3450, loss[loss=0.1621, simple_loss=0.2574, pruned_loss=0.03341, over 7155.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2638, pruned_loss=0.03302, over 1420054.34 frames.], batch size: 18, lr: 2.98e-04
+2022-04-30 02:44:00,604 INFO [train.py:763] (6/8) Epoch 25, batch 3500, loss[loss=0.1727, simple_loss=0.2749, pruned_loss=0.03528, over 7381.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2644, pruned_loss=0.03314, over 1418830.39 frames.], batch size: 23, lr: 2.98e-04
+2022-04-30 02:45:06,557 INFO [train.py:763] (6/8) Epoch 25, batch 3550, loss[loss=0.2008, simple_loss=0.2913, pruned_loss=0.05515, over 7416.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2646, pruned_loss=0.03323, over 1421371.73 frames.], batch size: 21, lr: 2.98e-04
+2022-04-30 02:46:12,317 INFO [train.py:763] (6/8) Epoch 25, batch 3600, loss[loss=0.1709, simple_loss=0.2832, pruned_loss=0.02931, over 7182.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2643, pruned_loss=0.03302, over 1425528.85 frames.], batch size: 23, lr: 2.98e-04
+2022-04-30 02:47:18,089 INFO [train.py:763] (6/8) Epoch 25, batch 3650, loss[loss=0.1697, simple_loss=0.2671, pruned_loss=0.03618, over 7267.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2637, pruned_loss=0.03251, over 1426756.75 frames.], batch size: 19, lr: 2.98e-04
+2022-04-30 02:48:25,755 INFO [train.py:763] (6/8) Epoch 25, batch 3700, loss[loss=0.1658, simple_loss=0.2639, pruned_loss=0.03389, over 7067.00 frames.], tot_loss[loss=0.1651, simple_loss=0.264, pruned_loss=0.03304, over 1424558.12 frames.], batch size: 18, lr: 2.98e-04
+2022-04-30 02:49:32,897 INFO [train.py:763] (6/8) Epoch 25, batch 3750, loss[loss=0.1713, simple_loss=0.2718, pruned_loss=0.03537, over 7156.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2647, pruned_loss=0.03311, over 1423223.45 frames.], batch size: 19, lr: 2.98e-04
+2022-04-30 02:50:38,248 INFO [train.py:763] (6/8) Epoch 25, batch 3800, loss[loss=0.1733, simple_loss=0.2752, pruned_loss=0.03571, over 6426.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2646, pruned_loss=0.03284, over 1421159.95 frames.], batch size: 38, lr: 2.98e-04
+2022-04-30 02:51:43,564 INFO [train.py:763] (6/8) Epoch 25, batch 3850, loss[loss=0.1634, simple_loss=0.2756, pruned_loss=0.02558, over 7147.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2648, pruned_loss=0.03322, over 1418413.12 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 02:52:57,812 INFO [train.py:763] (6/8) Epoch 25, batch 3900, loss[loss=0.1582, simple_loss=0.2467, pruned_loss=0.03485, over 7401.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2658, pruned_loss=0.03334, over 1420939.44 frames.], batch size: 18, lr: 2.97e-04
+2022-04-30 02:54:03,676 INFO [train.py:763] (6/8) Epoch 25, batch 3950, loss[loss=0.1798, simple_loss=0.2756, pruned_loss=0.04202, over 7227.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2658, pruned_loss=0.03375, over 1425667.35 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 02:55:09,638 INFO [train.py:763] (6/8) Epoch 25, batch 4000, loss[loss=0.1478, simple_loss=0.2537, pruned_loss=0.02096, over 7424.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2648, pruned_loss=0.03334, over 1418328.03 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 02:56:14,888 INFO [train.py:763] (6/8) Epoch 25, batch 4050, loss[loss=0.1866, simple_loss=0.2874, pruned_loss=0.04294, over 7407.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2654, pruned_loss=0.03384, over 1419393.44 frames.], batch size: 21, lr: 2.97e-04
+2022-04-30 02:57:21,069 INFO [train.py:763] (6/8) Epoch 25, batch 4100, loss[loss=0.1434, simple_loss=0.2522, pruned_loss=0.01731, over 7407.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2657, pruned_loss=0.03382, over 1417502.41 frames.], batch size: 21, lr: 2.97e-04
+2022-04-30 02:58:26,417 INFO [train.py:763] (6/8) Epoch 25, batch 4150, loss[loss=0.1385, simple_loss=0.2325, pruned_loss=0.02222, over 7272.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2655, pruned_loss=0.03358, over 1422364.43 frames.], batch size: 19, lr: 2.97e-04
+2022-04-30 02:59:32,220 INFO [train.py:763] (6/8) Epoch 25, batch 4200, loss[loss=0.1835, simple_loss=0.2751, pruned_loss=0.04601, over 7063.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2658, pruned_loss=0.03368, over 1419110.77 frames.], batch size: 28, lr: 2.97e-04
+2022-04-30 03:00:37,740 INFO [train.py:763] (6/8) Epoch 25, batch 4250, loss[loss=0.1517, simple_loss=0.2501, pruned_loss=0.02666, over 7165.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2655, pruned_loss=0.03391, over 1418416.37 frames.], batch size: 18, lr: 2.97e-04
+2022-04-30 03:01:43,170 INFO [train.py:763] (6/8) Epoch 25, batch 4300, loss[loss=0.17, simple_loss=0.2697, pruned_loss=0.03508, over 7211.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2662, pruned_loss=0.034, over 1422362.63 frames.], batch size: 26, lr: 2.97e-04
+2022-04-30 03:03:06,200 INFO [train.py:763] (6/8) Epoch 25, batch 4350, loss[loss=0.1801, simple_loss=0.2794, pruned_loss=0.04038, over 7228.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2656, pruned_loss=0.03364, over 1414571.71 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 03:04:20,102 INFO [train.py:763] (6/8) Epoch 25, batch 4400, loss[loss=0.1387, simple_loss=0.2371, pruned_loss=0.02012, over 7061.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2665, pruned_loss=0.03397, over 1414384.83 frames.], batch size: 18, lr: 2.97e-04
+2022-04-30 03:05:34,210 INFO [train.py:763] (6/8) Epoch 25, batch 4450, loss[loss=0.1648, simple_loss=0.2724, pruned_loss=0.02858, over 7279.00 frames.], tot_loss[loss=0.167, simple_loss=0.2663, pruned_loss=0.03379, over 1414200.12 frames.], batch size: 24, lr: 2.97e-04
+2022-04-30 03:06:39,194 INFO [train.py:763] (6/8) Epoch 25, batch 4500, loss[loss=0.161, simple_loss=0.2617, pruned_loss=0.03013, over 7329.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2665, pruned_loss=0.03398, over 1399136.03 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 03:08:11,353 INFO [train.py:763] (6/8) Epoch 25, batch 4550, loss[loss=0.173, simple_loss=0.2652, pruned_loss=0.04037, over 4948.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2671, pruned_loss=0.03464, over 1389378.31 frames.], batch size: 52, lr: 2.97e-04
+2022-04-30 03:09:39,542 INFO [train.py:763] (6/8) Epoch 26, batch 0, loss[loss=0.1626, simple_loss=0.2456, pruned_loss=0.03985, over 7157.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2456, pruned_loss=0.03985, over 7157.00 frames.], batch size: 18, lr: 2.91e-04
+2022-04-30 03:10:45,449 INFO [train.py:763] (6/8) Epoch 26, batch 50, loss[loss=0.152, simple_loss=0.2382, pruned_loss=0.03293, over 7279.00 frames.], tot_loss[loss=0.164, simple_loss=0.2615, pruned_loss=0.03322, over 318418.99 frames.], batch size: 17, lr: 2.91e-04
+2022-04-30 03:11:50,711 INFO [train.py:763] (6/8) Epoch 26, batch 100, loss[loss=0.1351, simple_loss=0.2301, pruned_loss=0.02006, over 7280.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2626, pruned_loss=0.03177, over 562093.38 frames.], batch size: 17, lr: 2.91e-04
+2022-04-30 03:12:56,050 INFO [train.py:763] (6/8) Epoch 26, batch 150, loss[loss=0.1511, simple_loss=0.2537, pruned_loss=0.02424, over 6497.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2644, pruned_loss=0.03316, over 751572.84 frames.], batch size: 38, lr: 2.91e-04
+2022-04-30 03:14:01,247 INFO [train.py:763] (6/8) Epoch 26, batch 200, loss[loss=0.1572, simple_loss=0.267, pruned_loss=0.02369, over 7161.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2651, pruned_loss=0.03355, over 894413.16 frames.], batch size: 26, lr: 2.91e-04
+2022-04-30 03:15:07,041 INFO [train.py:763] (6/8) Epoch 26, batch 250, loss[loss=0.1659, simple_loss=0.2722, pruned_loss=0.02983, over 6368.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2652, pruned_loss=0.03344, over 1006320.89 frames.], batch size: 37, lr: 2.91e-04
+2022-04-30 03:16:13,122 INFO [train.py:763] (6/8) Epoch 26, batch 300, loss[loss=0.1696, simple_loss=0.2762, pruned_loss=0.0315, over 6143.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2646, pruned_loss=0.03292, over 1100140.14 frames.], batch size: 37, lr: 2.91e-04
+2022-04-30 03:17:18,447 INFO [train.py:763] (6/8) Epoch 26, batch 350, loss[loss=0.1798, simple_loss=0.2792, pruned_loss=0.04017, over 6737.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2642, pruned_loss=0.03315, over 1167480.33 frames.], batch size: 31, lr: 2.91e-04
+2022-04-30 03:18:23,748 INFO [train.py:763] (6/8) Epoch 26, batch 400, loss[loss=0.1468, simple_loss=0.2454, pruned_loss=0.02412, over 7144.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2634, pruned_loss=0.03281, over 1227469.98 frames.], batch size: 20, lr: 2.91e-04
+2022-04-30 03:19:29,470 INFO [train.py:763] (6/8) Epoch 26, batch 450, loss[loss=0.1524, simple_loss=0.2556, pruned_loss=0.02464, over 7231.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2633, pruned_loss=0.0323, over 1275469.55 frames.], batch size: 20, lr: 2.91e-04
+2022-04-30 03:20:34,846 INFO [train.py:763] (6/8) Epoch 26, batch 500, loss[loss=0.2046, simple_loss=0.2931, pruned_loss=0.05809, over 5113.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2632, pruned_loss=0.03264, over 1307438.60 frames.], batch size: 52, lr: 2.91e-04
+2022-04-30 03:21:40,169 INFO [train.py:763] (6/8) Epoch 26, batch 550, loss[loss=0.1661, simple_loss=0.2706, pruned_loss=0.03077, over 7202.00 frames.], tot_loss[loss=0.164, simple_loss=0.2633, pruned_loss=0.03237, over 1331364.93 frames.], batch size: 22, lr: 2.90e-04
+2022-04-30 03:22:45,578 INFO [train.py:763] (6/8) Epoch 26, batch 600, loss[loss=0.1622, simple_loss=0.2597, pruned_loss=0.03237, over 7262.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2629, pruned_loss=0.03209, over 1354147.45 frames.], batch size: 19, lr: 2.90e-04
+2022-04-30 03:23:51,104 INFO [train.py:763] (6/8) Epoch 26, batch 650, loss[loss=0.1357, simple_loss=0.2336, pruned_loss=0.01893, over 7270.00 frames.], tot_loss[loss=0.1626, simple_loss=0.262, pruned_loss=0.03159, over 1371538.67 frames.], batch size: 18, lr: 2.90e-04
+2022-04-30 03:24:56,236 INFO [train.py:763] (6/8) Epoch 26, batch 700, loss[loss=0.1632, simple_loss=0.2606, pruned_loss=0.03286, over 7119.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2631, pruned_loss=0.0319, over 1380455.76 frames.], batch size: 21, lr: 2.90e-04
+2022-04-30 03:26:12,125 INFO [train.py:763] (6/8) Epoch 26, batch 750, loss[loss=0.1563, simple_loss=0.2513, pruned_loss=0.03064, over 7139.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2628, pruned_loss=0.03164, over 1388159.08 frames.], batch size: 20, lr: 2.90e-04
+2022-04-30 03:27:17,952 INFO [train.py:763] (6/8) Epoch 26, batch 800, loss[loss=0.1703, simple_loss=0.2737, pruned_loss=0.0334, over 7232.00 frames.], tot_loss[loss=0.164, simple_loss=0.2635, pruned_loss=0.0323, over 1394702.88 frames.], batch size: 20, lr: 2.90e-04
+2022-04-30 03:28:23,823 INFO [train.py:763] (6/8) Epoch 26, batch 850, loss[loss=0.1726, simple_loss=0.272, pruned_loss=0.03663, over 5040.00 frames.], tot_loss[loss=0.165, simple_loss=0.2647, pruned_loss=0.03259, over 1397729.81 frames.], batch size: 52, lr: 2.90e-04
+2022-04-30 03:29:29,379 INFO [train.py:763] (6/8) Epoch 26, batch 900, loss[loss=0.1322, simple_loss=0.231, pruned_loss=0.01671, over 7388.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2639, pruned_loss=0.03238, over 1407055.47 frames.], batch size: 18, lr: 2.90e-04
+2022-04-30 03:30:35,251 INFO [train.py:763] (6/8) Epoch 26, batch 950, loss[loss=0.184, simple_loss=0.2612, pruned_loss=0.05339, over 6823.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2654, pruned_loss=0.03302, over 1408086.28 frames.], batch size: 15, lr: 2.90e-04
+2022-04-30 03:31:40,715 INFO [train.py:763] (6/8) Epoch 26, batch 1000, loss[loss=0.1804, simple_loss=0.2879, pruned_loss=0.03648, over 7275.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2659, pruned_loss=0.03348, over 1411034.63 frames.], batch size: 24, lr: 2.90e-04
+2022-04-30 03:32:46,140 INFO [train.py:763] (6/8) Epoch 26, batch 1050, loss[loss=0.1709, simple_loss=0.279, pruned_loss=0.03145, over 7212.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2657, pruned_loss=0.03285, over 1416713.98 frames.], batch size: 23, lr: 2.90e-04
+2022-04-30 03:33:51,498 INFO [train.py:763] (6/8) Epoch 26, batch 1100, loss[loss=0.1872, simple_loss=0.2895, pruned_loss=0.04247, over 7205.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2645, pruned_loss=0.0324, over 1421431.61 frames.], batch size: 22, lr: 2.90e-04
+2022-04-30 03:34:56,894 INFO [train.py:763] (6/8) Epoch 26, batch 1150, loss[loss=0.1541, simple_loss=0.2554, pruned_loss=0.02641, over 7156.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2648, pruned_loss=0.0323, over 1422516.72 frames.], batch size: 19, lr: 2.90e-04
+2022-04-30 03:36:02,472 INFO [train.py:763] (6/8) Epoch 26, batch 1200, loss[loss=0.1563, simple_loss=0.2607, pruned_loss=0.02592, over 7308.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2655, pruned_loss=0.03261, over 1426273.18 frames.], batch size: 24, lr: 2.90e-04
+2022-04-30 03:37:08,328 INFO [train.py:763] (6/8) Epoch 26, batch 1250, loss[loss=0.1954, simple_loss=0.2965, pruned_loss=0.04711, over 6333.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2643, pruned_loss=0.03249, over 1425685.81 frames.], batch size: 37, lr: 2.90e-04
+2022-04-30 03:38:14,026 INFO [train.py:763] (6/8) Epoch 26, batch 1300, loss[loss=0.1436, simple_loss=0.2333, pruned_loss=0.02692, over 7276.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2639, pruned_loss=0.03296, over 1421489.02 frames.], batch size: 18, lr: 2.90e-04
+2022-04-30 03:39:20,367 INFO [train.py:763] (6/8) Epoch 26, batch 1350, loss[loss=0.132, simple_loss=0.2275, pruned_loss=0.01826, over 7412.00 frames.], tot_loss[loss=0.1636, simple_loss=0.262, pruned_loss=0.03258, over 1425575.28 frames.], batch size: 18, lr: 2.89e-04
+2022-04-30 03:40:25,491 INFO [train.py:763] (6/8) Epoch 26, batch 1400, loss[loss=0.1724, simple_loss=0.2727, pruned_loss=0.03604, over 7199.00 frames.], tot_loss[loss=0.164, simple_loss=0.2625, pruned_loss=0.03275, over 1418857.50 frames.], batch size: 23, lr: 2.89e-04
+2022-04-30 03:41:30,976 INFO [train.py:763] (6/8) Epoch 26, batch 1450, loss[loss=0.1608, simple_loss=0.2678, pruned_loss=0.02686, over 7277.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2633, pruned_loss=0.03297, over 1420926.54 frames.], batch size: 18, lr: 2.89e-04
+2022-04-30 03:42:36,428 INFO [train.py:763] (6/8) Epoch 26, batch 1500, loss[loss=0.2008, simple_loss=0.294, pruned_loss=0.05381, over 4978.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2637, pruned_loss=0.03291, over 1417257.22 frames.], batch size: 52, lr: 2.89e-04
+2022-04-30 03:43:42,572 INFO [train.py:763] (6/8) Epoch 26, batch 1550, loss[loss=0.1445, simple_loss=0.2529, pruned_loss=0.01802, over 7117.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2638, pruned_loss=0.03254, over 1420887.57 frames.], batch size: 21, lr: 2.89e-04
+2022-04-30 03:44:49,280 INFO [train.py:763] (6/8) Epoch 26, batch 1600, loss[loss=0.1572, simple_loss=0.2577, pruned_loss=0.02833, over 7253.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2631, pruned_loss=0.03236, over 1424568.24 frames.], batch size: 19, lr: 2.89e-04
+2022-04-30 03:45:54,876 INFO [train.py:763] (6/8) Epoch 26, batch 1650, loss[loss=0.1715, simple_loss=0.2771, pruned_loss=0.03291, over 7169.00 frames.], tot_loss[loss=0.164, simple_loss=0.2633, pruned_loss=0.03238, over 1428745.78 frames.], batch size: 26, lr: 2.89e-04
+2022-04-30 03:47:00,375 INFO [train.py:763] (6/8) Epoch 26, batch 1700, loss[loss=0.1642, simple_loss=0.2793, pruned_loss=0.02458, over 7324.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2631, pruned_loss=0.03214, over 1430480.57 frames.], batch size: 22, lr: 2.89e-04
+2022-04-30 03:48:06,019 INFO [train.py:763] (6/8) Epoch 26, batch 1750, loss[loss=0.1838, simple_loss=0.2937, pruned_loss=0.0369, over 7160.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2642, pruned_loss=0.03257, over 1430923.55 frames.], batch size: 26, lr: 2.89e-04
+2022-04-30 03:49:13,274 INFO [train.py:763] (6/8) Epoch 26, batch 1800, loss[loss=0.1724, simple_loss=0.2685, pruned_loss=0.0382, over 7127.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2642, pruned_loss=0.03283, over 1428963.04 frames.], batch size: 21, lr: 2.89e-04
+2022-04-30 03:50:19,935 INFO [train.py:763] (6/8) Epoch 26, batch 1850, loss[loss=0.1797, simple_loss=0.2872, pruned_loss=0.03614, over 4904.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2647, pruned_loss=0.03306, over 1429089.58 frames.], batch size: 54, lr: 2.89e-04
+2022-04-30 03:51:25,629 INFO [train.py:763] (6/8) Epoch 26, batch 1900, loss[loss=0.1497, simple_loss=0.2434, pruned_loss=0.02805, over 7366.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2632, pruned_loss=0.0326, over 1427791.73 frames.], batch size: 19, lr: 2.89e-04
+2022-04-30 03:52:30,901 INFO [train.py:763] (6/8) Epoch 26, batch 1950, loss[loss=0.1917, simple_loss=0.2852, pruned_loss=0.04912, over 6398.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2632, pruned_loss=0.03295, over 1423785.01 frames.], batch size: 37, lr: 2.89e-04
+2022-04-30 03:53:36,220 INFO [train.py:763] (6/8) Epoch 26, batch 2000, loss[loss=0.1735, simple_loss=0.2711, pruned_loss=0.03795, over 6837.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2634, pruned_loss=0.03306, over 1421817.13 frames.], batch size: 31, lr: 2.89e-04
+2022-04-30 03:54:41,492 INFO [train.py:763] (6/8) Epoch 26, batch 2050, loss[loss=0.1667, simple_loss=0.2709, pruned_loss=0.03124, over 7174.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2642, pruned_loss=0.03311, over 1425193.89 frames.], batch size: 26, lr: 2.89e-04
+2022-04-30 03:55:48,143 INFO [train.py:763] (6/8) Epoch 26, batch 2100, loss[loss=0.1709, simple_loss=0.2753, pruned_loss=0.03325, over 7214.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2637, pruned_loss=0.03295, over 1423393.17 frames.], batch size: 22, lr: 2.89e-04
+2022-04-30 03:56:54,316 INFO [train.py:763] (6/8) Epoch 26, batch 2150, loss[loss=0.1801, simple_loss=0.2835, pruned_loss=0.03833, over 7285.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2653, pruned_loss=0.03363, over 1427287.53 frames.], batch size: 25, lr: 2.89e-04
+2022-04-30 03:57:59,846 INFO [train.py:763] (6/8) Epoch 26, batch 2200, loss[loss=0.153, simple_loss=0.2616, pruned_loss=0.02221, over 7243.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2653, pruned_loss=0.03363, over 1425677.91 frames.], batch size: 20, lr: 2.88e-04
+2022-04-30 03:59:06,003 INFO [train.py:763] (6/8) Epoch 26, batch 2250, loss[loss=0.1393, simple_loss=0.2326, pruned_loss=0.02307, over 7004.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2647, pruned_loss=0.0333, over 1430849.53 frames.], batch size: 16, lr: 2.88e-04
+2022-04-30 04:00:11,172 INFO [train.py:763] (6/8) Epoch 26, batch 2300, loss[loss=0.1483, simple_loss=0.2455, pruned_loss=0.02552, over 7142.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2652, pruned_loss=0.03355, over 1432218.10 frames.], batch size: 17, lr: 2.88e-04
+2022-04-30 04:01:17,206 INFO [train.py:763] (6/8) Epoch 26, batch 2350, loss[loss=0.1579, simple_loss=0.2606, pruned_loss=0.02759, over 7143.00 frames.], tot_loss[loss=0.1668, simple_loss=0.266, pruned_loss=0.03385, over 1431238.28 frames.], batch size: 20, lr: 2.88e-04
+2022-04-30 04:02:24,608 INFO [train.py:763] (6/8) Epoch 26, batch 2400, loss[loss=0.192, simple_loss=0.2872, pruned_loss=0.04844, over 7290.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2654, pruned_loss=0.03354, over 1432864.86 frames.], batch size: 24, lr: 2.88e-04
+2022-04-30 04:03:31,275 INFO [train.py:763] (6/8) Epoch 26, batch 2450, loss[loss=0.1592, simple_loss=0.2696, pruned_loss=0.02441, over 7236.00 frames.], tot_loss[loss=0.1657, simple_loss=0.265, pruned_loss=0.03319, over 1435876.28 frames.], batch size: 20, lr: 2.88e-04
+2022-04-30 04:04:36,619 INFO [train.py:763] (6/8) Epoch 26, batch 2500, loss[loss=0.1826, simple_loss=0.2934, pruned_loss=0.03593, over 7210.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2646, pruned_loss=0.03334, over 1437405.08 frames.], batch size: 21, lr: 2.88e-04
+2022-04-30 04:05:41,764 INFO [train.py:763] (6/8) Epoch 26, batch 2550, loss[loss=0.1796, simple_loss=0.2811, pruned_loss=0.039, over 6751.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2641, pruned_loss=0.03314, over 1435137.63 frames.], batch size: 31, lr: 2.88e-04
+2022-04-30 04:06:47,201 INFO [train.py:763] (6/8) Epoch 26, batch 2600, loss[loss=0.1481, simple_loss=0.2388, pruned_loss=0.02868, over 7229.00 frames.], tot_loss[loss=0.1658, simple_loss=0.265, pruned_loss=0.03331, over 1435757.65 frames.], batch size: 16, lr: 2.88e-04
+2022-04-30 04:07:52,617 INFO [train.py:763] (6/8) Epoch 26, batch 2650, loss[loss=0.187, simple_loss=0.2902, pruned_loss=0.04185, over 7255.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2647, pruned_loss=0.03325, over 1431958.14 frames.], batch size: 24, lr: 2.88e-04
+2022-04-30 04:08:58,042 INFO [train.py:763] (6/8) Epoch 26, batch 2700, loss[loss=0.1592, simple_loss=0.267, pruned_loss=0.02568, over 7332.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2646, pruned_loss=0.03349, over 1430490.54 frames.], batch size: 22, lr: 2.88e-04
+2022-04-30 04:10:03,925 INFO [train.py:763] (6/8) Epoch 26, batch 2750, loss[loss=0.1622, simple_loss=0.2617, pruned_loss=0.03139, over 7158.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2643, pruned_loss=0.033, over 1430401.30 frames.], batch size: 19, lr: 2.88e-04
+2022-04-30 04:11:09,746 INFO [train.py:763] (6/8) Epoch 26, batch 2800, loss[loss=0.1752, simple_loss=0.2725, pruned_loss=0.039, over 7282.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2641, pruned_loss=0.03271, over 1428964.09 frames.], batch size: 25, lr: 2.88e-04
+2022-04-30 04:12:16,487 INFO [train.py:763] (6/8) Epoch 26, batch 2850, loss[loss=0.1485, simple_loss=0.2556, pruned_loss=0.02074, over 7248.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2642, pruned_loss=0.03282, over 1428197.89 frames.], batch size: 19, lr: 2.88e-04
+2022-04-30 04:13:21,770 INFO [train.py:763] (6/8) Epoch 26, batch 2900, loss[loss=0.1332, simple_loss=0.2375, pruned_loss=0.01442, over 7170.00 frames.], tot_loss[loss=0.1643, simple_loss=0.264, pruned_loss=0.03232, over 1426972.23 frames.], batch size: 19, lr: 2.88e-04
+2022-04-30 04:14:26,919 INFO [train.py:763] (6/8) Epoch 26, batch 2950, loss[loss=0.1548, simple_loss=0.2554, pruned_loss=0.02707, over 7121.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2642, pruned_loss=0.03263, over 1420617.91 frames.], batch size: 21, lr: 2.88e-04
+2022-04-30 04:15:32,488 INFO [train.py:763] (6/8) Epoch 26, batch 3000, loss[loss=0.1843, simple_loss=0.2911, pruned_loss=0.03879, over 7417.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2638, pruned_loss=0.0326, over 1418838.13 frames.], batch size: 21, lr: 2.88e-04
+2022-04-30 04:15:32,489 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 04:15:47,843 INFO [train.py:792] (6/8) Epoch 26, validation: loss=0.1682, simple_loss=0.2653, pruned_loss=0.03549, over 698248.00 frames.
+2022-04-30 04:16:54,021 INFO [train.py:763] (6/8) Epoch 26, batch 3050, loss[loss=0.1483, simple_loss=0.2558, pruned_loss=0.02042, over 7105.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2638, pruned_loss=0.03325, over 1410850.67 frames.], batch size: 21, lr: 2.87e-04
+2022-04-30 04:17:59,871 INFO [train.py:763] (6/8) Epoch 26, batch 3100, loss[loss=0.1712, simple_loss=0.2881, pruned_loss=0.02718, over 7321.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2652, pruned_loss=0.03356, over 1416521.05 frames.], batch size: 21, lr: 2.87e-04
+2022-04-30 04:19:05,973 INFO [train.py:763] (6/8) Epoch 26, batch 3150, loss[loss=0.1762, simple_loss=0.2758, pruned_loss=0.0383, over 7196.00 frames.], tot_loss[loss=0.1658, simple_loss=0.265, pruned_loss=0.03329, over 1417896.05 frames.], batch size: 22, lr: 2.87e-04
+2022-04-30 04:20:11,640 INFO [train.py:763] (6/8) Epoch 26, batch 3200, loss[loss=0.1932, simple_loss=0.2876, pruned_loss=0.04935, over 7199.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2645, pruned_loss=0.03293, over 1419843.50 frames.], batch size: 23, lr: 2.87e-04
+2022-04-30 04:21:17,162 INFO [train.py:763] (6/8) Epoch 26, batch 3250, loss[loss=0.1682, simple_loss=0.266, pruned_loss=0.03524, over 6356.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2637, pruned_loss=0.03248, over 1420170.16 frames.], batch size: 38, lr: 2.87e-04
+2022-04-30 04:22:22,722 INFO [train.py:763] (6/8) Epoch 26, batch 3300, loss[loss=0.1518, simple_loss=0.2616, pruned_loss=0.021, over 6717.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2641, pruned_loss=0.03286, over 1420190.63 frames.], batch size: 31, lr: 2.87e-04
+2022-04-30 04:23:27,755 INFO [train.py:763] (6/8) Epoch 26, batch 3350, loss[loss=0.1745, simple_loss=0.2822, pruned_loss=0.0334, over 7344.00 frames.], tot_loss[loss=0.166, simple_loss=0.2656, pruned_loss=0.03321, over 1421394.89 frames.], batch size: 22, lr: 2.87e-04
+2022-04-30 04:24:33,267 INFO [train.py:763] (6/8) Epoch 26, batch 3400, loss[loss=0.1644, simple_loss=0.2771, pruned_loss=0.02582, over 7153.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2659, pruned_loss=0.03332, over 1418473.80 frames.], batch size: 20, lr: 2.87e-04
+2022-04-30 04:25:38,628 INFO [train.py:763] (6/8) Epoch 26, batch 3450, loss[loss=0.1486, simple_loss=0.2448, pruned_loss=0.02627, over 7346.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2649, pruned_loss=0.0324, over 1421610.40 frames.], batch size: 22, lr: 2.87e-04
+2022-04-30 04:26:44,100 INFO [train.py:763] (6/8) Epoch 26, batch 3500, loss[loss=0.1245, simple_loss=0.214, pruned_loss=0.0175, over 6820.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2648, pruned_loss=0.0324, over 1424024.63 frames.], batch size: 15, lr: 2.87e-04
+2022-04-30 04:27:49,685 INFO [train.py:763] (6/8) Epoch 26, batch 3550, loss[loss=0.1848, simple_loss=0.2742, pruned_loss=0.04769, over 5106.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2648, pruned_loss=0.03275, over 1417389.37 frames.], batch size: 53, lr: 2.87e-04
+2022-04-30 04:28:54,784 INFO [train.py:763] (6/8) Epoch 26, batch 3600, loss[loss=0.1615, simple_loss=0.2776, pruned_loss=0.02267, over 7158.00 frames.], tot_loss[loss=0.165, simple_loss=0.2646, pruned_loss=0.03269, over 1414645.26 frames.], batch size: 19, lr: 2.87e-04
+2022-04-30 04:30:00,886 INFO [train.py:763] (6/8) Epoch 26, batch 3650, loss[loss=0.1707, simple_loss=0.2795, pruned_loss=0.031, over 7060.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2636, pruned_loss=0.03235, over 1413339.48 frames.], batch size: 18, lr: 2.87e-04
+2022-04-30 04:31:07,246 INFO [train.py:763] (6/8) Epoch 26, batch 3700, loss[loss=0.1535, simple_loss=0.2383, pruned_loss=0.03429, over 7268.00 frames.], tot_loss[loss=0.164, simple_loss=0.2631, pruned_loss=0.03246, over 1412484.21 frames.], batch size: 18, lr: 2.87e-04
+2022-04-30 04:32:12,928 INFO [train.py:763] (6/8) Epoch 26, batch 3750, loss[loss=0.1662, simple_loss=0.2739, pruned_loss=0.02919, over 7211.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2621, pruned_loss=0.03231, over 1416332.71 frames.], batch size: 21, lr: 2.87e-04
+2022-04-30 04:33:19,996 INFO [train.py:763] (6/8) Epoch 26, batch 3800, loss[loss=0.1725, simple_loss=0.28, pruned_loss=0.03248, over 7333.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2618, pruned_loss=0.03241, over 1420513.64 frames.], batch size: 20, lr: 2.87e-04
+2022-04-30 04:34:26,373 INFO [train.py:763] (6/8) Epoch 26, batch 3850, loss[loss=0.1305, simple_loss=0.2153, pruned_loss=0.0229, over 7426.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2633, pruned_loss=0.0327, over 1414814.01 frames.], batch size: 18, lr: 2.87e-04
+2022-04-30 04:35:31,744 INFO [train.py:763] (6/8) Epoch 26, batch 3900, loss[loss=0.1812, simple_loss=0.291, pruned_loss=0.03575, over 7054.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2641, pruned_loss=0.03288, over 1415470.03 frames.], batch size: 28, lr: 2.86e-04
+2022-04-30 04:36:37,010 INFO [train.py:763] (6/8) Epoch 26, batch 3950, loss[loss=0.1582, simple_loss=0.2579, pruned_loss=0.02923, over 7354.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2643, pruned_loss=0.033, over 1420016.40 frames.], batch size: 19, lr: 2.86e-04
+2022-04-30 04:37:42,773 INFO [train.py:763] (6/8) Epoch 26, batch 4000, loss[loss=0.1604, simple_loss=0.2681, pruned_loss=0.02634, over 7051.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2645, pruned_loss=0.03286, over 1424733.90 frames.], batch size: 28, lr: 2.86e-04
+2022-04-30 04:38:48,120 INFO [train.py:763] (6/8) Epoch 26, batch 4050, loss[loss=0.1926, simple_loss=0.2786, pruned_loss=0.0533, over 7322.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2649, pruned_loss=0.03317, over 1425526.65 frames.], batch size: 20, lr: 2.86e-04
+2022-04-30 04:39:53,364 INFO [train.py:763] (6/8) Epoch 26, batch 4100, loss[loss=0.1639, simple_loss=0.2698, pruned_loss=0.02907, over 7334.00 frames.], tot_loss[loss=0.165, simple_loss=0.2644, pruned_loss=0.0328, over 1425015.88 frames.], batch size: 20, lr: 2.86e-04
+2022-04-30 04:40:58,512 INFO [train.py:763] (6/8) Epoch 26, batch 4150, loss[loss=0.1443, simple_loss=0.249, pruned_loss=0.01975, over 7123.00 frames.], tot_loss[loss=0.1643, simple_loss=0.264, pruned_loss=0.03228, over 1421555.17 frames.], batch size: 21, lr: 2.86e-04
+2022-04-30 04:42:03,901 INFO [train.py:763] (6/8) Epoch 26, batch 4200, loss[loss=0.1589, simple_loss=0.2616, pruned_loss=0.0281, over 7335.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2631, pruned_loss=0.0318, over 1422412.02 frames.], batch size: 22, lr: 2.86e-04
+2022-04-30 04:43:08,780 INFO [train.py:763] (6/8) Epoch 26, batch 4250, loss[loss=0.1701, simple_loss=0.2774, pruned_loss=0.03139, over 7412.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2644, pruned_loss=0.03218, over 1415253.83 frames.], batch size: 21, lr: 2.86e-04
+2022-04-30 04:44:14,520 INFO [train.py:763] (6/8) Epoch 26, batch 4300, loss[loss=0.1747, simple_loss=0.2789, pruned_loss=0.03521, over 6788.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2651, pruned_loss=0.03265, over 1412982.27 frames.], batch size: 31, lr: 2.86e-04
+2022-04-30 04:45:19,676 INFO [train.py:763] (6/8) Epoch 26, batch 4350, loss[loss=0.1462, simple_loss=0.2387, pruned_loss=0.0269, over 7000.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2649, pruned_loss=0.03309, over 1412601.47 frames.], batch size: 16, lr: 2.86e-04
+2022-04-30 04:46:24,705 INFO [train.py:763] (6/8) Epoch 26, batch 4400, loss[loss=0.1532, simple_loss=0.2506, pruned_loss=0.02789, over 6361.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2654, pruned_loss=0.03346, over 1399561.49 frames.], batch size: 37, lr: 2.86e-04
+2022-04-30 04:47:29,335 INFO [train.py:763] (6/8) Epoch 26, batch 4450, loss[loss=0.1655, simple_loss=0.2702, pruned_loss=0.03044, over 7347.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2647, pruned_loss=0.03343, over 1395031.97 frames.], batch size: 22, lr: 2.86e-04
+2022-04-30 04:48:34,529 INFO [train.py:763] (6/8) Epoch 26, batch 4500, loss[loss=0.1989, simple_loss=0.2988, pruned_loss=0.04953, over 7164.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2653, pruned_loss=0.0339, over 1386216.59 frames.], batch size: 18, lr: 2.86e-04
+2022-04-30 04:49:39,408 INFO [train.py:763] (6/8) Epoch 26, batch 4550, loss[loss=0.2148, simple_loss=0.2965, pruned_loss=0.06657, over 5106.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2639, pruned_loss=0.03397, over 1369938.90 frames.], batch size: 52, lr: 2.86e-04
+2022-04-30 04:51:07,357 INFO [train.py:763] (6/8) Epoch 27, batch 0, loss[loss=0.1697, simple_loss=0.2706, pruned_loss=0.03436, over 7273.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2706, pruned_loss=0.03436, over 7273.00 frames.], batch size: 19, lr: 2.81e-04
+2022-04-30 04:52:13,084 INFO [train.py:763] (6/8) Epoch 27, batch 50, loss[loss=0.1598, simple_loss=0.2481, pruned_loss=0.03577, over 7255.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2619, pruned_loss=0.03033, over 322301.12 frames.], batch size: 19, lr: 2.81e-04
+2022-04-30 04:53:19,208 INFO [train.py:763] (6/8) Epoch 27, batch 100, loss[loss=0.1721, simple_loss=0.2709, pruned_loss=0.03666, over 7139.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2642, pruned_loss=0.0318, over 565756.80 frames.], batch size: 20, lr: 2.80e-04
+2022-04-30 04:54:25,259 INFO [train.py:763] (6/8) Epoch 27, batch 150, loss[loss=0.1576, simple_loss=0.264, pruned_loss=0.02557, over 6346.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2648, pruned_loss=0.03178, over 753387.23 frames.], batch size: 38, lr: 2.80e-04
+2022-04-30 04:55:31,414 INFO [train.py:763] (6/8) Epoch 27, batch 200, loss[loss=0.1922, simple_loss=0.2899, pruned_loss=0.0473, over 7208.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2657, pruned_loss=0.03269, over 899503.03 frames.], batch size: 23, lr: 2.80e-04
+2022-04-30 04:56:38,040 INFO [train.py:763] (6/8) Epoch 27, batch 250, loss[loss=0.205, simple_loss=0.2913, pruned_loss=0.05935, over 7298.00 frames.], tot_loss[loss=0.166, simple_loss=0.2657, pruned_loss=0.03319, over 1015517.80 frames.], batch size: 24, lr: 2.80e-04
+2022-04-30 04:57:44,219 INFO [train.py:763] (6/8) Epoch 27, batch 300, loss[loss=0.169, simple_loss=0.2781, pruned_loss=0.02998, over 6739.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2651, pruned_loss=0.03219, over 1105587.19 frames.], batch size: 31, lr: 2.80e-04
+2022-04-30 04:58:50,092 INFO [train.py:763] (6/8) Epoch 27, batch 350, loss[loss=0.1644, simple_loss=0.2716, pruned_loss=0.02864, over 7162.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2633, pruned_loss=0.03164, over 1178290.70 frames.], batch size: 19, lr: 2.80e-04
+2022-04-30 04:59:56,369 INFO [train.py:763] (6/8) Epoch 27, batch 400, loss[loss=0.1411, simple_loss=0.2429, pruned_loss=0.01965, over 7148.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2635, pruned_loss=0.03185, over 1233911.69 frames.], batch size: 17, lr: 2.80e-04
+2022-04-30 05:01:02,255 INFO [train.py:763] (6/8) Epoch 27, batch 450, loss[loss=0.1678, simple_loss=0.272, pruned_loss=0.03181, over 7323.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2637, pruned_loss=0.03204, over 1270840.04 frames.], batch size: 25, lr: 2.80e-04
+2022-04-30 05:02:08,167 INFO [train.py:763] (6/8) Epoch 27, batch 500, loss[loss=0.1411, simple_loss=0.2496, pruned_loss=0.01631, over 7315.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2635, pruned_loss=0.03167, over 1308593.63 frames.], batch size: 21, lr: 2.80e-04
+2022-04-30 05:03:14,024 INFO [train.py:763] (6/8) Epoch 27, batch 550, loss[loss=0.1593, simple_loss=0.2612, pruned_loss=0.02872, over 7060.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2627, pruned_loss=0.03188, over 1330344.95 frames.], batch size: 18, lr: 2.80e-04
+2022-04-30 05:04:19,658 INFO [train.py:763] (6/8) Epoch 27, batch 600, loss[loss=0.1638, simple_loss=0.2745, pruned_loss=0.02656, over 7328.00 frames.], tot_loss[loss=0.163, simple_loss=0.2625, pruned_loss=0.0317, over 1348473.73 frames.], batch size: 20, lr: 2.80e-04
+2022-04-30 05:05:24,801 INFO [train.py:763] (6/8) Epoch 27, batch 650, loss[loss=0.173, simple_loss=0.2853, pruned_loss=0.03038, over 7151.00 frames.], tot_loss[loss=0.1634, simple_loss=0.263, pruned_loss=0.0319, over 1365831.57 frames.], batch size: 28, lr: 2.80e-04
+2022-04-30 05:06:40,260 INFO [train.py:763] (6/8) Epoch 27, batch 700, loss[loss=0.1426, simple_loss=0.2398, pruned_loss=0.02277, over 7052.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2628, pruned_loss=0.03213, over 1380171.92 frames.], batch size: 18, lr: 2.80e-04
+2022-04-30 05:07:46,094 INFO [train.py:763] (6/8) Epoch 27, batch 750, loss[loss=0.1413, simple_loss=0.2454, pruned_loss=0.01865, over 7220.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2621, pruned_loss=0.03205, over 1391357.27 frames.], batch size: 21, lr: 2.80e-04
+2022-04-30 05:08:51,495 INFO [train.py:763] (6/8) Epoch 27, batch 800, loss[loss=0.1699, simple_loss=0.2772, pruned_loss=0.03125, over 7014.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2622, pruned_loss=0.03175, over 1398863.67 frames.], batch size: 28, lr: 2.80e-04
+2022-04-30 05:09:56,919 INFO [train.py:763] (6/8) Epoch 27, batch 850, loss[loss=0.1815, simple_loss=0.2781, pruned_loss=0.0424, over 7255.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2624, pruned_loss=0.03193, over 1406392.67 frames.], batch size: 25, lr: 2.80e-04
+2022-04-30 05:11:02,106 INFO [train.py:763] (6/8) Epoch 27, batch 900, loss[loss=0.1414, simple_loss=0.2357, pruned_loss=0.02353, over 6995.00 frames.], tot_loss[loss=0.1634, simple_loss=0.263, pruned_loss=0.03193, over 1408196.07 frames.], batch size: 16, lr: 2.80e-04
+2022-04-30 05:12:07,298 INFO [train.py:763] (6/8) Epoch 27, batch 950, loss[loss=0.1721, simple_loss=0.2571, pruned_loss=0.04358, over 7173.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2634, pruned_loss=0.03201, over 1411089.06 frames.], batch size: 18, lr: 2.80e-04
+2022-04-30 05:13:12,791 INFO [train.py:763] (6/8) Epoch 27, batch 1000, loss[loss=0.1753, simple_loss=0.274, pruned_loss=0.03833, over 7423.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2624, pruned_loss=0.03164, over 1416946.55 frames.], batch size: 20, lr: 2.79e-04
+2022-04-30 05:14:18,816 INFO [train.py:763] (6/8) Epoch 27, batch 1050, loss[loss=0.1514, simple_loss=0.2535, pruned_loss=0.02465, over 7420.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2631, pruned_loss=0.03225, over 1416482.68 frames.], batch size: 21, lr: 2.79e-04
+2022-04-30 05:15:25,042 INFO [train.py:763] (6/8) Epoch 27, batch 1100, loss[loss=0.1341, simple_loss=0.2244, pruned_loss=0.02191, over 7450.00 frames.], tot_loss[loss=0.1646, simple_loss=0.264, pruned_loss=0.03258, over 1415896.14 frames.], batch size: 19, lr: 2.79e-04
+2022-04-30 05:16:31,242 INFO [train.py:763] (6/8) Epoch 27, batch 1150, loss[loss=0.1811, simple_loss=0.2837, pruned_loss=0.03926, over 7187.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2634, pruned_loss=0.03246, over 1420502.15 frames.], batch size: 23, lr: 2.79e-04
+2022-04-30 05:17:47,509 INFO [train.py:763] (6/8) Epoch 27, batch 1200, loss[loss=0.1668, simple_loss=0.2517, pruned_loss=0.04102, over 7135.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2629, pruned_loss=0.03233, over 1425317.03 frames.], batch size: 17, lr: 2.79e-04
+2022-04-30 05:19:01,885 INFO [train.py:763] (6/8) Epoch 27, batch 1250, loss[loss=0.1569, simple_loss=0.247, pruned_loss=0.0334, over 7130.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2631, pruned_loss=0.03224, over 1423415.53 frames.], batch size: 17, lr: 2.79e-04
+2022-04-30 05:20:26,021 INFO [train.py:763] (6/8) Epoch 27, batch 1300, loss[loss=0.1414, simple_loss=0.2333, pruned_loss=0.02478, over 7275.00 frames.], tot_loss[loss=0.164, simple_loss=0.2632, pruned_loss=0.03244, over 1419478.21 frames.], batch size: 18, lr: 2.79e-04
+2022-04-30 05:21:31,875 INFO [train.py:763] (6/8) Epoch 27, batch 1350, loss[loss=0.1674, simple_loss=0.2566, pruned_loss=0.03914, over 7348.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2637, pruned_loss=0.03273, over 1420065.23 frames.], batch size: 19, lr: 2.79e-04
+2022-04-30 05:22:37,303 INFO [train.py:763] (6/8) Epoch 27, batch 1400, loss[loss=0.1474, simple_loss=0.2483, pruned_loss=0.02327, over 7064.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2643, pruned_loss=0.03308, over 1420405.29 frames.], batch size: 18, lr: 2.79e-04
+2022-04-30 05:24:10,243 INFO [train.py:763] (6/8) Epoch 27, batch 1450, loss[loss=0.1479, simple_loss=0.2497, pruned_loss=0.02307, over 7329.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2633, pruned_loss=0.03262, over 1422442.28 frames.], batch size: 20, lr: 2.79e-04
+2022-04-30 05:25:16,095 INFO [train.py:763] (6/8) Epoch 27, batch 1500, loss[loss=0.1694, simple_loss=0.2775, pruned_loss=0.03062, over 7115.00 frames.], tot_loss[loss=0.165, simple_loss=0.2648, pruned_loss=0.03266, over 1424743.86 frames.], batch size: 21, lr: 2.79e-04
+2022-04-30 05:26:22,000 INFO [train.py:763] (6/8) Epoch 27, batch 1550, loss[loss=0.1396, simple_loss=0.2392, pruned_loss=0.02002, over 7229.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2641, pruned_loss=0.03257, over 1421897.03 frames.], batch size: 16, lr: 2.79e-04
+2022-04-30 05:27:29,035 INFO [train.py:763] (6/8) Epoch 27, batch 1600, loss[loss=0.1664, simple_loss=0.275, pruned_loss=0.02895, over 7427.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2635, pruned_loss=0.03241, over 1425871.22 frames.], batch size: 21, lr: 2.79e-04
+2022-04-30 05:28:35,021 INFO [train.py:763] (6/8) Epoch 27, batch 1650, loss[loss=0.1489, simple_loss=0.2502, pruned_loss=0.02376, over 7071.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2632, pruned_loss=0.03248, over 1426769.80 frames.], batch size: 18, lr: 2.79e-04
+2022-04-30 05:29:41,381 INFO [train.py:763] (6/8) Epoch 27, batch 1700, loss[loss=0.1506, simple_loss=0.2495, pruned_loss=0.02588, over 7351.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2638, pruned_loss=0.03237, over 1427673.58 frames.], batch size: 19, lr: 2.79e-04
+2022-04-30 05:30:48,529 INFO [train.py:763] (6/8) Epoch 27, batch 1750, loss[loss=0.1798, simple_loss=0.2758, pruned_loss=0.04192, over 6748.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2632, pruned_loss=0.03231, over 1429313.95 frames.], batch size: 31, lr: 2.79e-04
+2022-04-30 05:31:54,572 INFO [train.py:763] (6/8) Epoch 27, batch 1800, loss[loss=0.162, simple_loss=0.2621, pruned_loss=0.03092, over 7229.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2635, pruned_loss=0.03267, over 1428819.46 frames.], batch size: 20, lr: 2.79e-04
+2022-04-30 05:33:00,692 INFO [train.py:763] (6/8) Epoch 27, batch 1850, loss[loss=0.144, simple_loss=0.2435, pruned_loss=0.02225, over 7163.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2634, pruned_loss=0.03236, over 1431162.94 frames.], batch size: 19, lr: 2.79e-04
+2022-04-30 05:34:06,885 INFO [train.py:763] (6/8) Epoch 27, batch 1900, loss[loss=0.1307, simple_loss=0.2259, pruned_loss=0.01781, over 7257.00 frames.], tot_loss[loss=0.164, simple_loss=0.2636, pruned_loss=0.03219, over 1431147.63 frames.], batch size: 17, lr: 2.78e-04
+2022-04-30 05:35:13,692 INFO [train.py:763] (6/8) Epoch 27, batch 1950, loss[loss=0.1598, simple_loss=0.2707, pruned_loss=0.02445, over 6460.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2639, pruned_loss=0.0325, over 1426439.66 frames.], batch size: 38, lr: 2.78e-04
+2022-04-30 05:36:20,337 INFO [train.py:763] (6/8) Epoch 27, batch 2000, loss[loss=0.1613, simple_loss=0.2682, pruned_loss=0.02724, over 7215.00 frames.], tot_loss[loss=0.164, simple_loss=0.2635, pruned_loss=0.03219, over 1425223.27 frames.], batch size: 21, lr: 2.78e-04
+2022-04-30 05:37:26,472 INFO [train.py:763] (6/8) Epoch 27, batch 2050, loss[loss=0.1887, simple_loss=0.2843, pruned_loss=0.04657, over 7191.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2644, pruned_loss=0.03265, over 1423993.05 frames.], batch size: 23, lr: 2.78e-04
+2022-04-30 05:38:32,946 INFO [train.py:763] (6/8) Epoch 27, batch 2100, loss[loss=0.1788, simple_loss=0.291, pruned_loss=0.03333, over 7319.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2634, pruned_loss=0.03176, over 1423622.41 frames.], batch size: 25, lr: 2.78e-04
+2022-04-30 05:39:38,770 INFO [train.py:763] (6/8) Epoch 27, batch 2150, loss[loss=0.1346, simple_loss=0.2286, pruned_loss=0.02033, over 7149.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2635, pruned_loss=0.03199, over 1422012.86 frames.], batch size: 17, lr: 2.78e-04
+2022-04-30 05:40:44,413 INFO [train.py:763] (6/8) Epoch 27, batch 2200, loss[loss=0.1935, simple_loss=0.2941, pruned_loss=0.04647, over 7263.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2637, pruned_loss=0.0324, over 1420436.12 frames.], batch size: 24, lr: 2.78e-04
+2022-04-30 05:41:50,159 INFO [train.py:763] (6/8) Epoch 27, batch 2250, loss[loss=0.175, simple_loss=0.2791, pruned_loss=0.03547, over 7337.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2635, pruned_loss=0.03247, over 1423870.48 frames.], batch size: 22, lr: 2.78e-04
+2022-04-30 05:42:56,034 INFO [train.py:763] (6/8) Epoch 27, batch 2300, loss[loss=0.1647, simple_loss=0.2617, pruned_loss=0.03391, over 7153.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2638, pruned_loss=0.03251, over 1421843.55 frames.], batch size: 20, lr: 2.78e-04
+2022-04-30 05:44:01,767 INFO [train.py:763] (6/8) Epoch 27, batch 2350, loss[loss=0.1726, simple_loss=0.2631, pruned_loss=0.04108, over 7159.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2633, pruned_loss=0.03242, over 1419298.78 frames.], batch size: 19, lr: 2.78e-04
+2022-04-30 05:45:08,045 INFO [train.py:763] (6/8) Epoch 27, batch 2400, loss[loss=0.1752, simple_loss=0.2759, pruned_loss=0.03719, over 7187.00 frames.], tot_loss[loss=0.1649, simple_loss=0.264, pruned_loss=0.03286, over 1422473.76 frames.], batch size: 23, lr: 2.78e-04
+2022-04-30 05:46:14,165 INFO [train.py:763] (6/8) Epoch 27, batch 2450, loss[loss=0.1602, simple_loss=0.2612, pruned_loss=0.02955, over 6586.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2629, pruned_loss=0.03244, over 1423849.33 frames.], batch size: 38, lr: 2.78e-04
+2022-04-30 05:47:19,804 INFO [train.py:763] (6/8) Epoch 27, batch 2500, loss[loss=0.158, simple_loss=0.2378, pruned_loss=0.03915, over 6786.00 frames.], tot_loss[loss=0.1646, simple_loss=0.263, pruned_loss=0.03311, over 1419698.82 frames.], batch size: 15, lr: 2.78e-04
+2022-04-30 05:48:25,888 INFO [train.py:763] (6/8) Epoch 27, batch 2550, loss[loss=0.1626, simple_loss=0.2592, pruned_loss=0.03297, over 7255.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2632, pruned_loss=0.0331, over 1420428.06 frames.], batch size: 19, lr: 2.78e-04
+2022-04-30 05:49:31,726 INFO [train.py:763] (6/8) Epoch 27, batch 2600, loss[loss=0.1599, simple_loss=0.2683, pruned_loss=0.02579, over 7228.00 frames.], tot_loss[loss=0.164, simple_loss=0.2622, pruned_loss=0.03287, over 1420540.05 frames.], batch size: 20, lr: 2.78e-04
+2022-04-30 05:50:37,402 INFO [train.py:763] (6/8) Epoch 27, batch 2650, loss[loss=0.14, simple_loss=0.239, pruned_loss=0.02049, over 7004.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2622, pruned_loss=0.03259, over 1419684.77 frames.], batch size: 16, lr: 2.78e-04
+2022-04-30 05:51:42,954 INFO [train.py:763] (6/8) Epoch 27, batch 2700, loss[loss=0.161, simple_loss=0.2631, pruned_loss=0.02947, over 7322.00 frames.], tot_loss[loss=0.163, simple_loss=0.2619, pruned_loss=0.03207, over 1421461.47 frames.], batch size: 21, lr: 2.78e-04
+2022-04-30 05:52:49,038 INFO [train.py:763] (6/8) Epoch 27, batch 2750, loss[loss=0.1703, simple_loss=0.2741, pruned_loss=0.03332, over 7261.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2616, pruned_loss=0.03183, over 1420916.96 frames.], batch size: 19, lr: 2.78e-04
+2022-04-30 05:53:54,756 INFO [train.py:763] (6/8) Epoch 27, batch 2800, loss[loss=0.1628, simple_loss=0.2678, pruned_loss=0.02886, over 7242.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2623, pruned_loss=0.03225, over 1417002.76 frames.], batch size: 20, lr: 2.77e-04
+2022-04-30 05:55:00,520 INFO [train.py:763] (6/8) Epoch 27, batch 2850, loss[loss=0.1448, simple_loss=0.242, pruned_loss=0.02382, over 7123.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2617, pruned_loss=0.03209, over 1421395.12 frames.], batch size: 17, lr: 2.77e-04
+2022-04-30 05:56:06,158 INFO [train.py:763] (6/8) Epoch 27, batch 2900, loss[loss=0.1545, simple_loss=0.2529, pruned_loss=0.02806, over 7274.00 frames.], tot_loss[loss=0.1642, simple_loss=0.263, pruned_loss=0.03265, over 1420607.64 frames.], batch size: 25, lr: 2.77e-04
+2022-04-30 05:57:11,713 INFO [train.py:763] (6/8) Epoch 27, batch 2950, loss[loss=0.1903, simple_loss=0.2887, pruned_loss=0.04599, over 7211.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2634, pruned_loss=0.03272, over 1423409.83 frames.], batch size: 23, lr: 2.77e-04
+2022-04-30 05:58:18,060 INFO [train.py:763] (6/8) Epoch 27, batch 3000, loss[loss=0.1613, simple_loss=0.2613, pruned_loss=0.03066, over 7029.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2648, pruned_loss=0.03339, over 1425083.87 frames.], batch size: 28, lr: 2.77e-04
+2022-04-30 05:58:18,061 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 05:58:33,165 INFO [train.py:792] (6/8) Epoch 27, validation: loss=0.1686, simple_loss=0.2648, pruned_loss=0.03621, over 698248.00 frames.
+2022-04-30 05:59:40,075 INFO [train.py:763] (6/8) Epoch 27, batch 3050, loss[loss=0.1282, simple_loss=0.2119, pruned_loss=0.02228, over 7129.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2646, pruned_loss=0.03346, over 1426899.33 frames.], batch size: 17, lr: 2.77e-04
+2022-04-30 06:00:45,835 INFO [train.py:763] (6/8) Epoch 27, batch 3100, loss[loss=0.1791, simple_loss=0.277, pruned_loss=0.04063, over 7369.00 frames.], tot_loss[loss=0.165, simple_loss=0.2636, pruned_loss=0.03324, over 1425408.31 frames.], batch size: 23, lr: 2.77e-04
+2022-04-30 06:01:51,942 INFO [train.py:763] (6/8) Epoch 27, batch 3150, loss[loss=0.1465, simple_loss=0.2432, pruned_loss=0.02489, over 7415.00 frames.], tot_loss[loss=0.1645, simple_loss=0.263, pruned_loss=0.03298, over 1424240.22 frames.], batch size: 18, lr: 2.77e-04
+2022-04-30 06:02:58,133 INFO [train.py:763] (6/8) Epoch 27, batch 3200, loss[loss=0.1615, simple_loss=0.2711, pruned_loss=0.02594, over 7319.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2632, pruned_loss=0.03274, over 1425056.58 frames.], batch size: 21, lr: 2.77e-04
+2022-04-30 06:04:04,077 INFO [train.py:763] (6/8) Epoch 27, batch 3250, loss[loss=0.1524, simple_loss=0.2458, pruned_loss=0.02952, over 7157.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2625, pruned_loss=0.03268, over 1424618.15 frames.], batch size: 18, lr: 2.77e-04
+2022-04-30 06:05:10,047 INFO [train.py:763] (6/8) Epoch 27, batch 3300, loss[loss=0.1548, simple_loss=0.2462, pruned_loss=0.0317, over 6987.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2628, pruned_loss=0.0325, over 1423314.65 frames.], batch size: 16, lr: 2.77e-04
+2022-04-30 06:06:16,491 INFO [train.py:763] (6/8) Epoch 27, batch 3350, loss[loss=0.2002, simple_loss=0.3033, pruned_loss=0.04856, over 7383.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2636, pruned_loss=0.03261, over 1420914.45 frames.], batch size: 23, lr: 2.77e-04
+2022-04-30 06:07:23,075 INFO [train.py:763] (6/8) Epoch 27, batch 3400, loss[loss=0.1638, simple_loss=0.2686, pruned_loss=0.02955, over 7324.00 frames.], tot_loss[loss=0.164, simple_loss=0.2632, pruned_loss=0.03235, over 1422873.86 frames.], batch size: 20, lr: 2.77e-04
+2022-04-30 06:08:29,075 INFO [train.py:763] (6/8) Epoch 27, batch 3450, loss[loss=0.1976, simple_loss=0.2877, pruned_loss=0.05372, over 7212.00 frames.], tot_loss[loss=0.1638, simple_loss=0.263, pruned_loss=0.03227, over 1424124.49 frames.], batch size: 22, lr: 2.77e-04
+2022-04-30 06:09:34,963 INFO [train.py:763] (6/8) Epoch 27, batch 3500, loss[loss=0.1503, simple_loss=0.2561, pruned_loss=0.02226, over 7069.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2639, pruned_loss=0.03256, over 1423175.90 frames.], batch size: 18, lr: 2.77e-04
+2022-04-30 06:10:40,828 INFO [train.py:763] (6/8) Epoch 27, batch 3550, loss[loss=0.157, simple_loss=0.2548, pruned_loss=0.02962, over 7343.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2643, pruned_loss=0.03228, over 1423856.10 frames.], batch size: 22, lr: 2.77e-04
+2022-04-30 06:11:46,447 INFO [train.py:763] (6/8) Epoch 27, batch 3600, loss[loss=0.1687, simple_loss=0.2637, pruned_loss=0.03683, over 7069.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2645, pruned_loss=0.03238, over 1423115.59 frames.], batch size: 18, lr: 2.77e-04
+2022-04-30 06:12:52,026 INFO [train.py:763] (6/8) Epoch 27, batch 3650, loss[loss=0.2136, simple_loss=0.2958, pruned_loss=0.06572, over 7409.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2642, pruned_loss=0.03244, over 1423208.89 frames.], batch size: 21, lr: 2.77e-04
+2022-04-30 06:13:58,382 INFO [train.py:763] (6/8) Epoch 27, batch 3700, loss[loss=0.1581, simple_loss=0.2584, pruned_loss=0.02897, over 7435.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2635, pruned_loss=0.03207, over 1423582.17 frames.], batch size: 20, lr: 2.77e-04
+2022-04-30 06:15:04,063 INFO [train.py:763] (6/8) Epoch 27, batch 3750, loss[loss=0.1779, simple_loss=0.2868, pruned_loss=0.0345, over 5261.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2635, pruned_loss=0.03211, over 1419218.27 frames.], batch size: 52, lr: 2.76e-04
+2022-04-30 06:16:10,309 INFO [train.py:763] (6/8) Epoch 27, batch 3800, loss[loss=0.1649, simple_loss=0.2503, pruned_loss=0.03976, over 7274.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2643, pruned_loss=0.03265, over 1421042.87 frames.], batch size: 17, lr: 2.76e-04
+2022-04-30 06:17:16,531 INFO [train.py:763] (6/8) Epoch 27, batch 3850, loss[loss=0.1864, simple_loss=0.2874, pruned_loss=0.0427, over 7152.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2646, pruned_loss=0.03286, over 1424754.53 frames.], batch size: 19, lr: 2.76e-04
+2022-04-30 06:18:22,910 INFO [train.py:763] (6/8) Epoch 27, batch 3900, loss[loss=0.1737, simple_loss=0.2735, pruned_loss=0.03696, over 7208.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2646, pruned_loss=0.03292, over 1423713.59 frames.], batch size: 22, lr: 2.76e-04
+2022-04-30 06:19:28,541 INFO [train.py:763] (6/8) Epoch 27, batch 3950, loss[loss=0.161, simple_loss=0.2639, pruned_loss=0.029, over 7204.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2637, pruned_loss=0.03281, over 1424951.98 frames.], batch size: 22, lr: 2.76e-04
+2022-04-30 06:20:34,798 INFO [train.py:763] (6/8) Epoch 27, batch 4000, loss[loss=0.1656, simple_loss=0.2668, pruned_loss=0.03219, over 6751.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2626, pruned_loss=0.03236, over 1422397.21 frames.], batch size: 31, lr: 2.76e-04
+2022-04-30 06:21:40,918 INFO [train.py:763] (6/8) Epoch 27, batch 4050, loss[loss=0.1996, simple_loss=0.2849, pruned_loss=0.05713, over 4954.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2624, pruned_loss=0.03234, over 1416120.55 frames.], batch size: 52, lr: 2.76e-04
+2022-04-30 06:22:47,109 INFO [train.py:763] (6/8) Epoch 27, batch 4100, loss[loss=0.1664, simple_loss=0.2546, pruned_loss=0.03908, over 7150.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2626, pruned_loss=0.0323, over 1417788.19 frames.], batch size: 17, lr: 2.76e-04
+2022-04-30 06:24:03,945 INFO [train.py:763] (6/8) Epoch 27, batch 4150, loss[loss=0.1368, simple_loss=0.236, pruned_loss=0.01879, over 7151.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2636, pruned_loss=0.03269, over 1423365.07 frames.], batch size: 19, lr: 2.76e-04
+2022-04-30 06:25:09,376 INFO [train.py:763] (6/8) Epoch 27, batch 4200, loss[loss=0.1953, simple_loss=0.2921, pruned_loss=0.0493, over 4950.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2646, pruned_loss=0.03293, over 1417154.36 frames.], batch size: 53, lr: 2.76e-04
+2022-04-30 06:26:15,108 INFO [train.py:763] (6/8) Epoch 27, batch 4250, loss[loss=0.1576, simple_loss=0.2473, pruned_loss=0.03398, over 7069.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2645, pruned_loss=0.03294, over 1414343.58 frames.], batch size: 18, lr: 2.76e-04
+2022-04-30 06:27:21,141 INFO [train.py:763] (6/8) Epoch 27, batch 4300, loss[loss=0.1478, simple_loss=0.2451, pruned_loss=0.02522, over 7143.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2642, pruned_loss=0.03315, over 1415801.74 frames.], batch size: 17, lr: 2.76e-04
+2022-04-30 06:28:27,403 INFO [train.py:763] (6/8) Epoch 27, batch 4350, loss[loss=0.1585, simple_loss=0.2661, pruned_loss=0.0255, over 7218.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2646, pruned_loss=0.03295, over 1416932.37 frames.], batch size: 21, lr: 2.76e-04
+2022-04-30 06:29:33,357 INFO [train.py:763] (6/8) Epoch 27, batch 4400, loss[loss=0.1599, simple_loss=0.268, pruned_loss=0.0259, over 6445.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2646, pruned_loss=0.03303, over 1408953.15 frames.], batch size: 38, lr: 2.76e-04
+2022-04-30 06:30:39,369 INFO [train.py:763] (6/8) Epoch 27, batch 4450, loss[loss=0.1573, simple_loss=0.2498, pruned_loss=0.03239, over 6815.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2653, pruned_loss=0.03325, over 1403266.44 frames.], batch size: 15, lr: 2.76e-04
+2022-04-30 06:31:44,897 INFO [train.py:763] (6/8) Epoch 27, batch 4500, loss[loss=0.1649, simple_loss=0.274, pruned_loss=0.02793, over 7209.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2654, pruned_loss=0.03315, over 1391483.89 frames.], batch size: 21, lr: 2.76e-04
+2022-04-30 06:32:50,036 INFO [train.py:763] (6/8) Epoch 27, batch 4550, loss[loss=0.1746, simple_loss=0.2803, pruned_loss=0.03444, over 6310.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2664, pruned_loss=0.03399, over 1360533.83 frames.], batch size: 37, lr: 2.76e-04
+2022-04-30 06:34:19,193 INFO [train.py:763] (6/8) Epoch 28, batch 0, loss[loss=0.1724, simple_loss=0.2576, pruned_loss=0.04362, over 7135.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2576, pruned_loss=0.04362, over 7135.00 frames.], batch size: 28, lr: 2.71e-04
+2022-04-30 06:35:24,834 INFO [train.py:763] (6/8) Epoch 28, batch 50, loss[loss=0.1873, simple_loss=0.2827, pruned_loss=0.04597, over 7302.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2638, pruned_loss=0.03274, over 323734.98 frames.], batch size: 24, lr: 2.71e-04
+2022-04-30 06:36:31,683 INFO [train.py:763] (6/8) Epoch 28, batch 100, loss[loss=0.1907, simple_loss=0.2924, pruned_loss=0.04446, over 7316.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2644, pruned_loss=0.03295, over 570251.87 frames.], batch size: 21, lr: 2.71e-04
+2022-04-30 06:37:37,371 INFO [train.py:763] (6/8) Epoch 28, batch 150, loss[loss=0.1824, simple_loss=0.288, pruned_loss=0.03841, over 7236.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2629, pruned_loss=0.03205, over 759997.51 frames.], batch size: 20, lr: 2.71e-04
+2022-04-30 06:38:43,679 INFO [train.py:763] (6/8) Epoch 28, batch 200, loss[loss=0.1413, simple_loss=0.2416, pruned_loss=0.02048, over 7056.00 frames.], tot_loss[loss=0.1633, simple_loss=0.263, pruned_loss=0.03177, over 908919.46 frames.], batch size: 18, lr: 2.71e-04
+2022-04-30 06:39:49,240 INFO [train.py:763] (6/8) Epoch 28, batch 250, loss[loss=0.1812, simple_loss=0.2809, pruned_loss=0.04078, over 5052.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2625, pruned_loss=0.03153, over 1019721.94 frames.], batch size: 53, lr: 2.71e-04
+2022-04-30 06:40:54,484 INFO [train.py:763] (6/8) Epoch 28, batch 300, loss[loss=0.1545, simple_loss=0.2433, pruned_loss=0.03279, over 7170.00 frames.], tot_loss[loss=0.1622, simple_loss=0.262, pruned_loss=0.03121, over 1109774.69 frames.], batch size: 18, lr: 2.70e-04
+2022-04-30 06:41:59,623 INFO [train.py:763] (6/8) Epoch 28, batch 350, loss[loss=0.162, simple_loss=0.2507, pruned_loss=0.03665, over 7070.00 frames.], tot_loss[loss=0.1629, simple_loss=0.263, pruned_loss=0.03145, over 1181743.62 frames.], batch size: 18, lr: 2.70e-04
+2022-04-30 06:43:05,887 INFO [train.py:763] (6/8) Epoch 28, batch 400, loss[loss=0.161, simple_loss=0.2721, pruned_loss=0.02489, over 7150.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2645, pruned_loss=0.03194, over 1237086.18 frames.], batch size: 20, lr: 2.70e-04
+2022-04-30 06:44:12,422 INFO [train.py:763] (6/8) Epoch 28, batch 450, loss[loss=0.169, simple_loss=0.2626, pruned_loss=0.03769, over 7118.00 frames.], tot_loss[loss=0.164, simple_loss=0.2639, pruned_loss=0.03203, over 1282988.82 frames.], batch size: 21, lr: 2.70e-04
+2022-04-30 06:45:17,939 INFO [train.py:763] (6/8) Epoch 28, batch 500, loss[loss=0.2087, simple_loss=0.292, pruned_loss=0.06267, over 5073.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2634, pruned_loss=0.03209, over 1310603.78 frames.], batch size: 54, lr: 2.70e-04
+2022-04-30 06:46:23,648 INFO [train.py:763] (6/8) Epoch 28, batch 550, loss[loss=0.179, simple_loss=0.2756, pruned_loss=0.04117, over 7220.00 frames.], tot_loss[loss=0.1635, simple_loss=0.263, pruned_loss=0.03196, over 1332742.50 frames.], batch size: 21, lr: 2.70e-04
+2022-04-30 06:47:29,780 INFO [train.py:763] (6/8) Epoch 28, batch 600, loss[loss=0.1736, simple_loss=0.2749, pruned_loss=0.03608, over 7250.00 frames.], tot_loss[loss=0.1629, simple_loss=0.262, pruned_loss=0.03187, over 1349503.49 frames.], batch size: 19, lr: 2.70e-04
+2022-04-30 06:48:35,461 INFO [train.py:763] (6/8) Epoch 28, batch 650, loss[loss=0.1656, simple_loss=0.2612, pruned_loss=0.035, over 7059.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2616, pruned_loss=0.0317, over 1368090.06 frames.], batch size: 18, lr: 2.70e-04
+2022-04-30 06:49:42,651 INFO [train.py:763] (6/8) Epoch 28, batch 700, loss[loss=0.1796, simple_loss=0.2722, pruned_loss=0.04346, over 4996.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2627, pruned_loss=0.03208, over 1376182.79 frames.], batch size: 52, lr: 2.70e-04
+2022-04-30 06:50:48,233 INFO [train.py:763] (6/8) Epoch 28, batch 750, loss[loss=0.1505, simple_loss=0.2548, pruned_loss=0.02312, over 7427.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2621, pruned_loss=0.03182, over 1383638.17 frames.], batch size: 20, lr: 2.70e-04
+2022-04-30 06:51:53,705 INFO [train.py:763] (6/8) Epoch 28, batch 800, loss[loss=0.1645, simple_loss=0.2713, pruned_loss=0.02882, over 7115.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2628, pruned_loss=0.03209, over 1389003.93 frames.], batch size: 21, lr: 2.70e-04
+2022-04-30 06:52:59,921 INFO [train.py:763] (6/8) Epoch 28, batch 850, loss[loss=0.1789, simple_loss=0.281, pruned_loss=0.03844, over 6302.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2642, pruned_loss=0.03278, over 1393004.42 frames.], batch size: 37, lr: 2.70e-04
+2022-04-30 06:54:06,451 INFO [train.py:763] (6/8) Epoch 28, batch 900, loss[loss=0.1726, simple_loss=0.2744, pruned_loss=0.0354, over 6800.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2637, pruned_loss=0.03297, over 1399912.88 frames.], batch size: 31, lr: 2.70e-04
+2022-04-30 06:55:12,103 INFO [train.py:763] (6/8) Epoch 28, batch 950, loss[loss=0.1975, simple_loss=0.2978, pruned_loss=0.04855, over 7217.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2635, pruned_loss=0.03255, over 1409348.07 frames.], batch size: 22, lr: 2.70e-04
+2022-04-30 06:56:17,978 INFO [train.py:763] (6/8) Epoch 28, batch 1000, loss[loss=0.1598, simple_loss=0.2491, pruned_loss=0.03528, over 6801.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2626, pruned_loss=0.03215, over 1415197.63 frames.], batch size: 15, lr: 2.70e-04
+2022-04-30 06:57:23,503 INFO [train.py:763] (6/8) Epoch 28, batch 1050, loss[loss=0.1764, simple_loss=0.2792, pruned_loss=0.03681, over 7408.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2629, pruned_loss=0.03239, over 1420089.69 frames.], batch size: 21, lr: 2.70e-04
+2022-04-30 06:58:29,249 INFO [train.py:763] (6/8) Epoch 28, batch 1100, loss[loss=0.1619, simple_loss=0.2523, pruned_loss=0.03576, over 7279.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2632, pruned_loss=0.03271, over 1422622.83 frames.], batch size: 17, lr: 2.70e-04
+2022-04-30 06:59:35,659 INFO [train.py:763] (6/8) Epoch 28, batch 1150, loss[loss=0.1833, simple_loss=0.2862, pruned_loss=0.04025, over 7053.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2627, pruned_loss=0.0326, over 1420972.84 frames.], batch size: 28, lr: 2.70e-04
+2022-04-30 07:00:40,812 INFO [train.py:763] (6/8) Epoch 28, batch 1200, loss[loss=0.1679, simple_loss=0.2664, pruned_loss=0.03465, over 7095.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2646, pruned_loss=0.0329, over 1423549.85 frames.], batch size: 28, lr: 2.70e-04
+2022-04-30 07:01:47,023 INFO [train.py:763] (6/8) Epoch 28, batch 1250, loss[loss=0.1919, simple_loss=0.2924, pruned_loss=0.04569, over 7223.00 frames.], tot_loss[loss=0.165, simple_loss=0.2641, pruned_loss=0.03293, over 1416769.96 frames.], batch size: 22, lr: 2.70e-04
+2022-04-30 07:02:52,972 INFO [train.py:763] (6/8) Epoch 28, batch 1300, loss[loss=0.1754, simple_loss=0.2752, pruned_loss=0.0378, over 7141.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2643, pruned_loss=0.03302, over 1419580.91 frames.], batch size: 20, lr: 2.69e-04
+2022-04-30 07:03:58,475 INFO [train.py:763] (6/8) Epoch 28, batch 1350, loss[loss=0.1581, simple_loss=0.2636, pruned_loss=0.02628, over 7102.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2635, pruned_loss=0.03209, over 1425335.97 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:05:04,527 INFO [train.py:763] (6/8) Epoch 28, batch 1400, loss[loss=0.1505, simple_loss=0.2389, pruned_loss=0.03106, over 7275.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2634, pruned_loss=0.03192, over 1426735.23 frames.], batch size: 17, lr: 2.69e-04
+2022-04-30 07:06:10,013 INFO [train.py:763] (6/8) Epoch 28, batch 1450, loss[loss=0.1746, simple_loss=0.2797, pruned_loss=0.03473, over 7290.00 frames.], tot_loss[loss=0.1633, simple_loss=0.263, pruned_loss=0.03184, over 1430643.53 frames.], batch size: 24, lr: 2.69e-04
+2022-04-30 07:07:16,030 INFO [train.py:763] (6/8) Epoch 28, batch 1500, loss[loss=0.1729, simple_loss=0.2742, pruned_loss=0.03586, over 7331.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2631, pruned_loss=0.03172, over 1428201.27 frames.], batch size: 20, lr: 2.69e-04
+2022-04-30 07:08:21,694 INFO [train.py:763] (6/8) Epoch 28, batch 1550, loss[loss=0.1651, simple_loss=0.2715, pruned_loss=0.02931, over 7231.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2633, pruned_loss=0.03172, over 1430651.64 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:09:26,977 INFO [train.py:763] (6/8) Epoch 28, batch 1600, loss[loss=0.1656, simple_loss=0.256, pruned_loss=0.03762, over 6811.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2634, pruned_loss=0.03189, over 1427386.96 frames.], batch size: 15, lr: 2.69e-04
+2022-04-30 07:10:32,954 INFO [train.py:763] (6/8) Epoch 28, batch 1650, loss[loss=0.1341, simple_loss=0.231, pruned_loss=0.01862, over 6784.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2625, pruned_loss=0.03164, over 1428457.10 frames.], batch size: 15, lr: 2.69e-04
+2022-04-30 07:11:39,867 INFO [train.py:763] (6/8) Epoch 28, batch 1700, loss[loss=0.1555, simple_loss=0.2528, pruned_loss=0.0291, over 7261.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2623, pruned_loss=0.03147, over 1431057.59 frames.], batch size: 19, lr: 2.69e-04
+2022-04-30 07:12:45,212 INFO [train.py:763] (6/8) Epoch 28, batch 1750, loss[loss=0.1634, simple_loss=0.2681, pruned_loss=0.02935, over 7123.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03127, over 1433035.34 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:13:50,838 INFO [train.py:763] (6/8) Epoch 28, batch 1800, loss[loss=0.1244, simple_loss=0.2163, pruned_loss=0.01626, over 7005.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2619, pruned_loss=0.0314, over 1423871.89 frames.], batch size: 16, lr: 2.69e-04
+2022-04-30 07:14:56,962 INFO [train.py:763] (6/8) Epoch 28, batch 1850, loss[loss=0.1544, simple_loss=0.2491, pruned_loss=0.0298, over 7406.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2632, pruned_loss=0.03184, over 1426407.11 frames.], batch size: 18, lr: 2.69e-04
+2022-04-30 07:16:03,029 INFO [train.py:763] (6/8) Epoch 28, batch 1900, loss[loss=0.174, simple_loss=0.2734, pruned_loss=0.03728, over 7114.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2632, pruned_loss=0.03179, over 1426647.92 frames.], batch size: 26, lr: 2.69e-04
+2022-04-30 07:17:09,679 INFO [train.py:763] (6/8) Epoch 28, batch 1950, loss[loss=0.1897, simple_loss=0.2931, pruned_loss=0.0431, over 7317.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2641, pruned_loss=0.03225, over 1428728.49 frames.], batch size: 25, lr: 2.69e-04
+2022-04-30 07:18:15,511 INFO [train.py:763] (6/8) Epoch 28, batch 2000, loss[loss=0.1872, simple_loss=0.2872, pruned_loss=0.04364, over 7198.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2637, pruned_loss=0.03232, over 1431535.86 frames.], batch size: 23, lr: 2.69e-04
+2022-04-30 07:19:21,143 INFO [train.py:763] (6/8) Epoch 28, batch 2050, loss[loss=0.1726, simple_loss=0.2733, pruned_loss=0.03591, over 7327.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2641, pruned_loss=0.03262, over 1424694.50 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:20:26,750 INFO [train.py:763] (6/8) Epoch 28, batch 2100, loss[loss=0.1587, simple_loss=0.2662, pruned_loss=0.02559, over 7316.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2626, pruned_loss=0.03181, over 1427471.24 frames.], batch size: 25, lr: 2.69e-04
+2022-04-30 07:21:33,843 INFO [train.py:763] (6/8) Epoch 28, batch 2150, loss[loss=0.1632, simple_loss=0.2578, pruned_loss=0.03425, over 7220.00 frames.], tot_loss[loss=0.1634, simple_loss=0.263, pruned_loss=0.03194, over 1428245.66 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:22:48,760 INFO [train.py:763] (6/8) Epoch 28, batch 2200, loss[loss=0.1663, simple_loss=0.2721, pruned_loss=0.03021, over 7285.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2629, pruned_loss=0.0318, over 1422673.44 frames.], batch size: 25, lr: 2.69e-04
+2022-04-30 07:23:56,120 INFO [train.py:763] (6/8) Epoch 28, batch 2250, loss[loss=0.1532, simple_loss=0.25, pruned_loss=0.02817, over 7113.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2632, pruned_loss=0.0318, over 1426445.84 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:25:01,835 INFO [train.py:763] (6/8) Epoch 28, batch 2300, loss[loss=0.1933, simple_loss=0.2911, pruned_loss=0.04777, over 7282.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2622, pruned_loss=0.03144, over 1427747.62 frames.], batch size: 24, lr: 2.68e-04
+2022-04-30 07:26:07,550 INFO [train.py:763] (6/8) Epoch 28, batch 2350, loss[loss=0.1561, simple_loss=0.2547, pruned_loss=0.02874, over 7073.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2621, pruned_loss=0.03138, over 1425081.87 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:27:14,957 INFO [train.py:763] (6/8) Epoch 28, batch 2400, loss[loss=0.1839, simple_loss=0.2817, pruned_loss=0.04305, over 7362.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2617, pruned_loss=0.03139, over 1426402.79 frames.], batch size: 19, lr: 2.68e-04
+2022-04-30 07:28:20,444 INFO [train.py:763] (6/8) Epoch 28, batch 2450, loss[loss=0.1583, simple_loss=0.2647, pruned_loss=0.02596, over 7104.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2627, pruned_loss=0.0318, over 1417222.57 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:29:26,096 INFO [train.py:763] (6/8) Epoch 28, batch 2500, loss[loss=0.146, simple_loss=0.2454, pruned_loss=0.02333, over 7410.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2617, pruned_loss=0.03109, over 1420141.81 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:30:32,280 INFO [train.py:763] (6/8) Epoch 28, batch 2550, loss[loss=0.1294, simple_loss=0.2286, pruned_loss=0.01504, over 7160.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2613, pruned_loss=0.03119, over 1416869.28 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:31:37,900 INFO [train.py:763] (6/8) Epoch 28, batch 2600, loss[loss=0.1589, simple_loss=0.2716, pruned_loss=0.02315, over 7218.00 frames.], tot_loss[loss=0.1624, simple_loss=0.262, pruned_loss=0.03142, over 1415441.47 frames.], batch size: 23, lr: 2.68e-04
+2022-04-30 07:32:43,456 INFO [train.py:763] (6/8) Epoch 28, batch 2650, loss[loss=0.1439, simple_loss=0.2306, pruned_loss=0.02859, over 7415.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2615, pruned_loss=0.03105, over 1418010.43 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:33:59,645 INFO [train.py:763] (6/8) Epoch 28, batch 2700, loss[loss=0.1895, simple_loss=0.2877, pruned_loss=0.04563, over 5405.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2603, pruned_loss=0.03077, over 1418472.16 frames.], batch size: 52, lr: 2.68e-04
+2022-04-30 07:35:13,949 INFO [train.py:763] (6/8) Epoch 28, batch 2750, loss[loss=0.2022, simple_loss=0.3024, pruned_loss=0.05106, over 7311.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2612, pruned_loss=0.03115, over 1414789.96 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:36:28,356 INFO [train.py:763] (6/8) Epoch 28, batch 2800, loss[loss=0.1791, simple_loss=0.2751, pruned_loss=0.04161, over 7334.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2615, pruned_loss=0.03101, over 1418607.09 frames.], batch size: 22, lr: 2.68e-04
+2022-04-30 07:37:44,243 INFO [train.py:763] (6/8) Epoch 28, batch 2850, loss[loss=0.1506, simple_loss=0.248, pruned_loss=0.02666, over 7255.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2612, pruned_loss=0.03125, over 1419645.18 frames.], batch size: 19, lr: 2.68e-04
+2022-04-30 07:38:58,499 INFO [train.py:763] (6/8) Epoch 28, batch 2900, loss[loss=0.1651, simple_loss=0.2487, pruned_loss=0.04078, over 7260.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2618, pruned_loss=0.03139, over 1418759.64 frames.], batch size: 17, lr: 2.68e-04
+2022-04-30 07:40:13,608 INFO [train.py:763] (6/8) Epoch 28, batch 2950, loss[loss=0.1598, simple_loss=0.2577, pruned_loss=0.03096, over 7138.00 frames.], tot_loss[loss=0.1616, simple_loss=0.261, pruned_loss=0.03109, over 1418602.55 frames.], batch size: 17, lr: 2.68e-04
+2022-04-30 07:41:27,529 INFO [train.py:763] (6/8) Epoch 28, batch 3000, loss[loss=0.159, simple_loss=0.2569, pruned_loss=0.0305, over 7223.00 frames.], tot_loss[loss=0.162, simple_loss=0.2615, pruned_loss=0.03126, over 1418730.21 frames.], batch size: 20, lr: 2.68e-04
+2022-04-30 07:41:27,530 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 07:41:44,121 INFO [train.py:792] (6/8) Epoch 28, validation: loss=0.1685, simple_loss=0.2656, pruned_loss=0.03573, over 698248.00 frames.
+2022-04-30 07:42:49,824 INFO [train.py:763] (6/8) Epoch 28, batch 3050, loss[loss=0.1398, simple_loss=0.232, pruned_loss=0.02376, over 7155.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2614, pruned_loss=0.03149, over 1421268.26 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:43:55,528 INFO [train.py:763] (6/8) Epoch 28, batch 3100, loss[loss=0.1434, simple_loss=0.2468, pruned_loss=0.02, over 7285.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2606, pruned_loss=0.03085, over 1417827.69 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:45:01,628 INFO [train.py:763] (6/8) Epoch 28, batch 3150, loss[loss=0.184, simple_loss=0.2933, pruned_loss=0.03735, over 7207.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2616, pruned_loss=0.03084, over 1421358.61 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:46:07,725 INFO [train.py:763] (6/8) Epoch 28, batch 3200, loss[loss=0.1774, simple_loss=0.2857, pruned_loss=0.03459, over 7125.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2629, pruned_loss=0.03078, over 1421650.70 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:47:14,413 INFO [train.py:763] (6/8) Epoch 28, batch 3250, loss[loss=0.1501, simple_loss=0.2391, pruned_loss=0.03052, over 7253.00 frames.], tot_loss[loss=0.162, simple_loss=0.2622, pruned_loss=0.0309, over 1421534.94 frames.], batch size: 16, lr: 2.67e-04
+2022-04-30 07:48:20,829 INFO [train.py:763] (6/8) Epoch 28, batch 3300, loss[loss=0.1682, simple_loss=0.2723, pruned_loss=0.03201, over 7212.00 frames.], tot_loss[loss=0.1634, simple_loss=0.264, pruned_loss=0.03145, over 1420914.85 frames.], batch size: 21, lr: 2.67e-04
+2022-04-30 07:49:26,936 INFO [train.py:763] (6/8) Epoch 28, batch 3350, loss[loss=0.1605, simple_loss=0.2623, pruned_loss=0.0294, over 7021.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2633, pruned_loss=0.03111, over 1418188.57 frames.], batch size: 28, lr: 2.67e-04
+2022-04-30 07:50:33,794 INFO [train.py:763] (6/8) Epoch 28, batch 3400, loss[loss=0.1537, simple_loss=0.2572, pruned_loss=0.02509, over 7060.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2646, pruned_loss=0.03215, over 1417339.21 frames.], batch size: 18, lr: 2.67e-04
+2022-04-30 07:51:39,846 INFO [train.py:763] (6/8) Epoch 28, batch 3450, loss[loss=0.1449, simple_loss=0.2299, pruned_loss=0.02995, over 7286.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2634, pruned_loss=0.03192, over 1419689.41 frames.], batch size: 17, lr: 2.67e-04
+2022-04-30 07:52:45,407 INFO [train.py:763] (6/8) Epoch 28, batch 3500, loss[loss=0.161, simple_loss=0.2654, pruned_loss=0.02832, over 6932.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2631, pruned_loss=0.0317, over 1419473.91 frames.], batch size: 32, lr: 2.67e-04
+2022-04-30 07:53:50,886 INFO [train.py:763] (6/8) Epoch 28, batch 3550, loss[loss=0.1455, simple_loss=0.2377, pruned_loss=0.02671, over 7288.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2613, pruned_loss=0.03096, over 1422401.78 frames.], batch size: 18, lr: 2.67e-04
+2022-04-30 07:54:56,702 INFO [train.py:763] (6/8) Epoch 28, batch 3600, loss[loss=0.1326, simple_loss=0.2276, pruned_loss=0.01877, over 7227.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2625, pruned_loss=0.03201, over 1422930.75 frames.], batch size: 16, lr: 2.67e-04
+2022-04-30 07:56:02,360 INFO [train.py:763] (6/8) Epoch 28, batch 3650, loss[loss=0.1485, simple_loss=0.2504, pruned_loss=0.02329, over 7337.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2617, pruned_loss=0.0314, over 1425973.14 frames.], batch size: 22, lr: 2.67e-04
+2022-04-30 07:57:08,118 INFO [train.py:763] (6/8) Epoch 28, batch 3700, loss[loss=0.1917, simple_loss=0.2864, pruned_loss=0.0485, over 7231.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2608, pruned_loss=0.03129, over 1425224.70 frames.], batch size: 23, lr: 2.67e-04
+2022-04-30 07:58:13,561 INFO [train.py:763] (6/8) Epoch 28, batch 3750, loss[loss=0.2308, simple_loss=0.3187, pruned_loss=0.07144, over 4995.00 frames.], tot_loss[loss=0.163, simple_loss=0.2622, pruned_loss=0.03192, over 1425600.18 frames.], batch size: 53, lr: 2.67e-04
+2022-04-30 07:59:19,063 INFO [train.py:763] (6/8) Epoch 28, batch 3800, loss[loss=0.1645, simple_loss=0.2632, pruned_loss=0.03291, over 7427.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2633, pruned_loss=0.03216, over 1426031.52 frames.], batch size: 20, lr: 2.67e-04
+2022-04-30 08:00:24,610 INFO [train.py:763] (6/8) Epoch 28, batch 3850, loss[loss=0.1737, simple_loss=0.2592, pruned_loss=0.0441, over 7358.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2626, pruned_loss=0.03208, over 1426511.23 frames.], batch size: 23, lr: 2.67e-04
+2022-04-30 08:01:31,083 INFO [train.py:763] (6/8) Epoch 28, batch 3900, loss[loss=0.1857, simple_loss=0.2843, pruned_loss=0.0436, over 7303.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2623, pruned_loss=0.03191, over 1429099.41 frames.], batch size: 24, lr: 2.67e-04
+2022-04-30 08:02:37,687 INFO [train.py:763] (6/8) Epoch 28, batch 3950, loss[loss=0.138, simple_loss=0.2342, pruned_loss=0.02084, over 7423.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2634, pruned_loss=0.03198, over 1430065.75 frames.], batch size: 18, lr: 2.67e-04
+2022-04-30 08:03:44,064 INFO [train.py:763] (6/8) Epoch 28, batch 4000, loss[loss=0.1762, simple_loss=0.2847, pruned_loss=0.03383, over 7336.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2643, pruned_loss=0.03255, over 1430164.40 frames.], batch size: 22, lr: 2.67e-04
+2022-04-30 08:04:50,784 INFO [train.py:763] (6/8) Epoch 28, batch 4050, loss[loss=0.1337, simple_loss=0.2271, pruned_loss=0.02017, over 7282.00 frames.], tot_loss[loss=0.165, simple_loss=0.2644, pruned_loss=0.03275, over 1429044.10 frames.], batch size: 17, lr: 2.67e-04
+2022-04-30 08:05:55,980 INFO [train.py:763] (6/8) Epoch 28, batch 4100, loss[loss=0.1794, simple_loss=0.2853, pruned_loss=0.0367, over 7340.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2642, pruned_loss=0.03239, over 1429713.70 frames.], batch size: 22, lr: 2.67e-04
+2022-04-30 08:07:02,672 INFO [train.py:763] (6/8) Epoch 28, batch 4150, loss[loss=0.1435, simple_loss=0.2486, pruned_loss=0.01922, over 7335.00 frames.], tot_loss[loss=0.1643, simple_loss=0.264, pruned_loss=0.03231, over 1423779.38 frames.], batch size: 21, lr: 2.67e-04
+2022-04-30 08:08:09,181 INFO [train.py:763] (6/8) Epoch 28, batch 4200, loss[loss=0.1562, simple_loss=0.2479, pruned_loss=0.03219, over 7262.00 frames.], tot_loss[loss=0.165, simple_loss=0.2649, pruned_loss=0.03258, over 1421063.17 frames.], batch size: 19, lr: 2.66e-04
+2022-04-30 08:09:14,667 INFO [train.py:763] (6/8) Epoch 28, batch 4250, loss[loss=0.177, simple_loss=0.27, pruned_loss=0.04199, over 6706.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2645, pruned_loss=0.0324, over 1421326.77 frames.], batch size: 31, lr: 2.66e-04
+2022-04-30 08:10:19,666 INFO [train.py:763] (6/8) Epoch 28, batch 4300, loss[loss=0.1514, simple_loss=0.2431, pruned_loss=0.0298, over 7169.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2643, pruned_loss=0.03165, over 1417451.88 frames.], batch size: 18, lr: 2.66e-04
+2022-04-30 08:11:24,967 INFO [train.py:763] (6/8) Epoch 28, batch 4350, loss[loss=0.1595, simple_loss=0.2549, pruned_loss=0.03211, over 7316.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2629, pruned_loss=0.03168, over 1419097.81 frames.], batch size: 21, lr: 2.66e-04
+2022-04-30 08:12:30,144 INFO [train.py:763] (6/8) Epoch 28, batch 4400, loss[loss=0.1776, simple_loss=0.2752, pruned_loss=0.04004, over 7273.00 frames.], tot_loss[loss=0.1638, simple_loss=0.263, pruned_loss=0.03231, over 1409555.77 frames.], batch size: 24, lr: 2.66e-04
+2022-04-30 08:13:35,273 INFO [train.py:763] (6/8) Epoch 28, batch 4450, loss[loss=0.1582, simple_loss=0.255, pruned_loss=0.03065, over 6328.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2636, pruned_loss=0.03286, over 1400673.93 frames.], batch size: 37, lr: 2.66e-04
+2022-04-30 08:14:40,130 INFO [train.py:763] (6/8) Epoch 28, batch 4500, loss[loss=0.1918, simple_loss=0.2845, pruned_loss=0.0495, over 7207.00 frames.], tot_loss[loss=0.166, simple_loss=0.2647, pruned_loss=0.03367, over 1378228.90 frames.], batch size: 22, lr: 2.66e-04
+2022-04-30 08:15:45,362 INFO [train.py:763] (6/8) Epoch 28, batch 4550, loss[loss=0.2092, simple_loss=0.3072, pruned_loss=0.05566, over 5108.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2664, pruned_loss=0.03413, over 1359954.95 frames.], batch size: 52, lr: 2.66e-04
+2022-04-30 08:17:05,897 INFO [train.py:763] (6/8) Epoch 29, batch 0, loss[loss=0.1651, simple_loss=0.2716, pruned_loss=0.02927, over 7313.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2716, pruned_loss=0.02927, over 7313.00 frames.], batch size: 20, lr: 2.62e-04
+2022-04-30 08:18:11,696 INFO [train.py:763] (6/8) Epoch 29, batch 50, loss[loss=0.1455, simple_loss=0.2454, pruned_loss=0.02285, over 7283.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2632, pruned_loss=0.03216, over 323739.92 frames.], batch size: 18, lr: 2.62e-04
+2022-04-30 08:19:17,260 INFO [train.py:763] (6/8) Epoch 29, batch 100, loss[loss=0.1448, simple_loss=0.2292, pruned_loss=0.03015, over 7266.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2604, pruned_loss=0.03205, over 571804.44 frames.], batch size: 17, lr: 2.62e-04
+2022-04-30 08:20:22,571 INFO [train.py:763] (6/8) Epoch 29, batch 150, loss[loss=0.1821, simple_loss=0.2877, pruned_loss=0.03828, over 7321.00 frames.], tot_loss[loss=0.163, simple_loss=0.2619, pruned_loss=0.03201, over 748449.44 frames.], batch size: 24, lr: 2.62e-04
+2022-04-30 08:21:28,004 INFO [train.py:763] (6/8) Epoch 29, batch 200, loss[loss=0.1304, simple_loss=0.2283, pruned_loss=0.01626, over 7356.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2618, pruned_loss=0.03255, over 898600.51 frames.], batch size: 19, lr: 2.61e-04
+2022-04-30 08:22:33,080 INFO [train.py:763] (6/8) Epoch 29, batch 250, loss[loss=0.1298, simple_loss=0.2275, pruned_loss=0.01603, over 7260.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2627, pruned_loss=0.03243, over 1015075.77 frames.], batch size: 16, lr: 2.61e-04
+2022-04-30 08:23:39,498 INFO [train.py:763] (6/8) Epoch 29, batch 300, loss[loss=0.1605, simple_loss=0.2522, pruned_loss=0.03435, over 7268.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2638, pruned_loss=0.03283, over 1107819.75 frames.], batch size: 18, lr: 2.61e-04
+2022-04-30 08:24:46,640 INFO [train.py:763] (6/8) Epoch 29, batch 350, loss[loss=0.1725, simple_loss=0.2713, pruned_loss=0.0368, over 7330.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2627, pruned_loss=0.03208, over 1181061.21 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:25:52,372 INFO [train.py:763] (6/8) Epoch 29, batch 400, loss[loss=0.173, simple_loss=0.2821, pruned_loss=0.03193, over 7293.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2625, pruned_loss=0.03144, over 1237296.34 frames.], batch size: 24, lr: 2.61e-04
+2022-04-30 08:26:57,830 INFO [train.py:763] (6/8) Epoch 29, batch 450, loss[loss=0.1798, simple_loss=0.2737, pruned_loss=0.04293, over 7413.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2624, pruned_loss=0.03149, over 1279527.77 frames.], batch size: 21, lr: 2.61e-04
+2022-04-30 08:28:03,214 INFO [train.py:763] (6/8) Epoch 29, batch 500, loss[loss=0.1642, simple_loss=0.2625, pruned_loss=0.03294, over 7330.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2629, pruned_loss=0.03193, over 1308781.72 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:29:08,673 INFO [train.py:763] (6/8) Epoch 29, batch 550, loss[loss=0.1572, simple_loss=0.2708, pruned_loss=0.02176, over 7253.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.0319, over 1336640.11 frames.], batch size: 24, lr: 2.61e-04
+2022-04-30 08:30:14,688 INFO [train.py:763] (6/8) Epoch 29, batch 600, loss[loss=0.1567, simple_loss=0.2605, pruned_loss=0.02643, over 7207.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2639, pruned_loss=0.03232, over 1351870.32 frames.], batch size: 22, lr: 2.61e-04
+2022-04-30 08:31:20,878 INFO [train.py:763] (6/8) Epoch 29, batch 650, loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.03057, over 7062.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2637, pruned_loss=0.03198, over 1366497.39 frames.], batch size: 18, lr: 2.61e-04
+2022-04-30 08:32:27,045 INFO [train.py:763] (6/8) Epoch 29, batch 700, loss[loss=0.1565, simple_loss=0.2473, pruned_loss=0.0329, over 7333.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2638, pruned_loss=0.03202, over 1374707.72 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:33:32,283 INFO [train.py:763] (6/8) Epoch 29, batch 750, loss[loss=0.1423, simple_loss=0.2464, pruned_loss=0.01905, over 7229.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2632, pruned_loss=0.03185, over 1381913.12 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:34:37,540 INFO [train.py:763] (6/8) Epoch 29, batch 800, loss[loss=0.1659, simple_loss=0.2636, pruned_loss=0.03407, over 7325.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2621, pruned_loss=0.03149, over 1389056.11 frames.], batch size: 22, lr: 2.61e-04
+2022-04-30 08:35:43,022 INFO [train.py:763] (6/8) Epoch 29, batch 850, loss[loss=0.1522, simple_loss=0.2542, pruned_loss=0.0251, over 7061.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2614, pruned_loss=0.03149, over 1397863.25 frames.], batch size: 18, lr: 2.61e-04
+2022-04-30 08:36:48,529 INFO [train.py:763] (6/8) Epoch 29, batch 900, loss[loss=0.1811, simple_loss=0.2871, pruned_loss=0.03755, over 7228.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2616, pruned_loss=0.03168, over 1401924.25 frames.], batch size: 21, lr: 2.61e-04
+2022-04-30 08:37:53,910 INFO [train.py:763] (6/8) Epoch 29, batch 950, loss[loss=0.1626, simple_loss=0.2717, pruned_loss=0.02673, over 7117.00 frames.], tot_loss[loss=0.163, simple_loss=0.2625, pruned_loss=0.03179, over 1407566.02 frames.], batch size: 21, lr: 2.61e-04
+2022-04-30 08:38:59,975 INFO [train.py:763] (6/8) Epoch 29, batch 1000, loss[loss=0.1646, simple_loss=0.2768, pruned_loss=0.02621, over 7143.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2636, pruned_loss=0.03201, over 1411032.59 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:40:06,270 INFO [train.py:763] (6/8) Epoch 29, batch 1050, loss[loss=0.1335, simple_loss=0.228, pruned_loss=0.01947, over 7269.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2639, pruned_loss=0.03217, over 1407679.89 frames.], batch size: 18, lr: 2.61e-04
+2022-04-30 08:41:11,506 INFO [train.py:763] (6/8) Epoch 29, batch 1100, loss[loss=0.1739, simple_loss=0.2817, pruned_loss=0.03299, over 7318.00 frames.], tot_loss[loss=0.1648, simple_loss=0.265, pruned_loss=0.03228, over 1417101.52 frames.], batch size: 21, lr: 2.61e-04
+2022-04-30 08:42:16,628 INFO [train.py:763] (6/8) Epoch 29, batch 1150, loss[loss=0.1417, simple_loss=0.2407, pruned_loss=0.02128, over 7020.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2648, pruned_loss=0.03215, over 1417672.87 frames.], batch size: 16, lr: 2.61e-04
+2022-04-30 08:43:21,915 INFO [train.py:763] (6/8) Epoch 29, batch 1200, loss[loss=0.149, simple_loss=0.2436, pruned_loss=0.02719, over 7156.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2639, pruned_loss=0.03145, over 1421713.04 frames.], batch size: 19, lr: 2.61e-04
+2022-04-30 08:44:27,478 INFO [train.py:763] (6/8) Epoch 29, batch 1250, loss[loss=0.1878, simple_loss=0.2805, pruned_loss=0.0475, over 4949.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2628, pruned_loss=0.03139, over 1416684.68 frames.], batch size: 53, lr: 2.60e-04
+2022-04-30 08:45:34,625 INFO [train.py:763] (6/8) Epoch 29, batch 1300, loss[loss=0.162, simple_loss=0.2717, pruned_loss=0.02611, over 7332.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2624, pruned_loss=0.03117, over 1418613.64 frames.], batch size: 22, lr: 2.60e-04
+2022-04-30 08:46:42,214 INFO [train.py:763] (6/8) Epoch 29, batch 1350, loss[loss=0.1667, simple_loss=0.2709, pruned_loss=0.03124, over 6202.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2626, pruned_loss=0.03127, over 1419304.90 frames.], batch size: 37, lr: 2.60e-04
+2022-04-30 08:47:48,988 INFO [train.py:763] (6/8) Epoch 29, batch 1400, loss[loss=0.1791, simple_loss=0.2651, pruned_loss=0.04661, over 6839.00 frames.], tot_loss[loss=0.1623, simple_loss=0.262, pruned_loss=0.03128, over 1419220.42 frames.], batch size: 15, lr: 2.60e-04
+2022-04-30 08:48:56,275 INFO [train.py:763] (6/8) Epoch 29, batch 1450, loss[loss=0.1802, simple_loss=0.2791, pruned_loss=0.04069, over 7121.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2625, pruned_loss=0.03153, over 1418427.06 frames.], batch size: 21, lr: 2.60e-04
+2022-04-30 08:50:03,377 INFO [train.py:763] (6/8) Epoch 29, batch 1500, loss[loss=0.1658, simple_loss=0.2599, pruned_loss=0.03581, over 7262.00 frames.], tot_loss[loss=0.163, simple_loss=0.2628, pruned_loss=0.03162, over 1417606.41 frames.], batch size: 19, lr: 2.60e-04
+2022-04-30 08:51:09,978 INFO [train.py:763] (6/8) Epoch 29, batch 1550, loss[loss=0.1869, simple_loss=0.2866, pruned_loss=0.04358, over 7225.00 frames.], tot_loss[loss=0.163, simple_loss=0.2629, pruned_loss=0.03153, over 1418407.16 frames.], batch size: 23, lr: 2.60e-04
+2022-04-30 08:52:16,971 INFO [train.py:763] (6/8) Epoch 29, batch 1600, loss[loss=0.1637, simple_loss=0.2716, pruned_loss=0.02788, over 7319.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2633, pruned_loss=0.03183, over 1419571.08 frames.], batch size: 21, lr: 2.60e-04
+2022-04-30 08:53:22,974 INFO [train.py:763] (6/8) Epoch 29, batch 1650, loss[loss=0.1701, simple_loss=0.2782, pruned_loss=0.03098, over 7158.00 frames.], tot_loss[loss=0.1633, simple_loss=0.263, pruned_loss=0.03177, over 1423519.25 frames.], batch size: 26, lr: 2.60e-04
+2022-04-30 08:54:28,292 INFO [train.py:763] (6/8) Epoch 29, batch 1700, loss[loss=0.1667, simple_loss=0.2568, pruned_loss=0.0383, over 7124.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2639, pruned_loss=0.03234, over 1426671.46 frames.], batch size: 17, lr: 2.60e-04
+2022-04-30 08:55:35,257 INFO [train.py:763] (6/8) Epoch 29, batch 1750, loss[loss=0.1806, simple_loss=0.279, pruned_loss=0.04113, over 7148.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2636, pruned_loss=0.03242, over 1422833.31 frames.], batch size: 20, lr: 2.60e-04
+2022-04-30 08:56:42,197 INFO [train.py:763] (6/8) Epoch 29, batch 1800, loss[loss=0.185, simple_loss=0.2786, pruned_loss=0.04573, over 5193.00 frames.], tot_loss[loss=0.164, simple_loss=0.2633, pruned_loss=0.03235, over 1420293.70 frames.], batch size: 53, lr: 2.60e-04
+2022-04-30 08:57:49,264 INFO [train.py:763] (6/8) Epoch 29, batch 1850, loss[loss=0.1849, simple_loss=0.2847, pruned_loss=0.04255, over 7116.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2619, pruned_loss=0.03182, over 1424557.85 frames.], batch size: 21, lr: 2.60e-04
+2022-04-30 08:58:55,867 INFO [train.py:763] (6/8) Epoch 29, batch 1900, loss[loss=0.1328, simple_loss=0.2172, pruned_loss=0.02419, over 7193.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2617, pruned_loss=0.03179, over 1427253.48 frames.], batch size: 16, lr: 2.60e-04
+2022-04-30 09:00:01,477 INFO [train.py:763] (6/8) Epoch 29, batch 1950, loss[loss=0.1526, simple_loss=0.2431, pruned_loss=0.03106, over 7266.00 frames.], tot_loss[loss=0.1626, simple_loss=0.262, pruned_loss=0.03163, over 1428552.61 frames.], batch size: 17, lr: 2.60e-04
+2022-04-30 09:01:06,700 INFO [train.py:763] (6/8) Epoch 29, batch 2000, loss[loss=0.1731, simple_loss=0.2782, pruned_loss=0.03396, over 7327.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2621, pruned_loss=0.03151, over 1430612.86 frames.], batch size: 22, lr: 2.60e-04
+2022-04-30 09:02:12,107 INFO [train.py:763] (6/8) Epoch 29, batch 2050, loss[loss=0.1925, simple_loss=0.2941, pruned_loss=0.04546, over 7213.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2622, pruned_loss=0.03153, over 1430929.33 frames.], batch size: 23, lr: 2.60e-04
+2022-04-30 09:03:17,247 INFO [train.py:763] (6/8) Epoch 29, batch 2100, loss[loss=0.1486, simple_loss=0.2577, pruned_loss=0.01979, over 7144.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2619, pruned_loss=0.03146, over 1429789.77 frames.], batch size: 20, lr: 2.60e-04
+2022-04-30 09:04:22,317 INFO [train.py:763] (6/8) Epoch 29, batch 2150, loss[loss=0.1422, simple_loss=0.2412, pruned_loss=0.0216, over 7135.00 frames.], tot_loss[loss=0.1626, simple_loss=0.262, pruned_loss=0.03158, over 1428411.16 frames.], batch size: 17, lr: 2.60e-04
+2022-04-30 09:05:27,761 INFO [train.py:763] (6/8) Epoch 29, batch 2200, loss[loss=0.1744, simple_loss=0.2697, pruned_loss=0.03953, over 7282.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2616, pruned_loss=0.03161, over 1423175.68 frames.], batch size: 24, lr: 2.60e-04
+2022-04-30 09:06:32,910 INFO [train.py:763] (6/8) Epoch 29, batch 2250, loss[loss=0.172, simple_loss=0.2767, pruned_loss=0.03365, over 7149.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2624, pruned_loss=0.03198, over 1421491.21 frames.], batch size: 26, lr: 2.59e-04
+2022-04-30 09:07:38,519 INFO [train.py:763] (6/8) Epoch 29, batch 2300, loss[loss=0.1353, simple_loss=0.2365, pruned_loss=0.01702, over 7327.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2628, pruned_loss=0.03173, over 1417795.86 frames.], batch size: 20, lr: 2.59e-04
+2022-04-30 09:08:43,788 INFO [train.py:763] (6/8) Epoch 29, batch 2350, loss[loss=0.1653, simple_loss=0.2618, pruned_loss=0.03438, over 7339.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2626, pruned_loss=0.03182, over 1420231.89 frames.], batch size: 22, lr: 2.59e-04
+2022-04-30 09:09:49,528 INFO [train.py:763] (6/8) Epoch 29, batch 2400, loss[loss=0.1813, simple_loss=0.2885, pruned_loss=0.03703, over 7289.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2629, pruned_loss=0.03174, over 1421651.40 frames.], batch size: 25, lr: 2.59e-04
+2022-04-30 09:10:55,176 INFO [train.py:763] (6/8) Epoch 29, batch 2450, loss[loss=0.177, simple_loss=0.2775, pruned_loss=0.03823, over 7147.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2621, pruned_loss=0.03162, over 1426013.99 frames.], batch size: 20, lr: 2.59e-04
+2022-04-30 09:12:00,712 INFO [train.py:763] (6/8) Epoch 29, batch 2500, loss[loss=0.1431, simple_loss=0.2337, pruned_loss=0.02622, over 6815.00 frames.], tot_loss[loss=0.163, simple_loss=0.2626, pruned_loss=0.03171, over 1430540.14 frames.], batch size: 15, lr: 2.59e-04
+2022-04-30 09:13:06,081 INFO [train.py:763] (6/8) Epoch 29, batch 2550, loss[loss=0.1632, simple_loss=0.2511, pruned_loss=0.03764, over 7401.00 frames.], tot_loss[loss=0.1627, simple_loss=0.262, pruned_loss=0.0317, over 1427541.76 frames.], batch size: 18, lr: 2.59e-04
+2022-04-30 09:14:11,174 INFO [train.py:763] (6/8) Epoch 29, batch 2600, loss[loss=0.1544, simple_loss=0.2621, pruned_loss=0.02336, over 7118.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2618, pruned_loss=0.03177, over 1426837.97 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:15:16,454 INFO [train.py:763] (6/8) Epoch 29, batch 2650, loss[loss=0.1474, simple_loss=0.2345, pruned_loss=0.03015, over 7126.00 frames.], tot_loss[loss=0.162, simple_loss=0.2611, pruned_loss=0.03145, over 1428758.83 frames.], batch size: 17, lr: 2.59e-04
+2022-04-30 09:16:21,501 INFO [train.py:763] (6/8) Epoch 29, batch 2700, loss[loss=0.1564, simple_loss=0.2612, pruned_loss=0.02577, over 7119.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2619, pruned_loss=0.0315, over 1429407.17 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:17:27,766 INFO [train.py:763] (6/8) Epoch 29, batch 2750, loss[loss=0.16, simple_loss=0.2668, pruned_loss=0.02663, over 7236.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2624, pruned_loss=0.03131, over 1425573.16 frames.], batch size: 20, lr: 2.59e-04
+2022-04-30 09:18:33,544 INFO [train.py:763] (6/8) Epoch 29, batch 2800, loss[loss=0.1501, simple_loss=0.2494, pruned_loss=0.02541, over 7327.00 frames.], tot_loss[loss=0.163, simple_loss=0.263, pruned_loss=0.03155, over 1424493.34 frames.], batch size: 22, lr: 2.59e-04
+2022-04-30 09:19:39,945 INFO [train.py:763] (6/8) Epoch 29, batch 2850, loss[loss=0.163, simple_loss=0.2599, pruned_loss=0.03308, over 7240.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2625, pruned_loss=0.03151, over 1418743.71 frames.], batch size: 20, lr: 2.59e-04
+2022-04-30 09:20:45,381 INFO [train.py:763] (6/8) Epoch 29, batch 2900, loss[loss=0.1428, simple_loss=0.2351, pruned_loss=0.02528, over 6990.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2614, pruned_loss=0.03088, over 1421576.29 frames.], batch size: 16, lr: 2.59e-04
+2022-04-30 09:22:01,684 INFO [train.py:763] (6/8) Epoch 29, batch 2950, loss[loss=0.1753, simple_loss=0.2822, pruned_loss=0.03421, over 6527.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03115, over 1422281.52 frames.], batch size: 38, lr: 2.59e-04
+2022-04-30 09:23:07,151 INFO [train.py:763] (6/8) Epoch 29, batch 3000, loss[loss=0.167, simple_loss=0.2646, pruned_loss=0.0347, over 7119.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2618, pruned_loss=0.03162, over 1425382.42 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:23:07,152 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 09:23:22,371 INFO [train.py:792] (6/8) Epoch 29, validation: loss=0.1693, simple_loss=0.2664, pruned_loss=0.03606, over 698248.00 frames.
+2022-04-30 09:24:27,450 INFO [train.py:763] (6/8) Epoch 29, batch 3050, loss[loss=0.1504, simple_loss=0.2448, pruned_loss=0.02804, over 7116.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2621, pruned_loss=0.03134, over 1426779.85 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:25:32,595 INFO [train.py:763] (6/8) Epoch 29, batch 3100, loss[loss=0.1642, simple_loss=0.2632, pruned_loss=0.03259, over 7418.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03128, over 1426885.99 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:26:38,422 INFO [train.py:763] (6/8) Epoch 29, batch 3150, loss[loss=0.146, simple_loss=0.2399, pruned_loss=0.02608, over 7158.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2613, pruned_loss=0.03105, over 1422441.26 frames.], batch size: 18, lr: 2.59e-04
+2022-04-30 09:27:44,834 INFO [train.py:763] (6/8) Epoch 29, batch 3200, loss[loss=0.1415, simple_loss=0.2425, pruned_loss=0.02028, over 7262.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2605, pruned_loss=0.03111, over 1425763.96 frames.], batch size: 19, lr: 2.59e-04
+2022-04-30 09:28:51,942 INFO [train.py:763] (6/8) Epoch 29, batch 3250, loss[loss=0.1783, simple_loss=0.2738, pruned_loss=0.04146, over 7092.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2613, pruned_loss=0.03152, over 1421427.99 frames.], batch size: 28, lr: 2.59e-04
+2022-04-30 09:29:57,732 INFO [train.py:763] (6/8) Epoch 29, batch 3300, loss[loss=0.146, simple_loss=0.2417, pruned_loss=0.02515, over 7334.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2618, pruned_loss=0.03138, over 1423904.20 frames.], batch size: 20, lr: 2.58e-04
+2022-04-30 09:31:03,712 INFO [train.py:763] (6/8) Epoch 29, batch 3350, loss[loss=0.1451, simple_loss=0.2424, pruned_loss=0.02392, over 7283.00 frames.], tot_loss[loss=0.162, simple_loss=0.2614, pruned_loss=0.03127, over 1427937.62 frames.], batch size: 17, lr: 2.58e-04
+2022-04-30 09:32:09,340 INFO [train.py:763] (6/8) Epoch 29, batch 3400, loss[loss=0.1797, simple_loss=0.2805, pruned_loss=0.03943, over 5169.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2613, pruned_loss=0.03116, over 1424552.20 frames.], batch size: 52, lr: 2.58e-04
+2022-04-30 09:33:15,080 INFO [train.py:763] (6/8) Epoch 29, batch 3450, loss[loss=0.1525, simple_loss=0.261, pruned_loss=0.02201, over 7287.00 frames.], tot_loss[loss=0.1613, simple_loss=0.261, pruned_loss=0.03081, over 1421337.07 frames.], batch size: 24, lr: 2.58e-04
+2022-04-30 09:34:21,150 INFO [train.py:763] (6/8) Epoch 29, batch 3500, loss[loss=0.1911, simple_loss=0.2913, pruned_loss=0.04551, over 7138.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.0308, over 1422900.06 frames.], batch size: 26, lr: 2.58e-04
+2022-04-30 09:35:26,536 INFO [train.py:763] (6/8) Epoch 29, batch 3550, loss[loss=0.1288, simple_loss=0.2231, pruned_loss=0.01725, over 7178.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03072, over 1422319.19 frames.], batch size: 18, lr: 2.58e-04
+2022-04-30 09:36:32,239 INFO [train.py:763] (6/8) Epoch 29, batch 3600, loss[loss=0.1768, simple_loss=0.2749, pruned_loss=0.03931, over 7265.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.0307, over 1427101.09 frames.], batch size: 19, lr: 2.58e-04
+2022-04-30 09:37:46,878 INFO [train.py:763] (6/8) Epoch 29, batch 3650, loss[loss=0.1734, simple_loss=0.2743, pruned_loss=0.03624, over 6822.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2623, pruned_loss=0.03156, over 1428834.53 frames.], batch size: 31, lr: 2.58e-04
+2022-04-30 09:38:52,212 INFO [train.py:763] (6/8) Epoch 29, batch 3700, loss[loss=0.157, simple_loss=0.2394, pruned_loss=0.03732, over 7282.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2616, pruned_loss=0.03151, over 1429788.94 frames.], batch size: 17, lr: 2.58e-04
+2022-04-30 09:39:59,120 INFO [train.py:763] (6/8) Epoch 29, batch 3750, loss[loss=0.1605, simple_loss=0.2577, pruned_loss=0.03168, over 6940.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2613, pruned_loss=0.03128, over 1432629.57 frames.], batch size: 28, lr: 2.58e-04
+2022-04-30 09:41:05,834 INFO [train.py:763] (6/8) Epoch 29, batch 3800, loss[loss=0.1845, simple_loss=0.2864, pruned_loss=0.04129, over 7204.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03127, over 1425285.65 frames.], batch size: 22, lr: 2.58e-04
+2022-04-30 09:42:11,178 INFO [train.py:763] (6/8) Epoch 29, batch 3850, loss[loss=0.1472, simple_loss=0.2379, pruned_loss=0.02826, over 7210.00 frames.], tot_loss[loss=0.1621, simple_loss=0.262, pruned_loss=0.03107, over 1425997.28 frames.], batch size: 16, lr: 2.58e-04
+2022-04-30 09:43:16,819 INFO [train.py:763] (6/8) Epoch 29, batch 3900, loss[loss=0.1486, simple_loss=0.2411, pruned_loss=0.02806, over 7149.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03114, over 1426589.15 frames.], batch size: 17, lr: 2.58e-04
+2022-04-30 09:44:22,549 INFO [train.py:763] (6/8) Epoch 29, batch 3950, loss[loss=0.2026, simple_loss=0.3051, pruned_loss=0.05007, over 7366.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2635, pruned_loss=0.03154, over 1420911.45 frames.], batch size: 23, lr: 2.58e-04
+2022-04-30 09:45:27,973 INFO [train.py:763] (6/8) Epoch 29, batch 4000, loss[loss=0.1783, simple_loss=0.2799, pruned_loss=0.03835, over 7296.00 frames.], tot_loss[loss=0.1637, simple_loss=0.264, pruned_loss=0.03171, over 1418637.88 frames.], batch size: 25, lr: 2.58e-04
+2022-04-30 09:46:33,250 INFO [train.py:763] (6/8) Epoch 29, batch 4050, loss[loss=0.1871, simple_loss=0.2824, pruned_loss=0.04593, over 7090.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2629, pruned_loss=0.0317, over 1418293.73 frames.], batch size: 28, lr: 2.58e-04
+2022-04-30 09:47:39,265 INFO [train.py:763] (6/8) Epoch 29, batch 4100, loss[loss=0.1619, simple_loss=0.2644, pruned_loss=0.02971, over 7325.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2617, pruned_loss=0.0313, over 1420290.44 frames.], batch size: 21, lr: 2.58e-04
+2022-04-30 09:48:45,603 INFO [train.py:763] (6/8) Epoch 29, batch 4150, loss[loss=0.1592, simple_loss=0.2675, pruned_loss=0.02541, over 7212.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2611, pruned_loss=0.03128, over 1420699.35 frames.], batch size: 21, lr: 2.58e-04
+2022-04-30 09:50:00,124 INFO [train.py:763] (6/8) Epoch 29, batch 4200, loss[loss=0.1691, simple_loss=0.2651, pruned_loss=0.03658, over 7422.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2612, pruned_loss=0.03111, over 1421778.18 frames.], batch size: 20, lr: 2.58e-04
+2022-04-30 09:51:13,969 INFO [train.py:763] (6/8) Epoch 29, batch 4250, loss[loss=0.1775, simple_loss=0.2841, pruned_loss=0.03543, over 7381.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2631, pruned_loss=0.03158, over 1416797.38 frames.], batch size: 23, lr: 2.58e-04
+2022-04-30 09:52:28,883 INFO [train.py:763] (6/8) Epoch 29, batch 4300, loss[loss=0.1357, simple_loss=0.2285, pruned_loss=0.02141, over 7288.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2626, pruned_loss=0.03162, over 1420135.38 frames.], batch size: 17, lr: 2.58e-04
+2022-04-30 09:53:43,988 INFO [train.py:763] (6/8) Epoch 29, batch 4350, loss[loss=0.1534, simple_loss=0.251, pruned_loss=0.02792, over 7232.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2618, pruned_loss=0.03101, over 1421662.13 frames.], batch size: 20, lr: 2.58e-04
+2022-04-30 09:54:58,498 INFO [train.py:763] (6/8) Epoch 29, batch 4400, loss[loss=0.1798, simple_loss=0.2885, pruned_loss=0.03558, over 7239.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2616, pruned_loss=0.03106, over 1418016.77 frames.], batch size: 20, lr: 2.57e-04
+2022-04-30 09:56:12,787 INFO [train.py:763] (6/8) Epoch 29, batch 4450, loss[loss=0.1692, simple_loss=0.2826, pruned_loss=0.02789, over 6547.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2611, pruned_loss=0.03088, over 1412940.39 frames.], batch size: 38, lr: 2.57e-04
+2022-04-30 09:57:18,024 INFO [train.py:763] (6/8) Epoch 29, batch 4500, loss[loss=0.2014, simple_loss=0.2972, pruned_loss=0.05283, over 4873.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2626, pruned_loss=0.03147, over 1398538.24 frames.], batch size: 52, lr: 2.57e-04
+2022-04-30 09:58:32,305 INFO [train.py:763] (6/8) Epoch 29, batch 4550, loss[loss=0.2009, simple_loss=0.2886, pruned_loss=0.05663, over 4817.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2651, pruned_loss=0.03297, over 1357412.74 frames.], batch size: 52, lr: 2.57e-04
+2022-04-30 10:00:01,320 INFO [train.py:763] (6/8) Epoch 30, batch 0, loss[loss=0.1556, simple_loss=0.2554, pruned_loss=0.02791, over 7319.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2554, pruned_loss=0.02791, over 7319.00 frames.], batch size: 20, lr: 2.53e-04
+2022-04-30 10:01:06,993 INFO [train.py:763] (6/8) Epoch 30, batch 50, loss[loss=0.1594, simple_loss=0.2613, pruned_loss=0.02877, over 7253.00 frames.], tot_loss[loss=0.165, simple_loss=0.2638, pruned_loss=0.03308, over 316842.56 frames.], batch size: 19, lr: 2.53e-04
+2022-04-30 10:02:12,185 INFO [train.py:763] (6/8) Epoch 30, batch 100, loss[loss=0.1608, simple_loss=0.261, pruned_loss=0.0303, over 7385.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2638, pruned_loss=0.03226, over 561966.19 frames.], batch size: 23, lr: 2.53e-04
+2022-04-30 10:03:17,807 INFO [train.py:763] (6/8) Epoch 30, batch 150, loss[loss=0.1654, simple_loss=0.2774, pruned_loss=0.02664, over 7211.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2611, pruned_loss=0.03129, over 756126.08 frames.], batch size: 22, lr: 2.53e-04
+2022-04-30 10:04:23,871 INFO [train.py:763] (6/8) Epoch 30, batch 200, loss[loss=0.2091, simple_loss=0.2922, pruned_loss=0.06299, over 4954.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2605, pruned_loss=0.03137, over 901296.27 frames.], batch size: 52, lr: 2.53e-04
+2022-04-30 10:05:29,996 INFO [train.py:763] (6/8) Epoch 30, batch 250, loss[loss=0.1861, simple_loss=0.2864, pruned_loss=0.04288, over 7257.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2619, pruned_loss=0.03165, over 1015757.26 frames.], batch size: 25, lr: 2.53e-04
+2022-04-30 10:06:35,955 INFO [train.py:763] (6/8) Epoch 30, batch 300, loss[loss=0.1438, simple_loss=0.2521, pruned_loss=0.0178, over 7325.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2625, pruned_loss=0.03166, over 1107227.72 frames.], batch size: 21, lr: 2.53e-04
+2022-04-30 10:07:41,455 INFO [train.py:763] (6/8) Epoch 30, batch 350, loss[loss=0.158, simple_loss=0.2514, pruned_loss=0.03228, over 7168.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2616, pruned_loss=0.03147, over 1174267.48 frames.], batch size: 18, lr: 2.53e-04
+2022-04-30 10:08:46,856 INFO [train.py:763] (6/8) Epoch 30, batch 400, loss[loss=0.1644, simple_loss=0.2777, pruned_loss=0.02557, over 7217.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.0312, over 1225727.09 frames.], batch size: 21, lr: 2.53e-04
+2022-04-30 10:09:52,321 INFO [train.py:763] (6/8) Epoch 30, batch 450, loss[loss=0.1987, simple_loss=0.2935, pruned_loss=0.05194, over 7125.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2622, pruned_loss=0.03084, over 1267445.85 frames.], batch size: 26, lr: 2.53e-04
+2022-04-30 10:10:57,857 INFO [train.py:763] (6/8) Epoch 30, batch 500, loss[loss=0.13, simple_loss=0.2217, pruned_loss=0.0192, over 7278.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03075, over 1303159.28 frames.], batch size: 17, lr: 2.53e-04
+2022-04-30 10:12:03,592 INFO [train.py:763] (6/8) Epoch 30, batch 550, loss[loss=0.1604, simple_loss=0.2755, pruned_loss=0.02262, over 7416.00 frames.], tot_loss[loss=0.1619, simple_loss=0.262, pruned_loss=0.03092, over 1329664.68 frames.], batch size: 21, lr: 2.53e-04
+2022-04-30 10:13:09,479 INFO [train.py:763] (6/8) Epoch 30, batch 600, loss[loss=0.1589, simple_loss=0.2523, pruned_loss=0.0328, over 7065.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2636, pruned_loss=0.03152, over 1348888.59 frames.], batch size: 18, lr: 2.53e-04
+2022-04-30 10:14:15,864 INFO [train.py:763] (6/8) Epoch 30, batch 650, loss[loss=0.1704, simple_loss=0.2829, pruned_loss=0.02893, over 7142.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2631, pruned_loss=0.03154, over 1369569.28 frames.], batch size: 20, lr: 2.53e-04
+2022-04-30 10:15:21,895 INFO [train.py:763] (6/8) Epoch 30, batch 700, loss[loss=0.1553, simple_loss=0.2436, pruned_loss=0.03353, over 7241.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2624, pruned_loss=0.03113, over 1378972.01 frames.], batch size: 16, lr: 2.52e-04
+2022-04-30 10:16:28,670 INFO [train.py:763] (6/8) Epoch 30, batch 750, loss[loss=0.1799, simple_loss=0.2847, pruned_loss=0.03754, over 7228.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2626, pruned_loss=0.03099, over 1386772.30 frames.], batch size: 20, lr: 2.52e-04
+2022-04-30 10:17:34,227 INFO [train.py:763] (6/8) Epoch 30, batch 800, loss[loss=0.1426, simple_loss=0.2444, pruned_loss=0.02043, over 7331.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2619, pruned_loss=0.03086, over 1395109.48 frames.], batch size: 20, lr: 2.52e-04
+2022-04-30 10:18:39,961 INFO [train.py:763] (6/8) Epoch 30, batch 850, loss[loss=0.1707, simple_loss=0.2718, pruned_loss=0.03483, over 7437.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.03074, over 1398816.59 frames.], batch size: 20, lr: 2.52e-04
+2022-04-30 10:19:45,740 INFO [train.py:763] (6/8) Epoch 30, batch 900, loss[loss=0.1503, simple_loss=0.243, pruned_loss=0.02883, over 7197.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2611, pruned_loss=0.03085, over 1403726.18 frames.], batch size: 16, lr: 2.52e-04
+2022-04-30 10:20:52,536 INFO [train.py:763] (6/8) Epoch 30, batch 950, loss[loss=0.1659, simple_loss=0.2683, pruned_loss=0.03175, over 7106.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2611, pruned_loss=0.03106, over 1405849.95 frames.], batch size: 28, lr: 2.52e-04
+2022-04-30 10:21:58,500 INFO [train.py:763] (6/8) Epoch 30, batch 1000, loss[loss=0.1649, simple_loss=0.278, pruned_loss=0.02597, over 7342.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2612, pruned_loss=0.03102, over 1407825.77 frames.], batch size: 22, lr: 2.52e-04
+2022-04-30 10:23:04,010 INFO [train.py:763] (6/8) Epoch 30, batch 1050, loss[loss=0.1583, simple_loss=0.2614, pruned_loss=0.02758, over 7060.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2613, pruned_loss=0.03087, over 1410744.58 frames.], batch size: 28, lr: 2.52e-04
+2022-04-30 10:24:09,738 INFO [train.py:763] (6/8) Epoch 30, batch 1100, loss[loss=0.1501, simple_loss=0.2522, pruned_loss=0.02396, over 7063.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2613, pruned_loss=0.03085, over 1414951.61 frames.], batch size: 18, lr: 2.52e-04
+2022-04-30 10:25:15,761 INFO [train.py:763] (6/8) Epoch 30, batch 1150, loss[loss=0.1477, simple_loss=0.2472, pruned_loss=0.0241, over 7446.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2608, pruned_loss=0.03076, over 1417204.00 frames.], batch size: 19, lr: 2.52e-04
+2022-04-30 10:26:21,664 INFO [train.py:763] (6/8) Epoch 30, batch 1200, loss[loss=0.182, simple_loss=0.2788, pruned_loss=0.04266, over 7208.00 frames.], tot_loss[loss=0.1605, simple_loss=0.26, pruned_loss=0.03052, over 1419243.35 frames.], batch size: 22, lr: 2.52e-04
+2022-04-30 10:27:27,466 INFO [train.py:763] (6/8) Epoch 30, batch 1250, loss[loss=0.1456, simple_loss=0.2405, pruned_loss=0.02532, over 7406.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2605, pruned_loss=0.0307, over 1418521.37 frames.], batch size: 18, lr: 2.52e-04
+2022-04-30 10:28:33,937 INFO [train.py:763] (6/8) Epoch 30, batch 1300, loss[loss=0.1782, simple_loss=0.2911, pruned_loss=0.03262, over 7153.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2612, pruned_loss=0.03071, over 1417149.47 frames.], batch size: 26, lr: 2.52e-04
+2022-04-30 10:29:40,215 INFO [train.py:763] (6/8) Epoch 30, batch 1350, loss[loss=0.1502, simple_loss=0.2431, pruned_loss=0.02865, over 7139.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2629, pruned_loss=0.03117, over 1414689.01 frames.], batch size: 17, lr: 2.52e-04
+2022-04-30 10:30:45,703 INFO [train.py:763] (6/8) Epoch 30, batch 1400, loss[loss=0.1781, simple_loss=0.2846, pruned_loss=0.0358, over 7346.00 frames.], tot_loss[loss=0.162, simple_loss=0.2626, pruned_loss=0.03071, over 1418766.22 frames.], batch size: 22, lr: 2.52e-04
+2022-04-30 10:31:51,072 INFO [train.py:763] (6/8) Epoch 30, batch 1450, loss[loss=0.1535, simple_loss=0.2591, pruned_loss=0.0239, over 7140.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2618, pruned_loss=0.03051, over 1420073.32 frames.], batch size: 20, lr: 2.52e-04
+2022-04-30 10:32:56,517 INFO [train.py:763] (6/8) Epoch 30, batch 1500, loss[loss=0.1768, simple_loss=0.283, pruned_loss=0.03532, over 7308.00 frames.], tot_loss[loss=0.1621, simple_loss=0.263, pruned_loss=0.03055, over 1425839.26 frames.], batch size: 25, lr: 2.52e-04
+2022-04-30 10:34:02,181 INFO [train.py:763] (6/8) Epoch 30, batch 1550, loss[loss=0.2002, simple_loss=0.2923, pruned_loss=0.054, over 7297.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2625, pruned_loss=0.03084, over 1427941.56 frames.], batch size: 25, lr: 2.52e-04
+2022-04-30 10:35:07,679 INFO [train.py:763] (6/8) Epoch 30, batch 1600, loss[loss=0.1638, simple_loss=0.2639, pruned_loss=0.03186, over 7256.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2618, pruned_loss=0.03056, over 1429122.95 frames.], batch size: 19, lr: 2.52e-04
+2022-04-30 10:36:13,951 INFO [train.py:763] (6/8) Epoch 30, batch 1650, loss[loss=0.1351, simple_loss=0.2474, pruned_loss=0.01136, over 7121.00 frames.], tot_loss[loss=0.162, simple_loss=0.2625, pruned_loss=0.03073, over 1429260.66 frames.], batch size: 21, lr: 2.52e-04
+2022-04-30 10:37:20,416 INFO [train.py:763] (6/8) Epoch 30, batch 1700, loss[loss=0.1691, simple_loss=0.2746, pruned_loss=0.03179, over 7312.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2613, pruned_loss=0.03058, over 1425921.50 frames.], batch size: 24, lr: 2.52e-04
+2022-04-30 10:38:27,156 INFO [train.py:763] (6/8) Epoch 30, batch 1750, loss[loss=0.174, simple_loss=0.28, pruned_loss=0.034, over 7360.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2622, pruned_loss=0.03105, over 1427978.99 frames.], batch size: 23, lr: 2.52e-04
+2022-04-30 10:39:33,033 INFO [train.py:763] (6/8) Epoch 30, batch 1800, loss[loss=0.1458, simple_loss=0.2512, pruned_loss=0.0202, over 7428.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2614, pruned_loss=0.03088, over 1423595.81 frames.], batch size: 20, lr: 2.51e-04
+2022-04-30 10:40:39,032 INFO [train.py:763] (6/8) Epoch 30, batch 1850, loss[loss=0.1382, simple_loss=0.2357, pruned_loss=0.02039, over 7134.00 frames.], tot_loss[loss=0.1613, simple_loss=0.261, pruned_loss=0.03076, over 1421789.34 frames.], batch size: 17, lr: 2.51e-04
+2022-04-30 10:41:45,827 INFO [train.py:763] (6/8) Epoch 30, batch 1900, loss[loss=0.1775, simple_loss=0.2789, pruned_loss=0.03808, over 7322.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03079, over 1425295.99 frames.], batch size: 20, lr: 2.51e-04
+2022-04-30 10:42:51,810 INFO [train.py:763] (6/8) Epoch 30, batch 1950, loss[loss=0.1772, simple_loss=0.2799, pruned_loss=0.03723, over 7365.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2618, pruned_loss=0.031, over 1425201.60 frames.], batch size: 23, lr: 2.51e-04
+2022-04-30 10:43:59,476 INFO [train.py:763] (6/8) Epoch 30, batch 2000, loss[loss=0.1677, simple_loss=0.2634, pruned_loss=0.036, over 7168.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2608, pruned_loss=0.03088, over 1426878.01 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:45:05,771 INFO [train.py:763] (6/8) Epoch 30, batch 2050, loss[loss=0.1539, simple_loss=0.2548, pruned_loss=0.02652, over 7199.00 frames.], tot_loss[loss=0.1607, simple_loss=0.26, pruned_loss=0.03073, over 1424290.28 frames.], batch size: 22, lr: 2.51e-04
+2022-04-30 10:46:11,293 INFO [train.py:763] (6/8) Epoch 30, batch 2100, loss[loss=0.1749, simple_loss=0.2722, pruned_loss=0.0388, over 7159.00 frames.], tot_loss[loss=0.1615, simple_loss=0.261, pruned_loss=0.03105, over 1423496.43 frames.], batch size: 19, lr: 2.51e-04
+2022-04-30 10:47:17,302 INFO [train.py:763] (6/8) Epoch 30, batch 2150, loss[loss=0.1208, simple_loss=0.2198, pruned_loss=0.01093, over 7171.00 frames.], tot_loss[loss=0.16, simple_loss=0.2595, pruned_loss=0.03027, over 1427452.85 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:48:22,848 INFO [train.py:763] (6/8) Epoch 30, batch 2200, loss[loss=0.1623, simple_loss=0.247, pruned_loss=0.03885, over 7079.00 frames.], tot_loss[loss=0.161, simple_loss=0.2605, pruned_loss=0.03077, over 1428551.40 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:49:28,456 INFO [train.py:763] (6/8) Epoch 30, batch 2250, loss[loss=0.1773, simple_loss=0.2846, pruned_loss=0.03497, over 7192.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03077, over 1427496.77 frames.], batch size: 23, lr: 2.51e-04
+2022-04-30 10:50:34,516 INFO [train.py:763] (6/8) Epoch 30, batch 2300, loss[loss=0.1467, simple_loss=0.2529, pruned_loss=0.02026, over 7254.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2618, pruned_loss=0.03121, over 1429575.30 frames.], batch size: 19, lr: 2.51e-04
+2022-04-30 10:51:40,504 INFO [train.py:763] (6/8) Epoch 30, batch 2350, loss[loss=0.1814, simple_loss=0.2851, pruned_loss=0.03878, over 7060.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2617, pruned_loss=0.03138, over 1430519.46 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:52:46,205 INFO [train.py:763] (6/8) Epoch 30, batch 2400, loss[loss=0.1793, simple_loss=0.285, pruned_loss=0.0368, over 7227.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2625, pruned_loss=0.03152, over 1429427.70 frames.], batch size: 21, lr: 2.51e-04
+2022-04-30 10:53:51,759 INFO [train.py:763] (6/8) Epoch 30, batch 2450, loss[loss=0.1698, simple_loss=0.2735, pruned_loss=0.03307, over 7225.00 frames.], tot_loss[loss=0.163, simple_loss=0.2632, pruned_loss=0.03146, over 1425587.71 frames.], batch size: 21, lr: 2.51e-04
+2022-04-30 10:54:57,034 INFO [train.py:763] (6/8) Epoch 30, batch 2500, loss[loss=0.1754, simple_loss=0.2923, pruned_loss=0.02922, over 7330.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2629, pruned_loss=0.03144, over 1427719.14 frames.], batch size: 22, lr: 2.51e-04
+2022-04-30 10:56:03,558 INFO [train.py:763] (6/8) Epoch 30, batch 2550, loss[loss=0.157, simple_loss=0.2621, pruned_loss=0.02597, over 7184.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2628, pruned_loss=0.03139, over 1428836.63 frames.], batch size: 23, lr: 2.51e-04
+2022-04-30 10:57:09,407 INFO [train.py:763] (6/8) Epoch 30, batch 2600, loss[loss=0.1488, simple_loss=0.2453, pruned_loss=0.0262, over 7423.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2627, pruned_loss=0.03154, over 1428141.25 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:58:15,104 INFO [train.py:763] (6/8) Epoch 30, batch 2650, loss[loss=0.1708, simple_loss=0.2819, pruned_loss=0.02985, over 7410.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2622, pruned_loss=0.03147, over 1425662.65 frames.], batch size: 21, lr: 2.51e-04
+2022-04-30 10:59:20,430 INFO [train.py:763] (6/8) Epoch 30, batch 2700, loss[loss=0.1627, simple_loss=0.2688, pruned_loss=0.02834, over 7281.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2631, pruned_loss=0.03162, over 1419288.87 frames.], batch size: 25, lr: 2.51e-04
+2022-04-30 11:00:26,176 INFO [train.py:763] (6/8) Epoch 30, batch 2750, loss[loss=0.1587, simple_loss=0.266, pruned_loss=0.0257, over 7145.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03115, over 1419938.48 frames.], batch size: 20, lr: 2.51e-04
+2022-04-30 11:01:31,736 INFO [train.py:763] (6/8) Epoch 30, batch 2800, loss[loss=0.1473, simple_loss=0.2495, pruned_loss=0.02253, over 7173.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2627, pruned_loss=0.03182, over 1422429.09 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 11:02:36,838 INFO [train.py:763] (6/8) Epoch 30, batch 2850, loss[loss=0.1945, simple_loss=0.2898, pruned_loss=0.04955, over 7200.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2631, pruned_loss=0.03192, over 1419851.37 frames.], batch size: 22, lr: 2.51e-04
+2022-04-30 11:03:42,112 INFO [train.py:763] (6/8) Epoch 30, batch 2900, loss[loss=0.1525, simple_loss=0.2665, pruned_loss=0.01928, over 7110.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2625, pruned_loss=0.03154, over 1423240.63 frames.], batch size: 21, lr: 2.51e-04
+2022-04-30 11:04:47,459 INFO [train.py:763] (6/8) Epoch 30, batch 2950, loss[loss=0.1462, simple_loss=0.2404, pruned_loss=0.02594, over 7258.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2625, pruned_loss=0.03147, over 1422500.14 frames.], batch size: 19, lr: 2.50e-04
+2022-04-30 11:05:53,066 INFO [train.py:763] (6/8) Epoch 30, batch 3000, loss[loss=0.1479, simple_loss=0.2525, pruned_loss=0.0216, over 7327.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2621, pruned_loss=0.03144, over 1422862.37 frames.], batch size: 20, lr: 2.50e-04
+2022-04-30 11:05:53,067 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 11:06:08,153 INFO [train.py:792] (6/8) Epoch 30, validation: loss=0.1701, simple_loss=0.2661, pruned_loss=0.03704, over 698248.00 frames.
+2022-04-30 11:07:13,674 INFO [train.py:763] (6/8) Epoch 30, batch 3050, loss[loss=0.1519, simple_loss=0.2408, pruned_loss=0.03152, over 6997.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2623, pruned_loss=0.03167, over 1422385.39 frames.], batch size: 16, lr: 2.50e-04
+2022-04-30 11:08:19,233 INFO [train.py:763] (6/8) Epoch 30, batch 3100, loss[loss=0.1916, simple_loss=0.2969, pruned_loss=0.04318, over 7241.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2623, pruned_loss=0.03157, over 1425934.99 frames.], batch size: 25, lr: 2.50e-04
+2022-04-30 11:09:24,927 INFO [train.py:763] (6/8) Epoch 30, batch 3150, loss[loss=0.1427, simple_loss=0.226, pruned_loss=0.02969, over 7010.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2628, pruned_loss=0.03154, over 1425759.42 frames.], batch size: 16, lr: 2.50e-04
+2022-04-30 11:10:31,195 INFO [train.py:763] (6/8) Epoch 30, batch 3200, loss[loss=0.1767, simple_loss=0.2768, pruned_loss=0.03833, over 7200.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2626, pruned_loss=0.03132, over 1417491.81 frames.], batch size: 23, lr: 2.50e-04
+2022-04-30 11:11:37,939 INFO [train.py:763] (6/8) Epoch 30, batch 3250, loss[loss=0.1836, simple_loss=0.2915, pruned_loss=0.03789, over 7150.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2633, pruned_loss=0.03151, over 1417159.28 frames.], batch size: 20, lr: 2.50e-04
+2022-04-30 11:12:45,388 INFO [train.py:763] (6/8) Epoch 30, batch 3300, loss[loss=0.1593, simple_loss=0.2515, pruned_loss=0.03351, over 7272.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2619, pruned_loss=0.03099, over 1423247.67 frames.], batch size: 17, lr: 2.50e-04
+2022-04-30 11:13:51,986 INFO [train.py:763] (6/8) Epoch 30, batch 3350, loss[loss=0.1584, simple_loss=0.2706, pruned_loss=0.02316, over 7217.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2616, pruned_loss=0.03088, over 1422491.52 frames.], batch size: 21, lr: 2.50e-04
+2022-04-30 11:14:57,146 INFO [train.py:763] (6/8) Epoch 30, batch 3400, loss[loss=0.1746, simple_loss=0.277, pruned_loss=0.03613, over 7300.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2608, pruned_loss=0.03066, over 1421959.55 frames.], batch size: 25, lr: 2.50e-04
+2022-04-30 11:16:02,381 INFO [train.py:763] (6/8) Epoch 30, batch 3450, loss[loss=0.1831, simple_loss=0.2916, pruned_loss=0.03724, over 6235.00 frames.], tot_loss[loss=0.1623, simple_loss=0.262, pruned_loss=0.03128, over 1426116.96 frames.], batch size: 37, lr: 2.50e-04
+2022-04-30 11:17:08,607 INFO [train.py:763] (6/8) Epoch 30, batch 3500, loss[loss=0.1891, simple_loss=0.289, pruned_loss=0.04463, over 7388.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.03116, over 1427068.73 frames.], batch size: 23, lr: 2.50e-04
+2022-04-30 11:18:14,700 INFO [train.py:763] (6/8) Epoch 30, batch 3550, loss[loss=0.1676, simple_loss=0.2696, pruned_loss=0.03285, over 7437.00 frames.], tot_loss[loss=0.1622, simple_loss=0.262, pruned_loss=0.03122, over 1428252.80 frames.], batch size: 20, lr: 2.50e-04
+2022-04-30 11:19:20,437 INFO [train.py:763] (6/8) Epoch 30, batch 3600, loss[loss=0.1559, simple_loss=0.2544, pruned_loss=0.02875, over 7289.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2634, pruned_loss=0.03222, over 1422960.28 frames.], batch size: 24, lr: 2.50e-04
+2022-04-30 11:20:25,887 INFO [train.py:763] (6/8) Epoch 30, batch 3650, loss[loss=0.1482, simple_loss=0.2452, pruned_loss=0.02562, over 7133.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2628, pruned_loss=0.0318, over 1422512.41 frames.], batch size: 17, lr: 2.50e-04
+2022-04-30 11:21:32,101 INFO [train.py:763] (6/8) Epoch 30, batch 3700, loss[loss=0.1459, simple_loss=0.2328, pruned_loss=0.02954, over 7286.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2615, pruned_loss=0.03112, over 1425493.57 frames.], batch size: 17, lr: 2.50e-04
+2022-04-30 11:22:38,026 INFO [train.py:763] (6/8) Epoch 30, batch 3750, loss[loss=0.143, simple_loss=0.2431, pruned_loss=0.02149, over 7257.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2619, pruned_loss=0.03162, over 1423992.50 frames.], batch size: 19, lr: 2.50e-04
+2022-04-30 11:23:45,245 INFO [train.py:763] (6/8) Epoch 30, batch 3800, loss[loss=0.1368, simple_loss=0.2301, pruned_loss=0.02172, over 7269.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2608, pruned_loss=0.03103, over 1426437.58 frames.], batch size: 18, lr: 2.50e-04
+2022-04-30 11:24:50,560 INFO [train.py:763] (6/8) Epoch 30, batch 3850, loss[loss=0.1642, simple_loss=0.2681, pruned_loss=0.03018, over 7056.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2616, pruned_loss=0.03101, over 1425513.65 frames.], batch size: 18, lr: 2.50e-04
+2022-04-30 11:25:56,096 INFO [train.py:763] (6/8) Epoch 30, batch 3900, loss[loss=0.1619, simple_loss=0.2744, pruned_loss=0.02466, over 7259.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.03062, over 1429039.07 frames.], batch size: 24, lr: 2.50e-04
+2022-04-30 11:27:01,585 INFO [train.py:763] (6/8) Epoch 30, batch 3950, loss[loss=0.1745, simple_loss=0.2661, pruned_loss=0.04149, over 7354.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2601, pruned_loss=0.03044, over 1429296.34 frames.], batch size: 19, lr: 2.50e-04
+2022-04-30 11:28:06,972 INFO [train.py:763] (6/8) Epoch 30, batch 4000, loss[loss=0.1556, simple_loss=0.254, pruned_loss=0.02859, over 7175.00 frames.], tot_loss[loss=0.1613, simple_loss=0.261, pruned_loss=0.03077, over 1426506.47 frames.], batch size: 18, lr: 2.50e-04
+2022-04-30 11:29:11,958 INFO [train.py:763] (6/8) Epoch 30, batch 4050, loss[loss=0.1617, simple_loss=0.2672, pruned_loss=0.02807, over 7305.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2614, pruned_loss=0.03054, over 1425702.40 frames.], batch size: 24, lr: 2.49e-04
+2022-04-30 11:30:18,168 INFO [train.py:763] (6/8) Epoch 30, batch 4100, loss[loss=0.1479, simple_loss=0.2441, pruned_loss=0.02587, over 7163.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2617, pruned_loss=0.03063, over 1427600.81 frames.], batch size: 19, lr: 2.49e-04
+2022-04-30 11:31:24,159 INFO [train.py:763] (6/8) Epoch 30, batch 4150, loss[loss=0.1781, simple_loss=0.2818, pruned_loss=0.03719, over 7109.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2609, pruned_loss=0.0302, over 1429466.69 frames.], batch size: 21, lr: 2.49e-04
+2022-04-30 11:32:29,731 INFO [train.py:763] (6/8) Epoch 30, batch 4200, loss[loss=0.135, simple_loss=0.2216, pruned_loss=0.02416, over 6839.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2599, pruned_loss=0.03021, over 1431113.96 frames.], batch size: 15, lr: 2.49e-04
+2022-04-30 11:33:35,007 INFO [train.py:763] (6/8) Epoch 30, batch 4250, loss[loss=0.1831, simple_loss=0.286, pruned_loss=0.04008, over 7179.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03034, over 1427688.45 frames.], batch size: 26, lr: 2.49e-04
+2022-04-30 11:34:41,235 INFO [train.py:763] (6/8) Epoch 30, batch 4300, loss[loss=0.1885, simple_loss=0.2916, pruned_loss=0.0427, over 7288.00 frames.], tot_loss[loss=0.16, simple_loss=0.2602, pruned_loss=0.02993, over 1431430.91 frames.], batch size: 24, lr: 2.49e-04
+2022-04-30 11:35:46,142 INFO [train.py:763] (6/8) Epoch 30, batch 4350, loss[loss=0.157, simple_loss=0.2454, pruned_loss=0.0343, over 7124.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2603, pruned_loss=0.02991, over 1422678.37 frames.], batch size: 21, lr: 2.49e-04
+2022-04-30 11:36:51,030 INFO [train.py:763] (6/8) Epoch 30, batch 4400, loss[loss=0.1823, simple_loss=0.2774, pruned_loss=0.04362, over 7122.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03058, over 1412199.78 frames.], batch size: 21, lr: 2.49e-04
+2022-04-30 11:37:56,308 INFO [train.py:763] (6/8) Epoch 30, batch 4450, loss[loss=0.1869, simple_loss=0.2927, pruned_loss=0.0405, over 6348.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2612, pruned_loss=0.03071, over 1410494.89 frames.], batch size: 38, lr: 2.49e-04
+2022-04-30 11:39:02,209 INFO [train.py:763] (6/8) Epoch 30, batch 4500, loss[loss=0.158, simple_loss=0.2662, pruned_loss=0.02492, over 6468.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2626, pruned_loss=0.03122, over 1386205.53 frames.], batch size: 38, lr: 2.49e-04
+2022-04-30 11:40:07,228 INFO [train.py:763] (6/8) Epoch 30, batch 4550, loss[loss=0.1596, simple_loss=0.254, pruned_loss=0.03265, over 5261.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2637, pruned_loss=0.032, over 1356252.32 frames.], batch size: 52, lr: 2.49e-04
+2022-04-30 11:41:35,693 INFO [train.py:763] (6/8) Epoch 31, batch 0, loss[loss=0.2024, simple_loss=0.2944, pruned_loss=0.05516, over 5345.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2944, pruned_loss=0.05516, over 5345.00 frames.], batch size: 52, lr: 2.45e-04
+2022-04-30 11:42:41,158 INFO [train.py:763] (6/8) Epoch 31, batch 50, loss[loss=0.1858, simple_loss=0.2913, pruned_loss=0.04015, over 6335.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2692, pruned_loss=0.0336, over 319930.44 frames.], batch size: 37, lr: 2.45e-04
+2022-04-30 11:43:46,470 INFO [train.py:763] (6/8) Epoch 31, batch 100, loss[loss=0.1601, simple_loss=0.2613, pruned_loss=0.02943, over 7281.00 frames.], tot_loss[loss=0.164, simple_loss=0.2642, pruned_loss=0.03188, over 567283.82 frames.], batch size: 25, lr: 2.45e-04
+2022-04-30 11:44:52,571 INFO [train.py:763] (6/8) Epoch 31, batch 150, loss[loss=0.1777, simple_loss=0.2809, pruned_loss=0.03728, over 7209.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2621, pruned_loss=0.03085, over 758655.01 frames.], batch size: 26, lr: 2.45e-04
+2022-04-30 11:45:58,817 INFO [train.py:763] (6/8) Epoch 31, batch 200, loss[loss=0.1494, simple_loss=0.2421, pruned_loss=0.02835, over 6988.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2619, pruned_loss=0.03029, over 903525.60 frames.], batch size: 16, lr: 2.45e-04
+2022-04-30 11:47:04,082 INFO [train.py:763] (6/8) Epoch 31, batch 250, loss[loss=0.1544, simple_loss=0.2557, pruned_loss=0.0266, over 7287.00 frames.], tot_loss[loss=0.1622, simple_loss=0.263, pruned_loss=0.03075, over 1023161.75 frames.], batch size: 24, lr: 2.45e-04
+2022-04-30 11:48:09,435 INFO [train.py:763] (6/8) Epoch 31, batch 300, loss[loss=0.2166, simple_loss=0.3144, pruned_loss=0.0594, over 7285.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2634, pruned_loss=0.03143, over 1113882.90 frames.], batch size: 24, lr: 2.45e-04
+2022-04-30 11:49:14,696 INFO [train.py:763] (6/8) Epoch 31, batch 350, loss[loss=0.1586, simple_loss=0.2622, pruned_loss=0.02748, over 7035.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.03102, over 1181643.05 frames.], batch size: 28, lr: 2.45e-04
+2022-04-30 11:50:20,236 INFO [train.py:763] (6/8) Epoch 31, batch 400, loss[loss=0.1822, simple_loss=0.2795, pruned_loss=0.04245, over 7181.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2618, pruned_loss=0.03117, over 1236876.86 frames.], batch size: 26, lr: 2.45e-04
+2022-04-30 11:51:25,628 INFO [train.py:763] (6/8) Epoch 31, batch 450, loss[loss=0.1716, simple_loss=0.2828, pruned_loss=0.03018, over 7321.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2615, pruned_loss=0.03055, over 1277001.79 frames.], batch size: 21, lr: 2.45e-04
+2022-04-30 11:52:41,063 INFO [train.py:763] (6/8) Epoch 31, batch 500, loss[loss=0.1596, simple_loss=0.2729, pruned_loss=0.02319, over 7318.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2613, pruned_loss=0.03015, over 1313050.21 frames.], batch size: 22, lr: 2.45e-04
+2022-04-30 11:53:47,763 INFO [train.py:763] (6/8) Epoch 31, batch 550, loss[loss=0.1832, simple_loss=0.2784, pruned_loss=0.044, over 7334.00 frames.], tot_loss[loss=0.1604, simple_loss=0.261, pruned_loss=0.02988, over 1341712.51 frames.], batch size: 22, lr: 2.45e-04
+2022-04-30 11:54:53,977 INFO [train.py:763] (6/8) Epoch 31, batch 600, loss[loss=0.1308, simple_loss=0.2209, pruned_loss=0.02032, over 7134.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2608, pruned_loss=0.03046, over 1364173.46 frames.], batch size: 17, lr: 2.45e-04
+2022-04-30 11:55:59,949 INFO [train.py:763] (6/8) Epoch 31, batch 650, loss[loss=0.1476, simple_loss=0.2361, pruned_loss=0.0296, over 6983.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2604, pruned_loss=0.03064, over 1379601.12 frames.], batch size: 16, lr: 2.45e-04
+2022-04-30 11:57:06,500 INFO [train.py:763] (6/8) Epoch 31, batch 700, loss[loss=0.1601, simple_loss=0.2657, pruned_loss=0.02727, over 7198.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2609, pruned_loss=0.03044, over 1388245.74 frames.], batch size: 23, lr: 2.45e-04
+2022-04-30 11:58:13,270 INFO [train.py:763] (6/8) Epoch 31, batch 750, loss[loss=0.1732, simple_loss=0.2842, pruned_loss=0.03107, over 7122.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2613, pruned_loss=0.03048, over 1396277.54 frames.], batch size: 21, lr: 2.44e-04
+2022-04-30 11:59:18,737 INFO [train.py:763] (6/8) Epoch 31, batch 800, loss[loss=0.1618, simple_loss=0.2536, pruned_loss=0.035, over 7289.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2618, pruned_loss=0.03072, over 1400862.64 frames.], batch size: 18, lr: 2.44e-04
+2022-04-30 12:00:24,036 INFO [train.py:763] (6/8) Epoch 31, batch 850, loss[loss=0.1488, simple_loss=0.2518, pruned_loss=0.02293, over 7267.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2623, pruned_loss=0.03097, over 1408473.17 frames.], batch size: 25, lr: 2.44e-04
+2022-04-30 12:01:28,731 INFO [train.py:763] (6/8) Epoch 31, batch 900, loss[loss=0.1701, simple_loss=0.2784, pruned_loss=0.03095, over 7337.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2633, pruned_loss=0.03111, over 1411417.67 frames.], batch size: 22, lr: 2.44e-04
+2022-04-30 12:02:34,059 INFO [train.py:763] (6/8) Epoch 31, batch 950, loss[loss=0.1489, simple_loss=0.248, pruned_loss=0.02487, over 7257.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2623, pruned_loss=0.03098, over 1413323.02 frames.], batch size: 16, lr: 2.44e-04
+2022-04-30 12:03:39,305 INFO [train.py:763] (6/8) Epoch 31, batch 1000, loss[loss=0.1894, simple_loss=0.2897, pruned_loss=0.04448, over 7436.00 frames.], tot_loss[loss=0.1621, simple_loss=0.262, pruned_loss=0.03117, over 1417444.26 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:04:53,739 INFO [train.py:763] (6/8) Epoch 31, batch 1050, loss[loss=0.1767, simple_loss=0.2858, pruned_loss=0.03379, over 7239.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2615, pruned_loss=0.03082, over 1421111.08 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:05:59,156 INFO [train.py:763] (6/8) Epoch 31, batch 1100, loss[loss=0.1579, simple_loss=0.2672, pruned_loss=0.02429, over 7190.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2613, pruned_loss=0.03103, over 1418999.75 frames.], batch size: 22, lr: 2.44e-04
+2022-04-30 12:07:23,601 INFO [train.py:763] (6/8) Epoch 31, batch 1150, loss[loss=0.1345, simple_loss=0.228, pruned_loss=0.02053, over 7130.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2613, pruned_loss=0.03093, over 1422997.94 frames.], batch size: 17, lr: 2.44e-04
+2022-04-30 12:08:30,099 INFO [train.py:763] (6/8) Epoch 31, batch 1200, loss[loss=0.1539, simple_loss=0.2606, pruned_loss=0.02359, over 7425.00 frames.], tot_loss[loss=0.161, simple_loss=0.2606, pruned_loss=0.03066, over 1425472.24 frames.], batch size: 21, lr: 2.44e-04
+2022-04-30 12:09:54,555 INFO [train.py:763] (6/8) Epoch 31, batch 1250, loss[loss=0.1855, simple_loss=0.2806, pruned_loss=0.0452, over 7201.00 frames.], tot_loss[loss=0.1618, simple_loss=0.261, pruned_loss=0.03128, over 1418941.50 frames.], batch size: 23, lr: 2.44e-04
+2022-04-30 12:11:00,227 INFO [train.py:763] (6/8) Epoch 31, batch 1300, loss[loss=0.1592, simple_loss=0.2676, pruned_loss=0.02537, over 7151.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2605, pruned_loss=0.03104, over 1423735.94 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:12:14,868 INFO [train.py:763] (6/8) Epoch 31, batch 1350, loss[loss=0.1574, simple_loss=0.2488, pruned_loss=0.033, over 7337.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2605, pruned_loss=0.03098, over 1421838.66 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:13:22,478 INFO [train.py:763] (6/8) Epoch 31, batch 1400, loss[loss=0.1519, simple_loss=0.2587, pruned_loss=0.0225, over 7239.00 frames.], tot_loss[loss=0.161, simple_loss=0.2606, pruned_loss=0.03069, over 1422229.62 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:14:38,782 INFO [train.py:763] (6/8) Epoch 31, batch 1450, loss[loss=0.1517, simple_loss=0.2544, pruned_loss=0.02457, over 7331.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2613, pruned_loss=0.03083, over 1423825.40 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:15:46,112 INFO [train.py:763] (6/8) Epoch 31, batch 1500, loss[loss=0.1723, simple_loss=0.2743, pruned_loss=0.03512, over 5045.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03025, over 1422271.54 frames.], batch size: 52, lr: 2.44e-04
+2022-04-30 12:16:51,629 INFO [train.py:763] (6/8) Epoch 31, batch 1550, loss[loss=0.1377, simple_loss=0.2351, pruned_loss=0.02011, over 7397.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2601, pruned_loss=0.03025, over 1420895.62 frames.], batch size: 18, lr: 2.44e-04
+2022-04-30 12:17:56,939 INFO [train.py:763] (6/8) Epoch 31, batch 1600, loss[loss=0.1954, simple_loss=0.2835, pruned_loss=0.05371, over 7195.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2602, pruned_loss=0.03043, over 1416962.76 frames.], batch size: 23, lr: 2.44e-04
+2022-04-30 12:19:02,305 INFO [train.py:763] (6/8) Epoch 31, batch 1650, loss[loss=0.1438, simple_loss=0.2472, pruned_loss=0.02023, over 7412.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2614, pruned_loss=0.03091, over 1416673.87 frames.], batch size: 21, lr: 2.44e-04
+2022-04-30 12:20:07,951 INFO [train.py:763] (6/8) Epoch 31, batch 1700, loss[loss=0.1427, simple_loss=0.2526, pruned_loss=0.01638, over 7109.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2611, pruned_loss=0.03105, over 1412304.36 frames.], batch size: 21, lr: 2.44e-04
+2022-04-30 12:21:14,752 INFO [train.py:763] (6/8) Epoch 31, batch 1750, loss[loss=0.1714, simple_loss=0.2634, pruned_loss=0.03973, over 5004.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.0308, over 1410269.23 frames.], batch size: 53, lr: 2.44e-04
+2022-04-30 12:22:33,260 INFO [train.py:763] (6/8) Epoch 31, batch 1800, loss[loss=0.1559, simple_loss=0.2585, pruned_loss=0.02665, over 7233.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03109, over 1411396.95 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:23:40,152 INFO [train.py:763] (6/8) Epoch 31, batch 1850, loss[loss=0.1575, simple_loss=0.2489, pruned_loss=0.03303, over 6992.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2614, pruned_loss=0.03111, over 1405183.63 frames.], batch size: 16, lr: 2.44e-04
+2022-04-30 12:24:46,004 INFO [train.py:763] (6/8) Epoch 31, batch 1900, loss[loss=0.1393, simple_loss=0.2339, pruned_loss=0.02231, over 7352.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2591, pruned_loss=0.03019, over 1411898.75 frames.], batch size: 19, lr: 2.44e-04
+2022-04-30 12:25:51,350 INFO [train.py:763] (6/8) Epoch 31, batch 1950, loss[loss=0.1476, simple_loss=0.2393, pruned_loss=0.02795, over 7362.00 frames.], tot_loss[loss=0.1598, simple_loss=0.259, pruned_loss=0.03037, over 1418106.26 frames.], batch size: 19, lr: 2.43e-04
+2022-04-30 12:26:56,757 INFO [train.py:763] (6/8) Epoch 31, batch 2000, loss[loss=0.1362, simple_loss=0.235, pruned_loss=0.01874, over 7283.00 frames.], tot_loss[loss=0.16, simple_loss=0.2596, pruned_loss=0.03022, over 1419338.02 frames.], batch size: 18, lr: 2.43e-04
+2022-04-30 12:28:01,919 INFO [train.py:763] (6/8) Epoch 31, batch 2050, loss[loss=0.1681, simple_loss=0.2674, pruned_loss=0.03439, over 7137.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2597, pruned_loss=0.03035, over 1415758.59 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:29:07,874 INFO [train.py:763] (6/8) Epoch 31, batch 2100, loss[loss=0.1459, simple_loss=0.2404, pruned_loss=0.02574, over 7239.00 frames.], tot_loss[loss=0.1621, simple_loss=0.262, pruned_loss=0.03107, over 1415942.67 frames.], batch size: 16, lr: 2.43e-04
+2022-04-30 12:30:13,158 INFO [train.py:763] (6/8) Epoch 31, batch 2150, loss[loss=0.1372, simple_loss=0.2457, pruned_loss=0.01436, over 7212.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2624, pruned_loss=0.031, over 1420134.22 frames.], batch size: 21, lr: 2.43e-04
+2022-04-30 12:31:18,653 INFO [train.py:763] (6/8) Epoch 31, batch 2200, loss[loss=0.1634, simple_loss=0.2692, pruned_loss=0.02882, over 7216.00 frames.], tot_loss[loss=0.162, simple_loss=0.2618, pruned_loss=0.03107, over 1423002.17 frames.], batch size: 26, lr: 2.43e-04
+2022-04-30 12:32:23,985 INFO [train.py:763] (6/8) Epoch 31, batch 2250, loss[loss=0.1696, simple_loss=0.265, pruned_loss=0.03713, over 7457.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03122, over 1425343.34 frames.], batch size: 19, lr: 2.43e-04
+2022-04-30 12:33:30,744 INFO [train.py:763] (6/8) Epoch 31, batch 2300, loss[loss=0.1831, simple_loss=0.286, pruned_loss=0.04006, over 7343.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2624, pruned_loss=0.03142, over 1422769.62 frames.], batch size: 22, lr: 2.43e-04
+2022-04-30 12:34:36,637 INFO [train.py:763] (6/8) Epoch 31, batch 2350, loss[loss=0.1438, simple_loss=0.2369, pruned_loss=0.02528, over 7280.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2632, pruned_loss=0.03115, over 1426274.95 frames.], batch size: 17, lr: 2.43e-04
+2022-04-30 12:35:41,756 INFO [train.py:763] (6/8) Epoch 31, batch 2400, loss[loss=0.1521, simple_loss=0.2471, pruned_loss=0.02857, over 7328.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2625, pruned_loss=0.03083, over 1422161.02 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:36:47,282 INFO [train.py:763] (6/8) Epoch 31, batch 2450, loss[loss=0.1889, simple_loss=0.2952, pruned_loss=0.04135, over 7105.00 frames.], tot_loss[loss=0.1619, simple_loss=0.262, pruned_loss=0.03093, over 1423491.99 frames.], batch size: 26, lr: 2.43e-04
+2022-04-30 12:37:52,780 INFO [train.py:763] (6/8) Epoch 31, batch 2500, loss[loss=0.1409, simple_loss=0.2372, pruned_loss=0.02231, over 7281.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2622, pruned_loss=0.03122, over 1425567.42 frames.], batch size: 17, lr: 2.43e-04
+2022-04-30 12:38:58,018 INFO [train.py:763] (6/8) Epoch 31, batch 2550, loss[loss=0.1436, simple_loss=0.2515, pruned_loss=0.01788, over 7334.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2623, pruned_loss=0.03128, over 1423164.90 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:40:03,279 INFO [train.py:763] (6/8) Epoch 31, batch 2600, loss[loss=0.1843, simple_loss=0.2713, pruned_loss=0.04869, over 7126.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2619, pruned_loss=0.0313, over 1421838.21 frames.], batch size: 17, lr: 2.43e-04
+2022-04-30 12:41:08,492 INFO [train.py:763] (6/8) Epoch 31, batch 2650, loss[loss=0.1709, simple_loss=0.2837, pruned_loss=0.02911, over 7173.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2619, pruned_loss=0.03096, over 1424313.23 frames.], batch size: 26, lr: 2.43e-04
+2022-04-30 12:42:15,312 INFO [train.py:763] (6/8) Epoch 31, batch 2700, loss[loss=0.1661, simple_loss=0.2753, pruned_loss=0.02848, over 7331.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2614, pruned_loss=0.03098, over 1423385.05 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:43:20,589 INFO [train.py:763] (6/8) Epoch 31, batch 2750, loss[loss=0.1651, simple_loss=0.2611, pruned_loss=0.03449, over 7029.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2607, pruned_loss=0.03058, over 1424917.77 frames.], batch size: 28, lr: 2.43e-04
+2022-04-30 12:44:27,160 INFO [train.py:763] (6/8) Epoch 31, batch 2800, loss[loss=0.139, simple_loss=0.23, pruned_loss=0.02395, over 7412.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2605, pruned_loss=0.0307, over 1423800.35 frames.], batch size: 18, lr: 2.43e-04
+2022-04-30 12:45:34,133 INFO [train.py:763] (6/8) Epoch 31, batch 2850, loss[loss=0.176, simple_loss=0.284, pruned_loss=0.03403, over 6435.00 frames.], tot_loss[loss=0.161, simple_loss=0.2604, pruned_loss=0.03075, over 1420633.16 frames.], batch size: 38, lr: 2.43e-04
+2022-04-30 12:46:39,728 INFO [train.py:763] (6/8) Epoch 31, batch 2900, loss[loss=0.1668, simple_loss=0.2654, pruned_loss=0.03413, over 7233.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2619, pruned_loss=0.03085, over 1424798.21 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:47:44,759 INFO [train.py:763] (6/8) Epoch 31, batch 2950, loss[loss=0.1514, simple_loss=0.2508, pruned_loss=0.02602, over 7205.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2626, pruned_loss=0.03093, over 1418427.11 frames.], batch size: 23, lr: 2.43e-04
+2022-04-30 12:48:50,666 INFO [train.py:763] (6/8) Epoch 31, batch 3000, loss[loss=0.1389, simple_loss=0.24, pruned_loss=0.01894, over 7420.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2625, pruned_loss=0.03096, over 1418998.04 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:48:50,667 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 12:49:05,873 INFO [train.py:792] (6/8) Epoch 31, validation: loss=0.1686, simple_loss=0.2652, pruned_loss=0.03603, over 698248.00 frames.
+2022-04-30 12:50:12,207 INFO [train.py:763] (6/8) Epoch 31, batch 3050, loss[loss=0.1781, simple_loss=0.2897, pruned_loss=0.03323, over 7326.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2626, pruned_loss=0.03103, over 1422922.26 frames.], batch size: 25, lr: 2.43e-04
+2022-04-30 12:51:18,205 INFO [train.py:763] (6/8) Epoch 31, batch 3100, loss[loss=0.1645, simple_loss=0.271, pruned_loss=0.029, over 7123.00 frames.], tot_loss[loss=0.162, simple_loss=0.2624, pruned_loss=0.0308, over 1425874.39 frames.], batch size: 28, lr: 2.42e-04
+2022-04-30 12:52:23,640 INFO [train.py:763] (6/8) Epoch 31, batch 3150, loss[loss=0.1504, simple_loss=0.235, pruned_loss=0.03295, over 7260.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2622, pruned_loss=0.03109, over 1423199.72 frames.], batch size: 17, lr: 2.42e-04
+2022-04-30 12:53:29,086 INFO [train.py:763] (6/8) Epoch 31, batch 3200, loss[loss=0.1712, simple_loss=0.2756, pruned_loss=0.03337, over 7119.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2625, pruned_loss=0.03084, over 1426187.25 frames.], batch size: 21, lr: 2.42e-04
+2022-04-30 12:54:36,193 INFO [train.py:763] (6/8) Epoch 31, batch 3250, loss[loss=0.1607, simple_loss=0.2582, pruned_loss=0.03159, over 7339.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2623, pruned_loss=0.03089, over 1427024.94 frames.], batch size: 22, lr: 2.42e-04
+2022-04-30 12:55:42,984 INFO [train.py:763] (6/8) Epoch 31, batch 3300, loss[loss=0.158, simple_loss=0.2613, pruned_loss=0.02735, over 7443.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2619, pruned_loss=0.03086, over 1423176.83 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 12:56:50,143 INFO [train.py:763] (6/8) Epoch 31, batch 3350, loss[loss=0.1827, simple_loss=0.2887, pruned_loss=0.03832, over 7328.00 frames.], tot_loss[loss=0.161, simple_loss=0.2605, pruned_loss=0.03078, over 1425224.26 frames.], batch size: 21, lr: 2.42e-04
+2022-04-30 12:57:56,833 INFO [train.py:763] (6/8) Epoch 31, batch 3400, loss[loss=0.1865, simple_loss=0.2947, pruned_loss=0.03913, over 7328.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2613, pruned_loss=0.03092, over 1422569.09 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 12:59:03,245 INFO [train.py:763] (6/8) Epoch 31, batch 3450, loss[loss=0.1722, simple_loss=0.2726, pruned_loss=0.03587, over 7204.00 frames.], tot_loss[loss=0.162, simple_loss=0.2621, pruned_loss=0.03094, over 1425620.02 frames.], batch size: 22, lr: 2.42e-04
+2022-04-30 13:00:08,923 INFO [train.py:763] (6/8) Epoch 31, batch 3500, loss[loss=0.1562, simple_loss=0.2561, pruned_loss=0.02818, over 7288.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2623, pruned_loss=0.03106, over 1428503.71 frames.], batch size: 24, lr: 2.42e-04
+2022-04-30 13:01:14,843 INFO [train.py:763] (6/8) Epoch 31, batch 3550, loss[loss=0.1804, simple_loss=0.2932, pruned_loss=0.03384, over 7380.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.03101, over 1431714.81 frames.], batch size: 23, lr: 2.42e-04
+2022-04-30 13:02:21,337 INFO [train.py:763] (6/8) Epoch 31, batch 3600, loss[loss=0.1529, simple_loss=0.2583, pruned_loss=0.02374, over 6350.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2619, pruned_loss=0.03123, over 1428600.35 frames.], batch size: 37, lr: 2.42e-04
+2022-04-30 13:03:26,537 INFO [train.py:763] (6/8) Epoch 31, batch 3650, loss[loss=0.1502, simple_loss=0.2664, pruned_loss=0.01702, over 7226.00 frames.], tot_loss[loss=0.162, simple_loss=0.2623, pruned_loss=0.03086, over 1428466.39 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 13:04:32,084 INFO [train.py:763] (6/8) Epoch 31, batch 3700, loss[loss=0.1476, simple_loss=0.241, pruned_loss=0.02715, over 7139.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03057, over 1430270.74 frames.], batch size: 17, lr: 2.42e-04
+2022-04-30 13:05:36,815 INFO [train.py:763] (6/8) Epoch 31, batch 3750, loss[loss=0.1697, simple_loss=0.2731, pruned_loss=0.03309, over 7197.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2608, pruned_loss=0.03047, over 1425302.12 frames.], batch size: 23, lr: 2.42e-04
+2022-04-30 13:06:42,587 INFO [train.py:763] (6/8) Epoch 31, batch 3800, loss[loss=0.1654, simple_loss=0.2612, pruned_loss=0.03478, over 7365.00 frames.], tot_loss[loss=0.1617, simple_loss=0.262, pruned_loss=0.03073, over 1426434.95 frames.], batch size: 23, lr: 2.42e-04
+2022-04-30 13:07:47,978 INFO [train.py:763] (6/8) Epoch 31, batch 3850, loss[loss=0.1525, simple_loss=0.2542, pruned_loss=0.02539, over 7442.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2615, pruned_loss=0.03046, over 1428207.78 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 13:08:53,258 INFO [train.py:763] (6/8) Epoch 31, batch 3900, loss[loss=0.1622, simple_loss=0.2621, pruned_loss=0.03117, over 7169.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2619, pruned_loss=0.03048, over 1429516.21 frames.], batch size: 18, lr: 2.42e-04
+2022-04-30 13:09:58,650 INFO [train.py:763] (6/8) Epoch 31, batch 3950, loss[loss=0.1744, simple_loss=0.2776, pruned_loss=0.03566, over 7209.00 frames.], tot_loss[loss=0.162, simple_loss=0.2625, pruned_loss=0.03077, over 1424215.40 frames.], batch size: 21, lr: 2.42e-04
+2022-04-30 13:11:04,249 INFO [train.py:763] (6/8) Epoch 31, batch 4000, loss[loss=0.1385, simple_loss=0.2363, pruned_loss=0.02032, over 7417.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2611, pruned_loss=0.03033, over 1422458.30 frames.], batch size: 18, lr: 2.42e-04
+2022-04-30 13:12:09,632 INFO [train.py:763] (6/8) Epoch 31, batch 4050, loss[loss=0.1918, simple_loss=0.2971, pruned_loss=0.04321, over 7397.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03035, over 1419837.83 frames.], batch size: 23, lr: 2.42e-04
+2022-04-30 13:13:15,761 INFO [train.py:763] (6/8) Epoch 31, batch 4100, loss[loss=0.1753, simple_loss=0.2736, pruned_loss=0.03848, over 7202.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2609, pruned_loss=0.03013, over 1418148.42 frames.], batch size: 22, lr: 2.42e-04
+2022-04-30 13:14:21,775 INFO [train.py:763] (6/8) Epoch 31, batch 4150, loss[loss=0.1785, simple_loss=0.286, pruned_loss=0.03552, over 7210.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2605, pruned_loss=0.02995, over 1421576.05 frames.], batch size: 21, lr: 2.42e-04
+2022-04-30 13:15:28,687 INFO [train.py:763] (6/8) Epoch 31, batch 4200, loss[loss=0.1547, simple_loss=0.2614, pruned_loss=0.02398, over 7330.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2598, pruned_loss=0.03026, over 1421549.55 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 13:16:35,574 INFO [train.py:763] (6/8) Epoch 31, batch 4250, loss[loss=0.15, simple_loss=0.248, pruned_loss=0.02598, over 7245.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2601, pruned_loss=0.03042, over 1421279.60 frames.], batch size: 19, lr: 2.42e-04
+2022-04-30 13:17:40,856 INFO [train.py:763] (6/8) Epoch 31, batch 4300, loss[loss=0.1224, simple_loss=0.21, pruned_loss=0.01743, over 7409.00 frames.], tot_loss[loss=0.16, simple_loss=0.2594, pruned_loss=0.03031, over 1421273.75 frames.], batch size: 18, lr: 2.42e-04
+2022-04-30 13:18:46,143 INFO [train.py:763] (6/8) Epoch 31, batch 4350, loss[loss=0.1522, simple_loss=0.2587, pruned_loss=0.02282, over 7174.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2604, pruned_loss=0.03051, over 1421205.75 frames.], batch size: 18, lr: 2.41e-04
+2022-04-30 13:19:51,343 INFO [train.py:763] (6/8) Epoch 31, batch 4400, loss[loss=0.1713, simple_loss=0.282, pruned_loss=0.03026, over 7289.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2608, pruned_loss=0.03046, over 1408136.41 frames.], batch size: 25, lr: 2.41e-04
+2022-04-30 13:20:57,006 INFO [train.py:763] (6/8) Epoch 31, batch 4450, loss[loss=0.146, simple_loss=0.2434, pruned_loss=0.02434, over 6755.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2618, pruned_loss=0.03117, over 1404977.83 frames.], batch size: 15, lr: 2.41e-04
+2022-04-30 13:22:02,214 INFO [train.py:763] (6/8) Epoch 31, batch 4500, loss[loss=0.1927, simple_loss=0.2868, pruned_loss=0.04929, over 6812.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2624, pruned_loss=0.03137, over 1396924.05 frames.], batch size: 31, lr: 2.41e-04
+2022-04-30 13:23:07,078 INFO [train.py:763] (6/8) Epoch 31, batch 4550, loss[loss=0.1652, simple_loss=0.2686, pruned_loss=0.03091, over 4976.00 frames.], tot_loss[loss=0.1626, simple_loss=0.262, pruned_loss=0.03158, over 1358903.04 frames.], batch size: 53, lr: 2.41e-04
+2022-04-30 13:24:35,149 INFO [train.py:763] (6/8) Epoch 32, batch 0, loss[loss=0.1651, simple_loss=0.2636, pruned_loss=0.03333, over 6831.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2636, pruned_loss=0.03333, over 6831.00 frames.], batch size: 31, lr: 2.38e-04
+2022-04-30 13:25:38,923 INFO [train.py:763] (6/8) Epoch 32, batch 50, loss[loss=0.2012, simple_loss=0.3017, pruned_loss=0.05042, over 5101.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2624, pruned_loss=0.03051, over 314714.02 frames.], batch size: 52, lr: 2.38e-04
+2022-04-30 13:26:41,320 INFO [train.py:763] (6/8) Epoch 32, batch 100, loss[loss=0.1638, simple_loss=0.2661, pruned_loss=0.03074, over 6458.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2627, pruned_loss=0.03079, over 560159.46 frames.], batch size: 38, lr: 2.38e-04
+2022-04-30 13:27:47,092 INFO [train.py:763] (6/8) Epoch 32, batch 150, loss[loss=0.1652, simple_loss=0.2734, pruned_loss=0.02846, over 7199.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2633, pruned_loss=0.03079, over 752579.24 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:28:52,460 INFO [train.py:763] (6/8) Epoch 32, batch 200, loss[loss=0.1385, simple_loss=0.2314, pruned_loss=0.0228, over 7025.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2626, pruned_loss=0.03053, over 896162.79 frames.], batch size: 16, lr: 2.37e-04
+2022-04-30 13:29:57,593 INFO [train.py:763] (6/8) Epoch 32, batch 250, loss[loss=0.1334, simple_loss=0.2348, pruned_loss=0.016, over 7237.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2627, pruned_loss=0.03049, over 1011011.70 frames.], batch size: 20, lr: 2.37e-04
+2022-04-30 13:31:03,088 INFO [train.py:763] (6/8) Epoch 32, batch 300, loss[loss=0.1457, simple_loss=0.2529, pruned_loss=0.01924, over 6818.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2617, pruned_loss=0.03047, over 1094866.42 frames.], batch size: 31, lr: 2.37e-04
+2022-04-30 13:32:10,107 INFO [train.py:763] (6/8) Epoch 32, batch 350, loss[loss=0.1287, simple_loss=0.2205, pruned_loss=0.01846, over 7399.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2613, pruned_loss=0.03065, over 1164998.62 frames.], batch size: 18, lr: 2.37e-04
+2022-04-30 13:33:15,978 INFO [train.py:763] (6/8) Epoch 32, batch 400, loss[loss=0.1731, simple_loss=0.2644, pruned_loss=0.0409, over 7429.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2608, pruned_loss=0.03072, over 1222638.56 frames.], batch size: 20, lr: 2.37e-04
+2022-04-30 13:34:21,565 INFO [train.py:763] (6/8) Epoch 32, batch 450, loss[loss=0.1727, simple_loss=0.2799, pruned_loss=0.03273, over 6722.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2604, pruned_loss=0.03073, over 1264063.51 frames.], batch size: 31, lr: 2.37e-04
+2022-04-30 13:35:26,874 INFO [train.py:763] (6/8) Epoch 32, batch 500, loss[loss=0.1827, simple_loss=0.2819, pruned_loss=0.04173, over 7205.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2612, pruned_loss=0.03091, over 1302147.11 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:36:32,827 INFO [train.py:763] (6/8) Epoch 32, batch 550, loss[loss=0.1725, simple_loss=0.2746, pruned_loss=0.03518, over 7321.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2621, pruned_loss=0.03082, over 1330383.35 frames.], batch size: 21, lr: 2.37e-04
+2022-04-30 13:37:38,143 INFO [train.py:763] (6/8) Epoch 32, batch 600, loss[loss=0.1601, simple_loss=0.2701, pruned_loss=0.02504, over 7276.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2622, pruned_loss=0.03077, over 1348513.84 frames.], batch size: 24, lr: 2.37e-04
+2022-04-30 13:38:43,402 INFO [train.py:763] (6/8) Epoch 32, batch 650, loss[loss=0.1663, simple_loss=0.2686, pruned_loss=0.03196, over 7208.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2629, pruned_loss=0.03095, over 1365465.76 frames.], batch size: 26, lr: 2.37e-04
+2022-04-30 13:39:48,620 INFO [train.py:763] (6/8) Epoch 32, batch 700, loss[loss=0.1415, simple_loss=0.2199, pruned_loss=0.03153, over 7135.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2632, pruned_loss=0.03129, over 1375724.80 frames.], batch size: 17, lr: 2.37e-04
+2022-04-30 13:40:55,114 INFO [train.py:763] (6/8) Epoch 32, batch 750, loss[loss=0.1639, simple_loss=0.2661, pruned_loss=0.03085, over 7213.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2639, pruned_loss=0.03147, over 1381387.17 frames.], batch size: 21, lr: 2.37e-04
+2022-04-30 13:42:02,294 INFO [train.py:763] (6/8) Epoch 32, batch 800, loss[loss=0.1806, simple_loss=0.2765, pruned_loss=0.04234, over 7427.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2625, pruned_loss=0.03138, over 1393876.66 frames.], batch size: 20, lr: 2.37e-04
+2022-04-30 13:43:08,542 INFO [train.py:763] (6/8) Epoch 32, batch 850, loss[loss=0.1631, simple_loss=0.275, pruned_loss=0.02564, over 7382.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2625, pruned_loss=0.03107, over 1401501.58 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:44:14,305 INFO [train.py:763] (6/8) Epoch 32, batch 900, loss[loss=0.1693, simple_loss=0.2729, pruned_loss=0.03288, over 7210.00 frames.], tot_loss[loss=0.1609, simple_loss=0.261, pruned_loss=0.03046, over 1411407.40 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:45:21,095 INFO [train.py:763] (6/8) Epoch 32, batch 950, loss[loss=0.1492, simple_loss=0.262, pruned_loss=0.01825, over 7431.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03077, over 1415758.89 frames.], batch size: 20, lr: 2.37e-04
+2022-04-30 13:46:27,403 INFO [train.py:763] (6/8) Epoch 32, batch 1000, loss[loss=0.168, simple_loss=0.2666, pruned_loss=0.03469, over 7210.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03065, over 1414930.30 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:47:33,313 INFO [train.py:763] (6/8) Epoch 32, batch 1050, loss[loss=0.1777, simple_loss=0.2955, pruned_loss=0.02992, over 7033.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2609, pruned_loss=0.03043, over 1413894.91 frames.], batch size: 28, lr: 2.37e-04
+2022-04-30 13:48:38,619 INFO [train.py:763] (6/8) Epoch 32, batch 1100, loss[loss=0.1709, simple_loss=0.2778, pruned_loss=0.03201, over 7271.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2614, pruned_loss=0.0306, over 1419147.99 frames.], batch size: 24, lr: 2.37e-04
+2022-04-30 13:49:45,242 INFO [train.py:763] (6/8) Epoch 32, batch 1150, loss[loss=0.1891, simple_loss=0.2895, pruned_loss=0.04435, over 7199.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2608, pruned_loss=0.03004, over 1419857.42 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:50:50,722 INFO [train.py:763] (6/8) Epoch 32, batch 1200, loss[loss=0.1812, simple_loss=0.2802, pruned_loss=0.04111, over 7186.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2617, pruned_loss=0.03037, over 1422501.35 frames.], batch size: 26, lr: 2.37e-04
+2022-04-30 13:51:56,749 INFO [train.py:763] (6/8) Epoch 32, batch 1250, loss[loss=0.1521, simple_loss=0.2601, pruned_loss=0.02203, over 6277.00 frames.], tot_loss[loss=0.1618, simple_loss=0.262, pruned_loss=0.03077, over 1421245.04 frames.], batch size: 37, lr: 2.37e-04
+2022-04-30 13:53:02,502 INFO [train.py:763] (6/8) Epoch 32, batch 1300, loss[loss=0.1568, simple_loss=0.2583, pruned_loss=0.02768, over 7220.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2615, pruned_loss=0.03048, over 1421635.05 frames.], batch size: 21, lr: 2.37e-04
+2022-04-30 13:54:10,200 INFO [train.py:763] (6/8) Epoch 32, batch 1350, loss[loss=0.1519, simple_loss=0.2408, pruned_loss=0.03147, over 7274.00 frames.], tot_loss[loss=0.161, simple_loss=0.2611, pruned_loss=0.03049, over 1420428.93 frames.], batch size: 17, lr: 2.37e-04
+2022-04-30 13:55:17,151 INFO [train.py:763] (6/8) Epoch 32, batch 1400, loss[loss=0.1544, simple_loss=0.2594, pruned_loss=0.02469, over 7144.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2608, pruned_loss=0.03029, over 1422753.44 frames.], batch size: 20, lr: 2.36e-04
+2022-04-30 13:56:22,420 INFO [train.py:763] (6/8) Epoch 32, batch 1450, loss[loss=0.1526, simple_loss=0.2584, pruned_loss=0.02336, over 6870.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2611, pruned_loss=0.03016, over 1425351.78 frames.], batch size: 31, lr: 2.36e-04
+2022-04-30 13:57:27,827 INFO [train.py:763] (6/8) Epoch 32, batch 1500, loss[loss=0.1803, simple_loss=0.2691, pruned_loss=0.0458, over 4857.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2611, pruned_loss=0.03032, over 1422432.94 frames.], batch size: 52, lr: 2.36e-04
+2022-04-30 13:58:33,079 INFO [train.py:763] (6/8) Epoch 32, batch 1550, loss[loss=0.153, simple_loss=0.2577, pruned_loss=0.0241, over 7211.00 frames.], tot_loss[loss=0.161, simple_loss=0.2612, pruned_loss=0.03036, over 1418542.51 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 13:59:38,327 INFO [train.py:763] (6/8) Epoch 32, batch 1600, loss[loss=0.1759, simple_loss=0.2775, pruned_loss=0.03714, over 7418.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2616, pruned_loss=0.03063, over 1419808.71 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 14:00:43,687 INFO [train.py:763] (6/8) Epoch 32, batch 1650, loss[loss=0.1524, simple_loss=0.2596, pruned_loss=0.0226, over 7223.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2615, pruned_loss=0.03078, over 1420463.48 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 14:01:48,789 INFO [train.py:763] (6/8) Epoch 32, batch 1700, loss[loss=0.1691, simple_loss=0.2838, pruned_loss=0.02724, over 7281.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2616, pruned_loss=0.03055, over 1422956.50 frames.], batch size: 24, lr: 2.36e-04
+2022-04-30 14:02:54,186 INFO [train.py:763] (6/8) Epoch 32, batch 1750, loss[loss=0.1919, simple_loss=0.2911, pruned_loss=0.04632, over 7066.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2624, pruned_loss=0.03066, over 1416002.95 frames.], batch size: 28, lr: 2.36e-04
+2022-04-30 14:03:59,641 INFO [train.py:763] (6/8) Epoch 32, batch 1800, loss[loss=0.1378, simple_loss=0.234, pruned_loss=0.02076, over 7259.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2625, pruned_loss=0.03064, over 1419259.30 frames.], batch size: 19, lr: 2.36e-04
+2022-04-30 14:05:06,116 INFO [train.py:763] (6/8) Epoch 32, batch 1850, loss[loss=0.1647, simple_loss=0.2645, pruned_loss=0.03248, over 7322.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2627, pruned_loss=0.03043, over 1422334.48 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 14:06:21,243 INFO [train.py:763] (6/8) Epoch 32, batch 1900, loss[loss=0.1801, simple_loss=0.2765, pruned_loss=0.04187, over 7387.00 frames.], tot_loss[loss=0.1613, simple_loss=0.262, pruned_loss=0.03028, over 1424945.82 frames.], batch size: 23, lr: 2.36e-04
+2022-04-30 14:07:26,710 INFO [train.py:763] (6/8) Epoch 32, batch 1950, loss[loss=0.1479, simple_loss=0.2592, pruned_loss=0.01832, over 7314.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2612, pruned_loss=0.03005, over 1423841.83 frames.], batch size: 24, lr: 2.36e-04
+2022-04-30 14:08:33,679 INFO [train.py:763] (6/8) Epoch 32, batch 2000, loss[loss=0.1688, simple_loss=0.2673, pruned_loss=0.03515, over 6341.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2607, pruned_loss=0.02991, over 1424939.19 frames.], batch size: 37, lr: 2.36e-04
+2022-04-30 14:09:39,828 INFO [train.py:763] (6/8) Epoch 32, batch 2050, loss[loss=0.1644, simple_loss=0.2644, pruned_loss=0.03219, over 7159.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2607, pruned_loss=0.02984, over 1425361.11 frames.], batch size: 18, lr: 2.36e-04
+2022-04-30 14:10:45,532 INFO [train.py:763] (6/8) Epoch 32, batch 2100, loss[loss=0.1737, simple_loss=0.2719, pruned_loss=0.03776, over 7179.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.0302, over 1426809.86 frames.], batch size: 19, lr: 2.36e-04
+2022-04-30 14:11:52,556 INFO [train.py:763] (6/8) Epoch 32, batch 2150, loss[loss=0.1292, simple_loss=0.2217, pruned_loss=0.01834, over 7408.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03005, over 1427137.97 frames.], batch size: 18, lr: 2.36e-04
+2022-04-30 14:12:58,735 INFO [train.py:763] (6/8) Epoch 32, batch 2200, loss[loss=0.1883, simple_loss=0.2923, pruned_loss=0.04209, over 5140.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2604, pruned_loss=0.03017, over 1422356.15 frames.], batch size: 52, lr: 2.36e-04
+2022-04-30 14:14:05,702 INFO [train.py:763] (6/8) Epoch 32, batch 2250, loss[loss=0.1653, simple_loss=0.2618, pruned_loss=0.03443, over 7210.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2607, pruned_loss=0.03088, over 1420354.82 frames.], batch size: 26, lr: 2.36e-04
+2022-04-30 14:15:12,725 INFO [train.py:763] (6/8) Epoch 32, batch 2300, loss[loss=0.1708, simple_loss=0.2653, pruned_loss=0.03811, over 7216.00 frames.], tot_loss[loss=0.1609, simple_loss=0.26, pruned_loss=0.03087, over 1419471.48 frames.], batch size: 22, lr: 2.36e-04
+2022-04-30 14:16:18,552 INFO [train.py:763] (6/8) Epoch 32, batch 2350, loss[loss=0.1595, simple_loss=0.2487, pruned_loss=0.03517, over 7273.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2594, pruned_loss=0.03049, over 1422629.35 frames.], batch size: 16, lr: 2.36e-04
+2022-04-30 14:17:25,998 INFO [train.py:763] (6/8) Epoch 32, batch 2400, loss[loss=0.1542, simple_loss=0.262, pruned_loss=0.02324, over 7428.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2591, pruned_loss=0.03025, over 1425354.67 frames.], batch size: 20, lr: 2.36e-04
+2022-04-30 14:18:32,878 INFO [train.py:763] (6/8) Epoch 32, batch 2450, loss[loss=0.1549, simple_loss=0.2586, pruned_loss=0.02566, over 7263.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2591, pruned_loss=0.03014, over 1427148.57 frames.], batch size: 19, lr: 2.36e-04
+2022-04-30 14:19:38,455 INFO [train.py:763] (6/8) Epoch 32, batch 2500, loss[loss=0.1771, simple_loss=0.2822, pruned_loss=0.03596, over 7322.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2593, pruned_loss=0.03013, over 1428837.80 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 14:20:45,070 INFO [train.py:763] (6/8) Epoch 32, batch 2550, loss[loss=0.1824, simple_loss=0.2744, pruned_loss=0.04518, over 7378.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2586, pruned_loss=0.03022, over 1427467.23 frames.], batch size: 23, lr: 2.36e-04
+2022-04-30 14:21:59,923 INFO [train.py:763] (6/8) Epoch 32, batch 2600, loss[loss=0.1761, simple_loss=0.2793, pruned_loss=0.03645, over 7204.00 frames.], tot_loss[loss=0.1598, simple_loss=0.259, pruned_loss=0.03027, over 1427160.77 frames.], batch size: 23, lr: 2.36e-04
+2022-04-30 14:23:23,011 INFO [train.py:763] (6/8) Epoch 32, batch 2650, loss[loss=0.142, simple_loss=0.2287, pruned_loss=0.02758, over 7214.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2595, pruned_loss=0.03072, over 1422653.54 frames.], batch size: 16, lr: 2.35e-04
+2022-04-30 14:24:36,941 INFO [train.py:763] (6/8) Epoch 32, batch 2700, loss[loss=0.1486, simple_loss=0.2418, pruned_loss=0.02767, over 7435.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2602, pruned_loss=0.0311, over 1424714.01 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:25:51,354 INFO [train.py:763] (6/8) Epoch 32, batch 2750, loss[loss=0.1609, simple_loss=0.2596, pruned_loss=0.03109, over 7269.00 frames.], tot_loss[loss=0.161, simple_loss=0.2605, pruned_loss=0.03077, over 1425437.83 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:26:57,661 INFO [train.py:763] (6/8) Epoch 32, batch 2800, loss[loss=0.1812, simple_loss=0.2899, pruned_loss=0.03623, over 7184.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2596, pruned_loss=0.03056, over 1424670.37 frames.], batch size: 23, lr: 2.35e-04
+2022-04-30 14:28:12,044 INFO [train.py:763] (6/8) Epoch 32, batch 2850, loss[loss=0.1583, simple_loss=0.2643, pruned_loss=0.02616, over 7311.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2589, pruned_loss=0.03009, over 1426213.58 frames.], batch size: 21, lr: 2.35e-04
+2022-04-30 14:29:27,083 INFO [train.py:763] (6/8) Epoch 32, batch 2900, loss[loss=0.1659, simple_loss=0.2713, pruned_loss=0.03022, over 7276.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2595, pruned_loss=0.03017, over 1425351.98 frames.], batch size: 25, lr: 2.35e-04
+2022-04-30 14:30:33,974 INFO [train.py:763] (6/8) Epoch 32, batch 2950, loss[loss=0.1509, simple_loss=0.2572, pruned_loss=0.02237, over 7423.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2603, pruned_loss=0.03009, over 1427408.85 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:31:40,120 INFO [train.py:763] (6/8) Epoch 32, batch 3000, loss[loss=0.1586, simple_loss=0.2509, pruned_loss=0.03317, over 7058.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2601, pruned_loss=0.03004, over 1426159.29 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:31:40,121 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 14:31:55,319 INFO [train.py:792] (6/8) Epoch 32, validation: loss=0.1696, simple_loss=0.2645, pruned_loss=0.0374, over 698248.00 frames.
+2022-04-30 14:33:01,804 INFO [train.py:763] (6/8) Epoch 32, batch 3050, loss[loss=0.1629, simple_loss=0.2757, pruned_loss=0.02507, over 6412.00 frames.], tot_loss[loss=0.16, simple_loss=0.2597, pruned_loss=0.03015, over 1422932.31 frames.], batch size: 38, lr: 2.35e-04
+2022-04-30 14:34:07,507 INFO [train.py:763] (6/8) Epoch 32, batch 3100, loss[loss=0.1596, simple_loss=0.2662, pruned_loss=0.02651, over 7372.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2602, pruned_loss=0.0301, over 1424189.30 frames.], batch size: 23, lr: 2.35e-04
+2022-04-30 14:35:13,885 INFO [train.py:763] (6/8) Epoch 32, batch 3150, loss[loss=0.1366, simple_loss=0.2305, pruned_loss=0.02135, over 7065.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2594, pruned_loss=0.02986, over 1422412.38 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:36:20,358 INFO [train.py:763] (6/8) Epoch 32, batch 3200, loss[loss=0.1636, simple_loss=0.2553, pruned_loss=0.03597, over 7180.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03007, over 1422959.67 frames.], batch size: 16, lr: 2.35e-04
+2022-04-30 14:37:25,786 INFO [train.py:763] (6/8) Epoch 32, batch 3250, loss[loss=0.1518, simple_loss=0.2516, pruned_loss=0.02602, over 7267.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2604, pruned_loss=0.0301, over 1420775.47 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:38:31,357 INFO [train.py:763] (6/8) Epoch 32, batch 3300, loss[loss=0.1836, simple_loss=0.284, pruned_loss=0.04158, over 7231.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2592, pruned_loss=0.0298, over 1425537.31 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:39:37,090 INFO [train.py:763] (6/8) Epoch 32, batch 3350, loss[loss=0.1484, simple_loss=0.2522, pruned_loss=0.02229, over 7317.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2593, pruned_loss=0.02967, over 1428690.81 frames.], batch size: 21, lr: 2.35e-04
+2022-04-30 14:40:43,416 INFO [train.py:763] (6/8) Epoch 32, batch 3400, loss[loss=0.1472, simple_loss=0.232, pruned_loss=0.03122, over 7277.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2593, pruned_loss=0.0298, over 1428321.93 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:41:50,121 INFO [train.py:763] (6/8) Epoch 32, batch 3450, loss[loss=0.1633, simple_loss=0.2671, pruned_loss=0.02979, over 7328.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2597, pruned_loss=0.03002, over 1431872.95 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:42:56,324 INFO [train.py:763] (6/8) Epoch 32, batch 3500, loss[loss=0.153, simple_loss=0.2511, pruned_loss=0.02743, over 7376.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03038, over 1428012.86 frames.], batch size: 23, lr: 2.35e-04
+2022-04-30 14:44:01,646 INFO [train.py:763] (6/8) Epoch 32, batch 3550, loss[loss=0.1527, simple_loss=0.234, pruned_loss=0.03565, over 7415.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2598, pruned_loss=0.03027, over 1426970.75 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:45:06,994 INFO [train.py:763] (6/8) Epoch 32, batch 3600, loss[loss=0.1471, simple_loss=0.2518, pruned_loss=0.02125, over 7329.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2598, pruned_loss=0.03033, over 1424244.47 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:46:12,677 INFO [train.py:763] (6/8) Epoch 32, batch 3650, loss[loss=0.1517, simple_loss=0.2489, pruned_loss=0.02725, over 7327.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2589, pruned_loss=0.02999, over 1423735.72 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:47:18,402 INFO [train.py:763] (6/8) Epoch 32, batch 3700, loss[loss=0.143, simple_loss=0.2263, pruned_loss=0.02983, over 7273.00 frames.], tot_loss[loss=0.16, simple_loss=0.2599, pruned_loss=0.03, over 1427291.49 frames.], batch size: 17, lr: 2.35e-04
+2022-04-30 14:48:25,079 INFO [train.py:763] (6/8) Epoch 32, batch 3750, loss[loss=0.1663, simple_loss=0.2625, pruned_loss=0.03509, over 7216.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03032, over 1426897.17 frames.], batch size: 21, lr: 2.35e-04
+2022-04-30 14:49:30,591 INFO [train.py:763] (6/8) Epoch 32, batch 3800, loss[loss=0.1722, simple_loss=0.282, pruned_loss=0.03115, over 7207.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03042, over 1427930.77 frames.], batch size: 23, lr: 2.35e-04
+2022-04-30 14:50:35,840 INFO [train.py:763] (6/8) Epoch 32, batch 3850, loss[loss=0.1613, simple_loss=0.2646, pruned_loss=0.02898, over 7324.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2603, pruned_loss=0.03026, over 1428214.61 frames.], batch size: 21, lr: 2.35e-04
+2022-04-30 14:51:41,192 INFO [train.py:763] (6/8) Epoch 32, batch 3900, loss[loss=0.1462, simple_loss=0.2355, pruned_loss=0.02851, over 6809.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2619, pruned_loss=0.03071, over 1428341.60 frames.], batch size: 15, lr: 2.35e-04
+2022-04-30 14:52:46,610 INFO [train.py:763] (6/8) Epoch 32, batch 3950, loss[loss=0.1477, simple_loss=0.2418, pruned_loss=0.02677, over 7406.00 frames.], tot_loss[loss=0.162, simple_loss=0.2626, pruned_loss=0.03068, over 1430808.84 frames.], batch size: 18, lr: 2.34e-04
+2022-04-30 14:53:52,266 INFO [train.py:763] (6/8) Epoch 32, batch 4000, loss[loss=0.174, simple_loss=0.281, pruned_loss=0.03352, over 6276.00 frames.], tot_loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.03059, over 1430866.76 frames.], batch size: 37, lr: 2.34e-04
+2022-04-30 14:54:57,659 INFO [train.py:763] (6/8) Epoch 32, batch 4050, loss[loss=0.1526, simple_loss=0.2537, pruned_loss=0.02577, over 7272.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.03117, over 1427513.90 frames.], batch size: 18, lr: 2.34e-04
+2022-04-30 14:56:02,794 INFO [train.py:763] (6/8) Epoch 32, batch 4100, loss[loss=0.1617, simple_loss=0.2711, pruned_loss=0.02612, over 7198.00 frames.], tot_loss[loss=0.161, simple_loss=0.2606, pruned_loss=0.0307, over 1422257.22 frames.], batch size: 26, lr: 2.34e-04
+2022-04-30 14:57:08,461 INFO [train.py:763] (6/8) Epoch 32, batch 4150, loss[loss=0.1344, simple_loss=0.2191, pruned_loss=0.02484, over 7271.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2603, pruned_loss=0.03047, over 1422410.56 frames.], batch size: 16, lr: 2.34e-04
+2022-04-30 14:58:14,266 INFO [train.py:763] (6/8) Epoch 32, batch 4200, loss[loss=0.1495, simple_loss=0.2484, pruned_loss=0.02527, over 7257.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2601, pruned_loss=0.0301, over 1421548.85 frames.], batch size: 19, lr: 2.34e-04
+2022-04-30 14:59:19,681 INFO [train.py:763] (6/8) Epoch 32, batch 4250, loss[loss=0.1454, simple_loss=0.2491, pruned_loss=0.02085, over 7419.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03, over 1421153.14 frames.], batch size: 20, lr: 2.34e-04
+2022-04-30 15:00:26,352 INFO [train.py:763] (6/8) Epoch 32, batch 4300, loss[loss=0.1642, simple_loss=0.2738, pruned_loss=0.02734, over 6740.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2606, pruned_loss=0.03028, over 1419606.40 frames.], batch size: 31, lr: 2.34e-04
+2022-04-30 15:01:32,994 INFO [train.py:763] (6/8) Epoch 32, batch 4350, loss[loss=0.1533, simple_loss=0.2567, pruned_loss=0.02493, over 7227.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2595, pruned_loss=0.03001, over 1416427.68 frames.], batch size: 21, lr: 2.34e-04
+2022-04-30 15:02:38,278 INFO [train.py:763] (6/8) Epoch 32, batch 4400, loss[loss=0.1594, simple_loss=0.2713, pruned_loss=0.02371, over 7141.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2593, pruned_loss=0.02985, over 1414669.16 frames.], batch size: 20, lr: 2.34e-04
+2022-04-30 15:03:43,365 INFO [train.py:763] (6/8) Epoch 32, batch 4450, loss[loss=0.1707, simple_loss=0.2738, pruned_loss=0.03377, over 7321.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2599, pruned_loss=0.02985, over 1406773.68 frames.], batch size: 22, lr: 2.34e-04
+2022-04-30 15:04:48,247 INFO [train.py:763] (6/8) Epoch 32, batch 4500, loss[loss=0.1566, simple_loss=0.2668, pruned_loss=0.02316, over 7149.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2602, pruned_loss=0.02984, over 1395870.77 frames.], batch size: 20, lr: 2.34e-04
+2022-04-30 15:05:53,073 INFO [train.py:763] (6/8) Epoch 32, batch 4550, loss[loss=0.2002, simple_loss=0.2892, pruned_loss=0.05561, over 5229.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2608, pruned_loss=0.03012, over 1374694.55 frames.], batch size: 52, lr: 2.34e-04
+2022-04-30 15:07:21,085 INFO [train.py:763] (6/8) Epoch 33, batch 0, loss[loss=0.1662, simple_loss=0.2656, pruned_loss=0.03333, over 7418.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2656, pruned_loss=0.03333, over 7418.00 frames.], batch size: 20, lr: 2.31e-04
+2022-04-30 15:08:26,674 INFO [train.py:763] (6/8) Epoch 33, batch 50, loss[loss=0.1595, simple_loss=0.2623, pruned_loss=0.02839, over 7121.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2557, pruned_loss=0.02956, over 324405.69 frames.], batch size: 28, lr: 2.30e-04
+2022-04-30 15:09:31,882 INFO [train.py:763] (6/8) Epoch 33, batch 100, loss[loss=0.1513, simple_loss=0.2565, pruned_loss=0.02309, over 7122.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2583, pruned_loss=0.02962, over 565417.97 frames.], batch size: 21, lr: 2.30e-04
+2022-04-30 15:10:37,375 INFO [train.py:763] (6/8) Epoch 33, batch 150, loss[loss=0.1612, simple_loss=0.2548, pruned_loss=0.03381, over 7061.00 frames.], tot_loss[loss=0.1588, simple_loss=0.258, pruned_loss=0.02976, over 755275.28 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:11:42,899 INFO [train.py:763] (6/8) Epoch 33, batch 200, loss[loss=0.1554, simple_loss=0.2493, pruned_loss=0.03079, over 7270.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2578, pruned_loss=0.02953, over 905192.66 frames.], batch size: 17, lr: 2.30e-04
+2022-04-30 15:12:48,575 INFO [train.py:763] (6/8) Epoch 33, batch 250, loss[loss=0.1771, simple_loss=0.2755, pruned_loss=0.03929, over 4792.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2581, pruned_loss=0.02957, over 1011036.74 frames.], batch size: 52, lr: 2.30e-04
+2022-04-30 15:13:55,819 INFO [train.py:763] (6/8) Epoch 33, batch 300, loss[loss=0.1807, simple_loss=0.2797, pruned_loss=0.04091, over 7384.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2587, pruned_loss=0.02939, over 1101909.20 frames.], batch size: 23, lr: 2.30e-04
+2022-04-30 15:15:01,948 INFO [train.py:763] (6/8) Epoch 33, batch 350, loss[loss=0.1393, simple_loss=0.2335, pruned_loss=0.02254, over 7137.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03068, over 1167266.61 frames.], batch size: 17, lr: 2.30e-04
+2022-04-30 15:16:08,933 INFO [train.py:763] (6/8) Epoch 33, batch 400, loss[loss=0.1697, simple_loss=0.2766, pruned_loss=0.03137, over 7422.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2601, pruned_loss=0.03026, over 1227954.01 frames.], batch size: 21, lr: 2.30e-04
+2022-04-30 15:17:14,699 INFO [train.py:763] (6/8) Epoch 33, batch 450, loss[loss=0.1525, simple_loss=0.2472, pruned_loss=0.02887, over 7400.00 frames.], tot_loss[loss=0.16, simple_loss=0.2601, pruned_loss=0.02998, over 1272782.47 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:18:21,053 INFO [train.py:763] (6/8) Epoch 33, batch 500, loss[loss=0.1623, simple_loss=0.2678, pruned_loss=0.02839, over 7303.00 frames.], tot_loss[loss=0.16, simple_loss=0.2604, pruned_loss=0.02981, over 1305505.87 frames.], batch size: 24, lr: 2.30e-04
+2022-04-30 15:19:26,293 INFO [train.py:763] (6/8) Epoch 33, batch 550, loss[loss=0.1682, simple_loss=0.2738, pruned_loss=0.03127, over 6325.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2608, pruned_loss=0.03006, over 1329055.91 frames.], batch size: 37, lr: 2.30e-04
+2022-04-30 15:20:43,086 INFO [train.py:763] (6/8) Epoch 33, batch 600, loss[loss=0.1789, simple_loss=0.2834, pruned_loss=0.03721, over 7316.00 frames.], tot_loss[loss=0.1604, simple_loss=0.261, pruned_loss=0.02991, over 1351594.53 frames.], batch size: 25, lr: 2.30e-04
+2022-04-30 15:21:48,337 INFO [train.py:763] (6/8) Epoch 33, batch 650, loss[loss=0.1373, simple_loss=0.2296, pruned_loss=0.02246, over 7158.00 frames.], tot_loss[loss=0.16, simple_loss=0.2605, pruned_loss=0.0298, over 1369781.96 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:22:53,613 INFO [train.py:763] (6/8) Epoch 33, batch 700, loss[loss=0.1511, simple_loss=0.2381, pruned_loss=0.03202, over 7140.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2594, pruned_loss=0.0297, over 1377555.31 frames.], batch size: 17, lr: 2.30e-04
+2022-04-30 15:23:58,785 INFO [train.py:763] (6/8) Epoch 33, batch 750, loss[loss=0.1628, simple_loss=0.2664, pruned_loss=0.02956, over 7201.00 frames.], tot_loss[loss=0.1599, simple_loss=0.26, pruned_loss=0.02993, over 1388778.20 frames.], batch size: 23, lr: 2.30e-04
+2022-04-30 15:25:05,622 INFO [train.py:763] (6/8) Epoch 33, batch 800, loss[loss=0.1383, simple_loss=0.2239, pruned_loss=0.02633, over 7260.00 frames.], tot_loss[loss=0.1599, simple_loss=0.26, pruned_loss=0.02986, over 1394794.14 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:26:11,925 INFO [train.py:763] (6/8) Epoch 33, batch 850, loss[loss=0.1587, simple_loss=0.2744, pruned_loss=0.02151, over 6535.00 frames.], tot_loss[loss=0.16, simple_loss=0.2601, pruned_loss=0.02993, over 1404980.25 frames.], batch size: 38, lr: 2.30e-04
+2022-04-30 15:27:17,421 INFO [train.py:763] (6/8) Epoch 33, batch 900, loss[loss=0.1872, simple_loss=0.2809, pruned_loss=0.04671, over 5128.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2598, pruned_loss=0.03004, over 1409791.34 frames.], batch size: 52, lr: 2.30e-04
+2022-04-30 15:28:22,825 INFO [train.py:763] (6/8) Epoch 33, batch 950, loss[loss=0.1769, simple_loss=0.2706, pruned_loss=0.0416, over 7279.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2599, pruned_loss=0.03029, over 1408779.41 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:29:28,255 INFO [train.py:763] (6/8) Epoch 33, batch 1000, loss[loss=0.1454, simple_loss=0.2458, pruned_loss=0.02254, over 7428.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2596, pruned_loss=0.03046, over 1409959.96 frames.], batch size: 20, lr: 2.30e-04
+2022-04-30 15:30:33,672 INFO [train.py:763] (6/8) Epoch 33, batch 1050, loss[loss=0.1469, simple_loss=0.2531, pruned_loss=0.02028, over 7174.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2595, pruned_loss=0.03019, over 1415501.72 frames.], batch size: 19, lr: 2.30e-04
+2022-04-30 15:31:40,472 INFO [train.py:763] (6/8) Epoch 33, batch 1100, loss[loss=0.1575, simple_loss=0.2756, pruned_loss=0.01977, over 6277.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2601, pruned_loss=0.03015, over 1413821.94 frames.], batch size: 38, lr: 2.30e-04
+2022-04-30 15:32:45,928 INFO [train.py:763] (6/8) Epoch 33, batch 1150, loss[loss=0.1632, simple_loss=0.2567, pruned_loss=0.03491, over 7438.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2593, pruned_loss=0.03015, over 1416033.50 frames.], batch size: 20, lr: 2.30e-04
+2022-04-30 15:33:51,344 INFO [train.py:763] (6/8) Epoch 33, batch 1200, loss[loss=0.1891, simple_loss=0.2905, pruned_loss=0.04384, over 7218.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2595, pruned_loss=0.03033, over 1420290.47 frames.], batch size: 23, lr: 2.30e-04
+2022-04-30 15:34:56,638 INFO [train.py:763] (6/8) Epoch 33, batch 1250, loss[loss=0.1516, simple_loss=0.2564, pruned_loss=0.0234, over 7322.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2594, pruned_loss=0.03038, over 1418105.78 frames.], batch size: 22, lr: 2.30e-04
+2022-04-30 15:36:02,656 INFO [train.py:763] (6/8) Epoch 33, batch 1300, loss[loss=0.1553, simple_loss=0.2612, pruned_loss=0.02466, over 7234.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2593, pruned_loss=0.03057, over 1417954.69 frames.], batch size: 26, lr: 2.30e-04
+2022-04-30 15:37:09,803 INFO [train.py:763] (6/8) Epoch 33, batch 1350, loss[loss=0.1398, simple_loss=0.2478, pruned_loss=0.01586, over 7215.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2589, pruned_loss=0.03041, over 1418629.98 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 15:38:16,865 INFO [train.py:763] (6/8) Epoch 33, batch 1400, loss[loss=0.1559, simple_loss=0.2475, pruned_loss=0.03215, over 7255.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2585, pruned_loss=0.0304, over 1423054.63 frames.], batch size: 19, lr: 2.29e-04
+2022-04-30 15:39:22,844 INFO [train.py:763] (6/8) Epoch 33, batch 1450, loss[loss=0.1582, simple_loss=0.2561, pruned_loss=0.03017, over 7423.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2591, pruned_loss=0.03027, over 1426081.82 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 15:40:28,340 INFO [train.py:763] (6/8) Epoch 33, batch 1500, loss[loss=0.166, simple_loss=0.2656, pruned_loss=0.03321, over 7370.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2598, pruned_loss=0.03031, over 1424898.88 frames.], batch size: 23, lr: 2.29e-04
+2022-04-30 15:41:33,826 INFO [train.py:763] (6/8) Epoch 33, batch 1550, loss[loss=0.1646, simple_loss=0.2619, pruned_loss=0.03361, over 7296.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2605, pruned_loss=0.03058, over 1422187.34 frames.], batch size: 24, lr: 2.29e-04
+2022-04-30 15:42:39,069 INFO [train.py:763] (6/8) Epoch 33, batch 1600, loss[loss=0.1505, simple_loss=0.2448, pruned_loss=0.02806, over 7330.00 frames.], tot_loss[loss=0.16, simple_loss=0.2599, pruned_loss=0.03006, over 1422828.26 frames.], batch size: 20, lr: 2.29e-04
+2022-04-30 15:43:46,170 INFO [train.py:763] (6/8) Epoch 33, batch 1650, loss[loss=0.1739, simple_loss=0.2779, pruned_loss=0.035, over 7197.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2607, pruned_loss=0.03003, over 1422483.38 frames.], batch size: 22, lr: 2.29e-04
+2022-04-30 15:44:53,520 INFO [train.py:763] (6/8) Epoch 33, batch 1700, loss[loss=0.1809, simple_loss=0.2749, pruned_loss=0.04345, over 7376.00 frames.], tot_loss[loss=0.1606, simple_loss=0.261, pruned_loss=0.03017, over 1426769.34 frames.], batch size: 23, lr: 2.29e-04
+2022-04-30 15:46:00,132 INFO [train.py:763] (6/8) Epoch 33, batch 1750, loss[loss=0.1736, simple_loss=0.2766, pruned_loss=0.03534, over 7018.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2612, pruned_loss=0.03049, over 1421472.99 frames.], batch size: 28, lr: 2.29e-04
+2022-04-30 15:47:05,294 INFO [train.py:763] (6/8) Epoch 33, batch 1800, loss[loss=0.1375, simple_loss=0.2333, pruned_loss=0.02085, over 7288.00 frames.], tot_loss[loss=0.161, simple_loss=0.2613, pruned_loss=0.03036, over 1422670.08 frames.], batch size: 17, lr: 2.29e-04
+2022-04-30 15:48:11,898 INFO [train.py:763] (6/8) Epoch 33, batch 1850, loss[loss=0.146, simple_loss=0.2546, pruned_loss=0.01877, over 7312.00 frames.], tot_loss[loss=0.1606, simple_loss=0.261, pruned_loss=0.03008, over 1415896.02 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 15:49:17,342 INFO [train.py:763] (6/8) Epoch 33, batch 1900, loss[loss=0.157, simple_loss=0.2591, pruned_loss=0.02749, over 6772.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2608, pruned_loss=0.02981, over 1412257.41 frames.], batch size: 31, lr: 2.29e-04
+2022-04-30 15:50:23,827 INFO [train.py:763] (6/8) Epoch 33, batch 1950, loss[loss=0.132, simple_loss=0.2218, pruned_loss=0.02108, over 6995.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2612, pruned_loss=0.03028, over 1418354.37 frames.], batch size: 16, lr: 2.29e-04
+2022-04-30 15:51:31,074 INFO [train.py:763] (6/8) Epoch 33, batch 2000, loss[loss=0.1453, simple_loss=0.2342, pruned_loss=0.02817, over 7403.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2609, pruned_loss=0.02984, over 1422879.51 frames.], batch size: 18, lr: 2.29e-04
+2022-04-30 15:52:37,447 INFO [train.py:763] (6/8) Epoch 33, batch 2050, loss[loss=0.1802, simple_loss=0.2925, pruned_loss=0.03391, over 7214.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03002, over 1422188.56 frames.], batch size: 26, lr: 2.29e-04
+2022-04-30 15:53:42,709 INFO [train.py:763] (6/8) Epoch 33, batch 2100, loss[loss=0.1679, simple_loss=0.2739, pruned_loss=0.03097, over 7196.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2607, pruned_loss=0.02981, over 1424330.40 frames.], batch size: 23, lr: 2.29e-04
+2022-04-30 15:54:47,943 INFO [train.py:763] (6/8) Epoch 33, batch 2150, loss[loss=0.1804, simple_loss=0.2918, pruned_loss=0.03447, over 7281.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2607, pruned_loss=0.02992, over 1422634.16 frames.], batch size: 24, lr: 2.29e-04
+2022-04-30 15:55:53,181 INFO [train.py:763] (6/8) Epoch 33, batch 2200, loss[loss=0.174, simple_loss=0.283, pruned_loss=0.03252, over 7320.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2613, pruned_loss=0.02995, over 1425696.85 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 15:56:58,913 INFO [train.py:763] (6/8) Epoch 33, batch 2250, loss[loss=0.1457, simple_loss=0.243, pruned_loss=0.0242, over 7290.00 frames.], tot_loss[loss=0.1605, simple_loss=0.261, pruned_loss=0.03006, over 1423186.45 frames.], batch size: 18, lr: 2.29e-04
+2022-04-30 15:58:05,272 INFO [train.py:763] (6/8) Epoch 33, batch 2300, loss[loss=0.1646, simple_loss=0.2681, pruned_loss=0.03058, over 7144.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2617, pruned_loss=0.03031, over 1424644.15 frames.], batch size: 19, lr: 2.29e-04
+2022-04-30 15:59:10,708 INFO [train.py:763] (6/8) Epoch 33, batch 2350, loss[loss=0.1664, simple_loss=0.2565, pruned_loss=0.03815, over 7165.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2608, pruned_loss=0.02994, over 1425941.71 frames.], batch size: 19, lr: 2.29e-04
+2022-04-30 16:00:16,789 INFO [train.py:763] (6/8) Epoch 33, batch 2400, loss[loss=0.1664, simple_loss=0.2827, pruned_loss=0.02506, over 7374.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03023, over 1426893.83 frames.], batch size: 23, lr: 2.29e-04
+2022-04-30 16:01:22,891 INFO [train.py:763] (6/8) Epoch 33, batch 2450, loss[loss=0.1558, simple_loss=0.2692, pruned_loss=0.02124, over 7227.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03039, over 1420533.61 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 16:02:28,046 INFO [train.py:763] (6/8) Epoch 33, batch 2500, loss[loss=0.14, simple_loss=0.2325, pruned_loss=0.02377, over 6989.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2606, pruned_loss=0.03021, over 1418949.32 frames.], batch size: 16, lr: 2.29e-04
+2022-04-30 16:03:33,224 INFO [train.py:763] (6/8) Epoch 33, batch 2550, loss[loss=0.1819, simple_loss=0.2851, pruned_loss=0.03933, over 7342.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2608, pruned_loss=0.03014, over 1420504.58 frames.], batch size: 22, lr: 2.29e-04
+2022-04-30 16:04:38,852 INFO [train.py:763] (6/8) Epoch 33, batch 2600, loss[loss=0.1547, simple_loss=0.246, pruned_loss=0.03168, over 7063.00 frames.], tot_loss[loss=0.161, simple_loss=0.2611, pruned_loss=0.03048, over 1419636.64 frames.], batch size: 18, lr: 2.29e-04
+2022-04-30 16:05:45,689 INFO [train.py:763] (6/8) Epoch 33, batch 2650, loss[loss=0.1446, simple_loss=0.2462, pruned_loss=0.02155, over 7340.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2606, pruned_loss=0.03019, over 1420629.50 frames.], batch size: 22, lr: 2.29e-04
+2022-04-30 16:06:52,534 INFO [train.py:763] (6/8) Epoch 33, batch 2700, loss[loss=0.1378, simple_loss=0.2384, pruned_loss=0.01865, over 7278.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2607, pruned_loss=0.03034, over 1425553.48 frames.], batch size: 18, lr: 2.28e-04
+2022-04-30 16:07:59,668 INFO [train.py:763] (6/8) Epoch 33, batch 2750, loss[loss=0.1828, simple_loss=0.2885, pruned_loss=0.03851, over 7308.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2608, pruned_loss=0.03034, over 1424443.93 frames.], batch size: 21, lr: 2.28e-04
+2022-04-30 16:09:06,754 INFO [train.py:763] (6/8) Epoch 33, batch 2800, loss[loss=0.1537, simple_loss=0.2487, pruned_loss=0.02936, over 7408.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2607, pruned_loss=0.03011, over 1429482.97 frames.], batch size: 18, lr: 2.28e-04
+2022-04-30 16:10:13,297 INFO [train.py:763] (6/8) Epoch 33, batch 2850, loss[loss=0.1673, simple_loss=0.2762, pruned_loss=0.02915, over 7206.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2608, pruned_loss=0.03033, over 1430498.10 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:11:18,329 INFO [train.py:763] (6/8) Epoch 33, batch 2900, loss[loss=0.1541, simple_loss=0.258, pruned_loss=0.02511, over 7145.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2608, pruned_loss=0.0303, over 1427569.74 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:12:24,337 INFO [train.py:763] (6/8) Epoch 33, batch 2950, loss[loss=0.1616, simple_loss=0.2676, pruned_loss=0.02781, over 7144.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03021, over 1428396.36 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:13:31,371 INFO [train.py:763] (6/8) Epoch 33, batch 3000, loss[loss=0.1608, simple_loss=0.2605, pruned_loss=0.03057, over 7357.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03019, over 1428146.63 frames.], batch size: 19, lr: 2.28e-04
+2022-04-30 16:13:31,372 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 16:13:46,765 INFO [train.py:792] (6/8) Epoch 33, validation: loss=0.1701, simple_loss=0.2653, pruned_loss=0.03746, over 698248.00 frames.
+2022-04-30 16:14:51,751 INFO [train.py:763] (6/8) Epoch 33, batch 3050, loss[loss=0.1714, simple_loss=0.271, pruned_loss=0.03592, over 7359.00 frames.], tot_loss[loss=0.161, simple_loss=0.2613, pruned_loss=0.03032, over 1428416.96 frames.], batch size: 19, lr: 2.28e-04
+2022-04-30 16:15:58,065 INFO [train.py:763] (6/8) Epoch 33, batch 3100, loss[loss=0.1678, simple_loss=0.2562, pruned_loss=0.0397, over 6813.00 frames.], tot_loss[loss=0.161, simple_loss=0.2614, pruned_loss=0.03027, over 1429888.72 frames.], batch size: 15, lr: 2.28e-04
+2022-04-30 16:17:04,991 INFO [train.py:763] (6/8) Epoch 33, batch 3150, loss[loss=0.1514, simple_loss=0.2395, pruned_loss=0.03163, over 7282.00 frames.], tot_loss[loss=0.1604, simple_loss=0.261, pruned_loss=0.02992, over 1430022.22 frames.], batch size: 17, lr: 2.28e-04
+2022-04-30 16:18:11,884 INFO [train.py:763] (6/8) Epoch 33, batch 3200, loss[loss=0.2146, simple_loss=0.2975, pruned_loss=0.06587, over 4943.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2608, pruned_loss=0.0301, over 1425553.66 frames.], batch size: 52, lr: 2.28e-04
+2022-04-30 16:19:17,473 INFO [train.py:763] (6/8) Epoch 33, batch 3250, loss[loss=0.1328, simple_loss=0.2325, pruned_loss=0.01659, over 7131.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2603, pruned_loss=0.03017, over 1422969.01 frames.], batch size: 17, lr: 2.28e-04
+2022-04-30 16:20:22,899 INFO [train.py:763] (6/8) Epoch 33, batch 3300, loss[loss=0.1798, simple_loss=0.2894, pruned_loss=0.03511, over 7052.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2606, pruned_loss=0.03033, over 1419785.16 frames.], batch size: 28, lr: 2.28e-04
+2022-04-30 16:21:28,692 INFO [train.py:763] (6/8) Epoch 33, batch 3350, loss[loss=0.1636, simple_loss=0.2609, pruned_loss=0.0332, over 7154.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2593, pruned_loss=0.03001, over 1422099.37 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:22:44,420 INFO [train.py:763] (6/8) Epoch 33, batch 3400, loss[loss=0.1627, simple_loss=0.2706, pruned_loss=0.02735, over 7207.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2603, pruned_loss=0.03014, over 1422388.52 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:23:50,290 INFO [train.py:763] (6/8) Epoch 33, batch 3450, loss[loss=0.1397, simple_loss=0.2309, pruned_loss=0.02429, over 7021.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2593, pruned_loss=0.03009, over 1427793.27 frames.], batch size: 16, lr: 2.28e-04
+2022-04-30 16:24:55,494 INFO [train.py:763] (6/8) Epoch 33, batch 3500, loss[loss=0.1755, simple_loss=0.2818, pruned_loss=0.03456, over 7194.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.0304, over 1429485.14 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:26:01,145 INFO [train.py:763] (6/8) Epoch 33, batch 3550, loss[loss=0.1439, simple_loss=0.2317, pruned_loss=0.02809, over 7286.00 frames.], tot_loss[loss=0.16, simple_loss=0.2598, pruned_loss=0.03009, over 1431801.02 frames.], batch size: 17, lr: 2.28e-04
+2022-04-30 16:27:06,627 INFO [train.py:763] (6/8) Epoch 33, batch 3600, loss[loss=0.1684, simple_loss=0.2766, pruned_loss=0.03009, over 7326.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2602, pruned_loss=0.03027, over 1433482.62 frames.], batch size: 21, lr: 2.28e-04
+2022-04-30 16:28:13,515 INFO [train.py:763] (6/8) Epoch 33, batch 3650, loss[loss=0.1611, simple_loss=0.265, pruned_loss=0.02855, over 6311.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2599, pruned_loss=0.03021, over 1428985.98 frames.], batch size: 38, lr: 2.28e-04
+2022-04-30 16:29:20,563 INFO [train.py:763] (6/8) Epoch 33, batch 3700, loss[loss=0.1677, simple_loss=0.2643, pruned_loss=0.03556, over 7238.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2583, pruned_loss=0.03001, over 1424595.18 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:30:26,040 INFO [train.py:763] (6/8) Epoch 33, batch 3750, loss[loss=0.1579, simple_loss=0.2538, pruned_loss=0.03097, over 7300.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2581, pruned_loss=0.03022, over 1423033.04 frames.], batch size: 24, lr: 2.28e-04
+2022-04-30 16:31:31,701 INFO [train.py:763] (6/8) Epoch 33, batch 3800, loss[loss=0.1726, simple_loss=0.2758, pruned_loss=0.03466, over 7148.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2592, pruned_loss=0.0305, over 1426944.61 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:32:38,581 INFO [train.py:763] (6/8) Epoch 33, batch 3850, loss[loss=0.1928, simple_loss=0.2918, pruned_loss=0.04688, over 7211.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2589, pruned_loss=0.03063, over 1428569.46 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:33:45,461 INFO [train.py:763] (6/8) Epoch 33, batch 3900, loss[loss=0.1913, simple_loss=0.2919, pruned_loss=0.0454, over 7198.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2587, pruned_loss=0.03055, over 1427173.26 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:34:52,422 INFO [train.py:763] (6/8) Epoch 33, batch 3950, loss[loss=0.1477, simple_loss=0.2538, pruned_loss=0.02083, over 7325.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2594, pruned_loss=0.03073, over 1424011.30 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:35:59,192 INFO [train.py:763] (6/8) Epoch 33, batch 4000, loss[loss=0.1556, simple_loss=0.2546, pruned_loss=0.02836, over 7062.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2603, pruned_loss=0.03073, over 1424346.51 frames.], batch size: 18, lr: 2.28e-04
+2022-04-30 16:37:13,143 INFO [train.py:763] (6/8) Epoch 33, batch 4050, loss[loss=0.2009, simple_loss=0.2946, pruned_loss=0.05353, over 7178.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.03057, over 1419640.93 frames.], batch size: 26, lr: 2.27e-04
+2022-04-30 16:38:27,105 INFO [train.py:763] (6/8) Epoch 33, batch 4100, loss[loss=0.1583, simple_loss=0.2647, pruned_loss=0.02594, over 6237.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03018, over 1419489.28 frames.], batch size: 37, lr: 2.27e-04
+2022-04-30 16:39:41,393 INFO [train.py:763] (6/8) Epoch 33, batch 4150, loss[loss=0.1453, simple_loss=0.2468, pruned_loss=0.02194, over 7408.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03029, over 1417941.55 frames.], batch size: 18, lr: 2.27e-04
+2022-04-30 16:40:55,330 INFO [train.py:763] (6/8) Epoch 33, batch 4200, loss[loss=0.138, simple_loss=0.2388, pruned_loss=0.01856, over 7244.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2603, pruned_loss=0.02996, over 1420972.73 frames.], batch size: 20, lr: 2.27e-04
+2022-04-30 16:42:02,052 INFO [train.py:763] (6/8) Epoch 33, batch 4250, loss[loss=0.1302, simple_loss=0.2198, pruned_loss=0.02036, over 7150.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2605, pruned_loss=0.03007, over 1420414.92 frames.], batch size: 17, lr: 2.27e-04
+2022-04-30 16:43:17,918 INFO [train.py:763] (6/8) Epoch 33, batch 4300, loss[loss=0.138, simple_loss=0.2253, pruned_loss=0.02537, over 7435.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.03018, over 1421010.78 frames.], batch size: 17, lr: 2.27e-04
+2022-04-30 16:44:24,710 INFO [train.py:763] (6/8) Epoch 33, batch 4350, loss[loss=0.1516, simple_loss=0.2396, pruned_loss=0.03175, over 6795.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2615, pruned_loss=0.0305, over 1416190.24 frames.], batch size: 15, lr: 2.27e-04
+2022-04-30 16:45:48,494 INFO [train.py:763] (6/8) Epoch 33, batch 4400, loss[loss=0.1671, simple_loss=0.2704, pruned_loss=0.03186, over 7155.00 frames.], tot_loss[loss=0.1608, simple_loss=0.261, pruned_loss=0.03031, over 1416770.09 frames.], batch size: 18, lr: 2.27e-04
+2022-04-30 16:46:53,554 INFO [train.py:763] (6/8) Epoch 33, batch 4450, loss[loss=0.1921, simple_loss=0.2839, pruned_loss=0.05017, over 7182.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2618, pruned_loss=0.03116, over 1401223.70 frames.], batch size: 23, lr: 2.27e-04
+2022-04-30 16:48:00,202 INFO [train.py:763] (6/8) Epoch 33, batch 4500, loss[loss=0.1826, simple_loss=0.275, pruned_loss=0.04511, over 5520.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2619, pruned_loss=0.0312, over 1392988.81 frames.], batch size: 54, lr: 2.27e-04
+2022-04-30 16:49:05,830 INFO [train.py:763] (6/8) Epoch 33, batch 4550, loss[loss=0.1869, simple_loss=0.2784, pruned_loss=0.04768, over 5159.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2638, pruned_loss=0.03193, over 1352179.35 frames.], batch size: 52, lr: 2.27e-04
+2022-04-30 16:50:25,417 INFO [train.py:763] (6/8) Epoch 34, batch 0, loss[loss=0.182, simple_loss=0.2874, pruned_loss=0.03832, over 7224.00 frames.], tot_loss[loss=0.182, simple_loss=0.2874, pruned_loss=0.03832, over 7224.00 frames.], batch size: 20, lr: 2.24e-04
+2022-04-30 16:51:31,605 INFO [train.py:763] (6/8) Epoch 34, batch 50, loss[loss=0.1789, simple_loss=0.2783, pruned_loss=0.03974, over 7289.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2624, pruned_loss=0.03038, over 317857.30 frames.], batch size: 24, lr: 2.24e-04
+2022-04-30 16:52:37,604 INFO [train.py:763] (6/8) Epoch 34, batch 100, loss[loss=0.1929, simple_loss=0.2911, pruned_loss=0.04735, over 7117.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2597, pruned_loss=0.02973, over 567561.32 frames.], batch size: 26, lr: 2.24e-04
+2022-04-30 16:53:43,311 INFO [train.py:763] (6/8) Epoch 34, batch 150, loss[loss=0.1731, simple_loss=0.2663, pruned_loss=0.03997, over 7382.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2603, pruned_loss=0.02966, over 760431.13 frames.], batch size: 23, lr: 2.24e-04
+2022-04-30 16:54:49,443 INFO [train.py:763] (6/8) Epoch 34, batch 200, loss[loss=0.1583, simple_loss=0.2578, pruned_loss=0.02934, over 7077.00 frames.], tot_loss[loss=0.161, simple_loss=0.2609, pruned_loss=0.03053, over 909183.83 frames.], batch size: 18, lr: 2.24e-04
+2022-04-30 16:55:56,555 INFO [train.py:763] (6/8) Epoch 34, batch 250, loss[loss=0.1579, simple_loss=0.2624, pruned_loss=0.02667, over 7231.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2601, pruned_loss=0.03013, over 1026617.93 frames.], batch size: 20, lr: 2.24e-04
+2022-04-30 16:57:03,055 INFO [train.py:763] (6/8) Epoch 34, batch 300, loss[loss=0.1433, simple_loss=0.2465, pruned_loss=0.02008, over 7161.00 frames.], tot_loss[loss=0.1601, simple_loss=0.26, pruned_loss=0.03017, over 1113998.18 frames.], batch size: 19, lr: 2.24e-04
+2022-04-30 16:58:08,938 INFO [train.py:763] (6/8) Epoch 34, batch 350, loss[loss=0.1686, simple_loss=0.2734, pruned_loss=0.03193, over 7202.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2596, pruned_loss=0.02952, over 1185388.96 frames.], batch size: 23, lr: 2.24e-04
+2022-04-30 16:59:14,459 INFO [train.py:763] (6/8) Epoch 34, batch 400, loss[loss=0.1612, simple_loss=0.2653, pruned_loss=0.02854, over 7327.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2597, pruned_loss=0.02957, over 1239728.90 frames.], batch size: 20, lr: 2.24e-04
+2022-04-30 17:00:20,018 INFO [train.py:763] (6/8) Epoch 34, batch 450, loss[loss=0.1753, simple_loss=0.28, pruned_loss=0.03531, over 6732.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2592, pruned_loss=0.02933, over 1283890.73 frames.], batch size: 31, lr: 2.24e-04
+2022-04-30 17:01:26,962 INFO [train.py:763] (6/8) Epoch 34, batch 500, loss[loss=0.1496, simple_loss=0.2493, pruned_loss=0.0249, over 7336.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2589, pruned_loss=0.02915, over 1312737.43 frames.], batch size: 20, lr: 2.23e-04
+2022-04-30 17:02:32,705 INFO [train.py:763] (6/8) Epoch 34, batch 550, loss[loss=0.1568, simple_loss=0.2541, pruned_loss=0.02976, over 7064.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2586, pruned_loss=0.02906, over 1334427.34 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:03:38,762 INFO [train.py:763] (6/8) Epoch 34, batch 600, loss[loss=0.1681, simple_loss=0.2748, pruned_loss=0.03065, over 7336.00 frames.], tot_loss[loss=0.159, simple_loss=0.2594, pruned_loss=0.02926, over 1353169.42 frames.], batch size: 22, lr: 2.23e-04
+2022-04-30 17:04:44,666 INFO [train.py:763] (6/8) Epoch 34, batch 650, loss[loss=0.1359, simple_loss=0.2295, pruned_loss=0.02114, over 7160.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2597, pruned_loss=0.02925, over 1372069.17 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:05:50,787 INFO [train.py:763] (6/8) Epoch 34, batch 700, loss[loss=0.1463, simple_loss=0.2349, pruned_loss=0.02885, over 7266.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2595, pruned_loss=0.0292, over 1386295.31 frames.], batch size: 17, lr: 2.23e-04
+2022-04-30 17:06:58,023 INFO [train.py:763] (6/8) Epoch 34, batch 750, loss[loss=0.1411, simple_loss=0.2367, pruned_loss=0.02269, over 7255.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2589, pruned_loss=0.02934, over 1393971.77 frames.], batch size: 19, lr: 2.23e-04
+2022-04-30 17:08:04,370 INFO [train.py:763] (6/8) Epoch 34, batch 800, loss[loss=0.1625, simple_loss=0.2741, pruned_loss=0.02551, over 7217.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2594, pruned_loss=0.02918, over 1402192.70 frames.], batch size: 21, lr: 2.23e-04
+2022-04-30 17:09:09,695 INFO [train.py:763] (6/8) Epoch 34, batch 850, loss[loss=0.1681, simple_loss=0.2762, pruned_loss=0.03004, over 7280.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2603, pruned_loss=0.02925, over 1402909.47 frames.], batch size: 24, lr: 2.23e-04
+2022-04-30 17:10:15,223 INFO [train.py:763] (6/8) Epoch 34, batch 900, loss[loss=0.1735, simple_loss=0.2726, pruned_loss=0.03723, over 4750.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2606, pruned_loss=0.02961, over 1405704.22 frames.], batch size: 52, lr: 2.23e-04
+2022-04-30 17:11:21,166 INFO [train.py:763] (6/8) Epoch 34, batch 950, loss[loss=0.1626, simple_loss=0.2569, pruned_loss=0.03418, over 7268.00 frames.], tot_loss[loss=0.1595, simple_loss=0.26, pruned_loss=0.02956, over 1409260.33 frames.], batch size: 19, lr: 2.23e-04
+2022-04-30 17:12:27,412 INFO [train.py:763] (6/8) Epoch 34, batch 1000, loss[loss=0.1742, simple_loss=0.2751, pruned_loss=0.03668, over 6757.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2607, pruned_loss=0.02983, over 1410603.62 frames.], batch size: 31, lr: 2.23e-04
+2022-04-30 17:13:34,600 INFO [train.py:763] (6/8) Epoch 34, batch 1050, loss[loss=0.1618, simple_loss=0.2583, pruned_loss=0.03267, over 7418.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2592, pruned_loss=0.02917, over 1415741.16 frames.], batch size: 21, lr: 2.23e-04
+2022-04-30 17:14:40,036 INFO [train.py:763] (6/8) Epoch 34, batch 1100, loss[loss=0.1436, simple_loss=0.2448, pruned_loss=0.02113, over 7358.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2578, pruned_loss=0.02877, over 1420063.54 frames.], batch size: 19, lr: 2.23e-04
+2022-04-30 17:15:45,151 INFO [train.py:763] (6/8) Epoch 34, batch 1150, loss[loss=0.185, simple_loss=0.2987, pruned_loss=0.03569, over 7193.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2586, pruned_loss=0.02911, over 1421476.69 frames.], batch size: 23, lr: 2.23e-04
+2022-04-30 17:16:50,473 INFO [train.py:763] (6/8) Epoch 34, batch 1200, loss[loss=0.1617, simple_loss=0.2656, pruned_loss=0.02889, over 7266.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2586, pruned_loss=0.02896, over 1424979.89 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:17:56,082 INFO [train.py:763] (6/8) Epoch 34, batch 1250, loss[loss=0.1686, simple_loss=0.27, pruned_loss=0.03363, over 7321.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02945, over 1424806.19 frames.], batch size: 22, lr: 2.23e-04
+2022-04-30 17:19:02,073 INFO [train.py:763] (6/8) Epoch 34, batch 1300, loss[loss=0.1673, simple_loss=0.2717, pruned_loss=0.03146, over 7108.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2603, pruned_loss=0.02998, over 1421358.77 frames.], batch size: 28, lr: 2.23e-04
+2022-04-30 17:20:07,321 INFO [train.py:763] (6/8) Epoch 34, batch 1350, loss[loss=0.1981, simple_loss=0.2961, pruned_loss=0.05004, over 7061.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2612, pruned_loss=0.03049, over 1423854.56 frames.], batch size: 28, lr: 2.23e-04
+2022-04-30 17:21:12,464 INFO [train.py:763] (6/8) Epoch 34, batch 1400, loss[loss=0.1342, simple_loss=0.2347, pruned_loss=0.01684, over 7328.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2618, pruned_loss=0.03067, over 1421438.48 frames.], batch size: 20, lr: 2.23e-04
+2022-04-30 17:22:17,957 INFO [train.py:763] (6/8) Epoch 34, batch 1450, loss[loss=0.1609, simple_loss=0.26, pruned_loss=0.03091, over 7268.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2609, pruned_loss=0.03063, over 1419356.38 frames.], batch size: 19, lr: 2.23e-04
+2022-04-30 17:23:24,436 INFO [train.py:763] (6/8) Epoch 34, batch 1500, loss[loss=0.1472, simple_loss=0.2395, pruned_loss=0.02747, over 7133.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2605, pruned_loss=0.03054, over 1420417.29 frames.], batch size: 17, lr: 2.23e-04
+2022-04-30 17:24:29,699 INFO [train.py:763] (6/8) Epoch 34, batch 1550, loss[loss=0.2071, simple_loss=0.3178, pruned_loss=0.04827, over 7216.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2614, pruned_loss=0.03072, over 1420706.44 frames.], batch size: 21, lr: 2.23e-04
+2022-04-30 17:25:36,513 INFO [train.py:763] (6/8) Epoch 34, batch 1600, loss[loss=0.1679, simple_loss=0.2616, pruned_loss=0.03703, over 7045.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.03054, over 1422360.12 frames.], batch size: 28, lr: 2.23e-04
+2022-04-30 17:26:43,360 INFO [train.py:763] (6/8) Epoch 34, batch 1650, loss[loss=0.1346, simple_loss=0.2289, pruned_loss=0.02016, over 7416.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2607, pruned_loss=0.03022, over 1426953.68 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:27:48,836 INFO [train.py:763] (6/8) Epoch 34, batch 1700, loss[loss=0.1679, simple_loss=0.2611, pruned_loss=0.03738, over 5230.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2605, pruned_loss=0.03031, over 1426600.38 frames.], batch size: 52, lr: 2.23e-04
+2022-04-30 17:28:54,323 INFO [train.py:763] (6/8) Epoch 34, batch 1750, loss[loss=0.1397, simple_loss=0.2388, pruned_loss=0.02024, over 7175.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2598, pruned_loss=0.03022, over 1426465.29 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:29:59,724 INFO [train.py:763] (6/8) Epoch 34, batch 1800, loss[loss=0.1751, simple_loss=0.2762, pruned_loss=0.03706, over 7296.00 frames.], tot_loss[loss=0.1592, simple_loss=0.259, pruned_loss=0.02972, over 1430245.41 frames.], batch size: 25, lr: 2.23e-04
+2022-04-30 17:31:04,982 INFO [train.py:763] (6/8) Epoch 34, batch 1850, loss[loss=0.1252, simple_loss=0.222, pruned_loss=0.01422, over 7071.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2586, pruned_loss=0.02953, over 1426420.63 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:32:10,319 INFO [train.py:763] (6/8) Epoch 34, batch 1900, loss[loss=0.1533, simple_loss=0.2508, pruned_loss=0.02786, over 7385.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2588, pruned_loss=0.02968, over 1426331.08 frames.], batch size: 23, lr: 2.22e-04
+2022-04-30 17:33:15,842 INFO [train.py:763] (6/8) Epoch 34, batch 1950, loss[loss=0.1361, simple_loss=0.2261, pruned_loss=0.02307, over 7160.00 frames.], tot_loss[loss=0.1591, simple_loss=0.259, pruned_loss=0.02961, over 1424478.25 frames.], batch size: 18, lr: 2.22e-04
+2022-04-30 17:34:22,119 INFO [train.py:763] (6/8) Epoch 34, batch 2000, loss[loss=0.1416, simple_loss=0.2443, pruned_loss=0.0195, over 6371.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2595, pruned_loss=0.02969, over 1420385.37 frames.], batch size: 37, lr: 2.22e-04
+2022-04-30 17:35:27,875 INFO [train.py:763] (6/8) Epoch 34, batch 2050, loss[loss=0.148, simple_loss=0.2539, pruned_loss=0.02098, over 7120.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02959, over 1421256.45 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:36:33,095 INFO [train.py:763] (6/8) Epoch 34, batch 2100, loss[loss=0.1663, simple_loss=0.2784, pruned_loss=0.02705, over 7411.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2601, pruned_loss=0.02957, over 1424001.94 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:37:40,166 INFO [train.py:763] (6/8) Epoch 34, batch 2150, loss[loss=0.1795, simple_loss=0.2767, pruned_loss=0.04118, over 6307.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2599, pruned_loss=0.02951, over 1427290.43 frames.], batch size: 37, lr: 2.22e-04
+2022-04-30 17:38:46,197 INFO [train.py:763] (6/8) Epoch 34, batch 2200, loss[loss=0.1585, simple_loss=0.2511, pruned_loss=0.03295, over 7432.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2593, pruned_loss=0.02955, over 1424452.41 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 17:39:51,385 INFO [train.py:763] (6/8) Epoch 34, batch 2250, loss[loss=0.1667, simple_loss=0.2566, pruned_loss=0.0384, over 7272.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2589, pruned_loss=0.02935, over 1422242.18 frames.], batch size: 18, lr: 2.22e-04
+2022-04-30 17:40:56,558 INFO [train.py:763] (6/8) Epoch 34, batch 2300, loss[loss=0.1761, simple_loss=0.2783, pruned_loss=0.03692, over 7145.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2595, pruned_loss=0.02983, over 1419278.35 frames.], batch size: 26, lr: 2.22e-04
+2022-04-30 17:42:01,782 INFO [train.py:763] (6/8) Epoch 34, batch 2350, loss[loss=0.1572, simple_loss=0.2622, pruned_loss=0.0261, over 7010.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2599, pruned_loss=0.02981, over 1417561.11 frames.], batch size: 28, lr: 2.22e-04
+2022-04-30 17:43:08,015 INFO [train.py:763] (6/8) Epoch 34, batch 2400, loss[loss=0.1365, simple_loss=0.2223, pruned_loss=0.02539, over 7014.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2599, pruned_loss=0.02973, over 1422100.58 frames.], batch size: 16, lr: 2.22e-04
+2022-04-30 17:44:15,065 INFO [train.py:763] (6/8) Epoch 34, batch 2450, loss[loss=0.1511, simple_loss=0.2537, pruned_loss=0.02426, over 7446.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2593, pruned_loss=0.02961, over 1423308.72 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 17:45:22,382 INFO [train.py:763] (6/8) Epoch 34, batch 2500, loss[loss=0.1819, simple_loss=0.2865, pruned_loss=0.03866, over 6570.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2586, pruned_loss=0.02977, over 1425242.77 frames.], batch size: 38, lr: 2.22e-04
+2022-04-30 17:46:28,715 INFO [train.py:763] (6/8) Epoch 34, batch 2550, loss[loss=0.1677, simple_loss=0.2759, pruned_loss=0.02979, over 7108.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2589, pruned_loss=0.02991, over 1425036.57 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:47:35,757 INFO [train.py:763] (6/8) Epoch 34, batch 2600, loss[loss=0.188, simple_loss=0.279, pruned_loss=0.04847, over 7200.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2587, pruned_loss=0.03003, over 1424084.61 frames.], batch size: 22, lr: 2.22e-04
+2022-04-30 17:48:40,940 INFO [train.py:763] (6/8) Epoch 34, batch 2650, loss[loss=0.1637, simple_loss=0.2655, pruned_loss=0.03101, over 7233.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2589, pruned_loss=0.03041, over 1422680.95 frames.], batch size: 23, lr: 2.22e-04
+2022-04-30 17:49:46,280 INFO [train.py:763] (6/8) Epoch 34, batch 2700, loss[loss=0.1527, simple_loss=0.2537, pruned_loss=0.02583, over 7121.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2585, pruned_loss=0.02992, over 1424292.00 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:50:51,545 INFO [train.py:763] (6/8) Epoch 34, batch 2750, loss[loss=0.17, simple_loss=0.2726, pruned_loss=0.03365, over 7323.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2592, pruned_loss=0.0301, over 1423515.99 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:51:57,771 INFO [train.py:763] (6/8) Epoch 34, batch 2800, loss[loss=0.1628, simple_loss=0.2552, pruned_loss=0.03524, over 7332.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2597, pruned_loss=0.0302, over 1424962.51 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 17:53:04,540 INFO [train.py:763] (6/8) Epoch 34, batch 2850, loss[loss=0.1478, simple_loss=0.2533, pruned_loss=0.0211, over 7154.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2598, pruned_loss=0.02998, over 1423956.56 frames.], batch size: 19, lr: 2.22e-04
+2022-04-30 17:54:11,663 INFO [train.py:763] (6/8) Epoch 34, batch 2900, loss[loss=0.1634, simple_loss=0.2649, pruned_loss=0.03099, over 6488.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2597, pruned_loss=0.02989, over 1422684.23 frames.], batch size: 38, lr: 2.22e-04
+2022-04-30 17:55:17,494 INFO [train.py:763] (6/8) Epoch 34, batch 2950, loss[loss=0.1394, simple_loss=0.2243, pruned_loss=0.02721, over 6811.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2605, pruned_loss=0.0301, over 1416269.59 frames.], batch size: 15, lr: 2.22e-04
+2022-04-30 17:56:22,956 INFO [train.py:763] (6/8) Epoch 34, batch 3000, loss[loss=0.1662, simple_loss=0.2725, pruned_loss=0.02996, over 7387.00 frames.], tot_loss[loss=0.1599, simple_loss=0.26, pruned_loss=0.02986, over 1419819.76 frames.], batch size: 23, lr: 2.22e-04
+2022-04-30 17:56:22,957 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 17:56:38,270 INFO [train.py:792] (6/8) Epoch 34, validation: loss=0.1686, simple_loss=0.2638, pruned_loss=0.03669, over 698248.00 frames.
+2022-04-30 17:57:44,372 INFO [train.py:763] (6/8) Epoch 34, batch 3050, loss[loss=0.1546, simple_loss=0.2574, pruned_loss=0.02593, over 7234.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2597, pruned_loss=0.02964, over 1422705.37 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 17:58:51,171 INFO [train.py:763] (6/8) Epoch 34, batch 3100, loss[loss=0.1725, simple_loss=0.2749, pruned_loss=0.03504, over 7397.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2593, pruned_loss=0.02956, over 1419622.03 frames.], batch size: 23, lr: 2.22e-04
+2022-04-30 17:59:56,669 INFO [train.py:763] (6/8) Epoch 34, batch 3150, loss[loss=0.1767, simple_loss=0.2743, pruned_loss=0.03955, over 7204.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2581, pruned_loss=0.02918, over 1421417.47 frames.], batch size: 22, lr: 2.22e-04
+2022-04-30 18:01:02,260 INFO [train.py:763] (6/8) Epoch 34, batch 3200, loss[loss=0.163, simple_loss=0.2673, pruned_loss=0.0293, over 7198.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2598, pruned_loss=0.02977, over 1426319.44 frames.], batch size: 22, lr: 2.22e-04
+2022-04-30 18:02:09,379 INFO [train.py:763] (6/8) Epoch 34, batch 3250, loss[loss=0.1562, simple_loss=0.2578, pruned_loss=0.02732, over 7424.00 frames.], tot_loss[loss=0.1598, simple_loss=0.26, pruned_loss=0.02977, over 1424678.12 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 18:03:15,761 INFO [train.py:763] (6/8) Epoch 34, batch 3300, loss[loss=0.1406, simple_loss=0.2512, pruned_loss=0.01504, over 7431.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2604, pruned_loss=0.02987, over 1425947.27 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 18:04:21,126 INFO [train.py:763] (6/8) Epoch 34, batch 3350, loss[loss=0.1502, simple_loss=0.2564, pruned_loss=0.02196, over 7419.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2606, pruned_loss=0.02984, over 1429352.69 frames.], batch size: 20, lr: 2.21e-04
+2022-04-30 18:05:26,508 INFO [train.py:763] (6/8) Epoch 34, batch 3400, loss[loss=0.1432, simple_loss=0.2449, pruned_loss=0.02076, over 7254.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2598, pruned_loss=0.02962, over 1426763.62 frames.], batch size: 18, lr: 2.21e-04
+2022-04-30 18:06:31,974 INFO [train.py:763] (6/8) Epoch 34, batch 3450, loss[loss=0.1312, simple_loss=0.2321, pruned_loss=0.0152, over 7013.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2598, pruned_loss=0.02983, over 1429408.34 frames.], batch size: 16, lr: 2.21e-04
+2022-04-30 18:07:37,450 INFO [train.py:763] (6/8) Epoch 34, batch 3500, loss[loss=0.1649, simple_loss=0.2795, pruned_loss=0.02515, over 7358.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2599, pruned_loss=0.02986, over 1428058.21 frames.], batch size: 22, lr: 2.21e-04
+2022-04-30 18:08:42,511 INFO [train.py:763] (6/8) Epoch 34, batch 3550, loss[loss=0.1593, simple_loss=0.266, pruned_loss=0.0263, over 6801.00 frames.], tot_loss[loss=0.1598, simple_loss=0.26, pruned_loss=0.02979, over 1421469.38 frames.], batch size: 31, lr: 2.21e-04
+2022-04-30 18:09:48,192 INFO [train.py:763] (6/8) Epoch 34, batch 3600, loss[loss=0.1759, simple_loss=0.2752, pruned_loss=0.03833, over 7215.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2602, pruned_loss=0.02984, over 1419949.60 frames.], batch size: 22, lr: 2.21e-04
+2022-04-30 18:10:55,328 INFO [train.py:763] (6/8) Epoch 34, batch 3650, loss[loss=0.1617, simple_loss=0.2632, pruned_loss=0.03004, over 7291.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2618, pruned_loss=0.03049, over 1421355.61 frames.], batch size: 25, lr: 2.21e-04
+2022-04-30 18:12:01,493 INFO [train.py:763] (6/8) Epoch 34, batch 3700, loss[loss=0.1483, simple_loss=0.2467, pruned_loss=0.02497, over 6534.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2614, pruned_loss=0.03053, over 1420993.68 frames.], batch size: 38, lr: 2.21e-04
+2022-04-30 18:13:06,703 INFO [train.py:763] (6/8) Epoch 34, batch 3750, loss[loss=0.175, simple_loss=0.2669, pruned_loss=0.04162, over 5190.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2608, pruned_loss=0.0301, over 1418838.36 frames.], batch size: 52, lr: 2.21e-04
+2022-04-30 18:14:11,990 INFO [train.py:763] (6/8) Epoch 34, batch 3800, loss[loss=0.1633, simple_loss=0.2697, pruned_loss=0.02841, over 6766.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2604, pruned_loss=0.0296, over 1419038.63 frames.], batch size: 31, lr: 2.21e-04
+2022-04-30 18:15:17,336 INFO [train.py:763] (6/8) Epoch 34, batch 3850, loss[loss=0.1937, simple_loss=0.2908, pruned_loss=0.04837, over 7287.00 frames.], tot_loss[loss=0.1597, simple_loss=0.26, pruned_loss=0.02971, over 1422200.74 frames.], batch size: 24, lr: 2.21e-04
+2022-04-30 18:16:23,811 INFO [train.py:763] (6/8) Epoch 34, batch 3900, loss[loss=0.1683, simple_loss=0.2584, pruned_loss=0.03908, over 6805.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2606, pruned_loss=0.03028, over 1417986.64 frames.], batch size: 15, lr: 2.21e-04
+2022-04-30 18:17:30,969 INFO [train.py:763] (6/8) Epoch 34, batch 3950, loss[loss=0.125, simple_loss=0.2158, pruned_loss=0.01711, over 7132.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2598, pruned_loss=0.03001, over 1418056.86 frames.], batch size: 17, lr: 2.21e-04
+2022-04-30 18:18:37,954 INFO [train.py:763] (6/8) Epoch 34, batch 4000, loss[loss=0.1468, simple_loss=0.2267, pruned_loss=0.03351, over 7000.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2594, pruned_loss=0.02989, over 1418064.57 frames.], batch size: 16, lr: 2.21e-04
+2022-04-30 18:19:54,713 INFO [train.py:763] (6/8) Epoch 34, batch 4050, loss[loss=0.1539, simple_loss=0.2583, pruned_loss=0.02478, over 6324.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2598, pruned_loss=0.0297, over 1420533.47 frames.], batch size: 37, lr: 2.21e-04
+2022-04-30 18:21:01,811 INFO [train.py:763] (6/8) Epoch 34, batch 4100, loss[loss=0.1728, simple_loss=0.2829, pruned_loss=0.03138, over 7216.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2599, pruned_loss=0.02963, over 1425411.41 frames.], batch size: 21, lr: 2.21e-04
+2022-04-30 18:22:08,689 INFO [train.py:763] (6/8) Epoch 34, batch 4150, loss[loss=0.1406, simple_loss=0.2413, pruned_loss=0.01997, over 7325.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2591, pruned_loss=0.02973, over 1424033.55 frames.], batch size: 21, lr: 2.21e-04
+2022-04-30 18:23:15,041 INFO [train.py:763] (6/8) Epoch 34, batch 4200, loss[loss=0.1497, simple_loss=0.2547, pruned_loss=0.02238, over 7318.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2597, pruned_loss=0.02977, over 1421960.16 frames.], batch size: 21, lr: 2.21e-04
+2022-04-30 18:24:20,539 INFO [train.py:763] (6/8) Epoch 34, batch 4250, loss[loss=0.1343, simple_loss=0.2244, pruned_loss=0.02205, over 7279.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2593, pruned_loss=0.02931, over 1426660.56 frames.], batch size: 17, lr: 2.21e-04
+2022-04-30 18:25:25,963 INFO [train.py:763] (6/8) Epoch 34, batch 4300, loss[loss=0.1842, simple_loss=0.2875, pruned_loss=0.04038, over 7202.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2582, pruned_loss=0.02901, over 1417865.30 frames.], batch size: 26, lr: 2.21e-04
+2022-04-30 18:26:32,749 INFO [train.py:763] (6/8) Epoch 34, batch 4350, loss[loss=0.1687, simple_loss=0.2712, pruned_loss=0.0331, over 7302.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2592, pruned_loss=0.02945, over 1413489.23 frames.], batch size: 24, lr: 2.21e-04
+2022-04-30 18:27:38,206 INFO [train.py:763] (6/8) Epoch 34, batch 4400, loss[loss=0.139, simple_loss=0.2371, pruned_loss=0.0205, over 7163.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2594, pruned_loss=0.0292, over 1409145.11 frames.], batch size: 19, lr: 2.21e-04
+2022-04-30 18:28:42,658 INFO [train.py:763] (6/8) Epoch 34, batch 4450, loss[loss=0.1922, simple_loss=0.286, pruned_loss=0.04917, over 6686.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2602, pruned_loss=0.02956, over 1392674.75 frames.], batch size: 31, lr: 2.21e-04
+2022-04-30 18:29:47,245 INFO [train.py:763] (6/8) Epoch 34, batch 4500, loss[loss=0.1553, simple_loss=0.2581, pruned_loss=0.02623, over 7134.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2603, pruned_loss=0.02996, over 1378812.94 frames.], batch size: 26, lr: 2.21e-04
+2022-04-30 18:30:51,775 INFO [train.py:763] (6/8) Epoch 34, batch 4550, loss[loss=0.1871, simple_loss=0.2862, pruned_loss=0.04394, over 4925.00 frames.], tot_loss[loss=0.162, simple_loss=0.2627, pruned_loss=0.03061, over 1353297.33 frames.], batch size: 52, lr: 2.21e-04
+2022-04-30 18:32:11,387 INFO [train.py:763] (6/8) Epoch 35, batch 0, loss[loss=0.1581, simple_loss=0.2619, pruned_loss=0.02719, over 7328.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2619, pruned_loss=0.02719, over 7328.00 frames.], batch size: 20, lr: 2.18e-04
+2022-04-30 18:33:17,375 INFO [train.py:763] (6/8) Epoch 35, batch 50, loss[loss=0.161, simple_loss=0.2594, pruned_loss=0.03132, over 7411.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2601, pruned_loss=0.03022, over 316269.88 frames.], batch size: 20, lr: 2.18e-04
+2022-04-30 18:34:22,744 INFO [train.py:763] (6/8) Epoch 35, batch 100, loss[loss=0.1776, simple_loss=0.27, pruned_loss=0.04253, over 4878.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2581, pruned_loss=0.02908, over 561694.14 frames.], batch size: 52, lr: 2.17e-04
+2022-04-30 18:35:28,403 INFO [train.py:763] (6/8) Epoch 35, batch 150, loss[loss=0.1624, simple_loss=0.2743, pruned_loss=0.02523, over 7233.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2575, pruned_loss=0.0286, over 751336.75 frames.], batch size: 20, lr: 2.17e-04
+2022-04-30 18:36:34,085 INFO [train.py:763] (6/8) Epoch 35, batch 200, loss[loss=0.1557, simple_loss=0.2633, pruned_loss=0.02399, over 7319.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2593, pruned_loss=0.02888, over 901145.95 frames.], batch size: 21, lr: 2.17e-04
+2022-04-30 18:37:50,842 INFO [train.py:763] (6/8) Epoch 35, batch 250, loss[loss=0.1556, simple_loss=0.2615, pruned_loss=0.02485, over 7158.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2583, pruned_loss=0.02905, over 1020490.61 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 18:38:58,241 INFO [train.py:763] (6/8) Epoch 35, batch 300, loss[loss=0.185, simple_loss=0.2921, pruned_loss=0.03893, over 7218.00 frames.], tot_loss[loss=0.158, simple_loss=0.2583, pruned_loss=0.02881, over 1104837.16 frames.], batch size: 26, lr: 2.17e-04
+2022-04-30 18:40:05,545 INFO [train.py:763] (6/8) Epoch 35, batch 350, loss[loss=0.1544, simple_loss=0.2684, pruned_loss=0.02023, over 6833.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2583, pruned_loss=0.02846, over 1174185.72 frames.], batch size: 31, lr: 2.17e-04
+2022-04-30 18:41:12,762 INFO [train.py:763] (6/8) Epoch 35, batch 400, loss[loss=0.163, simple_loss=0.2644, pruned_loss=0.03082, over 7208.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2594, pruned_loss=0.02915, over 1230081.20 frames.], batch size: 22, lr: 2.17e-04
+2022-04-30 18:42:19,850 INFO [train.py:763] (6/8) Epoch 35, batch 450, loss[loss=0.1726, simple_loss=0.269, pruned_loss=0.03817, over 7132.00 frames.], tot_loss[loss=0.159, simple_loss=0.2593, pruned_loss=0.02938, over 1277728.99 frames.], batch size: 26, lr: 2.17e-04
+2022-04-30 18:43:25,154 INFO [train.py:763] (6/8) Epoch 35, batch 500, loss[loss=0.1657, simple_loss=0.2652, pruned_loss=0.03307, over 7199.00 frames.], tot_loss[loss=0.1597, simple_loss=0.26, pruned_loss=0.02968, over 1309473.04 frames.], batch size: 23, lr: 2.17e-04
+2022-04-30 18:44:30,967 INFO [train.py:763] (6/8) Epoch 35, batch 550, loss[loss=0.1629, simple_loss=0.2612, pruned_loss=0.03234, over 7434.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2606, pruned_loss=0.02983, over 1335859.05 frames.], batch size: 20, lr: 2.17e-04
+2022-04-30 18:45:37,235 INFO [train.py:763] (6/8) Epoch 35, batch 600, loss[loss=0.1575, simple_loss=0.2578, pruned_loss=0.02863, over 7211.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2604, pruned_loss=0.0302, over 1358126.39 frames.], batch size: 23, lr: 2.17e-04
+2022-04-30 18:46:44,900 INFO [train.py:763] (6/8) Epoch 35, batch 650, loss[loss=0.1476, simple_loss=0.256, pruned_loss=0.01961, over 7152.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2594, pruned_loss=0.03011, over 1372506.22 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 18:47:52,735 INFO [train.py:763] (6/8) Epoch 35, batch 700, loss[loss=0.1444, simple_loss=0.2423, pruned_loss=0.02321, over 7232.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2592, pruned_loss=0.02983, over 1384229.61 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 18:48:58,272 INFO [train.py:763] (6/8) Epoch 35, batch 750, loss[loss=0.1656, simple_loss=0.2577, pruned_loss=0.03676, over 7329.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2594, pruned_loss=0.02986, over 1384283.57 frames.], batch size: 20, lr: 2.17e-04
+2022-04-30 18:50:03,734 INFO [train.py:763] (6/8) Epoch 35, batch 800, loss[loss=0.1696, simple_loss=0.281, pruned_loss=0.02913, over 7421.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2597, pruned_loss=0.02975, over 1393112.25 frames.], batch size: 21, lr: 2.17e-04
+2022-04-30 18:51:09,202 INFO [train.py:763] (6/8) Epoch 35, batch 850, loss[loss=0.1605, simple_loss=0.2702, pruned_loss=0.02538, over 7220.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2599, pruned_loss=0.02973, over 1395103.50 frames.], batch size: 21, lr: 2.17e-04
+2022-04-30 18:52:23,431 INFO [train.py:763] (6/8) Epoch 35, batch 900, loss[loss=0.1524, simple_loss=0.256, pruned_loss=0.02444, over 6800.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2599, pruned_loss=0.02991, over 1402524.11 frames.], batch size: 31, lr: 2.17e-04
+2022-04-30 18:53:37,769 INFO [train.py:763] (6/8) Epoch 35, batch 950, loss[loss=0.134, simple_loss=0.2249, pruned_loss=0.02162, over 7008.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2603, pruned_loss=0.0302, over 1405509.55 frames.], batch size: 16, lr: 2.17e-04
+2022-04-30 18:54:42,876 INFO [train.py:763] (6/8) Epoch 35, batch 1000, loss[loss=0.1559, simple_loss=0.2497, pruned_loss=0.03103, over 7266.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2604, pruned_loss=0.03006, over 1406600.72 frames.], batch size: 17, lr: 2.17e-04
+2022-04-30 18:55:57,241 INFO [train.py:763] (6/8) Epoch 35, batch 1050, loss[loss=0.1515, simple_loss=0.2478, pruned_loss=0.0276, over 7356.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2599, pruned_loss=0.02983, over 1407125.18 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 18:57:20,344 INFO [train.py:763] (6/8) Epoch 35, batch 1100, loss[loss=0.1779, simple_loss=0.286, pruned_loss=0.03487, over 7206.00 frames.], tot_loss[loss=0.1599, simple_loss=0.26, pruned_loss=0.02991, over 1407411.25 frames.], batch size: 22, lr: 2.17e-04
+2022-04-30 18:58:25,986 INFO [train.py:763] (6/8) Epoch 35, batch 1150, loss[loss=0.1637, simple_loss=0.2699, pruned_loss=0.02878, over 7265.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2596, pruned_loss=0.02993, over 1412360.84 frames.], batch size: 24, lr: 2.17e-04
+2022-04-30 18:59:32,076 INFO [train.py:763] (6/8) Epoch 35, batch 1200, loss[loss=0.1471, simple_loss=0.2346, pruned_loss=0.02983, over 7281.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2605, pruned_loss=0.0305, over 1407780.77 frames.], batch size: 17, lr: 2.17e-04
+2022-04-30 19:00:55,256 INFO [train.py:763] (6/8) Epoch 35, batch 1250, loss[loss=0.1507, simple_loss=0.2445, pruned_loss=0.02845, over 7002.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2599, pruned_loss=0.03024, over 1409208.47 frames.], batch size: 16, lr: 2.17e-04
+2022-04-30 19:02:00,725 INFO [train.py:763] (6/8) Epoch 35, batch 1300, loss[loss=0.1367, simple_loss=0.2292, pruned_loss=0.02209, over 7156.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2601, pruned_loss=0.03042, over 1412822.32 frames.], batch size: 17, lr: 2.17e-04
+2022-04-30 19:03:07,767 INFO [train.py:763] (6/8) Epoch 35, batch 1350, loss[loss=0.1663, simple_loss=0.2616, pruned_loss=0.03552, over 7254.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2599, pruned_loss=0.03019, over 1418324.81 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 19:04:12,917 INFO [train.py:763] (6/8) Epoch 35, batch 1400, loss[loss=0.1301, simple_loss=0.2146, pruned_loss=0.02282, over 6994.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03006, over 1417093.20 frames.], batch size: 16, lr: 2.17e-04
+2022-04-30 19:05:18,874 INFO [train.py:763] (6/8) Epoch 35, batch 1450, loss[loss=0.1604, simple_loss=0.2485, pruned_loss=0.0361, over 7194.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2597, pruned_loss=0.02983, over 1414661.01 frames.], batch size: 16, lr: 2.17e-04
+2022-04-30 19:06:24,727 INFO [train.py:763] (6/8) Epoch 35, batch 1500, loss[loss=0.157, simple_loss=0.2668, pruned_loss=0.02361, over 7327.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2596, pruned_loss=0.02936, over 1418499.70 frames.], batch size: 21, lr: 2.17e-04
+2022-04-30 19:07:30,580 INFO [train.py:763] (6/8) Epoch 35, batch 1550, loss[loss=0.1643, simple_loss=0.2724, pruned_loss=0.02808, over 7233.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2597, pruned_loss=0.02927, over 1419567.52 frames.], batch size: 20, lr: 2.17e-04
+2022-04-30 19:08:36,019 INFO [train.py:763] (6/8) Epoch 35, batch 1600, loss[loss=0.1895, simple_loss=0.2824, pruned_loss=0.0483, over 7374.00 frames.], tot_loss[loss=0.159, simple_loss=0.259, pruned_loss=0.02955, over 1419575.04 frames.], batch size: 23, lr: 2.16e-04
+2022-04-30 19:09:42,626 INFO [train.py:763] (6/8) Epoch 35, batch 1650, loss[loss=0.1665, simple_loss=0.2687, pruned_loss=0.03219, over 7154.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2591, pruned_loss=0.0297, over 1420474.78 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:10:49,565 INFO [train.py:763] (6/8) Epoch 35, batch 1700, loss[loss=0.1763, simple_loss=0.2766, pruned_loss=0.03796, over 7271.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2595, pruned_loss=0.02941, over 1423524.37 frames.], batch size: 25, lr: 2.16e-04
+2022-04-30 19:11:56,504 INFO [train.py:763] (6/8) Epoch 35, batch 1750, loss[loss=0.1494, simple_loss=0.2427, pruned_loss=0.02808, over 7260.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2599, pruned_loss=0.02955, over 1420566.90 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:13:03,550 INFO [train.py:763] (6/8) Epoch 35, batch 1800, loss[loss=0.1774, simple_loss=0.279, pruned_loss=0.03791, over 7207.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2603, pruned_loss=0.02961, over 1422179.35 frames.], batch size: 23, lr: 2.16e-04
+2022-04-30 19:14:09,381 INFO [train.py:763] (6/8) Epoch 35, batch 1850, loss[loss=0.1991, simple_loss=0.304, pruned_loss=0.04707, over 7120.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2599, pruned_loss=0.02932, over 1425274.53 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:15:15,152 INFO [train.py:763] (6/8) Epoch 35, batch 1900, loss[loss=0.161, simple_loss=0.2742, pruned_loss=0.02388, over 6756.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.02941, over 1426875.48 frames.], batch size: 31, lr: 2.16e-04
+2022-04-30 19:16:21,441 INFO [train.py:763] (6/8) Epoch 35, batch 1950, loss[loss=0.1562, simple_loss=0.2646, pruned_loss=0.02391, over 7232.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2598, pruned_loss=0.02973, over 1424079.77 frames.], batch size: 20, lr: 2.16e-04
+2022-04-30 19:17:27,501 INFO [train.py:763] (6/8) Epoch 35, batch 2000, loss[loss=0.1433, simple_loss=0.2342, pruned_loss=0.02624, over 7012.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2611, pruned_loss=0.0301, over 1421513.11 frames.], batch size: 16, lr: 2.16e-04
+2022-04-30 19:18:34,537 INFO [train.py:763] (6/8) Epoch 35, batch 2050, loss[loss=0.1845, simple_loss=0.2872, pruned_loss=0.04092, over 7313.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2605, pruned_loss=0.02982, over 1425763.56 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:19:40,358 INFO [train.py:763] (6/8) Epoch 35, batch 2100, loss[loss=0.1616, simple_loss=0.2607, pruned_loss=0.03127, over 7412.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2597, pruned_loss=0.02962, over 1424035.47 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:20:47,328 INFO [train.py:763] (6/8) Epoch 35, batch 2150, loss[loss=0.1498, simple_loss=0.2525, pruned_loss=0.02349, over 7256.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2591, pruned_loss=0.0292, over 1426313.75 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:21:54,059 INFO [train.py:763] (6/8) Epoch 35, batch 2200, loss[loss=0.1418, simple_loss=0.2315, pruned_loss=0.02603, over 7414.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2593, pruned_loss=0.02918, over 1425270.01 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:23:01,262 INFO [train.py:763] (6/8) Epoch 35, batch 2250, loss[loss=0.1699, simple_loss=0.2801, pruned_loss=0.02987, over 7328.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2593, pruned_loss=0.02898, over 1421493.88 frames.], batch size: 22, lr: 2.16e-04
+2022-04-30 19:24:07,987 INFO [train.py:763] (6/8) Epoch 35, batch 2300, loss[loss=0.1557, simple_loss=0.2519, pruned_loss=0.02979, over 7125.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2584, pruned_loss=0.02911, over 1425009.79 frames.], batch size: 17, lr: 2.16e-04
+2022-04-30 19:25:12,950 INFO [train.py:763] (6/8) Epoch 35, batch 2350, loss[loss=0.1693, simple_loss=0.2656, pruned_loss=0.03655, over 5022.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2601, pruned_loss=0.02951, over 1423804.79 frames.], batch size: 52, lr: 2.16e-04
+2022-04-30 19:26:18,890 INFO [train.py:763] (6/8) Epoch 35, batch 2400, loss[loss=0.1424, simple_loss=0.2385, pruned_loss=0.02311, over 7417.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2597, pruned_loss=0.02932, over 1426583.99 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:27:24,048 INFO [train.py:763] (6/8) Epoch 35, batch 2450, loss[loss=0.136, simple_loss=0.2343, pruned_loss=0.01885, over 7174.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2591, pruned_loss=0.02927, over 1421865.27 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:28:30,199 INFO [train.py:763] (6/8) Epoch 35, batch 2500, loss[loss=0.1511, simple_loss=0.2453, pruned_loss=0.02846, over 7144.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2595, pruned_loss=0.02974, over 1426713.54 frames.], batch size: 20, lr: 2.16e-04
+2022-04-30 19:29:36,784 INFO [train.py:763] (6/8) Epoch 35, batch 2550, loss[loss=0.1367, simple_loss=0.2314, pruned_loss=0.02107, over 7361.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2598, pruned_loss=0.02989, over 1424325.73 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:30:41,923 INFO [train.py:763] (6/8) Epoch 35, batch 2600, loss[loss=0.1464, simple_loss=0.255, pruned_loss=0.01891, over 7152.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2595, pruned_loss=0.02962, over 1425512.62 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:31:47,695 INFO [train.py:763] (6/8) Epoch 35, batch 2650, loss[loss=0.2116, simple_loss=0.3049, pruned_loss=0.05921, over 4977.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2592, pruned_loss=0.02974, over 1424060.49 frames.], batch size: 53, lr: 2.16e-04
+2022-04-30 19:32:53,214 INFO [train.py:763] (6/8) Epoch 35, batch 2700, loss[loss=0.1567, simple_loss=0.2663, pruned_loss=0.02351, over 7308.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2586, pruned_loss=0.0299, over 1425140.62 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:33:59,269 INFO [train.py:763] (6/8) Epoch 35, batch 2750, loss[loss=0.1552, simple_loss=0.2594, pruned_loss=0.02548, over 7120.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2591, pruned_loss=0.03011, over 1426536.56 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:35:05,457 INFO [train.py:763] (6/8) Epoch 35, batch 2800, loss[loss=0.1716, simple_loss=0.2843, pruned_loss=0.02946, over 7202.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2588, pruned_loss=0.03024, over 1428220.93 frames.], batch size: 22, lr: 2.16e-04
+2022-04-30 19:36:12,140 INFO [train.py:763] (6/8) Epoch 35, batch 2850, loss[loss=0.14, simple_loss=0.2346, pruned_loss=0.02267, over 7297.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2582, pruned_loss=0.02998, over 1428994.57 frames.], batch size: 17, lr: 2.16e-04
+2022-04-30 19:37:18,076 INFO [train.py:763] (6/8) Epoch 35, batch 2900, loss[loss=0.1243, simple_loss=0.2299, pruned_loss=0.009364, over 7258.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2571, pruned_loss=0.02967, over 1428348.11 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:38:23,361 INFO [train.py:763] (6/8) Epoch 35, batch 2950, loss[loss=0.1358, simple_loss=0.2364, pruned_loss=0.01762, over 7172.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2586, pruned_loss=0.02994, over 1425988.44 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:39:28,872 INFO [train.py:763] (6/8) Epoch 35, batch 3000, loss[loss=0.1386, simple_loss=0.2359, pruned_loss=0.02061, over 7165.00 frames.], tot_loss[loss=0.1605, simple_loss=0.26, pruned_loss=0.03046, over 1423138.41 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:39:28,873 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 19:39:43,929 INFO [train.py:792] (6/8) Epoch 35, validation: loss=0.1681, simple_loss=0.2634, pruned_loss=0.03644, over 698248.00 frames.
+2022-04-30 19:40:49,417 INFO [train.py:763] (6/8) Epoch 35, batch 3050, loss[loss=0.1571, simple_loss=0.2617, pruned_loss=0.02627, over 7276.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2602, pruned_loss=0.03065, over 1424935.77 frames.], batch size: 24, lr: 2.16e-04
+2022-04-30 19:41:55,474 INFO [train.py:763] (6/8) Epoch 35, batch 3100, loss[loss=0.171, simple_loss=0.2756, pruned_loss=0.03319, over 7304.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2604, pruned_loss=0.03041, over 1428994.59 frames.], batch size: 25, lr: 2.15e-04
+2022-04-30 19:43:02,578 INFO [train.py:763] (6/8) Epoch 35, batch 3150, loss[loss=0.1535, simple_loss=0.2659, pruned_loss=0.02051, over 7370.00 frames.], tot_loss[loss=0.16, simple_loss=0.2599, pruned_loss=0.03007, over 1427079.84 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 19:44:09,466 INFO [train.py:763] (6/8) Epoch 35, batch 3200, loss[loss=0.157, simple_loss=0.2385, pruned_loss=0.03775, over 7150.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2602, pruned_loss=0.03042, over 1419977.77 frames.], batch size: 17, lr: 2.15e-04
+2022-04-30 19:45:15,567 INFO [train.py:763] (6/8) Epoch 35, batch 3250, loss[loss=0.1608, simple_loss=0.2538, pruned_loss=0.03394, over 5106.00 frames.], tot_loss[loss=0.16, simple_loss=0.2596, pruned_loss=0.03021, over 1417714.38 frames.], batch size: 52, lr: 2.15e-04
+2022-04-30 19:46:21,013 INFO [train.py:763] (6/8) Epoch 35, batch 3300, loss[loss=0.1731, simple_loss=0.2682, pruned_loss=0.039, over 7193.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2597, pruned_loss=0.03006, over 1421357.57 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 19:47:26,300 INFO [train.py:763] (6/8) Epoch 35, batch 3350, loss[loss=0.1509, simple_loss=0.2488, pruned_loss=0.02649, over 7202.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2594, pruned_loss=0.02949, over 1425083.62 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 19:48:32,222 INFO [train.py:763] (6/8) Epoch 35, batch 3400, loss[loss=0.1384, simple_loss=0.2405, pruned_loss=0.01819, over 7261.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2588, pruned_loss=0.02915, over 1424457.89 frames.], batch size: 19, lr: 2.15e-04
+2022-04-30 19:49:37,618 INFO [train.py:763] (6/8) Epoch 35, batch 3450, loss[loss=0.1396, simple_loss=0.2317, pruned_loss=0.02379, over 7278.00 frames.], tot_loss[loss=0.159, simple_loss=0.2591, pruned_loss=0.02939, over 1421555.86 frames.], batch size: 17, lr: 2.15e-04
+2022-04-30 19:50:43,218 INFO [train.py:763] (6/8) Epoch 35, batch 3500, loss[loss=0.1537, simple_loss=0.2558, pruned_loss=0.0258, over 7421.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2588, pruned_loss=0.02984, over 1418729.05 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 19:51:48,957 INFO [train.py:763] (6/8) Epoch 35, batch 3550, loss[loss=0.1639, simple_loss=0.2621, pruned_loss=0.03288, over 7073.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2582, pruned_loss=0.02946, over 1422696.24 frames.], batch size: 28, lr: 2.15e-04
+2022-04-30 19:52:54,556 INFO [train.py:763] (6/8) Epoch 35, batch 3600, loss[loss=0.1884, simple_loss=0.2902, pruned_loss=0.04325, over 7259.00 frames.], tot_loss[loss=0.159, simple_loss=0.2586, pruned_loss=0.02966, over 1421609.68 frames.], batch size: 25, lr: 2.15e-04
+2022-04-30 19:54:00,483 INFO [train.py:763] (6/8) Epoch 35, batch 3650, loss[loss=0.1651, simple_loss=0.2692, pruned_loss=0.03048, over 7287.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2584, pruned_loss=0.0292, over 1422812.53 frames.], batch size: 24, lr: 2.15e-04
+2022-04-30 19:55:05,855 INFO [train.py:763] (6/8) Epoch 35, batch 3700, loss[loss=0.1557, simple_loss=0.2643, pruned_loss=0.02355, over 7109.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2585, pruned_loss=0.0295, over 1425739.86 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 19:56:11,429 INFO [train.py:763] (6/8) Epoch 35, batch 3750, loss[loss=0.1641, simple_loss=0.2636, pruned_loss=0.03229, over 7327.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2591, pruned_loss=0.02966, over 1424945.12 frames.], batch size: 22, lr: 2.15e-04
+2022-04-30 19:57:16,646 INFO [train.py:763] (6/8) Epoch 35, batch 3800, loss[loss=0.1444, simple_loss=0.2388, pruned_loss=0.02504, over 7362.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2604, pruned_loss=0.03004, over 1427098.26 frames.], batch size: 19, lr: 2.15e-04
+2022-04-30 19:58:21,846 INFO [train.py:763] (6/8) Epoch 35, batch 3850, loss[loss=0.1332, simple_loss=0.225, pruned_loss=0.02066, over 7437.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.03018, over 1423801.10 frames.], batch size: 17, lr: 2.15e-04
+2022-04-30 19:59:27,368 INFO [train.py:763] (6/8) Epoch 35, batch 3900, loss[loss=0.1711, simple_loss=0.2795, pruned_loss=0.03135, over 7186.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2599, pruned_loss=0.02992, over 1426072.72 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 20:00:33,650 INFO [train.py:763] (6/8) Epoch 35, batch 3950, loss[loss=0.1647, simple_loss=0.2663, pruned_loss=0.03156, over 6821.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2609, pruned_loss=0.03012, over 1424496.54 frames.], batch size: 31, lr: 2.15e-04
+2022-04-30 20:01:41,043 INFO [train.py:763] (6/8) Epoch 35, batch 4000, loss[loss=0.1745, simple_loss=0.2833, pruned_loss=0.03284, over 7048.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2611, pruned_loss=0.03007, over 1424447.90 frames.], batch size: 28, lr: 2.15e-04
+2022-04-30 20:02:46,172 INFO [train.py:763] (6/8) Epoch 35, batch 4050, loss[loss=0.1567, simple_loss=0.2575, pruned_loss=0.02798, over 7222.00 frames.], tot_loss[loss=0.16, simple_loss=0.2605, pruned_loss=0.02977, over 1427163.88 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 20:03:51,653 INFO [train.py:763] (6/8) Epoch 35, batch 4100, loss[loss=0.142, simple_loss=0.2375, pruned_loss=0.02324, over 7136.00 frames.], tot_loss[loss=0.1594, simple_loss=0.26, pruned_loss=0.02941, over 1426995.59 frames.], batch size: 17, lr: 2.15e-04
+2022-04-30 20:04:57,465 INFO [train.py:763] (6/8) Epoch 35, batch 4150, loss[loss=0.1496, simple_loss=0.2623, pruned_loss=0.01843, over 7205.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02943, over 1420587.37 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 20:06:03,151 INFO [train.py:763] (6/8) Epoch 35, batch 4200, loss[loss=0.1664, simple_loss=0.2672, pruned_loss=0.03276, over 7236.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2594, pruned_loss=0.02975, over 1417724.82 frames.], batch size: 20, lr: 2.15e-04
+2022-04-30 20:07:09,101 INFO [train.py:763] (6/8) Epoch 35, batch 4250, loss[loss=0.1672, simple_loss=0.263, pruned_loss=0.03572, over 7204.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2594, pruned_loss=0.02979, over 1416688.94 frames.], batch size: 22, lr: 2.15e-04
+2022-04-30 20:08:14,297 INFO [train.py:763] (6/8) Epoch 35, batch 4300, loss[loss=0.1711, simple_loss=0.263, pruned_loss=0.03961, over 7204.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2589, pruned_loss=0.02969, over 1413110.29 frames.], batch size: 22, lr: 2.15e-04
+2022-04-30 20:09:20,407 INFO [train.py:763] (6/8) Epoch 35, batch 4350, loss[loss=0.1669, simple_loss=0.2673, pruned_loss=0.03321, over 7433.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2578, pruned_loss=0.02927, over 1411977.60 frames.], batch size: 20, lr: 2.15e-04
+2022-04-30 20:10:26,458 INFO [train.py:763] (6/8) Epoch 35, batch 4400, loss[loss=0.1313, simple_loss=0.2298, pruned_loss=0.0164, over 7353.00 frames.], tot_loss[loss=0.1572, simple_loss=0.257, pruned_loss=0.02868, over 1416692.13 frames.], batch size: 19, lr: 2.15e-04
+2022-04-30 20:11:33,066 INFO [train.py:763] (6/8) Epoch 35, batch 4450, loss[loss=0.1662, simple_loss=0.275, pruned_loss=0.02873, over 7223.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2568, pruned_loss=0.02879, over 1406150.94 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 20:12:39,737 INFO [train.py:763] (6/8) Epoch 35, batch 4500, loss[loss=0.15, simple_loss=0.2551, pruned_loss=0.02248, over 7231.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2576, pruned_loss=0.02904, over 1393929.80 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 20:13:46,254 INFO [train.py:763] (6/8) Epoch 35, batch 4550, loss[loss=0.1498, simple_loss=0.2524, pruned_loss=0.02363, over 7258.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2591, pruned_loss=0.02998, over 1354892.50 frames.], batch size: 19, lr: 2.15e-04
+2022-04-30 20:15:13,847 INFO [train.py:763] (6/8) Epoch 36, batch 0, loss[loss=0.1607, simple_loss=0.2668, pruned_loss=0.02727, over 7336.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2668, pruned_loss=0.02727, over 7336.00 frames.], batch size: 22, lr: 2.12e-04
+2022-04-30 20:16:19,180 INFO [train.py:763] (6/8) Epoch 36, batch 50, loss[loss=0.1525, simple_loss=0.2487, pruned_loss=0.02812, over 7068.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2624, pruned_loss=0.03069, over 320659.74 frames.], batch size: 18, lr: 2.12e-04
+2022-04-30 20:17:24,381 INFO [train.py:763] (6/8) Epoch 36, batch 100, loss[loss=0.1471, simple_loss=0.2509, pruned_loss=0.02163, over 7326.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2614, pruned_loss=0.0296, over 566617.66 frames.], batch size: 20, lr: 2.12e-04
+2022-04-30 20:18:29,498 INFO [train.py:763] (6/8) Epoch 36, batch 150, loss[loss=0.1534, simple_loss=0.2638, pruned_loss=0.02148, over 7078.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2603, pruned_loss=0.02918, over 753834.49 frames.], batch size: 28, lr: 2.11e-04
+2022-04-30 20:19:34,475 INFO [train.py:763] (6/8) Epoch 36, batch 200, loss[loss=0.1654, simple_loss=0.2743, pruned_loss=0.02825, over 7315.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2616, pruned_loss=0.02886, over 905147.67 frames.], batch size: 21, lr: 2.11e-04
+2022-04-30 20:20:39,731 INFO [train.py:763] (6/8) Epoch 36, batch 250, loss[loss=0.1625, simple_loss=0.2653, pruned_loss=0.02985, over 7263.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2609, pruned_loss=0.02915, over 1016792.30 frames.], batch size: 19, lr: 2.11e-04
+2022-04-30 20:21:45,227 INFO [train.py:763] (6/8) Epoch 36, batch 300, loss[loss=0.1735, simple_loss=0.2817, pruned_loss=0.03261, over 7328.00 frames.], tot_loss[loss=0.1593, simple_loss=0.26, pruned_loss=0.02929, over 1102764.64 frames.], batch size: 22, lr: 2.11e-04
+2022-04-30 20:22:50,518 INFO [train.py:763] (6/8) Epoch 36, batch 350, loss[loss=0.154, simple_loss=0.2531, pruned_loss=0.02748, over 7170.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2603, pruned_loss=0.02928, over 1171539.51 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:23:55,934 INFO [train.py:763] (6/8) Epoch 36, batch 400, loss[loss=0.144, simple_loss=0.2467, pruned_loss=0.02068, over 7235.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2597, pruned_loss=0.0289, over 1230800.37 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:25:01,048 INFO [train.py:763] (6/8) Epoch 36, batch 450, loss[loss=0.1634, simple_loss=0.2628, pruned_loss=0.03199, over 7153.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2594, pruned_loss=0.02877, over 1275604.80 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:26:07,077 INFO [train.py:763] (6/8) Epoch 36, batch 500, loss[loss=0.1559, simple_loss=0.2593, pruned_loss=0.02629, over 7233.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2589, pruned_loss=0.0287, over 1306143.63 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:27:14,408 INFO [train.py:763] (6/8) Epoch 36, batch 550, loss[loss=0.1387, simple_loss=0.2322, pruned_loss=0.02261, over 7073.00 frames.], tot_loss[loss=0.1584, simple_loss=0.259, pruned_loss=0.02887, over 1322941.58 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:28:22,079 INFO [train.py:763] (6/8) Epoch 36, batch 600, loss[loss=0.1697, simple_loss=0.2662, pruned_loss=0.03667, over 7431.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2581, pruned_loss=0.02882, over 1348150.32 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:29:29,898 INFO [train.py:763] (6/8) Epoch 36, batch 650, loss[loss=0.1346, simple_loss=0.228, pruned_loss=0.02056, over 7128.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2569, pruned_loss=0.02884, over 1366965.64 frames.], batch size: 17, lr: 2.11e-04
+2022-04-30 20:30:35,971 INFO [train.py:763] (6/8) Epoch 36, batch 700, loss[loss=0.178, simple_loss=0.2874, pruned_loss=0.03427, over 7228.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2579, pruned_loss=0.02926, over 1379915.94 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:31:41,364 INFO [train.py:763] (6/8) Epoch 36, batch 750, loss[loss=0.1765, simple_loss=0.2771, pruned_loss=0.03797, over 7160.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2577, pruned_loss=0.02937, over 1388475.03 frames.], batch size: 19, lr: 2.11e-04
+2022-04-30 20:32:47,597 INFO [train.py:763] (6/8) Epoch 36, batch 800, loss[loss=0.1486, simple_loss=0.2414, pruned_loss=0.0279, over 7399.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2575, pruned_loss=0.02936, over 1398602.02 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:33:53,518 INFO [train.py:763] (6/8) Epoch 36, batch 850, loss[loss=0.1465, simple_loss=0.2356, pruned_loss=0.02868, over 7255.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2593, pruned_loss=0.03004, over 1398002.59 frames.], batch size: 19, lr: 2.11e-04
+2022-04-30 20:34:59,126 INFO [train.py:763] (6/8) Epoch 36, batch 900, loss[loss=0.1408, simple_loss=0.2357, pruned_loss=0.02299, over 7066.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2584, pruned_loss=0.02966, over 1407030.90 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:36:04,438 INFO [train.py:763] (6/8) Epoch 36, batch 950, loss[loss=0.1367, simple_loss=0.2294, pruned_loss=0.02198, over 7296.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2588, pruned_loss=0.0298, over 1410962.55 frames.], batch size: 17, lr: 2.11e-04
+2022-04-30 20:37:09,730 INFO [train.py:763] (6/8) Epoch 36, batch 1000, loss[loss=0.1789, simple_loss=0.2847, pruned_loss=0.03655, over 6874.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2589, pruned_loss=0.02931, over 1413557.76 frames.], batch size: 31, lr: 2.11e-04
+2022-04-30 20:38:15,273 INFO [train.py:763] (6/8) Epoch 36, batch 1050, loss[loss=0.154, simple_loss=0.2602, pruned_loss=0.02388, over 7367.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2583, pruned_loss=0.02895, over 1417735.84 frames.], batch size: 23, lr: 2.11e-04
+2022-04-30 20:39:20,505 INFO [train.py:763] (6/8) Epoch 36, batch 1100, loss[loss=0.1622, simple_loss=0.2586, pruned_loss=0.03285, over 7226.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2582, pruned_loss=0.029, over 1418901.81 frames.], batch size: 21, lr: 2.11e-04
+2022-04-30 20:40:26,463 INFO [train.py:763] (6/8) Epoch 36, batch 1150, loss[loss=0.1669, simple_loss=0.264, pruned_loss=0.03494, over 4934.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2579, pruned_loss=0.02867, over 1418026.82 frames.], batch size: 52, lr: 2.11e-04
+2022-04-30 20:41:32,755 INFO [train.py:763] (6/8) Epoch 36, batch 1200, loss[loss=0.1545, simple_loss=0.2641, pruned_loss=0.02241, over 7147.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2587, pruned_loss=0.02877, over 1419793.01 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:42:37,808 INFO [train.py:763] (6/8) Epoch 36, batch 1250, loss[loss=0.1639, simple_loss=0.2654, pruned_loss=0.03121, over 7211.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.02865, over 1420087.22 frames.], batch size: 22, lr: 2.11e-04
+2022-04-30 20:43:42,983 INFO [train.py:763] (6/8) Epoch 36, batch 1300, loss[loss=0.1501, simple_loss=0.2368, pruned_loss=0.03173, over 7159.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2589, pruned_loss=0.02884, over 1422428.69 frames.], batch size: 17, lr: 2.11e-04
+2022-04-30 20:44:48,210 INFO [train.py:763] (6/8) Epoch 36, batch 1350, loss[loss=0.1406, simple_loss=0.2307, pruned_loss=0.02522, over 7064.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.02879, over 1418120.15 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:45:54,981 INFO [train.py:763] (6/8) Epoch 36, batch 1400, loss[loss=0.1261, simple_loss=0.2138, pruned_loss=0.01921, over 6991.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2587, pruned_loss=0.02899, over 1417996.26 frames.], batch size: 16, lr: 2.11e-04
+2022-04-30 20:47:00,118 INFO [train.py:763] (6/8) Epoch 36, batch 1450, loss[loss=0.1741, simple_loss=0.2746, pruned_loss=0.03676, over 7268.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2599, pruned_loss=0.02939, over 1419421.38 frames.], batch size: 24, lr: 2.11e-04
+2022-04-30 20:48:05,224 INFO [train.py:763] (6/8) Epoch 36, batch 1500, loss[loss=0.1927, simple_loss=0.2988, pruned_loss=0.04326, over 7292.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2599, pruned_loss=0.02922, over 1416329.95 frames.], batch size: 24, lr: 2.11e-04
+2022-04-30 20:49:10,951 INFO [train.py:763] (6/8) Epoch 36, batch 1550, loss[loss=0.1553, simple_loss=0.2656, pruned_loss=0.02249, over 6922.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2603, pruned_loss=0.02975, over 1412483.93 frames.], batch size: 32, lr: 2.11e-04
+2022-04-30 20:50:16,848 INFO [train.py:763] (6/8) Epoch 36, batch 1600, loss[loss=0.1777, simple_loss=0.282, pruned_loss=0.03665, over 7375.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2593, pruned_loss=0.0292, over 1412579.47 frames.], batch size: 23, lr: 2.11e-04
+2022-04-30 20:51:24,012 INFO [train.py:763] (6/8) Epoch 36, batch 1650, loss[loss=0.1749, simple_loss=0.2795, pruned_loss=0.03513, over 7218.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2592, pruned_loss=0.02918, over 1415697.25 frames.], batch size: 22, lr: 2.11e-04
+2022-04-30 20:52:38,231 INFO [train.py:763] (6/8) Epoch 36, batch 1700, loss[loss=0.1542, simple_loss=0.2622, pruned_loss=0.02312, over 7160.00 frames.], tot_loss[loss=0.1593, simple_loss=0.26, pruned_loss=0.02928, over 1414413.29 frames.], batch size: 19, lr: 2.11e-04
+2022-04-30 20:53:43,584 INFO [train.py:763] (6/8) Epoch 36, batch 1750, loss[loss=0.1432, simple_loss=0.2477, pruned_loss=0.0194, over 7359.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2598, pruned_loss=0.02933, over 1408872.02 frames.], batch size: 19, lr: 2.10e-04
+2022-04-30 20:54:48,732 INFO [train.py:763] (6/8) Epoch 36, batch 1800, loss[loss=0.1752, simple_loss=0.2754, pruned_loss=0.03755, over 7302.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2607, pruned_loss=0.02998, over 1411200.10 frames.], batch size: 24, lr: 2.10e-04
+2022-04-30 20:55:54,037 INFO [train.py:763] (6/8) Epoch 36, batch 1850, loss[loss=0.1712, simple_loss=0.2633, pruned_loss=0.03955, over 7271.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2603, pruned_loss=0.02996, over 1411424.22 frames.], batch size: 19, lr: 2.10e-04
+2022-04-30 20:56:59,660 INFO [train.py:763] (6/8) Epoch 36, batch 1900, loss[loss=0.1468, simple_loss=0.2479, pruned_loss=0.02282, over 6729.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2608, pruned_loss=0.03, over 1417038.31 frames.], batch size: 31, lr: 2.10e-04
+2022-04-30 20:58:07,235 INFO [train.py:763] (6/8) Epoch 36, batch 1950, loss[loss=0.1543, simple_loss=0.2557, pruned_loss=0.02647, over 7213.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2599, pruned_loss=0.03033, over 1419989.15 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 20:59:14,631 INFO [train.py:763] (6/8) Epoch 36, batch 2000, loss[loss=0.176, simple_loss=0.2864, pruned_loss=0.03283, over 7400.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2601, pruned_loss=0.03015, over 1416698.98 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 21:00:22,194 INFO [train.py:763] (6/8) Epoch 36, batch 2050, loss[loss=0.1663, simple_loss=0.2714, pruned_loss=0.03063, over 7238.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03026, over 1420319.66 frames.], batch size: 20, lr: 2.10e-04
+2022-04-30 21:01:28,531 INFO [train.py:763] (6/8) Epoch 36, batch 2100, loss[loss=0.1619, simple_loss=0.2666, pruned_loss=0.02858, over 7148.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2599, pruned_loss=0.02995, over 1420062.92 frames.], batch size: 20, lr: 2.10e-04
+2022-04-30 21:02:35,091 INFO [train.py:763] (6/8) Epoch 36, batch 2150, loss[loss=0.1566, simple_loss=0.261, pruned_loss=0.02606, over 7414.00 frames.], tot_loss[loss=0.1598, simple_loss=0.26, pruned_loss=0.02983, over 1417421.44 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 21:03:42,384 INFO [train.py:763] (6/8) Epoch 36, batch 2200, loss[loss=0.1635, simple_loss=0.2538, pruned_loss=0.03657, over 7251.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2595, pruned_loss=0.02975, over 1419036.44 frames.], batch size: 19, lr: 2.10e-04
+2022-04-30 21:04:49,053 INFO [train.py:763] (6/8) Epoch 36, batch 2250, loss[loss=0.1617, simple_loss=0.2624, pruned_loss=0.03047, over 7155.00 frames.], tot_loss[loss=0.16, simple_loss=0.26, pruned_loss=0.02996, over 1419123.24 frames.], batch size: 20, lr: 2.10e-04
+2022-04-30 21:05:54,013 INFO [train.py:763] (6/8) Epoch 36, batch 2300, loss[loss=0.1746, simple_loss=0.2697, pruned_loss=0.03976, over 7192.00 frames.], tot_loss[loss=0.16, simple_loss=0.2602, pruned_loss=0.02991, over 1418644.37 frames.], batch size: 23, lr: 2.10e-04
+2022-04-30 21:06:59,114 INFO [train.py:763] (6/8) Epoch 36, batch 2350, loss[loss=0.1369, simple_loss=0.2276, pruned_loss=0.02307, over 7277.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2604, pruned_loss=0.03007, over 1413266.78 frames.], batch size: 17, lr: 2.10e-04
+2022-04-30 21:08:06,482 INFO [train.py:763] (6/8) Epoch 36, batch 2400, loss[loss=0.1906, simple_loss=0.2899, pruned_loss=0.0456, over 7287.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03015, over 1419717.84 frames.], batch size: 25, lr: 2.10e-04
+2022-04-30 21:09:12,591 INFO [train.py:763] (6/8) Epoch 36, batch 2450, loss[loss=0.1573, simple_loss=0.2675, pruned_loss=0.02354, over 7186.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2601, pruned_loss=0.02982, over 1424923.54 frames.], batch size: 26, lr: 2.10e-04
+2022-04-30 21:10:36,030 INFO [train.py:763] (6/8) Epoch 36, batch 2500, loss[loss=0.1367, simple_loss=0.2407, pruned_loss=0.01634, over 7159.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2591, pruned_loss=0.02953, over 1428336.38 frames.], batch size: 19, lr: 2.10e-04
+2022-04-30 21:11:41,254 INFO [train.py:763] (6/8) Epoch 36, batch 2550, loss[loss=0.2049, simple_loss=0.292, pruned_loss=0.05894, over 7284.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2592, pruned_loss=0.02977, over 1428226.03 frames.], batch size: 24, lr: 2.10e-04
+2022-04-30 21:12:55,224 INFO [train.py:763] (6/8) Epoch 36, batch 2600, loss[loss=0.145, simple_loss=0.2351, pruned_loss=0.02747, over 6804.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2593, pruned_loss=0.02986, over 1424597.80 frames.], batch size: 15, lr: 2.10e-04
+2022-04-30 21:14:18,382 INFO [train.py:763] (6/8) Epoch 36, batch 2650, loss[loss=0.1726, simple_loss=0.2736, pruned_loss=0.03583, over 7197.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2596, pruned_loss=0.02974, over 1427922.23 frames.], batch size: 22, lr: 2.10e-04
+2022-04-30 21:15:32,422 INFO [train.py:763] (6/8) Epoch 36, batch 2700, loss[loss=0.1619, simple_loss=0.2726, pruned_loss=0.02555, over 6532.00 frames.], tot_loss[loss=0.16, simple_loss=0.2602, pruned_loss=0.02988, over 1424146.39 frames.], batch size: 38, lr: 2.10e-04
+2022-04-30 21:16:46,240 INFO [train.py:763] (6/8) Epoch 36, batch 2750, loss[loss=0.2049, simple_loss=0.299, pruned_loss=0.0554, over 5334.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2611, pruned_loss=0.02976, over 1425189.46 frames.], batch size: 52, lr: 2.10e-04
+2022-04-30 21:17:52,035 INFO [train.py:763] (6/8) Epoch 36, batch 2800, loss[loss=0.1579, simple_loss=0.2492, pruned_loss=0.03326, over 7284.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2598, pruned_loss=0.02935, over 1429399.99 frames.], batch size: 18, lr: 2.10e-04
+2022-04-30 21:19:07,515 INFO [train.py:763] (6/8) Epoch 36, batch 2850, loss[loss=0.1752, simple_loss=0.2815, pruned_loss=0.03442, over 6347.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2597, pruned_loss=0.02953, over 1427927.82 frames.], batch size: 38, lr: 2.10e-04
+2022-04-30 21:20:12,993 INFO [train.py:763] (6/8) Epoch 36, batch 2900, loss[loss=0.1337, simple_loss=0.2274, pruned_loss=0.01999, over 6986.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2592, pruned_loss=0.02934, over 1428628.86 frames.], batch size: 16, lr: 2.10e-04
+2022-04-30 21:21:20,753 INFO [train.py:763] (6/8) Epoch 36, batch 2950, loss[loss=0.1526, simple_loss=0.2668, pruned_loss=0.01922, over 7436.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2593, pruned_loss=0.02943, over 1425232.70 frames.], batch size: 20, lr: 2.10e-04
+2022-04-30 21:22:27,899 INFO [train.py:763] (6/8) Epoch 36, batch 3000, loss[loss=0.1552, simple_loss=0.2602, pruned_loss=0.02517, over 7208.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02938, over 1420370.25 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 21:22:27,900 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 21:22:43,065 INFO [train.py:792] (6/8) Epoch 36, validation: loss=0.1683, simple_loss=0.2628, pruned_loss=0.03692, over 698248.00 frames.
+2022-04-30 21:23:48,280 INFO [train.py:763] (6/8) Epoch 36, batch 3050, loss[loss=0.1704, simple_loss=0.2682, pruned_loss=0.03628, over 6775.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2594, pruned_loss=0.02952, over 1418972.77 frames.], batch size: 15, lr: 2.10e-04
+2022-04-30 21:24:54,041 INFO [train.py:763] (6/8) Epoch 36, batch 3100, loss[loss=0.1447, simple_loss=0.2414, pruned_loss=0.02398, over 7073.00 frames.], tot_loss[loss=0.159, simple_loss=0.2589, pruned_loss=0.02957, over 1417815.71 frames.], batch size: 18, lr: 2.10e-04
+2022-04-30 21:26:01,268 INFO [train.py:763] (6/8) Epoch 36, batch 3150, loss[loss=0.1232, simple_loss=0.2205, pruned_loss=0.01291, over 6991.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2584, pruned_loss=0.02921, over 1417007.36 frames.], batch size: 16, lr: 2.10e-04
+2022-04-30 21:27:07,752 INFO [train.py:763] (6/8) Epoch 36, batch 3200, loss[loss=0.1733, simple_loss=0.2696, pruned_loss=0.03854, over 4992.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2584, pruned_loss=0.0292, over 1417417.88 frames.], batch size: 52, lr: 2.10e-04
+2022-04-30 21:28:14,748 INFO [train.py:763] (6/8) Epoch 36, batch 3250, loss[loss=0.1745, simple_loss=0.2735, pruned_loss=0.03774, over 7224.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2588, pruned_loss=0.02939, over 1417067.14 frames.], batch size: 22, lr: 2.10e-04
+2022-04-30 21:29:20,186 INFO [train.py:763] (6/8) Epoch 36, batch 3300, loss[loss=0.1627, simple_loss=0.2641, pruned_loss=0.03065, over 7409.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2593, pruned_loss=0.02992, over 1414149.46 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 21:30:25,145 INFO [train.py:763] (6/8) Epoch 36, batch 3350, loss[loss=0.1819, simple_loss=0.2771, pruned_loss=0.04329, over 7378.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2601, pruned_loss=0.03007, over 1410931.78 frames.], batch size: 23, lr: 2.09e-04
+2022-04-30 21:31:31,786 INFO [train.py:763] (6/8) Epoch 36, batch 3400, loss[loss=0.1457, simple_loss=0.2448, pruned_loss=0.02327, over 7152.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2592, pruned_loss=0.02968, over 1415789.72 frames.], batch size: 17, lr: 2.09e-04
+2022-04-30 21:32:37,220 INFO [train.py:763] (6/8) Epoch 36, batch 3450, loss[loss=0.1539, simple_loss=0.2421, pruned_loss=0.03284, over 7282.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2586, pruned_loss=0.02952, over 1419013.40 frames.], batch size: 17, lr: 2.09e-04
+2022-04-30 21:33:42,450 INFO [train.py:763] (6/8) Epoch 36, batch 3500, loss[loss=0.1419, simple_loss=0.2392, pruned_loss=0.02228, over 7369.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2592, pruned_loss=0.02979, over 1416708.68 frames.], batch size: 19, lr: 2.09e-04
+2022-04-30 21:34:47,629 INFO [train.py:763] (6/8) Epoch 36, batch 3550, loss[loss=0.135, simple_loss=0.2283, pruned_loss=0.02087, over 6826.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2593, pruned_loss=0.02974, over 1413994.08 frames.], batch size: 15, lr: 2.09e-04
+2022-04-30 21:35:54,819 INFO [train.py:763] (6/8) Epoch 36, batch 3600, loss[loss=0.153, simple_loss=0.2402, pruned_loss=0.03294, over 6997.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2586, pruned_loss=0.02966, over 1420126.71 frames.], batch size: 16, lr: 2.09e-04
+2022-04-30 21:37:01,774 INFO [train.py:763] (6/8) Epoch 36, batch 3650, loss[loss=0.131, simple_loss=0.2305, pruned_loss=0.01576, over 7147.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2578, pruned_loss=0.02903, over 1422699.08 frames.], batch size: 19, lr: 2.09e-04
+2022-04-30 21:38:08,985 INFO [train.py:763] (6/8) Epoch 36, batch 3700, loss[loss=0.1706, simple_loss=0.2715, pruned_loss=0.03485, over 7235.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2582, pruned_loss=0.02921, over 1425632.81 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:39:14,212 INFO [train.py:763] (6/8) Epoch 36, batch 3750, loss[loss=0.1887, simple_loss=0.2796, pruned_loss=0.04891, over 7307.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2594, pruned_loss=0.02972, over 1422090.57 frames.], batch size: 24, lr: 2.09e-04
+2022-04-30 21:40:19,606 INFO [train.py:763] (6/8) Epoch 36, batch 3800, loss[loss=0.1358, simple_loss=0.2298, pruned_loss=0.02096, over 7292.00 frames.], tot_loss[loss=0.1591, simple_loss=0.259, pruned_loss=0.02956, over 1424040.00 frames.], batch size: 17, lr: 2.09e-04
+2022-04-30 21:41:25,005 INFO [train.py:763] (6/8) Epoch 36, batch 3850, loss[loss=0.1603, simple_loss=0.2577, pruned_loss=0.03142, over 5239.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2584, pruned_loss=0.02922, over 1422977.16 frames.], batch size: 52, lr: 2.09e-04
+2022-04-30 21:42:30,258 INFO [train.py:763] (6/8) Epoch 36, batch 3900, loss[loss=0.1593, simple_loss=0.2601, pruned_loss=0.02928, over 7326.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2576, pruned_loss=0.029, over 1425178.68 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:43:35,825 INFO [train.py:763] (6/8) Epoch 36, batch 3950, loss[loss=0.1601, simple_loss=0.2616, pruned_loss=0.02931, over 7274.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2581, pruned_loss=0.02923, over 1426582.77 frames.], batch size: 18, lr: 2.09e-04
+2022-04-30 21:44:41,558 INFO [train.py:763] (6/8) Epoch 36, batch 4000, loss[loss=0.1651, simple_loss=0.2625, pruned_loss=0.03385, over 7154.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2585, pruned_loss=0.02927, over 1427496.87 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:45:48,439 INFO [train.py:763] (6/8) Epoch 36, batch 4050, loss[loss=0.1515, simple_loss=0.2535, pruned_loss=0.02479, over 7138.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2583, pruned_loss=0.02912, over 1426803.59 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:46:54,637 INFO [train.py:763] (6/8) Epoch 36, batch 4100, loss[loss=0.1771, simple_loss=0.2786, pruned_loss=0.03777, over 7350.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2589, pruned_loss=0.02912, over 1424522.21 frames.], batch size: 25, lr: 2.09e-04
+2022-04-30 21:48:00,282 INFO [train.py:763] (6/8) Epoch 36, batch 4150, loss[loss=0.1626, simple_loss=0.2571, pruned_loss=0.03407, over 7213.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2591, pruned_loss=0.02901, over 1426153.67 frames.], batch size: 21, lr: 2.09e-04
+2022-04-30 21:49:06,726 INFO [train.py:763] (6/8) Epoch 36, batch 4200, loss[loss=0.153, simple_loss=0.2533, pruned_loss=0.02638, over 7341.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2585, pruned_loss=0.02884, over 1428665.37 frames.], batch size: 22, lr: 2.09e-04
+2022-04-30 21:50:13,179 INFO [train.py:763] (6/8) Epoch 36, batch 4250, loss[loss=0.157, simple_loss=0.2644, pruned_loss=0.02481, over 7202.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2579, pruned_loss=0.02882, over 1431633.05 frames.], batch size: 22, lr: 2.09e-04
+2022-04-30 21:51:18,753 INFO [train.py:763] (6/8) Epoch 36, batch 4300, loss[loss=0.1774, simple_loss=0.2766, pruned_loss=0.03914, over 7329.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2588, pruned_loss=0.02948, over 1426302.90 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:52:24,306 INFO [train.py:763] (6/8) Epoch 36, batch 4350, loss[loss=0.1794, simple_loss=0.2798, pruned_loss=0.03951, over 7335.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2586, pruned_loss=0.02936, over 1430492.00 frames.], batch size: 22, lr: 2.09e-04
+2022-04-30 21:53:30,948 INFO [train.py:763] (6/8) Epoch 36, batch 4400, loss[loss=0.1515, simple_loss=0.2582, pruned_loss=0.02245, over 7344.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2585, pruned_loss=0.02931, over 1423138.91 frames.], batch size: 22, lr: 2.09e-04
+2022-04-30 21:54:38,273 INFO [train.py:763] (6/8) Epoch 36, batch 4450, loss[loss=0.1365, simple_loss=0.2301, pruned_loss=0.02142, over 7409.00 frames.], tot_loss[loss=0.1589, simple_loss=0.259, pruned_loss=0.02934, over 1422135.59 frames.], batch size: 18, lr: 2.09e-04
+2022-04-30 21:55:43,446 INFO [train.py:763] (6/8) Epoch 36, batch 4500, loss[loss=0.1476, simple_loss=0.2425, pruned_loss=0.02633, over 7269.00 frames.], tot_loss[loss=0.1589, simple_loss=0.259, pruned_loss=0.02945, over 1416436.33 frames.], batch size: 18, lr: 2.09e-04
+2022-04-30 21:56:47,990 INFO [train.py:763] (6/8) Epoch 36, batch 4550, loss[loss=0.1706, simple_loss=0.2764, pruned_loss=0.03239, over 6444.00 frames.], tot_loss[loss=0.16, simple_loss=0.2601, pruned_loss=0.02995, over 1391714.08 frames.], batch size: 38, lr: 2.09e-04
+2022-04-30 21:58:07,233 INFO [train.py:763] (6/8) Epoch 37, batch 0, loss[loss=0.1447, simple_loss=0.2365, pruned_loss=0.02645, over 7367.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2365, pruned_loss=0.02645, over 7367.00 frames.], batch size: 19, lr: 2.06e-04
+2022-04-30 21:59:13,920 INFO [train.py:763] (6/8) Epoch 37, batch 50, loss[loss=0.1451, simple_loss=0.2451, pruned_loss=0.02257, over 6295.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2537, pruned_loss=0.0268, over 322392.87 frames.], batch size: 37, lr: 2.06e-04
+2022-04-30 22:00:20,543 INFO [train.py:763] (6/8) Epoch 37, batch 100, loss[loss=0.1371, simple_loss=0.2426, pruned_loss=0.01579, over 7256.00 frames.], tot_loss[loss=0.1565, simple_loss=0.257, pruned_loss=0.02798, over 560394.99 frames.], batch size: 19, lr: 2.06e-04
+2022-04-30 22:01:27,320 INFO [train.py:763] (6/8) Epoch 37, batch 150, loss[loss=0.1921, simple_loss=0.2921, pruned_loss=0.04605, over 7378.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2599, pruned_loss=0.02835, over 748093.42 frames.], batch size: 23, lr: 2.06e-04
+2022-04-30 22:02:34,175 INFO [train.py:763] (6/8) Epoch 37, batch 200, loss[loss=0.1396, simple_loss=0.2426, pruned_loss=0.0183, over 7400.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2579, pruned_loss=0.02847, over 897252.25 frames.], batch size: 21, lr: 2.06e-04
+2022-04-30 22:03:39,631 INFO [train.py:763] (6/8) Epoch 37, batch 250, loss[loss=0.144, simple_loss=0.2423, pruned_loss=0.02284, over 7358.00 frames.], tot_loss[loss=0.1575, simple_loss=0.258, pruned_loss=0.02853, over 1016589.15 frames.], batch size: 19, lr: 2.06e-04
+2022-04-30 22:04:45,208 INFO [train.py:763] (6/8) Epoch 37, batch 300, loss[loss=0.165, simple_loss=0.2748, pruned_loss=0.02763, over 7230.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2589, pruned_loss=0.02881, over 1106698.66 frames.], batch size: 20, lr: 2.06e-04
+2022-04-30 22:05:51,656 INFO [train.py:763] (6/8) Epoch 37, batch 350, loss[loss=0.1467, simple_loss=0.2484, pruned_loss=0.02249, over 7257.00 frames.], tot_loss[loss=0.1575, simple_loss=0.258, pruned_loss=0.02851, over 1174300.09 frames.], batch size: 19, lr: 2.06e-04
+2022-04-30 22:06:57,561 INFO [train.py:763] (6/8) Epoch 37, batch 400, loss[loss=0.1447, simple_loss=0.231, pruned_loss=0.02918, over 7292.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2571, pruned_loss=0.02817, over 1233827.99 frames.], batch size: 17, lr: 2.06e-04
+2022-04-30 22:08:03,015 INFO [train.py:763] (6/8) Epoch 37, batch 450, loss[loss=0.1358, simple_loss=0.2428, pruned_loss=0.01438, over 7114.00 frames.], tot_loss[loss=0.1566, simple_loss=0.257, pruned_loss=0.02816, over 1277239.98 frames.], batch size: 21, lr: 2.06e-04
+2022-04-30 22:09:09,258 INFO [train.py:763] (6/8) Epoch 37, batch 500, loss[loss=0.147, simple_loss=0.2446, pruned_loss=0.02474, over 7291.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2556, pruned_loss=0.02787, over 1313089.53 frames.], batch size: 18, lr: 2.06e-04
+2022-04-30 22:10:16,183 INFO [train.py:763] (6/8) Epoch 37, batch 550, loss[loss=0.155, simple_loss=0.2588, pruned_loss=0.0256, over 7324.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2569, pruned_loss=0.02815, over 1337027.78 frames.], batch size: 20, lr: 2.06e-04
+2022-04-30 22:11:22,963 INFO [train.py:763] (6/8) Epoch 37, batch 600, loss[loss=0.1874, simple_loss=0.282, pruned_loss=0.0464, over 7364.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2584, pruned_loss=0.02883, over 1358210.06 frames.], batch size: 23, lr: 2.06e-04
+2022-04-30 22:12:30,633 INFO [train.py:763] (6/8) Epoch 37, batch 650, loss[loss=0.1509, simple_loss=0.2607, pruned_loss=0.02058, over 7345.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2589, pruned_loss=0.02888, over 1373836.04 frames.], batch size: 22, lr: 2.06e-04
+2022-04-30 22:13:38,155 INFO [train.py:763] (6/8) Epoch 37, batch 700, loss[loss=0.1468, simple_loss=0.2486, pruned_loss=0.02252, over 7171.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2581, pruned_loss=0.02872, over 1385785.26 frames.], batch size: 18, lr: 2.06e-04
+2022-04-30 22:14:45,729 INFO [train.py:763] (6/8) Epoch 37, batch 750, loss[loss=0.1757, simple_loss=0.2793, pruned_loss=0.03599, over 7361.00 frames.], tot_loss[loss=0.158, simple_loss=0.2588, pruned_loss=0.0286, over 1400588.75 frames.], batch size: 23, lr: 2.05e-04
+2022-04-30 22:15:51,455 INFO [train.py:763] (6/8) Epoch 37, batch 800, loss[loss=0.1482, simple_loss=0.2421, pruned_loss=0.02717, over 7406.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2594, pruned_loss=0.0289, over 1408219.76 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:16:56,739 INFO [train.py:763] (6/8) Epoch 37, batch 850, loss[loss=0.1715, simple_loss=0.2616, pruned_loss=0.04073, over 7355.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2589, pruned_loss=0.02862, over 1411476.37 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:18:02,419 INFO [train.py:763] (6/8) Epoch 37, batch 900, loss[loss=0.2202, simple_loss=0.31, pruned_loss=0.06518, over 7266.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2593, pruned_loss=0.02897, over 1413445.63 frames.], batch size: 24, lr: 2.05e-04
+2022-04-30 22:19:07,696 INFO [train.py:763] (6/8) Epoch 37, batch 950, loss[loss=0.1567, simple_loss=0.2555, pruned_loss=0.029, over 7251.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2594, pruned_loss=0.02914, over 1418841.69 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:20:12,875 INFO [train.py:763] (6/8) Epoch 37, batch 1000, loss[loss=0.1585, simple_loss=0.2631, pruned_loss=0.02696, over 7208.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2593, pruned_loss=0.02906, over 1421991.47 frames.], batch size: 22, lr: 2.05e-04
+2022-04-30 22:21:18,159 INFO [train.py:763] (6/8) Epoch 37, batch 1050, loss[loss=0.1407, simple_loss=0.2416, pruned_loss=0.01993, over 7322.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2593, pruned_loss=0.02887, over 1422494.51 frames.], batch size: 20, lr: 2.05e-04
+2022-04-30 22:22:25,733 INFO [train.py:763] (6/8) Epoch 37, batch 1100, loss[loss=0.1486, simple_loss=0.2404, pruned_loss=0.02838, over 6820.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2601, pruned_loss=0.02909, over 1425521.74 frames.], batch size: 15, lr: 2.05e-04
+2022-04-30 22:23:31,644 INFO [train.py:763] (6/8) Epoch 37, batch 1150, loss[loss=0.1376, simple_loss=0.2256, pruned_loss=0.02479, over 7296.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2597, pruned_loss=0.02866, over 1422824.47 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:24:36,968 INFO [train.py:763] (6/8) Epoch 37, batch 1200, loss[loss=0.1643, simple_loss=0.2729, pruned_loss=0.02787, over 7136.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2597, pruned_loss=0.02851, over 1424042.81 frames.], batch size: 26, lr: 2.05e-04
+2022-04-30 22:25:43,905 INFO [train.py:763] (6/8) Epoch 37, batch 1250, loss[loss=0.1586, simple_loss=0.2594, pruned_loss=0.02894, over 6396.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2602, pruned_loss=0.02867, over 1427608.27 frames.], batch size: 38, lr: 2.05e-04
+2022-04-30 22:26:50,671 INFO [train.py:763] (6/8) Epoch 37, batch 1300, loss[loss=0.1277, simple_loss=0.2315, pruned_loss=0.01198, over 7296.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2604, pruned_loss=0.02893, over 1427019.99 frames.], batch size: 17, lr: 2.05e-04
+2022-04-30 22:27:56,061 INFO [train.py:763] (6/8) Epoch 37, batch 1350, loss[loss=0.1593, simple_loss=0.2665, pruned_loss=0.02607, over 7128.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2591, pruned_loss=0.02888, over 1420283.23 frames.], batch size: 21, lr: 2.05e-04
+2022-04-30 22:29:02,058 INFO [train.py:763] (6/8) Epoch 37, batch 1400, loss[loss=0.1787, simple_loss=0.2855, pruned_loss=0.03596, over 7276.00 frames.], tot_loss[loss=0.1575, simple_loss=0.258, pruned_loss=0.0285, over 1421016.65 frames.], batch size: 24, lr: 2.05e-04
+2022-04-30 22:30:07,330 INFO [train.py:763] (6/8) Epoch 37, batch 1450, loss[loss=0.1593, simple_loss=0.2617, pruned_loss=0.02843, over 7210.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2593, pruned_loss=0.02887, over 1425037.06 frames.], batch size: 22, lr: 2.05e-04
+2022-04-30 22:31:13,183 INFO [train.py:763] (6/8) Epoch 37, batch 1500, loss[loss=0.1466, simple_loss=0.2524, pruned_loss=0.02043, over 7305.00 frames.], tot_loss[loss=0.158, simple_loss=0.2586, pruned_loss=0.02866, over 1425438.76 frames.], batch size: 25, lr: 2.05e-04
+2022-04-30 22:32:18,522 INFO [train.py:763] (6/8) Epoch 37, batch 1550, loss[loss=0.139, simple_loss=0.2383, pruned_loss=0.01982, over 7244.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2591, pruned_loss=0.02874, over 1422847.19 frames.], batch size: 20, lr: 2.05e-04
+2022-04-30 22:33:23,884 INFO [train.py:763] (6/8) Epoch 37, batch 1600, loss[loss=0.153, simple_loss=0.2561, pruned_loss=0.02491, over 7266.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2598, pruned_loss=0.02936, over 1426038.76 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:34:29,220 INFO [train.py:763] (6/8) Epoch 37, batch 1650, loss[loss=0.1517, simple_loss=0.2615, pruned_loss=0.02094, over 7105.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2593, pruned_loss=0.02929, over 1425213.53 frames.], batch size: 28, lr: 2.05e-04
+2022-04-30 22:35:34,592 INFO [train.py:763] (6/8) Epoch 37, batch 1700, loss[loss=0.1572, simple_loss=0.257, pruned_loss=0.02867, over 7174.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2585, pruned_loss=0.02937, over 1423751.32 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:36:40,245 INFO [train.py:763] (6/8) Epoch 37, batch 1750, loss[loss=0.1863, simple_loss=0.287, pruned_loss=0.04277, over 5275.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2582, pruned_loss=0.02937, over 1421891.64 frames.], batch size: 53, lr: 2.05e-04
+2022-04-30 22:37:45,570 INFO [train.py:763] (6/8) Epoch 37, batch 1800, loss[loss=0.1491, simple_loss=0.2514, pruned_loss=0.02338, over 7330.00 frames.], tot_loss[loss=0.1573, simple_loss=0.257, pruned_loss=0.02875, over 1420165.30 frames.], batch size: 20, lr: 2.05e-04
+2022-04-30 22:38:50,830 INFO [train.py:763] (6/8) Epoch 37, batch 1850, loss[loss=0.1532, simple_loss=0.2423, pruned_loss=0.0321, over 7262.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2572, pruned_loss=0.02859, over 1422016.20 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:39:57,186 INFO [train.py:763] (6/8) Epoch 37, batch 1900, loss[loss=0.1521, simple_loss=0.2399, pruned_loss=0.03218, over 6821.00 frames.], tot_loss[loss=0.158, simple_loss=0.2581, pruned_loss=0.02896, over 1424726.08 frames.], batch size: 15, lr: 2.05e-04
+2022-04-30 22:41:04,599 INFO [train.py:763] (6/8) Epoch 37, batch 1950, loss[loss=0.1561, simple_loss=0.2671, pruned_loss=0.02258, over 7252.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2592, pruned_loss=0.02916, over 1426827.92 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:42:12,275 INFO [train.py:763] (6/8) Epoch 37, batch 2000, loss[loss=0.1491, simple_loss=0.2465, pruned_loss=0.02583, over 7407.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2585, pruned_loss=0.02923, over 1425457.05 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:43:17,402 INFO [train.py:763] (6/8) Epoch 37, batch 2050, loss[loss=0.1777, simple_loss=0.2809, pruned_loss=0.03722, over 7259.00 frames.], tot_loss[loss=0.1589, simple_loss=0.259, pruned_loss=0.02938, over 1423187.62 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:44:22,375 INFO [train.py:763] (6/8) Epoch 37, batch 2100, loss[loss=0.1858, simple_loss=0.2983, pruned_loss=0.03666, over 7169.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2595, pruned_loss=0.02942, over 1417673.61 frames.], batch size: 26, lr: 2.05e-04
+2022-04-30 22:45:27,588 INFO [train.py:763] (6/8) Epoch 37, batch 2150, loss[loss=0.1612, simple_loss=0.2481, pruned_loss=0.03713, over 7071.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2598, pruned_loss=0.02965, over 1418254.31 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:46:32,465 INFO [train.py:763] (6/8) Epoch 37, batch 2200, loss[loss=0.1429, simple_loss=0.233, pruned_loss=0.02642, over 7065.00 frames.], tot_loss[loss=0.16, simple_loss=0.2604, pruned_loss=0.02985, over 1419199.44 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:47:37,563 INFO [train.py:763] (6/8) Epoch 37, batch 2250, loss[loss=0.1658, simple_loss=0.2643, pruned_loss=0.03369, over 6312.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2601, pruned_loss=0.02968, over 1418086.98 frames.], batch size: 38, lr: 2.05e-04
+2022-04-30 22:48:44,665 INFO [train.py:763] (6/8) Epoch 37, batch 2300, loss[loss=0.1473, simple_loss=0.2355, pruned_loss=0.02958, over 7069.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2603, pruned_loss=0.0296, over 1422495.07 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:49:50,010 INFO [train.py:763] (6/8) Epoch 37, batch 2350, loss[loss=0.1563, simple_loss=0.2591, pruned_loss=0.02674, over 7325.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2597, pruned_loss=0.02929, over 1419939.14 frames.], batch size: 20, lr: 2.05e-04
+2022-04-30 22:50:55,502 INFO [train.py:763] (6/8) Epoch 37, batch 2400, loss[loss=0.1553, simple_loss=0.2435, pruned_loss=0.03354, over 7403.00 frames.], tot_loss[loss=0.159, simple_loss=0.2595, pruned_loss=0.02922, over 1425322.55 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:52:02,206 INFO [train.py:763] (6/8) Epoch 37, batch 2450, loss[loss=0.1649, simple_loss=0.2657, pruned_loss=0.03208, over 7334.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2595, pruned_loss=0.02908, over 1426806.36 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 22:53:07,501 INFO [train.py:763] (6/8) Epoch 37, batch 2500, loss[loss=0.1453, simple_loss=0.2342, pruned_loss=0.02817, over 7167.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2598, pruned_loss=0.02964, over 1426731.08 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 22:54:13,276 INFO [train.py:763] (6/8) Epoch 37, batch 2550, loss[loss=0.1464, simple_loss=0.2398, pruned_loss=0.02647, over 7167.00 frames.], tot_loss[loss=0.159, simple_loss=0.2596, pruned_loss=0.02921, over 1424315.28 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 22:55:19,541 INFO [train.py:763] (6/8) Epoch 37, batch 2600, loss[loss=0.1682, simple_loss=0.2795, pruned_loss=0.02848, over 7432.00 frames.], tot_loss[loss=0.1586, simple_loss=0.259, pruned_loss=0.0291, over 1424300.33 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 22:56:24,705 INFO [train.py:763] (6/8) Epoch 37, batch 2650, loss[loss=0.1692, simple_loss=0.2706, pruned_loss=0.0339, over 7214.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2592, pruned_loss=0.02883, over 1425101.34 frames.], batch size: 23, lr: 2.04e-04
+2022-04-30 22:57:30,429 INFO [train.py:763] (6/8) Epoch 37, batch 2700, loss[loss=0.164, simple_loss=0.2614, pruned_loss=0.03329, over 7237.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2592, pruned_loss=0.02892, over 1423211.43 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 22:58:35,701 INFO [train.py:763] (6/8) Epoch 37, batch 2750, loss[loss=0.145, simple_loss=0.2447, pruned_loss=0.02265, over 7344.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2596, pruned_loss=0.02903, over 1424836.54 frames.], batch size: 19, lr: 2.04e-04
+2022-04-30 22:59:42,058 INFO [train.py:763] (6/8) Epoch 37, batch 2800, loss[loss=0.1616, simple_loss=0.2635, pruned_loss=0.02978, over 7281.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2595, pruned_loss=0.02886, over 1423287.43 frames.], batch size: 24, lr: 2.04e-04
+2022-04-30 23:00:49,138 INFO [train.py:763] (6/8) Epoch 37, batch 2850, loss[loss=0.1437, simple_loss=0.2557, pruned_loss=0.01582, over 7420.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2595, pruned_loss=0.02868, over 1423528.77 frames.], batch size: 21, lr: 2.04e-04
+2022-04-30 23:01:56,136 INFO [train.py:763] (6/8) Epoch 37, batch 2900, loss[loss=0.1405, simple_loss=0.2367, pruned_loss=0.02211, over 7142.00 frames.], tot_loss[loss=0.158, simple_loss=0.2584, pruned_loss=0.02875, over 1424604.46 frames.], batch size: 17, lr: 2.04e-04
+2022-04-30 23:03:03,259 INFO [train.py:763] (6/8) Epoch 37, batch 2950, loss[loss=0.1494, simple_loss=0.2385, pruned_loss=0.03016, over 7400.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2591, pruned_loss=0.02905, over 1428982.91 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 23:04:10,216 INFO [train.py:763] (6/8) Epoch 37, batch 3000, loss[loss=0.1662, simple_loss=0.2637, pruned_loss=0.03439, over 7196.00 frames.], tot_loss[loss=0.1583, simple_loss=0.259, pruned_loss=0.0288, over 1428012.70 frames.], batch size: 23, lr: 2.04e-04
+2022-04-30 23:04:10,217 INFO [train.py:783] (6/8) Computing validation loss
+2022-04-30 23:04:25,434 INFO [train.py:792] (6/8) Epoch 37, validation: loss=0.1692, simple_loss=0.2632, pruned_loss=0.03757, over 698248.00 frames.
+2022-04-30 23:05:32,516 INFO [train.py:763] (6/8) Epoch 37, batch 3050, loss[loss=0.1883, simple_loss=0.2772, pruned_loss=0.04966, over 7166.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.02945, over 1428367.34 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 23:06:38,293 INFO [train.py:763] (6/8) Epoch 37, batch 3100, loss[loss=0.1643, simple_loss=0.2594, pruned_loss=0.03463, over 7219.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02943, over 1421895.47 frames.], batch size: 22, lr: 2.04e-04
+2022-04-30 23:07:53,029 INFO [train.py:763] (6/8) Epoch 37, batch 3150, loss[loss=0.1544, simple_loss=0.256, pruned_loss=0.02644, over 7377.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2588, pruned_loss=0.02934, over 1420165.89 frames.], batch size: 23, lr: 2.04e-04
+2022-04-30 23:08:58,935 INFO [train.py:763] (6/8) Epoch 37, batch 3200, loss[loss=0.144, simple_loss=0.256, pruned_loss=0.01603, over 7118.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2593, pruned_loss=0.02961, over 1425005.68 frames.], batch size: 21, lr: 2.04e-04
+2022-04-30 23:10:06,289 INFO [train.py:763] (6/8) Epoch 37, batch 3250, loss[loss=0.1303, simple_loss=0.2214, pruned_loss=0.01958, over 7291.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2584, pruned_loss=0.02916, over 1426152.99 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 23:11:13,123 INFO [train.py:763] (6/8) Epoch 37, batch 3300, loss[loss=0.1679, simple_loss=0.271, pruned_loss=0.03238, over 7227.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2584, pruned_loss=0.02926, over 1426028.36 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:12:18,274 INFO [train.py:763] (6/8) Epoch 37, batch 3350, loss[loss=0.171, simple_loss=0.2673, pruned_loss=0.03731, over 7203.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2592, pruned_loss=0.02911, over 1426907.84 frames.], batch size: 22, lr: 2.04e-04
+2022-04-30 23:13:23,567 INFO [train.py:763] (6/8) Epoch 37, batch 3400, loss[loss=0.1886, simple_loss=0.3038, pruned_loss=0.03667, over 6763.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2593, pruned_loss=0.02901, over 1430610.57 frames.], batch size: 31, lr: 2.04e-04
+2022-04-30 23:14:28,971 INFO [train.py:763] (6/8) Epoch 37, batch 3450, loss[loss=0.1559, simple_loss=0.2503, pruned_loss=0.0307, over 7434.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2598, pruned_loss=0.02933, over 1431421.03 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:15:34,297 INFO [train.py:763] (6/8) Epoch 37, batch 3500, loss[loss=0.1702, simple_loss=0.28, pruned_loss=0.03018, over 7234.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2595, pruned_loss=0.02893, over 1430852.93 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:16:39,548 INFO [train.py:763] (6/8) Epoch 37, batch 3550, loss[loss=0.1769, simple_loss=0.2722, pruned_loss=0.04082, over 7156.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2605, pruned_loss=0.02912, over 1431784.47 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:17:44,640 INFO [train.py:763] (6/8) Epoch 37, batch 3600, loss[loss=0.1679, simple_loss=0.2719, pruned_loss=0.03199, over 6762.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2609, pruned_loss=0.02971, over 1429763.06 frames.], batch size: 31, lr: 2.04e-04
+2022-04-30 23:18:50,218 INFO [train.py:763] (6/8) Epoch 37, batch 3650, loss[loss=0.1748, simple_loss=0.2839, pruned_loss=0.03287, over 7068.00 frames.], tot_loss[loss=0.1592, simple_loss=0.26, pruned_loss=0.02917, over 1431782.25 frames.], batch size: 28, lr: 2.04e-04
+2022-04-30 23:19:55,914 INFO [train.py:763] (6/8) Epoch 37, batch 3700, loss[loss=0.1819, simple_loss=0.2878, pruned_loss=0.03798, over 7300.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2597, pruned_loss=0.02953, over 1423138.10 frames.], batch size: 24, lr: 2.04e-04
+2022-04-30 23:21:00,948 INFO [train.py:763] (6/8) Epoch 37, batch 3750, loss[loss=0.1219, simple_loss=0.2239, pruned_loss=0.009968, over 7167.00 frames.], tot_loss[loss=0.1587, simple_loss=0.259, pruned_loss=0.02923, over 1418497.52 frames.], batch size: 19, lr: 2.04e-04
+2022-04-30 23:22:07,063 INFO [train.py:763] (6/8) Epoch 37, batch 3800, loss[loss=0.1709, simple_loss=0.2663, pruned_loss=0.03772, over 7370.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2587, pruned_loss=0.02925, over 1418389.98 frames.], batch size: 23, lr: 2.04e-04
+2022-04-30 23:23:12,319 INFO [train.py:763] (6/8) Epoch 37, batch 3850, loss[loss=0.1508, simple_loss=0.2629, pruned_loss=0.01934, over 7096.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2587, pruned_loss=0.02934, over 1420957.90 frames.], batch size: 21, lr: 2.04e-04
+2022-04-30 23:24:18,022 INFO [train.py:763] (6/8) Epoch 37, batch 3900, loss[loss=0.1542, simple_loss=0.2602, pruned_loss=0.0241, over 7322.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2584, pruned_loss=0.02947, over 1422621.23 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:25:32,659 INFO [train.py:763] (6/8) Epoch 37, batch 3950, loss[loss=0.1914, simple_loss=0.2916, pruned_loss=0.04559, over 7203.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2578, pruned_loss=0.02948, over 1418386.03 frames.], batch size: 22, lr: 2.04e-04
+2022-04-30 23:26:37,884 INFO [train.py:763] (6/8) Epoch 37, batch 4000, loss[loss=0.1511, simple_loss=0.2532, pruned_loss=0.02443, over 7159.00 frames.], tot_loss[loss=0.158, simple_loss=0.2578, pruned_loss=0.02916, over 1418869.92 frames.], batch size: 19, lr: 2.04e-04
+2022-04-30 23:28:01,971 INFO [train.py:763] (6/8) Epoch 37, batch 4050, loss[loss=0.1429, simple_loss=0.2364, pruned_loss=0.02472, over 7270.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2578, pruned_loss=0.02935, over 1411910.38 frames.], batch size: 17, lr: 2.04e-04
+2022-04-30 23:29:07,115 INFO [train.py:763] (6/8) Epoch 37, batch 4100, loss[loss=0.1446, simple_loss=0.2611, pruned_loss=0.0141, over 7220.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2587, pruned_loss=0.02945, over 1414334.90 frames.], batch size: 21, lr: 2.04e-04
+2022-04-30 23:30:21,707 INFO [train.py:763] (6/8) Epoch 37, batch 4150, loss[loss=0.1574, simple_loss=0.2585, pruned_loss=0.02817, over 7269.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2575, pruned_loss=0.0291, over 1413653.79 frames.], batch size: 19, lr: 2.03e-04
+2022-04-30 23:31:36,415 INFO [train.py:763] (6/8) Epoch 37, batch 4200, loss[loss=0.1647, simple_loss=0.2713, pruned_loss=0.02901, over 7271.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2577, pruned_loss=0.02861, over 1414449.34 frames.], batch size: 24, lr: 2.03e-04
+2022-04-30 23:32:51,952 INFO [train.py:763] (6/8) Epoch 37, batch 4250, loss[loss=0.1467, simple_loss=0.2525, pruned_loss=0.02044, over 7238.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2576, pruned_loss=0.02856, over 1414608.67 frames.], batch size: 20, lr: 2.03e-04
+2022-04-30 23:33:58,666 INFO [train.py:763] (6/8) Epoch 37, batch 4300, loss[loss=0.1712, simple_loss=0.262, pruned_loss=0.04021, over 4597.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2559, pruned_loss=0.02845, over 1411729.04 frames.], batch size: 52, lr: 2.03e-04
+2022-04-30 23:35:04,835 INFO [train.py:763] (6/8) Epoch 37, batch 4350, loss[loss=0.15, simple_loss=0.2419, pruned_loss=0.02906, over 7006.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2551, pruned_loss=0.02824, over 1414223.47 frames.], batch size: 16, lr: 2.03e-04
+2022-04-30 23:36:10,338 INFO [train.py:763] (6/8) Epoch 37, batch 4400, loss[loss=0.135, simple_loss=0.2259, pruned_loss=0.02204, over 6828.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2543, pruned_loss=0.02778, over 1413743.50 frames.], batch size: 15, lr: 2.03e-04
+2022-04-30 23:37:17,178 INFO [train.py:763] (6/8) Epoch 37, batch 4450, loss[loss=0.1395, simple_loss=0.2291, pruned_loss=0.02493, over 7268.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2535, pruned_loss=0.02784, over 1405657.44 frames.], batch size: 16, lr: 2.03e-04
+2022-04-30 23:38:22,786 INFO [train.py:763] (6/8) Epoch 37, batch 4500, loss[loss=0.1598, simple_loss=0.2619, pruned_loss=0.02883, over 6259.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2536, pruned_loss=0.02836, over 1382188.86 frames.], batch size: 38, lr: 2.03e-04
+2022-04-30 23:39:28,656 INFO [train.py:763] (6/8) Epoch 37, batch 4550, loss[loss=0.1656, simple_loss=0.254, pruned_loss=0.03856, over 5107.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2537, pruned_loss=0.02868, over 1356211.82 frames.], batch size: 52, lr: 2.03e-04
+2022-04-30 23:40:56,596 INFO [train.py:763] (6/8) Epoch 38, batch 0, loss[loss=0.1577, simple_loss=0.2658, pruned_loss=0.02478, over 7270.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2658, pruned_loss=0.02478, over 7270.00 frames.], batch size: 19, lr: 2.01e-04
+2022-04-30 23:42:03,206 INFO [train.py:763] (6/8) Epoch 38, batch 50, loss[loss=0.1547, simple_loss=0.2621, pruned_loss=0.0236, over 7145.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2634, pruned_loss=0.0298, over 320110.89 frames.], batch size: 20, lr: 2.01e-04
+2022-04-30 23:43:10,051 INFO [train.py:763] (6/8) Epoch 38, batch 100, loss[loss=0.1415, simple_loss=0.2473, pruned_loss=0.01783, over 6857.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2605, pruned_loss=0.0289, over 565190.12 frames.], batch size: 31, lr: 2.01e-04
+2022-04-30 23:44:16,830 INFO [train.py:763] (6/8) Epoch 38, batch 150, loss[loss=0.1509, simple_loss=0.2429, pruned_loss=0.02947, over 7160.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2578, pruned_loss=0.02851, over 754302.05 frames.], batch size: 18, lr: 2.01e-04
+2022-04-30 23:45:22,813 INFO [train.py:763] (6/8) Epoch 38, batch 200, loss[loss=0.1374, simple_loss=0.2378, pruned_loss=0.01851, over 7419.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2584, pruned_loss=0.02873, over 901260.12 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:46:29,136 INFO [train.py:763] (6/8) Epoch 38, batch 250, loss[loss=0.1512, simple_loss=0.2533, pruned_loss=0.0246, over 6517.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2589, pruned_loss=0.02913, over 1017656.49 frames.], batch size: 38, lr: 2.00e-04
+2022-04-30 23:47:35,366 INFO [train.py:763] (6/8) Epoch 38, batch 300, loss[loss=0.1442, simple_loss=0.2415, pruned_loss=0.02346, over 7425.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2588, pruned_loss=0.02882, over 1112845.65 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:48:41,486 INFO [train.py:763] (6/8) Epoch 38, batch 350, loss[loss=0.1619, simple_loss=0.2672, pruned_loss=0.02825, over 7312.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2582, pruned_loss=0.02866, over 1178958.12 frames.], batch size: 24, lr: 2.00e-04
+2022-04-30 23:49:47,446 INFO [train.py:763] (6/8) Epoch 38, batch 400, loss[loss=0.1737, simple_loss=0.2899, pruned_loss=0.02876, over 7219.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2583, pruned_loss=0.02868, over 1228253.95 frames.], batch size: 21, lr: 2.00e-04
+2022-04-30 23:50:53,873 INFO [train.py:763] (6/8) Epoch 38, batch 450, loss[loss=0.1758, simple_loss=0.2727, pruned_loss=0.03946, over 7188.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2579, pruned_loss=0.02876, over 1273061.12 frames.], batch size: 23, lr: 2.00e-04
+2022-04-30 23:52:00,163 INFO [train.py:763] (6/8) Epoch 38, batch 500, loss[loss=0.1824, simple_loss=0.3006, pruned_loss=0.03215, over 7154.00 frames.], tot_loss[loss=0.1581, simple_loss=0.258, pruned_loss=0.02909, over 1300203.07 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:53:06,414 INFO [train.py:763] (6/8) Epoch 38, batch 550, loss[loss=0.1592, simple_loss=0.2613, pruned_loss=0.02859, over 7417.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2581, pruned_loss=0.02929, over 1325557.59 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:54:12,146 INFO [train.py:763] (6/8) Epoch 38, batch 600, loss[loss=0.1392, simple_loss=0.2323, pruned_loss=0.02299, over 7168.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2582, pruned_loss=0.02902, over 1344366.01 frames.], batch size: 18, lr: 2.00e-04
+2022-04-30 23:55:17,888 INFO [train.py:763] (6/8) Epoch 38, batch 650, loss[loss=0.1516, simple_loss=0.2397, pruned_loss=0.03176, over 7266.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2584, pruned_loss=0.02924, over 1364533.56 frames.], batch size: 17, lr: 2.00e-04
+2022-04-30 23:56:23,413 INFO [train.py:763] (6/8) Epoch 38, batch 700, loss[loss=0.1515, simple_loss=0.2434, pruned_loss=0.02976, over 7216.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2574, pruned_loss=0.02905, over 1377835.50 frames.], batch size: 16, lr: 2.00e-04
+2022-04-30 23:57:28,962 INFO [train.py:763] (6/8) Epoch 38, batch 750, loss[loss=0.1504, simple_loss=0.2615, pruned_loss=0.0197, over 6517.00 frames.], tot_loss[loss=0.157, simple_loss=0.2569, pruned_loss=0.02853, over 1386944.37 frames.], batch size: 38, lr: 2.00e-04
+2022-04-30 23:58:35,119 INFO [train.py:763] (6/8) Epoch 38, batch 800, loss[loss=0.1457, simple_loss=0.2438, pruned_loss=0.02377, over 7232.00 frames.], tot_loss[loss=0.1568, simple_loss=0.257, pruned_loss=0.02834, over 1399310.61 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:59:41,183 INFO [train.py:763] (6/8) Epoch 38, batch 850, loss[loss=0.1698, simple_loss=0.2717, pruned_loss=0.03395, over 7081.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2566, pruned_loss=0.02827, over 1404832.07 frames.], batch size: 28, lr: 2.00e-04
+2022-05-01 00:00:47,056 INFO [train.py:763] (6/8) Epoch 38, batch 900, loss[loss=0.1747, simple_loss=0.2832, pruned_loss=0.03312, over 7409.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2574, pruned_loss=0.02843, over 1403789.35 frames.], batch size: 21, lr: 2.00e-04
+2022-05-01 00:01:52,976 INFO [train.py:763] (6/8) Epoch 38, batch 950, loss[loss=0.1645, simple_loss=0.2644, pruned_loss=0.03232, over 7142.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2583, pruned_loss=0.02863, over 1404872.69 frames.], batch size: 17, lr: 2.00e-04
+2022-05-01 00:02:58,570 INFO [train.py:763] (6/8) Epoch 38, batch 1000, loss[loss=0.1541, simple_loss=0.2425, pruned_loss=0.03285, over 7360.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2576, pruned_loss=0.02858, over 1408381.22 frames.], batch size: 19, lr: 2.00e-04
+2022-05-01 00:04:03,996 INFO [train.py:763] (6/8) Epoch 38, batch 1050, loss[loss=0.16, simple_loss=0.27, pruned_loss=0.02499, over 6727.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2572, pruned_loss=0.02847, over 1410884.29 frames.], batch size: 31, lr: 2.00e-04
+2022-05-01 00:05:09,984 INFO [train.py:763] (6/8) Epoch 38, batch 1100, loss[loss=0.1781, simple_loss=0.2749, pruned_loss=0.04068, over 7371.00 frames.], tot_loss[loss=0.1568, simple_loss=0.257, pruned_loss=0.0283, over 1416428.59 frames.], batch size: 23, lr: 2.00e-04
+2022-05-01 00:06:15,679 INFO [train.py:763] (6/8) Epoch 38, batch 1150, loss[loss=0.1555, simple_loss=0.2561, pruned_loss=0.02748, over 7287.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2562, pruned_loss=0.02796, over 1419610.72 frames.], batch size: 18, lr: 2.00e-04
+2022-05-01 00:07:21,226 INFO [train.py:763] (6/8) Epoch 38, batch 1200, loss[loss=0.166, simple_loss=0.2686, pruned_loss=0.03174, over 6650.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2563, pruned_loss=0.02803, over 1420725.24 frames.], batch size: 31, lr: 2.00e-04
+2022-05-01 00:08:27,093 INFO [train.py:763] (6/8) Epoch 38, batch 1250, loss[loss=0.1465, simple_loss=0.2411, pruned_loss=0.02596, over 7419.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2569, pruned_loss=0.02836, over 1421522.00 frames.], batch size: 20, lr: 2.00e-04
+2022-05-01 00:09:34,186 INFO [train.py:763] (6/8) Epoch 38, batch 1300, loss[loss=0.1519, simple_loss=0.2413, pruned_loss=0.03124, over 7264.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2571, pruned_loss=0.02862, over 1425601.96 frames.], batch size: 17, lr: 2.00e-04
+2022-05-01 00:10:39,853 INFO [train.py:763] (6/8) Epoch 38, batch 1350, loss[loss=0.1366, simple_loss=0.2296, pruned_loss=0.02183, over 7341.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2577, pruned_loss=0.02875, over 1425613.40 frames.], batch size: 20, lr: 2.00e-04
+2022-05-01 00:11:45,177 INFO [train.py:763] (6/8) Epoch 38, batch 1400, loss[loss=0.1679, simple_loss=0.2626, pruned_loss=0.03662, over 7162.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2576, pruned_loss=0.02859, over 1425194.29 frames.], batch size: 19, lr: 2.00e-04
+2022-05-01 00:12:50,403 INFO [train.py:763] (6/8) Epoch 38, batch 1450, loss[loss=0.1765, simple_loss=0.2795, pruned_loss=0.03677, over 7310.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2587, pruned_loss=0.02893, over 1425600.92 frames.], batch size: 25, lr: 2.00e-04
+2022-05-01 00:13:56,000 INFO [train.py:763] (6/8) Epoch 38, batch 1500, loss[loss=0.1634, simple_loss=0.2757, pruned_loss=0.02551, over 7121.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2595, pruned_loss=0.02909, over 1424315.03 frames.], batch size: 21, lr: 2.00e-04
+2022-05-01 00:15:03,017 INFO [train.py:763] (6/8) Epoch 38, batch 1550, loss[loss=0.1613, simple_loss=0.266, pruned_loss=0.02824, over 7214.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2587, pruned_loss=0.02885, over 1424540.86 frames.], batch size: 22, lr: 2.00e-04
+2022-05-01 00:16:09,260 INFO [train.py:763] (6/8) Epoch 38, batch 1600, loss[loss=0.1739, simple_loss=0.2736, pruned_loss=0.03716, over 6742.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2577, pruned_loss=0.02867, over 1426036.84 frames.], batch size: 31, lr: 2.00e-04
+2022-05-01 00:17:15,072 INFO [train.py:763] (6/8) Epoch 38, batch 1650, loss[loss=0.1564, simple_loss=0.2615, pruned_loss=0.02565, over 7217.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2572, pruned_loss=0.02853, over 1424790.79 frames.], batch size: 21, lr: 2.00e-04
+2022-05-01 00:18:31,384 INFO [train.py:763] (6/8) Epoch 38, batch 1700, loss[loss=0.1546, simple_loss=0.2619, pruned_loss=0.02371, over 7102.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2581, pruned_loss=0.02837, over 1426788.82 frames.], batch size: 28, lr: 2.00e-04
+2022-05-01 00:19:36,541 INFO [train.py:763] (6/8) Epoch 38, batch 1750, loss[loss=0.1596, simple_loss=0.2615, pruned_loss=0.02888, over 7435.00 frames.], tot_loss[loss=0.1571, simple_loss=0.258, pruned_loss=0.0281, over 1426182.46 frames.], batch size: 20, lr: 2.00e-04
+2022-05-01 00:20:42,268 INFO [train.py:763] (6/8) Epoch 38, batch 1800, loss[loss=0.1656, simple_loss=0.2613, pruned_loss=0.03493, over 7191.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2587, pruned_loss=0.0284, over 1423547.68 frames.], batch size: 23, lr: 2.00e-04
+2022-05-01 00:21:47,759 INFO [train.py:763] (6/8) Epoch 38, batch 1850, loss[loss=0.1448, simple_loss=0.2387, pruned_loss=0.02543, over 7151.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2582, pruned_loss=0.02828, over 1421040.02 frames.], batch size: 19, lr: 2.00e-04
+2022-05-01 00:22:54,647 INFO [train.py:763] (6/8) Epoch 38, batch 1900, loss[loss=0.1514, simple_loss=0.2505, pruned_loss=0.02611, over 7279.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2577, pruned_loss=0.02848, over 1423969.12 frames.], batch size: 18, lr: 2.00e-04
+2022-05-01 00:24:00,341 INFO [train.py:763] (6/8) Epoch 38, batch 1950, loss[loss=0.1652, simple_loss=0.2707, pruned_loss=0.0298, over 7328.00 frames.], tot_loss[loss=0.158, simple_loss=0.2585, pruned_loss=0.0287, over 1423687.40 frames.], batch size: 21, lr: 1.99e-04
+2022-05-01 00:25:06,446 INFO [train.py:763] (6/8) Epoch 38, batch 2000, loss[loss=0.1523, simple_loss=0.2467, pruned_loss=0.02894, over 7265.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2583, pruned_loss=0.02832, over 1422942.73 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:26:13,054 INFO [train.py:763] (6/8) Epoch 38, batch 2050, loss[loss=0.1748, simple_loss=0.2734, pruned_loss=0.03812, over 7324.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2595, pruned_loss=0.02884, over 1420940.46 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:27:18,299 INFO [train.py:763] (6/8) Epoch 38, batch 2100, loss[loss=0.1649, simple_loss=0.251, pruned_loss=0.03937, over 7183.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2595, pruned_loss=0.02902, over 1422929.14 frames.], batch size: 16, lr: 1.99e-04
+2022-05-01 00:28:25,365 INFO [train.py:763] (6/8) Epoch 38, batch 2150, loss[loss=0.1525, simple_loss=0.2491, pruned_loss=0.02798, over 7257.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2592, pruned_loss=0.02883, over 1420007.70 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:29:31,365 INFO [train.py:763] (6/8) Epoch 38, batch 2200, loss[loss=0.1679, simple_loss=0.2673, pruned_loss=0.0343, over 7196.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2597, pruned_loss=0.02888, over 1421095.79 frames.], batch size: 22, lr: 1.99e-04
+2022-05-01 00:30:38,812 INFO [train.py:763] (6/8) Epoch 38, batch 2250, loss[loss=0.147, simple_loss=0.2516, pruned_loss=0.02122, over 7152.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2586, pruned_loss=0.02865, over 1423784.48 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:31:44,023 INFO [train.py:763] (6/8) Epoch 38, batch 2300, loss[loss=0.1445, simple_loss=0.2482, pruned_loss=0.02043, over 7167.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2585, pruned_loss=0.02863, over 1423350.93 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:32:50,159 INFO [train.py:763] (6/8) Epoch 38, batch 2350, loss[loss=0.1727, simple_loss=0.2703, pruned_loss=0.03749, over 7228.00 frames.], tot_loss[loss=0.1575, simple_loss=0.258, pruned_loss=0.02848, over 1424895.77 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:33:55,524 INFO [train.py:763] (6/8) Epoch 38, batch 2400, loss[loss=0.1636, simple_loss=0.2632, pruned_loss=0.03198, over 7148.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2581, pruned_loss=0.02852, over 1427610.19 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:35:01,020 INFO [train.py:763] (6/8) Epoch 38, batch 2450, loss[loss=0.1414, simple_loss=0.2366, pruned_loss=0.02309, over 7413.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2573, pruned_loss=0.02813, over 1428657.36 frames.], batch size: 18, lr: 1.99e-04
+2022-05-01 00:36:06,995 INFO [train.py:763] (6/8) Epoch 38, batch 2500, loss[loss=0.1423, simple_loss=0.2377, pruned_loss=0.0235, over 7401.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2574, pruned_loss=0.02806, over 1427062.18 frames.], batch size: 18, lr: 1.99e-04
+2022-05-01 00:37:12,686 INFO [train.py:763] (6/8) Epoch 38, batch 2550, loss[loss=0.1554, simple_loss=0.2551, pruned_loss=0.02783, over 7438.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2569, pruned_loss=0.02803, over 1431826.08 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:38:18,037 INFO [train.py:763] (6/8) Epoch 38, batch 2600, loss[loss=0.1692, simple_loss=0.2775, pruned_loss=0.0304, over 7171.00 frames.], tot_loss[loss=0.157, simple_loss=0.2576, pruned_loss=0.02824, over 1429710.65 frames.], batch size: 26, lr: 1.99e-04
+2022-05-01 00:39:23,363 INFO [train.py:763] (6/8) Epoch 38, batch 2650, loss[loss=0.176, simple_loss=0.2776, pruned_loss=0.03722, over 7055.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2574, pruned_loss=0.028, over 1430171.78 frames.], batch size: 28, lr: 1.99e-04
+2022-05-01 00:40:27,512 INFO [train.py:763] (6/8) Epoch 38, batch 2700, loss[loss=0.1592, simple_loss=0.2632, pruned_loss=0.02765, over 7298.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2572, pruned_loss=0.02786, over 1428389.83 frames.], batch size: 25, lr: 1.99e-04
+2022-05-01 00:41:33,242 INFO [train.py:763] (6/8) Epoch 38, batch 2750, loss[loss=0.1418, simple_loss=0.2456, pruned_loss=0.01902, over 7163.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2571, pruned_loss=0.02783, over 1428554.19 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:42:38,766 INFO [train.py:763] (6/8) Epoch 38, batch 2800, loss[loss=0.1622, simple_loss=0.27, pruned_loss=0.02718, over 7318.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2581, pruned_loss=0.02837, over 1426246.58 frames.], batch size: 22, lr: 1.99e-04
+2022-05-01 00:43:44,128 INFO [train.py:763] (6/8) Epoch 38, batch 2850, loss[loss=0.1581, simple_loss=0.2654, pruned_loss=0.02544, over 6208.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2587, pruned_loss=0.02881, over 1425685.66 frames.], batch size: 38, lr: 1.99e-04
+2022-05-01 00:44:49,675 INFO [train.py:763] (6/8) Epoch 38, batch 2900, loss[loss=0.1572, simple_loss=0.2609, pruned_loss=0.02673, over 7313.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2584, pruned_loss=0.02842, over 1424887.70 frames.], batch size: 21, lr: 1.99e-04
+2022-05-01 00:45:55,141 INFO [train.py:763] (6/8) Epoch 38, batch 2950, loss[loss=0.1656, simple_loss=0.2631, pruned_loss=0.03407, over 7341.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2576, pruned_loss=0.02868, over 1428675.81 frames.], batch size: 22, lr: 1.99e-04
+2022-05-01 00:47:00,416 INFO [train.py:763] (6/8) Epoch 38, batch 3000, loss[loss=0.1616, simple_loss=0.2737, pruned_loss=0.02479, over 7231.00 frames.], tot_loss[loss=0.1576, simple_loss=0.258, pruned_loss=0.02859, over 1429084.54 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:47:00,417 INFO [train.py:783] (6/8) Computing validation loss
+2022-05-01 00:47:15,873 INFO [train.py:792] (6/8) Epoch 38, validation: loss=0.1707, simple_loss=0.2648, pruned_loss=0.03834, over 698248.00 frames.
+2022-05-01 00:48:21,031 INFO [train.py:763] (6/8) Epoch 38, batch 3050, loss[loss=0.1472, simple_loss=0.2388, pruned_loss=0.02782, over 7135.00 frames.], tot_loss[loss=0.1576, simple_loss=0.258, pruned_loss=0.02862, over 1426245.35 frames.], batch size: 17, lr: 1.99e-04
+2022-05-01 00:49:26,204 INFO [train.py:763] (6/8) Epoch 38, batch 3100, loss[loss=0.1605, simple_loss=0.268, pruned_loss=0.02647, over 6363.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2585, pruned_loss=0.02859, over 1418349.64 frames.], batch size: 38, lr: 1.99e-04
+2022-05-01 00:50:31,506 INFO [train.py:763] (6/8) Epoch 38, batch 3150, loss[loss=0.1573, simple_loss=0.2547, pruned_loss=0.02995, over 7411.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2583, pruned_loss=0.02828, over 1423851.46 frames.], batch size: 21, lr: 1.99e-04
+2022-05-01 00:51:36,875 INFO [train.py:763] (6/8) Epoch 38, batch 3200, loss[loss=0.1733, simple_loss=0.2798, pruned_loss=0.03341, over 6337.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2585, pruned_loss=0.02833, over 1424769.86 frames.], batch size: 38, lr: 1.99e-04
+2022-05-01 00:52:42,221 INFO [train.py:763] (6/8) Epoch 38, batch 3250, loss[loss=0.1649, simple_loss=0.2649, pruned_loss=0.03248, over 6439.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2581, pruned_loss=0.02826, over 1424442.04 frames.], batch size: 37, lr: 1.99e-04
+2022-05-01 00:53:47,530 INFO [train.py:763] (6/8) Epoch 38, batch 3300, loss[loss=0.1362, simple_loss=0.2361, pruned_loss=0.01819, over 7159.00 frames.], tot_loss[loss=0.157, simple_loss=0.2576, pruned_loss=0.02823, over 1423896.39 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:54:52,915 INFO [train.py:763] (6/8) Epoch 38, batch 3350, loss[loss=0.1383, simple_loss=0.2392, pruned_loss=0.01873, over 7148.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2568, pruned_loss=0.02802, over 1425435.21 frames.], batch size: 17, lr: 1.99e-04
+2022-05-01 00:55:59,021 INFO [train.py:763] (6/8) Epoch 38, batch 3400, loss[loss=0.1615, simple_loss=0.2609, pruned_loss=0.03106, over 7351.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2564, pruned_loss=0.02803, over 1426809.61 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:57:06,507 INFO [train.py:763] (6/8) Epoch 38, batch 3450, loss[loss=0.1717, simple_loss=0.2792, pruned_loss=0.03214, over 7196.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2564, pruned_loss=0.02804, over 1419452.70 frames.], batch size: 23, lr: 1.99e-04
+2022-05-01 00:58:13,608 INFO [train.py:763] (6/8) Epoch 38, batch 3500, loss[loss=0.1413, simple_loss=0.227, pruned_loss=0.0278, over 7153.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2574, pruned_loss=0.02873, over 1420587.00 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:59:19,214 INFO [train.py:763] (6/8) Epoch 38, batch 3550, loss[loss=0.1586, simple_loss=0.2681, pruned_loss=0.02453, over 7348.00 frames.], tot_loss[loss=0.157, simple_loss=0.2567, pruned_loss=0.02866, over 1423757.56 frames.], batch size: 22, lr: 1.99e-04
+2022-05-01 01:00:25,364 INFO [train.py:763] (6/8) Epoch 38, batch 3600, loss[loss=0.1662, simple_loss=0.2556, pruned_loss=0.03841, over 7271.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2576, pruned_loss=0.02898, over 1424625.71 frames.], batch size: 18, lr: 1.99e-04
+2022-05-01 01:01:30,601 INFO [train.py:763] (6/8) Epoch 38, batch 3650, loss[loss=0.1451, simple_loss=0.2461, pruned_loss=0.02201, over 7024.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2582, pruned_loss=0.02911, over 1425961.22 frames.], batch size: 28, lr: 1.99e-04
+2022-05-01 01:02:35,744 INFO [train.py:763] (6/8) Epoch 38, batch 3700, loss[loss=0.172, simple_loss=0.2703, pruned_loss=0.0368, over 6341.00 frames.], tot_loss[loss=0.158, simple_loss=0.2582, pruned_loss=0.02895, over 1422486.74 frames.], batch size: 37, lr: 1.99e-04
+2022-05-01 01:03:41,347 INFO [train.py:763] (6/8) Epoch 38, batch 3750, loss[loss=0.1735, simple_loss=0.2786, pruned_loss=0.0342, over 7217.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2573, pruned_loss=0.02912, over 1416448.07 frames.], batch size: 23, lr: 1.98e-04
+2022-05-01 01:04:46,828 INFO [train.py:763] (6/8) Epoch 38, batch 3800, loss[loss=0.157, simple_loss=0.2417, pruned_loss=0.03618, over 7362.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2571, pruned_loss=0.02902, over 1422882.06 frames.], batch size: 19, lr: 1.98e-04
+2022-05-01 01:05:52,025 INFO [train.py:763] (6/8) Epoch 38, batch 3850, loss[loss=0.2124, simple_loss=0.2933, pruned_loss=0.06581, over 4985.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2564, pruned_loss=0.0289, over 1419645.91 frames.], batch size: 52, lr: 1.98e-04
+2022-05-01 01:06:57,234 INFO [train.py:763] (6/8) Epoch 38, batch 3900, loss[loss=0.1807, simple_loss=0.2752, pruned_loss=0.04312, over 7101.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2568, pruned_loss=0.02876, over 1420928.30 frames.], batch size: 28, lr: 1.98e-04
+2022-05-01 01:08:02,838 INFO [train.py:763] (6/8) Epoch 38, batch 3950, loss[loss=0.1714, simple_loss=0.2793, pruned_loss=0.03177, over 7310.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2574, pruned_loss=0.0284, over 1422915.44 frames.], batch size: 25, lr: 1.98e-04
+2022-05-01 01:09:08,085 INFO [train.py:763] (6/8) Epoch 38, batch 4000, loss[loss=0.1563, simple_loss=0.2705, pruned_loss=0.02104, over 6740.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2578, pruned_loss=0.0284, over 1425794.06 frames.], batch size: 31, lr: 1.98e-04
+2022-05-01 01:10:13,457 INFO [train.py:763] (6/8) Epoch 38, batch 4050, loss[loss=0.16, simple_loss=0.2634, pruned_loss=0.02826, over 6925.00 frames.], tot_loss[loss=0.1582, simple_loss=0.259, pruned_loss=0.02869, over 1424116.27 frames.], batch size: 31, lr: 1.98e-04
+2022-05-01 01:11:18,889 INFO [train.py:763] (6/8) Epoch 38, batch 4100, loss[loss=0.1494, simple_loss=0.2632, pruned_loss=0.01782, over 7211.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2586, pruned_loss=0.02898, over 1423053.91 frames.], batch size: 21, lr: 1.98e-04
+2022-05-01 01:12:24,229 INFO [train.py:763] (6/8) Epoch 38, batch 4150, loss[loss=0.1588, simple_loss=0.2627, pruned_loss=0.02747, over 7211.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2579, pruned_loss=0.02856, over 1420565.07 frames.], batch size: 21, lr: 1.98e-04
+2022-05-01 01:13:30,536 INFO [train.py:763] (6/8) Epoch 38, batch 4200, loss[loss=0.1537, simple_loss=0.2557, pruned_loss=0.0259, over 6774.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2585, pruned_loss=0.02864, over 1419667.18 frames.], batch size: 31, lr: 1.98e-04
+2022-05-01 01:14:35,836 INFO [train.py:763] (6/8) Epoch 38, batch 4250, loss[loss=0.1566, simple_loss=0.2406, pruned_loss=0.03631, over 7138.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2587, pruned_loss=0.02871, over 1416629.98 frames.], batch size: 17, lr: 1.98e-04
+2022-05-01 01:15:41,254 INFO [train.py:763] (6/8) Epoch 38, batch 4300, loss[loss=0.1625, simple_loss=0.2682, pruned_loss=0.02839, over 7298.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2599, pruned_loss=0.0288, over 1417075.24 frames.], batch size: 25, lr: 1.98e-04
+2022-05-01 01:16:46,656 INFO [train.py:763] (6/8) Epoch 38, batch 4350, loss[loss=0.1384, simple_loss=0.2459, pruned_loss=0.01548, over 7431.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2597, pruned_loss=0.02883, over 1413953.48 frames.], batch size: 20, lr: 1.98e-04
+2022-05-01 01:17:51,729 INFO [train.py:763] (6/8) Epoch 38, batch 4400, loss[loss=0.1665, simple_loss=0.2587, pruned_loss=0.0372, over 7334.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2606, pruned_loss=0.0293, over 1410767.00 frames.], batch size: 22, lr: 1.98e-04
+2022-05-01 01:18:57,843 INFO [train.py:763] (6/8) Epoch 38, batch 4450, loss[loss=0.1381, simple_loss=0.234, pruned_loss=0.0211, over 6989.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2613, pruned_loss=0.02969, over 1397666.74 frames.], batch size: 16, lr: 1.98e-04
+2022-05-01 01:20:03,928 INFO [train.py:763] (6/8) Epoch 38, batch 4500, loss[loss=0.1471, simple_loss=0.2463, pruned_loss=0.02395, over 7178.00 frames.], tot_loss[loss=0.1611, simple_loss=0.262, pruned_loss=0.03013, over 1385770.35 frames.], batch size: 18, lr: 1.98e-04
+2022-05-01 01:21:09,323 INFO [train.py:763] (6/8) Epoch 38, batch 4550, loss[loss=0.1998, simple_loss=0.2911, pruned_loss=0.05428, over 4848.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2642, pruned_loss=0.03148, over 1347312.14 frames.], batch size: 52, lr: 1.98e-04
+2022-05-01 01:22:39,307 INFO [train.py:763] (6/8) Epoch 39, batch 0, loss[loss=0.1787, simple_loss=0.2822, pruned_loss=0.03755, over 7268.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2822, pruned_loss=0.03755, over 7268.00 frames.], batch size: 24, lr: 1.96e-04
+2022-05-01 01:23:45,002 INFO [train.py:763] (6/8) Epoch 39, batch 50, loss[loss=0.1255, simple_loss=0.221, pruned_loss=0.015, over 7280.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2595, pruned_loss=0.03015, over 317289.99 frames.], batch size: 17, lr: 1.95e-04
+2022-05-01 01:24:50,355 INFO [train.py:763] (6/8) Epoch 39, batch 100, loss[loss=0.1404, simple_loss=0.2496, pruned_loss=0.01563, over 7371.00 frames.], tot_loss[loss=0.1569, simple_loss=0.257, pruned_loss=0.0284, over 562396.80 frames.], batch size: 19, lr: 1.95e-04
+2022-05-01 01:25:56,224 INFO [train.py:763] (6/8) Epoch 39, batch 150, loss[loss=0.1557, simple_loss=0.2566, pruned_loss=0.02743, over 7233.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2551, pruned_loss=0.0281, over 755323.79 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:27:01,295 INFO [train.py:763] (6/8) Epoch 39, batch 200, loss[loss=0.153, simple_loss=0.2523, pruned_loss=0.02688, over 7428.00 frames.], tot_loss[loss=0.157, simple_loss=0.2577, pruned_loss=0.0282, over 904211.49 frames.], batch size: 18, lr: 1.95e-04
+2022-05-01 01:28:06,660 INFO [train.py:763] (6/8) Epoch 39, batch 250, loss[loss=0.169, simple_loss=0.2664, pruned_loss=0.0358, over 7100.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2575, pruned_loss=0.02807, over 1017629.47 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:29:11,529 INFO [train.py:763] (6/8) Epoch 39, batch 300, loss[loss=0.1731, simple_loss=0.2694, pruned_loss=0.03839, over 7301.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2573, pruned_loss=0.02784, over 1108240.51 frames.], batch size: 24, lr: 1.95e-04
+2022-05-01 01:30:16,876 INFO [train.py:763] (6/8) Epoch 39, batch 350, loss[loss=0.1576, simple_loss=0.2585, pruned_loss=0.02832, over 7144.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2568, pruned_loss=0.02776, over 1172545.79 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:31:22,221 INFO [train.py:763] (6/8) Epoch 39, batch 400, loss[loss=0.1612, simple_loss=0.269, pruned_loss=0.02668, over 7157.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2575, pruned_loss=0.02766, over 1229569.14 frames.], batch size: 26, lr: 1.95e-04
+2022-05-01 01:32:27,454 INFO [train.py:763] (6/8) Epoch 39, batch 450, loss[loss=0.161, simple_loss=0.2702, pruned_loss=0.02592, over 7273.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2567, pruned_loss=0.02733, over 1273038.52 frames.], batch size: 25, lr: 1.95e-04
+2022-05-01 01:33:32,868 INFO [train.py:763] (6/8) Epoch 39, batch 500, loss[loss=0.1459, simple_loss=0.2558, pruned_loss=0.01801, over 7321.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2566, pruned_loss=0.02745, over 1305064.21 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:34:38,281 INFO [train.py:763] (6/8) Epoch 39, batch 550, loss[loss=0.1687, simple_loss=0.2734, pruned_loss=0.03199, over 7228.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2573, pruned_loss=0.02772, over 1326530.67 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:35:43,499 INFO [train.py:763] (6/8) Epoch 39, batch 600, loss[loss=0.1744, simple_loss=0.2676, pruned_loss=0.0406, over 7261.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2569, pruned_loss=0.02789, over 1348726.08 frames.], batch size: 19, lr: 1.95e-04
+2022-05-01 01:36:48,739 INFO [train.py:763] (6/8) Epoch 39, batch 650, loss[loss=0.1512, simple_loss=0.2515, pruned_loss=0.02542, over 7227.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2568, pruned_loss=0.02787, over 1367387.09 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:37:53,923 INFO [train.py:763] (6/8) Epoch 39, batch 700, loss[loss=0.1457, simple_loss=0.2439, pruned_loss=0.02382, over 7278.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2569, pruned_loss=0.02761, over 1380770.78 frames.], batch size: 18, lr: 1.95e-04
+2022-05-01 01:38:59,265 INFO [train.py:763] (6/8) Epoch 39, batch 750, loss[loss=0.1372, simple_loss=0.2325, pruned_loss=0.021, over 7363.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2564, pruned_loss=0.02759, over 1386658.16 frames.], batch size: 19, lr: 1.95e-04
+2022-05-01 01:40:04,494 INFO [train.py:763] (6/8) Epoch 39, batch 800, loss[loss=0.1597, simple_loss=0.2609, pruned_loss=0.02921, over 7111.00 frames.], tot_loss[loss=0.1553, simple_loss=0.256, pruned_loss=0.02728, over 1396243.07 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:41:18,503 INFO [train.py:763] (6/8) Epoch 39, batch 850, loss[loss=0.1296, simple_loss=0.2247, pruned_loss=0.0173, over 7136.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2565, pruned_loss=0.0275, over 1402885.33 frames.], batch size: 17, lr: 1.95e-04
+2022-05-01 01:42:32,265 INFO [train.py:763] (6/8) Epoch 39, batch 900, loss[loss=0.1652, simple_loss=0.2726, pruned_loss=0.02888, over 7207.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2572, pruned_loss=0.02778, over 1408767.45 frames.], batch size: 23, lr: 1.95e-04
+2022-05-01 01:43:55,210 INFO [train.py:763] (6/8) Epoch 39, batch 950, loss[loss=0.1966, simple_loss=0.2966, pruned_loss=0.04833, over 4948.00 frames.], tot_loss[loss=0.157, simple_loss=0.2582, pruned_loss=0.0279, over 1411471.54 frames.], batch size: 52, lr: 1.95e-04
+2022-05-01 01:45:01,262 INFO [train.py:763] (6/8) Epoch 39, batch 1000, loss[loss=0.1555, simple_loss=0.2599, pruned_loss=0.0255, over 7117.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2581, pruned_loss=0.0282, over 1409580.67 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:46:06,272 INFO [train.py:763] (6/8) Epoch 39, batch 1050, loss[loss=0.1436, simple_loss=0.2534, pruned_loss=0.01686, over 7228.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2585, pruned_loss=0.02837, over 1409271.97 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:47:29,494 INFO [train.py:763] (6/8) Epoch 39, batch 1100, loss[loss=0.1473, simple_loss=0.2387, pruned_loss=0.02792, over 7162.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2582, pruned_loss=0.02854, over 1407956.41 frames.], batch size: 18, lr: 1.95e-04
+2022-05-01 01:48:43,943 INFO [train.py:763] (6/8) Epoch 39, batch 1150, loss[loss=0.1561, simple_loss=0.2616, pruned_loss=0.02525, over 6783.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2576, pruned_loss=0.02843, over 1415211.76 frames.], batch size: 31, lr: 1.95e-04
+2022-05-01 01:49:48,904 INFO [train.py:763] (6/8) Epoch 39, batch 1200, loss[loss=0.161, simple_loss=0.2682, pruned_loss=0.02693, over 6244.00 frames.], tot_loss[loss=0.1576, simple_loss=0.258, pruned_loss=0.02855, over 1417610.62 frames.], batch size: 38, lr: 1.95e-04
+2022-05-01 01:50:54,369 INFO [train.py:763] (6/8) Epoch 39, batch 1250, loss[loss=0.1739, simple_loss=0.281, pruned_loss=0.03341, over 7279.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2582, pruned_loss=0.02881, over 1422060.26 frames.], batch size: 25, lr: 1.95e-04
+2022-05-01 01:51:59,441 INFO [train.py:763] (6/8) Epoch 39, batch 1300, loss[loss=0.1561, simple_loss=0.2603, pruned_loss=0.02589, over 7414.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2586, pruned_loss=0.02889, over 1422497.30 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:53:04,817 INFO [train.py:763] (6/8) Epoch 39, batch 1350, loss[loss=0.1697, simple_loss=0.2736, pruned_loss=0.03292, over 6470.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2585, pruned_loss=0.02886, over 1422030.94 frames.], batch size: 37, lr: 1.95e-04
+2022-05-01 01:54:11,090 INFO [train.py:763] (6/8) Epoch 39, batch 1400, loss[loss=0.1655, simple_loss=0.2696, pruned_loss=0.03071, over 6183.00 frames.], tot_loss[loss=0.1575, simple_loss=0.258, pruned_loss=0.02848, over 1423321.94 frames.], batch size: 37, lr: 1.95e-04
+2022-05-01 01:55:16,354 INFO [train.py:763] (6/8) Epoch 39, batch 1450, loss[loss=0.1776, simple_loss=0.2798, pruned_loss=0.03765, over 7196.00 frames.], tot_loss[loss=0.157, simple_loss=0.2578, pruned_loss=0.0281, over 1424581.87 frames.], batch size: 23, lr: 1.95e-04
+2022-05-01 01:56:21,483 INFO [train.py:763] (6/8) Epoch 39, batch 1500, loss[loss=0.1513, simple_loss=0.248, pruned_loss=0.02734, over 7145.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2583, pruned_loss=0.02838, over 1425075.39 frames.], batch size: 17, lr: 1.95e-04
+2022-05-01 01:57:28,706 INFO [train.py:763] (6/8) Epoch 39, batch 1550, loss[loss=0.1856, simple_loss=0.2944, pruned_loss=0.03837, over 7201.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2572, pruned_loss=0.02801, over 1423436.32 frames.], batch size: 23, lr: 1.95e-04
+2022-05-01 01:58:35,232 INFO [train.py:763] (6/8) Epoch 39, batch 1600, loss[loss=0.1708, simple_loss=0.2819, pruned_loss=0.02985, over 7096.00 frames.], tot_loss[loss=0.157, simple_loss=0.2577, pruned_loss=0.02815, over 1426034.23 frames.], batch size: 28, lr: 1.95e-04
+2022-05-01 01:59:41,356 INFO [train.py:763] (6/8) Epoch 39, batch 1650, loss[loss=0.1637, simple_loss=0.2693, pruned_loss=0.02902, over 5111.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2575, pruned_loss=0.02808, over 1419721.66 frames.], batch size: 52, lr: 1.95e-04
+2022-05-01 02:00:47,163 INFO [train.py:763] (6/8) Epoch 39, batch 1700, loss[loss=0.1349, simple_loss=0.2242, pruned_loss=0.02285, over 6984.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2581, pruned_loss=0.02861, over 1412535.18 frames.], batch size: 16, lr: 1.95e-04
+2022-05-01 02:01:53,361 INFO [train.py:763] (6/8) Epoch 39, batch 1750, loss[loss=0.1651, simple_loss=0.2724, pruned_loss=0.0289, over 7309.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2575, pruned_loss=0.02857, over 1414622.23 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 02:02:58,282 INFO [train.py:763] (6/8) Epoch 39, batch 1800, loss[loss=0.1694, simple_loss=0.2775, pruned_loss=0.03065, over 7347.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.02858, over 1417097.10 frames.], batch size: 22, lr: 1.95e-04
+2022-05-01 02:04:03,602 INFO [train.py:763] (6/8) Epoch 39, batch 1850, loss[loss=0.1378, simple_loss=0.2302, pruned_loss=0.02264, over 7073.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2579, pruned_loss=0.02842, over 1420372.21 frames.], batch size: 18, lr: 1.95e-04
+2022-05-01 02:05:08,884 INFO [train.py:763] (6/8) Epoch 39, batch 1900, loss[loss=0.1349, simple_loss=0.2352, pruned_loss=0.01732, over 7174.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2586, pruned_loss=0.02845, over 1423749.92 frames.], batch size: 19, lr: 1.94e-04
+2022-05-01 02:06:14,311 INFO [train.py:763] (6/8) Epoch 39, batch 1950, loss[loss=0.2081, simple_loss=0.3013, pruned_loss=0.05747, over 5137.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2589, pruned_loss=0.02868, over 1417964.54 frames.], batch size: 52, lr: 1.94e-04
+2022-05-01 02:07:19,648 INFO [train.py:763] (6/8) Epoch 39, batch 2000, loss[loss=0.1355, simple_loss=0.2295, pruned_loss=0.02076, over 7079.00 frames.], tot_loss[loss=0.158, simple_loss=0.2588, pruned_loss=0.02863, over 1421737.32 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:08:24,809 INFO [train.py:763] (6/8) Epoch 39, batch 2050, loss[loss=0.1367, simple_loss=0.236, pruned_loss=0.01869, over 7434.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2582, pruned_loss=0.02838, over 1425927.22 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:09:30,530 INFO [train.py:763] (6/8) Epoch 39, batch 2100, loss[loss=0.1369, simple_loss=0.2217, pruned_loss=0.02608, over 7406.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2572, pruned_loss=0.02787, over 1424766.87 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:10:35,935 INFO [train.py:763] (6/8) Epoch 39, batch 2150, loss[loss=0.171, simple_loss=0.2864, pruned_loss=0.02782, over 7144.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2576, pruned_loss=0.02812, over 1428974.78 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:11:43,129 INFO [train.py:763] (6/8) Epoch 39, batch 2200, loss[loss=0.1695, simple_loss=0.2642, pruned_loss=0.03745, over 7236.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2577, pruned_loss=0.02837, over 1431664.25 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:12:48,270 INFO [train.py:763] (6/8) Epoch 39, batch 2250, loss[loss=0.1677, simple_loss=0.2743, pruned_loss=0.03056, over 7197.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2581, pruned_loss=0.02863, over 1430135.03 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:13:53,567 INFO [train.py:763] (6/8) Epoch 39, batch 2300, loss[loss=0.1705, simple_loss=0.268, pruned_loss=0.03644, over 7434.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2572, pruned_loss=0.02874, over 1426304.40 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:15:00,724 INFO [train.py:763] (6/8) Epoch 39, batch 2350, loss[loss=0.1742, simple_loss=0.2826, pruned_loss=0.03288, over 7347.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2562, pruned_loss=0.02858, over 1425061.33 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:16:07,773 INFO [train.py:763] (6/8) Epoch 39, batch 2400, loss[loss=0.1654, simple_loss=0.2739, pruned_loss=0.02848, over 7198.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2563, pruned_loss=0.02835, over 1425182.76 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:17:13,329 INFO [train.py:763] (6/8) Epoch 39, batch 2450, loss[loss=0.168, simple_loss=0.2689, pruned_loss=0.03359, over 7133.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2573, pruned_loss=0.02868, over 1420489.54 frames.], batch size: 28, lr: 1.94e-04
+2022-05-01 02:18:19,521 INFO [train.py:763] (6/8) Epoch 39, batch 2500, loss[loss=0.1661, simple_loss=0.2711, pruned_loss=0.03059, over 7422.00 frames.], tot_loss[loss=0.157, simple_loss=0.2571, pruned_loss=0.02844, over 1418122.07 frames.], batch size: 21, lr: 1.94e-04
+2022-05-01 02:19:24,722 INFO [train.py:763] (6/8) Epoch 39, batch 2550, loss[loss=0.1848, simple_loss=0.2853, pruned_loss=0.04214, over 7048.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2584, pruned_loss=0.02867, over 1418103.94 frames.], batch size: 28, lr: 1.94e-04
+2022-05-01 02:20:31,563 INFO [train.py:763] (6/8) Epoch 39, batch 2600, loss[loss=0.1763, simple_loss=0.2829, pruned_loss=0.03486, over 7337.00 frames.], tot_loss[loss=0.157, simple_loss=0.2574, pruned_loss=0.02829, over 1417305.07 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:21:37,534 INFO [train.py:763] (6/8) Epoch 39, batch 2650, loss[loss=0.1567, simple_loss=0.2558, pruned_loss=0.02878, over 7158.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2579, pruned_loss=0.0285, over 1420043.01 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:22:43,388 INFO [train.py:763] (6/8) Epoch 39, batch 2700, loss[loss=0.1731, simple_loss=0.2724, pruned_loss=0.03695, over 7174.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2583, pruned_loss=0.02844, over 1422096.51 frames.], batch size: 26, lr: 1.94e-04
+2022-05-01 02:23:48,617 INFO [train.py:763] (6/8) Epoch 39, batch 2750, loss[loss=0.1605, simple_loss=0.2591, pruned_loss=0.03098, over 7287.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2577, pruned_loss=0.02797, over 1426070.58 frames.], batch size: 24, lr: 1.94e-04
+2022-05-01 02:24:53,689 INFO [train.py:763] (6/8) Epoch 39, batch 2800, loss[loss=0.1517, simple_loss=0.2587, pruned_loss=0.02233, over 7069.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2584, pruned_loss=0.02817, over 1422784.89 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:25:58,655 INFO [train.py:763] (6/8) Epoch 39, batch 2850, loss[loss=0.1729, simple_loss=0.2908, pruned_loss=0.0275, over 6461.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2585, pruned_loss=0.02804, over 1418443.65 frames.], batch size: 38, lr: 1.94e-04
+2022-05-01 02:27:03,581 INFO [train.py:763] (6/8) Epoch 39, batch 2900, loss[loss=0.1439, simple_loss=0.2427, pruned_loss=0.02258, over 7072.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2578, pruned_loss=0.0278, over 1418612.84 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:28:08,501 INFO [train.py:763] (6/8) Epoch 39, batch 2950, loss[loss=0.1597, simple_loss=0.2601, pruned_loss=0.02959, over 7279.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2591, pruned_loss=0.02824, over 1417541.88 frames.], batch size: 24, lr: 1.94e-04
+2022-05-01 02:29:13,389 INFO [train.py:763] (6/8) Epoch 39, batch 3000, loss[loss=0.1763, simple_loss=0.2733, pruned_loss=0.0396, over 7343.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2599, pruned_loss=0.02855, over 1412448.94 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:29:13,390 INFO [train.py:783] (6/8) Computing validation loss
+2022-05-01 02:29:28,415 INFO [train.py:792] (6/8) Epoch 39, validation: loss=0.1688, simple_loss=0.2638, pruned_loss=0.03694, over 698248.00 frames.
+2022-05-01 02:30:33,958 INFO [train.py:763] (6/8) Epoch 39, batch 3050, loss[loss=0.1629, simple_loss=0.2609, pruned_loss=0.03243, over 7363.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2597, pruned_loss=0.02881, over 1415204.39 frames.], batch size: 19, lr: 1.94e-04
+2022-05-01 02:31:41,155 INFO [train.py:763] (6/8) Epoch 39, batch 3100, loss[loss=0.1692, simple_loss=0.2687, pruned_loss=0.03484, over 7179.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2595, pruned_loss=0.02877, over 1417763.14 frames.], batch size: 26, lr: 1.94e-04
+2022-05-01 02:32:47,803 INFO [train.py:763] (6/8) Epoch 39, batch 3150, loss[loss=0.1477, simple_loss=0.2506, pruned_loss=0.02242, over 7142.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2592, pruned_loss=0.02835, over 1421483.89 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:33:53,387 INFO [train.py:763] (6/8) Epoch 39, batch 3200, loss[loss=0.1684, simple_loss=0.2672, pruned_loss=0.03473, over 5162.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2596, pruned_loss=0.02861, over 1421788.90 frames.], batch size: 53, lr: 1.94e-04
+2022-05-01 02:34:58,489 INFO [train.py:763] (6/8) Epoch 39, batch 3250, loss[loss=0.1617, simple_loss=0.2618, pruned_loss=0.03078, over 7361.00 frames.], tot_loss[loss=0.1589, simple_loss=0.26, pruned_loss=0.02891, over 1420750.55 frames.], batch size: 23, lr: 1.94e-04
+2022-05-01 02:36:03,619 INFO [train.py:763] (6/8) Epoch 39, batch 3300, loss[loss=0.1476, simple_loss=0.2557, pruned_loss=0.01979, over 7114.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2588, pruned_loss=0.02851, over 1419159.25 frames.], batch size: 21, lr: 1.94e-04
+2022-05-01 02:37:08,800 INFO [train.py:763] (6/8) Epoch 39, batch 3350, loss[loss=0.167, simple_loss=0.2729, pruned_loss=0.03052, over 7116.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2589, pruned_loss=0.02847, over 1417096.61 frames.], batch size: 21, lr: 1.94e-04
+2022-05-01 02:38:14,798 INFO [train.py:763] (6/8) Epoch 39, batch 3400, loss[loss=0.1442, simple_loss=0.2473, pruned_loss=0.02052, over 7160.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2576, pruned_loss=0.02772, over 1418745.32 frames.], batch size: 19, lr: 1.94e-04
+2022-05-01 02:39:20,471 INFO [train.py:763] (6/8) Epoch 39, batch 3450, loss[loss=0.1282, simple_loss=0.2244, pruned_loss=0.01599, over 7282.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2579, pruned_loss=0.02773, over 1417996.90 frames.], batch size: 17, lr: 1.94e-04
+2022-05-01 02:40:25,651 INFO [train.py:763] (6/8) Epoch 39, batch 3500, loss[loss=0.1486, simple_loss=0.2541, pruned_loss=0.02149, over 7317.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2589, pruned_loss=0.02819, over 1418539.48 frames.], batch size: 21, lr: 1.94e-04
+2022-05-01 02:41:31,488 INFO [train.py:763] (6/8) Epoch 39, batch 3550, loss[loss=0.1393, simple_loss=0.2323, pruned_loss=0.02313, over 7067.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2574, pruned_loss=0.02818, over 1420164.60 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:42:37,767 INFO [train.py:763] (6/8) Epoch 39, batch 3600, loss[loss=0.1649, simple_loss=0.2612, pruned_loss=0.03432, over 4521.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2585, pruned_loss=0.02894, over 1417249.93 frames.], batch size: 53, lr: 1.94e-04
+2022-05-01 02:43:44,824 INFO [train.py:763] (6/8) Epoch 39, batch 3650, loss[loss=0.167, simple_loss=0.2624, pruned_loss=0.03583, over 6326.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2578, pruned_loss=0.02884, over 1418972.80 frames.], batch size: 37, lr: 1.94e-04
+2022-05-01 02:44:50,054 INFO [train.py:763] (6/8) Epoch 39, batch 3700, loss[loss=0.1453, simple_loss=0.2379, pruned_loss=0.02635, over 7141.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2579, pruned_loss=0.02855, over 1423488.59 frames.], batch size: 17, lr: 1.94e-04
+2022-05-01 02:45:55,096 INFO [train.py:763] (6/8) Epoch 39, batch 3750, loss[loss=0.1505, simple_loss=0.2574, pruned_loss=0.02178, over 7366.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2582, pruned_loss=0.02847, over 1419979.25 frames.], batch size: 19, lr: 1.93e-04
+2022-05-01 02:47:00,706 INFO [train.py:763] (6/8) Epoch 39, batch 3800, loss[loss=0.12, simple_loss=0.2104, pruned_loss=0.0148, over 6984.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2577, pruned_loss=0.02828, over 1424562.31 frames.], batch size: 16, lr: 1.93e-04
+2022-05-01 02:48:07,768 INFO [train.py:763] (6/8) Epoch 39, batch 3850, loss[loss=0.1689, simple_loss=0.2773, pruned_loss=0.0302, over 7415.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2571, pruned_loss=0.02798, over 1419568.23 frames.], batch size: 21, lr: 1.93e-04
+2022-05-01 02:49:13,631 INFO [train.py:763] (6/8) Epoch 39, batch 3900, loss[loss=0.1914, simple_loss=0.3025, pruned_loss=0.04011, over 7208.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2572, pruned_loss=0.02808, over 1419492.45 frames.], batch size: 23, lr: 1.93e-04
+2022-05-01 02:50:20,007 INFO [train.py:763] (6/8) Epoch 39, batch 3950, loss[loss=0.1452, simple_loss=0.2379, pruned_loss=0.0263, over 7046.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2563, pruned_loss=0.02842, over 1415653.30 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 02:51:25,346 INFO [train.py:763] (6/8) Epoch 39, batch 4000, loss[loss=0.1392, simple_loss=0.2361, pruned_loss=0.02112, over 7132.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2563, pruned_loss=0.02823, over 1414836.14 frames.], batch size: 17, lr: 1.93e-04
+2022-05-01 02:52:30,795 INFO [train.py:763] (6/8) Epoch 39, batch 4050, loss[loss=0.176, simple_loss=0.2867, pruned_loss=0.03267, over 7211.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2561, pruned_loss=0.02801, over 1419111.26 frames.], batch size: 22, lr: 1.93e-04
+2022-05-01 02:53:35,946 INFO [train.py:763] (6/8) Epoch 39, batch 4100, loss[loss=0.1584, simple_loss=0.2604, pruned_loss=0.02821, over 7241.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2564, pruned_loss=0.02823, over 1419175.24 frames.], batch size: 20, lr: 1.93e-04
+2022-05-01 02:54:41,370 INFO [train.py:763] (6/8) Epoch 39, batch 4150, loss[loss=0.1509, simple_loss=0.2452, pruned_loss=0.0283, over 7273.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2565, pruned_loss=0.02808, over 1421642.21 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 02:55:46,810 INFO [train.py:763] (6/8) Epoch 39, batch 4200, loss[loss=0.14, simple_loss=0.2377, pruned_loss=0.02121, over 7155.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2572, pruned_loss=0.02795, over 1423275.81 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 02:56:52,116 INFO [train.py:763] (6/8) Epoch 39, batch 4250, loss[loss=0.1819, simple_loss=0.2907, pruned_loss=0.03659, over 7317.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2572, pruned_loss=0.02846, over 1419640.51 frames.], batch size: 21, lr: 1.93e-04
+2022-05-01 02:57:57,424 INFO [train.py:763] (6/8) Epoch 39, batch 4300, loss[loss=0.1373, simple_loss=0.237, pruned_loss=0.01884, over 7174.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2575, pruned_loss=0.0286, over 1420786.42 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 02:59:02,812 INFO [train.py:763] (6/8) Epoch 39, batch 4350, loss[loss=0.1553, simple_loss=0.2538, pruned_loss=0.02837, over 7330.00 frames.], tot_loss[loss=0.1575, simple_loss=0.258, pruned_loss=0.02851, over 1422393.68 frames.], batch size: 20, lr: 1.93e-04
+2022-05-01 03:00:09,028 INFO [train.py:763] (6/8) Epoch 39, batch 4400, loss[loss=0.1772, simple_loss=0.2819, pruned_loss=0.0362, over 6785.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2582, pruned_loss=0.02839, over 1422208.21 frames.], batch size: 31, lr: 1.93e-04
+2022-05-01 03:01:14,006 INFO [train.py:763] (6/8) Epoch 39, batch 4450, loss[loss=0.1353, simple_loss=0.234, pruned_loss=0.01835, over 7154.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2585, pruned_loss=0.0285, over 1408780.41 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 03:02:19,221 INFO [train.py:763] (6/8) Epoch 39, batch 4500, loss[loss=0.1508, simple_loss=0.2576, pruned_loss=0.02194, over 7216.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2593, pruned_loss=0.0291, over 1401562.16 frames.], batch size: 21, lr: 1.93e-04
+2022-05-01 03:03:25,870 INFO [train.py:763] (6/8) Epoch 39, batch 4550, loss[loss=0.1229, simple_loss=0.2086, pruned_loss=0.01859, over 7214.00 frames.], tot_loss[loss=0.1566, simple_loss=0.256, pruned_loss=0.02858, over 1394028.04 frames.], batch size: 16, lr: 1.93e-04
+2022-05-01 03:04:15,372 INFO [train.py:971] (6/8) Done!