diff --git "a/exp/log/log-train-2022-05-13-19-15-59-7" "b/exp/log/log-train-2022-05-13-19-15-59-7"
new file mode 100644--- /dev/null
+++ "b/exp/log/log-train-2022-05-13-19-15-59-7"
@@ -0,0 +1,3784 @@
+2022-05-13 19:15:59,543 INFO [train.py:876] (7/8) Training started
+2022-05-13 19:15:59,544 INFO [train.py:886] (7/8) Device: cuda:7
+2022-05-13 19:15:59,547 INFO [train.py:895] (7/8) {'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': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 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-without-random-combiner', 'icefall-git-sha1': '7b786ce-dirty', 'icefall-git-date': 'Fri May 13 18:53:22 2022', 'icefall-path': '/ceph-fj/fangjun/open-source-2/icefall-deeper-conformer-2', 'k2-path': '/ceph-fj/fangjun/open-source-2/k2-multi-22/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-fj/fangjun/open-source-2/lhotse-multi-3/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-6-0415002726-7dc5bf9fdc-w24k9', 'IP address': '10.177.28.71'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 40, 'start_epoch': 1, 'start_batch': 0, 'exp_dir': PosixPath('pruned_transducer_stateless5/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': 4000, 'keep_last_k': 30, 'average_period': 100, '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}
+2022-05-13 19:15:59,547 INFO [train.py:897] (7/8) About to create model
+2022-05-13 19:16:00,245 INFO [train.py:901] (7/8) Number of model parameters: 116553580
+2022-05-13 19:16:07,871 INFO [train.py:916] (7/8) Using DDP
+2022-05-13 19:16:09,396 INFO [asr_datamodule.py:391] (7/8) About to get train-clean-100 cuts
+2022-05-13 19:16:17,908 INFO [asr_datamodule.py:398] (7/8) About to get train-clean-360 cuts
+2022-05-13 19:16:51,577 INFO [asr_datamodule.py:405] (7/8) About to get train-other-500 cuts
+2022-05-13 19:17:46,498 INFO [asr_datamodule.py:209] (7/8) Enable MUSAN
+2022-05-13 19:17:46,498 INFO [asr_datamodule.py:210] (7/8) About to get Musan cuts
+2022-05-13 19:17:48,452 INFO [asr_datamodule.py:238] (7/8) Enable SpecAugment
+2022-05-13 19:17:48,453 INFO [asr_datamodule.py:239] (7/8) Time warp factor: 80
+2022-05-13 19:17:48,453 INFO [asr_datamodule.py:251] (7/8) Num frame mask: 10
+2022-05-13 19:17:48,453 INFO [asr_datamodule.py:264] (7/8) About to create train dataset
+2022-05-13 19:17:48,453 INFO [asr_datamodule.py:292] (7/8) Using BucketingSampler.
+2022-05-13 19:17:54,452 INFO [asr_datamodule.py:308] (7/8) About to create train dataloader
+2022-05-13 19:17:54,453 INFO [asr_datamodule.py:412] (7/8) About to get dev-clean cuts
+2022-05-13 19:17:54,795 INFO [asr_datamodule.py:417] (7/8) About to get dev-other cuts
+2022-05-13 19:17:55,002 INFO [asr_datamodule.py:339] (7/8) About to create dev dataset
+2022-05-13 19:17:55,015 INFO [asr_datamodule.py:358] (7/8) About to create dev dataloader
+2022-05-13 19:17:55,015 INFO [train.py:1078] (7/8) Sanity check -- see if any of the batches in epoch 1 would cause OOM.
+2022-05-13 19:18:18,421 INFO [distributed.py:874] (7/8) Reducer buckets have been rebuilt in this iteration.
+2022-05-13 19:18:42,072 INFO [train.py:812] (7/8) Epoch 1, batch 0, loss[loss=0.8802, simple_loss=1.76, pruned_loss=6.746, over 7292.00 frames.], tot_loss[loss=0.8802, simple_loss=1.76, pruned_loss=6.746, over 7292.00 frames.], batch size: 17, lr: 3.00e-03
+2022-05-13 19:19:41,286 INFO [train.py:812] (7/8) Epoch 1, batch 50, loss[loss=0.4808, simple_loss=0.9616, pruned_loss=7.055, over 7156.00 frames.], tot_loss[loss=0.5587, simple_loss=1.117, pruned_loss=7.123, over 323654.95 frames.], batch size: 19, lr: 3.00e-03
+2022-05-13 19:20:39,835 INFO [train.py:812] (7/8) Epoch 1, batch 100, loss[loss=0.4057, simple_loss=0.8114, pruned_loss=6.587, over 6992.00 frames.], tot_loss[loss=0.4936, simple_loss=0.9871, pruned_loss=6.966, over 565893.19 frames.], batch size: 16, lr: 3.00e-03
+2022-05-13 19:21:38,661 INFO [train.py:812] (7/8) Epoch 1, batch 150, loss[loss=0.3643, simple_loss=0.7287, pruned_loss=6.728, over 7429.00 frames.], tot_loss[loss=0.4634, simple_loss=0.9267, pruned_loss=6.876, over 758349.43 frames.], batch size: 17, lr: 3.00e-03
+2022-05-13 19:22:36,965 INFO [train.py:812] (7/8) Epoch 1, batch 200, loss[loss=0.4294, simple_loss=0.8588, pruned_loss=6.792, over 7295.00 frames.], tot_loss[loss=0.4423, simple_loss=0.8847, pruned_loss=6.84, over 907946.06 frames.], batch size: 25, lr: 3.00e-03
+2022-05-13 19:23:35,691 INFO [train.py:812] (7/8) Epoch 1, batch 250, loss[loss=0.4118, simple_loss=0.8235, pruned_loss=6.926, over 7337.00 frames.], tot_loss[loss=0.4284, simple_loss=0.8568, pruned_loss=6.831, over 1016113.76 frames.], batch size: 21, lr: 3.00e-03
+2022-05-13 19:24:34,054 INFO [train.py:812] (7/8) Epoch 1, batch 300, loss[loss=0.4035, simple_loss=0.807, pruned_loss=6.846, over 7271.00 frames.], tot_loss[loss=0.4179, simple_loss=0.8359, pruned_loss=6.824, over 1108046.42 frames.], batch size: 25, lr: 3.00e-03
+2022-05-13 19:25:33,464 INFO [train.py:812] (7/8) Epoch 1, batch 350, loss[loss=0.3729, simple_loss=0.7459, pruned_loss=6.847, over 7251.00 frames.], tot_loss[loss=0.4084, simple_loss=0.8168, pruned_loss=6.812, over 1178560.34 frames.], batch size: 19, lr: 3.00e-03
+2022-05-13 19:26:31,650 INFO [train.py:812] (7/8) Epoch 1, batch 400, loss[loss=0.3694, simple_loss=0.7389, pruned_loss=6.799, over 7416.00 frames.], tot_loss[loss=0.4022, simple_loss=0.8043, pruned_loss=6.801, over 1231256.83 frames.], batch size: 21, lr: 3.00e-03
+2022-05-13 19:27:30,043 INFO [train.py:812] (7/8) Epoch 1, batch 450, loss[loss=0.3468, simple_loss=0.6936, pruned_loss=6.813, over 7415.00 frames.], tot_loss[loss=0.3931, simple_loss=0.7862, pruned_loss=6.787, over 1267392.15 frames.], batch size: 21, lr: 2.99e-03
+2022-05-13 19:28:29,401 INFO [train.py:812] (7/8) Epoch 1, batch 500, loss[loss=0.3205, simple_loss=0.6409, pruned_loss=6.686, over 7200.00 frames.], tot_loss[loss=0.3779, simple_loss=0.7558, pruned_loss=6.771, over 1303605.71 frames.], batch size: 22, lr: 2.99e-03
+2022-05-13 19:29:27,230 INFO [train.py:812] (7/8) Epoch 1, batch 550, loss[loss=0.3266, simple_loss=0.6533, pruned_loss=6.789, over 7338.00 frames.], tot_loss[loss=0.3633, simple_loss=0.7266, pruned_loss=6.767, over 1329819.61 frames.], batch size: 22, lr: 2.99e-03
+2022-05-13 19:30:26,704 INFO [train.py:812] (7/8) Epoch 1, batch 600, loss[loss=0.2796, simple_loss=0.5591, pruned_loss=6.708, over 7107.00 frames.], tot_loss[loss=0.3479, simple_loss=0.6959, pruned_loss=6.764, over 1350521.69 frames.], batch size: 21, lr: 2.99e-03
+2022-05-13 19:31:24,376 INFO [train.py:812] (7/8) Epoch 1, batch 650, loss[loss=0.2173, simple_loss=0.4347, pruned_loss=6.558, over 7007.00 frames.], tot_loss[loss=0.3325, simple_loss=0.665, pruned_loss=6.757, over 1368818.91 frames.], batch size: 16, lr: 2.99e-03
+2022-05-13 19:32:22,749 INFO [train.py:812] (7/8) Epoch 1, batch 700, loss[loss=0.2709, simple_loss=0.5419, pruned_loss=6.819, over 7214.00 frames.], tot_loss[loss=0.3168, simple_loss=0.6335, pruned_loss=6.746, over 1380636.47 frames.], batch size: 23, lr: 2.99e-03
+2022-05-13 19:33:21,793 INFO [train.py:812] (7/8) Epoch 1, batch 750, loss[loss=0.214, simple_loss=0.4279, pruned_loss=6.436, over 7282.00 frames.], tot_loss[loss=0.302, simple_loss=0.604, pruned_loss=6.736, over 1392393.26 frames.], batch size: 17, lr: 2.98e-03
+2022-05-13 19:34:19,631 INFO [train.py:812] (7/8) Epoch 1, batch 800, loss[loss=0.2447, simple_loss=0.4893, pruned_loss=6.645, over 7117.00 frames.], tot_loss[loss=0.2903, simple_loss=0.5806, pruned_loss=6.735, over 1397508.98 frames.], batch size: 21, lr: 2.98e-03
+2022-05-13 19:35:17,961 INFO [train.py:812] (7/8) Epoch 1, batch 850, loss[loss=0.261, simple_loss=0.522, pruned_loss=6.82, over 7221.00 frames.], tot_loss[loss=0.2801, simple_loss=0.5601, pruned_loss=6.735, over 1402758.36 frames.], batch size: 21, lr: 2.98e-03
+2022-05-13 19:36:17,425 INFO [train.py:812] (7/8) Epoch 1, batch 900, loss[loss=0.2562, simple_loss=0.5125, pruned_loss=6.822, over 7319.00 frames.], tot_loss[loss=0.2693, simple_loss=0.5385, pruned_loss=6.73, over 1408475.78 frames.], batch size: 21, lr: 2.98e-03
+2022-05-13 19:37:15,470 INFO [train.py:812] (7/8) Epoch 1, batch 950, loss[loss=0.2104, simple_loss=0.4207, pruned_loss=6.547, over 7021.00 frames.], tot_loss[loss=0.2621, simple_loss=0.5242, pruned_loss=6.734, over 1405706.88 frames.], batch size: 16, lr: 2.97e-03
+2022-05-13 19:38:15,214 INFO [train.py:812] (7/8) Epoch 1, batch 1000, loss[loss=0.1982, simple_loss=0.3965, pruned_loss=6.593, over 7014.00 frames.], tot_loss[loss=0.2561, simple_loss=0.5123, pruned_loss=6.737, over 1406348.85 frames.], batch size: 16, lr: 2.97e-03
+2022-05-13 19:39:14,107 INFO [train.py:812] (7/8) Epoch 1, batch 1050, loss[loss=0.1915, simple_loss=0.3831, pruned_loss=6.569, over 6999.00 frames.], tot_loss[loss=0.2502, simple_loss=0.5004, pruned_loss=6.744, over 1408441.01 frames.], batch size: 16, lr: 2.97e-03
+2022-05-13 19:40:12,445 INFO [train.py:812] (7/8) Epoch 1, batch 1100, loss[loss=0.2281, simple_loss=0.4562, pruned_loss=6.856, over 7208.00 frames.], tot_loss[loss=0.2448, simple_loss=0.4895, pruned_loss=6.749, over 1411458.53 frames.], batch size: 22, lr: 2.96e-03
+2022-05-13 19:41:10,387 INFO [train.py:812] (7/8) Epoch 1, batch 1150, loss[loss=0.2404, simple_loss=0.4808, pruned_loss=6.918, over 6817.00 frames.], tot_loss[loss=0.2389, simple_loss=0.4778, pruned_loss=6.75, over 1412922.55 frames.], batch size: 31, lr: 2.96e-03
+2022-05-13 19:42:08,540 INFO [train.py:812] (7/8) Epoch 1, batch 1200, loss[loss=0.2664, simple_loss=0.5328, pruned_loss=6.993, over 7151.00 frames.], tot_loss[loss=0.2344, simple_loss=0.4688, pruned_loss=6.754, over 1420383.35 frames.], batch size: 26, lr: 2.96e-03
+2022-05-13 19:43:07,180 INFO [train.py:812] (7/8) Epoch 1, batch 1250, loss[loss=0.2251, simple_loss=0.4503, pruned_loss=6.858, over 7384.00 frames.], tot_loss[loss=0.2303, simple_loss=0.4607, pruned_loss=6.756, over 1414223.27 frames.], batch size: 23, lr: 2.95e-03
+2022-05-13 19:44:06,134 INFO [train.py:812] (7/8) Epoch 1, batch 1300, loss[loss=0.2283, simple_loss=0.4567, pruned_loss=6.855, over 7271.00 frames.], tot_loss[loss=0.2265, simple_loss=0.4531, pruned_loss=6.76, over 1421399.42 frames.], batch size: 24, lr: 2.95e-03
+2022-05-13 19:45:04,294 INFO [train.py:812] (7/8) Epoch 1, batch 1350, loss[loss=0.2244, simple_loss=0.4489, pruned_loss=6.823, over 7154.00 frames.], tot_loss[loss=0.2224, simple_loss=0.4448, pruned_loss=6.753, over 1422770.83 frames.], batch size: 20, lr: 2.95e-03
+2022-05-13 19:46:03,489 INFO [train.py:812] (7/8) Epoch 1, batch 1400, loss[loss=0.2267, simple_loss=0.4534, pruned_loss=6.873, over 7312.00 frames.], tot_loss[loss=0.2211, simple_loss=0.4423, pruned_loss=6.763, over 1418882.25 frames.], batch size: 24, lr: 2.94e-03
+2022-05-13 19:47:02,134 INFO [train.py:812] (7/8) Epoch 1, batch 1450, loss[loss=0.1714, simple_loss=0.3428, pruned_loss=6.664, over 7128.00 frames.], tot_loss[loss=0.2181, simple_loss=0.4363, pruned_loss=6.764, over 1419888.77 frames.], batch size: 17, lr: 2.94e-03
+2022-05-13 19:48:00,936 INFO [train.py:812] (7/8) Epoch 1, batch 1500, loss[loss=0.2231, simple_loss=0.4461, pruned_loss=6.812, over 7293.00 frames.], tot_loss[loss=0.2158, simple_loss=0.4316, pruned_loss=6.767, over 1422685.94 frames.], batch size: 24, lr: 2.94e-03
+2022-05-13 19:48:59,506 INFO [train.py:812] (7/8) Epoch 1, batch 1550, loss[loss=0.2072, simple_loss=0.4144, pruned_loss=6.774, over 7108.00 frames.], tot_loss[loss=0.2139, simple_loss=0.4278, pruned_loss=6.765, over 1422533.61 frames.], batch size: 21, lr: 2.93e-03
+2022-05-13 19:49:59,144 INFO [train.py:812] (7/8) Epoch 1, batch 1600, loss[loss=0.205, simple_loss=0.4101, pruned_loss=6.675, over 7331.00 frames.], tot_loss[loss=0.2114, simple_loss=0.4228, pruned_loss=6.761, over 1420066.34 frames.], batch size: 20, lr: 2.93e-03
+2022-05-13 19:50:59,027 INFO [train.py:812] (7/8) Epoch 1, batch 1650, loss[loss=0.1906, simple_loss=0.3813, pruned_loss=6.649, over 7163.00 frames.], tot_loss[loss=0.2092, simple_loss=0.4184, pruned_loss=6.759, over 1421842.80 frames.], batch size: 18, lr: 2.92e-03
+2022-05-13 19:51:59,072 INFO [train.py:812] (7/8) Epoch 1, batch 1700, loss[loss=0.2102, simple_loss=0.4203, pruned_loss=6.851, over 6529.00 frames.], tot_loss[loss=0.2071, simple_loss=0.4141, pruned_loss=6.761, over 1417238.91 frames.], batch size: 38, lr: 2.92e-03
+2022-05-13 19:52:58,903 INFO [train.py:812] (7/8) Epoch 1, batch 1750, loss[loss=0.1971, simple_loss=0.3943, pruned_loss=6.747, over 6374.00 frames.], tot_loss[loss=0.2039, simple_loss=0.4077, pruned_loss=6.755, over 1417098.62 frames.], batch size: 37, lr: 2.91e-03
+2022-05-13 19:54:00,195 INFO [train.py:812] (7/8) Epoch 1, batch 1800, loss[loss=0.2103, simple_loss=0.4205, pruned_loss=6.898, over 7030.00 frames.], tot_loss[loss=0.2023, simple_loss=0.4045, pruned_loss=6.757, over 1417496.87 frames.], batch size: 28, lr: 2.91e-03
+2022-05-13 19:54:58,687 INFO [train.py:812] (7/8) Epoch 1, batch 1850, loss[loss=0.2256, simple_loss=0.4512, pruned_loss=6.784, over 5370.00 frames.], tot_loss[loss=0.2001, simple_loss=0.4001, pruned_loss=6.756, over 1418566.32 frames.], batch size: 53, lr: 2.91e-03
+2022-05-13 19:55:57,033 INFO [train.py:812] (7/8) Epoch 1, batch 1900, loss[loss=0.194, simple_loss=0.388, pruned_loss=6.822, over 7260.00 frames.], tot_loss[loss=0.1991, simple_loss=0.3981, pruned_loss=6.758, over 1418525.20 frames.], batch size: 19, lr: 2.90e-03
+2022-05-13 19:56:55,453 INFO [train.py:812] (7/8) Epoch 1, batch 1950, loss[loss=0.2235, simple_loss=0.447, pruned_loss=6.823, over 7321.00 frames.], tot_loss[loss=0.1979, simple_loss=0.3957, pruned_loss=6.756, over 1421328.80 frames.], batch size: 21, lr: 2.90e-03
+2022-05-13 19:57:54,266 INFO [train.py:812] (7/8) Epoch 1, batch 2000, loss[loss=0.1755, simple_loss=0.3509, pruned_loss=6.699, over 6733.00 frames.], tot_loss[loss=0.1971, simple_loss=0.3941, pruned_loss=6.758, over 1421835.13 frames.], batch size: 15, lr: 2.89e-03
+2022-05-13 19:58:53,079 INFO [train.py:812] (7/8) Epoch 1, batch 2050, loss[loss=0.1935, simple_loss=0.387, pruned_loss=6.785, over 7213.00 frames.], tot_loss[loss=0.1959, simple_loss=0.3918, pruned_loss=6.759, over 1421009.57 frames.], batch size: 26, lr: 2.89e-03
+2022-05-13 19:59:51,435 INFO [train.py:812] (7/8) Epoch 1, batch 2100, loss[loss=0.1804, simple_loss=0.3609, pruned_loss=6.784, over 7167.00 frames.], tot_loss[loss=0.1956, simple_loss=0.3912, pruned_loss=6.76, over 1418723.33 frames.], batch size: 18, lr: 2.88e-03
+2022-05-13 20:00:49,550 INFO [train.py:812] (7/8) Epoch 1, batch 2150, loss[loss=0.1937, simple_loss=0.3873, pruned_loss=6.677, over 7340.00 frames.], tot_loss[loss=0.1951, simple_loss=0.3901, pruned_loss=6.758, over 1422125.29 frames.], batch size: 22, lr: 2.88e-03
+2022-05-13 20:01:48,646 INFO [train.py:812] (7/8) Epoch 1, batch 2200, loss[loss=0.2048, simple_loss=0.4096, pruned_loss=6.7, over 7295.00 frames.], tot_loss[loss=0.1936, simple_loss=0.3871, pruned_loss=6.759, over 1421458.99 frames.], batch size: 25, lr: 2.87e-03
+2022-05-13 20:02:47,481 INFO [train.py:812] (7/8) Epoch 1, batch 2250, loss[loss=0.2085, simple_loss=0.4171, pruned_loss=6.855, over 7220.00 frames.], tot_loss[loss=0.1918, simple_loss=0.3837, pruned_loss=6.752, over 1421141.95 frames.], batch size: 21, lr: 2.86e-03
+2022-05-13 20:03:45,880 INFO [train.py:812] (7/8) Epoch 1, batch 2300, loss[loss=0.1887, simple_loss=0.3775, pruned_loss=6.824, over 7261.00 frames.], tot_loss[loss=0.1913, simple_loss=0.3825, pruned_loss=6.753, over 1416548.90 frames.], batch size: 19, lr: 2.86e-03
+2022-05-13 20:04:43,237 INFO [train.py:812] (7/8) Epoch 1, batch 2350, loss[loss=0.2072, simple_loss=0.4144, pruned_loss=6.759, over 5169.00 frames.], tot_loss[loss=0.1907, simple_loss=0.3814, pruned_loss=6.754, over 1415764.62 frames.], batch size: 52, lr: 2.85e-03
+2022-05-13 20:05:42,794 INFO [train.py:812] (7/8) Epoch 1, batch 2400, loss[loss=0.1946, simple_loss=0.3892, pruned_loss=6.811, over 7434.00 frames.], tot_loss[loss=0.1902, simple_loss=0.3803, pruned_loss=6.757, over 1411490.93 frames.], batch size: 20, lr: 2.85e-03
+2022-05-13 20:06:41,434 INFO [train.py:812] (7/8) Epoch 1, batch 2450, loss[loss=0.2215, simple_loss=0.4431, pruned_loss=6.82, over 5039.00 frames.], tot_loss[loss=0.189, simple_loss=0.3779, pruned_loss=6.757, over 1411544.76 frames.], batch size: 52, lr: 2.84e-03
+2022-05-13 20:07:40,744 INFO [train.py:812] (7/8) Epoch 1, batch 2500, loss[loss=0.1859, simple_loss=0.3718, pruned_loss=6.773, over 7338.00 frames.], tot_loss[loss=0.1879, simple_loss=0.3758, pruned_loss=6.754, over 1417263.10 frames.], batch size: 20, lr: 2.84e-03
+2022-05-13 20:08:39,354 INFO [train.py:812] (7/8) Epoch 1, batch 2550, loss[loss=0.1615, simple_loss=0.3231, pruned_loss=6.692, over 7406.00 frames.], tot_loss[loss=0.1879, simple_loss=0.3759, pruned_loss=6.751, over 1417722.95 frames.], batch size: 18, lr: 2.83e-03
+2022-05-13 20:09:37,912 INFO [train.py:812] (7/8) Epoch 1, batch 2600, loss[loss=0.194, simple_loss=0.3881, pruned_loss=6.88, over 7224.00 frames.], tot_loss[loss=0.187, simple_loss=0.374, pruned_loss=6.745, over 1419797.69 frames.], batch size: 20, lr: 2.83e-03
+2022-05-13 20:10:35,884 INFO [train.py:812] (7/8) Epoch 1, batch 2650, loss[loss=0.1784, simple_loss=0.3567, pruned_loss=6.738, over 7236.00 frames.], tot_loss[loss=0.1859, simple_loss=0.3717, pruned_loss=6.744, over 1421737.22 frames.], batch size: 20, lr: 2.82e-03
+2022-05-13 20:11:35,636 INFO [train.py:812] (7/8) Epoch 1, batch 2700, loss[loss=0.1928, simple_loss=0.3857, pruned_loss=6.821, over 7147.00 frames.], tot_loss[loss=0.1852, simple_loss=0.3703, pruned_loss=6.744, over 1421672.96 frames.], batch size: 20, lr: 2.81e-03
+2022-05-13 20:12:32,575 INFO [train.py:812] (7/8) Epoch 1, batch 2750, loss[loss=0.1716, simple_loss=0.3432, pruned_loss=6.782, over 7330.00 frames.], tot_loss[loss=0.1847, simple_loss=0.3695, pruned_loss=6.746, over 1422537.92 frames.], batch size: 20, lr: 2.81e-03
+2022-05-13 20:13:32,059 INFO [train.py:812] (7/8) Epoch 1, batch 2800, loss[loss=0.2022, simple_loss=0.4044, pruned_loss=6.885, over 7139.00 frames.], tot_loss[loss=0.1848, simple_loss=0.3696, pruned_loss=6.746, over 1421071.69 frames.], batch size: 20, lr: 2.80e-03
+2022-05-13 20:14:30,995 INFO [train.py:812] (7/8) Epoch 1, batch 2850, loss[loss=0.1685, simple_loss=0.3371, pruned_loss=6.698, over 7363.00 frames.], tot_loss[loss=0.1837, simple_loss=0.3674, pruned_loss=6.743, over 1424328.61 frames.], batch size: 19, lr: 2.80e-03
+2022-05-13 20:15:28,513 INFO [train.py:812] (7/8) Epoch 1, batch 2900, loss[loss=0.1595, simple_loss=0.319, pruned_loss=6.707, over 7323.00 frames.], tot_loss[loss=0.1846, simple_loss=0.3692, pruned_loss=6.746, over 1419939.87 frames.], batch size: 20, lr: 2.79e-03
+2022-05-13 20:16:27,597 INFO [train.py:812] (7/8) Epoch 1, batch 2950, loss[loss=0.1872, simple_loss=0.3743, pruned_loss=6.788, over 7216.00 frames.], tot_loss[loss=0.1841, simple_loss=0.3683, pruned_loss=6.744, over 1414920.49 frames.], batch size: 26, lr: 2.78e-03
+2022-05-13 20:17:26,766 INFO [train.py:812] (7/8) Epoch 1, batch 3000, loss[loss=0.3397, simple_loss=0.3681, pruned_loss=1.557, over 7289.00 frames.], tot_loss[loss=0.2175, simple_loss=0.3664, pruned_loss=6.719, over 1419275.99 frames.], batch size: 17, lr: 2.78e-03
+2022-05-13 20:17:26,767 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-13 20:17:34,929 INFO [train.py:841] (7/8) Epoch 1, validation: loss=2.094, simple_loss=0.4148, pruned_loss=1.887, over 698248.00 frames.
+2022-05-13 20:18:33,868 INFO [train.py:812] (7/8) Epoch 1, batch 3050, loss[loss=0.3095, simple_loss=0.4167, pruned_loss=1.011, over 6376.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3757, pruned_loss=5.509, over 1418876.73 frames.], batch size: 37, lr: 2.77e-03
+2022-05-13 20:19:33,938 INFO [train.py:812] (7/8) Epoch 1, batch 3100, loss[loss=0.2398, simple_loss=0.3654, pruned_loss=0.5711, over 7408.00 frames.], tot_loss[loss=0.2437, simple_loss=0.3707, pruned_loss=4.432, over 1424548.72 frames.], batch size: 21, lr: 2.77e-03
+2022-05-13 20:20:32,566 INFO [train.py:812] (7/8) Epoch 1, batch 3150, loss[loss=0.2103, simple_loss=0.3529, pruned_loss=0.3386, over 7419.00 frames.], tot_loss[loss=0.2394, simple_loss=0.3686, pruned_loss=3.543, over 1426117.12 frames.], batch size: 21, lr: 2.76e-03
+2022-05-13 20:21:30,577 INFO [train.py:812] (7/8) Epoch 1, batch 3200, loss[loss=0.2272, simple_loss=0.393, pruned_loss=0.3068, over 7302.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3679, pruned_loss=2.833, over 1422439.89 frames.], batch size: 24, lr: 2.75e-03
+2022-05-13 20:22:29,497 INFO [train.py:812] (7/8) Epoch 1, batch 3250, loss[loss=0.2352, simple_loss=0.4118, pruned_loss=0.2927, over 7136.00 frames.], tot_loss[loss=0.228, simple_loss=0.3669, pruned_loss=2.263, over 1422366.58 frames.], batch size: 20, lr: 2.75e-03
+2022-05-13 20:23:28,348 INFO [train.py:812] (7/8) Epoch 1, batch 3300, loss[loss=0.2107, simple_loss=0.3746, pruned_loss=0.2343, over 7373.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3666, pruned_loss=1.819, over 1417928.87 frames.], batch size: 23, lr: 2.74e-03
+2022-05-13 20:24:25,743 INFO [train.py:812] (7/8) Epoch 1, batch 3350, loss[loss=0.2144, simple_loss=0.3796, pruned_loss=0.2455, over 7298.00 frames.], tot_loss[loss=0.2183, simple_loss=0.3652, pruned_loss=1.457, over 1422523.82 frames.], batch size: 24, lr: 2.73e-03
+2022-05-13 20:25:24,236 INFO [train.py:812] (7/8) Epoch 1, batch 3400, loss[loss=0.1778, simple_loss=0.3201, pruned_loss=0.1772, over 7255.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3641, pruned_loss=1.178, over 1423700.37 frames.], batch size: 19, lr: 2.73e-03
+2022-05-13 20:26:22,149 INFO [train.py:812] (7/8) Epoch 1, batch 3450, loss[loss=0.2136, simple_loss=0.3846, pruned_loss=0.2131, over 7290.00 frames.], tot_loss[loss=0.2112, simple_loss=0.3636, pruned_loss=0.9597, over 1424174.57 frames.], batch size: 25, lr: 2.72e-03
+2022-05-13 20:27:20,160 INFO [train.py:812] (7/8) Epoch 1, batch 3500, loss[loss=0.209, simple_loss=0.3784, pruned_loss=0.1977, over 7160.00 frames.], tot_loss[loss=0.2077, simple_loss=0.3617, pruned_loss=0.7878, over 1421740.46 frames.], batch size: 26, lr: 2.72e-03
+2022-05-13 20:28:19,225 INFO [train.py:812] (7/8) Epoch 1, batch 3550, loss[loss=0.2017, simple_loss=0.3675, pruned_loss=0.179, over 7237.00 frames.], tot_loss[loss=0.2041, simple_loss=0.3587, pruned_loss=0.6511, over 1423005.20 frames.], batch size: 21, lr: 2.71e-03
+2022-05-13 20:29:18,114 INFO [train.py:812] (7/8) Epoch 1, batch 3600, loss[loss=0.1869, simple_loss=0.3376, pruned_loss=0.1812, over 6992.00 frames.], tot_loss[loss=0.2012, simple_loss=0.3564, pruned_loss=0.545, over 1421569.82 frames.], batch size: 16, lr: 2.70e-03
+2022-05-13 20:30:25,548 INFO [train.py:812] (7/8) Epoch 1, batch 3650, loss[loss=0.1892, simple_loss=0.3437, pruned_loss=0.1738, over 7228.00 frames.], tot_loss[loss=0.1983, simple_loss=0.3536, pruned_loss=0.4596, over 1421649.83 frames.], batch size: 21, lr: 2.70e-03
+2022-05-13 20:32:10,023 INFO [train.py:812] (7/8) Epoch 1, batch 3700, loss[loss=0.203, simple_loss=0.3708, pruned_loss=0.1758, over 6793.00 frames.], tot_loss[loss=0.1967, simple_loss=0.3526, pruned_loss=0.3938, over 1427061.89 frames.], batch size: 31, lr: 2.69e-03
+2022-05-13 20:33:27,123 INFO [train.py:812] (7/8) Epoch 1, batch 3750, loss[loss=0.1955, simple_loss=0.354, pruned_loss=0.1848, over 7271.00 frames.], tot_loss[loss=0.195, simple_loss=0.351, pruned_loss=0.3432, over 1419788.77 frames.], batch size: 18, lr: 2.68e-03
+2022-05-13 20:34:26,675 INFO [train.py:812] (7/8) Epoch 1, batch 3800, loss[loss=0.1748, simple_loss=0.3208, pruned_loss=0.1439, over 7130.00 frames.], tot_loss[loss=0.1935, simple_loss=0.3499, pruned_loss=0.3015, over 1419538.54 frames.], batch size: 17, lr: 2.68e-03
+2022-05-13 20:35:25,760 INFO [train.py:812] (7/8) Epoch 1, batch 3850, loss[loss=0.1717, simple_loss=0.3179, pruned_loss=0.128, over 7145.00 frames.], tot_loss[loss=0.1922, simple_loss=0.3487, pruned_loss=0.2683, over 1424953.07 frames.], batch size: 17, lr: 2.67e-03
+2022-05-13 20:36:24,059 INFO [train.py:812] (7/8) Epoch 1, batch 3900, loss[loss=0.1786, simple_loss=0.3279, pruned_loss=0.1462, over 6763.00 frames.], tot_loss[loss=0.1917, simple_loss=0.3487, pruned_loss=0.2435, over 1420102.65 frames.], batch size: 15, lr: 2.66e-03
+2022-05-13 20:37:21,139 INFO [train.py:812] (7/8) Epoch 1, batch 3950, loss[loss=0.1591, simple_loss=0.2973, pruned_loss=0.1047, over 7283.00 frames.], tot_loss[loss=0.1904, simple_loss=0.3472, pruned_loss=0.2223, over 1417883.50 frames.], batch size: 16, lr: 2.66e-03
+2022-05-13 20:38:27,975 INFO [train.py:812] (7/8) Epoch 1, batch 4000, loss[loss=0.2111, simple_loss=0.3879, pruned_loss=0.1715, over 7322.00 frames.], tot_loss[loss=0.1901, simple_loss=0.3474, pruned_loss=0.2065, over 1420144.81 frames.], batch size: 21, lr: 2.65e-03
+2022-05-13 20:39:26,743 INFO [train.py:812] (7/8) Epoch 1, batch 4050, loss[loss=0.1991, simple_loss=0.3681, pruned_loss=0.1507, over 7088.00 frames.], tot_loss[loss=0.1889, simple_loss=0.3459, pruned_loss=0.1924, over 1420986.61 frames.], batch size: 28, lr: 2.64e-03
+2022-05-13 20:40:25,278 INFO [train.py:812] (7/8) Epoch 1, batch 4100, loss[loss=0.1856, simple_loss=0.3417, pruned_loss=0.1473, over 7255.00 frames.], tot_loss[loss=0.1879, simple_loss=0.3445, pruned_loss=0.1821, over 1420838.97 frames.], batch size: 19, lr: 2.64e-03
+2022-05-13 20:41:23,952 INFO [train.py:812] (7/8) Epoch 1, batch 4150, loss[loss=0.1722, simple_loss=0.3187, pruned_loss=0.1285, over 7067.00 frames.], tot_loss[loss=0.1878, simple_loss=0.3447, pruned_loss=0.1739, over 1425556.72 frames.], batch size: 18, lr: 2.63e-03
+2022-05-13 20:42:23,009 INFO [train.py:812] (7/8) Epoch 1, batch 4200, loss[loss=0.1913, simple_loss=0.3517, pruned_loss=0.1548, over 7202.00 frames.], tot_loss[loss=0.1876, simple_loss=0.3448, pruned_loss=0.167, over 1424509.60 frames.], batch size: 22, lr: 2.63e-03
+2022-05-13 20:43:21,457 INFO [train.py:812] (7/8) Epoch 1, batch 4250, loss[loss=0.1771, simple_loss=0.3301, pruned_loss=0.1209, over 7432.00 frames.], tot_loss[loss=0.1877, simple_loss=0.3453, pruned_loss=0.1625, over 1423321.73 frames.], batch size: 20, lr: 2.62e-03
+2022-05-13 20:44:20,474 INFO [train.py:812] (7/8) Epoch 1, batch 4300, loss[loss=0.1921, simple_loss=0.3546, pruned_loss=0.1479, over 7065.00 frames.], tot_loss[loss=0.1878, simple_loss=0.3458, pruned_loss=0.1587, over 1422956.20 frames.], batch size: 28, lr: 2.61e-03
+2022-05-13 20:45:18,968 INFO [train.py:812] (7/8) Epoch 1, batch 4350, loss[loss=0.2037, simple_loss=0.3769, pruned_loss=0.1524, over 7435.00 frames.], tot_loss[loss=0.1874, simple_loss=0.3453, pruned_loss=0.1544, over 1426595.26 frames.], batch size: 20, lr: 2.61e-03
+2022-05-13 20:46:18,364 INFO [train.py:812] (7/8) Epoch 1, batch 4400, loss[loss=0.1703, simple_loss=0.3172, pruned_loss=0.1173, over 7267.00 frames.], tot_loss[loss=0.1879, simple_loss=0.3464, pruned_loss=0.1525, over 1424121.99 frames.], batch size: 18, lr: 2.60e-03
+2022-05-13 20:47:17,300 INFO [train.py:812] (7/8) Epoch 1, batch 4450, loss[loss=0.1715, simple_loss=0.3195, pruned_loss=0.117, over 7435.00 frames.], tot_loss[loss=0.1885, simple_loss=0.3477, pruned_loss=0.1512, over 1423293.09 frames.], batch size: 20, lr: 2.59e-03
+2022-05-13 20:48:16,748 INFO [train.py:812] (7/8) Epoch 1, batch 4500, loss[loss=0.1954, simple_loss=0.3606, pruned_loss=0.1514, over 6391.00 frames.], tot_loss[loss=0.1888, simple_loss=0.3482, pruned_loss=0.1498, over 1413621.79 frames.], batch size: 38, lr: 2.59e-03
+2022-05-13 20:49:13,816 INFO [train.py:812] (7/8) Epoch 1, batch 4550, loss[loss=0.1998, simple_loss=0.3658, pruned_loss=0.1689, over 4748.00 frames.], tot_loss[loss=0.1893, simple_loss=0.3492, pruned_loss=0.1494, over 1393311.82 frames.], batch size: 52, lr: 2.58e-03
+2022-05-13 20:50:25,962 INFO [train.py:812] (7/8) Epoch 2, batch 0, loss[loss=0.2081, simple_loss=0.3804, pruned_loss=0.179, over 7149.00 frames.], tot_loss[loss=0.2081, simple_loss=0.3804, pruned_loss=0.179, over 7149.00 frames.], batch size: 26, lr: 2.56e-03
+2022-05-13 20:51:25,858 INFO [train.py:812] (7/8) Epoch 2, batch 50, loss[loss=0.1803, simple_loss=0.335, pruned_loss=0.1281, over 7224.00 frames.], tot_loss[loss=0.1836, simple_loss=0.3395, pruned_loss=0.1383, over 311646.10 frames.], batch size: 20, lr: 2.55e-03
+2022-05-13 20:52:24,934 INFO [train.py:812] (7/8) Epoch 2, batch 100, loss[loss=0.1538, simple_loss=0.2889, pruned_loss=0.09381, over 7430.00 frames.], tot_loss[loss=0.1827, simple_loss=0.3382, pruned_loss=0.1358, over 560206.11 frames.], batch size: 20, lr: 2.54e-03
+2022-05-13 20:53:23,918 INFO [train.py:812] (7/8) Epoch 2, batch 150, loss[loss=0.1656, simple_loss=0.3121, pruned_loss=0.0952, over 7339.00 frames.], tot_loss[loss=0.183, simple_loss=0.3389, pruned_loss=0.1349, over 751525.52 frames.], batch size: 20, lr: 2.54e-03
+2022-05-13 20:54:21,321 INFO [train.py:812] (7/8) Epoch 2, batch 200, loss[loss=0.1564, simple_loss=0.2941, pruned_loss=0.09333, over 7162.00 frames.], tot_loss[loss=0.1824, simple_loss=0.3382, pruned_loss=0.1331, over 900713.92 frames.], batch size: 19, lr: 2.53e-03
+2022-05-13 20:55:19,849 INFO [train.py:812] (7/8) Epoch 2, batch 250, loss[loss=0.2009, simple_loss=0.3696, pruned_loss=0.1606, over 7377.00 frames.], tot_loss[loss=0.1822, simple_loss=0.3379, pruned_loss=0.1327, over 1015852.27 frames.], batch size: 23, lr: 2.53e-03
+2022-05-13 20:56:18,142 INFO [train.py:812] (7/8) Epoch 2, batch 300, loss[loss=0.1673, simple_loss=0.3097, pruned_loss=0.1244, over 7257.00 frames.], tot_loss[loss=0.1821, simple_loss=0.3379, pruned_loss=0.1318, over 1104215.67 frames.], batch size: 19, lr: 2.52e-03
+2022-05-13 20:57:16,240 INFO [train.py:812] (7/8) Epoch 2, batch 350, loss[loss=0.1622, simple_loss=0.3051, pruned_loss=0.09621, over 7211.00 frames.], tot_loss[loss=0.1818, simple_loss=0.3374, pruned_loss=0.1315, over 1172607.84 frames.], batch size: 21, lr: 2.51e-03
+2022-05-13 20:58:14,766 INFO [train.py:812] (7/8) Epoch 2, batch 400, loss[loss=0.2162, simple_loss=0.3987, pruned_loss=0.1685, over 7134.00 frames.], tot_loss[loss=0.1827, simple_loss=0.3388, pruned_loss=0.1329, over 1229396.74 frames.], batch size: 20, lr: 2.51e-03
+2022-05-13 20:59:13,933 INFO [train.py:812] (7/8) Epoch 2, batch 450, loss[loss=0.1779, simple_loss=0.3315, pruned_loss=0.1221, over 7153.00 frames.], tot_loss[loss=0.1829, simple_loss=0.3393, pruned_loss=0.1324, over 1274708.61 frames.], batch size: 19, lr: 2.50e-03
+2022-05-13 21:00:12,354 INFO [train.py:812] (7/8) Epoch 2, batch 500, loss[loss=0.1679, simple_loss=0.3141, pruned_loss=0.1087, over 7165.00 frames.], tot_loss[loss=0.182, simple_loss=0.3378, pruned_loss=0.1307, over 1306705.50 frames.], batch size: 18, lr: 2.49e-03
+2022-05-13 21:01:12,124 INFO [train.py:812] (7/8) Epoch 2, batch 550, loss[loss=0.1768, simple_loss=0.3281, pruned_loss=0.1279, over 7349.00 frames.], tot_loss[loss=0.1812, simple_loss=0.3364, pruned_loss=0.1299, over 1332244.17 frames.], batch size: 19, lr: 2.49e-03
+2022-05-13 21:02:10,007 INFO [train.py:812] (7/8) Epoch 2, batch 600, loss[loss=0.1678, simple_loss=0.3143, pruned_loss=0.106, over 7383.00 frames.], tot_loss[loss=0.1815, simple_loss=0.337, pruned_loss=0.1297, over 1354373.08 frames.], batch size: 23, lr: 2.48e-03
+2022-05-13 21:03:09,014 INFO [train.py:812] (7/8) Epoch 2, batch 650, loss[loss=0.1623, simple_loss=0.304, pruned_loss=0.1032, over 7264.00 frames.], tot_loss[loss=0.1815, simple_loss=0.3371, pruned_loss=0.1296, over 1368304.23 frames.], batch size: 18, lr: 2.48e-03
+2022-05-13 21:04:08,349 INFO [train.py:812] (7/8) Epoch 2, batch 700, loss[loss=0.2088, simple_loss=0.3788, pruned_loss=0.1943, over 4687.00 frames.], tot_loss[loss=0.1806, simple_loss=0.3355, pruned_loss=0.1287, over 1380317.03 frames.], batch size: 52, lr: 2.47e-03
+2022-05-13 21:05:07,248 INFO [train.py:812] (7/8) Epoch 2, batch 750, loss[loss=0.1632, simple_loss=0.3063, pruned_loss=0.1003, over 7249.00 frames.], tot_loss[loss=0.1802, simple_loss=0.3349, pruned_loss=0.1275, over 1391466.70 frames.], batch size: 19, lr: 2.46e-03
+2022-05-13 21:06:06,464 INFO [train.py:812] (7/8) Epoch 2, batch 800, loss[loss=0.1736, simple_loss=0.3223, pruned_loss=0.1247, over 7064.00 frames.], tot_loss[loss=0.1795, simple_loss=0.3338, pruned_loss=0.1261, over 1401053.14 frames.], batch size: 18, lr: 2.46e-03
+2022-05-13 21:07:06,107 INFO [train.py:812] (7/8) Epoch 2, batch 850, loss[loss=0.1617, simple_loss=0.3043, pruned_loss=0.09588, over 7330.00 frames.], tot_loss[loss=0.179, simple_loss=0.3329, pruned_loss=0.1251, over 1409137.86 frames.], batch size: 20, lr: 2.45e-03
+2022-05-13 21:08:05,142 INFO [train.py:812] (7/8) Epoch 2, batch 900, loss[loss=0.1666, simple_loss=0.3123, pruned_loss=0.1052, over 7425.00 frames.], tot_loss[loss=0.1781, simple_loss=0.3315, pruned_loss=0.1232, over 1413798.57 frames.], batch size: 20, lr: 2.45e-03
+2022-05-13 21:09:04,143 INFO [train.py:812] (7/8) Epoch 2, batch 950, loss[loss=0.195, simple_loss=0.3608, pruned_loss=0.1462, over 7250.00 frames.], tot_loss[loss=0.1784, simple_loss=0.3321, pruned_loss=0.1236, over 1414907.21 frames.], batch size: 19, lr: 2.44e-03
+2022-05-13 21:10:02,123 INFO [train.py:812] (7/8) Epoch 2, batch 1000, loss[loss=0.1786, simple_loss=0.3308, pruned_loss=0.1316, over 6687.00 frames.], tot_loss[loss=0.1778, simple_loss=0.3311, pruned_loss=0.1221, over 1416461.46 frames.], batch size: 31, lr: 2.43e-03
+2022-05-13 21:11:00,278 INFO [train.py:812] (7/8) Epoch 2, batch 1050, loss[loss=0.1898, simple_loss=0.3527, pruned_loss=0.1349, over 7424.00 frames.], tot_loss[loss=0.1779, simple_loss=0.3314, pruned_loss=0.1225, over 1418497.38 frames.], batch size: 20, lr: 2.43e-03
+2022-05-13 21:11:59,267 INFO [train.py:812] (7/8) Epoch 2, batch 1100, loss[loss=0.1676, simple_loss=0.3121, pruned_loss=0.115, over 7176.00 frames.], tot_loss[loss=0.1782, simple_loss=0.3319, pruned_loss=0.1226, over 1420144.17 frames.], batch size: 18, lr: 2.42e-03
+2022-05-13 21:12:57,585 INFO [train.py:812] (7/8) Epoch 2, batch 1150, loss[loss=0.1686, simple_loss=0.3159, pruned_loss=0.1064, over 7239.00 frames.], tot_loss[loss=0.1774, simple_loss=0.3305, pruned_loss=0.1218, over 1424211.15 frames.], batch size: 20, lr: 2.41e-03
+2022-05-13 21:13:56,188 INFO [train.py:812] (7/8) Epoch 2, batch 1200, loss[loss=0.1687, simple_loss=0.3188, pruned_loss=0.09295, over 7034.00 frames.], tot_loss[loss=0.1767, simple_loss=0.3291, pruned_loss=0.1209, over 1423828.89 frames.], batch size: 28, lr: 2.41e-03
+2022-05-13 21:14:54,796 INFO [train.py:812] (7/8) Epoch 2, batch 1250, loss[loss=0.1527, simple_loss=0.2869, pruned_loss=0.09229, over 7289.00 frames.], tot_loss[loss=0.1769, simple_loss=0.3295, pruned_loss=0.121, over 1424488.74 frames.], batch size: 18, lr: 2.40e-03
+2022-05-13 21:15:53,371 INFO [train.py:812] (7/8) Epoch 2, batch 1300, loss[loss=0.1723, simple_loss=0.3221, pruned_loss=0.1122, over 7226.00 frames.], tot_loss[loss=0.1771, simple_loss=0.33, pruned_loss=0.1211, over 1417624.03 frames.], batch size: 21, lr: 2.40e-03
+2022-05-13 21:16:52,378 INFO [train.py:812] (7/8) Epoch 2, batch 1350, loss[loss=0.1719, simple_loss=0.318, pruned_loss=0.1293, over 7275.00 frames.], tot_loss[loss=0.1768, simple_loss=0.3295, pruned_loss=0.121, over 1421165.45 frames.], batch size: 17, lr: 2.39e-03
+2022-05-13 21:17:49,954 INFO [train.py:812] (7/8) Epoch 2, batch 1400, loss[loss=0.1848, simple_loss=0.3453, pruned_loss=0.1211, over 7221.00 frames.], tot_loss[loss=0.1766, simple_loss=0.3292, pruned_loss=0.1201, over 1419575.68 frames.], batch size: 21, lr: 2.39e-03
+2022-05-13 21:18:49,279 INFO [train.py:812] (7/8) Epoch 2, batch 1450, loss[loss=0.3009, simple_loss=0.3437, pruned_loss=0.129, over 7135.00 frames.], tot_loss[loss=0.1995, simple_loss=0.3308, pruned_loss=0.1226, over 1423473.60 frames.], batch size: 26, lr: 2.38e-03
+2022-05-13 21:19:47,694 INFO [train.py:812] (7/8) Epoch 2, batch 1500, loss[loss=0.2523, simple_loss=0.3081, pruned_loss=0.09827, over 6524.00 frames.], tot_loss[loss=0.2217, simple_loss=0.333, pruned_loss=0.1241, over 1424506.53 frames.], batch size: 38, lr: 2.37e-03
+2022-05-13 21:20:45,913 INFO [train.py:812] (7/8) Epoch 2, batch 1550, loss[loss=0.3226, simple_loss=0.3505, pruned_loss=0.1474, over 7424.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3351, pruned_loss=0.1246, over 1426912.81 frames.], batch size: 20, lr: 2.37e-03
+2022-05-13 21:21:43,127 INFO [train.py:812] (7/8) Epoch 2, batch 1600, loss[loss=0.2674, simple_loss=0.3219, pruned_loss=0.1064, over 7166.00 frames.], tot_loss[loss=0.2475, simple_loss=0.3338, pruned_loss=0.1223, over 1426069.46 frames.], batch size: 18, lr: 2.36e-03
+2022-05-13 21:22:41,937 INFO [train.py:812] (7/8) Epoch 2, batch 1650, loss[loss=0.2356, simple_loss=0.3007, pruned_loss=0.08526, over 7443.00 frames.], tot_loss[loss=0.2537, simple_loss=0.3322, pruned_loss=0.12, over 1425747.92 frames.], batch size: 20, lr: 2.36e-03
+2022-05-13 21:23:40,016 INFO [train.py:812] (7/8) Epoch 2, batch 1700, loss[loss=0.3177, simple_loss=0.3649, pruned_loss=0.1353, over 7404.00 frames.], tot_loss[loss=0.2615, simple_loss=0.3332, pruned_loss=0.1202, over 1423363.70 frames.], batch size: 21, lr: 2.35e-03
+2022-05-13 21:24:38,991 INFO [train.py:812] (7/8) Epoch 2, batch 1750, loss[loss=0.3009, simple_loss=0.3205, pruned_loss=0.1406, over 7280.00 frames.], tot_loss[loss=0.2676, simple_loss=0.3343, pruned_loss=0.1201, over 1422721.00 frames.], batch size: 18, lr: 2.34e-03
+2022-05-13 21:25:38,322 INFO [train.py:812] (7/8) Epoch 2, batch 1800, loss[loss=0.2669, simple_loss=0.3125, pruned_loss=0.1107, over 7348.00 frames.], tot_loss[loss=0.2705, simple_loss=0.3338, pruned_loss=0.1189, over 1424758.71 frames.], batch size: 19, lr: 2.34e-03
+2022-05-13 21:26:37,504 INFO [train.py:812] (7/8) Epoch 2, batch 1850, loss[loss=0.2664, simple_loss=0.322, pruned_loss=0.1054, over 7329.00 frames.], tot_loss[loss=0.2712, simple_loss=0.3322, pruned_loss=0.117, over 1424731.24 frames.], batch size: 20, lr: 2.33e-03
+2022-05-13 21:27:35,713 INFO [train.py:812] (7/8) Epoch 2, batch 1900, loss[loss=0.2414, simple_loss=0.2906, pruned_loss=0.09611, over 6996.00 frames.], tot_loss[loss=0.2733, simple_loss=0.3329, pruned_loss=0.1162, over 1428342.20 frames.], batch size: 16, lr: 2.33e-03
+2022-05-13 21:28:33,686 INFO [train.py:812] (7/8) Epoch 2, batch 1950, loss[loss=0.3043, simple_loss=0.342, pruned_loss=0.1332, over 7277.00 frames.], tot_loss[loss=0.2744, simple_loss=0.3328, pruned_loss=0.1152, over 1428725.53 frames.], batch size: 18, lr: 2.32e-03
+2022-05-13 21:29:31,802 INFO [train.py:812] (7/8) Epoch 2, batch 2000, loss[loss=0.2861, simple_loss=0.3529, pruned_loss=0.1097, over 7111.00 frames.], tot_loss[loss=0.2772, simple_loss=0.3344, pruned_loss=0.1156, over 1422957.06 frames.], batch size: 21, lr: 2.32e-03
+2022-05-13 21:30:31,573 INFO [train.py:812] (7/8) Epoch 2, batch 2050, loss[loss=0.3282, simple_loss=0.3765, pruned_loss=0.14, over 7063.00 frames.], tot_loss[loss=0.2776, simple_loss=0.3338, pruned_loss=0.1151, over 1424238.31 frames.], batch size: 28, lr: 2.31e-03
+2022-05-13 21:31:31,057 INFO [train.py:812] (7/8) Epoch 2, batch 2100, loss[loss=0.231, simple_loss=0.282, pruned_loss=0.09, over 7427.00 frames.], tot_loss[loss=0.2776, simple_loss=0.333, pruned_loss=0.1145, over 1424690.25 frames.], batch size: 18, lr: 2.31e-03
+2022-05-13 21:32:30,591 INFO [train.py:812] (7/8) Epoch 2, batch 2150, loss[loss=0.2623, simple_loss=0.3315, pruned_loss=0.09651, over 7409.00 frames.], tot_loss[loss=0.2773, simple_loss=0.3326, pruned_loss=0.1137, over 1422334.45 frames.], batch size: 21, lr: 2.30e-03
+2022-05-13 21:33:29,472 INFO [train.py:812] (7/8) Epoch 2, batch 2200, loss[loss=0.2982, simple_loss=0.3513, pruned_loss=0.1225, over 7112.00 frames.], tot_loss[loss=0.276, simple_loss=0.3306, pruned_loss=0.1128, over 1421431.34 frames.], batch size: 21, lr: 2.29e-03
+2022-05-13 21:34:29,322 INFO [train.py:812] (7/8) Epoch 2, batch 2250, loss[loss=0.2715, simple_loss=0.3293, pruned_loss=0.1068, over 7225.00 frames.], tot_loss[loss=0.2732, simple_loss=0.3287, pruned_loss=0.1104, over 1422841.73 frames.], batch size: 21, lr: 2.29e-03
+2022-05-13 21:35:27,802 INFO [train.py:812] (7/8) Epoch 2, batch 2300, loss[loss=0.319, simple_loss=0.3713, pruned_loss=0.1334, over 7213.00 frames.], tot_loss[loss=0.2744, simple_loss=0.3299, pruned_loss=0.1107, over 1424133.39 frames.], batch size: 22, lr: 2.28e-03
+2022-05-13 21:36:26,845 INFO [train.py:812] (7/8) Epoch 2, batch 2350, loss[loss=0.2922, simple_loss=0.3444, pruned_loss=0.12, over 7233.00 frames.], tot_loss[loss=0.2756, simple_loss=0.331, pruned_loss=0.111, over 1422327.55 frames.], batch size: 20, lr: 2.28e-03
+2022-05-13 21:37:24,995 INFO [train.py:812] (7/8) Epoch 2, batch 2400, loss[loss=0.3171, simple_loss=0.3682, pruned_loss=0.133, over 7315.00 frames.], tot_loss[loss=0.2755, simple_loss=0.3312, pruned_loss=0.1106, over 1422699.02 frames.], batch size: 21, lr: 2.27e-03
+2022-05-13 21:38:23,875 INFO [train.py:812] (7/8) Epoch 2, batch 2450, loss[loss=0.2608, simple_loss=0.3271, pruned_loss=0.09721, over 7324.00 frames.], tot_loss[loss=0.2748, simple_loss=0.3312, pruned_loss=0.1098, over 1425707.07 frames.], batch size: 21, lr: 2.27e-03
+2022-05-13 21:39:23,294 INFO [train.py:812] (7/8) Epoch 2, batch 2500, loss[loss=0.3409, simple_loss=0.3789, pruned_loss=0.1514, over 7151.00 frames.], tot_loss[loss=0.2746, simple_loss=0.3311, pruned_loss=0.1096, over 1426246.30 frames.], batch size: 26, lr: 2.26e-03
+2022-05-13 21:40:21,949 INFO [train.py:812] (7/8) Epoch 2, batch 2550, loss[loss=0.2462, simple_loss=0.2978, pruned_loss=0.0973, over 6994.00 frames.], tot_loss[loss=0.2754, simple_loss=0.3313, pruned_loss=0.1101, over 1426673.07 frames.], batch size: 16, lr: 2.26e-03
+2022-05-13 21:41:21,084 INFO [train.py:812] (7/8) Epoch 2, batch 2600, loss[loss=0.2719, simple_loss=0.3332, pruned_loss=0.1053, over 7193.00 frames.], tot_loss[loss=0.2723, simple_loss=0.3293, pruned_loss=0.108, over 1428526.64 frames.], batch size: 26, lr: 2.25e-03
+2022-05-13 21:42:20,642 INFO [train.py:812] (7/8) Epoch 2, batch 2650, loss[loss=0.3546, simple_loss=0.3904, pruned_loss=0.1594, over 6445.00 frames.], tot_loss[loss=0.2735, simple_loss=0.3299, pruned_loss=0.1087, over 1426206.81 frames.], batch size: 38, lr: 2.25e-03
+2022-05-13 21:43:18,333 INFO [train.py:812] (7/8) Epoch 2, batch 2700, loss[loss=0.3358, simple_loss=0.3733, pruned_loss=0.1492, over 6863.00 frames.], tot_loss[loss=0.2717, simple_loss=0.3289, pruned_loss=0.1074, over 1425935.47 frames.], batch size: 31, lr: 2.24e-03
+2022-05-13 21:44:17,981 INFO [train.py:812] (7/8) Epoch 2, batch 2750, loss[loss=0.319, simple_loss=0.3543, pruned_loss=0.1418, over 7290.00 frames.], tot_loss[loss=0.2719, simple_loss=0.3283, pruned_loss=0.1079, over 1422922.88 frames.], batch size: 24, lr: 2.24e-03
+2022-05-13 21:45:15,709 INFO [train.py:812] (7/8) Epoch 2, batch 2800, loss[loss=0.2519, simple_loss=0.321, pruned_loss=0.09136, over 7217.00 frames.], tot_loss[loss=0.2695, simple_loss=0.3271, pruned_loss=0.1061, over 1425806.56 frames.], batch size: 23, lr: 2.23e-03
+2022-05-13 21:46:14,866 INFO [train.py:812] (7/8) Epoch 2, batch 2850, loss[loss=0.2987, simple_loss=0.3629, pruned_loss=0.1173, over 7297.00 frames.], tot_loss[loss=0.2703, simple_loss=0.3275, pruned_loss=0.1067, over 1425353.87 frames.], batch size: 24, lr: 2.23e-03
+2022-05-13 21:47:13,489 INFO [train.py:812] (7/8) Epoch 2, batch 2900, loss[loss=0.2555, simple_loss=0.3205, pruned_loss=0.09522, over 7236.00 frames.], tot_loss[loss=0.2711, simple_loss=0.3282, pruned_loss=0.107, over 1420060.45 frames.], batch size: 20, lr: 2.22e-03
+2022-05-13 21:48:11,768 INFO [train.py:812] (7/8) Epoch 2, batch 2950, loss[loss=0.2647, simple_loss=0.3396, pruned_loss=0.09485, over 7229.00 frames.], tot_loss[loss=0.2707, simple_loss=0.3284, pruned_loss=0.1065, over 1421626.73 frames.], batch size: 20, lr: 2.22e-03
+2022-05-13 21:49:10,857 INFO [train.py:812] (7/8) Epoch 2, batch 3000, loss[loss=0.1828, simple_loss=0.2546, pruned_loss=0.05551, over 7276.00 frames.], tot_loss[loss=0.2684, simple_loss=0.327, pruned_loss=0.1049, over 1425848.82 frames.], batch size: 17, lr: 2.21e-03
+2022-05-13 21:49:10,859 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-13 21:49:18,580 INFO [train.py:841] (7/8) Epoch 2, validation: loss=0.2016, simple_loss=0.2977, pruned_loss=0.0527, over 698248.00 frames.
+2022-05-13 21:50:17,437 INFO [train.py:812] (7/8) Epoch 2, batch 3050, loss[loss=0.2523, simple_loss=0.3198, pruned_loss=0.09245, over 7287.00 frames.], tot_loss[loss=0.2685, simple_loss=0.3271, pruned_loss=0.1049, over 1422682.45 frames.], batch size: 18, lr: 2.20e-03
+2022-05-13 21:51:15,142 INFO [train.py:812] (7/8) Epoch 2, batch 3100, loss[loss=0.3394, simple_loss=0.3675, pruned_loss=0.1557, over 5090.00 frames.], tot_loss[loss=0.2698, simple_loss=0.3285, pruned_loss=0.1055, over 1421507.72 frames.], batch size: 54, lr: 2.20e-03
+2022-05-13 21:52:13,960 INFO [train.py:812] (7/8) Epoch 2, batch 3150, loss[loss=0.2354, simple_loss=0.2963, pruned_loss=0.08723, over 6816.00 frames.], tot_loss[loss=0.2701, simple_loss=0.3292, pruned_loss=0.1055, over 1423417.30 frames.], batch size: 15, lr: 2.19e-03
+2022-05-13 21:53:13,059 INFO [train.py:812] (7/8) Epoch 2, batch 3200, loss[loss=0.314, simple_loss=0.3628, pruned_loss=0.1326, over 5438.00 frames.], tot_loss[loss=0.2726, simple_loss=0.3315, pruned_loss=0.1068, over 1413788.76 frames.], batch size: 52, lr: 2.19e-03
+2022-05-13 21:54:12,631 INFO [train.py:812] (7/8) Epoch 2, batch 3250, loss[loss=0.2602, simple_loss=0.3273, pruned_loss=0.09658, over 7210.00 frames.], tot_loss[loss=0.2721, simple_loss=0.3309, pruned_loss=0.1067, over 1415972.27 frames.], batch size: 23, lr: 2.18e-03
+2022-05-13 21:55:12,249 INFO [train.py:812] (7/8) Epoch 2, batch 3300, loss[loss=0.2496, simple_loss=0.3271, pruned_loss=0.08604, over 7197.00 frames.], tot_loss[loss=0.2715, simple_loss=0.3304, pruned_loss=0.1063, over 1421105.55 frames.], batch size: 22, lr: 2.18e-03
+2022-05-13 21:56:12,003 INFO [train.py:812] (7/8) Epoch 2, batch 3350, loss[loss=0.2904, simple_loss=0.3539, pruned_loss=0.1135, over 7129.00 frames.], tot_loss[loss=0.2712, simple_loss=0.3308, pruned_loss=0.1058, over 1424134.27 frames.], batch size: 26, lr: 2.18e-03
+2022-05-13 21:57:11,208 INFO [train.py:812] (7/8) Epoch 2, batch 3400, loss[loss=0.2191, simple_loss=0.292, pruned_loss=0.07306, over 7120.00 frames.], tot_loss[loss=0.2695, simple_loss=0.3291, pruned_loss=0.105, over 1425669.79 frames.], batch size: 17, lr: 2.17e-03
+2022-05-13 21:58:14,504 INFO [train.py:812] (7/8) Epoch 2, batch 3450, loss[loss=0.3223, simple_loss=0.3784, pruned_loss=0.1331, over 7301.00 frames.], tot_loss[loss=0.2681, simple_loss=0.3285, pruned_loss=0.1039, over 1427928.25 frames.], batch size: 24, lr: 2.17e-03
+2022-05-13 21:59:13,401 INFO [train.py:812] (7/8) Epoch 2, batch 3500, loss[loss=0.2997, simple_loss=0.3473, pruned_loss=0.1261, over 6455.00 frames.], tot_loss[loss=0.2671, simple_loss=0.3273, pruned_loss=0.1035, over 1424477.60 frames.], batch size: 38, lr: 2.16e-03
+2022-05-13 22:00:12,714 INFO [train.py:812] (7/8) Epoch 2, batch 3550, loss[loss=0.3081, simple_loss=0.3671, pruned_loss=0.1246, over 7297.00 frames.], tot_loss[loss=0.2668, simple_loss=0.3278, pruned_loss=0.1029, over 1424533.64 frames.], batch size: 25, lr: 2.16e-03
+2022-05-13 22:01:11,607 INFO [train.py:812] (7/8) Epoch 2, batch 3600, loss[loss=0.2957, simple_loss=0.3617, pruned_loss=0.1149, over 7236.00 frames.], tot_loss[loss=0.2672, simple_loss=0.3285, pruned_loss=0.103, over 1425748.11 frames.], batch size: 20, lr: 2.15e-03
+2022-05-13 22:02:11,457 INFO [train.py:812] (7/8) Epoch 2, batch 3650, loss[loss=0.28, simple_loss=0.327, pruned_loss=0.1165, over 7233.00 frames.], tot_loss[loss=0.266, simple_loss=0.3275, pruned_loss=0.1022, over 1427720.31 frames.], batch size: 16, lr: 2.15e-03
+2022-05-13 22:03:10,465 INFO [train.py:812] (7/8) Epoch 2, batch 3700, loss[loss=0.2415, simple_loss=0.3162, pruned_loss=0.08343, over 7166.00 frames.], tot_loss[loss=0.2656, simple_loss=0.3271, pruned_loss=0.102, over 1429004.98 frames.], batch size: 19, lr: 2.14e-03
+2022-05-13 22:04:09,818 INFO [train.py:812] (7/8) Epoch 2, batch 3750, loss[loss=0.2995, simple_loss=0.3508, pruned_loss=0.1241, over 7303.00 frames.], tot_loss[loss=0.2667, simple_loss=0.3277, pruned_loss=0.1029, over 1429335.78 frames.], batch size: 24, lr: 2.14e-03
+2022-05-13 22:05:09,277 INFO [train.py:812] (7/8) Epoch 2, batch 3800, loss[loss=0.2348, simple_loss=0.2901, pruned_loss=0.08973, over 7243.00 frames.], tot_loss[loss=0.2665, simple_loss=0.3273, pruned_loss=0.1028, over 1429212.86 frames.], batch size: 16, lr: 2.13e-03
+2022-05-13 22:06:07,977 INFO [train.py:812] (7/8) Epoch 2, batch 3850, loss[loss=0.269, simple_loss=0.3404, pruned_loss=0.09878, over 7113.00 frames.], tot_loss[loss=0.2662, simple_loss=0.3276, pruned_loss=0.1025, over 1431071.89 frames.], batch size: 26, lr: 2.13e-03
+2022-05-13 22:07:06,211 INFO [train.py:812] (7/8) Epoch 2, batch 3900, loss[loss=0.2809, simple_loss=0.3544, pruned_loss=0.1037, over 7303.00 frames.], tot_loss[loss=0.2658, simple_loss=0.3271, pruned_loss=0.1023, over 1430402.73 frames.], batch size: 24, lr: 2.12e-03
+2022-05-13 22:08:05,689 INFO [train.py:812] (7/8) Epoch 2, batch 3950, loss[loss=0.2846, simple_loss=0.3458, pruned_loss=0.1117, over 7113.00 frames.], tot_loss[loss=0.2645, simple_loss=0.326, pruned_loss=0.1015, over 1428210.15 frames.], batch size: 21, lr: 2.12e-03
+2022-05-13 22:09:04,776 INFO [train.py:812] (7/8) Epoch 2, batch 4000, loss[loss=0.2374, simple_loss=0.3175, pruned_loss=0.07871, over 7205.00 frames.], tot_loss[loss=0.2628, simple_loss=0.3251, pruned_loss=0.1002, over 1428540.16 frames.], batch size: 22, lr: 2.11e-03
+2022-05-13 22:10:02,698 INFO [train.py:812] (7/8) Epoch 2, batch 4050, loss[loss=0.292, simple_loss=0.3483, pruned_loss=0.1178, over 6810.00 frames.], tot_loss[loss=0.2626, simple_loss=0.3248, pruned_loss=0.1002, over 1425972.68 frames.], batch size: 31, lr: 2.11e-03
+2022-05-13 22:11:01,227 INFO [train.py:812] (7/8) Epoch 2, batch 4100, loss[loss=0.2637, simple_loss=0.3265, pruned_loss=0.1004, over 7212.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3251, pruned_loss=0.1001, over 1421555.77 frames.], batch size: 21, lr: 2.10e-03
+2022-05-13 22:11:59,891 INFO [train.py:812] (7/8) Epoch 2, batch 4150, loss[loss=0.2711, simple_loss=0.3334, pruned_loss=0.1044, over 6805.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3252, pruned_loss=0.1001, over 1420221.28 frames.], batch size: 31, lr: 2.10e-03
+2022-05-13 22:12:58,538 INFO [train.py:812] (7/8) Epoch 2, batch 4200, loss[loss=0.2061, simple_loss=0.2712, pruned_loss=0.07049, over 7272.00 frames.], tot_loss[loss=0.262, simple_loss=0.3241, pruned_loss=0.09995, over 1418786.82 frames.], batch size: 18, lr: 2.10e-03
+2022-05-13 22:13:58,104 INFO [train.py:812] (7/8) Epoch 2, batch 4250, loss[loss=0.2085, simple_loss=0.289, pruned_loss=0.06402, over 7291.00 frames.], tot_loss[loss=0.263, simple_loss=0.325, pruned_loss=0.1005, over 1413766.52 frames.], batch size: 18, lr: 2.09e-03
+2022-05-13 22:14:56,714 INFO [train.py:812] (7/8) Epoch 2, batch 4300, loss[loss=0.2606, simple_loss=0.3139, pruned_loss=0.1037, over 7279.00 frames.], tot_loss[loss=0.2629, simple_loss=0.3249, pruned_loss=0.1005, over 1412256.75 frames.], batch size: 25, lr: 2.09e-03
+2022-05-13 22:15:55,445 INFO [train.py:812] (7/8) Epoch 2, batch 4350, loss[loss=0.2041, simple_loss=0.2727, pruned_loss=0.06776, over 7005.00 frames.], tot_loss[loss=0.2625, simple_loss=0.325, pruned_loss=0.1, over 1412861.02 frames.], batch size: 16, lr: 2.08e-03
+2022-05-13 22:16:54,226 INFO [train.py:812] (7/8) Epoch 2, batch 4400, loss[loss=0.227, simple_loss=0.3103, pruned_loss=0.07185, over 7313.00 frames.], tot_loss[loss=0.2616, simple_loss=0.3242, pruned_loss=0.09947, over 1408388.83 frames.], batch size: 21, lr: 2.08e-03
+2022-05-13 22:17:52,740 INFO [train.py:812] (7/8) Epoch 2, batch 4450, loss[loss=0.2533, simple_loss=0.322, pruned_loss=0.09233, over 6334.00 frames.], tot_loss[loss=0.2606, simple_loss=0.3237, pruned_loss=0.09875, over 1400646.85 frames.], batch size: 37, lr: 2.07e-03
+2022-05-13 22:18:50,576 INFO [train.py:812] (7/8) Epoch 2, batch 4500, loss[loss=0.3195, simple_loss=0.3564, pruned_loss=0.1413, over 6399.00 frames.], tot_loss[loss=0.2597, simple_loss=0.3223, pruned_loss=0.09856, over 1385830.92 frames.], batch size: 38, lr: 2.07e-03
+2022-05-13 22:19:49,238 INFO [train.py:812] (7/8) Epoch 2, batch 4550, loss[loss=0.3423, simple_loss=0.3589, pruned_loss=0.1629, over 4889.00 frames.], tot_loss[loss=0.2647, simple_loss=0.3259, pruned_loss=0.1017, over 1355173.69 frames.], batch size: 52, lr: 2.06e-03
+2022-05-13 22:20:58,933 INFO [train.py:812] (7/8) Epoch 3, batch 0, loss[loss=0.1937, simple_loss=0.2625, pruned_loss=0.06246, over 7295.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2625, pruned_loss=0.06246, over 7295.00 frames.], batch size: 17, lr: 2.02e-03
+2022-05-13 22:21:58,083 INFO [train.py:812] (7/8) Epoch 3, batch 50, loss[loss=0.3155, simple_loss=0.3708, pruned_loss=0.1301, over 7308.00 frames.], tot_loss[loss=0.2588, simple_loss=0.3218, pruned_loss=0.09791, over 321179.08 frames.], batch size: 25, lr: 2.02e-03
+2022-05-13 22:22:56,173 INFO [train.py:812] (7/8) Epoch 3, batch 100, loss[loss=0.2558, simple_loss=0.3103, pruned_loss=0.1006, over 7009.00 frames.], tot_loss[loss=0.257, simple_loss=0.3207, pruned_loss=0.09664, over 568659.51 frames.], batch size: 16, lr: 2.01e-03
+2022-05-13 22:23:56,111 INFO [train.py:812] (7/8) Epoch 3, batch 150, loss[loss=0.2885, simple_loss=0.3497, pruned_loss=0.1136, over 6663.00 frames.], tot_loss[loss=0.2548, simple_loss=0.3192, pruned_loss=0.09522, over 761385.70 frames.], batch size: 31, lr: 2.01e-03
+2022-05-13 22:24:53,611 INFO [train.py:812] (7/8) Epoch 3, batch 200, loss[loss=0.251, simple_loss=0.3019, pruned_loss=0.1, over 7274.00 frames.], tot_loss[loss=0.2553, simple_loss=0.3191, pruned_loss=0.09572, over 900899.79 frames.], batch size: 16, lr: 2.00e-03
+2022-05-13 22:25:53,039 INFO [train.py:812] (7/8) Epoch 3, batch 250, loss[loss=0.2398, simple_loss=0.3076, pruned_loss=0.08607, over 7361.00 frames.], tot_loss[loss=0.2567, simple_loss=0.3209, pruned_loss=0.09631, over 1011619.47 frames.], batch size: 19, lr: 2.00e-03
+2022-05-13 22:26:52,130 INFO [train.py:812] (7/8) Epoch 3, batch 300, loss[loss=0.2742, simple_loss=0.3408, pruned_loss=0.1038, over 6807.00 frames.], tot_loss[loss=0.2587, simple_loss=0.3231, pruned_loss=0.09711, over 1102071.45 frames.], batch size: 31, lr: 2.00e-03
+2022-05-13 22:27:51,996 INFO [train.py:812] (7/8) Epoch 3, batch 350, loss[loss=0.26, simple_loss=0.3346, pruned_loss=0.09264, over 7315.00 frames.], tot_loss[loss=0.257, simple_loss=0.3225, pruned_loss=0.09577, over 1172924.88 frames.], batch size: 21, lr: 1.99e-03
+2022-05-13 22:29:00,829 INFO [train.py:812] (7/8) Epoch 3, batch 400, loss[loss=0.2202, simple_loss=0.3051, pruned_loss=0.06763, over 7271.00 frames.], tot_loss[loss=0.2568, simple_loss=0.3221, pruned_loss=0.09581, over 1224252.87 frames.], batch size: 24, lr: 1.99e-03
+2022-05-13 22:29:59,488 INFO [train.py:812] (7/8) Epoch 3, batch 450, loss[loss=0.2933, simple_loss=0.3522, pruned_loss=0.1172, over 7217.00 frames.], tot_loss[loss=0.2581, simple_loss=0.3229, pruned_loss=0.09668, over 1264752.69 frames.], batch size: 22, lr: 1.98e-03
+2022-05-13 22:31:07,406 INFO [train.py:812] (7/8) Epoch 3, batch 500, loss[loss=0.218, simple_loss=0.2816, pruned_loss=0.07723, over 7016.00 frames.], tot_loss[loss=0.2571, simple_loss=0.3219, pruned_loss=0.09618, over 1302275.53 frames.], batch size: 16, lr: 1.98e-03
+2022-05-13 22:32:54,351 INFO [train.py:812] (7/8) Epoch 3, batch 550, loss[loss=0.2132, simple_loss=0.3015, pruned_loss=0.0624, over 7226.00 frames.], tot_loss[loss=0.2564, simple_loss=0.3217, pruned_loss=0.09552, over 1332402.48 frames.], batch size: 21, lr: 1.98e-03
+2022-05-13 22:34:03,119 INFO [train.py:812] (7/8) Epoch 3, batch 600, loss[loss=0.3223, simple_loss=0.3763, pruned_loss=0.1341, over 7292.00 frames.], tot_loss[loss=0.255, simple_loss=0.3206, pruned_loss=0.09469, over 1354117.83 frames.], batch size: 25, lr: 1.97e-03
+2022-05-13 22:35:02,677 INFO [train.py:812] (7/8) Epoch 3, batch 650, loss[loss=0.269, simple_loss=0.3289, pruned_loss=0.1046, over 7356.00 frames.], tot_loss[loss=0.2542, simple_loss=0.3199, pruned_loss=0.09423, over 1368307.73 frames.], batch size: 19, lr: 1.97e-03
+2022-05-13 22:36:02,074 INFO [train.py:812] (7/8) Epoch 3, batch 700, loss[loss=0.2469, simple_loss=0.315, pruned_loss=0.08937, over 7215.00 frames.], tot_loss[loss=0.2543, simple_loss=0.3203, pruned_loss=0.09416, over 1378324.89 frames.], batch size: 21, lr: 1.96e-03
+2022-05-13 22:37:01,841 INFO [train.py:812] (7/8) Epoch 3, batch 750, loss[loss=0.2808, simple_loss=0.3423, pruned_loss=0.1097, over 7204.00 frames.], tot_loss[loss=0.2551, simple_loss=0.3208, pruned_loss=0.09466, over 1391746.28 frames.], batch size: 23, lr: 1.96e-03
+2022-05-13 22:38:00,559 INFO [train.py:812] (7/8) Epoch 3, batch 800, loss[loss=0.2942, simple_loss=0.3571, pruned_loss=0.1157, over 7196.00 frames.], tot_loss[loss=0.2558, simple_loss=0.3216, pruned_loss=0.09502, over 1402657.98 frames.], batch size: 23, lr: 1.96e-03
+2022-05-13 22:38:59,727 INFO [train.py:812] (7/8) Epoch 3, batch 850, loss[loss=0.261, simple_loss=0.3381, pruned_loss=0.09194, over 7330.00 frames.], tot_loss[loss=0.2532, simple_loss=0.3195, pruned_loss=0.09349, over 1410377.31 frames.], batch size: 25, lr: 1.95e-03
+2022-05-13 22:39:58,516 INFO [train.py:812] (7/8) Epoch 3, batch 900, loss[loss=0.2419, simple_loss=0.3049, pruned_loss=0.08948, over 7059.00 frames.], tot_loss[loss=0.2538, simple_loss=0.3198, pruned_loss=0.09394, over 1412465.75 frames.], batch size: 18, lr: 1.95e-03
+2022-05-13 22:40:58,712 INFO [train.py:812] (7/8) Epoch 3, batch 950, loss[loss=0.2466, simple_loss=0.3249, pruned_loss=0.08418, over 7154.00 frames.], tot_loss[loss=0.2515, simple_loss=0.3182, pruned_loss=0.09241, over 1417508.33 frames.], batch size: 20, lr: 1.94e-03
+2022-05-13 22:41:58,354 INFO [train.py:812] (7/8) Epoch 3, batch 1000, loss[loss=0.2595, simple_loss=0.335, pruned_loss=0.092, over 6741.00 frames.], tot_loss[loss=0.2523, simple_loss=0.3188, pruned_loss=0.09293, over 1415946.32 frames.], batch size: 31, lr: 1.94e-03
+2022-05-13 22:42:57,516 INFO [train.py:812] (7/8) Epoch 3, batch 1050, loss[loss=0.215, simple_loss=0.2858, pruned_loss=0.07206, over 7288.00 frames.], tot_loss[loss=0.2529, simple_loss=0.3194, pruned_loss=0.09323, over 1415259.36 frames.], batch size: 18, lr: 1.94e-03
+2022-05-13 22:43:56,811 INFO [train.py:812] (7/8) Epoch 3, batch 1100, loss[loss=0.2291, simple_loss=0.3118, pruned_loss=0.07315, over 7212.00 frames.], tot_loss[loss=0.2532, simple_loss=0.32, pruned_loss=0.09319, over 1420054.05 frames.], batch size: 21, lr: 1.93e-03
+2022-05-13 22:44:56,360 INFO [train.py:812] (7/8) Epoch 3, batch 1150, loss[loss=0.2937, simple_loss=0.3459, pruned_loss=0.1208, over 7228.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3186, pruned_loss=0.09258, over 1420488.88 frames.], batch size: 20, lr: 1.93e-03
+2022-05-13 22:45:54,844 INFO [train.py:812] (7/8) Epoch 3, batch 1200, loss[loss=0.2239, simple_loss=0.294, pruned_loss=0.07686, over 7424.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3176, pruned_loss=0.092, over 1423387.92 frames.], batch size: 20, lr: 1.93e-03
+2022-05-13 22:46:52,772 INFO [train.py:812] (7/8) Epoch 3, batch 1250, loss[loss=0.2377, simple_loss=0.3084, pruned_loss=0.08353, over 7408.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3172, pruned_loss=0.09188, over 1424137.18 frames.], batch size: 21, lr: 1.92e-03
+2022-05-13 22:47:52,045 INFO [train.py:812] (7/8) Epoch 3, batch 1300, loss[loss=0.2106, simple_loss=0.2894, pruned_loss=0.06593, over 7323.00 frames.], tot_loss[loss=0.2495, simple_loss=0.3166, pruned_loss=0.09119, over 1425848.34 frames.], batch size: 21, lr: 1.92e-03
+2022-05-13 22:48:50,103 INFO [train.py:812] (7/8) Epoch 3, batch 1350, loss[loss=0.2486, simple_loss=0.3129, pruned_loss=0.09214, over 7433.00 frames.], tot_loss[loss=0.2508, simple_loss=0.318, pruned_loss=0.09184, over 1426034.07 frames.], batch size: 20, lr: 1.91e-03
+2022-05-13 22:49:48,142 INFO [train.py:812] (7/8) Epoch 3, batch 1400, loss[loss=0.2026, simple_loss=0.2833, pruned_loss=0.06091, over 7159.00 frames.], tot_loss[loss=0.2511, simple_loss=0.3186, pruned_loss=0.09185, over 1423666.81 frames.], batch size: 19, lr: 1.91e-03
+2022-05-13 22:50:48,096 INFO [train.py:812] (7/8) Epoch 3, batch 1450, loss[loss=0.2333, simple_loss=0.3004, pruned_loss=0.08308, over 7149.00 frames.], tot_loss[loss=0.2516, simple_loss=0.319, pruned_loss=0.09208, over 1420431.11 frames.], batch size: 17, lr: 1.91e-03
+2022-05-13 22:51:47,029 INFO [train.py:812] (7/8) Epoch 3, batch 1500, loss[loss=0.2434, simple_loss=0.3191, pruned_loss=0.08387, over 7320.00 frames.], tot_loss[loss=0.2531, simple_loss=0.3197, pruned_loss=0.09328, over 1418109.67 frames.], batch size: 21, lr: 1.90e-03
+2022-05-13 22:52:47,292 INFO [train.py:812] (7/8) Epoch 3, batch 1550, loss[loss=0.2375, simple_loss=0.3151, pruned_loss=0.07989, over 7166.00 frames.], tot_loss[loss=0.2517, simple_loss=0.3187, pruned_loss=0.09239, over 1422357.20 frames.], batch size: 19, lr: 1.90e-03
+2022-05-13 22:53:45,789 INFO [train.py:812] (7/8) Epoch 3, batch 1600, loss[loss=0.2403, simple_loss=0.3115, pruned_loss=0.08459, over 7158.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3174, pruned_loss=0.09179, over 1424107.32 frames.], batch size: 19, lr: 1.90e-03
+2022-05-13 22:54:44,651 INFO [train.py:812] (7/8) Epoch 3, batch 1650, loss[loss=0.2215, simple_loss=0.2974, pruned_loss=0.07282, over 7430.00 frames.], tot_loss[loss=0.2499, simple_loss=0.3169, pruned_loss=0.09144, over 1426783.92 frames.], batch size: 20, lr: 1.89e-03
+2022-05-13 22:55:42,319 INFO [train.py:812] (7/8) Epoch 3, batch 1700, loss[loss=0.2658, simple_loss=0.3412, pruned_loss=0.09519, over 7146.00 frames.], tot_loss[loss=0.2497, simple_loss=0.3168, pruned_loss=0.09128, over 1417347.18 frames.], batch size: 20, lr: 1.89e-03
+2022-05-13 22:56:41,887 INFO [train.py:812] (7/8) Epoch 3, batch 1750, loss[loss=0.2179, simple_loss=0.2984, pruned_loss=0.06868, over 7225.00 frames.], tot_loss[loss=0.2472, simple_loss=0.3151, pruned_loss=0.08969, over 1424343.45 frames.], batch size: 20, lr: 1.88e-03
+2022-05-13 22:57:40,310 INFO [train.py:812] (7/8) Epoch 3, batch 1800, loss[loss=0.2313, simple_loss=0.2953, pruned_loss=0.0837, over 7124.00 frames.], tot_loss[loss=0.2473, simple_loss=0.3145, pruned_loss=0.08999, over 1417218.29 frames.], batch size: 21, lr: 1.88e-03
+2022-05-13 22:58:39,783 INFO [train.py:812] (7/8) Epoch 3, batch 1850, loss[loss=0.2499, simple_loss=0.3309, pruned_loss=0.08439, over 7415.00 frames.], tot_loss[loss=0.2479, simple_loss=0.315, pruned_loss=0.09043, over 1418636.68 frames.], batch size: 21, lr: 1.88e-03
+2022-05-13 22:59:38,900 INFO [train.py:812] (7/8) Epoch 3, batch 1900, loss[loss=0.2153, simple_loss=0.288, pruned_loss=0.07128, over 7162.00 frames.], tot_loss[loss=0.2473, simple_loss=0.3146, pruned_loss=0.09004, over 1416657.43 frames.], batch size: 18, lr: 1.87e-03
+2022-05-13 23:00:38,459 INFO [train.py:812] (7/8) Epoch 3, batch 1950, loss[loss=0.3018, simple_loss=0.3607, pruned_loss=0.1215, over 6793.00 frames.], tot_loss[loss=0.2476, simple_loss=0.3149, pruned_loss=0.0902, over 1418463.24 frames.], batch size: 31, lr: 1.87e-03
+2022-05-13 23:01:37,632 INFO [train.py:812] (7/8) Epoch 3, batch 2000, loss[loss=0.2271, simple_loss=0.2937, pruned_loss=0.08021, over 7148.00 frames.], tot_loss[loss=0.2465, simple_loss=0.3138, pruned_loss=0.08962, over 1422729.03 frames.], batch size: 19, lr: 1.87e-03
+2022-05-13 23:02:36,955 INFO [train.py:812] (7/8) Epoch 3, batch 2050, loss[loss=0.2826, simple_loss=0.3318, pruned_loss=0.1167, over 5035.00 frames.], tot_loss[loss=0.2475, simple_loss=0.3153, pruned_loss=0.08984, over 1422066.27 frames.], batch size: 52, lr: 1.86e-03
+2022-05-13 23:03:35,473 INFO [train.py:812] (7/8) Epoch 3, batch 2100, loss[loss=0.2543, simple_loss=0.3286, pruned_loss=0.08998, over 7315.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3156, pruned_loss=0.08998, over 1424972.53 frames.], batch size: 21, lr: 1.86e-03
+2022-05-13 23:04:34,089 INFO [train.py:812] (7/8) Epoch 3, batch 2150, loss[loss=0.276, simple_loss=0.3417, pruned_loss=0.1052, over 7230.00 frames.], tot_loss[loss=0.248, simple_loss=0.3158, pruned_loss=0.09015, over 1426990.47 frames.], batch size: 20, lr: 1.86e-03
+2022-05-13 23:05:32,789 INFO [train.py:812] (7/8) Epoch 3, batch 2200, loss[loss=0.2585, simple_loss=0.3221, pruned_loss=0.09742, over 7147.00 frames.], tot_loss[loss=0.2469, simple_loss=0.3146, pruned_loss=0.08963, over 1425902.47 frames.], batch size: 20, lr: 1.85e-03
+2022-05-13 23:06:32,219 INFO [train.py:812] (7/8) Epoch 3, batch 2250, loss[loss=0.2751, simple_loss=0.336, pruned_loss=0.107, over 7337.00 frames.], tot_loss[loss=0.2477, simple_loss=0.3156, pruned_loss=0.08992, over 1425396.14 frames.], batch size: 20, lr: 1.85e-03
+2022-05-13 23:07:31,575 INFO [train.py:812] (7/8) Epoch 3, batch 2300, loss[loss=0.2381, simple_loss=0.3052, pruned_loss=0.08553, over 7370.00 frames.], tot_loss[loss=0.2474, simple_loss=0.315, pruned_loss=0.08986, over 1414031.05 frames.], batch size: 19, lr: 1.85e-03
+2022-05-13 23:08:31,287 INFO [train.py:812] (7/8) Epoch 3, batch 2350, loss[loss=0.2269, simple_loss=0.2948, pruned_loss=0.07946, over 7252.00 frames.], tot_loss[loss=0.246, simple_loss=0.3141, pruned_loss=0.08894, over 1415612.48 frames.], batch size: 19, lr: 1.84e-03
+2022-05-13 23:09:29,625 INFO [train.py:812] (7/8) Epoch 3, batch 2400, loss[loss=0.1821, simple_loss=0.262, pruned_loss=0.05106, over 7258.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3149, pruned_loss=0.08913, over 1418706.87 frames.], batch size: 19, lr: 1.84e-03
+2022-05-13 23:10:29,125 INFO [train.py:812] (7/8) Epoch 3, batch 2450, loss[loss=0.238, simple_loss=0.3199, pruned_loss=0.07801, over 7244.00 frames.], tot_loss[loss=0.2471, simple_loss=0.3159, pruned_loss=0.08914, over 1415902.86 frames.], batch size: 20, lr: 1.84e-03
+2022-05-13 23:11:28,104 INFO [train.py:812] (7/8) Epoch 3, batch 2500, loss[loss=0.2476, simple_loss=0.325, pruned_loss=0.08515, over 7147.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3147, pruned_loss=0.08875, over 1414186.18 frames.], batch size: 19, lr: 1.83e-03
+2022-05-13 23:12:27,759 INFO [train.py:812] (7/8) Epoch 3, batch 2550, loss[loss=0.244, simple_loss=0.322, pruned_loss=0.08296, over 7218.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3141, pruned_loss=0.08848, over 1414043.00 frames.], batch size: 21, lr: 1.83e-03
+2022-05-13 23:13:27,088 INFO [train.py:812] (7/8) Epoch 3, batch 2600, loss[loss=0.2168, simple_loss=0.2868, pruned_loss=0.07337, over 7278.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3128, pruned_loss=0.08751, over 1420360.81 frames.], batch size: 18, lr: 1.83e-03
+2022-05-13 23:14:26,498 INFO [train.py:812] (7/8) Epoch 3, batch 2650, loss[loss=0.2401, simple_loss=0.3176, pruned_loss=0.08128, over 7320.00 frames.], tot_loss[loss=0.2434, simple_loss=0.3121, pruned_loss=0.08733, over 1419626.63 frames.], batch size: 20, lr: 1.82e-03
+2022-05-13 23:15:24,427 INFO [train.py:812] (7/8) Epoch 3, batch 2700, loss[loss=0.2365, simple_loss=0.2984, pruned_loss=0.08732, over 7052.00 frames.], tot_loss[loss=0.244, simple_loss=0.3129, pruned_loss=0.08758, over 1420275.94 frames.], batch size: 18, lr: 1.82e-03
+2022-05-13 23:16:23,949 INFO [train.py:812] (7/8) Epoch 3, batch 2750, loss[loss=0.2881, simple_loss=0.3461, pruned_loss=0.115, over 7185.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3139, pruned_loss=0.08824, over 1419155.72 frames.], batch size: 26, lr: 1.82e-03
+2022-05-13 23:17:22,930 INFO [train.py:812] (7/8) Epoch 3, batch 2800, loss[loss=0.334, simple_loss=0.3725, pruned_loss=0.1478, over 5338.00 frames.], tot_loss[loss=0.245, simple_loss=0.3137, pruned_loss=0.08818, over 1418920.80 frames.], batch size: 53, lr: 1.81e-03
+2022-05-13 23:18:30,863 INFO [train.py:812] (7/8) Epoch 3, batch 2850, loss[loss=0.2856, simple_loss=0.3422, pruned_loss=0.1144, over 7222.00 frames.], tot_loss[loss=0.2441, simple_loss=0.3127, pruned_loss=0.08775, over 1421594.10 frames.], batch size: 21, lr: 1.81e-03
+2022-05-13 23:19:29,921 INFO [train.py:812] (7/8) Epoch 3, batch 2900, loss[loss=0.2627, simple_loss=0.3328, pruned_loss=0.09633, over 6393.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3121, pruned_loss=0.08684, over 1417063.07 frames.], batch size: 38, lr: 1.81e-03
+2022-05-13 23:20:29,335 INFO [train.py:812] (7/8) Epoch 3, batch 2950, loss[loss=0.2435, simple_loss=0.3222, pruned_loss=0.08239, over 7127.00 frames.], tot_loss[loss=0.2451, simple_loss=0.3142, pruned_loss=0.08801, over 1415867.27 frames.], batch size: 26, lr: 1.80e-03
+2022-05-13 23:21:28,558 INFO [train.py:812] (7/8) Epoch 3, batch 3000, loss[loss=0.2115, simple_loss=0.2926, pruned_loss=0.06522, over 7330.00 frames.], tot_loss[loss=0.2437, simple_loss=0.3129, pruned_loss=0.08725, over 1419586.07 frames.], batch size: 22, lr: 1.80e-03
+2022-05-13 23:21:28,560 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-13 23:21:36,068 INFO [train.py:841] (7/8) Epoch 3, validation: loss=0.1862, simple_loss=0.2867, pruned_loss=0.04278, over 698248.00 frames.
+2022-05-13 23:22:33,863 INFO [train.py:812] (7/8) Epoch 3, batch 3050, loss[loss=0.2475, simple_loss=0.3169, pruned_loss=0.08905, over 7409.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3127, pruned_loss=0.08642, over 1424465.80 frames.], batch size: 21, lr: 1.80e-03
+2022-05-13 23:23:30,808 INFO [train.py:812] (7/8) Epoch 3, batch 3100, loss[loss=0.2504, simple_loss=0.3231, pruned_loss=0.08886, over 7281.00 frames.], tot_loss[loss=0.2416, simple_loss=0.3119, pruned_loss=0.08563, over 1427611.27 frames.], batch size: 18, lr: 1.79e-03
+2022-05-13 23:24:30,051 INFO [train.py:812] (7/8) Epoch 3, batch 3150, loss[loss=0.2189, simple_loss=0.2964, pruned_loss=0.07069, over 7215.00 frames.], tot_loss[loss=0.2416, simple_loss=0.3119, pruned_loss=0.08567, over 1422692.81 frames.], batch size: 21, lr: 1.79e-03
+2022-05-13 23:25:29,480 INFO [train.py:812] (7/8) Epoch 3, batch 3200, loss[loss=0.2831, simple_loss=0.346, pruned_loss=0.11, over 7393.00 frames.], tot_loss[loss=0.242, simple_loss=0.3124, pruned_loss=0.08582, over 1425635.28 frames.], batch size: 23, lr: 1.79e-03
+2022-05-13 23:26:29,140 INFO [train.py:812] (7/8) Epoch 3, batch 3250, loss[loss=0.2072, simple_loss=0.2903, pruned_loss=0.0621, over 7161.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3129, pruned_loss=0.08632, over 1426740.53 frames.], batch size: 19, lr: 1.79e-03
+2022-05-13 23:27:27,218 INFO [train.py:812] (7/8) Epoch 3, batch 3300, loss[loss=0.2658, simple_loss=0.3336, pruned_loss=0.09896, over 7124.00 frames.], tot_loss[loss=0.2413, simple_loss=0.3117, pruned_loss=0.08547, over 1428883.50 frames.], batch size: 26, lr: 1.78e-03
+2022-05-13 23:28:26,196 INFO [train.py:812] (7/8) Epoch 3, batch 3350, loss[loss=0.197, simple_loss=0.2779, pruned_loss=0.05804, over 7274.00 frames.], tot_loss[loss=0.2418, simple_loss=0.3122, pruned_loss=0.08566, over 1425187.50 frames.], batch size: 18, lr: 1.78e-03
+2022-05-13 23:29:23,921 INFO [train.py:812] (7/8) Epoch 3, batch 3400, loss[loss=0.2173, simple_loss=0.2811, pruned_loss=0.07675, over 7411.00 frames.], tot_loss[loss=0.2417, simple_loss=0.3122, pruned_loss=0.08558, over 1422883.47 frames.], batch size: 18, lr: 1.78e-03
+2022-05-13 23:30:22,243 INFO [train.py:812] (7/8) Epoch 3, batch 3450, loss[loss=0.2656, simple_loss=0.3228, pruned_loss=0.1042, over 7263.00 frames.], tot_loss[loss=0.2414, simple_loss=0.3119, pruned_loss=0.08547, over 1420053.80 frames.], batch size: 19, lr: 1.77e-03
+2022-05-13 23:31:20,931 INFO [train.py:812] (7/8) Epoch 3, batch 3500, loss[loss=0.2264, simple_loss=0.2979, pruned_loss=0.07741, over 7284.00 frames.], tot_loss[loss=0.2409, simple_loss=0.311, pruned_loss=0.08543, over 1420975.63 frames.], batch size: 25, lr: 1.77e-03
+2022-05-13 23:32:20,563 INFO [train.py:812] (7/8) Epoch 3, batch 3550, loss[loss=0.2337, simple_loss=0.3038, pruned_loss=0.08186, over 7220.00 frames.], tot_loss[loss=0.2425, simple_loss=0.3124, pruned_loss=0.0863, over 1419837.48 frames.], batch size: 21, lr: 1.77e-03
+2022-05-13 23:33:19,850 INFO [train.py:812] (7/8) Epoch 3, batch 3600, loss[loss=0.2452, simple_loss=0.3264, pruned_loss=0.08194, over 7292.00 frames.], tot_loss[loss=0.2424, simple_loss=0.312, pruned_loss=0.08641, over 1421408.57 frames.], batch size: 24, lr: 1.76e-03
+2022-05-13 23:34:19,488 INFO [train.py:812] (7/8) Epoch 3, batch 3650, loss[loss=0.2284, simple_loss=0.3084, pruned_loss=0.07421, over 7387.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3116, pruned_loss=0.08649, over 1421003.68 frames.], batch size: 23, lr: 1.76e-03
+2022-05-13 23:35:18,570 INFO [train.py:812] (7/8) Epoch 3, batch 3700, loss[loss=0.214, simple_loss=0.2795, pruned_loss=0.07424, over 7420.00 frames.], tot_loss[loss=0.2418, simple_loss=0.3116, pruned_loss=0.08597, over 1415807.51 frames.], batch size: 18, lr: 1.76e-03
+2022-05-13 23:36:18,229 INFO [train.py:812] (7/8) Epoch 3, batch 3750, loss[loss=0.1801, simple_loss=0.2481, pruned_loss=0.05609, over 7273.00 frames.], tot_loss[loss=0.241, simple_loss=0.3109, pruned_loss=0.08561, over 1421921.32 frames.], batch size: 18, lr: 1.76e-03
+2022-05-13 23:37:16,817 INFO [train.py:812] (7/8) Epoch 3, batch 3800, loss[loss=0.2269, simple_loss=0.2955, pruned_loss=0.0792, over 7167.00 frames.], tot_loss[loss=0.2397, simple_loss=0.31, pruned_loss=0.08475, over 1422218.28 frames.], batch size: 18, lr: 1.75e-03
+2022-05-13 23:38:16,223 INFO [train.py:812] (7/8) Epoch 3, batch 3850, loss[loss=0.2385, simple_loss=0.3222, pruned_loss=0.07739, over 7326.00 frames.], tot_loss[loss=0.2399, simple_loss=0.31, pruned_loss=0.08485, over 1421479.98 frames.], batch size: 22, lr: 1.75e-03
+2022-05-13 23:39:15,496 INFO [train.py:812] (7/8) Epoch 3, batch 3900, loss[loss=0.2656, simple_loss=0.335, pruned_loss=0.09812, over 7317.00 frames.], tot_loss[loss=0.2396, simple_loss=0.31, pruned_loss=0.08459, over 1423175.30 frames.], batch size: 20, lr: 1.75e-03
+2022-05-13 23:40:14,833 INFO [train.py:812] (7/8) Epoch 3, batch 3950, loss[loss=0.2192, simple_loss=0.2981, pruned_loss=0.07018, over 7332.00 frames.], tot_loss[loss=0.2387, simple_loss=0.3094, pruned_loss=0.084, over 1420607.25 frames.], batch size: 21, lr: 1.74e-03
+2022-05-13 23:41:13,988 INFO [train.py:812] (7/8) Epoch 3, batch 4000, loss[loss=0.2504, simple_loss=0.3359, pruned_loss=0.08244, over 7337.00 frames.], tot_loss[loss=0.2383, simple_loss=0.3093, pruned_loss=0.08364, over 1425518.61 frames.], batch size: 22, lr: 1.74e-03
+2022-05-13 23:42:13,710 INFO [train.py:812] (7/8) Epoch 3, batch 4050, loss[loss=0.2403, simple_loss=0.321, pruned_loss=0.07981, over 7418.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3089, pruned_loss=0.08335, over 1426594.70 frames.], batch size: 20, lr: 1.74e-03
+2022-05-13 23:43:12,804 INFO [train.py:812] (7/8) Epoch 3, batch 4100, loss[loss=0.2217, simple_loss=0.288, pruned_loss=0.07775, over 7082.00 frames.], tot_loss[loss=0.24, simple_loss=0.3103, pruned_loss=0.08478, over 1417672.93 frames.], batch size: 18, lr: 1.73e-03
+2022-05-13 23:44:12,484 INFO [train.py:812] (7/8) Epoch 3, batch 4150, loss[loss=0.2519, simple_loss=0.3147, pruned_loss=0.09453, over 7109.00 frames.], tot_loss[loss=0.2405, simple_loss=0.3109, pruned_loss=0.08504, over 1422004.83 frames.], batch size: 21, lr: 1.73e-03
+2022-05-13 23:45:10,736 INFO [train.py:812] (7/8) Epoch 3, batch 4200, loss[loss=0.2632, simple_loss=0.3303, pruned_loss=0.09807, over 7130.00 frames.], tot_loss[loss=0.2393, simple_loss=0.3101, pruned_loss=0.08422, over 1421380.56 frames.], batch size: 28, lr: 1.73e-03
+2022-05-13 23:46:09,948 INFO [train.py:812] (7/8) Epoch 3, batch 4250, loss[loss=0.2741, simple_loss=0.3391, pruned_loss=0.1046, over 7209.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3105, pruned_loss=0.08453, over 1422261.45 frames.], batch size: 22, lr: 1.73e-03
+2022-05-13 23:47:09,084 INFO [train.py:812] (7/8) Epoch 3, batch 4300, loss[loss=0.2129, simple_loss=0.2847, pruned_loss=0.07057, over 7076.00 frames.], tot_loss[loss=0.2413, simple_loss=0.3117, pruned_loss=0.08546, over 1424693.84 frames.], batch size: 18, lr: 1.72e-03
+2022-05-13 23:48:08,241 INFO [train.py:812] (7/8) Epoch 3, batch 4350, loss[loss=0.2435, simple_loss=0.3311, pruned_loss=0.07798, over 7144.00 frames.], tot_loss[loss=0.2416, simple_loss=0.312, pruned_loss=0.08567, over 1426583.99 frames.], batch size: 20, lr: 1.72e-03
+2022-05-13 23:49:06,742 INFO [train.py:812] (7/8) Epoch 3, batch 4400, loss[loss=0.2735, simple_loss=0.3575, pruned_loss=0.09477, over 7292.00 frames.], tot_loss[loss=0.241, simple_loss=0.3114, pruned_loss=0.08526, over 1421187.30 frames.], batch size: 25, lr: 1.72e-03
+2022-05-13 23:50:05,690 INFO [train.py:812] (7/8) Epoch 3, batch 4450, loss[loss=0.2625, simple_loss=0.3285, pruned_loss=0.09828, over 7327.00 frames.], tot_loss[loss=0.2424, simple_loss=0.3128, pruned_loss=0.08599, over 1412977.34 frames.], batch size: 22, lr: 1.71e-03
+2022-05-13 23:51:04,284 INFO [train.py:812] (7/8) Epoch 3, batch 4500, loss[loss=0.1913, simple_loss=0.2831, pruned_loss=0.04979, over 7125.00 frames.], tot_loss[loss=0.2415, simple_loss=0.3123, pruned_loss=0.08534, over 1406291.01 frames.], batch size: 21, lr: 1.71e-03
+2022-05-13 23:52:01,845 INFO [train.py:812] (7/8) Epoch 3, batch 4550, loss[loss=0.2489, simple_loss=0.3146, pruned_loss=0.09165, over 6319.00 frames.], tot_loss[loss=0.244, simple_loss=0.3141, pruned_loss=0.08693, over 1378307.81 frames.], batch size: 38, lr: 1.71e-03
+2022-05-13 23:53:11,489 INFO [train.py:812] (7/8) Epoch 4, batch 0, loss[loss=0.2689, simple_loss=0.3435, pruned_loss=0.09716, over 7211.00 frames.], tot_loss[loss=0.2689, simple_loss=0.3435, pruned_loss=0.09716, over 7211.00 frames.], batch size: 23, lr: 1.66e-03
+2022-05-13 23:54:10,722 INFO [train.py:812] (7/8) Epoch 4, batch 50, loss[loss=0.2288, simple_loss=0.2924, pruned_loss=0.08263, over 7264.00 frames.], tot_loss[loss=0.235, simple_loss=0.3053, pruned_loss=0.08239, over 318408.50 frames.], batch size: 17, lr: 1.66e-03
+2022-05-13 23:55:09,424 INFO [train.py:812] (7/8) Epoch 4, batch 100, loss[loss=0.2219, simple_loss=0.2879, pruned_loss=0.07795, over 7272.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3055, pruned_loss=0.08142, over 564960.05 frames.], batch size: 17, lr: 1.65e-03
+2022-05-13 23:56:09,359 INFO [train.py:812] (7/8) Epoch 4, batch 150, loss[loss=0.2414, simple_loss=0.3225, pruned_loss=0.08014, over 7339.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3065, pruned_loss=0.081, over 755663.26 frames.], batch size: 22, lr: 1.65e-03
+2022-05-13 23:57:08,472 INFO [train.py:812] (7/8) Epoch 4, batch 200, loss[loss=0.2682, simple_loss=0.3295, pruned_loss=0.1034, over 7205.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3059, pruned_loss=0.0802, over 904028.41 frames.], batch size: 23, lr: 1.65e-03
+2022-05-13 23:58:07,173 INFO [train.py:812] (7/8) Epoch 4, batch 250, loss[loss=0.2417, simple_loss=0.3137, pruned_loss=0.08482, over 7332.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3081, pruned_loss=0.08078, over 1015826.65 frames.], batch size: 22, lr: 1.64e-03
+2022-05-13 23:59:06,624 INFO [train.py:812] (7/8) Epoch 4, batch 300, loss[loss=0.313, simple_loss=0.3744, pruned_loss=0.1258, over 7386.00 frames.], tot_loss[loss=0.2355, simple_loss=0.3088, pruned_loss=0.08107, over 1110516.49 frames.], batch size: 23, lr: 1.64e-03
+2022-05-14 00:00:06,148 INFO [train.py:812] (7/8) Epoch 4, batch 350, loss[loss=0.2548, simple_loss=0.3363, pruned_loss=0.08662, over 7319.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3083, pruned_loss=0.08073, over 1181664.37 frames.], batch size: 21, lr: 1.64e-03
+2022-05-14 00:01:05,143 INFO [train.py:812] (7/8) Epoch 4, batch 400, loss[loss=0.2001, simple_loss=0.2806, pruned_loss=0.05978, over 7228.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3059, pruned_loss=0.08056, over 1232112.84 frames.], batch size: 20, lr: 1.64e-03
+2022-05-14 00:02:04,563 INFO [train.py:812] (7/8) Epoch 4, batch 450, loss[loss=0.2643, simple_loss=0.3316, pruned_loss=0.09847, over 7135.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3052, pruned_loss=0.08009, over 1274212.32 frames.], batch size: 20, lr: 1.63e-03
+2022-05-14 00:03:03,251 INFO [train.py:812] (7/8) Epoch 4, batch 500, loss[loss=0.2013, simple_loss=0.2792, pruned_loss=0.06166, over 7157.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3066, pruned_loss=0.08057, over 1303823.77 frames.], batch size: 19, lr: 1.63e-03
+2022-05-14 00:04:02,761 INFO [train.py:812] (7/8) Epoch 4, batch 550, loss[loss=0.2007, simple_loss=0.2822, pruned_loss=0.05958, over 7159.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3073, pruned_loss=0.08113, over 1329176.40 frames.], batch size: 18, lr: 1.63e-03
+2022-05-14 00:05:01,392 INFO [train.py:812] (7/8) Epoch 4, batch 600, loss[loss=0.2398, simple_loss=0.3158, pruned_loss=0.08186, over 6262.00 frames.], tot_loss[loss=0.2337, simple_loss=0.3062, pruned_loss=0.08061, over 1346800.45 frames.], batch size: 37, lr: 1.63e-03
+2022-05-14 00:06:00,861 INFO [train.py:812] (7/8) Epoch 4, batch 650, loss[loss=0.2207, simple_loss=0.3067, pruned_loss=0.06732, over 7429.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3055, pruned_loss=0.07966, over 1367059.12 frames.], batch size: 20, lr: 1.62e-03
+2022-05-14 00:07:00,196 INFO [train.py:812] (7/8) Epoch 4, batch 700, loss[loss=0.2196, simple_loss=0.3062, pruned_loss=0.06647, over 7283.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3044, pruned_loss=0.07902, over 1384316.09 frames.], batch size: 24, lr: 1.62e-03
+2022-05-14 00:07:59,231 INFO [train.py:812] (7/8) Epoch 4, batch 750, loss[loss=0.2778, simple_loss=0.3425, pruned_loss=0.1066, over 7298.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3036, pruned_loss=0.07883, over 1392523.85 frames.], batch size: 24, lr: 1.62e-03
+2022-05-14 00:08:58,483 INFO [train.py:812] (7/8) Epoch 4, batch 800, loss[loss=0.2193, simple_loss=0.2927, pruned_loss=0.07298, over 7267.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3052, pruned_loss=0.07969, over 1397463.72 frames.], batch size: 19, lr: 1.62e-03
+2022-05-14 00:09:58,479 INFO [train.py:812] (7/8) Epoch 4, batch 850, loss[loss=0.2425, simple_loss=0.3201, pruned_loss=0.08247, over 7068.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3058, pruned_loss=0.07981, over 1407714.77 frames.], batch size: 18, lr: 1.61e-03
+2022-05-14 00:10:57,759 INFO [train.py:812] (7/8) Epoch 4, batch 900, loss[loss=0.2588, simple_loss=0.3253, pruned_loss=0.09615, over 7116.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3058, pruned_loss=0.07982, over 1415765.04 frames.], batch size: 21, lr: 1.61e-03
+2022-05-14 00:11:56,784 INFO [train.py:812] (7/8) Epoch 4, batch 950, loss[loss=0.227, simple_loss=0.3015, pruned_loss=0.07628, over 7227.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3058, pruned_loss=0.07967, over 1420481.51 frames.], batch size: 26, lr: 1.61e-03
+2022-05-14 00:12:55,439 INFO [train.py:812] (7/8) Epoch 4, batch 1000, loss[loss=0.1985, simple_loss=0.2763, pruned_loss=0.06037, over 7284.00 frames.], tot_loss[loss=0.2316, simple_loss=0.305, pruned_loss=0.07909, over 1421183.67 frames.], batch size: 18, lr: 1.61e-03
+2022-05-14 00:13:54,525 INFO [train.py:812] (7/8) Epoch 4, batch 1050, loss[loss=0.2589, simple_loss=0.3207, pruned_loss=0.0986, over 6756.00 frames.], tot_loss[loss=0.2315, simple_loss=0.305, pruned_loss=0.07898, over 1419461.95 frames.], batch size: 31, lr: 1.60e-03
+2022-05-14 00:14:53,511 INFO [train.py:812] (7/8) Epoch 4, batch 1100, loss[loss=0.2322, simple_loss=0.3095, pruned_loss=0.07742, over 7409.00 frames.], tot_loss[loss=0.2303, simple_loss=0.3037, pruned_loss=0.07843, over 1420830.30 frames.], batch size: 21, lr: 1.60e-03
+2022-05-14 00:15:52,737 INFO [train.py:812] (7/8) Epoch 4, batch 1150, loss[loss=0.2317, simple_loss=0.2966, pruned_loss=0.08335, over 7320.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3053, pruned_loss=0.07871, over 1418661.98 frames.], batch size: 21, lr: 1.60e-03
+2022-05-14 00:16:51,407 INFO [train.py:812] (7/8) Epoch 4, batch 1200, loss[loss=0.2096, simple_loss=0.302, pruned_loss=0.05859, over 7319.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3066, pruned_loss=0.07983, over 1416491.17 frames.], batch size: 21, lr: 1.60e-03
+2022-05-14 00:17:50,485 INFO [train.py:812] (7/8) Epoch 4, batch 1250, loss[loss=0.2057, simple_loss=0.2708, pruned_loss=0.0703, over 7243.00 frames.], tot_loss[loss=0.232, simple_loss=0.3056, pruned_loss=0.07923, over 1414582.61 frames.], batch size: 16, lr: 1.59e-03
+2022-05-14 00:18:48,749 INFO [train.py:812] (7/8) Epoch 4, batch 1300, loss[loss=0.2922, simple_loss=0.3585, pruned_loss=0.1129, over 7192.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3055, pruned_loss=0.07934, over 1417303.25 frames.], batch size: 23, lr: 1.59e-03
+2022-05-14 00:19:47,573 INFO [train.py:812] (7/8) Epoch 4, batch 1350, loss[loss=0.1895, simple_loss=0.2781, pruned_loss=0.05039, over 7243.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3054, pruned_loss=0.07889, over 1416681.98 frames.], batch size: 20, lr: 1.59e-03
+2022-05-14 00:20:44,869 INFO [train.py:812] (7/8) Epoch 4, batch 1400, loss[loss=0.2404, simple_loss=0.3084, pruned_loss=0.08618, over 7223.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3043, pruned_loss=0.07865, over 1420053.45 frames.], batch size: 22, lr: 1.59e-03
+2022-05-14 00:21:44,678 INFO [train.py:812] (7/8) Epoch 4, batch 1450, loss[loss=0.2533, simple_loss=0.3286, pruned_loss=0.08898, over 7292.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3055, pruned_loss=0.07871, over 1421740.89 frames.], batch size: 24, lr: 1.59e-03
+2022-05-14 00:22:43,719 INFO [train.py:812] (7/8) Epoch 4, batch 1500, loss[loss=0.2437, simple_loss=0.3196, pruned_loss=0.0839, over 7303.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3062, pruned_loss=0.07922, over 1419348.07 frames.], batch size: 24, lr: 1.58e-03
+2022-05-14 00:23:43,466 INFO [train.py:812] (7/8) Epoch 4, batch 1550, loss[loss=0.2949, simple_loss=0.3472, pruned_loss=0.1213, over 5070.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3059, pruned_loss=0.0791, over 1418563.77 frames.], batch size: 53, lr: 1.58e-03
+2022-05-14 00:24:41,315 INFO [train.py:812] (7/8) Epoch 4, batch 1600, loss[loss=0.2552, simple_loss=0.3265, pruned_loss=0.09202, over 7281.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3067, pruned_loss=0.07956, over 1414906.90 frames.], batch size: 25, lr: 1.58e-03
+2022-05-14 00:25:40,760 INFO [train.py:812] (7/8) Epoch 4, batch 1650, loss[loss=0.2209, simple_loss=0.3013, pruned_loss=0.07026, over 7326.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3047, pruned_loss=0.07857, over 1416770.27 frames.], batch size: 20, lr: 1.58e-03
+2022-05-14 00:26:39,550 INFO [train.py:812] (7/8) Epoch 4, batch 1700, loss[loss=0.2147, simple_loss=0.301, pruned_loss=0.0642, over 7144.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3039, pruned_loss=0.07765, over 1419957.60 frames.], batch size: 20, lr: 1.57e-03
+2022-05-14 00:27:38,806 INFO [train.py:812] (7/8) Epoch 4, batch 1750, loss[loss=0.2712, simple_loss=0.3305, pruned_loss=0.106, over 7219.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3045, pruned_loss=0.07818, over 1418938.78 frames.], batch size: 22, lr: 1.57e-03
+2022-05-14 00:28:45,543 INFO [train.py:812] (7/8) Epoch 4, batch 1800, loss[loss=0.2752, simple_loss=0.3312, pruned_loss=0.1096, over 7212.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3057, pruned_loss=0.07894, over 1420734.80 frames.], batch size: 21, lr: 1.57e-03
+2022-05-14 00:29:45,178 INFO [train.py:812] (7/8) Epoch 4, batch 1850, loss[loss=0.2731, simple_loss=0.3231, pruned_loss=0.1116, over 7141.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3058, pruned_loss=0.07884, over 1419564.32 frames.], batch size: 17, lr: 1.57e-03
+2022-05-14 00:30:44,423 INFO [train.py:812] (7/8) Epoch 4, batch 1900, loss[loss=0.2263, simple_loss=0.2994, pruned_loss=0.0766, over 7159.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3064, pruned_loss=0.07925, over 1422759.87 frames.], batch size: 19, lr: 1.56e-03
+2022-05-14 00:31:43,813 INFO [train.py:812] (7/8) Epoch 4, batch 1950, loss[loss=0.2629, simple_loss=0.3267, pruned_loss=0.09955, over 6624.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3056, pruned_loss=0.07876, over 1427766.41 frames.], batch size: 38, lr: 1.56e-03
+2022-05-14 00:32:40,447 INFO [train.py:812] (7/8) Epoch 4, batch 2000, loss[loss=0.2594, simple_loss=0.3381, pruned_loss=0.09038, over 7107.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3072, pruned_loss=0.07961, over 1425010.10 frames.], batch size: 21, lr: 1.56e-03
+2022-05-14 00:34:15,605 INFO [train.py:812] (7/8) Epoch 4, batch 2050, loss[loss=0.2259, simple_loss=0.3071, pruned_loss=0.07236, over 6885.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3068, pruned_loss=0.07986, over 1422084.44 frames.], batch size: 31, lr: 1.56e-03
+2022-05-14 00:35:41,838 INFO [train.py:812] (7/8) Epoch 4, batch 2100, loss[loss=0.2252, simple_loss=0.3063, pruned_loss=0.072, over 7313.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3059, pruned_loss=0.07931, over 1420576.31 frames.], batch size: 21, lr: 1.56e-03
+2022-05-14 00:36:41,428 INFO [train.py:812] (7/8) Epoch 4, batch 2150, loss[loss=0.2533, simple_loss=0.3275, pruned_loss=0.08951, over 7316.00 frames.], tot_loss[loss=0.231, simple_loss=0.3049, pruned_loss=0.07857, over 1422748.87 frames.], batch size: 22, lr: 1.55e-03
+2022-05-14 00:37:40,385 INFO [train.py:812] (7/8) Epoch 4, batch 2200, loss[loss=0.2299, simple_loss=0.3166, pruned_loss=0.07158, over 7218.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3043, pruned_loss=0.0782, over 1425369.44 frames.], batch size: 21, lr: 1.55e-03
+2022-05-14 00:38:47,600 INFO [train.py:812] (7/8) Epoch 4, batch 2250, loss[loss=0.2996, simple_loss=0.3467, pruned_loss=0.1263, over 4981.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3052, pruned_loss=0.07829, over 1426899.28 frames.], batch size: 52, lr: 1.55e-03
+2022-05-14 00:39:45,565 INFO [train.py:812] (7/8) Epoch 4, batch 2300, loss[loss=0.2289, simple_loss=0.2876, pruned_loss=0.08506, over 7158.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3042, pruned_loss=0.07773, over 1429791.14 frames.], batch size: 19, lr: 1.55e-03
+2022-05-14 00:40:45,451 INFO [train.py:812] (7/8) Epoch 4, batch 2350, loss[loss=0.2069, simple_loss=0.2851, pruned_loss=0.06438, over 7319.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3029, pruned_loss=0.07676, over 1430800.41 frames.], batch size: 20, lr: 1.54e-03
+2022-05-14 00:41:44,153 INFO [train.py:812] (7/8) Epoch 4, batch 2400, loss[loss=0.2419, simple_loss=0.3125, pruned_loss=0.08568, over 7332.00 frames.], tot_loss[loss=0.2305, simple_loss=0.3051, pruned_loss=0.07789, over 1433175.45 frames.], batch size: 25, lr: 1.54e-03
+2022-05-14 00:42:43,299 INFO [train.py:812] (7/8) Epoch 4, batch 2450, loss[loss=0.2655, simple_loss=0.3324, pruned_loss=0.09933, over 7377.00 frames.], tot_loss[loss=0.23, simple_loss=0.3048, pruned_loss=0.07757, over 1436059.14 frames.], batch size: 23, lr: 1.54e-03
+2022-05-14 00:43:42,459 INFO [train.py:812] (7/8) Epoch 4, batch 2500, loss[loss=0.2103, simple_loss=0.2923, pruned_loss=0.06412, over 7169.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3041, pruned_loss=0.07688, over 1434332.13 frames.], batch size: 19, lr: 1.54e-03
+2022-05-14 00:44:40,458 INFO [train.py:812] (7/8) Epoch 4, batch 2550, loss[loss=0.1889, simple_loss=0.2657, pruned_loss=0.05606, over 7407.00 frames.], tot_loss[loss=0.2286, simple_loss=0.3037, pruned_loss=0.07671, over 1426122.99 frames.], batch size: 18, lr: 1.54e-03
+2022-05-14 00:45:38,448 INFO [train.py:812] (7/8) Epoch 4, batch 2600, loss[loss=0.2046, simple_loss=0.2835, pruned_loss=0.06283, over 7229.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3059, pruned_loss=0.07826, over 1426507.16 frames.], batch size: 20, lr: 1.53e-03
+2022-05-14 00:46:37,725 INFO [train.py:812] (7/8) Epoch 4, batch 2650, loss[loss=0.2111, simple_loss=0.2801, pruned_loss=0.07107, over 7002.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3064, pruned_loss=0.07889, over 1420428.41 frames.], batch size: 16, lr: 1.53e-03
+2022-05-14 00:47:36,759 INFO [train.py:812] (7/8) Epoch 4, batch 2700, loss[loss=0.1947, simple_loss=0.2582, pruned_loss=0.06559, over 6827.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3061, pruned_loss=0.07868, over 1418646.13 frames.], batch size: 15, lr: 1.53e-03
+2022-05-14 00:48:35,489 INFO [train.py:812] (7/8) Epoch 4, batch 2750, loss[loss=0.2277, simple_loss=0.2999, pruned_loss=0.07775, over 7267.00 frames.], tot_loss[loss=0.231, simple_loss=0.3058, pruned_loss=0.07806, over 1421997.91 frames.], batch size: 19, lr: 1.53e-03
+2022-05-14 00:49:34,127 INFO [train.py:812] (7/8) Epoch 4, batch 2800, loss[loss=0.2416, simple_loss=0.3131, pruned_loss=0.08509, over 7163.00 frames.], tot_loss[loss=0.2295, simple_loss=0.3045, pruned_loss=0.0772, over 1424159.91 frames.], batch size: 19, lr: 1.53e-03
+2022-05-14 00:50:32,986 INFO [train.py:812] (7/8) Epoch 4, batch 2850, loss[loss=0.2497, simple_loss=0.3241, pruned_loss=0.08766, over 5048.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3034, pruned_loss=0.07662, over 1422608.45 frames.], batch size: 53, lr: 1.52e-03
+2022-05-14 00:51:31,221 INFO [train.py:812] (7/8) Epoch 4, batch 2900, loss[loss=0.2294, simple_loss=0.3151, pruned_loss=0.0719, over 6885.00 frames.], tot_loss[loss=0.2279, simple_loss=0.3029, pruned_loss=0.07644, over 1422707.41 frames.], batch size: 31, lr: 1.52e-03
+2022-05-14 00:52:31,118 INFO [train.py:812] (7/8) Epoch 4, batch 2950, loss[loss=0.2392, simple_loss=0.325, pruned_loss=0.07668, over 7106.00 frames.], tot_loss[loss=0.2279, simple_loss=0.3032, pruned_loss=0.07626, over 1427054.81 frames.], batch size: 28, lr: 1.52e-03
+2022-05-14 00:53:30,083 INFO [train.py:812] (7/8) Epoch 4, batch 3000, loss[loss=0.1974, simple_loss=0.2926, pruned_loss=0.05112, over 7156.00 frames.], tot_loss[loss=0.2287, simple_loss=0.3036, pruned_loss=0.07689, over 1425613.56 frames.], batch size: 20, lr: 1.52e-03
+2022-05-14 00:53:30,085 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 00:53:37,752 INFO [train.py:841] (7/8) Epoch 4, validation: loss=0.1771, simple_loss=0.279, pruned_loss=0.03761, over 698248.00 frames.
+2022-05-14 00:54:36,398 INFO [train.py:812] (7/8) Epoch 4, batch 3050, loss[loss=0.2367, simple_loss=0.3192, pruned_loss=0.07714, over 7117.00 frames.], tot_loss[loss=0.229, simple_loss=0.3037, pruned_loss=0.07713, over 1420524.71 frames.], batch size: 21, lr: 1.51e-03
+2022-05-14 00:55:35,301 INFO [train.py:812] (7/8) Epoch 4, batch 3100, loss[loss=0.2263, simple_loss=0.3023, pruned_loss=0.07516, over 7286.00 frames.], tot_loss[loss=0.2271, simple_loss=0.3019, pruned_loss=0.0761, over 1417285.16 frames.], batch size: 24, lr: 1.51e-03
+2022-05-14 00:56:35,167 INFO [train.py:812] (7/8) Epoch 4, batch 3150, loss[loss=0.2315, simple_loss=0.3188, pruned_loss=0.07205, over 7310.00 frames.], tot_loss[loss=0.2259, simple_loss=0.301, pruned_loss=0.0754, over 1421479.11 frames.], batch size: 25, lr: 1.51e-03
+2022-05-14 00:57:33,615 INFO [train.py:812] (7/8) Epoch 4, batch 3200, loss[loss=0.2023, simple_loss=0.2787, pruned_loss=0.06291, over 7069.00 frames.], tot_loss[loss=0.226, simple_loss=0.301, pruned_loss=0.07543, over 1422320.94 frames.], batch size: 18, lr: 1.51e-03
+2022-05-14 00:58:32,707 INFO [train.py:812] (7/8) Epoch 4, batch 3250, loss[loss=0.2253, simple_loss=0.303, pruned_loss=0.07385, over 7259.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3024, pruned_loss=0.07651, over 1422914.64 frames.], batch size: 19, lr: 1.51e-03
+2022-05-14 00:59:30,524 INFO [train.py:812] (7/8) Epoch 4, batch 3300, loss[loss=0.2334, simple_loss=0.3049, pruned_loss=0.08098, over 7200.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3016, pruned_loss=0.07573, over 1421762.23 frames.], batch size: 23, lr: 1.50e-03
+2022-05-14 01:00:29,657 INFO [train.py:812] (7/8) Epoch 4, batch 3350, loss[loss=0.2845, simple_loss=0.3602, pruned_loss=0.1044, over 6225.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3002, pruned_loss=0.07482, over 1419980.07 frames.], batch size: 37, lr: 1.50e-03
+2022-05-14 01:01:28,345 INFO [train.py:812] (7/8) Epoch 4, batch 3400, loss[loss=0.1749, simple_loss=0.2492, pruned_loss=0.05027, over 6990.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3003, pruned_loss=0.07562, over 1421287.87 frames.], batch size: 16, lr: 1.50e-03
+2022-05-14 01:02:28,076 INFO [train.py:812] (7/8) Epoch 4, batch 3450, loss[loss=0.1934, simple_loss=0.2767, pruned_loss=0.05506, over 7155.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3002, pruned_loss=0.07551, over 1426677.45 frames.], batch size: 18, lr: 1.50e-03
+2022-05-14 01:03:26,399 INFO [train.py:812] (7/8) Epoch 4, batch 3500, loss[loss=0.2252, simple_loss=0.3154, pruned_loss=0.06746, over 7384.00 frames.], tot_loss[loss=0.2255, simple_loss=0.3003, pruned_loss=0.07535, over 1428604.93 frames.], batch size: 23, lr: 1.50e-03
+2022-05-14 01:04:26,038 INFO [train.py:812] (7/8) Epoch 4, batch 3550, loss[loss=0.2137, simple_loss=0.2902, pruned_loss=0.06855, over 7299.00 frames.], tot_loss[loss=0.2239, simple_loss=0.2987, pruned_loss=0.07451, over 1429790.06 frames.], batch size: 24, lr: 1.49e-03
+2022-05-14 01:05:25,254 INFO [train.py:812] (7/8) Epoch 4, batch 3600, loss[loss=0.1862, simple_loss=0.2599, pruned_loss=0.05619, over 6985.00 frames.], tot_loss[loss=0.2236, simple_loss=0.2989, pruned_loss=0.07421, over 1427857.52 frames.], batch size: 16, lr: 1.49e-03
+2022-05-14 01:06:24,773 INFO [train.py:812] (7/8) Epoch 4, batch 3650, loss[loss=0.1794, simple_loss=0.2525, pruned_loss=0.05319, over 7129.00 frames.], tot_loss[loss=0.2245, simple_loss=0.2995, pruned_loss=0.07475, over 1428042.81 frames.], batch size: 17, lr: 1.49e-03
+2022-05-14 01:07:24,242 INFO [train.py:812] (7/8) Epoch 4, batch 3700, loss[loss=0.2096, simple_loss=0.2703, pruned_loss=0.07451, over 7003.00 frames.], tot_loss[loss=0.2237, simple_loss=0.2987, pruned_loss=0.07433, over 1427428.75 frames.], batch size: 16, lr: 1.49e-03
+2022-05-14 01:08:24,389 INFO [train.py:812] (7/8) Epoch 4, batch 3750, loss[loss=0.1969, simple_loss=0.2756, pruned_loss=0.05912, over 7429.00 frames.], tot_loss[loss=0.2231, simple_loss=0.2977, pruned_loss=0.07421, over 1425669.65 frames.], batch size: 20, lr: 1.49e-03
+2022-05-14 01:09:22,791 INFO [train.py:812] (7/8) Epoch 4, batch 3800, loss[loss=0.2225, simple_loss=0.295, pruned_loss=0.07496, over 7451.00 frames.], tot_loss[loss=0.2229, simple_loss=0.2982, pruned_loss=0.07381, over 1422303.62 frames.], batch size: 19, lr: 1.48e-03
+2022-05-14 01:10:22,630 INFO [train.py:812] (7/8) Epoch 4, batch 3850, loss[loss=0.2247, simple_loss=0.2859, pruned_loss=0.08172, over 7414.00 frames.], tot_loss[loss=0.2229, simple_loss=0.298, pruned_loss=0.07386, over 1426221.41 frames.], batch size: 18, lr: 1.48e-03
+2022-05-14 01:11:21,445 INFO [train.py:812] (7/8) Epoch 4, batch 3900, loss[loss=0.3202, simple_loss=0.3519, pruned_loss=0.1442, over 4715.00 frames.], tot_loss[loss=0.2232, simple_loss=0.2985, pruned_loss=0.07399, over 1427280.56 frames.], batch size: 52, lr: 1.48e-03
+2022-05-14 01:12:20,543 INFO [train.py:812] (7/8) Epoch 4, batch 3950, loss[loss=0.1887, simple_loss=0.2562, pruned_loss=0.06064, over 6786.00 frames.], tot_loss[loss=0.2233, simple_loss=0.2981, pruned_loss=0.07425, over 1425879.89 frames.], batch size: 15, lr: 1.48e-03
+2022-05-14 01:13:19,429 INFO [train.py:812] (7/8) Epoch 4, batch 4000, loss[loss=0.2073, simple_loss=0.2967, pruned_loss=0.05893, over 7217.00 frames.], tot_loss[loss=0.224, simple_loss=0.2987, pruned_loss=0.07464, over 1418114.49 frames.], batch size: 21, lr: 1.48e-03
+2022-05-14 01:14:19,006 INFO [train.py:812] (7/8) Epoch 4, batch 4050, loss[loss=0.3022, simple_loss=0.3656, pruned_loss=0.1195, over 7406.00 frames.], tot_loss[loss=0.2239, simple_loss=0.2991, pruned_loss=0.07436, over 1419834.63 frames.], batch size: 21, lr: 1.47e-03
+2022-05-14 01:15:18,257 INFO [train.py:812] (7/8) Epoch 4, batch 4100, loss[loss=0.2701, simple_loss=0.3346, pruned_loss=0.1028, over 6511.00 frames.], tot_loss[loss=0.2237, simple_loss=0.2992, pruned_loss=0.07415, over 1421582.65 frames.], batch size: 38, lr: 1.47e-03
+2022-05-14 01:16:17,181 INFO [train.py:812] (7/8) Epoch 4, batch 4150, loss[loss=0.176, simple_loss=0.2477, pruned_loss=0.05214, over 7443.00 frames.], tot_loss[loss=0.2226, simple_loss=0.2983, pruned_loss=0.07348, over 1423746.63 frames.], batch size: 17, lr: 1.47e-03
+2022-05-14 01:17:15,933 INFO [train.py:812] (7/8) Epoch 4, batch 4200, loss[loss=0.2266, simple_loss=0.3074, pruned_loss=0.07288, over 7153.00 frames.], tot_loss[loss=0.2229, simple_loss=0.2983, pruned_loss=0.07377, over 1422170.61 frames.], batch size: 19, lr: 1.47e-03
+2022-05-14 01:18:15,853 INFO [train.py:812] (7/8) Epoch 4, batch 4250, loss[loss=0.1846, simple_loss=0.2556, pruned_loss=0.05681, over 7361.00 frames.], tot_loss[loss=0.2232, simple_loss=0.2977, pruned_loss=0.07437, over 1414097.88 frames.], batch size: 19, lr: 1.47e-03
+2022-05-14 01:19:14,787 INFO [train.py:812] (7/8) Epoch 4, batch 4300, loss[loss=0.2189, simple_loss=0.2873, pruned_loss=0.07527, over 7346.00 frames.], tot_loss[loss=0.2232, simple_loss=0.297, pruned_loss=0.07469, over 1412749.70 frames.], batch size: 19, lr: 1.47e-03
+2022-05-14 01:20:14,312 INFO [train.py:812] (7/8) Epoch 4, batch 4350, loss[loss=0.2453, simple_loss=0.3164, pruned_loss=0.0871, over 6209.00 frames.], tot_loss[loss=0.2221, simple_loss=0.2958, pruned_loss=0.07421, over 1410940.94 frames.], batch size: 37, lr: 1.46e-03
+2022-05-14 01:21:13,840 INFO [train.py:812] (7/8) Epoch 4, batch 4400, loss[loss=0.2067, simple_loss=0.2829, pruned_loss=0.0652, over 7463.00 frames.], tot_loss[loss=0.2222, simple_loss=0.2955, pruned_loss=0.0745, over 1410657.08 frames.], batch size: 19, lr: 1.46e-03
+2022-05-14 01:22:13,456 INFO [train.py:812] (7/8) Epoch 4, batch 4450, loss[loss=0.2253, simple_loss=0.3107, pruned_loss=0.07, over 7388.00 frames.], tot_loss[loss=0.2221, simple_loss=0.2952, pruned_loss=0.07449, over 1402414.26 frames.], batch size: 23, lr: 1.46e-03
+2022-05-14 01:23:11,899 INFO [train.py:812] (7/8) Epoch 4, batch 4500, loss[loss=0.2986, simple_loss=0.3544, pruned_loss=0.1215, over 6211.00 frames.], tot_loss[loss=0.2224, simple_loss=0.2954, pruned_loss=0.07474, over 1397112.56 frames.], batch size: 37, lr: 1.46e-03
+2022-05-14 01:24:10,649 INFO [train.py:812] (7/8) Epoch 4, batch 4550, loss[loss=0.2493, simple_loss=0.3168, pruned_loss=0.09085, over 5102.00 frames.], tot_loss[loss=0.2266, simple_loss=0.2995, pruned_loss=0.07687, over 1362259.53 frames.], batch size: 53, lr: 1.46e-03
+2022-05-14 01:25:17,921 INFO [train.py:812] (7/8) Epoch 5, batch 0, loss[loss=0.223, simple_loss=0.3007, pruned_loss=0.07268, over 7198.00 frames.], tot_loss[loss=0.223, simple_loss=0.3007, pruned_loss=0.07268, over 7198.00 frames.], batch size: 23, lr: 1.40e-03
+2022-05-14 01:26:16,039 INFO [train.py:812] (7/8) Epoch 5, batch 50, loss[loss=0.2176, simple_loss=0.308, pruned_loss=0.06365, over 7343.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2947, pruned_loss=0.06971, over 321662.76 frames.], batch size: 22, lr: 1.40e-03
+2022-05-14 01:27:13,795 INFO [train.py:812] (7/8) Epoch 5, batch 100, loss[loss=0.2487, simple_loss=0.3244, pruned_loss=0.08649, over 7344.00 frames.], tot_loss[loss=0.2214, simple_loss=0.2981, pruned_loss=0.0724, over 567286.24 frames.], batch size: 22, lr: 1.40e-03
+2022-05-14 01:28:13,037 INFO [train.py:812] (7/8) Epoch 5, batch 150, loss[loss=0.2586, simple_loss=0.3185, pruned_loss=0.09933, over 5061.00 frames.], tot_loss[loss=0.2206, simple_loss=0.2981, pruned_loss=0.07157, over 755312.06 frames.], batch size: 52, lr: 1.40e-03
+2022-05-14 01:29:12,411 INFO [train.py:812] (7/8) Epoch 5, batch 200, loss[loss=0.2315, simple_loss=0.3084, pruned_loss=0.07725, over 7158.00 frames.], tot_loss[loss=0.2199, simple_loss=0.2976, pruned_loss=0.07111, over 903659.59 frames.], batch size: 19, lr: 1.40e-03
+2022-05-14 01:30:11,990 INFO [train.py:812] (7/8) Epoch 5, batch 250, loss[loss=0.293, simple_loss=0.3612, pruned_loss=0.1124, over 7334.00 frames.], tot_loss[loss=0.223, simple_loss=0.3009, pruned_loss=0.0725, over 1021990.85 frames.], batch size: 22, lr: 1.39e-03
+2022-05-14 01:31:10,350 INFO [train.py:812] (7/8) Epoch 5, batch 300, loss[loss=0.2081, simple_loss=0.271, pruned_loss=0.07265, over 7280.00 frames.], tot_loss[loss=0.2203, simple_loss=0.2979, pruned_loss=0.07132, over 1114101.97 frames.], batch size: 17, lr: 1.39e-03
+2022-05-14 01:32:09,264 INFO [train.py:812] (7/8) Epoch 5, batch 350, loss[loss=0.2207, simple_loss=0.304, pruned_loss=0.06873, over 7160.00 frames.], tot_loss[loss=0.2188, simple_loss=0.2962, pruned_loss=0.07064, over 1182708.51 frames.], batch size: 19, lr: 1.39e-03
+2022-05-14 01:33:06,941 INFO [train.py:812] (7/8) Epoch 5, batch 400, loss[loss=0.2164, simple_loss=0.3016, pruned_loss=0.06564, over 7124.00 frames.], tot_loss[loss=0.2189, simple_loss=0.2961, pruned_loss=0.0709, over 1233421.10 frames.], batch size: 28, lr: 1.39e-03
+2022-05-14 01:34:05,743 INFO [train.py:812] (7/8) Epoch 5, batch 450, loss[loss=0.2356, simple_loss=0.3167, pruned_loss=0.07722, over 7042.00 frames.], tot_loss[loss=0.219, simple_loss=0.2957, pruned_loss=0.07118, over 1274332.31 frames.], batch size: 28, lr: 1.39e-03
+2022-05-14 01:35:05,185 INFO [train.py:812] (7/8) Epoch 5, batch 500, loss[loss=0.2335, simple_loss=0.3181, pruned_loss=0.07442, over 7325.00 frames.], tot_loss[loss=0.2177, simple_loss=0.2949, pruned_loss=0.07027, over 1309187.20 frames.], batch size: 21, lr: 1.39e-03
+2022-05-14 01:36:04,783 INFO [train.py:812] (7/8) Epoch 5, batch 550, loss[loss=0.2464, simple_loss=0.3226, pruned_loss=0.08504, over 6710.00 frames.], tot_loss[loss=0.2181, simple_loss=0.2949, pruned_loss=0.07068, over 1334513.86 frames.], batch size: 31, lr: 1.38e-03
+2022-05-14 01:37:04,115 INFO [train.py:812] (7/8) Epoch 5, batch 600, loss[loss=0.2113, simple_loss=0.2768, pruned_loss=0.07288, over 7009.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2939, pruned_loss=0.07017, over 1355843.33 frames.], batch size: 16, lr: 1.38e-03
+2022-05-14 01:38:03,199 INFO [train.py:812] (7/8) Epoch 5, batch 650, loss[loss=0.2001, simple_loss=0.2823, pruned_loss=0.05894, over 7317.00 frames.], tot_loss[loss=0.2179, simple_loss=0.2945, pruned_loss=0.07062, over 1370901.94 frames.], batch size: 20, lr: 1.38e-03
+2022-05-14 01:39:02,118 INFO [train.py:812] (7/8) Epoch 5, batch 700, loss[loss=0.2778, simple_loss=0.3621, pruned_loss=0.09671, over 7290.00 frames.], tot_loss[loss=0.2188, simple_loss=0.2953, pruned_loss=0.07117, over 1380336.71 frames.], batch size: 25, lr: 1.38e-03
+2022-05-14 01:40:01,984 INFO [train.py:812] (7/8) Epoch 5, batch 750, loss[loss=0.2065, simple_loss=0.2744, pruned_loss=0.06928, over 7070.00 frames.], tot_loss[loss=0.2182, simple_loss=0.2943, pruned_loss=0.07106, over 1384891.37 frames.], batch size: 18, lr: 1.38e-03
+2022-05-14 01:40:59,765 INFO [train.py:812] (7/8) Epoch 5, batch 800, loss[loss=0.1924, simple_loss=0.2649, pruned_loss=0.05999, over 7074.00 frames.], tot_loss[loss=0.2161, simple_loss=0.292, pruned_loss=0.07012, over 1395800.12 frames.], batch size: 18, lr: 1.38e-03
+2022-05-14 01:41:57,366 INFO [train.py:812] (7/8) Epoch 5, batch 850, loss[loss=0.2086, simple_loss=0.2861, pruned_loss=0.06557, over 7073.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2912, pruned_loss=0.06919, over 1395618.97 frames.], batch size: 18, lr: 1.37e-03
+2022-05-14 01:42:55,845 INFO [train.py:812] (7/8) Epoch 5, batch 900, loss[loss=0.2421, simple_loss=0.3152, pruned_loss=0.08451, over 7317.00 frames.], tot_loss[loss=0.2152, simple_loss=0.2917, pruned_loss=0.06941, over 1403112.96 frames.], batch size: 21, lr: 1.37e-03
+2022-05-14 01:43:53,358 INFO [train.py:812] (7/8) Epoch 5, batch 950, loss[loss=0.2363, simple_loss=0.3177, pruned_loss=0.07747, over 7007.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2928, pruned_loss=0.06987, over 1406006.36 frames.], batch size: 28, lr: 1.37e-03
+2022-05-14 01:44:52,037 INFO [train.py:812] (7/8) Epoch 5, batch 1000, loss[loss=0.1814, simple_loss=0.2494, pruned_loss=0.05668, over 7062.00 frames.], tot_loss[loss=0.2152, simple_loss=0.2918, pruned_loss=0.06929, over 1410382.27 frames.], batch size: 18, lr: 1.37e-03
+2022-05-14 01:45:49,440 INFO [train.py:812] (7/8) Epoch 5, batch 1050, loss[loss=0.209, simple_loss=0.2883, pruned_loss=0.06485, over 7294.00 frames.], tot_loss[loss=0.2165, simple_loss=0.293, pruned_loss=0.06997, over 1416296.63 frames.], batch size: 24, lr: 1.37e-03
+2022-05-14 01:46:47,350 INFO [train.py:812] (7/8) Epoch 5, batch 1100, loss[loss=0.226, simple_loss=0.3019, pruned_loss=0.07511, over 6379.00 frames.], tot_loss[loss=0.2188, simple_loss=0.2951, pruned_loss=0.07121, over 1412160.06 frames.], batch size: 37, lr: 1.37e-03
+2022-05-14 01:47:47,058 INFO [train.py:812] (7/8) Epoch 5, batch 1150, loss[loss=0.2426, simple_loss=0.3169, pruned_loss=0.08418, over 7432.00 frames.], tot_loss[loss=0.2196, simple_loss=0.2963, pruned_loss=0.07148, over 1415235.00 frames.], batch size: 20, lr: 1.36e-03
+2022-05-14 01:48:45,965 INFO [train.py:812] (7/8) Epoch 5, batch 1200, loss[loss=0.2522, simple_loss=0.3229, pruned_loss=0.09072, over 6296.00 frames.], tot_loss[loss=0.2193, simple_loss=0.2957, pruned_loss=0.0715, over 1417048.23 frames.], batch size: 37, lr: 1.36e-03
+2022-05-14 01:49:45,461 INFO [train.py:812] (7/8) Epoch 5, batch 1250, loss[loss=0.1787, simple_loss=0.2683, pruned_loss=0.04453, over 7257.00 frames.], tot_loss[loss=0.2201, simple_loss=0.2964, pruned_loss=0.07184, over 1413209.27 frames.], batch size: 19, lr: 1.36e-03
+2022-05-14 01:50:43,678 INFO [train.py:812] (7/8) Epoch 5, batch 1300, loss[loss=0.2135, simple_loss=0.2969, pruned_loss=0.06507, over 7330.00 frames.], tot_loss[loss=0.2202, simple_loss=0.2973, pruned_loss=0.0716, over 1416536.34 frames.], batch size: 20, lr: 1.36e-03
+2022-05-14 01:51:42,416 INFO [train.py:812] (7/8) Epoch 5, batch 1350, loss[loss=0.1936, simple_loss=0.264, pruned_loss=0.06162, over 7146.00 frames.], tot_loss[loss=0.2185, simple_loss=0.2958, pruned_loss=0.07059, over 1423412.35 frames.], batch size: 17, lr: 1.36e-03
+2022-05-14 01:52:39,834 INFO [train.py:812] (7/8) Epoch 5, batch 1400, loss[loss=0.2364, simple_loss=0.3108, pruned_loss=0.08098, over 7245.00 frames.], tot_loss[loss=0.2195, simple_loss=0.2967, pruned_loss=0.07117, over 1419229.54 frames.], batch size: 20, lr: 1.36e-03
+2022-05-14 01:53:37,471 INFO [train.py:812] (7/8) Epoch 5, batch 1450, loss[loss=0.1925, simple_loss=0.2717, pruned_loss=0.0566, over 6995.00 frames.], tot_loss[loss=0.2193, simple_loss=0.297, pruned_loss=0.07076, over 1419545.57 frames.], batch size: 16, lr: 1.35e-03
+2022-05-14 01:54:35,107 INFO [train.py:812] (7/8) Epoch 5, batch 1500, loss[loss=0.2212, simple_loss=0.3024, pruned_loss=0.06997, over 7326.00 frames.], tot_loss[loss=0.2182, simple_loss=0.2958, pruned_loss=0.07028, over 1422844.31 frames.], batch size: 20, lr: 1.35e-03
+2022-05-14 01:55:34,694 INFO [train.py:812] (7/8) Epoch 5, batch 1550, loss[loss=0.2338, simple_loss=0.31, pruned_loss=0.0788, over 7380.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2942, pruned_loss=0.07003, over 1424747.97 frames.], batch size: 23, lr: 1.35e-03
+2022-05-14 01:56:33,061 INFO [train.py:812] (7/8) Epoch 5, batch 1600, loss[loss=0.2276, simple_loss=0.3083, pruned_loss=0.0734, over 7312.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2942, pruned_loss=0.07027, over 1424061.31 frames.], batch size: 25, lr: 1.35e-03
+2022-05-14 01:57:37,145 INFO [train.py:812] (7/8) Epoch 5, batch 1650, loss[loss=0.2424, simple_loss=0.3242, pruned_loss=0.08025, over 7125.00 frames.], tot_loss[loss=0.2183, simple_loss=0.2952, pruned_loss=0.07067, over 1421811.75 frames.], batch size: 21, lr: 1.35e-03
+2022-05-14 01:58:36,694 INFO [train.py:812] (7/8) Epoch 5, batch 1700, loss[loss=0.2079, simple_loss=0.2864, pruned_loss=0.06472, over 7343.00 frames.], tot_loss[loss=0.2185, simple_loss=0.2954, pruned_loss=0.07077, over 1423689.52 frames.], batch size: 22, lr: 1.35e-03
+2022-05-14 01:59:35,639 INFO [train.py:812] (7/8) Epoch 5, batch 1750, loss[loss=0.2236, simple_loss=0.309, pruned_loss=0.06904, over 7289.00 frames.], tot_loss[loss=0.2182, simple_loss=0.2952, pruned_loss=0.07063, over 1423330.72 frames.], batch size: 24, lr: 1.34e-03
+2022-05-14 02:00:34,978 INFO [train.py:812] (7/8) Epoch 5, batch 1800, loss[loss=0.2059, simple_loss=0.2923, pruned_loss=0.05978, over 7325.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2946, pruned_loss=0.07016, over 1425371.90 frames.], batch size: 21, lr: 1.34e-03
+2022-05-14 02:01:33,502 INFO [train.py:812] (7/8) Epoch 5, batch 1850, loss[loss=0.2375, simple_loss=0.3181, pruned_loss=0.07847, over 6322.00 frames.], tot_loss[loss=0.2179, simple_loss=0.2952, pruned_loss=0.07029, over 1425912.23 frames.], batch size: 37, lr: 1.34e-03
+2022-05-14 02:02:31,921 INFO [train.py:812] (7/8) Epoch 5, batch 1900, loss[loss=0.2128, simple_loss=0.2929, pruned_loss=0.06638, over 7127.00 frames.], tot_loss[loss=0.2183, simple_loss=0.2957, pruned_loss=0.07045, over 1427315.99 frames.], batch size: 21, lr: 1.34e-03
+2022-05-14 02:03:30,612 INFO [train.py:812] (7/8) Epoch 5, batch 1950, loss[loss=0.1764, simple_loss=0.2601, pruned_loss=0.0464, over 7162.00 frames.], tot_loss[loss=0.217, simple_loss=0.295, pruned_loss=0.06953, over 1428305.59 frames.], batch size: 18, lr: 1.34e-03
+2022-05-14 02:04:28,261 INFO [train.py:812] (7/8) Epoch 5, batch 2000, loss[loss=0.2349, simple_loss=0.3175, pruned_loss=0.07618, over 7281.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2945, pruned_loss=0.06957, over 1426189.01 frames.], batch size: 25, lr: 1.34e-03
+2022-05-14 02:05:26,877 INFO [train.py:812] (7/8) Epoch 5, batch 2050, loss[loss=0.2111, simple_loss=0.2946, pruned_loss=0.06383, over 7302.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2943, pruned_loss=0.06923, over 1431258.23 frames.], batch size: 24, lr: 1.34e-03
+2022-05-14 02:06:25,396 INFO [train.py:812] (7/8) Epoch 5, batch 2100, loss[loss=0.1993, simple_loss=0.2644, pruned_loss=0.06709, over 7408.00 frames.], tot_loss[loss=0.216, simple_loss=0.2941, pruned_loss=0.06896, over 1433949.22 frames.], batch size: 18, lr: 1.33e-03
+2022-05-14 02:07:23,987 INFO [train.py:812] (7/8) Epoch 5, batch 2150, loss[loss=0.2167, simple_loss=0.2916, pruned_loss=0.07091, over 7071.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2956, pruned_loss=0.06952, over 1432479.51 frames.], batch size: 18, lr: 1.33e-03
+2022-05-14 02:08:21,820 INFO [train.py:812] (7/8) Epoch 5, batch 2200, loss[loss=0.2278, simple_loss=0.3203, pruned_loss=0.06766, over 7337.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2946, pruned_loss=0.06928, over 1434211.33 frames.], batch size: 22, lr: 1.33e-03
+2022-05-14 02:09:20,800 INFO [train.py:812] (7/8) Epoch 5, batch 2250, loss[loss=0.2214, simple_loss=0.2993, pruned_loss=0.07179, over 7371.00 frames.], tot_loss[loss=0.216, simple_loss=0.2938, pruned_loss=0.06908, over 1431807.20 frames.], batch size: 23, lr: 1.33e-03
+2022-05-14 02:10:20,211 INFO [train.py:812] (7/8) Epoch 5, batch 2300, loss[loss=0.1849, simple_loss=0.261, pruned_loss=0.05441, over 7272.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2935, pruned_loss=0.06903, over 1430814.15 frames.], batch size: 17, lr: 1.33e-03
+2022-05-14 02:11:19,009 INFO [train.py:812] (7/8) Epoch 5, batch 2350, loss[loss=0.1944, simple_loss=0.2709, pruned_loss=0.059, over 7429.00 frames.], tot_loss[loss=0.2151, simple_loss=0.293, pruned_loss=0.06858, over 1434164.29 frames.], batch size: 18, lr: 1.33e-03
+2022-05-14 02:12:18,607 INFO [train.py:812] (7/8) Epoch 5, batch 2400, loss[loss=0.1972, simple_loss=0.2785, pruned_loss=0.05799, over 7223.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2928, pruned_loss=0.06901, over 1436460.12 frames.], batch size: 21, lr: 1.32e-03
+2022-05-14 02:13:16,817 INFO [train.py:812] (7/8) Epoch 5, batch 2450, loss[loss=0.1704, simple_loss=0.2568, pruned_loss=0.04203, over 7277.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2931, pruned_loss=0.06876, over 1435707.93 frames.], batch size: 18, lr: 1.32e-03
+2022-05-14 02:14:14,147 INFO [train.py:812] (7/8) Epoch 5, batch 2500, loss[loss=0.2135, simple_loss=0.2773, pruned_loss=0.07484, over 7189.00 frames.], tot_loss[loss=0.2152, simple_loss=0.2929, pruned_loss=0.06872, over 1433106.42 frames.], batch size: 22, lr: 1.32e-03
+2022-05-14 02:15:13,134 INFO [train.py:812] (7/8) Epoch 5, batch 2550, loss[loss=0.2495, simple_loss=0.3206, pruned_loss=0.08918, over 7143.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2923, pruned_loss=0.06804, over 1433406.44 frames.], batch size: 20, lr: 1.32e-03
+2022-05-14 02:16:11,221 INFO [train.py:812] (7/8) Epoch 5, batch 2600, loss[loss=0.2155, simple_loss=0.3054, pruned_loss=0.06278, over 7319.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2932, pruned_loss=0.06852, over 1431441.75 frames.], batch size: 21, lr: 1.32e-03
+2022-05-14 02:17:10,925 INFO [train.py:812] (7/8) Epoch 5, batch 2650, loss[loss=0.186, simple_loss=0.2669, pruned_loss=0.0525, over 6999.00 frames.], tot_loss[loss=0.2152, simple_loss=0.2932, pruned_loss=0.06861, over 1429915.42 frames.], batch size: 16, lr: 1.32e-03
+2022-05-14 02:18:10,476 INFO [train.py:812] (7/8) Epoch 5, batch 2700, loss[loss=0.1897, simple_loss=0.2678, pruned_loss=0.0558, over 7286.00 frames.], tot_loss[loss=0.2143, simple_loss=0.2923, pruned_loss=0.06821, over 1432174.87 frames.], batch size: 18, lr: 1.32e-03
+2022-05-14 02:19:10,241 INFO [train.py:812] (7/8) Epoch 5, batch 2750, loss[loss=0.2236, simple_loss=0.2939, pruned_loss=0.07659, over 7356.00 frames.], tot_loss[loss=0.2141, simple_loss=0.2917, pruned_loss=0.06824, over 1433402.18 frames.], batch size: 19, lr: 1.31e-03
+2022-05-14 02:20:09,529 INFO [train.py:812] (7/8) Epoch 5, batch 2800, loss[loss=0.1677, simple_loss=0.2443, pruned_loss=0.04558, over 7128.00 frames.], tot_loss[loss=0.2126, simple_loss=0.2906, pruned_loss=0.06733, over 1434304.05 frames.], batch size: 17, lr: 1.31e-03
+2022-05-14 02:21:07,486 INFO [train.py:812] (7/8) Epoch 5, batch 2850, loss[loss=0.2432, simple_loss=0.3256, pruned_loss=0.08039, over 6661.00 frames.], tot_loss[loss=0.2143, simple_loss=0.2919, pruned_loss=0.06832, over 1430843.93 frames.], batch size: 31, lr: 1.31e-03
+2022-05-14 02:22:06,273 INFO [train.py:812] (7/8) Epoch 5, batch 2900, loss[loss=0.2232, simple_loss=0.305, pruned_loss=0.07072, over 7288.00 frames.], tot_loss[loss=0.2144, simple_loss=0.2921, pruned_loss=0.06837, over 1429009.78 frames.], batch size: 24, lr: 1.31e-03
+2022-05-14 02:23:05,652 INFO [train.py:812] (7/8) Epoch 5, batch 2950, loss[loss=0.235, simple_loss=0.3141, pruned_loss=0.07793, over 7342.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2913, pruned_loss=0.0679, over 1429196.59 frames.], batch size: 22, lr: 1.31e-03
+2022-05-14 02:24:04,493 INFO [train.py:812] (7/8) Epoch 5, batch 3000, loss[loss=0.1993, simple_loss=0.2833, pruned_loss=0.05763, over 7165.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2916, pruned_loss=0.06811, over 1425093.04 frames.], batch size: 26, lr: 1.31e-03
+2022-05-14 02:24:04,495 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 02:24:12,114 INFO [train.py:841] (7/8) Epoch 5, validation: loss=0.1705, simple_loss=0.2732, pruned_loss=0.03391, over 698248.00 frames.
+2022-05-14 02:25:11,818 INFO [train.py:812] (7/8) Epoch 5, batch 3050, loss[loss=0.2417, simple_loss=0.3235, pruned_loss=0.07999, over 7193.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2919, pruned_loss=0.06761, over 1428672.33 frames.], batch size: 22, lr: 1.31e-03
+2022-05-14 02:26:09,583 INFO [train.py:812] (7/8) Epoch 5, batch 3100, loss[loss=0.2189, simple_loss=0.2957, pruned_loss=0.07105, over 7247.00 frames.], tot_loss[loss=0.2138, simple_loss=0.2923, pruned_loss=0.0677, over 1428260.73 frames.], batch size: 20, lr: 1.30e-03
+2022-05-14 02:27:19,090 INFO [train.py:812] (7/8) Epoch 5, batch 3150, loss[loss=0.1997, simple_loss=0.2849, pruned_loss=0.05723, over 7294.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2922, pruned_loss=0.06739, over 1429065.93 frames.], batch size: 25, lr: 1.30e-03
+2022-05-14 02:28:18,329 INFO [train.py:812] (7/8) Epoch 5, batch 3200, loss[loss=0.1999, simple_loss=0.2753, pruned_loss=0.0622, over 7372.00 frames.], tot_loss[loss=0.2138, simple_loss=0.2924, pruned_loss=0.06762, over 1429671.33 frames.], batch size: 19, lr: 1.30e-03
+2022-05-14 02:29:17,264 INFO [train.py:812] (7/8) Epoch 5, batch 3250, loss[loss=0.2218, simple_loss=0.2936, pruned_loss=0.07504, over 7180.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2914, pruned_loss=0.0674, over 1427011.01 frames.], batch size: 18, lr: 1.30e-03
+2022-05-14 02:30:15,425 INFO [train.py:812] (7/8) Epoch 5, batch 3300, loss[loss=0.2283, simple_loss=0.3106, pruned_loss=0.07297, over 7117.00 frames.], tot_loss[loss=0.214, simple_loss=0.2921, pruned_loss=0.06796, over 1422112.84 frames.], batch size: 26, lr: 1.30e-03
+2022-05-14 02:31:14,145 INFO [train.py:812] (7/8) Epoch 5, batch 3350, loss[loss=0.2359, simple_loss=0.3038, pruned_loss=0.08401, over 7125.00 frames.], tot_loss[loss=0.2138, simple_loss=0.2921, pruned_loss=0.06772, over 1424441.79 frames.], batch size: 21, lr: 1.30e-03
+2022-05-14 02:32:12,555 INFO [train.py:812] (7/8) Epoch 5, batch 3400, loss[loss=0.183, simple_loss=0.2709, pruned_loss=0.0476, over 7236.00 frames.], tot_loss[loss=0.2138, simple_loss=0.2926, pruned_loss=0.0675, over 1426797.13 frames.], batch size: 20, lr: 1.30e-03
+2022-05-14 02:33:11,764 INFO [train.py:812] (7/8) Epoch 5, batch 3450, loss[loss=0.2653, simple_loss=0.3474, pruned_loss=0.09161, over 7191.00 frames.], tot_loss[loss=0.215, simple_loss=0.2931, pruned_loss=0.06849, over 1426865.89 frames.], batch size: 23, lr: 1.29e-03
+2022-05-14 02:34:10,793 INFO [train.py:812] (7/8) Epoch 5, batch 3500, loss[loss=0.2201, simple_loss=0.3032, pruned_loss=0.06856, over 7329.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2932, pruned_loss=0.06823, over 1430253.06 frames.], batch size: 20, lr: 1.29e-03
+2022-05-14 02:35:38,325 INFO [train.py:812] (7/8) Epoch 5, batch 3550, loss[loss=0.2522, simple_loss=0.3336, pruned_loss=0.08541, over 7416.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2937, pruned_loss=0.06851, over 1424971.23 frames.], batch size: 21, lr: 1.29e-03
+2022-05-14 02:36:46,061 INFO [train.py:812] (7/8) Epoch 5, batch 3600, loss[loss=0.2281, simple_loss=0.2914, pruned_loss=0.08241, over 7269.00 frames.], tot_loss[loss=0.2147, simple_loss=0.2927, pruned_loss=0.06836, over 1421149.24 frames.], batch size: 19, lr: 1.29e-03
+2022-05-14 02:38:13,296 INFO [train.py:812] (7/8) Epoch 5, batch 3650, loss[loss=0.2201, simple_loss=0.2987, pruned_loss=0.07078, over 6733.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2933, pruned_loss=0.06899, over 1415259.93 frames.], batch size: 31, lr: 1.29e-03
+2022-05-14 02:39:12,944 INFO [train.py:812] (7/8) Epoch 5, batch 3700, loss[loss=0.2088, simple_loss=0.2892, pruned_loss=0.06417, over 7141.00 frames.], tot_loss[loss=0.2127, simple_loss=0.2902, pruned_loss=0.06762, over 1419159.66 frames.], batch size: 18, lr: 1.29e-03
+2022-05-14 02:40:11,655 INFO [train.py:812] (7/8) Epoch 5, batch 3750, loss[loss=0.1714, simple_loss=0.2554, pruned_loss=0.0437, over 7265.00 frames.], tot_loss[loss=0.2127, simple_loss=0.2907, pruned_loss=0.06738, over 1420810.62 frames.], batch size: 16, lr: 1.29e-03
+2022-05-14 02:41:09,968 INFO [train.py:812] (7/8) Epoch 5, batch 3800, loss[loss=0.1946, simple_loss=0.2672, pruned_loss=0.06096, over 7287.00 frames.], tot_loss[loss=0.2143, simple_loss=0.2923, pruned_loss=0.06815, over 1421680.77 frames.], batch size: 18, lr: 1.28e-03
+2022-05-14 02:42:07,632 INFO [train.py:812] (7/8) Epoch 5, batch 3850, loss[loss=0.2059, simple_loss=0.293, pruned_loss=0.05945, over 7417.00 frames.], tot_loss[loss=0.214, simple_loss=0.2921, pruned_loss=0.0679, over 1420760.20 frames.], batch size: 21, lr: 1.28e-03
+2022-05-14 02:43:06,322 INFO [train.py:812] (7/8) Epoch 5, batch 3900, loss[loss=0.2363, simple_loss=0.296, pruned_loss=0.08827, over 7155.00 frames.], tot_loss[loss=0.2127, simple_loss=0.2907, pruned_loss=0.06741, over 1418067.73 frames.], batch size: 18, lr: 1.28e-03
+2022-05-14 02:44:04,256 INFO [train.py:812] (7/8) Epoch 5, batch 3950, loss[loss=0.2084, simple_loss=0.2909, pruned_loss=0.063, over 7411.00 frames.], tot_loss[loss=0.2131, simple_loss=0.291, pruned_loss=0.06761, over 1415540.59 frames.], batch size: 21, lr: 1.28e-03
+2022-05-14 02:45:02,178 INFO [train.py:812] (7/8) Epoch 5, batch 4000, loss[loss=0.1923, simple_loss=0.2632, pruned_loss=0.06071, over 7435.00 frames.], tot_loss[loss=0.2133, simple_loss=0.2915, pruned_loss=0.06755, over 1418351.62 frames.], batch size: 20, lr: 1.28e-03
+2022-05-14 02:46:01,641 INFO [train.py:812] (7/8) Epoch 5, batch 4050, loss[loss=0.2333, simple_loss=0.3193, pruned_loss=0.07368, over 7214.00 frames.], tot_loss[loss=0.2133, simple_loss=0.2915, pruned_loss=0.06754, over 1419733.17 frames.], batch size: 21, lr: 1.28e-03
+2022-05-14 02:46:59,636 INFO [train.py:812] (7/8) Epoch 5, batch 4100, loss[loss=0.2198, simple_loss=0.2825, pruned_loss=0.07853, over 7263.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2938, pruned_loss=0.06854, over 1417122.70 frames.], batch size: 18, lr: 1.28e-03
+2022-05-14 02:47:58,869 INFO [train.py:812] (7/8) Epoch 5, batch 4150, loss[loss=0.2383, simple_loss=0.3084, pruned_loss=0.08413, over 7215.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2941, pruned_loss=0.06922, over 1415180.01 frames.], batch size: 22, lr: 1.27e-03
+2022-05-14 02:48:57,901 INFO [train.py:812] (7/8) Epoch 5, batch 4200, loss[loss=0.2295, simple_loss=0.3001, pruned_loss=0.07949, over 7140.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2939, pruned_loss=0.0691, over 1413709.14 frames.], batch size: 17, lr: 1.27e-03
+2022-05-14 02:49:57,156 INFO [train.py:812] (7/8) Epoch 5, batch 4250, loss[loss=0.1894, simple_loss=0.2733, pruned_loss=0.05277, over 7081.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2948, pruned_loss=0.06965, over 1414860.03 frames.], batch size: 18, lr: 1.27e-03
+2022-05-14 02:50:54,457 INFO [train.py:812] (7/8) Epoch 5, batch 4300, loss[loss=0.2088, simple_loss=0.2874, pruned_loss=0.06508, over 7139.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2948, pruned_loss=0.06942, over 1415691.04 frames.], batch size: 20, lr: 1.27e-03
+2022-05-14 02:51:52,681 INFO [train.py:812] (7/8) Epoch 5, batch 4350, loss[loss=0.2028, simple_loss=0.2927, pruned_loss=0.05645, over 7420.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2947, pruned_loss=0.06912, over 1414991.40 frames.], batch size: 21, lr: 1.27e-03
+2022-05-14 02:52:52,072 INFO [train.py:812] (7/8) Epoch 5, batch 4400, loss[loss=0.1713, simple_loss=0.2653, pruned_loss=0.03871, over 7259.00 frames.], tot_loss[loss=0.2166, simple_loss=0.295, pruned_loss=0.06912, over 1411279.89 frames.], batch size: 19, lr: 1.27e-03
+2022-05-14 02:53:51,764 INFO [train.py:812] (7/8) Epoch 5, batch 4450, loss[loss=0.2299, simple_loss=0.3083, pruned_loss=0.07575, over 6665.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2953, pruned_loss=0.06944, over 1405514.15 frames.], batch size: 31, lr: 1.27e-03
+2022-05-14 02:54:49,543 INFO [train.py:812] (7/8) Epoch 5, batch 4500, loss[loss=0.2553, simple_loss=0.3369, pruned_loss=0.08681, over 5142.00 frames.], tot_loss[loss=0.2179, simple_loss=0.2963, pruned_loss=0.06973, over 1395239.79 frames.], batch size: 52, lr: 1.27e-03
+2022-05-14 02:55:48,821 INFO [train.py:812] (7/8) Epoch 5, batch 4550, loss[loss=0.261, simple_loss=0.3246, pruned_loss=0.09865, over 4651.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2997, pruned_loss=0.07287, over 1339486.28 frames.], batch size: 52, lr: 1.26e-03
+2022-05-14 02:56:57,123 INFO [train.py:812] (7/8) Epoch 6, batch 0, loss[loss=0.201, simple_loss=0.2822, pruned_loss=0.05995, over 7150.00 frames.], tot_loss[loss=0.201, simple_loss=0.2822, pruned_loss=0.05995, over 7150.00 frames.], batch size: 19, lr: 1.21e-03
+2022-05-14 02:57:56,761 INFO [train.py:812] (7/8) Epoch 6, batch 50, loss[loss=0.2674, simple_loss=0.3292, pruned_loss=0.1028, over 4988.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2923, pruned_loss=0.06876, over 319285.96 frames.], batch size: 52, lr: 1.21e-03
+2022-05-14 02:58:56,424 INFO [train.py:812] (7/8) Epoch 6, batch 100, loss[loss=0.2286, simple_loss=0.3037, pruned_loss=0.07673, over 7146.00 frames.], tot_loss[loss=0.215, simple_loss=0.2929, pruned_loss=0.06858, over 562402.31 frames.], batch size: 20, lr: 1.21e-03
+2022-05-14 02:59:55,413 INFO [train.py:812] (7/8) Epoch 6, batch 150, loss[loss=0.2226, simple_loss=0.3046, pruned_loss=0.07027, over 6779.00 frames.], tot_loss[loss=0.215, simple_loss=0.2929, pruned_loss=0.06855, over 750213.10 frames.], batch size: 31, lr: 1.21e-03
+2022-05-14 03:00:54,876 INFO [train.py:812] (7/8) Epoch 6, batch 200, loss[loss=0.1954, simple_loss=0.2625, pruned_loss=0.06411, over 7390.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2919, pruned_loss=0.06718, over 899208.16 frames.], batch size: 18, lr: 1.21e-03
+2022-05-14 03:01:54,438 INFO [train.py:812] (7/8) Epoch 6, batch 250, loss[loss=0.2213, simple_loss=0.304, pruned_loss=0.06936, over 7328.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2898, pruned_loss=0.06501, over 1019282.18 frames.], batch size: 22, lr: 1.21e-03
+2022-05-14 03:02:54,527 INFO [train.py:812] (7/8) Epoch 6, batch 300, loss[loss=0.2431, simple_loss=0.319, pruned_loss=0.08363, over 7247.00 frames.], tot_loss[loss=0.2109, simple_loss=0.2905, pruned_loss=0.06564, over 1112097.38 frames.], batch size: 20, lr: 1.21e-03
+2022-05-14 03:03:51,900 INFO [train.py:812] (7/8) Epoch 6, batch 350, loss[loss=0.2078, simple_loss=0.2982, pruned_loss=0.05873, over 7326.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2897, pruned_loss=0.06579, over 1185036.93 frames.], batch size: 20, lr: 1.20e-03
+2022-05-14 03:04:49,946 INFO [train.py:812] (7/8) Epoch 6, batch 400, loss[loss=0.256, simple_loss=0.326, pruned_loss=0.09299, over 7376.00 frames.], tot_loss[loss=0.2116, simple_loss=0.2911, pruned_loss=0.06605, over 1236768.47 frames.], batch size: 23, lr: 1.20e-03
+2022-05-14 03:05:47,809 INFO [train.py:812] (7/8) Epoch 6, batch 450, loss[loss=0.2114, simple_loss=0.2734, pruned_loss=0.07468, over 6826.00 frames.], tot_loss[loss=0.2113, simple_loss=0.2908, pruned_loss=0.06588, over 1279257.68 frames.], batch size: 15, lr: 1.20e-03
+2022-05-14 03:06:47,306 INFO [train.py:812] (7/8) Epoch 6, batch 500, loss[loss=0.2487, simple_loss=0.3119, pruned_loss=0.09272, over 4866.00 frames.], tot_loss[loss=0.2103, simple_loss=0.29, pruned_loss=0.06532, over 1308122.70 frames.], batch size: 52, lr: 1.20e-03
+2022-05-14 03:07:45,182 INFO [train.py:812] (7/8) Epoch 6, batch 550, loss[loss=0.2806, simple_loss=0.3616, pruned_loss=0.09984, over 6135.00 frames.], tot_loss[loss=0.2115, simple_loss=0.2911, pruned_loss=0.06596, over 1331809.57 frames.], batch size: 37, lr: 1.20e-03
+2022-05-14 03:08:44,014 INFO [train.py:812] (7/8) Epoch 6, batch 600, loss[loss=0.1998, simple_loss=0.2851, pruned_loss=0.05726, over 7141.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2888, pruned_loss=0.06489, over 1351108.04 frames.], batch size: 20, lr: 1.20e-03
+2022-05-14 03:09:42,717 INFO [train.py:812] (7/8) Epoch 6, batch 650, loss[loss=0.23, simple_loss=0.3141, pruned_loss=0.07297, over 7412.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2883, pruned_loss=0.06448, over 1365520.28 frames.], batch size: 21, lr: 1.20e-03
+2022-05-14 03:10:42,190 INFO [train.py:812] (7/8) Epoch 6, batch 700, loss[loss=0.1904, simple_loss=0.2686, pruned_loss=0.05604, over 7184.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2879, pruned_loss=0.0642, over 1378076.90 frames.], batch size: 16, lr: 1.20e-03
+2022-05-14 03:11:41,198 INFO [train.py:812] (7/8) Epoch 6, batch 750, loss[loss=0.2097, simple_loss=0.2969, pruned_loss=0.06126, over 7227.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2892, pruned_loss=0.06452, over 1388262.77 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:12:41,110 INFO [train.py:812] (7/8) Epoch 6, batch 800, loss[loss=0.1955, simple_loss=0.2884, pruned_loss=0.05133, over 7224.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2887, pruned_loss=0.06436, over 1398734.03 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:13:40,505 INFO [train.py:812] (7/8) Epoch 6, batch 850, loss[loss=0.2318, simple_loss=0.3096, pruned_loss=0.07701, over 7198.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2897, pruned_loss=0.065, over 1404188.40 frames.], batch size: 23, lr: 1.19e-03
+2022-05-14 03:14:39,829 INFO [train.py:812] (7/8) Epoch 6, batch 900, loss[loss=0.1941, simple_loss=0.2854, pruned_loss=0.05141, over 7417.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2896, pruned_loss=0.06504, over 1406060.54 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:15:38,567 INFO [train.py:812] (7/8) Epoch 6, batch 950, loss[loss=0.1669, simple_loss=0.2459, pruned_loss=0.04399, over 7129.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2884, pruned_loss=0.0643, over 1407307.35 frames.], batch size: 17, lr: 1.19e-03
+2022-05-14 03:16:37,971 INFO [train.py:812] (7/8) Epoch 6, batch 1000, loss[loss=0.2218, simple_loss=0.2994, pruned_loss=0.07212, over 7417.00 frames.], tot_loss[loss=0.209, simple_loss=0.289, pruned_loss=0.0645, over 1408488.19 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:17:36,251 INFO [train.py:812] (7/8) Epoch 6, batch 1050, loss[loss=0.2111, simple_loss=0.2977, pruned_loss=0.06229, over 7346.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2892, pruned_loss=0.06514, over 1413332.66 frames.], batch size: 20, lr: 1.19e-03
+2022-05-14 03:18:39,080 INFO [train.py:812] (7/8) Epoch 6, batch 1100, loss[loss=0.2274, simple_loss=0.3256, pruned_loss=0.06456, over 7311.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2897, pruned_loss=0.06534, over 1408382.81 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:19:37,398 INFO [train.py:812] (7/8) Epoch 6, batch 1150, loss[loss=0.2133, simple_loss=0.2886, pruned_loss=0.06897, over 7141.00 frames.], tot_loss[loss=0.21, simple_loss=0.2901, pruned_loss=0.06498, over 1413207.87 frames.], batch size: 20, lr: 1.19e-03
+2022-05-14 03:20:36,664 INFO [train.py:812] (7/8) Epoch 6, batch 1200, loss[loss=0.2159, simple_loss=0.2952, pruned_loss=0.06834, over 7201.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2892, pruned_loss=0.06493, over 1414357.45 frames.], batch size: 26, lr: 1.18e-03
+2022-05-14 03:21:34,775 INFO [train.py:812] (7/8) Epoch 6, batch 1250, loss[loss=0.1884, simple_loss=0.2815, pruned_loss=0.04765, over 7147.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2895, pruned_loss=0.06493, over 1413564.29 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:22:34,598 INFO [train.py:812] (7/8) Epoch 6, batch 1300, loss[loss=0.1791, simple_loss=0.2598, pruned_loss=0.04916, over 7362.00 frames.], tot_loss[loss=0.2095, simple_loss=0.289, pruned_loss=0.06494, over 1411632.17 frames.], batch size: 19, lr: 1.18e-03
+2022-05-14 03:23:33,482 INFO [train.py:812] (7/8) Epoch 6, batch 1350, loss[loss=0.2526, simple_loss=0.3251, pruned_loss=0.09007, over 7032.00 frames.], tot_loss[loss=0.209, simple_loss=0.2885, pruned_loss=0.06474, over 1415051.08 frames.], batch size: 28, lr: 1.18e-03
+2022-05-14 03:24:32,561 INFO [train.py:812] (7/8) Epoch 6, batch 1400, loss[loss=0.1946, simple_loss=0.2812, pruned_loss=0.05404, over 7315.00 frames.], tot_loss[loss=0.208, simple_loss=0.288, pruned_loss=0.06403, over 1419141.13 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:25:31,700 INFO [train.py:812] (7/8) Epoch 6, batch 1450, loss[loss=0.1679, simple_loss=0.2537, pruned_loss=0.0411, over 7429.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2871, pruned_loss=0.06325, over 1420458.06 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:26:31,168 INFO [train.py:812] (7/8) Epoch 6, batch 1500, loss[loss=0.2041, simple_loss=0.2837, pruned_loss=0.06226, over 7142.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2875, pruned_loss=0.06345, over 1420151.54 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:27:30,181 INFO [train.py:812] (7/8) Epoch 6, batch 1550, loss[loss=0.2067, simple_loss=0.2782, pruned_loss=0.06758, over 7289.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2879, pruned_loss=0.06386, over 1422241.50 frames.], batch size: 17, lr: 1.18e-03
+2022-05-14 03:28:29,769 INFO [train.py:812] (7/8) Epoch 6, batch 1600, loss[loss=0.2278, simple_loss=0.3023, pruned_loss=0.07667, over 7427.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2883, pruned_loss=0.06451, over 1414934.67 frames.], batch size: 20, lr: 1.17e-03
+2022-05-14 03:29:29,264 INFO [train.py:812] (7/8) Epoch 6, batch 1650, loss[loss=0.2525, simple_loss=0.3252, pruned_loss=0.08983, over 7269.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2878, pruned_loss=0.06483, over 1414778.41 frames.], batch size: 25, lr: 1.17e-03
+2022-05-14 03:30:27,832 INFO [train.py:812] (7/8) Epoch 6, batch 1700, loss[loss=0.2207, simple_loss=0.3187, pruned_loss=0.06131, over 7206.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2886, pruned_loss=0.06526, over 1412665.54 frames.], batch size: 22, lr: 1.17e-03
+2022-05-14 03:31:26,919 INFO [train.py:812] (7/8) Epoch 6, batch 1750, loss[loss=0.2092, simple_loss=0.2716, pruned_loss=0.07335, over 7276.00 frames.], tot_loss[loss=0.2109, simple_loss=0.2896, pruned_loss=0.06608, over 1410109.13 frames.], batch size: 18, lr: 1.17e-03
+2022-05-14 03:32:26,467 INFO [train.py:812] (7/8) Epoch 6, batch 1800, loss[loss=0.2531, simple_loss=0.3145, pruned_loss=0.09586, over 4865.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2896, pruned_loss=0.06586, over 1411832.66 frames.], batch size: 52, lr: 1.17e-03
+2022-05-14 03:33:25,549 INFO [train.py:812] (7/8) Epoch 6, batch 1850, loss[loss=0.1775, simple_loss=0.2595, pruned_loss=0.04772, over 7150.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2883, pruned_loss=0.06524, over 1414817.26 frames.], batch size: 18, lr: 1.17e-03
+2022-05-14 03:34:24,896 INFO [train.py:812] (7/8) Epoch 6, batch 1900, loss[loss=0.1842, simple_loss=0.2582, pruned_loss=0.05507, over 7133.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2884, pruned_loss=0.06503, over 1413526.33 frames.], batch size: 17, lr: 1.17e-03
+2022-05-14 03:35:23,982 INFO [train.py:812] (7/8) Epoch 6, batch 1950, loss[loss=0.1973, simple_loss=0.2876, pruned_loss=0.05348, over 7099.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2886, pruned_loss=0.06453, over 1418964.44 frames.], batch size: 21, lr: 1.17e-03
+2022-05-14 03:36:21,527 INFO [train.py:812] (7/8) Epoch 6, batch 2000, loss[loss=0.1741, simple_loss=0.2548, pruned_loss=0.04669, over 7276.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2883, pruned_loss=0.06456, over 1423568.22 frames.], batch size: 18, lr: 1.17e-03
+2022-05-14 03:37:19,533 INFO [train.py:812] (7/8) Epoch 6, batch 2050, loss[loss=0.1897, simple_loss=0.2789, pruned_loss=0.05027, over 7088.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2881, pruned_loss=0.06355, over 1424709.50 frames.], batch size: 28, lr: 1.16e-03
+2022-05-14 03:38:19,369 INFO [train.py:812] (7/8) Epoch 6, batch 2100, loss[loss=0.2424, simple_loss=0.3029, pruned_loss=0.09092, over 6565.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2886, pruned_loss=0.06353, over 1426129.50 frames.], batch size: 38, lr: 1.16e-03
+2022-05-14 03:39:18,997 INFO [train.py:812] (7/8) Epoch 6, batch 2150, loss[loss=0.2, simple_loss=0.2888, pruned_loss=0.05557, over 7146.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2882, pruned_loss=0.06297, over 1431240.24 frames.], batch size: 20, lr: 1.16e-03
+2022-05-14 03:40:18,691 INFO [train.py:812] (7/8) Epoch 6, batch 2200, loss[loss=0.2118, simple_loss=0.2967, pruned_loss=0.06341, over 7131.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2875, pruned_loss=0.06291, over 1427516.04 frames.], batch size: 20, lr: 1.16e-03
+2022-05-14 03:41:17,658 INFO [train.py:812] (7/8) Epoch 6, batch 2250, loss[loss=0.2351, simple_loss=0.3051, pruned_loss=0.0825, over 7349.00 frames.], tot_loss[loss=0.207, simple_loss=0.2878, pruned_loss=0.06311, over 1425488.13 frames.], batch size: 19, lr: 1.16e-03
+2022-05-14 03:42:16,668 INFO [train.py:812] (7/8) Epoch 6, batch 2300, loss[loss=0.2359, simple_loss=0.317, pruned_loss=0.07738, over 7300.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2881, pruned_loss=0.0637, over 1422286.49 frames.], batch size: 24, lr: 1.16e-03
+2022-05-14 03:43:15,839 INFO [train.py:812] (7/8) Epoch 6, batch 2350, loss[loss=0.2368, simple_loss=0.307, pruned_loss=0.0833, over 7217.00 frames.], tot_loss[loss=0.207, simple_loss=0.287, pruned_loss=0.06352, over 1422021.09 frames.], batch size: 21, lr: 1.16e-03
+2022-05-14 03:44:15,964 INFO [train.py:812] (7/8) Epoch 6, batch 2400, loss[loss=0.2005, simple_loss=0.2858, pruned_loss=0.05757, over 7329.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2871, pruned_loss=0.06378, over 1422404.44 frames.], batch size: 20, lr: 1.16e-03
+2022-05-14 03:45:14,493 INFO [train.py:812] (7/8) Epoch 6, batch 2450, loss[loss=0.2197, simple_loss=0.3025, pruned_loss=0.06843, over 6896.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2873, pruned_loss=0.06387, over 1421684.10 frames.], batch size: 15, lr: 1.16e-03
+2022-05-14 03:46:13,730 INFO [train.py:812] (7/8) Epoch 6, batch 2500, loss[loss=0.2134, simple_loss=0.299, pruned_loss=0.06386, over 7344.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2872, pruned_loss=0.06366, over 1421240.61 frames.], batch size: 22, lr: 1.15e-03
+2022-05-14 03:47:11,223 INFO [train.py:812] (7/8) Epoch 6, batch 2550, loss[loss=0.1686, simple_loss=0.2488, pruned_loss=0.04427, over 6882.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2875, pruned_loss=0.06356, over 1423004.03 frames.], batch size: 15, lr: 1.15e-03
+2022-05-14 03:48:09,687 INFO [train.py:812] (7/8) Epoch 6, batch 2600, loss[loss=0.257, simple_loss=0.3385, pruned_loss=0.08778, over 7320.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2873, pruned_loss=0.06302, over 1425982.73 frames.], batch size: 21, lr: 1.15e-03
+2022-05-14 03:49:08,338 INFO [train.py:812] (7/8) Epoch 6, batch 2650, loss[loss=0.2417, simple_loss=0.3249, pruned_loss=0.07923, over 7298.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2881, pruned_loss=0.06354, over 1424350.55 frames.], batch size: 25, lr: 1.15e-03
+2022-05-14 03:50:08,419 INFO [train.py:812] (7/8) Epoch 6, batch 2700, loss[loss=0.2064, simple_loss=0.2743, pruned_loss=0.0693, over 6819.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2882, pruned_loss=0.06301, over 1425911.15 frames.], batch size: 15, lr: 1.15e-03
+2022-05-14 03:51:06,491 INFO [train.py:812] (7/8) Epoch 6, batch 2750, loss[loss=0.2085, simple_loss=0.2798, pruned_loss=0.06861, over 7238.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2877, pruned_loss=0.06277, over 1423296.71 frames.], batch size: 20, lr: 1.15e-03
+2022-05-14 03:52:05,543 INFO [train.py:812] (7/8) Epoch 6, batch 2800, loss[loss=0.2066, simple_loss=0.28, pruned_loss=0.06661, over 7280.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2876, pruned_loss=0.06294, over 1421240.07 frames.], batch size: 18, lr: 1.15e-03
+2022-05-14 03:53:03,397 INFO [train.py:812] (7/8) Epoch 6, batch 2850, loss[loss=0.1671, simple_loss=0.2503, pruned_loss=0.04193, over 7277.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2881, pruned_loss=0.06352, over 1418576.76 frames.], batch size: 17, lr: 1.15e-03
+2022-05-14 03:54:00,929 INFO [train.py:812] (7/8) Epoch 6, batch 2900, loss[loss=0.1922, simple_loss=0.2855, pruned_loss=0.04945, over 6644.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2881, pruned_loss=0.06325, over 1420486.17 frames.], batch size: 31, lr: 1.15e-03
+2022-05-14 03:54:58,730 INFO [train.py:812] (7/8) Epoch 6, batch 2950, loss[loss=0.1968, simple_loss=0.2852, pruned_loss=0.05419, over 7146.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2873, pruned_loss=0.06291, over 1419772.65 frames.], batch size: 20, lr: 1.14e-03
+2022-05-14 03:55:55,734 INFO [train.py:812] (7/8) Epoch 6, batch 3000, loss[loss=0.1888, simple_loss=0.281, pruned_loss=0.04827, over 7231.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2881, pruned_loss=0.06322, over 1419172.12 frames.], batch size: 20, lr: 1.14e-03
+2022-05-14 03:55:55,735 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 03:56:03,337 INFO [train.py:841] (7/8) Epoch 6, validation: loss=0.1668, simple_loss=0.2696, pruned_loss=0.03205, over 698248.00 frames.
+2022-05-14 03:57:02,161 INFO [train.py:812] (7/8) Epoch 6, batch 3050, loss[loss=0.2624, simple_loss=0.3271, pruned_loss=0.09881, over 7198.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2874, pruned_loss=0.06274, over 1424784.95 frames.], batch size: 23, lr: 1.14e-03
+2022-05-14 03:58:01,695 INFO [train.py:812] (7/8) Epoch 6, batch 3100, loss[loss=0.1985, simple_loss=0.2807, pruned_loss=0.05814, over 7345.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2858, pruned_loss=0.06269, over 1422829.11 frames.], batch size: 22, lr: 1.14e-03
+2022-05-14 03:58:58,858 INFO [train.py:812] (7/8) Epoch 6, batch 3150, loss[loss=0.2214, simple_loss=0.3039, pruned_loss=0.06944, over 7209.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2876, pruned_loss=0.06349, over 1422677.96 frames.], batch size: 23, lr: 1.14e-03
+2022-05-14 03:59:57,551 INFO [train.py:812] (7/8) Epoch 6, batch 3200, loss[loss=0.232, simple_loss=0.3037, pruned_loss=0.08014, over 7229.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2869, pruned_loss=0.06315, over 1424829.24 frames.], batch size: 21, lr: 1.14e-03
+2022-05-14 04:00:56,311 INFO [train.py:812] (7/8) Epoch 6, batch 3250, loss[loss=0.1722, simple_loss=0.2545, pruned_loss=0.04499, over 7360.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2865, pruned_loss=0.06253, over 1424251.68 frames.], batch size: 19, lr: 1.14e-03
+2022-05-14 04:01:55,510 INFO [train.py:812] (7/8) Epoch 6, batch 3300, loss[loss=0.2434, simple_loss=0.3138, pruned_loss=0.08646, over 7193.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2876, pruned_loss=0.06336, over 1421061.25 frames.], batch size: 23, lr: 1.14e-03
+2022-05-14 04:02:54,526 INFO [train.py:812] (7/8) Epoch 6, batch 3350, loss[loss=0.2013, simple_loss=0.2874, pruned_loss=0.05756, over 7249.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2871, pruned_loss=0.06302, over 1425609.11 frames.], batch size: 19, lr: 1.14e-03
+2022-05-14 04:03:53,920 INFO [train.py:812] (7/8) Epoch 6, batch 3400, loss[loss=0.2185, simple_loss=0.2915, pruned_loss=0.07272, over 7320.00 frames.], tot_loss[loss=0.2054, simple_loss=0.286, pruned_loss=0.06236, over 1425097.42 frames.], batch size: 24, lr: 1.14e-03
+2022-05-14 04:04:52,411 INFO [train.py:812] (7/8) Epoch 6, batch 3450, loss[loss=0.1946, simple_loss=0.278, pruned_loss=0.05557, over 7410.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2875, pruned_loss=0.06307, over 1427933.43 frames.], batch size: 21, lr: 1.13e-03
+2022-05-14 04:05:50,800 INFO [train.py:812] (7/8) Epoch 6, batch 3500, loss[loss=0.2171, simple_loss=0.2995, pruned_loss=0.06733, over 7198.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2863, pruned_loss=0.06248, over 1425334.71 frames.], batch size: 22, lr: 1.13e-03
+2022-05-14 04:06:49,099 INFO [train.py:812] (7/8) Epoch 6, batch 3550, loss[loss=0.2072, simple_loss=0.2878, pruned_loss=0.06334, over 7329.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2871, pruned_loss=0.06293, over 1427717.34 frames.], batch size: 21, lr: 1.13e-03
+2022-05-14 04:07:47,695 INFO [train.py:812] (7/8) Epoch 6, batch 3600, loss[loss=0.1631, simple_loss=0.2497, pruned_loss=0.03826, over 7155.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2867, pruned_loss=0.06254, over 1428908.91 frames.], batch size: 18, lr: 1.13e-03
+2022-05-14 04:08:46,822 INFO [train.py:812] (7/8) Epoch 6, batch 3650, loss[loss=0.194, simple_loss=0.2794, pruned_loss=0.05432, over 7404.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2871, pruned_loss=0.06314, over 1427634.28 frames.], batch size: 21, lr: 1.13e-03
+2022-05-14 04:09:44,241 INFO [train.py:812] (7/8) Epoch 6, batch 3700, loss[loss=0.1803, simple_loss=0.2697, pruned_loss=0.04541, over 7233.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2868, pruned_loss=0.06283, over 1426332.89 frames.], batch size: 20, lr: 1.13e-03
+2022-05-14 04:10:41,379 INFO [train.py:812] (7/8) Epoch 6, batch 3750, loss[loss=0.2081, simple_loss=0.2879, pruned_loss=0.06413, over 7384.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2864, pruned_loss=0.06311, over 1423911.92 frames.], batch size: 23, lr: 1.13e-03
+2022-05-14 04:11:40,671 INFO [train.py:812] (7/8) Epoch 6, batch 3800, loss[loss=0.197, simple_loss=0.29, pruned_loss=0.05202, over 7231.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2858, pruned_loss=0.0629, over 1419750.88 frames.], batch size: 20, lr: 1.13e-03
+2022-05-14 04:12:39,836 INFO [train.py:812] (7/8) Epoch 6, batch 3850, loss[loss=0.2112, simple_loss=0.2987, pruned_loss=0.06181, over 7427.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2871, pruned_loss=0.06335, over 1420132.34 frames.], batch size: 20, lr: 1.13e-03
+2022-05-14 04:13:39,028 INFO [train.py:812] (7/8) Epoch 6, batch 3900, loss[loss=0.1773, simple_loss=0.2489, pruned_loss=0.05291, over 7405.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2872, pruned_loss=0.0635, over 1424548.97 frames.], batch size: 18, lr: 1.13e-03
+2022-05-14 04:14:38,343 INFO [train.py:812] (7/8) Epoch 6, batch 3950, loss[loss=0.1871, simple_loss=0.2691, pruned_loss=0.05257, over 7295.00 frames.], tot_loss[loss=0.205, simple_loss=0.2852, pruned_loss=0.06241, over 1423810.19 frames.], batch size: 24, lr: 1.12e-03
+2022-05-14 04:15:37,096 INFO [train.py:812] (7/8) Epoch 6, batch 4000, loss[loss=0.2183, simple_loss=0.2954, pruned_loss=0.07057, over 7196.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2853, pruned_loss=0.06195, over 1426189.12 frames.], batch size: 23, lr: 1.12e-03
+2022-05-14 04:16:34,899 INFO [train.py:812] (7/8) Epoch 6, batch 4050, loss[loss=0.2334, simple_loss=0.3119, pruned_loss=0.07743, over 7305.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2851, pruned_loss=0.06237, over 1427219.98 frames.], batch size: 24, lr: 1.12e-03
+2022-05-14 04:17:34,634 INFO [train.py:812] (7/8) Epoch 6, batch 4100, loss[loss=0.1741, simple_loss=0.2573, pruned_loss=0.04546, over 7406.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2846, pruned_loss=0.06235, over 1427326.55 frames.], batch size: 18, lr: 1.12e-03
+2022-05-14 04:18:33,851 INFO [train.py:812] (7/8) Epoch 6, batch 4150, loss[loss=0.218, simple_loss=0.3126, pruned_loss=0.06169, over 6808.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2835, pruned_loss=0.06207, over 1427166.97 frames.], batch size: 31, lr: 1.12e-03
+2022-05-14 04:19:32,985 INFO [train.py:812] (7/8) Epoch 6, batch 4200, loss[loss=0.2364, simple_loss=0.3238, pruned_loss=0.0745, over 7113.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2833, pruned_loss=0.06155, over 1428227.15 frames.], batch size: 21, lr: 1.12e-03
+2022-05-14 04:20:33,172 INFO [train.py:812] (7/8) Epoch 6, batch 4250, loss[loss=0.2454, simple_loss=0.341, pruned_loss=0.0749, over 7386.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2834, pruned_loss=0.0614, over 1429118.68 frames.], batch size: 23, lr: 1.12e-03
+2022-05-14 04:21:32,402 INFO [train.py:812] (7/8) Epoch 6, batch 4300, loss[loss=0.1722, simple_loss=0.2531, pruned_loss=0.04565, over 7079.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2839, pruned_loss=0.0618, over 1424665.10 frames.], batch size: 18, lr: 1.12e-03
+2022-05-14 04:22:31,654 INFO [train.py:812] (7/8) Epoch 6, batch 4350, loss[loss=0.1678, simple_loss=0.262, pruned_loss=0.03676, over 7214.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2832, pruned_loss=0.06164, over 1424351.28 frames.], batch size: 21, lr: 1.12e-03
+2022-05-14 04:23:31,448 INFO [train.py:812] (7/8) Epoch 6, batch 4400, loss[loss=0.1896, simple_loss=0.2728, pruned_loss=0.05318, over 7426.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2822, pruned_loss=0.06116, over 1422770.82 frames.], batch size: 20, lr: 1.12e-03
+2022-05-14 04:24:30,588 INFO [train.py:812] (7/8) Epoch 6, batch 4450, loss[loss=0.1779, simple_loss=0.2502, pruned_loss=0.05275, over 7271.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2831, pruned_loss=0.06198, over 1409976.92 frames.], batch size: 17, lr: 1.11e-03
+2022-05-14 04:25:38,570 INFO [train.py:812] (7/8) Epoch 6, batch 4500, loss[loss=0.1943, simple_loss=0.2881, pruned_loss=0.05024, over 7233.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2799, pruned_loss=0.06043, over 1408749.81 frames.], batch size: 20, lr: 1.11e-03
+2022-05-14 04:26:36,439 INFO [train.py:812] (7/8) Epoch 6, batch 4550, loss[loss=0.3064, simple_loss=0.3727, pruned_loss=0.12, over 5067.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2832, pruned_loss=0.06324, over 1358788.16 frames.], batch size: 52, lr: 1.11e-03
+2022-05-14 04:27:44,601 INFO [train.py:812] (7/8) Epoch 7, batch 0, loss[loss=0.172, simple_loss=0.2551, pruned_loss=0.04445, over 7416.00 frames.], tot_loss[loss=0.172, simple_loss=0.2551, pruned_loss=0.04445, over 7416.00 frames.], batch size: 18, lr: 1.07e-03
+2022-05-14 04:28:43,265 INFO [train.py:812] (7/8) Epoch 7, batch 50, loss[loss=0.1912, simple_loss=0.2632, pruned_loss=0.05959, over 7405.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2839, pruned_loss=0.06266, over 322465.78 frames.], batch size: 18, lr: 1.07e-03
+2022-05-14 04:29:42,477 INFO [train.py:812] (7/8) Epoch 7, batch 100, loss[loss=0.176, simple_loss=0.2592, pruned_loss=0.04645, over 7159.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2808, pruned_loss=0.0594, over 567589.31 frames.], batch size: 19, lr: 1.06e-03
+2022-05-14 04:30:41,797 INFO [train.py:812] (7/8) Epoch 7, batch 150, loss[loss=0.2332, simple_loss=0.2971, pruned_loss=0.08463, over 7150.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2836, pruned_loss=0.06138, over 757293.96 frames.], batch size: 19, lr: 1.06e-03
+2022-05-14 04:31:41,632 INFO [train.py:812] (7/8) Epoch 7, batch 200, loss[loss=0.2182, simple_loss=0.3019, pruned_loss=0.06726, over 7355.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2839, pruned_loss=0.06143, over 906100.67 frames.], batch size: 23, lr: 1.06e-03
+2022-05-14 04:32:39,949 INFO [train.py:812] (7/8) Epoch 7, batch 250, loss[loss=0.2002, simple_loss=0.292, pruned_loss=0.05422, over 7142.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2852, pruned_loss=0.06149, over 1021055.50 frames.], batch size: 20, lr: 1.06e-03
+2022-05-14 04:33:39,375 INFO [train.py:812] (7/8) Epoch 7, batch 300, loss[loss=0.1553, simple_loss=0.2341, pruned_loss=0.03832, over 7221.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2849, pruned_loss=0.06126, over 1107104.46 frames.], batch size: 16, lr: 1.06e-03
+2022-05-14 04:34:57,043 INFO [train.py:812] (7/8) Epoch 7, batch 350, loss[loss=0.2036, simple_loss=0.2844, pruned_loss=0.06143, over 7117.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2841, pruned_loss=0.06051, over 1178789.37 frames.], batch size: 21, lr: 1.06e-03
+2022-05-14 04:35:53,876 INFO [train.py:812] (7/8) Epoch 7, batch 400, loss[loss=0.1717, simple_loss=0.2528, pruned_loss=0.04531, over 7174.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2851, pruned_loss=0.061, over 1231631.67 frames.], batch size: 18, lr: 1.06e-03
+2022-05-14 04:37:20,619 INFO [train.py:812] (7/8) Epoch 7, batch 450, loss[loss=0.1852, simple_loss=0.2673, pruned_loss=0.05158, over 7365.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2846, pruned_loss=0.06088, over 1277140.84 frames.], batch size: 19, lr: 1.06e-03
+2022-05-14 04:38:43,175 INFO [train.py:812] (7/8) Epoch 7, batch 500, loss[loss=0.2386, simple_loss=0.3127, pruned_loss=0.08226, over 6513.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2848, pruned_loss=0.06045, over 1306265.58 frames.], batch size: 38, lr: 1.06e-03
+2022-05-14 04:39:42,062 INFO [train.py:812] (7/8) Epoch 7, batch 550, loss[loss=0.1986, simple_loss=0.2809, pruned_loss=0.05814, over 7119.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2837, pruned_loss=0.06042, over 1331036.63 frames.], batch size: 21, lr: 1.06e-03
+2022-05-14 04:40:39,530 INFO [train.py:812] (7/8) Epoch 7, batch 600, loss[loss=0.2094, simple_loss=0.2926, pruned_loss=0.06305, over 7032.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2834, pruned_loss=0.0605, over 1349557.60 frames.], batch size: 28, lr: 1.06e-03
+2022-05-14 04:41:38,904 INFO [train.py:812] (7/8) Epoch 7, batch 650, loss[loss=0.2843, simple_loss=0.3309, pruned_loss=0.1188, over 4610.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2824, pruned_loss=0.06018, over 1364019.53 frames.], batch size: 52, lr: 1.05e-03
+2022-05-14 04:42:37,573 INFO [train.py:812] (7/8) Epoch 7, batch 700, loss[loss=0.1963, simple_loss=0.2801, pruned_loss=0.05627, over 7161.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2825, pruned_loss=0.06009, over 1378176.99 frames.], batch size: 18, lr: 1.05e-03
+2022-05-14 04:43:36,189 INFO [train.py:812] (7/8) Epoch 7, batch 750, loss[loss=0.1965, simple_loss=0.2842, pruned_loss=0.05433, over 6670.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2828, pruned_loss=0.06031, over 1390789.21 frames.], batch size: 31, lr: 1.05e-03
+2022-05-14 04:44:33,678 INFO [train.py:812] (7/8) Epoch 7, batch 800, loss[loss=0.184, simple_loss=0.2742, pruned_loss=0.04694, over 7335.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2827, pruned_loss=0.06054, over 1391232.50 frames.], batch size: 20, lr: 1.05e-03
+2022-05-14 04:45:32,945 INFO [train.py:812] (7/8) Epoch 7, batch 850, loss[loss=0.1973, simple_loss=0.2877, pruned_loss=0.05347, over 7303.00 frames.], tot_loss[loss=0.2013, simple_loss=0.282, pruned_loss=0.06023, over 1398903.01 frames.], batch size: 24, lr: 1.05e-03
+2022-05-14 04:46:32,296 INFO [train.py:812] (7/8) Epoch 7, batch 900, loss[loss=0.2405, simple_loss=0.3193, pruned_loss=0.08086, over 7373.00 frames.], tot_loss[loss=0.2019, simple_loss=0.283, pruned_loss=0.06039, over 1404755.13 frames.], batch size: 23, lr: 1.05e-03
+2022-05-14 04:47:31,125 INFO [train.py:812] (7/8) Epoch 7, batch 950, loss[loss=0.2104, simple_loss=0.2974, pruned_loss=0.06175, over 7371.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2832, pruned_loss=0.06005, over 1408578.24 frames.], batch size: 23, lr: 1.05e-03
+2022-05-14 04:48:29,704 INFO [train.py:812] (7/8) Epoch 7, batch 1000, loss[loss=0.197, simple_loss=0.2832, pruned_loss=0.05538, over 7388.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2822, pruned_loss=0.05971, over 1408950.34 frames.], batch size: 23, lr: 1.05e-03
+2022-05-14 04:49:29,154 INFO [train.py:812] (7/8) Epoch 7, batch 1050, loss[loss=0.193, simple_loss=0.277, pruned_loss=0.05446, over 7165.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2818, pruned_loss=0.05963, over 1416002.97 frames.], batch size: 19, lr: 1.05e-03
+2022-05-14 04:50:29,077 INFO [train.py:812] (7/8) Epoch 7, batch 1100, loss[loss=0.2341, simple_loss=0.3137, pruned_loss=0.07722, over 7289.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2818, pruned_loss=0.05929, over 1420242.26 frames.], batch size: 25, lr: 1.05e-03
+2022-05-14 04:51:28,389 INFO [train.py:812] (7/8) Epoch 7, batch 1150, loss[loss=0.1415, simple_loss=0.2239, pruned_loss=0.02957, over 7129.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2815, pruned_loss=0.05939, over 1418083.98 frames.], batch size: 17, lr: 1.05e-03
+2022-05-14 04:52:28,295 INFO [train.py:812] (7/8) Epoch 7, batch 1200, loss[loss=0.1736, simple_loss=0.2536, pruned_loss=0.04678, over 6790.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2823, pruned_loss=0.05995, over 1412567.64 frames.], batch size: 15, lr: 1.04e-03
+2022-05-14 04:53:27,889 INFO [train.py:812] (7/8) Epoch 7, batch 1250, loss[loss=0.1785, simple_loss=0.2642, pruned_loss=0.04637, over 7235.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2823, pruned_loss=0.06006, over 1414310.15 frames.], batch size: 20, lr: 1.04e-03
+2022-05-14 04:54:25,611 INFO [train.py:812] (7/8) Epoch 7, batch 1300, loss[loss=0.1697, simple_loss=0.2496, pruned_loss=0.04492, over 7294.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2814, pruned_loss=0.05976, over 1415775.97 frames.], batch size: 17, lr: 1.04e-03
+2022-05-14 04:55:24,159 INFO [train.py:812] (7/8) Epoch 7, batch 1350, loss[loss=0.2099, simple_loss=0.2948, pruned_loss=0.06253, over 7413.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2821, pruned_loss=0.05983, over 1420933.33 frames.], batch size: 21, lr: 1.04e-03
+2022-05-14 04:56:22,904 INFO [train.py:812] (7/8) Epoch 7, batch 1400, loss[loss=0.1984, simple_loss=0.2827, pruned_loss=0.05711, over 7149.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2831, pruned_loss=0.06058, over 1419150.89 frames.], batch size: 19, lr: 1.04e-03
+2022-05-14 04:57:22,046 INFO [train.py:812] (7/8) Epoch 7, batch 1450, loss[loss=0.1799, simple_loss=0.2778, pruned_loss=0.04098, over 6751.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2836, pruned_loss=0.06052, over 1419166.27 frames.], batch size: 31, lr: 1.04e-03
+2022-05-14 04:58:20,177 INFO [train.py:812] (7/8) Epoch 7, batch 1500, loss[loss=0.2194, simple_loss=0.3061, pruned_loss=0.06637, over 7414.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2824, pruned_loss=0.05937, over 1423593.70 frames.], batch size: 21, lr: 1.04e-03
+2022-05-14 04:59:18,895 INFO [train.py:812] (7/8) Epoch 7, batch 1550, loss[loss=0.1986, simple_loss=0.2913, pruned_loss=0.05296, over 7184.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2824, pruned_loss=0.05984, over 1418450.97 frames.], batch size: 26, lr: 1.04e-03
+2022-05-14 05:00:18,937 INFO [train.py:812] (7/8) Epoch 7, batch 1600, loss[loss=0.185, simple_loss=0.2813, pruned_loss=0.04441, over 7097.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2826, pruned_loss=0.05951, over 1424554.51 frames.], batch size: 21, lr: 1.04e-03
+2022-05-14 05:01:18,250 INFO [train.py:812] (7/8) Epoch 7, batch 1650, loss[loss=0.1768, simple_loss=0.2662, pruned_loss=0.04365, over 7061.00 frames.], tot_loss[loss=0.2003, simple_loss=0.282, pruned_loss=0.05927, over 1417921.47 frames.], batch size: 18, lr: 1.04e-03
+2022-05-14 05:02:16,834 INFO [train.py:812] (7/8) Epoch 7, batch 1700, loss[loss=0.229, simple_loss=0.3043, pruned_loss=0.07687, over 7187.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2807, pruned_loss=0.059, over 1416300.45 frames.], batch size: 22, lr: 1.04e-03
+2022-05-14 05:03:16,002 INFO [train.py:812] (7/8) Epoch 7, batch 1750, loss[loss=0.2144, simple_loss=0.2875, pruned_loss=0.07066, over 7330.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2814, pruned_loss=0.05969, over 1412362.61 frames.], batch size: 22, lr: 1.04e-03
+2022-05-14 05:04:14,638 INFO [train.py:812] (7/8) Epoch 7, batch 1800, loss[loss=0.2261, simple_loss=0.3036, pruned_loss=0.07435, over 7296.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2827, pruned_loss=0.05997, over 1414820.72 frames.], batch size: 25, lr: 1.03e-03
+2022-05-14 05:05:13,153 INFO [train.py:812] (7/8) Epoch 7, batch 1850, loss[loss=0.1752, simple_loss=0.2577, pruned_loss=0.04633, over 6991.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2819, pruned_loss=0.05942, over 1417092.89 frames.], batch size: 16, lr: 1.03e-03
+2022-05-14 05:06:10,521 INFO [train.py:812] (7/8) Epoch 7, batch 1900, loss[loss=0.224, simple_loss=0.2972, pruned_loss=0.07535, over 7054.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2832, pruned_loss=0.05999, over 1413612.12 frames.], batch size: 18, lr: 1.03e-03
+2022-05-14 05:07:08,644 INFO [train.py:812] (7/8) Epoch 7, batch 1950, loss[loss=0.184, simple_loss=0.2598, pruned_loss=0.05406, over 7274.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2826, pruned_loss=0.05981, over 1417105.92 frames.], batch size: 18, lr: 1.03e-03
+2022-05-14 05:08:07,343 INFO [train.py:812] (7/8) Epoch 7, batch 2000, loss[loss=0.2382, simple_loss=0.309, pruned_loss=0.08372, over 7289.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2828, pruned_loss=0.06017, over 1417754.46 frames.], batch size: 25, lr: 1.03e-03
+2022-05-14 05:09:04,307 INFO [train.py:812] (7/8) Epoch 7, batch 2050, loss[loss=0.2189, simple_loss=0.3118, pruned_loss=0.06299, over 7270.00 frames.], tot_loss[loss=0.202, simple_loss=0.2833, pruned_loss=0.06037, over 1414942.21 frames.], batch size: 24, lr: 1.03e-03
+2022-05-14 05:10:01,704 INFO [train.py:812] (7/8) Epoch 7, batch 2100, loss[loss=0.1653, simple_loss=0.2441, pruned_loss=0.04329, over 7005.00 frames.], tot_loss[loss=0.201, simple_loss=0.2823, pruned_loss=0.05988, over 1417908.43 frames.], batch size: 16, lr: 1.03e-03
+2022-05-14 05:11:00,106 INFO [train.py:812] (7/8) Epoch 7, batch 2150, loss[loss=0.1729, simple_loss=0.2617, pruned_loss=0.04206, over 7411.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2816, pruned_loss=0.05913, over 1423404.62 frames.], batch size: 21, lr: 1.03e-03
+2022-05-14 05:11:57,842 INFO [train.py:812] (7/8) Epoch 7, batch 2200, loss[loss=0.1824, simple_loss=0.2658, pruned_loss=0.04949, over 7147.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2812, pruned_loss=0.05902, over 1422130.63 frames.], batch size: 17, lr: 1.03e-03
+2022-05-14 05:12:56,746 INFO [train.py:812] (7/8) Epoch 7, batch 2250, loss[loss=0.1963, simple_loss=0.2729, pruned_loss=0.05983, over 7284.00 frames.], tot_loss[loss=0.201, simple_loss=0.2821, pruned_loss=0.05991, over 1416625.60 frames.], batch size: 17, lr: 1.03e-03
+2022-05-14 05:13:54,342 INFO [train.py:812] (7/8) Epoch 7, batch 2300, loss[loss=0.2124, simple_loss=0.2933, pruned_loss=0.06571, over 7215.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2822, pruned_loss=0.05959, over 1419901.71 frames.], batch size: 23, lr: 1.03e-03
+2022-05-14 05:14:53,684 INFO [train.py:812] (7/8) Epoch 7, batch 2350, loss[loss=0.1936, simple_loss=0.2796, pruned_loss=0.05374, over 7417.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2819, pruned_loss=0.05951, over 1416720.51 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:15:53,764 INFO [train.py:812] (7/8) Epoch 7, batch 2400, loss[loss=0.1809, simple_loss=0.2591, pruned_loss=0.05136, over 7291.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2808, pruned_loss=0.05894, over 1420587.29 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:16:51,059 INFO [train.py:812] (7/8) Epoch 7, batch 2450, loss[loss=0.215, simple_loss=0.2981, pruned_loss=0.06595, over 7408.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2815, pruned_loss=0.059, over 1416988.85 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:17:49,503 INFO [train.py:812] (7/8) Epoch 7, batch 2500, loss[loss=0.1978, simple_loss=0.2933, pruned_loss=0.05118, over 7322.00 frames.], tot_loss[loss=0.2003, simple_loss=0.282, pruned_loss=0.05932, over 1417132.09 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:18:48,432 INFO [train.py:812] (7/8) Epoch 7, batch 2550, loss[loss=0.1987, simple_loss=0.2868, pruned_loss=0.05525, over 7439.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2819, pruned_loss=0.05867, over 1423691.64 frames.], batch size: 20, lr: 1.02e-03
+2022-05-14 05:19:47,262 INFO [train.py:812] (7/8) Epoch 7, batch 2600, loss[loss=0.1525, simple_loss=0.2402, pruned_loss=0.03239, over 7161.00 frames.], tot_loss[loss=0.2, simple_loss=0.2817, pruned_loss=0.0591, over 1418212.44 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:20:45,589 INFO [train.py:812] (7/8) Epoch 7, batch 2650, loss[loss=0.2359, simple_loss=0.2974, pruned_loss=0.08714, over 7157.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2805, pruned_loss=0.05865, over 1417932.33 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:21:44,825 INFO [train.py:812] (7/8) Epoch 7, batch 2700, loss[loss=0.2014, simple_loss=0.2801, pruned_loss=0.06129, over 6807.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2804, pruned_loss=0.05831, over 1419453.01 frames.], batch size: 15, lr: 1.02e-03
+2022-05-14 05:22:44,423 INFO [train.py:812] (7/8) Epoch 7, batch 2750, loss[loss=0.1888, simple_loss=0.2578, pruned_loss=0.05987, over 7402.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2806, pruned_loss=0.05876, over 1419976.52 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:23:44,373 INFO [train.py:812] (7/8) Epoch 7, batch 2800, loss[loss=0.1834, simple_loss=0.2565, pruned_loss=0.05519, over 6995.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2801, pruned_loss=0.05849, over 1418007.31 frames.], batch size: 16, lr: 1.02e-03
+2022-05-14 05:24:43,868 INFO [train.py:812] (7/8) Epoch 7, batch 2850, loss[loss=0.204, simple_loss=0.2847, pruned_loss=0.06161, over 7318.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2796, pruned_loss=0.05865, over 1422572.07 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:25:43,747 INFO [train.py:812] (7/8) Epoch 7, batch 2900, loss[loss=0.2409, simple_loss=0.3085, pruned_loss=0.08669, over 5041.00 frames.], tot_loss[loss=0.198, simple_loss=0.2793, pruned_loss=0.05835, over 1424373.41 frames.], batch size: 55, lr: 1.02e-03
+2022-05-14 05:26:42,765 INFO [train.py:812] (7/8) Epoch 7, batch 2950, loss[loss=0.2073, simple_loss=0.283, pruned_loss=0.0658, over 7273.00 frames.], tot_loss[loss=0.1986, simple_loss=0.28, pruned_loss=0.0586, over 1424190.44 frames.], batch size: 25, lr: 1.01e-03
+2022-05-14 05:27:42,396 INFO [train.py:812] (7/8) Epoch 7, batch 3000, loss[loss=0.2223, simple_loss=0.3122, pruned_loss=0.06618, over 7201.00 frames.], tot_loss[loss=0.199, simple_loss=0.2808, pruned_loss=0.05857, over 1425880.87 frames.], batch size: 26, lr: 1.01e-03
+2022-05-14 05:27:42,397 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 05:27:49,661 INFO [train.py:841] (7/8) Epoch 7, validation: loss=0.1637, simple_loss=0.2662, pruned_loss=0.03066, over 698248.00 frames.
+2022-05-14 05:28:49,004 INFO [train.py:812] (7/8) Epoch 7, batch 3050, loss[loss=0.207, simple_loss=0.2913, pruned_loss=0.06134, over 7150.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2809, pruned_loss=0.05861, over 1426239.67 frames.], batch size: 26, lr: 1.01e-03
+2022-05-14 05:29:48,832 INFO [train.py:812] (7/8) Epoch 7, batch 3100, loss[loss=0.218, simple_loss=0.2966, pruned_loss=0.06972, over 7131.00 frames.], tot_loss[loss=0.2, simple_loss=0.2819, pruned_loss=0.059, over 1423478.09 frames.], batch size: 26, lr: 1.01e-03
+2022-05-14 05:30:48,436 INFO [train.py:812] (7/8) Epoch 7, batch 3150, loss[loss=0.1857, simple_loss=0.2709, pruned_loss=0.05024, over 7090.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2817, pruned_loss=0.05923, over 1426828.24 frames.], batch size: 28, lr: 1.01e-03
+2022-05-14 05:31:47,473 INFO [train.py:812] (7/8) Epoch 7, batch 3200, loss[loss=0.1798, simple_loss=0.2668, pruned_loss=0.0464, over 7332.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2824, pruned_loss=0.05924, over 1423076.98 frames.], batch size: 22, lr: 1.01e-03
+2022-05-14 05:32:46,905 INFO [train.py:812] (7/8) Epoch 7, batch 3250, loss[loss=0.2006, simple_loss=0.2893, pruned_loss=0.05593, over 7069.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2811, pruned_loss=0.05882, over 1422423.61 frames.], batch size: 28, lr: 1.01e-03
+2022-05-14 05:33:46,267 INFO [train.py:812] (7/8) Epoch 7, batch 3300, loss[loss=0.1928, simple_loss=0.2736, pruned_loss=0.05598, over 7153.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2815, pruned_loss=0.05891, over 1417820.21 frames.], batch size: 20, lr: 1.01e-03
+2022-05-14 05:34:45,894 INFO [train.py:812] (7/8) Epoch 7, batch 3350, loss[loss=0.165, simple_loss=0.2599, pruned_loss=0.0351, over 7171.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2812, pruned_loss=0.05879, over 1419299.21 frames.], batch size: 19, lr: 1.01e-03
+2022-05-14 05:35:44,969 INFO [train.py:812] (7/8) Epoch 7, batch 3400, loss[loss=0.2378, simple_loss=0.3115, pruned_loss=0.08204, over 7111.00 frames.], tot_loss[loss=0.201, simple_loss=0.2825, pruned_loss=0.05972, over 1422750.74 frames.], batch size: 21, lr: 1.01e-03
+2022-05-14 05:36:43,538 INFO [train.py:812] (7/8) Epoch 7, batch 3450, loss[loss=0.2216, simple_loss=0.3121, pruned_loss=0.06557, over 7295.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2826, pruned_loss=0.05951, over 1420347.16 frames.], batch size: 24, lr: 1.01e-03
+2022-05-14 05:37:43,031 INFO [train.py:812] (7/8) Epoch 7, batch 3500, loss[loss=0.2075, simple_loss=0.2965, pruned_loss=0.05927, over 7225.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2824, pruned_loss=0.05915, over 1422369.33 frames.], batch size: 21, lr: 1.01e-03
+2022-05-14 05:38:41,481 INFO [train.py:812] (7/8) Epoch 7, batch 3550, loss[loss=0.2436, simple_loss=0.3216, pruned_loss=0.08281, over 7376.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2814, pruned_loss=0.05859, over 1423507.29 frames.], batch size: 23, lr: 1.01e-03
+2022-05-14 05:39:40,580 INFO [train.py:812] (7/8) Epoch 7, batch 3600, loss[loss=0.2203, simple_loss=0.3062, pruned_loss=0.06721, over 7218.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2818, pruned_loss=0.05925, over 1424786.48 frames.], batch size: 21, lr: 1.00e-03
+2022-05-14 05:40:39,029 INFO [train.py:812] (7/8) Epoch 7, batch 3650, loss[loss=0.2178, simple_loss=0.2906, pruned_loss=0.07249, over 7026.00 frames.], tot_loss[loss=0.2002, simple_loss=0.282, pruned_loss=0.05918, over 1421278.24 frames.], batch size: 28, lr: 1.00e-03
+2022-05-14 05:41:38,753 INFO [train.py:812] (7/8) Epoch 7, batch 3700, loss[loss=0.1832, simple_loss=0.2667, pruned_loss=0.04989, over 7426.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2812, pruned_loss=0.05899, over 1422471.73 frames.], batch size: 20, lr: 1.00e-03
+2022-05-14 05:42:37,976 INFO [train.py:812] (7/8) Epoch 7, batch 3750, loss[loss=0.2655, simple_loss=0.3363, pruned_loss=0.09736, over 4772.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2809, pruned_loss=0.05898, over 1423129.97 frames.], batch size: 52, lr: 1.00e-03
+2022-05-14 05:43:37,520 INFO [train.py:812] (7/8) Epoch 7, batch 3800, loss[loss=0.1977, simple_loss=0.272, pruned_loss=0.06172, over 7358.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2801, pruned_loss=0.05837, over 1420137.95 frames.], batch size: 19, lr: 1.00e-03
+2022-05-14 05:44:35,609 INFO [train.py:812] (7/8) Epoch 7, batch 3850, loss[loss=0.2029, simple_loss=0.2766, pruned_loss=0.06463, over 7115.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2795, pruned_loss=0.05815, over 1423437.79 frames.], batch size: 17, lr: 1.00e-03
+2022-05-14 05:45:34,818 INFO [train.py:812] (7/8) Epoch 7, batch 3900, loss[loss=0.1962, simple_loss=0.2668, pruned_loss=0.06285, over 7164.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2793, pruned_loss=0.05776, over 1424436.83 frames.], batch size: 18, lr: 1.00e-03
+2022-05-14 05:46:31,699 INFO [train.py:812] (7/8) Epoch 7, batch 3950, loss[loss=0.2066, simple_loss=0.2923, pruned_loss=0.0605, over 7322.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2781, pruned_loss=0.05701, over 1427064.64 frames.], batch size: 22, lr: 9.99e-04
+2022-05-14 05:47:30,596 INFO [train.py:812] (7/8) Epoch 7, batch 4000, loss[loss=0.2026, simple_loss=0.2886, pruned_loss=0.05829, over 6726.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2778, pruned_loss=0.05671, over 1431318.44 frames.], batch size: 31, lr: 9.98e-04
+2022-05-14 05:48:29,684 INFO [train.py:812] (7/8) Epoch 7, batch 4050, loss[loss=0.1932, simple_loss=0.2787, pruned_loss=0.0539, over 7161.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2786, pruned_loss=0.05723, over 1429067.92 frames.], batch size: 18, lr: 9.98e-04
+2022-05-14 05:49:28,789 INFO [train.py:812] (7/8) Epoch 7, batch 4100, loss[loss=0.2118, simple_loss=0.3024, pruned_loss=0.06066, over 7119.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2794, pruned_loss=0.05777, over 1424432.66 frames.], batch size: 21, lr: 9.97e-04
+2022-05-14 05:50:26,095 INFO [train.py:812] (7/8) Epoch 7, batch 4150, loss[loss=0.205, simple_loss=0.29, pruned_loss=0.05999, over 7203.00 frames.], tot_loss[loss=0.1974, simple_loss=0.279, pruned_loss=0.05787, over 1425700.24 frames.], batch size: 23, lr: 9.96e-04
+2022-05-14 05:51:25,353 INFO [train.py:812] (7/8) Epoch 7, batch 4200, loss[loss=0.1628, simple_loss=0.2335, pruned_loss=0.04605, over 7266.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2787, pruned_loss=0.05772, over 1428515.89 frames.], batch size: 17, lr: 9.95e-04
+2022-05-14 05:52:24,637 INFO [train.py:812] (7/8) Epoch 7, batch 4250, loss[loss=0.1916, simple_loss=0.2727, pruned_loss=0.05524, over 7436.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2803, pruned_loss=0.05858, over 1423360.07 frames.], batch size: 20, lr: 9.95e-04
+2022-05-14 05:53:23,927 INFO [train.py:812] (7/8) Epoch 7, batch 4300, loss[loss=0.2478, simple_loss=0.3336, pruned_loss=0.08096, over 7231.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2827, pruned_loss=0.05984, over 1416452.67 frames.], batch size: 20, lr: 9.94e-04
+2022-05-14 05:54:23,369 INFO [train.py:812] (7/8) Epoch 7, batch 4350, loss[loss=0.2311, simple_loss=0.3119, pruned_loss=0.07513, over 6306.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2831, pruned_loss=0.05962, over 1409902.30 frames.], batch size: 37, lr: 9.93e-04
+2022-05-14 05:55:22,298 INFO [train.py:812] (7/8) Epoch 7, batch 4400, loss[loss=0.2227, simple_loss=0.309, pruned_loss=0.06826, over 6753.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2832, pruned_loss=0.06019, over 1411182.02 frames.], batch size: 31, lr: 9.92e-04
+2022-05-14 05:56:20,612 INFO [train.py:812] (7/8) Epoch 7, batch 4450, loss[loss=0.1872, simple_loss=0.2649, pruned_loss=0.05477, over 7211.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2832, pruned_loss=0.05966, over 1406247.16 frames.], batch size: 22, lr: 9.92e-04
+2022-05-14 05:57:24,441 INFO [train.py:812] (7/8) Epoch 7, batch 4500, loss[loss=0.2458, simple_loss=0.3271, pruned_loss=0.0822, over 7214.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2842, pruned_loss=0.06023, over 1403711.66 frames.], batch size: 22, lr: 9.91e-04
+2022-05-14 05:58:22,230 INFO [train.py:812] (7/8) Epoch 7, batch 4550, loss[loss=0.2216, simple_loss=0.3039, pruned_loss=0.06961, over 5102.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2854, pruned_loss=0.06102, over 1388535.96 frames.], batch size: 52, lr: 9.90e-04
+2022-05-14 05:59:32,606 INFO [train.py:812] (7/8) Epoch 8, batch 0, loss[loss=0.2053, simple_loss=0.2907, pruned_loss=0.0599, over 7339.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2907, pruned_loss=0.0599, over 7339.00 frames.], batch size: 22, lr: 9.49e-04
+2022-05-14 06:00:31,174 INFO [train.py:812] (7/8) Epoch 8, batch 50, loss[loss=0.2045, simple_loss=0.2784, pruned_loss=0.06526, over 7158.00 frames.], tot_loss[loss=0.197, simple_loss=0.2813, pruned_loss=0.05637, over 320998.08 frames.], batch size: 17, lr: 9.48e-04
+2022-05-14 06:01:30,414 INFO [train.py:812] (7/8) Epoch 8, batch 100, loss[loss=0.2126, simple_loss=0.2913, pruned_loss=0.06688, over 7315.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2811, pruned_loss=0.05697, over 569071.34 frames.], batch size: 25, lr: 9.48e-04
+2022-05-14 06:02:29,715 INFO [train.py:812] (7/8) Epoch 8, batch 150, loss[loss=0.1768, simple_loss=0.2743, pruned_loss=0.03962, over 7120.00 frames.], tot_loss[loss=0.196, simple_loss=0.2789, pruned_loss=0.05655, over 758457.83 frames.], batch size: 21, lr: 9.47e-04
+2022-05-14 06:03:26,772 INFO [train.py:812] (7/8) Epoch 8, batch 200, loss[loss=0.1835, simple_loss=0.2699, pruned_loss=0.04853, over 7226.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2801, pruned_loss=0.05754, over 907557.82 frames.], batch size: 22, lr: 9.46e-04
+2022-05-14 06:04:24,376 INFO [train.py:812] (7/8) Epoch 8, batch 250, loss[loss=0.1966, simple_loss=0.2902, pruned_loss=0.05153, over 7112.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2797, pruned_loss=0.057, over 1020626.43 frames.], batch size: 21, lr: 9.46e-04
+2022-05-14 06:05:21,334 INFO [train.py:812] (7/8) Epoch 8, batch 300, loss[loss=0.1798, simple_loss=0.261, pruned_loss=0.04928, over 7081.00 frames.], tot_loss[loss=0.1975, simple_loss=0.28, pruned_loss=0.05754, over 1106004.21 frames.], batch size: 18, lr: 9.45e-04
+2022-05-14 06:06:19,898 INFO [train.py:812] (7/8) Epoch 8, batch 350, loss[loss=0.2148, simple_loss=0.31, pruned_loss=0.0598, over 7124.00 frames.], tot_loss[loss=0.196, simple_loss=0.2782, pruned_loss=0.05695, over 1177475.83 frames.], batch size: 21, lr: 9.44e-04
+2022-05-14 06:07:19,522 INFO [train.py:812] (7/8) Epoch 8, batch 400, loss[loss=0.2253, simple_loss=0.2942, pruned_loss=0.07815, over 5056.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2782, pruned_loss=0.05653, over 1230705.23 frames.], batch size: 52, lr: 9.43e-04
+2022-05-14 06:08:18,818 INFO [train.py:812] (7/8) Epoch 8, batch 450, loss[loss=0.1727, simple_loss=0.2556, pruned_loss=0.04495, over 7259.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2775, pruned_loss=0.05644, over 1272392.75 frames.], batch size: 16, lr: 9.43e-04
+2022-05-14 06:09:18,383 INFO [train.py:812] (7/8) Epoch 8, batch 500, loss[loss=0.2039, simple_loss=0.2842, pruned_loss=0.06175, over 7186.00 frames.], tot_loss[loss=0.195, simple_loss=0.2776, pruned_loss=0.05619, over 1304869.27 frames.], batch size: 23, lr: 9.42e-04
+2022-05-14 06:10:16,967 INFO [train.py:812] (7/8) Epoch 8, batch 550, loss[loss=0.199, simple_loss=0.2779, pruned_loss=0.06009, over 7216.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2783, pruned_loss=0.05636, over 1332569.38 frames.], batch size: 23, lr: 9.41e-04
+2022-05-14 06:11:16,928 INFO [train.py:812] (7/8) Epoch 8, batch 600, loss[loss=0.1957, simple_loss=0.2892, pruned_loss=0.05106, over 7215.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2794, pruned_loss=0.05647, over 1352481.89 frames.], batch size: 21, lr: 9.41e-04
+2022-05-14 06:12:15,272 INFO [train.py:812] (7/8) Epoch 8, batch 650, loss[loss=0.1647, simple_loss=0.2527, pruned_loss=0.03829, over 7263.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2778, pruned_loss=0.0556, over 1367234.03 frames.], batch size: 19, lr: 9.40e-04
+2022-05-14 06:13:14,203 INFO [train.py:812] (7/8) Epoch 8, batch 700, loss[loss=0.233, simple_loss=0.303, pruned_loss=0.08147, over 5003.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2793, pruned_loss=0.05646, over 1376484.21 frames.], batch size: 52, lr: 9.39e-04
+2022-05-14 06:14:13,360 INFO [train.py:812] (7/8) Epoch 8, batch 750, loss[loss=0.1853, simple_loss=0.2688, pruned_loss=0.05091, over 7361.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2792, pruned_loss=0.05648, over 1385206.94 frames.], batch size: 19, lr: 9.39e-04
+2022-05-14 06:15:12,836 INFO [train.py:812] (7/8) Epoch 8, batch 800, loss[loss=0.2341, simple_loss=0.3114, pruned_loss=0.07841, over 6308.00 frames.], tot_loss[loss=0.1967, simple_loss=0.28, pruned_loss=0.05667, over 1390281.40 frames.], batch size: 38, lr: 9.38e-04
+2022-05-14 06:16:12,253 INFO [train.py:812] (7/8) Epoch 8, batch 850, loss[loss=0.1885, simple_loss=0.2613, pruned_loss=0.0579, over 7404.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2777, pruned_loss=0.05554, over 1399351.81 frames.], batch size: 18, lr: 9.37e-04
+2022-05-14 06:17:11,320 INFO [train.py:812] (7/8) Epoch 8, batch 900, loss[loss=0.2204, simple_loss=0.3017, pruned_loss=0.06952, over 6787.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2787, pruned_loss=0.05637, over 1399062.99 frames.], batch size: 31, lr: 9.36e-04
+2022-05-14 06:18:09,049 INFO [train.py:812] (7/8) Epoch 8, batch 950, loss[loss=0.1951, simple_loss=0.2789, pruned_loss=0.05558, over 7226.00 frames.], tot_loss[loss=0.196, simple_loss=0.2791, pruned_loss=0.05645, over 1405215.78 frames.], batch size: 20, lr: 9.36e-04
+2022-05-14 06:19:08,092 INFO [train.py:812] (7/8) Epoch 8, batch 1000, loss[loss=0.1971, simple_loss=0.2851, pruned_loss=0.05456, over 7225.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2791, pruned_loss=0.05634, over 1409759.13 frames.], batch size: 21, lr: 9.35e-04
+2022-05-14 06:20:06,240 INFO [train.py:812] (7/8) Epoch 8, batch 1050, loss[loss=0.1844, simple_loss=0.2495, pruned_loss=0.05961, over 7162.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2802, pruned_loss=0.05697, over 1408223.89 frames.], batch size: 17, lr: 9.34e-04
+2022-05-14 06:21:04,784 INFO [train.py:812] (7/8) Epoch 8, batch 1100, loss[loss=0.2244, simple_loss=0.3129, pruned_loss=0.06796, over 7203.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2795, pruned_loss=0.05671, over 1412892.15 frames.], batch size: 22, lr: 9.34e-04
+2022-05-14 06:22:02,889 INFO [train.py:812] (7/8) Epoch 8, batch 1150, loss[loss=0.2301, simple_loss=0.2978, pruned_loss=0.08125, over 5380.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2794, pruned_loss=0.05619, over 1418466.28 frames.], batch size: 53, lr: 9.33e-04
+2022-05-14 06:23:10,879 INFO [train.py:812] (7/8) Epoch 8, batch 1200, loss[loss=0.1596, simple_loss=0.2521, pruned_loss=0.03356, over 7150.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2789, pruned_loss=0.05579, over 1421410.84 frames.], batch size: 20, lr: 9.32e-04
+2022-05-14 06:24:10,086 INFO [train.py:812] (7/8) Epoch 8, batch 1250, loss[loss=0.1782, simple_loss=0.2601, pruned_loss=0.04815, over 7287.00 frames.], tot_loss[loss=0.195, simple_loss=0.2781, pruned_loss=0.05597, over 1420738.21 frames.], batch size: 18, lr: 9.32e-04
+2022-05-14 06:25:09,396 INFO [train.py:812] (7/8) Epoch 8, batch 1300, loss[loss=0.1909, simple_loss=0.2789, pruned_loss=0.05143, over 7137.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2786, pruned_loss=0.05607, over 1417613.81 frames.], batch size: 20, lr: 9.31e-04
+2022-05-14 06:26:08,294 INFO [train.py:812] (7/8) Epoch 8, batch 1350, loss[loss=0.1693, simple_loss=0.246, pruned_loss=0.04626, over 7165.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2784, pruned_loss=0.05611, over 1416768.14 frames.], batch size: 19, lr: 9.30e-04
+2022-05-14 06:27:08,021 INFO [train.py:812] (7/8) Epoch 8, batch 1400, loss[loss=0.1758, simple_loss=0.2548, pruned_loss=0.04842, over 7271.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2783, pruned_loss=0.05565, over 1418149.06 frames.], batch size: 18, lr: 9.30e-04
+2022-05-14 06:28:06,844 INFO [train.py:812] (7/8) Epoch 8, batch 1450, loss[loss=0.2045, simple_loss=0.2799, pruned_loss=0.06457, over 7166.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2785, pruned_loss=0.05564, over 1417231.83 frames.], batch size: 18, lr: 9.29e-04
+2022-05-14 06:29:06,655 INFO [train.py:812] (7/8) Epoch 8, batch 1500, loss[loss=0.1538, simple_loss=0.2322, pruned_loss=0.03768, over 7401.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2784, pruned_loss=0.05601, over 1416534.07 frames.], batch size: 18, lr: 9.28e-04
+2022-05-14 06:30:05,565 INFO [train.py:812] (7/8) Epoch 8, batch 1550, loss[loss=0.1997, simple_loss=0.2812, pruned_loss=0.05911, over 7212.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2776, pruned_loss=0.05553, over 1421224.97 frames.], batch size: 22, lr: 9.28e-04
+2022-05-14 06:31:05,150 INFO [train.py:812] (7/8) Epoch 8, batch 1600, loss[loss=0.1933, simple_loss=0.2802, pruned_loss=0.05316, over 6229.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2789, pruned_loss=0.05624, over 1421538.26 frames.], batch size: 37, lr: 9.27e-04
+2022-05-14 06:32:04,319 INFO [train.py:812] (7/8) Epoch 8, batch 1650, loss[loss=0.2088, simple_loss=0.2949, pruned_loss=0.06136, over 7264.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2797, pruned_loss=0.0566, over 1420396.05 frames.], batch size: 24, lr: 9.26e-04
+2022-05-14 06:33:04,129 INFO [train.py:812] (7/8) Epoch 8, batch 1700, loss[loss=0.1872, simple_loss=0.2878, pruned_loss=0.04325, over 7325.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2799, pruned_loss=0.05646, over 1420949.04 frames.], batch size: 21, lr: 9.26e-04
+2022-05-14 06:34:03,608 INFO [train.py:812] (7/8) Epoch 8, batch 1750, loss[loss=0.175, simple_loss=0.2699, pruned_loss=0.04003, over 7332.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2794, pruned_loss=0.05644, over 1421137.88 frames.], batch size: 22, lr: 9.25e-04
+2022-05-14 06:35:12,528 INFO [train.py:812] (7/8) Epoch 8, batch 1800, loss[loss=0.1882, simple_loss=0.2799, pruned_loss=0.04821, over 7334.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2779, pruned_loss=0.05581, over 1422244.50 frames.], batch size: 22, lr: 9.24e-04
+2022-05-14 06:36:21,374 INFO [train.py:812] (7/8) Epoch 8, batch 1850, loss[loss=0.2043, simple_loss=0.2797, pruned_loss=0.06443, over 7232.00 frames.], tot_loss[loss=0.196, simple_loss=0.279, pruned_loss=0.05647, over 1424113.62 frames.], batch size: 20, lr: 9.24e-04
+2022-05-14 06:37:30,738 INFO [train.py:812] (7/8) Epoch 8, batch 1900, loss[loss=0.2154, simple_loss=0.302, pruned_loss=0.06439, over 7312.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2775, pruned_loss=0.05606, over 1423061.56 frames.], batch size: 25, lr: 9.23e-04
+2022-05-14 06:38:48,477 INFO [train.py:812] (7/8) Epoch 8, batch 1950, loss[loss=0.1697, simple_loss=0.2385, pruned_loss=0.05044, over 6988.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2774, pruned_loss=0.05597, over 1426834.90 frames.], batch size: 16, lr: 9.22e-04
+2022-05-14 06:40:06,972 INFO [train.py:812] (7/8) Epoch 8, batch 2000, loss[loss=0.2207, simple_loss=0.3096, pruned_loss=0.06591, over 7117.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2777, pruned_loss=0.0561, over 1426650.75 frames.], batch size: 21, lr: 9.22e-04
+2022-05-14 06:41:06,035 INFO [train.py:812] (7/8) Epoch 8, batch 2050, loss[loss=0.2598, simple_loss=0.3164, pruned_loss=0.1017, over 4759.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2791, pruned_loss=0.05716, over 1420593.08 frames.], batch size: 53, lr: 9.21e-04
+2022-05-14 06:42:04,918 INFO [train.py:812] (7/8) Epoch 8, batch 2100, loss[loss=0.2047, simple_loss=0.2933, pruned_loss=0.0581, over 7236.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2788, pruned_loss=0.05677, over 1417125.35 frames.], batch size: 20, lr: 9.20e-04
+2022-05-14 06:43:04,010 INFO [train.py:812] (7/8) Epoch 8, batch 2150, loss[loss=0.2024, simple_loss=0.2886, pruned_loss=0.05815, over 7212.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2782, pruned_loss=0.05664, over 1418965.21 frames.], batch size: 22, lr: 9.20e-04
+2022-05-14 06:44:02,984 INFO [train.py:812] (7/8) Epoch 8, batch 2200, loss[loss=0.2345, simple_loss=0.3094, pruned_loss=0.07978, over 7295.00 frames.], tot_loss[loss=0.1948, simple_loss=0.277, pruned_loss=0.05627, over 1417712.13 frames.], batch size: 24, lr: 9.19e-04
+2022-05-14 06:45:01,887 INFO [train.py:812] (7/8) Epoch 8, batch 2250, loss[loss=0.1919, simple_loss=0.2785, pruned_loss=0.0527, over 7191.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2763, pruned_loss=0.05571, over 1412290.92 frames.], batch size: 23, lr: 9.18e-04
+2022-05-14 06:46:00,811 INFO [train.py:812] (7/8) Epoch 8, batch 2300, loss[loss=0.2011, simple_loss=0.2927, pruned_loss=0.0547, over 7427.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2763, pruned_loss=0.05577, over 1412657.84 frames.], batch size: 18, lr: 9.18e-04
+2022-05-14 06:46:59,520 INFO [train.py:812] (7/8) Epoch 8, batch 2350, loss[loss=0.1772, simple_loss=0.2562, pruned_loss=0.04908, over 7071.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2765, pruned_loss=0.05588, over 1412472.86 frames.], batch size: 18, lr: 9.17e-04
+2022-05-14 06:47:58,473 INFO [train.py:812] (7/8) Epoch 8, batch 2400, loss[loss=0.1836, simple_loss=0.2706, pruned_loss=0.04833, over 7257.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2761, pruned_loss=0.05564, over 1415921.49 frames.], batch size: 19, lr: 9.16e-04
+2022-05-14 06:48:57,545 INFO [train.py:812] (7/8) Epoch 8, batch 2450, loss[loss=0.197, simple_loss=0.2753, pruned_loss=0.0593, over 7309.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2753, pruned_loss=0.05491, over 1422469.87 frames.], batch size: 24, lr: 9.16e-04
+2022-05-14 06:49:57,019 INFO [train.py:812] (7/8) Epoch 8, batch 2500, loss[loss=0.2184, simple_loss=0.302, pruned_loss=0.06745, over 7318.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2761, pruned_loss=0.05536, over 1420180.58 frames.], batch size: 21, lr: 9.15e-04
+2022-05-14 06:50:55,709 INFO [train.py:812] (7/8) Epoch 8, batch 2550, loss[loss=0.1812, simple_loss=0.2651, pruned_loss=0.04863, over 7362.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2753, pruned_loss=0.05495, over 1424446.94 frames.], batch size: 19, lr: 9.14e-04
+2022-05-14 06:51:54,462 INFO [train.py:812] (7/8) Epoch 8, batch 2600, loss[loss=0.214, simple_loss=0.2755, pruned_loss=0.07621, over 7225.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2761, pruned_loss=0.05545, over 1425232.42 frames.], batch size: 16, lr: 9.14e-04
+2022-05-14 06:52:51,862 INFO [train.py:812] (7/8) Epoch 8, batch 2650, loss[loss=0.1831, simple_loss=0.2749, pruned_loss=0.04565, over 7121.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2768, pruned_loss=0.0559, over 1426137.46 frames.], batch size: 21, lr: 9.13e-04
+2022-05-14 06:53:49,770 INFO [train.py:812] (7/8) Epoch 8, batch 2700, loss[loss=0.1788, simple_loss=0.2525, pruned_loss=0.05257, over 6861.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2763, pruned_loss=0.05548, over 1428447.93 frames.], batch size: 15, lr: 9.12e-04
+2022-05-14 06:54:48,263 INFO [train.py:812] (7/8) Epoch 8, batch 2750, loss[loss=0.194, simple_loss=0.2588, pruned_loss=0.06462, over 6998.00 frames.], tot_loss[loss=0.193, simple_loss=0.2755, pruned_loss=0.05531, over 1426532.13 frames.], batch size: 16, lr: 9.12e-04
+2022-05-14 06:55:46,874 INFO [train.py:812] (7/8) Epoch 8, batch 2800, loss[loss=0.2088, simple_loss=0.2836, pruned_loss=0.06704, over 7145.00 frames.], tot_loss[loss=0.1931, simple_loss=0.276, pruned_loss=0.05513, over 1427167.26 frames.], batch size: 20, lr: 9.11e-04
+2022-05-14 06:56:44,450 INFO [train.py:812] (7/8) Epoch 8, batch 2850, loss[loss=0.2044, simple_loss=0.2855, pruned_loss=0.06164, over 7206.00 frames.], tot_loss[loss=0.193, simple_loss=0.2758, pruned_loss=0.05515, over 1425651.00 frames.], batch size: 22, lr: 9.11e-04
+2022-05-14 06:57:43,831 INFO [train.py:812] (7/8) Epoch 8, batch 2900, loss[loss=0.1971, simple_loss=0.2704, pruned_loss=0.06188, over 7136.00 frames.], tot_loss[loss=0.193, simple_loss=0.276, pruned_loss=0.05496, over 1424890.25 frames.], batch size: 17, lr: 9.10e-04
+2022-05-14 06:58:42,777 INFO [train.py:812] (7/8) Epoch 8, batch 2950, loss[loss=0.1619, simple_loss=0.2495, pruned_loss=0.0372, over 7058.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2744, pruned_loss=0.0543, over 1424663.90 frames.], batch size: 18, lr: 9.09e-04
+2022-05-14 06:59:42,254 INFO [train.py:812] (7/8) Epoch 8, batch 3000, loss[loss=0.2368, simple_loss=0.3083, pruned_loss=0.08267, over 4975.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2741, pruned_loss=0.05409, over 1421559.17 frames.], batch size: 52, lr: 9.09e-04
+2022-05-14 06:59:42,255 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 06:59:50,552 INFO [train.py:841] (7/8) Epoch 8, validation: loss=0.1612, simple_loss=0.2635, pruned_loss=0.0294, over 698248.00 frames.
+2022-05-14 07:00:48,531 INFO [train.py:812] (7/8) Epoch 8, batch 3050, loss[loss=0.207, simple_loss=0.285, pruned_loss=0.06453, over 6340.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2738, pruned_loss=0.05418, over 1414807.87 frames.], batch size: 38, lr: 9.08e-04
+2022-05-14 07:01:48,171 INFO [train.py:812] (7/8) Epoch 8, batch 3100, loss[loss=0.1808, simple_loss=0.263, pruned_loss=0.04927, over 7257.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2736, pruned_loss=0.05409, over 1419068.78 frames.], batch size: 19, lr: 9.07e-04
+2022-05-14 07:02:45,314 INFO [train.py:812] (7/8) Epoch 8, batch 3150, loss[loss=0.1626, simple_loss=0.2442, pruned_loss=0.04046, over 7422.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2736, pruned_loss=0.05454, over 1420054.32 frames.], batch size: 20, lr: 9.07e-04
+2022-05-14 07:03:44,366 INFO [train.py:812] (7/8) Epoch 8, batch 3200, loss[loss=0.1952, simple_loss=0.2831, pruned_loss=0.0537, over 7421.00 frames.], tot_loss[loss=0.192, simple_loss=0.2743, pruned_loss=0.05487, over 1422503.97 frames.], batch size: 20, lr: 9.06e-04
+2022-05-14 07:04:43,339 INFO [train.py:812] (7/8) Epoch 8, batch 3250, loss[loss=0.193, simple_loss=0.274, pruned_loss=0.05598, over 7076.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2748, pruned_loss=0.05473, over 1422309.37 frames.], batch size: 28, lr: 9.05e-04
+2022-05-14 07:05:41,235 INFO [train.py:812] (7/8) Epoch 8, batch 3300, loss[loss=0.1962, simple_loss=0.2827, pruned_loss=0.05489, over 6719.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2747, pruned_loss=0.05485, over 1421254.83 frames.], batch size: 31, lr: 9.05e-04
+2022-05-14 07:06:40,392 INFO [train.py:812] (7/8) Epoch 8, batch 3350, loss[loss=0.1884, simple_loss=0.2748, pruned_loss=0.05098, over 7425.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2743, pruned_loss=0.05425, over 1419461.51 frames.], batch size: 20, lr: 9.04e-04
+2022-05-14 07:07:39,838 INFO [train.py:812] (7/8) Epoch 8, batch 3400, loss[loss=0.2058, simple_loss=0.2881, pruned_loss=0.06177, over 6845.00 frames.], tot_loss[loss=0.191, simple_loss=0.274, pruned_loss=0.05403, over 1418238.53 frames.], batch size: 32, lr: 9.04e-04
+2022-05-14 07:08:38,498 INFO [train.py:812] (7/8) Epoch 8, batch 3450, loss[loss=0.189, simple_loss=0.2711, pruned_loss=0.05347, over 7430.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2757, pruned_loss=0.05505, over 1421065.58 frames.], batch size: 18, lr: 9.03e-04
+2022-05-14 07:09:37,938 INFO [train.py:812] (7/8) Epoch 8, batch 3500, loss[loss=0.186, simple_loss=0.2796, pruned_loss=0.04626, over 7369.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2761, pruned_loss=0.05504, over 1421105.60 frames.], batch size: 23, lr: 9.02e-04
+2022-05-14 07:10:37,046 INFO [train.py:812] (7/8) Epoch 8, batch 3550, loss[loss=0.2104, simple_loss=0.2905, pruned_loss=0.06513, over 7254.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2766, pruned_loss=0.05535, over 1422661.38 frames.], batch size: 19, lr: 9.02e-04
+2022-05-14 07:11:36,679 INFO [train.py:812] (7/8) Epoch 8, batch 3600, loss[loss=0.1565, simple_loss=0.2347, pruned_loss=0.03912, over 7288.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2763, pruned_loss=0.05533, over 1421553.03 frames.], batch size: 17, lr: 9.01e-04
+2022-05-14 07:12:33,643 INFO [train.py:812] (7/8) Epoch 8, batch 3650, loss[loss=0.1889, simple_loss=0.2732, pruned_loss=0.05234, over 7420.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2783, pruned_loss=0.05645, over 1415106.01 frames.], batch size: 21, lr: 9.01e-04
+2022-05-14 07:13:32,618 INFO [train.py:812] (7/8) Epoch 8, batch 3700, loss[loss=0.202, simple_loss=0.2868, pruned_loss=0.05858, over 7216.00 frames.], tot_loss[loss=0.193, simple_loss=0.276, pruned_loss=0.05501, over 1419248.56 frames.], batch size: 21, lr: 9.00e-04
+2022-05-14 07:14:31,423 INFO [train.py:812] (7/8) Epoch 8, batch 3750, loss[loss=0.206, simple_loss=0.2888, pruned_loss=0.06156, over 7167.00 frames.], tot_loss[loss=0.1928, simple_loss=0.276, pruned_loss=0.05486, over 1416135.53 frames.], batch size: 19, lr: 8.99e-04
+2022-05-14 07:15:30,620 INFO [train.py:812] (7/8) Epoch 8, batch 3800, loss[loss=0.1778, simple_loss=0.2649, pruned_loss=0.04529, over 7297.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2769, pruned_loss=0.05491, over 1419773.50 frames.], batch size: 24, lr: 8.99e-04
+2022-05-14 07:16:28,758 INFO [train.py:812] (7/8) Epoch 8, batch 3850, loss[loss=0.1876, simple_loss=0.2871, pruned_loss=0.04405, over 7219.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2776, pruned_loss=0.05484, over 1417326.84 frames.], batch size: 21, lr: 8.98e-04
+2022-05-14 07:17:33,268 INFO [train.py:812] (7/8) Epoch 8, batch 3900, loss[loss=0.1871, simple_loss=0.2618, pruned_loss=0.05615, over 7421.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2757, pruned_loss=0.0539, over 1421379.06 frames.], batch size: 20, lr: 8.97e-04
+2022-05-14 07:18:32,363 INFO [train.py:812] (7/8) Epoch 8, batch 3950, loss[loss=0.1833, simple_loss=0.2649, pruned_loss=0.05086, over 6982.00 frames.], tot_loss[loss=0.1913, simple_loss=0.275, pruned_loss=0.05382, over 1423907.80 frames.], batch size: 16, lr: 8.97e-04
+2022-05-14 07:19:31,336 INFO [train.py:812] (7/8) Epoch 8, batch 4000, loss[loss=0.2092, simple_loss=0.2923, pruned_loss=0.06309, over 7138.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2758, pruned_loss=0.05398, over 1423286.30 frames.], batch size: 20, lr: 8.96e-04
+2022-05-14 07:20:29,714 INFO [train.py:812] (7/8) Epoch 8, batch 4050, loss[loss=0.1781, simple_loss=0.2766, pruned_loss=0.03977, over 7409.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2752, pruned_loss=0.05421, over 1425559.10 frames.], batch size: 21, lr: 8.96e-04
+2022-05-14 07:21:29,491 INFO [train.py:812] (7/8) Epoch 8, batch 4100, loss[loss=0.1652, simple_loss=0.2352, pruned_loss=0.04759, over 7283.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2766, pruned_loss=0.05502, over 1418526.54 frames.], batch size: 17, lr: 8.95e-04
+2022-05-14 07:22:28,446 INFO [train.py:812] (7/8) Epoch 8, batch 4150, loss[loss=0.1918, simple_loss=0.2822, pruned_loss=0.05075, over 7328.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2771, pruned_loss=0.05505, over 1412289.61 frames.], batch size: 22, lr: 8.94e-04
+2022-05-14 07:23:28,054 INFO [train.py:812] (7/8) Epoch 8, batch 4200, loss[loss=0.1884, simple_loss=0.2802, pruned_loss=0.04827, over 7157.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2774, pruned_loss=0.05465, over 1415132.28 frames.], batch size: 20, lr: 8.94e-04
+2022-05-14 07:24:27,306 INFO [train.py:812] (7/8) Epoch 8, batch 4250, loss[loss=0.2207, simple_loss=0.2906, pruned_loss=0.07538, over 7194.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2771, pruned_loss=0.05465, over 1419712.80 frames.], batch size: 22, lr: 8.93e-04
+2022-05-14 07:25:26,260 INFO [train.py:812] (7/8) Epoch 8, batch 4300, loss[loss=0.2007, simple_loss=0.2824, pruned_loss=0.05951, over 7318.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2759, pruned_loss=0.05425, over 1418245.36 frames.], batch size: 21, lr: 8.93e-04
+2022-05-14 07:26:25,358 INFO [train.py:812] (7/8) Epoch 8, batch 4350, loss[loss=0.2351, simple_loss=0.3222, pruned_loss=0.07403, over 7121.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2749, pruned_loss=0.05387, over 1413521.93 frames.], batch size: 21, lr: 8.92e-04
+2022-05-14 07:27:24,404 INFO [train.py:812] (7/8) Epoch 8, batch 4400, loss[loss=0.1957, simple_loss=0.2732, pruned_loss=0.05911, over 7073.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2737, pruned_loss=0.05345, over 1416311.96 frames.], batch size: 28, lr: 8.91e-04
+2022-05-14 07:28:23,682 INFO [train.py:812] (7/8) Epoch 8, batch 4450, loss[loss=0.1824, simple_loss=0.2622, pruned_loss=0.05133, over 7325.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2737, pruned_loss=0.05361, over 1416160.81 frames.], batch size: 20, lr: 8.91e-04
+2022-05-14 07:29:23,615 INFO [train.py:812] (7/8) Epoch 8, batch 4500, loss[loss=0.1638, simple_loss=0.249, pruned_loss=0.03931, over 7160.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2736, pruned_loss=0.0537, over 1413554.87 frames.], batch size: 18, lr: 8.90e-04
+2022-05-14 07:30:22,923 INFO [train.py:812] (7/8) Epoch 8, batch 4550, loss[loss=0.1896, simple_loss=0.2517, pruned_loss=0.06372, over 7271.00 frames.], tot_loss[loss=0.1912, simple_loss=0.273, pruned_loss=0.05473, over 1395799.80 frames.], batch size: 17, lr: 8.90e-04
+2022-05-14 07:31:33,251 INFO [train.py:812] (7/8) Epoch 9, batch 0, loss[loss=0.2045, simple_loss=0.2885, pruned_loss=0.06026, over 7212.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2885, pruned_loss=0.06026, over 7212.00 frames.], batch size: 23, lr: 8.54e-04
+2022-05-14 07:32:31,257 INFO [train.py:812] (7/8) Epoch 9, batch 50, loss[loss=0.2281, simple_loss=0.3013, pruned_loss=0.07743, over 7029.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2779, pruned_loss=0.05437, over 319705.71 frames.], batch size: 28, lr: 8.53e-04
+2022-05-14 07:33:31,099 INFO [train.py:812] (7/8) Epoch 9, batch 100, loss[loss=0.2104, simple_loss=0.2892, pruned_loss=0.06584, over 7240.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2743, pruned_loss=0.05359, over 567515.76 frames.], batch size: 20, lr: 8.53e-04
+2022-05-14 07:34:29,339 INFO [train.py:812] (7/8) Epoch 9, batch 150, loss[loss=0.2218, simple_loss=0.2946, pruned_loss=0.0745, over 5120.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2749, pruned_loss=0.05368, over 754660.51 frames.], batch size: 52, lr: 8.52e-04
+2022-05-14 07:35:29,158 INFO [train.py:812] (7/8) Epoch 9, batch 200, loss[loss=0.2008, simple_loss=0.2846, pruned_loss=0.05855, over 7204.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2753, pruned_loss=0.05379, over 903557.94 frames.], batch size: 22, lr: 8.51e-04
+2022-05-14 07:36:28,034 INFO [train.py:812] (7/8) Epoch 9, batch 250, loss[loss=0.1764, simple_loss=0.2646, pruned_loss=0.04416, over 7429.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2751, pruned_loss=0.05363, over 1020333.79 frames.], batch size: 20, lr: 8.51e-04
+2022-05-14 07:37:25,202 INFO [train.py:812] (7/8) Epoch 9, batch 300, loss[loss=0.2013, simple_loss=0.2953, pruned_loss=0.05368, over 7318.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2748, pruned_loss=0.05343, over 1104650.84 frames.], batch size: 22, lr: 8.50e-04
+2022-05-14 07:38:24,970 INFO [train.py:812] (7/8) Epoch 9, batch 350, loss[loss=0.1617, simple_loss=0.2561, pruned_loss=0.03361, over 7159.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2727, pruned_loss=0.0522, over 1178618.67 frames.], batch size: 19, lr: 8.50e-04
+2022-05-14 07:39:24,209 INFO [train.py:812] (7/8) Epoch 9, batch 400, loss[loss=0.1849, simple_loss=0.2543, pruned_loss=0.05773, over 7146.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2738, pruned_loss=0.05293, over 1237695.80 frames.], batch size: 17, lr: 8.49e-04
+2022-05-14 07:40:21,432 INFO [train.py:812] (7/8) Epoch 9, batch 450, loss[loss=0.1548, simple_loss=0.2469, pruned_loss=0.03134, over 7258.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2724, pruned_loss=0.05228, over 1277799.18 frames.], batch size: 19, lr: 8.49e-04
+2022-05-14 07:41:19,804 INFO [train.py:812] (7/8) Epoch 9, batch 500, loss[loss=0.1393, simple_loss=0.2236, pruned_loss=0.02752, over 7397.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2737, pruned_loss=0.0528, over 1310396.80 frames.], batch size: 18, lr: 8.48e-04
+2022-05-14 07:42:19,046 INFO [train.py:812] (7/8) Epoch 9, batch 550, loss[loss=0.1783, simple_loss=0.258, pruned_loss=0.04928, over 7067.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2716, pruned_loss=0.05191, over 1338156.14 frames.], batch size: 18, lr: 8.48e-04
+2022-05-14 07:43:17,531 INFO [train.py:812] (7/8) Epoch 9, batch 600, loss[loss=0.1867, simple_loss=0.2681, pruned_loss=0.05266, over 7069.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2713, pruned_loss=0.05143, over 1360008.88 frames.], batch size: 18, lr: 8.47e-04
+2022-05-14 07:44:16,664 INFO [train.py:812] (7/8) Epoch 9, batch 650, loss[loss=0.1856, simple_loss=0.268, pruned_loss=0.05163, over 7369.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2719, pruned_loss=0.05145, over 1373683.59 frames.], batch size: 19, lr: 8.46e-04
+2022-05-14 07:45:15,395 INFO [train.py:812] (7/8) Epoch 9, batch 700, loss[loss=0.1556, simple_loss=0.2461, pruned_loss=0.0326, over 7430.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2722, pruned_loss=0.05169, over 1386453.65 frames.], batch size: 20, lr: 8.46e-04
+2022-05-14 07:46:13,738 INFO [train.py:812] (7/8) Epoch 9, batch 750, loss[loss=0.1813, simple_loss=0.2571, pruned_loss=0.05273, over 7174.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2725, pruned_loss=0.05163, over 1389238.49 frames.], batch size: 18, lr: 8.45e-04
+2022-05-14 07:47:13,076 INFO [train.py:812] (7/8) Epoch 9, batch 800, loss[loss=0.1878, simple_loss=0.2777, pruned_loss=0.049, over 7368.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2718, pruned_loss=0.05141, over 1395594.02 frames.], batch size: 23, lr: 8.45e-04
+2022-05-14 07:48:11,344 INFO [train.py:812] (7/8) Epoch 9, batch 850, loss[loss=0.1758, simple_loss=0.2682, pruned_loss=0.04172, over 7315.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2729, pruned_loss=0.05235, over 1400703.56 frames.], batch size: 21, lr: 8.44e-04
+2022-05-14 07:49:11,233 INFO [train.py:812] (7/8) Epoch 9, batch 900, loss[loss=0.1825, simple_loss=0.279, pruned_loss=0.043, over 7225.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2734, pruned_loss=0.05238, over 1409694.37 frames.], batch size: 21, lr: 8.44e-04
+2022-05-14 07:50:10,514 INFO [train.py:812] (7/8) Epoch 9, batch 950, loss[loss=0.1791, simple_loss=0.2686, pruned_loss=0.04477, over 7333.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2738, pruned_loss=0.0529, over 1408234.06 frames.], batch size: 20, lr: 8.43e-04
+2022-05-14 07:51:10,508 INFO [train.py:812] (7/8) Epoch 9, batch 1000, loss[loss=0.175, simple_loss=0.2631, pruned_loss=0.04342, over 7422.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2727, pruned_loss=0.05257, over 1412387.81 frames.], batch size: 20, lr: 8.43e-04
+2022-05-14 07:52:08,979 INFO [train.py:812] (7/8) Epoch 9, batch 1050, loss[loss=0.1834, simple_loss=0.2654, pruned_loss=0.05072, over 7262.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2738, pruned_loss=0.05297, over 1416922.57 frames.], batch size: 19, lr: 8.42e-04
+2022-05-14 07:53:07,758 INFO [train.py:812] (7/8) Epoch 9, batch 1100, loss[loss=0.1659, simple_loss=0.2316, pruned_loss=0.05013, over 7279.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2758, pruned_loss=0.05392, over 1420044.92 frames.], batch size: 17, lr: 8.41e-04
+2022-05-14 07:54:04,884 INFO [train.py:812] (7/8) Epoch 9, batch 1150, loss[loss=0.2076, simple_loss=0.2897, pruned_loss=0.06274, over 7337.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2746, pruned_loss=0.05338, over 1421337.60 frames.], batch size: 25, lr: 8.41e-04
+2022-05-14 07:55:04,951 INFO [train.py:812] (7/8) Epoch 9, batch 1200, loss[loss=0.1783, simple_loss=0.2588, pruned_loss=0.04888, over 7429.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2735, pruned_loss=0.0525, over 1421835.01 frames.], batch size: 20, lr: 8.40e-04
+2022-05-14 07:56:02,865 INFO [train.py:812] (7/8) Epoch 9, batch 1250, loss[loss=0.2015, simple_loss=0.2775, pruned_loss=0.06278, over 6792.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2728, pruned_loss=0.05242, over 1417155.65 frames.], batch size: 15, lr: 8.40e-04
+2022-05-14 07:57:02,101 INFO [train.py:812] (7/8) Epoch 9, batch 1300, loss[loss=0.2213, simple_loss=0.3108, pruned_loss=0.06592, over 7172.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2733, pruned_loss=0.05279, over 1413551.64 frames.], batch size: 19, lr: 8.39e-04
+2022-05-14 07:58:01,362 INFO [train.py:812] (7/8) Epoch 9, batch 1350, loss[loss=0.1645, simple_loss=0.2447, pruned_loss=0.04214, over 7431.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2742, pruned_loss=0.05307, over 1418808.58 frames.], batch size: 20, lr: 8.39e-04
+2022-05-14 07:59:00,891 INFO [train.py:812] (7/8) Epoch 9, batch 1400, loss[loss=0.1934, simple_loss=0.2833, pruned_loss=0.05181, over 7227.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2741, pruned_loss=0.05326, over 1415025.75 frames.], batch size: 21, lr: 8.38e-04
+2022-05-14 07:59:57,911 INFO [train.py:812] (7/8) Epoch 9, batch 1450, loss[loss=0.1841, simple_loss=0.2803, pruned_loss=0.04396, over 7312.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2737, pruned_loss=0.05301, over 1419778.15 frames.], batch size: 21, lr: 8.38e-04
+2022-05-14 08:00:55,548 INFO [train.py:812] (7/8) Epoch 9, batch 1500, loss[loss=0.1912, simple_loss=0.2867, pruned_loss=0.04787, over 7238.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2737, pruned_loss=0.0528, over 1423138.29 frames.], batch size: 20, lr: 8.37e-04
+2022-05-14 08:01:53,824 INFO [train.py:812] (7/8) Epoch 9, batch 1550, loss[loss=0.2281, simple_loss=0.3079, pruned_loss=0.07413, over 7205.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2736, pruned_loss=0.05299, over 1422812.22 frames.], batch size: 22, lr: 8.37e-04
+2022-05-14 08:02:52,017 INFO [train.py:812] (7/8) Epoch 9, batch 1600, loss[loss=0.1492, simple_loss=0.2406, pruned_loss=0.02886, over 7065.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2733, pruned_loss=0.05255, over 1420830.62 frames.], batch size: 18, lr: 8.36e-04
+2022-05-14 08:03:49,522 INFO [train.py:812] (7/8) Epoch 9, batch 1650, loss[loss=0.2, simple_loss=0.2894, pruned_loss=0.05526, over 7115.00 frames.], tot_loss[loss=0.19, simple_loss=0.2742, pruned_loss=0.05296, over 1421458.83 frames.], batch size: 21, lr: 8.35e-04
+2022-05-14 08:04:47,921 INFO [train.py:812] (7/8) Epoch 9, batch 1700, loss[loss=0.1896, simple_loss=0.2758, pruned_loss=0.05168, over 7151.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2751, pruned_loss=0.053, over 1419846.09 frames.], batch size: 20, lr: 8.35e-04
+2022-05-14 08:05:46,564 INFO [train.py:812] (7/8) Epoch 9, batch 1750, loss[loss=0.1815, simple_loss=0.2706, pruned_loss=0.04617, over 7315.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2737, pruned_loss=0.0525, over 1420974.80 frames.], batch size: 21, lr: 8.34e-04
+2022-05-14 08:06:45,615 INFO [train.py:812] (7/8) Epoch 9, batch 1800, loss[loss=0.2064, simple_loss=0.2894, pruned_loss=0.06167, over 7233.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2738, pruned_loss=0.05252, over 1417320.29 frames.], batch size: 20, lr: 8.34e-04
+2022-05-14 08:07:45,004 INFO [train.py:812] (7/8) Epoch 9, batch 1850, loss[loss=0.1727, simple_loss=0.2657, pruned_loss=0.03983, over 7225.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2742, pruned_loss=0.05246, over 1420893.54 frames.], batch size: 20, lr: 8.33e-04
+2022-05-14 08:08:44,868 INFO [train.py:812] (7/8) Epoch 9, batch 1900, loss[loss=0.177, simple_loss=0.2668, pruned_loss=0.04363, over 7169.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2755, pruned_loss=0.05329, over 1419882.93 frames.], batch size: 19, lr: 8.33e-04
+2022-05-14 08:09:44,244 INFO [train.py:812] (7/8) Epoch 9, batch 1950, loss[loss=0.1946, simple_loss=0.2883, pruned_loss=0.05044, over 7118.00 frames.], tot_loss[loss=0.1902, simple_loss=0.275, pruned_loss=0.05271, over 1420907.63 frames.], batch size: 21, lr: 8.32e-04
+2022-05-14 08:10:44,128 INFO [train.py:812] (7/8) Epoch 9, batch 2000, loss[loss=0.201, simple_loss=0.2774, pruned_loss=0.06237, over 7282.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2745, pruned_loss=0.05283, over 1422431.05 frames.], batch size: 24, lr: 8.32e-04
+2022-05-14 08:11:43,590 INFO [train.py:812] (7/8) Epoch 9, batch 2050, loss[loss=0.1782, simple_loss=0.2552, pruned_loss=0.05057, over 7270.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2748, pruned_loss=0.0532, over 1420690.71 frames.], batch size: 17, lr: 8.31e-04
+2022-05-14 08:12:43,255 INFO [train.py:812] (7/8) Epoch 9, batch 2100, loss[loss=0.1759, simple_loss=0.257, pruned_loss=0.04737, over 7250.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2742, pruned_loss=0.05276, over 1422786.79 frames.], batch size: 19, lr: 8.31e-04
+2022-05-14 08:13:42,078 INFO [train.py:812] (7/8) Epoch 9, batch 2150, loss[loss=0.164, simple_loss=0.2463, pruned_loss=0.04086, over 7062.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2739, pruned_loss=0.05235, over 1424936.23 frames.], batch size: 18, lr: 8.30e-04
+2022-05-14 08:14:40,842 INFO [train.py:812] (7/8) Epoch 9, batch 2200, loss[loss=0.1342, simple_loss=0.216, pruned_loss=0.0262, over 7277.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2741, pruned_loss=0.0527, over 1423326.88 frames.], batch size: 17, lr: 8.30e-04
+2022-05-14 08:15:40,332 INFO [train.py:812] (7/8) Epoch 9, batch 2250, loss[loss=0.1612, simple_loss=0.2474, pruned_loss=0.03752, over 7158.00 frames.], tot_loss[loss=0.1897, simple_loss=0.274, pruned_loss=0.05274, over 1423759.76 frames.], batch size: 18, lr: 8.29e-04
+2022-05-14 08:16:40,212 INFO [train.py:812] (7/8) Epoch 9, batch 2300, loss[loss=0.2078, simple_loss=0.2942, pruned_loss=0.06075, over 7144.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2737, pruned_loss=0.05261, over 1425340.32 frames.], batch size: 20, lr: 8.29e-04
+2022-05-14 08:17:37,480 INFO [train.py:812] (7/8) Epoch 9, batch 2350, loss[loss=0.1936, simple_loss=0.2835, pruned_loss=0.05183, over 6752.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2743, pruned_loss=0.05267, over 1424079.48 frames.], batch size: 31, lr: 8.28e-04
+2022-05-14 08:18:37,039 INFO [train.py:812] (7/8) Epoch 9, batch 2400, loss[loss=0.1791, simple_loss=0.254, pruned_loss=0.05216, over 7272.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2744, pruned_loss=0.05306, over 1423962.19 frames.], batch size: 18, lr: 8.28e-04
+2022-05-14 08:19:36,173 INFO [train.py:812] (7/8) Epoch 9, batch 2450, loss[loss=0.1804, simple_loss=0.255, pruned_loss=0.05291, over 7405.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2739, pruned_loss=0.05242, over 1425743.36 frames.], batch size: 18, lr: 8.27e-04
+2022-05-14 08:20:34,881 INFO [train.py:812] (7/8) Epoch 9, batch 2500, loss[loss=0.1862, simple_loss=0.2774, pruned_loss=0.04748, over 7205.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2731, pruned_loss=0.05194, over 1423949.78 frames.], batch size: 22, lr: 8.27e-04
+2022-05-14 08:21:44,005 INFO [train.py:812] (7/8) Epoch 9, batch 2550, loss[loss=0.151, simple_loss=0.2317, pruned_loss=0.03516, over 7138.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2731, pruned_loss=0.05238, over 1420601.95 frames.], batch size: 17, lr: 8.26e-04
+2022-05-14 08:22:42,430 INFO [train.py:812] (7/8) Epoch 9, batch 2600, loss[loss=0.2931, simple_loss=0.3703, pruned_loss=0.108, over 7377.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2737, pruned_loss=0.05272, over 1418222.33 frames.], batch size: 23, lr: 8.25e-04
+2022-05-14 08:23:41,247 INFO [train.py:812] (7/8) Epoch 9, batch 2650, loss[loss=0.2175, simple_loss=0.2838, pruned_loss=0.07563, over 4968.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2737, pruned_loss=0.05249, over 1417381.42 frames.], batch size: 54, lr: 8.25e-04
+2022-05-14 08:24:39,395 INFO [train.py:812] (7/8) Epoch 9, batch 2700, loss[loss=0.2089, simple_loss=0.2987, pruned_loss=0.05959, over 7339.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2741, pruned_loss=0.05241, over 1418437.66 frames.], batch size: 22, lr: 8.24e-04
+2022-05-14 08:25:38,221 INFO [train.py:812] (7/8) Epoch 9, batch 2750, loss[loss=0.1538, simple_loss=0.2474, pruned_loss=0.03009, over 7333.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2725, pruned_loss=0.05136, over 1422768.03 frames.], batch size: 20, lr: 8.24e-04
+2022-05-14 08:26:37,750 INFO [train.py:812] (7/8) Epoch 9, batch 2800, loss[loss=0.2144, simple_loss=0.2936, pruned_loss=0.06758, over 7204.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2728, pruned_loss=0.05163, over 1426074.89 frames.], batch size: 22, lr: 8.23e-04
+2022-05-14 08:27:35,925 INFO [train.py:812] (7/8) Epoch 9, batch 2850, loss[loss=0.1899, simple_loss=0.2742, pruned_loss=0.05277, over 7165.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2722, pruned_loss=0.05121, over 1428984.02 frames.], batch size: 19, lr: 8.23e-04
+2022-05-14 08:28:33,967 INFO [train.py:812] (7/8) Epoch 9, batch 2900, loss[loss=0.1783, simple_loss=0.2738, pruned_loss=0.0414, over 7321.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2714, pruned_loss=0.05083, over 1427700.81 frames.], batch size: 21, lr: 8.22e-04
+2022-05-14 08:29:31,254 INFO [train.py:812] (7/8) Epoch 9, batch 2950, loss[loss=0.1871, simple_loss=0.2718, pruned_loss=0.05117, over 7289.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2728, pruned_loss=0.05134, over 1424001.91 frames.], batch size: 18, lr: 8.22e-04
+2022-05-14 08:30:30,220 INFO [train.py:812] (7/8) Epoch 9, batch 3000, loss[loss=0.1952, simple_loss=0.28, pruned_loss=0.05519, over 7267.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2724, pruned_loss=0.05129, over 1422046.86 frames.], batch size: 24, lr: 8.21e-04
+2022-05-14 08:30:30,222 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 08:30:38,337 INFO [train.py:841] (7/8) Epoch 9, validation: loss=0.1602, simple_loss=0.262, pruned_loss=0.0292, over 698248.00 frames.
+2022-05-14 08:31:37,186 INFO [train.py:812] (7/8) Epoch 9, batch 3050, loss[loss=0.198, simple_loss=0.2813, pruned_loss=0.05739, over 7320.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2725, pruned_loss=0.05179, over 1418970.27 frames.], batch size: 20, lr: 8.21e-04
+2022-05-14 08:32:34,712 INFO [train.py:812] (7/8) Epoch 9, batch 3100, loss[loss=0.2015, simple_loss=0.282, pruned_loss=0.06048, over 6839.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2741, pruned_loss=0.05273, over 1414461.38 frames.], batch size: 31, lr: 8.20e-04
+2022-05-14 08:33:32,696 INFO [train.py:812] (7/8) Epoch 9, batch 3150, loss[loss=0.1979, simple_loss=0.2899, pruned_loss=0.05293, over 7163.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2734, pruned_loss=0.05268, over 1418144.67 frames.], batch size: 19, lr: 8.20e-04
+2022-05-14 08:34:32,461 INFO [train.py:812] (7/8) Epoch 9, batch 3200, loss[loss=0.1764, simple_loss=0.2733, pruned_loss=0.0397, over 7139.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2728, pruned_loss=0.05235, over 1422067.62 frames.], batch size: 20, lr: 8.19e-04
+2022-05-14 08:35:31,374 INFO [train.py:812] (7/8) Epoch 9, batch 3250, loss[loss=0.2696, simple_loss=0.3437, pruned_loss=0.09774, over 5381.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2734, pruned_loss=0.05235, over 1420050.52 frames.], batch size: 52, lr: 8.19e-04
+2022-05-14 08:36:46,167 INFO [train.py:812] (7/8) Epoch 9, batch 3300, loss[loss=0.2178, simple_loss=0.3015, pruned_loss=0.06707, over 7207.00 frames.], tot_loss[loss=0.188, simple_loss=0.2726, pruned_loss=0.05172, over 1419545.84 frames.], batch size: 22, lr: 8.18e-04
+2022-05-14 08:37:52,690 INFO [train.py:812] (7/8) Epoch 9, batch 3350, loss[loss=0.177, simple_loss=0.2665, pruned_loss=0.0437, over 7272.00 frames.], tot_loss[loss=0.187, simple_loss=0.2719, pruned_loss=0.05108, over 1422765.84 frames.], batch size: 19, lr: 8.18e-04
+2022-05-14 08:38:51,560 INFO [train.py:812] (7/8) Epoch 9, batch 3400, loss[loss=0.2487, simple_loss=0.3317, pruned_loss=0.08286, over 6801.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2724, pruned_loss=0.05147, over 1421223.84 frames.], batch size: 31, lr: 8.17e-04
+2022-05-14 08:39:59,389 INFO [train.py:812] (7/8) Epoch 9, batch 3450, loss[loss=0.1804, simple_loss=0.2574, pruned_loss=0.05166, over 7427.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2724, pruned_loss=0.05106, over 1423486.91 frames.], batch size: 18, lr: 8.17e-04
+2022-05-14 08:41:27,462 INFO [train.py:812] (7/8) Epoch 9, batch 3500, loss[loss=0.1702, simple_loss=0.2527, pruned_loss=0.0438, over 7173.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2727, pruned_loss=0.05145, over 1424211.02 frames.], batch size: 19, lr: 8.16e-04
+2022-05-14 08:42:35,760 INFO [train.py:812] (7/8) Epoch 9, batch 3550, loss[loss=0.1821, simple_loss=0.2539, pruned_loss=0.05513, over 7164.00 frames.], tot_loss[loss=0.1872, simple_loss=0.272, pruned_loss=0.05116, over 1426096.66 frames.], batch size: 18, lr: 8.16e-04
+2022-05-14 08:43:34,808 INFO [train.py:812] (7/8) Epoch 9, batch 3600, loss[loss=0.1677, simple_loss=0.2445, pruned_loss=0.04549, over 7277.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2724, pruned_loss=0.05125, over 1424546.01 frames.], batch size: 18, lr: 8.15e-04
+2022-05-14 08:44:32,198 INFO [train.py:812] (7/8) Epoch 9, batch 3650, loss[loss=0.1603, simple_loss=0.2386, pruned_loss=0.04099, over 7143.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2715, pruned_loss=0.05092, over 1426045.51 frames.], batch size: 17, lr: 8.15e-04
+2022-05-14 08:45:31,328 INFO [train.py:812] (7/8) Epoch 9, batch 3700, loss[loss=0.1597, simple_loss=0.2589, pruned_loss=0.03023, over 7335.00 frames.], tot_loss[loss=0.187, simple_loss=0.272, pruned_loss=0.05094, over 1426644.75 frames.], batch size: 25, lr: 8.14e-04
+2022-05-14 08:46:29,976 INFO [train.py:812] (7/8) Epoch 9, batch 3750, loss[loss=0.1995, simple_loss=0.2884, pruned_loss=0.05534, over 7430.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2727, pruned_loss=0.05103, over 1425604.96 frames.], batch size: 20, lr: 8.14e-04
+2022-05-14 08:47:28,955 INFO [train.py:812] (7/8) Epoch 9, batch 3800, loss[loss=0.1693, simple_loss=0.2575, pruned_loss=0.04049, over 7411.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2732, pruned_loss=0.05176, over 1428440.21 frames.], batch size: 18, lr: 8.13e-04
+2022-05-14 08:48:27,820 INFO [train.py:812] (7/8) Epoch 9, batch 3850, loss[loss=0.174, simple_loss=0.2535, pruned_loss=0.04724, over 7275.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2736, pruned_loss=0.05226, over 1430053.67 frames.], batch size: 17, lr: 8.13e-04
+2022-05-14 08:49:26,826 INFO [train.py:812] (7/8) Epoch 9, batch 3900, loss[loss=0.2407, simple_loss=0.3017, pruned_loss=0.08988, over 5079.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2744, pruned_loss=0.05255, over 1427684.48 frames.], batch size: 52, lr: 8.12e-04
+2022-05-14 08:50:26,285 INFO [train.py:812] (7/8) Epoch 9, batch 3950, loss[loss=0.2272, simple_loss=0.2987, pruned_loss=0.0778, over 6821.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2739, pruned_loss=0.05238, over 1428904.48 frames.], batch size: 31, lr: 8.12e-04
+2022-05-14 08:51:25,814 INFO [train.py:812] (7/8) Epoch 9, batch 4000, loss[loss=0.1834, simple_loss=0.2726, pruned_loss=0.04707, over 7231.00 frames.], tot_loss[loss=0.1906, simple_loss=0.275, pruned_loss=0.05307, over 1428331.61 frames.], batch size: 21, lr: 8.11e-04
+2022-05-14 08:52:25,232 INFO [train.py:812] (7/8) Epoch 9, batch 4050, loss[loss=0.181, simple_loss=0.2681, pruned_loss=0.04697, over 7406.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2731, pruned_loss=0.05231, over 1426624.17 frames.], batch size: 18, lr: 8.11e-04
+2022-05-14 08:53:25,011 INFO [train.py:812] (7/8) Epoch 9, batch 4100, loss[loss=0.1744, simple_loss=0.2455, pruned_loss=0.05167, over 7116.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2727, pruned_loss=0.0521, over 1427184.57 frames.], batch size: 17, lr: 8.10e-04
+2022-05-14 08:54:24,697 INFO [train.py:812] (7/8) Epoch 9, batch 4150, loss[loss=0.2009, simple_loss=0.2922, pruned_loss=0.0548, over 7130.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2728, pruned_loss=0.052, over 1422325.83 frames.], batch size: 28, lr: 8.10e-04
+2022-05-14 08:55:24,402 INFO [train.py:812] (7/8) Epoch 9, batch 4200, loss[loss=0.1708, simple_loss=0.2605, pruned_loss=0.04051, over 7319.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2713, pruned_loss=0.05123, over 1423214.05 frames.], batch size: 20, lr: 8.09e-04
+2022-05-14 08:56:23,029 INFO [train.py:812] (7/8) Epoch 9, batch 4250, loss[loss=0.1476, simple_loss=0.2264, pruned_loss=0.03441, over 7139.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2707, pruned_loss=0.05124, over 1419567.87 frames.], batch size: 17, lr: 8.09e-04
+2022-05-14 08:57:23,003 INFO [train.py:812] (7/8) Epoch 9, batch 4300, loss[loss=0.1922, simple_loss=0.2858, pruned_loss=0.04924, over 7405.00 frames.], tot_loss[loss=0.187, simple_loss=0.2709, pruned_loss=0.05157, over 1415262.84 frames.], batch size: 21, lr: 8.08e-04
+2022-05-14 08:58:21,497 INFO [train.py:812] (7/8) Epoch 9, batch 4350, loss[loss=0.1348, simple_loss=0.225, pruned_loss=0.02228, over 7263.00 frames.], tot_loss[loss=0.186, simple_loss=0.2701, pruned_loss=0.05089, over 1420940.67 frames.], batch size: 17, lr: 8.08e-04
+2022-05-14 08:59:21,277 INFO [train.py:812] (7/8) Epoch 9, batch 4400, loss[loss=0.1582, simple_loss=0.2535, pruned_loss=0.03151, over 7099.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2696, pruned_loss=0.0508, over 1417056.17 frames.], batch size: 28, lr: 8.07e-04
+2022-05-14 09:00:19,292 INFO [train.py:812] (7/8) Epoch 9, batch 4450, loss[loss=0.2113, simple_loss=0.3042, pruned_loss=0.05918, over 7093.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2683, pruned_loss=0.05088, over 1412312.52 frames.], batch size: 28, lr: 8.07e-04
+2022-05-14 09:01:19,112 INFO [train.py:812] (7/8) Epoch 9, batch 4500, loss[loss=0.1763, simple_loss=0.2673, pruned_loss=0.0426, over 7126.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2707, pruned_loss=0.05247, over 1395410.68 frames.], batch size: 28, lr: 8.07e-04
+2022-05-14 09:02:17,097 INFO [train.py:812] (7/8) Epoch 9, batch 4550, loss[loss=0.2046, simple_loss=0.2853, pruned_loss=0.06197, over 6355.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2746, pruned_loss=0.05496, over 1355792.81 frames.], batch size: 37, lr: 8.06e-04
+2022-05-14 09:03:24,815 INFO [train.py:812] (7/8) Epoch 10, batch 0, loss[loss=0.1826, simple_loss=0.2702, pruned_loss=0.04756, over 7421.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2702, pruned_loss=0.04756, over 7421.00 frames.], batch size: 21, lr: 7.75e-04
+2022-05-14 09:04:24,026 INFO [train.py:812] (7/8) Epoch 10, batch 50, loss[loss=0.2311, simple_loss=0.3225, pruned_loss=0.06989, over 7190.00 frames.], tot_loss[loss=0.1885, simple_loss=0.274, pruned_loss=0.05154, over 321247.25 frames.], batch size: 23, lr: 7.74e-04
+2022-05-14 09:05:23,114 INFO [train.py:812] (7/8) Epoch 10, batch 100, loss[loss=0.2221, simple_loss=0.296, pruned_loss=0.07406, over 5215.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2705, pruned_loss=0.05113, over 556666.27 frames.], batch size: 53, lr: 7.74e-04
+2022-05-14 09:06:22,316 INFO [train.py:812] (7/8) Epoch 10, batch 150, loss[loss=0.1569, simple_loss=0.2405, pruned_loss=0.03664, over 7426.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2717, pruned_loss=0.0511, over 750059.00 frames.], batch size: 20, lr: 7.73e-04
+2022-05-14 09:07:20,640 INFO [train.py:812] (7/8) Epoch 10, batch 200, loss[loss=0.1857, simple_loss=0.2759, pruned_loss=0.04772, over 7435.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2716, pruned_loss=0.05065, over 898723.69 frames.], batch size: 20, lr: 7.73e-04
+2022-05-14 09:08:19,911 INFO [train.py:812] (7/8) Epoch 10, batch 250, loss[loss=0.1509, simple_loss=0.2366, pruned_loss=0.0326, over 7169.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2729, pruned_loss=0.05096, over 1011813.48 frames.], batch size: 18, lr: 7.72e-04
+2022-05-14 09:09:19,101 INFO [train.py:812] (7/8) Epoch 10, batch 300, loss[loss=0.1486, simple_loss=0.2434, pruned_loss=0.02687, over 7327.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2732, pruned_loss=0.05147, over 1104575.31 frames.], batch size: 20, lr: 7.72e-04
+2022-05-14 09:10:16,363 INFO [train.py:812] (7/8) Epoch 10, batch 350, loss[loss=0.2004, simple_loss=0.287, pruned_loss=0.05692, over 7198.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2716, pruned_loss=0.05067, over 1173439.98 frames.], batch size: 23, lr: 7.71e-04
+2022-05-14 09:11:15,075 INFO [train.py:812] (7/8) Epoch 10, batch 400, loss[loss=0.1975, simple_loss=0.285, pruned_loss=0.05501, over 7207.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2717, pruned_loss=0.05036, over 1223245.07 frames.], batch size: 26, lr: 7.71e-04
+2022-05-14 09:12:14,078 INFO [train.py:812] (7/8) Epoch 10, batch 450, loss[loss=0.1972, simple_loss=0.2852, pruned_loss=0.05463, over 6503.00 frames.], tot_loss[loss=0.1861, simple_loss=0.272, pruned_loss=0.05015, over 1261111.10 frames.], batch size: 38, lr: 7.71e-04
+2022-05-14 09:13:13,647 INFO [train.py:812] (7/8) Epoch 10, batch 500, loss[loss=0.1922, simple_loss=0.2679, pruned_loss=0.05828, over 7159.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2722, pruned_loss=0.05051, over 1296213.70 frames.], batch size: 19, lr: 7.70e-04
+2022-05-14 09:14:12,284 INFO [train.py:812] (7/8) Epoch 10, batch 550, loss[loss=0.1328, simple_loss=0.2143, pruned_loss=0.02565, over 7152.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2712, pruned_loss=0.04984, over 1324727.29 frames.], batch size: 17, lr: 7.70e-04
+2022-05-14 09:15:10,155 INFO [train.py:812] (7/8) Epoch 10, batch 600, loss[loss=0.1567, simple_loss=0.2317, pruned_loss=0.04082, over 7282.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2715, pruned_loss=0.04995, over 1346321.38 frames.], batch size: 18, lr: 7.69e-04
+2022-05-14 09:16:08,340 INFO [train.py:812] (7/8) Epoch 10, batch 650, loss[loss=0.1636, simple_loss=0.2565, pruned_loss=0.03535, over 7142.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2714, pruned_loss=0.04985, over 1362610.31 frames.], batch size: 26, lr: 7.69e-04
+2022-05-14 09:17:07,960 INFO [train.py:812] (7/8) Epoch 10, batch 700, loss[loss=0.2186, simple_loss=0.3044, pruned_loss=0.06644, over 7308.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2712, pruned_loss=0.04962, over 1377041.14 frames.], batch size: 25, lr: 7.68e-04
+2022-05-14 09:18:07,560 INFO [train.py:812] (7/8) Epoch 10, batch 750, loss[loss=0.195, simple_loss=0.28, pruned_loss=0.05498, over 7431.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2706, pruned_loss=0.04953, over 1387617.11 frames.], batch size: 20, lr: 7.68e-04
+2022-05-14 09:19:06,555 INFO [train.py:812] (7/8) Epoch 10, batch 800, loss[loss=0.2222, simple_loss=0.3045, pruned_loss=0.06996, over 7292.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2711, pruned_loss=0.05, over 1394286.58 frames.], batch size: 24, lr: 7.67e-04
+2022-05-14 09:20:06,017 INFO [train.py:812] (7/8) Epoch 10, batch 850, loss[loss=0.192, simple_loss=0.2754, pruned_loss=0.05428, over 6324.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2715, pruned_loss=0.04999, over 1397192.84 frames.], batch size: 38, lr: 7.67e-04
+2022-05-14 09:21:05,093 INFO [train.py:812] (7/8) Epoch 10, batch 900, loss[loss=0.1764, simple_loss=0.2753, pruned_loss=0.03878, over 7322.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2705, pruned_loss=0.04943, over 1406936.05 frames.], batch size: 21, lr: 7.66e-04
+2022-05-14 09:22:03,800 INFO [train.py:812] (7/8) Epoch 10, batch 950, loss[loss=0.2123, simple_loss=0.3013, pruned_loss=0.06162, over 7202.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2715, pruned_loss=0.04994, over 1407235.93 frames.], batch size: 26, lr: 7.66e-04
+2022-05-14 09:23:02,578 INFO [train.py:812] (7/8) Epoch 10, batch 1000, loss[loss=0.1883, simple_loss=0.2792, pruned_loss=0.04869, over 7330.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2706, pruned_loss=0.04962, over 1414562.01 frames.], batch size: 20, lr: 7.66e-04
+2022-05-14 09:24:00,845 INFO [train.py:812] (7/8) Epoch 10, batch 1050, loss[loss=0.1675, simple_loss=0.2584, pruned_loss=0.03829, over 7041.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2702, pruned_loss=0.04946, over 1416709.01 frames.], batch size: 28, lr: 7.65e-04
+2022-05-14 09:24:59,389 INFO [train.py:812] (7/8) Epoch 10, batch 1100, loss[loss=0.2024, simple_loss=0.2748, pruned_loss=0.065, over 7040.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2709, pruned_loss=0.04987, over 1417141.06 frames.], batch size: 28, lr: 7.65e-04
+2022-05-14 09:25:57,301 INFO [train.py:812] (7/8) Epoch 10, batch 1150, loss[loss=0.1707, simple_loss=0.2639, pruned_loss=0.03877, over 7325.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2705, pruned_loss=0.04964, over 1421273.19 frames.], batch size: 20, lr: 7.64e-04
+2022-05-14 09:26:55,778 INFO [train.py:812] (7/8) Epoch 10, batch 1200, loss[loss=0.2228, simple_loss=0.309, pruned_loss=0.06834, over 7207.00 frames.], tot_loss[loss=0.1866, simple_loss=0.272, pruned_loss=0.05053, over 1420200.73 frames.], batch size: 23, lr: 7.64e-04
+2022-05-14 09:27:55,431 INFO [train.py:812] (7/8) Epoch 10, batch 1250, loss[loss=0.1786, simple_loss=0.25, pruned_loss=0.05364, over 7285.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2716, pruned_loss=0.05038, over 1419210.22 frames.], batch size: 17, lr: 7.63e-04
+2022-05-14 09:28:54,720 INFO [train.py:812] (7/8) Epoch 10, batch 1300, loss[loss=0.1645, simple_loss=0.2319, pruned_loss=0.04855, over 7009.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2709, pruned_loss=0.05064, over 1417449.10 frames.], batch size: 16, lr: 7.63e-04
+2022-05-14 09:29:54,208 INFO [train.py:812] (7/8) Epoch 10, batch 1350, loss[loss=0.163, simple_loss=0.2554, pruned_loss=0.03533, over 7316.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2705, pruned_loss=0.0506, over 1415953.96 frames.], batch size: 21, lr: 7.62e-04
+2022-05-14 09:30:53,036 INFO [train.py:812] (7/8) Epoch 10, batch 1400, loss[loss=0.1755, simple_loss=0.2636, pruned_loss=0.04375, over 7111.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2714, pruned_loss=0.05038, over 1419195.56 frames.], batch size: 21, lr: 7.62e-04
+2022-05-14 09:31:52,549 INFO [train.py:812] (7/8) Epoch 10, batch 1450, loss[loss=0.2575, simple_loss=0.3302, pruned_loss=0.09233, over 7302.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2715, pruned_loss=0.05067, over 1420172.33 frames.], batch size: 25, lr: 7.62e-04
+2022-05-14 09:32:51,564 INFO [train.py:812] (7/8) Epoch 10, batch 1500, loss[loss=0.2286, simple_loss=0.299, pruned_loss=0.07909, over 4970.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2722, pruned_loss=0.05096, over 1414911.08 frames.], batch size: 52, lr: 7.61e-04
+2022-05-14 09:33:51,514 INFO [train.py:812] (7/8) Epoch 10, batch 1550, loss[loss=0.1768, simple_loss=0.2563, pruned_loss=0.04861, over 7354.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2723, pruned_loss=0.05072, over 1418020.49 frames.], batch size: 19, lr: 7.61e-04
+2022-05-14 09:34:49,194 INFO [train.py:812] (7/8) Epoch 10, batch 1600, loss[loss=0.2363, simple_loss=0.3123, pruned_loss=0.08014, over 7256.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2723, pruned_loss=0.0509, over 1417491.85 frames.], batch size: 19, lr: 7.60e-04
+2022-05-14 09:35:46,404 INFO [train.py:812] (7/8) Epoch 10, batch 1650, loss[loss=0.1807, simple_loss=0.273, pruned_loss=0.04418, over 7404.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2716, pruned_loss=0.05065, over 1415651.64 frames.], batch size: 21, lr: 7.60e-04
+2022-05-14 09:36:44,435 INFO [train.py:812] (7/8) Epoch 10, batch 1700, loss[loss=0.2014, simple_loss=0.2946, pruned_loss=0.05409, over 7265.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2707, pruned_loss=0.05021, over 1414187.08 frames.], batch size: 24, lr: 7.59e-04
+2022-05-14 09:37:43,582 INFO [train.py:812] (7/8) Epoch 10, batch 1750, loss[loss=0.1618, simple_loss=0.2438, pruned_loss=0.03992, over 6745.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2717, pruned_loss=0.05074, over 1405689.85 frames.], batch size: 15, lr: 7.59e-04
+2022-05-14 09:38:41,662 INFO [train.py:812] (7/8) Epoch 10, batch 1800, loss[loss=0.1936, simple_loss=0.2822, pruned_loss=0.05251, over 7352.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2713, pruned_loss=0.0508, over 1410320.18 frames.], batch size: 19, lr: 7.59e-04
+2022-05-14 09:39:39,866 INFO [train.py:812] (7/8) Epoch 10, batch 1850, loss[loss=0.1875, simple_loss=0.2765, pruned_loss=0.04925, over 7353.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2714, pruned_loss=0.05073, over 1411301.16 frames.], batch size: 19, lr: 7.58e-04
+2022-05-14 09:40:38,506 INFO [train.py:812] (7/8) Epoch 10, batch 1900, loss[loss=0.1483, simple_loss=0.2367, pruned_loss=0.02988, over 7276.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2708, pruned_loss=0.04993, over 1415276.97 frames.], batch size: 18, lr: 7.58e-04
+2022-05-14 09:41:37,167 INFO [train.py:812] (7/8) Epoch 10, batch 1950, loss[loss=0.2079, simple_loss=0.2875, pruned_loss=0.06415, over 7195.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2703, pruned_loss=0.0495, over 1414711.54 frames.], batch size: 23, lr: 7.57e-04
+2022-05-14 09:42:35,072 INFO [train.py:812] (7/8) Epoch 10, batch 2000, loss[loss=0.1981, simple_loss=0.2948, pruned_loss=0.05068, over 7231.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2696, pruned_loss=0.04915, over 1418300.23 frames.], batch size: 20, lr: 7.57e-04
+2022-05-14 09:43:34,883 INFO [train.py:812] (7/8) Epoch 10, batch 2050, loss[loss=0.1885, simple_loss=0.2786, pruned_loss=0.04917, over 7175.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2701, pruned_loss=0.04981, over 1420296.90 frames.], batch size: 23, lr: 7.56e-04
+2022-05-14 09:44:34,096 INFO [train.py:812] (7/8) Epoch 10, batch 2100, loss[loss=0.1904, simple_loss=0.2715, pruned_loss=0.05463, over 7147.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2698, pruned_loss=0.04951, over 1424950.20 frames.], batch size: 20, lr: 7.56e-04
+2022-05-14 09:45:31,454 INFO [train.py:812] (7/8) Epoch 10, batch 2150, loss[loss=0.185, simple_loss=0.2633, pruned_loss=0.05339, over 7417.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2682, pruned_loss=0.04882, over 1426960.46 frames.], batch size: 18, lr: 7.56e-04
+2022-05-14 09:46:28,666 INFO [train.py:812] (7/8) Epoch 10, batch 2200, loss[loss=0.2071, simple_loss=0.287, pruned_loss=0.06358, over 6048.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2692, pruned_loss=0.04915, over 1426775.46 frames.], batch size: 37, lr: 7.55e-04
+2022-05-14 09:47:27,379 INFO [train.py:812] (7/8) Epoch 10, batch 2250, loss[loss=0.1987, simple_loss=0.2897, pruned_loss=0.05386, over 7326.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2691, pruned_loss=0.04918, over 1428442.95 frames.], batch size: 21, lr: 7.55e-04
+2022-05-14 09:48:25,603 INFO [train.py:812] (7/8) Epoch 10, batch 2300, loss[loss=0.1656, simple_loss=0.255, pruned_loss=0.03808, over 7153.00 frames.], tot_loss[loss=0.184, simple_loss=0.2696, pruned_loss=0.04921, over 1426688.58 frames.], batch size: 20, lr: 7.54e-04
+2022-05-14 09:49:24,938 INFO [train.py:812] (7/8) Epoch 10, batch 2350, loss[loss=0.2054, simple_loss=0.2875, pruned_loss=0.06163, over 7217.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2691, pruned_loss=0.04918, over 1425643.53 frames.], batch size: 22, lr: 7.54e-04
+2022-05-14 09:50:22,148 INFO [train.py:812] (7/8) Epoch 10, batch 2400, loss[loss=0.1919, simple_loss=0.2739, pruned_loss=0.05495, over 7278.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2687, pruned_loss=0.04895, over 1427049.26 frames.], batch size: 18, lr: 7.53e-04
+2022-05-14 09:51:20,807 INFO [train.py:812] (7/8) Epoch 10, batch 2450, loss[loss=0.1638, simple_loss=0.2539, pruned_loss=0.03683, over 7067.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2689, pruned_loss=0.04934, over 1430776.88 frames.], batch size: 18, lr: 7.53e-04
+2022-05-14 09:52:18,439 INFO [train.py:812] (7/8) Epoch 10, batch 2500, loss[loss=0.1978, simple_loss=0.286, pruned_loss=0.05478, over 7320.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2693, pruned_loss=0.04946, over 1428526.47 frames.], batch size: 21, lr: 7.53e-04
+2022-05-14 09:53:18,342 INFO [train.py:812] (7/8) Epoch 10, batch 2550, loss[loss=0.1957, simple_loss=0.2853, pruned_loss=0.05305, over 7221.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2691, pruned_loss=0.0493, over 1426165.52 frames.], batch size: 21, lr: 7.52e-04
+2022-05-14 09:54:18,087 INFO [train.py:812] (7/8) Epoch 10, batch 2600, loss[loss=0.2352, simple_loss=0.3192, pruned_loss=0.07562, over 7151.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2697, pruned_loss=0.04996, over 1429443.73 frames.], batch size: 26, lr: 7.52e-04
+2022-05-14 09:55:17,749 INFO [train.py:812] (7/8) Epoch 10, batch 2650, loss[loss=0.1955, simple_loss=0.292, pruned_loss=0.04949, over 7338.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2707, pruned_loss=0.05022, over 1425487.40 frames.], batch size: 22, lr: 7.51e-04
+2022-05-14 09:56:16,836 INFO [train.py:812] (7/8) Epoch 10, batch 2700, loss[loss=0.1969, simple_loss=0.2823, pruned_loss=0.05579, over 6771.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2698, pruned_loss=0.04996, over 1426476.42 frames.], batch size: 31, lr: 7.51e-04
+2022-05-14 09:57:23,641 INFO [train.py:812] (7/8) Epoch 10, batch 2750, loss[loss=0.1825, simple_loss=0.2727, pruned_loss=0.04618, over 6684.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2698, pruned_loss=0.04981, over 1424156.84 frames.], batch size: 31, lr: 7.50e-04
+2022-05-14 09:58:22,167 INFO [train.py:812] (7/8) Epoch 10, batch 2800, loss[loss=0.1853, simple_loss=0.2746, pruned_loss=0.04804, over 7385.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2691, pruned_loss=0.04936, over 1429588.52 frames.], batch size: 23, lr: 7.50e-04
+2022-05-14 09:59:21,356 INFO [train.py:812] (7/8) Epoch 10, batch 2850, loss[loss=0.1801, simple_loss=0.2727, pruned_loss=0.04374, over 7345.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2702, pruned_loss=0.04998, over 1427872.81 frames.], batch size: 22, lr: 7.50e-04
+2022-05-14 10:00:20,893 INFO [train.py:812] (7/8) Epoch 10, batch 2900, loss[loss=0.1711, simple_loss=0.2689, pruned_loss=0.03669, over 7103.00 frames.], tot_loss[loss=0.185, simple_loss=0.27, pruned_loss=0.04994, over 1427082.75 frames.], batch size: 21, lr: 7.49e-04
+2022-05-14 10:01:19,239 INFO [train.py:812] (7/8) Epoch 10, batch 2950, loss[loss=0.1762, simple_loss=0.2458, pruned_loss=0.05328, over 7277.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2691, pruned_loss=0.04974, over 1426841.41 frames.], batch size: 18, lr: 7.49e-04
+2022-05-14 10:02:18,304 INFO [train.py:812] (7/8) Epoch 10, batch 3000, loss[loss=0.1626, simple_loss=0.2388, pruned_loss=0.04317, over 7292.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2694, pruned_loss=0.05, over 1425949.12 frames.], batch size: 17, lr: 7.48e-04
+2022-05-14 10:02:18,305 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 10:02:25,810 INFO [train.py:841] (7/8) Epoch 10, validation: loss=0.1584, simple_loss=0.26, pruned_loss=0.0284, over 698248.00 frames.
+2022-05-14 10:03:25,437 INFO [train.py:812] (7/8) Epoch 10, batch 3050, loss[loss=0.1879, simple_loss=0.2819, pruned_loss=0.04696, over 7161.00 frames.], tot_loss[loss=0.184, simple_loss=0.2686, pruned_loss=0.04974, over 1426474.88 frames.], batch size: 19, lr: 7.48e-04
+2022-05-14 10:04:24,570 INFO [train.py:812] (7/8) Epoch 10, batch 3100, loss[loss=0.175, simple_loss=0.2683, pruned_loss=0.04088, over 7111.00 frames.], tot_loss[loss=0.184, simple_loss=0.2691, pruned_loss=0.0494, over 1429588.81 frames.], batch size: 21, lr: 7.47e-04
+2022-05-14 10:05:24,326 INFO [train.py:812] (7/8) Epoch 10, batch 3150, loss[loss=0.211, simple_loss=0.3047, pruned_loss=0.05862, over 7316.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2696, pruned_loss=0.04988, over 1425493.78 frames.], batch size: 21, lr: 7.47e-04
+2022-05-14 10:06:23,671 INFO [train.py:812] (7/8) Epoch 10, batch 3200, loss[loss=0.1636, simple_loss=0.2582, pruned_loss=0.03452, over 7237.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2686, pruned_loss=0.0491, over 1426354.04 frames.], batch size: 20, lr: 7.47e-04
+2022-05-14 10:07:23,050 INFO [train.py:812] (7/8) Epoch 10, batch 3250, loss[loss=0.1863, simple_loss=0.2799, pruned_loss=0.04634, over 7400.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2695, pruned_loss=0.04948, over 1428013.65 frames.], batch size: 21, lr: 7.46e-04
+2022-05-14 10:08:22,172 INFO [train.py:812] (7/8) Epoch 10, batch 3300, loss[loss=0.178, simple_loss=0.2715, pruned_loss=0.04229, over 7208.00 frames.], tot_loss[loss=0.184, simple_loss=0.2695, pruned_loss=0.04922, over 1428699.25 frames.], batch size: 22, lr: 7.46e-04
+2022-05-14 10:09:21,738 INFO [train.py:812] (7/8) Epoch 10, batch 3350, loss[loss=0.1863, simple_loss=0.2791, pruned_loss=0.04673, over 7197.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2697, pruned_loss=0.04932, over 1430186.05 frames.], batch size: 23, lr: 7.45e-04
+2022-05-14 10:10:20,645 INFO [train.py:812] (7/8) Epoch 10, batch 3400, loss[loss=0.1345, simple_loss=0.2182, pruned_loss=0.02538, over 7282.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2698, pruned_loss=0.04972, over 1426128.24 frames.], batch size: 17, lr: 7.45e-04
+2022-05-14 10:11:20,123 INFO [train.py:812] (7/8) Epoch 10, batch 3450, loss[loss=0.2053, simple_loss=0.2881, pruned_loss=0.0613, over 7279.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2701, pruned_loss=0.04988, over 1425671.37 frames.], batch size: 24, lr: 7.45e-04
+2022-05-14 10:12:19,099 INFO [train.py:812] (7/8) Epoch 10, batch 3500, loss[loss=0.1953, simple_loss=0.2954, pruned_loss=0.0476, over 7403.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2702, pruned_loss=0.04981, over 1425678.58 frames.], batch size: 21, lr: 7.44e-04
+2022-05-14 10:13:18,729 INFO [train.py:812] (7/8) Epoch 10, batch 3550, loss[loss=0.2034, simple_loss=0.2959, pruned_loss=0.05548, over 7029.00 frames.], tot_loss[loss=0.1838, simple_loss=0.269, pruned_loss=0.04932, over 1428311.97 frames.], batch size: 28, lr: 7.44e-04
+2022-05-14 10:14:16,927 INFO [train.py:812] (7/8) Epoch 10, batch 3600, loss[loss=0.2264, simple_loss=0.3044, pruned_loss=0.07423, over 7131.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2685, pruned_loss=0.04912, over 1428039.96 frames.], batch size: 28, lr: 7.43e-04
+2022-05-14 10:15:16,480 INFO [train.py:812] (7/8) Epoch 10, batch 3650, loss[loss=0.1913, simple_loss=0.2671, pruned_loss=0.05774, over 7064.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2687, pruned_loss=0.0494, over 1424235.98 frames.], batch size: 18, lr: 7.43e-04
+2022-05-14 10:16:15,519 INFO [train.py:812] (7/8) Epoch 10, batch 3700, loss[loss=0.1428, simple_loss=0.2232, pruned_loss=0.03118, over 7308.00 frames.], tot_loss[loss=0.1835, simple_loss=0.269, pruned_loss=0.04898, over 1426581.74 frames.], batch size: 17, lr: 7.43e-04
+2022-05-14 10:17:15,232 INFO [train.py:812] (7/8) Epoch 10, batch 3750, loss[loss=0.1823, simple_loss=0.2619, pruned_loss=0.05139, over 7154.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2703, pruned_loss=0.0494, over 1428509.39 frames.], batch size: 19, lr: 7.42e-04
+2022-05-14 10:18:14,403 INFO [train.py:812] (7/8) Epoch 10, batch 3800, loss[loss=0.1905, simple_loss=0.274, pruned_loss=0.05351, over 7430.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2698, pruned_loss=0.04924, over 1426341.90 frames.], batch size: 20, lr: 7.42e-04
+2022-05-14 10:19:12,979 INFO [train.py:812] (7/8) Epoch 10, batch 3850, loss[loss=0.1506, simple_loss=0.2367, pruned_loss=0.03227, over 7054.00 frames.], tot_loss[loss=0.1839, simple_loss=0.27, pruned_loss=0.04884, over 1425586.75 frames.], batch size: 18, lr: 7.41e-04
+2022-05-14 10:20:21,781 INFO [train.py:812] (7/8) Epoch 10, batch 3900, loss[loss=0.1566, simple_loss=0.2429, pruned_loss=0.03515, over 7157.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2695, pruned_loss=0.04876, over 1426826.73 frames.], batch size: 19, lr: 7.41e-04
+2022-05-14 10:21:21,343 INFO [train.py:812] (7/8) Epoch 10, batch 3950, loss[loss=0.2504, simple_loss=0.325, pruned_loss=0.08796, over 5246.00 frames.], tot_loss[loss=0.183, simple_loss=0.269, pruned_loss=0.0485, over 1420766.27 frames.], batch size: 52, lr: 7.41e-04
+2022-05-14 10:22:19,918 INFO [train.py:812] (7/8) Epoch 10, batch 4000, loss[loss=0.1673, simple_loss=0.2556, pruned_loss=0.0395, over 7267.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2696, pruned_loss=0.04889, over 1421660.21 frames.], batch size: 19, lr: 7.40e-04
+2022-05-14 10:23:18,836 INFO [train.py:812] (7/8) Epoch 10, batch 4050, loss[loss=0.1907, simple_loss=0.27, pruned_loss=0.05568, over 7138.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2702, pruned_loss=0.04921, over 1422021.59 frames.], batch size: 17, lr: 7.40e-04
+2022-05-14 10:24:17,014 INFO [train.py:812] (7/8) Epoch 10, batch 4100, loss[loss=0.1781, simple_loss=0.2803, pruned_loss=0.038, over 7316.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2703, pruned_loss=0.04923, over 1424247.10 frames.], batch size: 21, lr: 7.39e-04
+2022-05-14 10:25:16,606 INFO [train.py:812] (7/8) Epoch 10, batch 4150, loss[loss=0.1705, simple_loss=0.2537, pruned_loss=0.04367, over 7424.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2695, pruned_loss=0.0488, over 1424909.78 frames.], batch size: 18, lr: 7.39e-04
+2022-05-14 10:26:14,805 INFO [train.py:812] (7/8) Epoch 10, batch 4200, loss[loss=0.191, simple_loss=0.2879, pruned_loss=0.04703, over 7290.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2701, pruned_loss=0.04939, over 1426947.62 frames.], batch size: 24, lr: 7.39e-04
+2022-05-14 10:27:13,959 INFO [train.py:812] (7/8) Epoch 10, batch 4250, loss[loss=0.1534, simple_loss=0.2327, pruned_loss=0.03705, over 7286.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2702, pruned_loss=0.04956, over 1422077.87 frames.], batch size: 17, lr: 7.38e-04
+2022-05-14 10:28:13,123 INFO [train.py:812] (7/8) Epoch 10, batch 4300, loss[loss=0.2035, simple_loss=0.304, pruned_loss=0.05152, over 7303.00 frames.], tot_loss[loss=0.186, simple_loss=0.2714, pruned_loss=0.05033, over 1416507.51 frames.], batch size: 24, lr: 7.38e-04
+2022-05-14 10:29:10,987 INFO [train.py:812] (7/8) Epoch 10, batch 4350, loss[loss=0.2015, simple_loss=0.2808, pruned_loss=0.06108, over 5404.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2726, pruned_loss=0.05101, over 1407682.78 frames.], batch size: 52, lr: 7.37e-04
+2022-05-14 10:30:10,279 INFO [train.py:812] (7/8) Epoch 10, batch 4400, loss[loss=0.1819, simple_loss=0.2797, pruned_loss=0.04204, over 7215.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2733, pruned_loss=0.05116, over 1410249.96 frames.], batch size: 22, lr: 7.37e-04
+2022-05-14 10:31:10,045 INFO [train.py:812] (7/8) Epoch 10, batch 4450, loss[loss=0.1982, simple_loss=0.2768, pruned_loss=0.05976, over 4921.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2739, pruned_loss=0.05193, over 1394715.27 frames.], batch size: 52, lr: 7.37e-04
+2022-05-14 10:32:09,157 INFO [train.py:812] (7/8) Epoch 10, batch 4500, loss[loss=0.2118, simple_loss=0.2945, pruned_loss=0.0645, over 7141.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2733, pruned_loss=0.05217, over 1391289.89 frames.], batch size: 20, lr: 7.36e-04
+2022-05-14 10:33:08,632 INFO [train.py:812] (7/8) Epoch 10, batch 4550, loss[loss=0.1998, simple_loss=0.2892, pruned_loss=0.05518, over 7143.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2736, pruned_loss=0.05274, over 1370738.35 frames.], batch size: 26, lr: 7.36e-04
+2022-05-14 10:34:22,353 INFO [train.py:812] (7/8) Epoch 11, batch 0, loss[loss=0.176, simple_loss=0.2655, pruned_loss=0.04323, over 7425.00 frames.], tot_loss[loss=0.176, simple_loss=0.2655, pruned_loss=0.04323, over 7425.00 frames.], batch size: 20, lr: 7.08e-04
+2022-05-14 10:35:21,226 INFO [train.py:812] (7/8) Epoch 11, batch 50, loss[loss=0.1751, simple_loss=0.2665, pruned_loss=0.04182, over 7431.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2692, pruned_loss=0.049, over 322539.39 frames.], batch size: 20, lr: 7.08e-04
+2022-05-14 10:36:19,878 INFO [train.py:812] (7/8) Epoch 11, batch 100, loss[loss=0.1692, simple_loss=0.2428, pruned_loss=0.04776, over 7288.00 frames.], tot_loss[loss=0.1815, simple_loss=0.267, pruned_loss=0.04801, over 566650.01 frames.], batch size: 18, lr: 7.08e-04
+2022-05-14 10:37:28,477 INFO [train.py:812] (7/8) Epoch 11, batch 150, loss[loss=0.1926, simple_loss=0.2611, pruned_loss=0.06209, over 7228.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2714, pruned_loss=0.0502, over 759993.12 frames.], batch size: 16, lr: 7.07e-04
+2022-05-14 10:38:36,346 INFO [train.py:812] (7/8) Epoch 11, batch 200, loss[loss=0.1509, simple_loss=0.2332, pruned_loss=0.0343, over 7409.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2699, pruned_loss=0.04859, over 907402.39 frames.], batch size: 18, lr: 7.07e-04
+2022-05-14 10:39:34,546 INFO [train.py:812] (7/8) Epoch 11, batch 250, loss[loss=0.208, simple_loss=0.2969, pruned_loss=0.05955, over 6436.00 frames.], tot_loss[loss=0.182, simple_loss=0.2683, pruned_loss=0.04786, over 1022840.39 frames.], batch size: 38, lr: 7.06e-04
+2022-05-14 10:40:50,487 INFO [train.py:812] (7/8) Epoch 11, batch 300, loss[loss=0.2631, simple_loss=0.3298, pruned_loss=0.09818, over 5263.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2673, pruned_loss=0.04722, over 1114909.88 frames.], batch size: 52, lr: 7.06e-04
+2022-05-14 10:41:47,803 INFO [train.py:812] (7/8) Epoch 11, batch 350, loss[loss=0.223, simple_loss=0.3112, pruned_loss=0.06742, over 6802.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2684, pruned_loss=0.04763, over 1187145.70 frames.], batch size: 31, lr: 7.06e-04
+2022-05-14 10:43:03,934 INFO [train.py:812] (7/8) Epoch 11, batch 400, loss[loss=0.175, simple_loss=0.2763, pruned_loss=0.03687, over 7433.00 frames.], tot_loss[loss=0.182, simple_loss=0.2685, pruned_loss=0.04774, over 1240387.65 frames.], batch size: 20, lr: 7.05e-04
+2022-05-14 10:44:13,185 INFO [train.py:812] (7/8) Epoch 11, batch 450, loss[loss=0.1899, simple_loss=0.2816, pruned_loss=0.0491, over 7229.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2675, pruned_loss=0.04777, over 1280736.59 frames.], batch size: 20, lr: 7.05e-04
+2022-05-14 10:45:12,596 INFO [train.py:812] (7/8) Epoch 11, batch 500, loss[loss=0.2143, simple_loss=0.3012, pruned_loss=0.06374, over 7328.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2668, pruned_loss=0.04719, over 1315833.37 frames.], batch size: 20, lr: 7.04e-04
+2022-05-14 10:46:12,013 INFO [train.py:812] (7/8) Epoch 11, batch 550, loss[loss=0.177, simple_loss=0.2672, pruned_loss=0.04341, over 7059.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2666, pruned_loss=0.04715, over 1340821.74 frames.], batch size: 18, lr: 7.04e-04
+2022-05-14 10:47:11,329 INFO [train.py:812] (7/8) Epoch 11, batch 600, loss[loss=0.1404, simple_loss=0.2194, pruned_loss=0.03071, over 6991.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2666, pruned_loss=0.04733, over 1359943.73 frames.], batch size: 16, lr: 7.04e-04
+2022-05-14 10:48:09,780 INFO [train.py:812] (7/8) Epoch 11, batch 650, loss[loss=0.1624, simple_loss=0.2414, pruned_loss=0.04167, over 7127.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2674, pruned_loss=0.04788, over 1365757.24 frames.], batch size: 17, lr: 7.03e-04
+2022-05-14 10:49:08,412 INFO [train.py:812] (7/8) Epoch 11, batch 700, loss[loss=0.1676, simple_loss=0.2501, pruned_loss=0.04256, over 6800.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2691, pruned_loss=0.04853, over 1375533.35 frames.], batch size: 15, lr: 7.03e-04
+2022-05-14 10:50:07,708 INFO [train.py:812] (7/8) Epoch 11, batch 750, loss[loss=0.2176, simple_loss=0.2986, pruned_loss=0.06836, over 7148.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2685, pruned_loss=0.04848, over 1382668.27 frames.], batch size: 20, lr: 7.03e-04
+2022-05-14 10:51:05,932 INFO [train.py:812] (7/8) Epoch 11, batch 800, loss[loss=0.1827, simple_loss=0.2778, pruned_loss=0.04375, over 7166.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2682, pruned_loss=0.04838, over 1394062.51 frames.], batch size: 26, lr: 7.02e-04
+2022-05-14 10:52:03,643 INFO [train.py:812] (7/8) Epoch 11, batch 850, loss[loss=0.1866, simple_loss=0.274, pruned_loss=0.04963, over 7319.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2676, pruned_loss=0.04801, over 1398051.45 frames.], batch size: 20, lr: 7.02e-04
+2022-05-14 10:53:01,775 INFO [train.py:812] (7/8) Epoch 11, batch 900, loss[loss=0.1869, simple_loss=0.2685, pruned_loss=0.05266, over 7435.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2673, pruned_loss=0.04779, over 1406797.97 frames.], batch size: 20, lr: 7.02e-04
+2022-05-14 10:54:00,403 INFO [train.py:812] (7/8) Epoch 11, batch 950, loss[loss=0.1838, simple_loss=0.2572, pruned_loss=0.05514, over 7008.00 frames.], tot_loss[loss=0.181, simple_loss=0.2668, pruned_loss=0.04757, over 1409242.87 frames.], batch size: 16, lr: 7.01e-04
+2022-05-14 10:54:58,970 INFO [train.py:812] (7/8) Epoch 11, batch 1000, loss[loss=0.2429, simple_loss=0.3248, pruned_loss=0.08053, over 7303.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2671, pruned_loss=0.0473, over 1413390.21 frames.], batch size: 25, lr: 7.01e-04
+2022-05-14 10:55:58,062 INFO [train.py:812] (7/8) Epoch 11, batch 1050, loss[loss=0.178, simple_loss=0.2564, pruned_loss=0.04985, over 7249.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2687, pruned_loss=0.04793, over 1408787.58 frames.], batch size: 19, lr: 7.00e-04
+2022-05-14 10:56:57,240 INFO [train.py:812] (7/8) Epoch 11, batch 1100, loss[loss=0.1621, simple_loss=0.2477, pruned_loss=0.03826, over 7165.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2687, pruned_loss=0.0478, over 1413428.06 frames.], batch size: 18, lr: 7.00e-04
+2022-05-14 10:57:56,873 INFO [train.py:812] (7/8) Epoch 11, batch 1150, loss[loss=0.1589, simple_loss=0.2473, pruned_loss=0.03522, over 7063.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2679, pruned_loss=0.04728, over 1417591.87 frames.], batch size: 18, lr: 7.00e-04
+2022-05-14 10:58:55,469 INFO [train.py:812] (7/8) Epoch 11, batch 1200, loss[loss=0.1674, simple_loss=0.2418, pruned_loss=0.04653, over 7219.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2655, pruned_loss=0.04678, over 1421077.37 frames.], batch size: 16, lr: 6.99e-04
+2022-05-14 10:59:53,804 INFO [train.py:812] (7/8) Epoch 11, batch 1250, loss[loss=0.1366, simple_loss=0.213, pruned_loss=0.03013, over 7134.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2648, pruned_loss=0.04653, over 1424488.34 frames.], batch size: 17, lr: 6.99e-04
+2022-05-14 11:00:50,442 INFO [train.py:812] (7/8) Epoch 11, batch 1300, loss[loss=0.1696, simple_loss=0.2516, pruned_loss=0.04376, over 7324.00 frames.], tot_loss[loss=0.1792, simple_loss=0.265, pruned_loss=0.04675, over 1421295.05 frames.], batch size: 21, lr: 6.99e-04
+2022-05-14 11:01:49,346 INFO [train.py:812] (7/8) Epoch 11, batch 1350, loss[loss=0.2048, simple_loss=0.2883, pruned_loss=0.06069, over 7314.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2654, pruned_loss=0.04656, over 1424344.29 frames.], batch size: 21, lr: 6.98e-04
+2022-05-14 11:02:46,409 INFO [train.py:812] (7/8) Epoch 11, batch 1400, loss[loss=0.1739, simple_loss=0.2614, pruned_loss=0.04318, over 7162.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2658, pruned_loss=0.04655, over 1427797.87 frames.], batch size: 19, lr: 6.98e-04
+2022-05-14 11:03:44,663 INFO [train.py:812] (7/8) Epoch 11, batch 1450, loss[loss=0.1658, simple_loss=0.2502, pruned_loss=0.04063, over 7278.00 frames.], tot_loss[loss=0.181, simple_loss=0.2675, pruned_loss=0.0473, over 1428264.88 frames.], batch size: 17, lr: 6.97e-04
+2022-05-14 11:04:41,569 INFO [train.py:812] (7/8) Epoch 11, batch 1500, loss[loss=0.1804, simple_loss=0.2716, pruned_loss=0.04464, over 7076.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2673, pruned_loss=0.04715, over 1425916.53 frames.], batch size: 28, lr: 6.97e-04
+2022-05-14 11:05:41,379 INFO [train.py:812] (7/8) Epoch 11, batch 1550, loss[loss=0.1718, simple_loss=0.2612, pruned_loss=0.04121, over 7443.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2672, pruned_loss=0.04706, over 1424090.85 frames.], batch size: 20, lr: 6.97e-04
+2022-05-14 11:06:38,938 INFO [train.py:812] (7/8) Epoch 11, batch 1600, loss[loss=0.2047, simple_loss=0.2983, pruned_loss=0.0555, over 6706.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2673, pruned_loss=0.04741, over 1418315.95 frames.], batch size: 31, lr: 6.96e-04
+2022-05-14 11:07:38,282 INFO [train.py:812] (7/8) Epoch 11, batch 1650, loss[loss=0.1445, simple_loss=0.2245, pruned_loss=0.0323, over 7225.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2666, pruned_loss=0.04752, over 1418154.01 frames.], batch size: 16, lr: 6.96e-04
+2022-05-14 11:08:37,015 INFO [train.py:812] (7/8) Epoch 11, batch 1700, loss[loss=0.1709, simple_loss=0.2528, pruned_loss=0.04447, over 6788.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2676, pruned_loss=0.0478, over 1417070.28 frames.], batch size: 15, lr: 6.96e-04
+2022-05-14 11:09:36,835 INFO [train.py:812] (7/8) Epoch 11, batch 1750, loss[loss=0.1808, simple_loss=0.2756, pruned_loss=0.04301, over 7106.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2666, pruned_loss=0.0479, over 1413461.07 frames.], batch size: 21, lr: 6.95e-04
+2022-05-14 11:10:35,699 INFO [train.py:812] (7/8) Epoch 11, batch 1800, loss[loss=0.1984, simple_loss=0.2879, pruned_loss=0.05444, over 5155.00 frames.], tot_loss[loss=0.1802, simple_loss=0.266, pruned_loss=0.04723, over 1413117.78 frames.], batch size: 52, lr: 6.95e-04
+2022-05-14 11:11:35,370 INFO [train.py:812] (7/8) Epoch 11, batch 1850, loss[loss=0.1706, simple_loss=0.2595, pruned_loss=0.04088, over 6387.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2663, pruned_loss=0.0474, over 1417105.65 frames.], batch size: 37, lr: 6.95e-04
+2022-05-14 11:12:33,384 INFO [train.py:812] (7/8) Epoch 11, batch 1900, loss[loss=0.1966, simple_loss=0.2928, pruned_loss=0.05024, over 7324.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2663, pruned_loss=0.04743, over 1421853.34 frames.], batch size: 21, lr: 6.94e-04
+2022-05-14 11:13:32,959 INFO [train.py:812] (7/8) Epoch 11, batch 1950, loss[loss=0.1768, simple_loss=0.2598, pruned_loss=0.0469, over 7345.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2673, pruned_loss=0.04805, over 1422185.42 frames.], batch size: 19, lr: 6.94e-04
+2022-05-14 11:14:32,039 INFO [train.py:812] (7/8) Epoch 11, batch 2000, loss[loss=0.1661, simple_loss=0.2547, pruned_loss=0.03882, over 7160.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2677, pruned_loss=0.04767, over 1423687.76 frames.], batch size: 18, lr: 6.93e-04
+2022-05-14 11:15:30,903 INFO [train.py:812] (7/8) Epoch 11, batch 2050, loss[loss=0.1476, simple_loss=0.2212, pruned_loss=0.03702, over 7292.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2669, pruned_loss=0.04732, over 1425277.44 frames.], batch size: 17, lr: 6.93e-04
+2022-05-14 11:16:30,478 INFO [train.py:812] (7/8) Epoch 11, batch 2100, loss[loss=0.1926, simple_loss=0.2788, pruned_loss=0.05326, over 7366.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2667, pruned_loss=0.0469, over 1425788.26 frames.], batch size: 23, lr: 6.93e-04
+2022-05-14 11:17:37,604 INFO [train.py:812] (7/8) Epoch 11, batch 2150, loss[loss=0.1572, simple_loss=0.244, pruned_loss=0.03524, over 7145.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2668, pruned_loss=0.04721, over 1426233.04 frames.], batch size: 18, lr: 6.92e-04
+2022-05-14 11:18:36,051 INFO [train.py:812] (7/8) Epoch 11, batch 2200, loss[loss=0.2297, simple_loss=0.3091, pruned_loss=0.07519, over 7235.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2666, pruned_loss=0.04731, over 1423588.20 frames.], batch size: 20, lr: 6.92e-04
+2022-05-14 11:19:35,038 INFO [train.py:812] (7/8) Epoch 11, batch 2250, loss[loss=0.2069, simple_loss=0.2951, pruned_loss=0.05938, over 7344.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2675, pruned_loss=0.04768, over 1427561.74 frames.], batch size: 22, lr: 6.92e-04
+2022-05-14 11:20:34,394 INFO [train.py:812] (7/8) Epoch 11, batch 2300, loss[loss=0.1788, simple_loss=0.2744, pruned_loss=0.04163, over 7138.00 frames.], tot_loss[loss=0.1798, simple_loss=0.266, pruned_loss=0.04677, over 1427629.60 frames.], batch size: 26, lr: 6.91e-04
+2022-05-14 11:21:33,313 INFO [train.py:812] (7/8) Epoch 11, batch 2350, loss[loss=0.1804, simple_loss=0.2643, pruned_loss=0.04821, over 6691.00 frames.], tot_loss[loss=0.179, simple_loss=0.2652, pruned_loss=0.04642, over 1429444.26 frames.], batch size: 31, lr: 6.91e-04
+2022-05-14 11:22:32,026 INFO [train.py:812] (7/8) Epoch 11, batch 2400, loss[loss=0.2015, simple_loss=0.2975, pruned_loss=0.05271, over 7314.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2662, pruned_loss=0.04729, over 1422749.97 frames.], batch size: 21, lr: 6.91e-04
+2022-05-14 11:23:31,132 INFO [train.py:812] (7/8) Epoch 11, batch 2450, loss[loss=0.1778, simple_loss=0.2559, pruned_loss=0.04988, over 7021.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2652, pruned_loss=0.04684, over 1423509.23 frames.], batch size: 16, lr: 6.90e-04
+2022-05-14 11:24:30,225 INFO [train.py:812] (7/8) Epoch 11, batch 2500, loss[loss=0.1725, simple_loss=0.264, pruned_loss=0.04056, over 7154.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2654, pruned_loss=0.04703, over 1422712.71 frames.], batch size: 19, lr: 6.90e-04
+2022-05-14 11:25:29,330 INFO [train.py:812] (7/8) Epoch 11, batch 2550, loss[loss=0.1799, simple_loss=0.2619, pruned_loss=0.049, over 6774.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2657, pruned_loss=0.04697, over 1426486.83 frames.], batch size: 15, lr: 6.90e-04
+2022-05-14 11:26:27,814 INFO [train.py:812] (7/8) Epoch 11, batch 2600, loss[loss=0.1937, simple_loss=0.2776, pruned_loss=0.05494, over 7377.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2654, pruned_loss=0.04695, over 1428343.86 frames.], batch size: 23, lr: 6.89e-04
+2022-05-14 11:27:26,108 INFO [train.py:812] (7/8) Epoch 11, batch 2650, loss[loss=0.1717, simple_loss=0.251, pruned_loss=0.04616, over 7007.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2664, pruned_loss=0.047, over 1423906.92 frames.], batch size: 16, lr: 6.89e-04
+2022-05-14 11:28:23,572 INFO [train.py:812] (7/8) Epoch 11, batch 2700, loss[loss=0.1984, simple_loss=0.2816, pruned_loss=0.05762, over 7418.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2674, pruned_loss=0.04693, over 1427067.31 frames.], batch size: 21, lr: 6.89e-04
+2022-05-14 11:29:21,010 INFO [train.py:812] (7/8) Epoch 11, batch 2750, loss[loss=0.1548, simple_loss=0.2488, pruned_loss=0.03045, over 7288.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2659, pruned_loss=0.04643, over 1425629.22 frames.], batch size: 18, lr: 6.88e-04
+2022-05-14 11:30:17,983 INFO [train.py:812] (7/8) Epoch 11, batch 2800, loss[loss=0.1758, simple_loss=0.2659, pruned_loss=0.04285, over 7152.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2665, pruned_loss=0.04717, over 1424286.44 frames.], batch size: 19, lr: 6.88e-04
+2022-05-14 11:31:17,644 INFO [train.py:812] (7/8) Epoch 11, batch 2850, loss[loss=0.1618, simple_loss=0.2491, pruned_loss=0.03722, over 7315.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2657, pruned_loss=0.0466, over 1425280.43 frames.], batch size: 21, lr: 6.87e-04
+2022-05-14 11:32:14,509 INFO [train.py:812] (7/8) Epoch 11, batch 2900, loss[loss=0.2235, simple_loss=0.3026, pruned_loss=0.07223, over 7195.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2656, pruned_loss=0.0469, over 1427895.87 frames.], batch size: 23, lr: 6.87e-04
+2022-05-14 11:33:13,370 INFO [train.py:812] (7/8) Epoch 11, batch 2950, loss[loss=0.2003, simple_loss=0.2937, pruned_loss=0.05347, over 7201.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2668, pruned_loss=0.04711, over 1425520.62 frames.], batch size: 22, lr: 6.87e-04
+2022-05-14 11:34:12,279 INFO [train.py:812] (7/8) Epoch 11, batch 3000, loss[loss=0.1601, simple_loss=0.2422, pruned_loss=0.03898, over 7166.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2678, pruned_loss=0.04752, over 1423977.41 frames.], batch size: 18, lr: 6.86e-04
+2022-05-14 11:34:12,280 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 11:34:19,823 INFO [train.py:841] (7/8) Epoch 11, validation: loss=0.1564, simple_loss=0.2581, pruned_loss=0.02737, over 698248.00 frames.
+2022-05-14 11:35:18,280 INFO [train.py:812] (7/8) Epoch 11, batch 3050, loss[loss=0.1669, simple_loss=0.2676, pruned_loss=0.03313, over 7168.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2672, pruned_loss=0.04696, over 1427836.42 frames.], batch size: 26, lr: 6.86e-04
+2022-05-14 11:36:16,738 INFO [train.py:812] (7/8) Epoch 11, batch 3100, loss[loss=0.16, simple_loss=0.2447, pruned_loss=0.03765, over 7407.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2676, pruned_loss=0.04777, over 1425395.20 frames.], batch size: 18, lr: 6.86e-04
+2022-05-14 11:37:16,200 INFO [train.py:812] (7/8) Epoch 11, batch 3150, loss[loss=0.1662, simple_loss=0.2431, pruned_loss=0.04467, over 7277.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2669, pruned_loss=0.04762, over 1428322.52 frames.], batch size: 18, lr: 6.85e-04
+2022-05-14 11:38:15,188 INFO [train.py:812] (7/8) Epoch 11, batch 3200, loss[loss=0.1716, simple_loss=0.2466, pruned_loss=0.04836, over 7175.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2645, pruned_loss=0.04653, over 1430102.56 frames.], batch size: 18, lr: 6.85e-04
+2022-05-14 11:39:14,906 INFO [train.py:812] (7/8) Epoch 11, batch 3250, loss[loss=0.1904, simple_loss=0.2762, pruned_loss=0.05229, over 7064.00 frames.], tot_loss[loss=0.1795, simple_loss=0.265, pruned_loss=0.04702, over 1432101.65 frames.], batch size: 18, lr: 6.85e-04
+2022-05-14 11:40:14,271 INFO [train.py:812] (7/8) Epoch 11, batch 3300, loss[loss=0.184, simple_loss=0.2725, pruned_loss=0.04777, over 6296.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2659, pruned_loss=0.04725, over 1431027.04 frames.], batch size: 37, lr: 6.84e-04
+2022-05-14 11:41:13,858 INFO [train.py:812] (7/8) Epoch 11, batch 3350, loss[loss=0.1674, simple_loss=0.2666, pruned_loss=0.03407, over 7118.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2662, pruned_loss=0.04744, over 1425655.92 frames.], batch size: 21, lr: 6.84e-04
+2022-05-14 11:42:12,426 INFO [train.py:812] (7/8) Epoch 11, batch 3400, loss[loss=0.1592, simple_loss=0.2397, pruned_loss=0.03935, over 7000.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2662, pruned_loss=0.04734, over 1422259.51 frames.], batch size: 16, lr: 6.84e-04
+2022-05-14 11:43:11,500 INFO [train.py:812] (7/8) Epoch 11, batch 3450, loss[loss=0.1989, simple_loss=0.2987, pruned_loss=0.04951, over 7116.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2663, pruned_loss=0.04692, over 1425689.75 frames.], batch size: 21, lr: 6.83e-04
+2022-05-14 11:44:10,177 INFO [train.py:812] (7/8) Epoch 11, batch 3500, loss[loss=0.1602, simple_loss=0.2358, pruned_loss=0.04233, over 7412.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2662, pruned_loss=0.04714, over 1426118.22 frames.], batch size: 18, lr: 6.83e-04
+2022-05-14 11:45:10,028 INFO [train.py:812] (7/8) Epoch 11, batch 3550, loss[loss=0.1867, simple_loss=0.2728, pruned_loss=0.05026, over 6137.00 frames.], tot_loss[loss=0.18, simple_loss=0.2661, pruned_loss=0.04696, over 1424470.76 frames.], batch size: 37, lr: 6.83e-04
+2022-05-14 11:46:08,778 INFO [train.py:812] (7/8) Epoch 11, batch 3600, loss[loss=0.17, simple_loss=0.2633, pruned_loss=0.03832, over 6329.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2667, pruned_loss=0.04742, over 1420625.99 frames.], batch size: 37, lr: 6.82e-04
+2022-05-14 11:47:07,842 INFO [train.py:812] (7/8) Epoch 11, batch 3650, loss[loss=0.187, simple_loss=0.2738, pruned_loss=0.05007, over 7118.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2675, pruned_loss=0.0476, over 1422465.12 frames.], batch size: 21, lr: 6.82e-04
+2022-05-14 11:48:06,852 INFO [train.py:812] (7/8) Epoch 11, batch 3700, loss[loss=0.156, simple_loss=0.25, pruned_loss=0.03096, over 7113.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2666, pruned_loss=0.04723, over 1419182.15 frames.], batch size: 21, lr: 6.82e-04
+2022-05-14 11:49:06,482 INFO [train.py:812] (7/8) Epoch 11, batch 3750, loss[loss=0.2003, simple_loss=0.2758, pruned_loss=0.06236, over 7427.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2668, pruned_loss=0.04709, over 1424427.28 frames.], batch size: 20, lr: 6.81e-04
+2022-05-14 11:50:05,403 INFO [train.py:812] (7/8) Epoch 11, batch 3800, loss[loss=0.1627, simple_loss=0.2543, pruned_loss=0.03552, over 7298.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2672, pruned_loss=0.0471, over 1423187.26 frames.], batch size: 24, lr: 6.81e-04
+2022-05-14 11:51:04,566 INFO [train.py:812] (7/8) Epoch 11, batch 3850, loss[loss=0.2029, simple_loss=0.2922, pruned_loss=0.0568, over 7208.00 frames.], tot_loss[loss=0.18, simple_loss=0.2666, pruned_loss=0.04666, over 1427840.73 frames.], batch size: 22, lr: 6.81e-04
+2022-05-14 11:52:01,433 INFO [train.py:812] (7/8) Epoch 11, batch 3900, loss[loss=0.1753, simple_loss=0.2669, pruned_loss=0.04183, over 7380.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2665, pruned_loss=0.04668, over 1427538.63 frames.], batch size: 23, lr: 6.80e-04
+2022-05-14 11:53:00,875 INFO [train.py:812] (7/8) Epoch 11, batch 3950, loss[loss=0.2051, simple_loss=0.2856, pruned_loss=0.06227, over 7434.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2664, pruned_loss=0.04702, over 1426478.05 frames.], batch size: 20, lr: 6.80e-04
+2022-05-14 11:53:59,484 INFO [train.py:812] (7/8) Epoch 11, batch 4000, loss[loss=0.1694, simple_loss=0.2745, pruned_loss=0.03215, over 7234.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2664, pruned_loss=0.04697, over 1418233.51 frames.], batch size: 21, lr: 6.80e-04
+2022-05-14 11:54:58,933 INFO [train.py:812] (7/8) Epoch 11, batch 4050, loss[loss=0.1777, simple_loss=0.2689, pruned_loss=0.04322, over 7193.00 frames.], tot_loss[loss=0.1808, simple_loss=0.267, pruned_loss=0.04733, over 1417849.21 frames.], batch size: 22, lr: 6.79e-04
+2022-05-14 11:55:57,995 INFO [train.py:812] (7/8) Epoch 11, batch 4100, loss[loss=0.1897, simple_loss=0.2799, pruned_loss=0.04976, over 7193.00 frames.], tot_loss[loss=0.1808, simple_loss=0.267, pruned_loss=0.04729, over 1417439.08 frames.], batch size: 22, lr: 6.79e-04
+2022-05-14 11:56:56,044 INFO [train.py:812] (7/8) Epoch 11, batch 4150, loss[loss=0.1921, simple_loss=0.2824, pruned_loss=0.05091, over 6671.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2674, pruned_loss=0.04736, over 1413931.68 frames.], batch size: 31, lr: 6.79e-04
+2022-05-14 11:57:54,875 INFO [train.py:812] (7/8) Epoch 11, batch 4200, loss[loss=0.1816, simple_loss=0.2712, pruned_loss=0.04596, over 6989.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2682, pruned_loss=0.04771, over 1414833.52 frames.], batch size: 28, lr: 6.78e-04
+2022-05-14 11:58:54,381 INFO [train.py:812] (7/8) Epoch 11, batch 4250, loss[loss=0.2143, simple_loss=0.2929, pruned_loss=0.06783, over 5168.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2666, pruned_loss=0.04677, over 1414720.73 frames.], batch size: 53, lr: 6.78e-04
+2022-05-14 11:59:53,072 INFO [train.py:812] (7/8) Epoch 11, batch 4300, loss[loss=0.2753, simple_loss=0.3378, pruned_loss=0.1064, over 5251.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2672, pruned_loss=0.0475, over 1411828.05 frames.], batch size: 52, lr: 6.78e-04
+2022-05-14 12:00:52,229 INFO [train.py:812] (7/8) Epoch 11, batch 4350, loss[loss=0.1712, simple_loss=0.2674, pruned_loss=0.03745, over 7227.00 frames.], tot_loss[loss=0.182, simple_loss=0.268, pruned_loss=0.04796, over 1410309.14 frames.], batch size: 20, lr: 6.77e-04
+2022-05-14 12:01:50,124 INFO [train.py:812] (7/8) Epoch 11, batch 4400, loss[loss=0.2029, simple_loss=0.2885, pruned_loss=0.05861, over 7204.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2684, pruned_loss=0.04813, over 1415704.25 frames.], batch size: 22, lr: 6.77e-04
+2022-05-14 12:02:49,069 INFO [train.py:812] (7/8) Epoch 11, batch 4450, loss[loss=0.1938, simple_loss=0.2797, pruned_loss=0.0539, over 7232.00 frames.], tot_loss[loss=0.1839, simple_loss=0.27, pruned_loss=0.04883, over 1418467.71 frames.], batch size: 20, lr: 6.77e-04
+2022-05-14 12:03:48,083 INFO [train.py:812] (7/8) Epoch 11, batch 4500, loss[loss=0.2053, simple_loss=0.2829, pruned_loss=0.06385, over 5111.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2703, pruned_loss=0.04918, over 1411054.59 frames.], batch size: 52, lr: 6.76e-04
+2022-05-14 12:04:46,801 INFO [train.py:812] (7/8) Epoch 11, batch 4550, loss[loss=0.1741, simple_loss=0.2596, pruned_loss=0.04426, over 5039.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2722, pruned_loss=0.05128, over 1346226.58 frames.], batch size: 52, lr: 6.76e-04
+2022-05-14 12:05:54,979 INFO [train.py:812] (7/8) Epoch 12, batch 0, loss[loss=0.2011, simple_loss=0.2897, pruned_loss=0.05625, over 7429.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2897, pruned_loss=0.05625, over 7429.00 frames.], batch size: 21, lr: 6.52e-04
+2022-05-14 12:06:54,755 INFO [train.py:812] (7/8) Epoch 12, batch 50, loss[loss=0.1967, simple_loss=0.29, pruned_loss=0.05167, over 4736.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2666, pruned_loss=0.04706, over 319342.82 frames.], batch size: 52, lr: 6.52e-04
+2022-05-14 12:07:53,923 INFO [train.py:812] (7/8) Epoch 12, batch 100, loss[loss=0.1843, simple_loss=0.2738, pruned_loss=0.04737, over 6444.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2674, pruned_loss=0.04683, over 558857.05 frames.], batch size: 38, lr: 6.51e-04
+2022-05-14 12:08:53,468 INFO [train.py:812] (7/8) Epoch 12, batch 150, loss[loss=0.1447, simple_loss=0.2265, pruned_loss=0.0314, over 7283.00 frames.], tot_loss[loss=0.181, simple_loss=0.2682, pruned_loss=0.0469, over 748936.17 frames.], batch size: 17, lr: 6.51e-04
+2022-05-14 12:09:52,507 INFO [train.py:812] (7/8) Epoch 12, batch 200, loss[loss=0.1879, simple_loss=0.2751, pruned_loss=0.0504, over 7204.00 frames.], tot_loss[loss=0.181, simple_loss=0.2681, pruned_loss=0.04693, over 896336.83 frames.], batch size: 22, lr: 6.51e-04
+2022-05-14 12:10:51,870 INFO [train.py:812] (7/8) Epoch 12, batch 250, loss[loss=0.1813, simple_loss=0.2704, pruned_loss=0.04611, over 6697.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2668, pruned_loss=0.04648, over 1014852.34 frames.], batch size: 31, lr: 6.50e-04
+2022-05-14 12:11:51,055 INFO [train.py:812] (7/8) Epoch 12, batch 300, loss[loss=0.1747, simple_loss=0.2698, pruned_loss=0.03978, over 7209.00 frames.], tot_loss[loss=0.18, simple_loss=0.2671, pruned_loss=0.04645, over 1098065.47 frames.], batch size: 22, lr: 6.50e-04
+2022-05-14 12:12:50,801 INFO [train.py:812] (7/8) Epoch 12, batch 350, loss[loss=0.1619, simple_loss=0.2611, pruned_loss=0.03133, over 7341.00 frames.], tot_loss[loss=0.1803, simple_loss=0.267, pruned_loss=0.04684, over 1164846.08 frames.], batch size: 22, lr: 6.50e-04
+2022-05-14 12:13:50,275 INFO [train.py:812] (7/8) Epoch 12, batch 400, loss[loss=0.1746, simple_loss=0.268, pruned_loss=0.04061, over 7342.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2661, pruned_loss=0.0462, over 1219364.48 frames.], batch size: 22, lr: 6.49e-04
+2022-05-14 12:14:48,371 INFO [train.py:812] (7/8) Epoch 12, batch 450, loss[loss=0.1777, simple_loss=0.2635, pruned_loss=0.04599, over 7157.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2653, pruned_loss=0.04594, over 1268145.71 frames.], batch size: 19, lr: 6.49e-04
+2022-05-14 12:15:47,369 INFO [train.py:812] (7/8) Epoch 12, batch 500, loss[loss=0.2273, simple_loss=0.3033, pruned_loss=0.07564, over 7379.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2654, pruned_loss=0.04591, over 1302544.69 frames.], batch size: 23, lr: 6.49e-04
+2022-05-14 12:16:45,634 INFO [train.py:812] (7/8) Epoch 12, batch 550, loss[loss=0.185, simple_loss=0.2734, pruned_loss=0.04832, over 7414.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2653, pruned_loss=0.04577, over 1329864.57 frames.], batch size: 21, lr: 6.48e-04
+2022-05-14 12:17:43,527 INFO [train.py:812] (7/8) Epoch 12, batch 600, loss[loss=0.1673, simple_loss=0.2627, pruned_loss=0.03591, over 7343.00 frames.], tot_loss[loss=0.1786, simple_loss=0.265, pruned_loss=0.04604, over 1349427.73 frames.], batch size: 22, lr: 6.48e-04
+2022-05-14 12:18:41,748 INFO [train.py:812] (7/8) Epoch 12, batch 650, loss[loss=0.2319, simple_loss=0.317, pruned_loss=0.07342, over 7381.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2637, pruned_loss=0.04537, over 1370759.33 frames.], batch size: 23, lr: 6.48e-04
+2022-05-14 12:19:49,871 INFO [train.py:812] (7/8) Epoch 12, batch 700, loss[loss=0.1949, simple_loss=0.2803, pruned_loss=0.05474, over 7296.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2642, pruned_loss=0.04531, over 1381094.70 frames.], batch size: 24, lr: 6.47e-04
+2022-05-14 12:20:48,665 INFO [train.py:812] (7/8) Epoch 12, batch 750, loss[loss=0.1726, simple_loss=0.2589, pruned_loss=0.0432, over 7322.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2648, pruned_loss=0.0455, over 1386563.73 frames.], batch size: 20, lr: 6.47e-04
+2022-05-14 12:21:47,972 INFO [train.py:812] (7/8) Epoch 12, batch 800, loss[loss=0.1466, simple_loss=0.2199, pruned_loss=0.03662, over 7399.00 frames.], tot_loss[loss=0.177, simple_loss=0.2636, pruned_loss=0.04515, over 1398876.22 frames.], batch size: 18, lr: 6.47e-04
+2022-05-14 12:22:46,143 INFO [train.py:812] (7/8) Epoch 12, batch 850, loss[loss=0.173, simple_loss=0.266, pruned_loss=0.04007, over 6914.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2647, pruned_loss=0.04579, over 1402920.72 frames.], batch size: 31, lr: 6.46e-04
+2022-05-14 12:23:44,049 INFO [train.py:812] (7/8) Epoch 12, batch 900, loss[loss=0.1645, simple_loss=0.2598, pruned_loss=0.03464, over 7337.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2653, pruned_loss=0.04575, over 1407624.99 frames.], batch size: 22, lr: 6.46e-04
+2022-05-14 12:24:43,704 INFO [train.py:812] (7/8) Epoch 12, batch 950, loss[loss=0.157, simple_loss=0.2487, pruned_loss=0.03268, over 7435.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2646, pruned_loss=0.04547, over 1412171.94 frames.], batch size: 20, lr: 6.46e-04
+2022-05-14 12:25:42,182 INFO [train.py:812] (7/8) Epoch 12, batch 1000, loss[loss=0.1562, simple_loss=0.2408, pruned_loss=0.0358, over 7171.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2655, pruned_loss=0.04565, over 1414816.38 frames.], batch size: 19, lr: 6.46e-04
+2022-05-14 12:26:41,712 INFO [train.py:812] (7/8) Epoch 12, batch 1050, loss[loss=0.1597, simple_loss=0.2313, pruned_loss=0.04407, over 7407.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2653, pruned_loss=0.04555, over 1415283.36 frames.], batch size: 17, lr: 6.45e-04
+2022-05-14 12:27:40,732 INFO [train.py:812] (7/8) Epoch 12, batch 1100, loss[loss=0.1845, simple_loss=0.2677, pruned_loss=0.0507, over 7155.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2657, pruned_loss=0.04557, over 1419374.41 frames.], batch size: 19, lr: 6.45e-04
+2022-05-14 12:28:40,268 INFO [train.py:812] (7/8) Epoch 12, batch 1150, loss[loss=0.2013, simple_loss=0.2845, pruned_loss=0.05902, over 4882.00 frames.], tot_loss[loss=0.1778, simple_loss=0.265, pruned_loss=0.04527, over 1421322.77 frames.], batch size: 52, lr: 6.45e-04
+2022-05-14 12:29:38,143 INFO [train.py:812] (7/8) Epoch 12, batch 1200, loss[loss=0.1752, simple_loss=0.267, pruned_loss=0.04172, over 7118.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2649, pruned_loss=0.04527, over 1424019.70 frames.], batch size: 21, lr: 6.44e-04
+2022-05-14 12:30:37,090 INFO [train.py:812] (7/8) Epoch 12, batch 1250, loss[loss=0.1406, simple_loss=0.2237, pruned_loss=0.02876, over 7001.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2649, pruned_loss=0.04528, over 1424551.60 frames.], batch size: 16, lr: 6.44e-04
+2022-05-14 12:31:36,654 INFO [train.py:812] (7/8) Epoch 12, batch 1300, loss[loss=0.1585, simple_loss=0.2532, pruned_loss=0.03193, over 7319.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2642, pruned_loss=0.04466, over 1426149.86 frames.], batch size: 20, lr: 6.44e-04
+2022-05-14 12:32:34,830 INFO [train.py:812] (7/8) Epoch 12, batch 1350, loss[loss=0.2015, simple_loss=0.2833, pruned_loss=0.05986, over 7330.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2646, pruned_loss=0.04527, over 1423310.24 frames.], batch size: 21, lr: 6.43e-04
+2022-05-14 12:33:34,101 INFO [train.py:812] (7/8) Epoch 12, batch 1400, loss[loss=0.1697, simple_loss=0.2608, pruned_loss=0.03926, over 7323.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2639, pruned_loss=0.04488, over 1420268.51 frames.], batch size: 21, lr: 6.43e-04
+2022-05-14 12:34:33,364 INFO [train.py:812] (7/8) Epoch 12, batch 1450, loss[loss=0.168, simple_loss=0.2575, pruned_loss=0.03928, over 7062.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2641, pruned_loss=0.04499, over 1420565.75 frames.], batch size: 18, lr: 6.43e-04
+2022-05-14 12:35:32,052 INFO [train.py:812] (7/8) Epoch 12, batch 1500, loss[loss=0.2098, simple_loss=0.2997, pruned_loss=0.06, over 7200.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2645, pruned_loss=0.04521, over 1424638.54 frames.], batch size: 23, lr: 6.42e-04
+2022-05-14 12:36:36,814 INFO [train.py:812] (7/8) Epoch 12, batch 1550, loss[loss=0.165, simple_loss=0.2514, pruned_loss=0.03928, over 7229.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2639, pruned_loss=0.04547, over 1423403.11 frames.], batch size: 20, lr: 6.42e-04
+2022-05-14 12:37:35,875 INFO [train.py:812] (7/8) Epoch 12, batch 1600, loss[loss=0.157, simple_loss=0.2376, pruned_loss=0.03815, over 7357.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2651, pruned_loss=0.04583, over 1424572.31 frames.], batch size: 19, lr: 6.42e-04
+2022-05-14 12:38:44,937 INFO [train.py:812] (7/8) Epoch 12, batch 1650, loss[loss=0.1781, simple_loss=0.2681, pruned_loss=0.04408, over 7378.00 frames.], tot_loss[loss=0.1787, simple_loss=0.265, pruned_loss=0.04621, over 1425200.87 frames.], batch size: 23, lr: 6.42e-04
+2022-05-14 12:39:52,067 INFO [train.py:812] (7/8) Epoch 12, batch 1700, loss[loss=0.1686, simple_loss=0.2554, pruned_loss=0.04091, over 7211.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2661, pruned_loss=0.04683, over 1426917.23 frames.], batch size: 21, lr: 6.41e-04
+2022-05-14 12:40:51,420 INFO [train.py:812] (7/8) Epoch 12, batch 1750, loss[loss=0.1956, simple_loss=0.2829, pruned_loss=0.05413, over 7136.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2658, pruned_loss=0.04627, over 1427100.22 frames.], batch size: 26, lr: 6.41e-04
+2022-05-14 12:41:58,760 INFO [train.py:812] (7/8) Epoch 12, batch 1800, loss[loss=0.134, simple_loss=0.2095, pruned_loss=0.02927, over 6989.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2651, pruned_loss=0.04608, over 1427329.78 frames.], batch size: 16, lr: 6.41e-04
+2022-05-14 12:43:08,013 INFO [train.py:812] (7/8) Epoch 12, batch 1850, loss[loss=0.1832, simple_loss=0.2729, pruned_loss=0.04679, over 7160.00 frames.], tot_loss[loss=0.1774, simple_loss=0.264, pruned_loss=0.04543, over 1426144.63 frames.], batch size: 26, lr: 6.40e-04
+2022-05-14 12:44:16,818 INFO [train.py:812] (7/8) Epoch 12, batch 1900, loss[loss=0.1803, simple_loss=0.265, pruned_loss=0.04783, over 7432.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2642, pruned_loss=0.04574, over 1428149.55 frames.], batch size: 20, lr: 6.40e-04
+2022-05-14 12:45:34,920 INFO [train.py:812] (7/8) Epoch 12, batch 1950, loss[loss=0.1715, simple_loss=0.2433, pruned_loss=0.04982, over 7012.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2642, pruned_loss=0.04581, over 1426957.73 frames.], batch size: 16, lr: 6.40e-04
+2022-05-14 12:46:34,668 INFO [train.py:812] (7/8) Epoch 12, batch 2000, loss[loss=0.1801, simple_loss=0.2737, pruned_loss=0.0432, over 6126.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2642, pruned_loss=0.04564, over 1424624.19 frames.], batch size: 37, lr: 6.39e-04
+2022-05-14 12:47:34,786 INFO [train.py:812] (7/8) Epoch 12, batch 2050, loss[loss=0.2041, simple_loss=0.2801, pruned_loss=0.06401, over 7377.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2637, pruned_loss=0.04566, over 1422623.35 frames.], batch size: 23, lr: 6.39e-04
+2022-05-14 12:48:34,248 INFO [train.py:812] (7/8) Epoch 12, batch 2100, loss[loss=0.2179, simple_loss=0.2973, pruned_loss=0.06924, over 6769.00 frames.], tot_loss[loss=0.178, simple_loss=0.2643, pruned_loss=0.04588, over 1426799.31 frames.], batch size: 31, lr: 6.39e-04
+2022-05-14 12:49:34,276 INFO [train.py:812] (7/8) Epoch 12, batch 2150, loss[loss=0.1671, simple_loss=0.2432, pruned_loss=0.04545, over 6761.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2643, pruned_loss=0.04589, over 1421864.61 frames.], batch size: 15, lr: 6.38e-04
+2022-05-14 12:50:33,531 INFO [train.py:812] (7/8) Epoch 12, batch 2200, loss[loss=0.1629, simple_loss=0.2527, pruned_loss=0.03656, over 7449.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2643, pruned_loss=0.04573, over 1425814.05 frames.], batch size: 20, lr: 6.38e-04
+2022-05-14 12:51:31,647 INFO [train.py:812] (7/8) Epoch 12, batch 2250, loss[loss=0.1971, simple_loss=0.272, pruned_loss=0.06114, over 7137.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2641, pruned_loss=0.04582, over 1425092.51 frames.], batch size: 17, lr: 6.38e-04
+2022-05-14 12:52:29,487 INFO [train.py:812] (7/8) Epoch 12, batch 2300, loss[loss=0.1545, simple_loss=0.2431, pruned_loss=0.03294, over 7361.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2656, pruned_loss=0.04606, over 1423837.67 frames.], batch size: 19, lr: 6.38e-04
+2022-05-14 12:53:28,571 INFO [train.py:812] (7/8) Epoch 12, batch 2350, loss[loss=0.207, simple_loss=0.2908, pruned_loss=0.06162, over 7280.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2654, pruned_loss=0.04589, over 1425127.19 frames.], batch size: 24, lr: 6.37e-04
+2022-05-14 12:54:27,678 INFO [train.py:812] (7/8) Epoch 12, batch 2400, loss[loss=0.1982, simple_loss=0.2873, pruned_loss=0.05456, over 7110.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2665, pruned_loss=0.04624, over 1427288.58 frames.], batch size: 21, lr: 6.37e-04
+2022-05-14 12:55:26,386 INFO [train.py:812] (7/8) Epoch 12, batch 2450, loss[loss=0.2099, simple_loss=0.2905, pruned_loss=0.06465, over 7230.00 frames.], tot_loss[loss=0.179, simple_loss=0.266, pruned_loss=0.04602, over 1425018.05 frames.], batch size: 20, lr: 6.37e-04
+2022-05-14 12:56:25,375 INFO [train.py:812] (7/8) Epoch 12, batch 2500, loss[loss=0.1749, simple_loss=0.2559, pruned_loss=0.04697, over 7075.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2656, pruned_loss=0.04584, over 1425002.98 frames.], batch size: 18, lr: 6.36e-04
+2022-05-14 12:57:24,993 INFO [train.py:812] (7/8) Epoch 12, batch 2550, loss[loss=0.1538, simple_loss=0.2272, pruned_loss=0.04021, over 7283.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2659, pruned_loss=0.04568, over 1428262.51 frames.], batch size: 17, lr: 6.36e-04
+2022-05-14 12:58:23,587 INFO [train.py:812] (7/8) Epoch 12, batch 2600, loss[loss=0.2057, simple_loss=0.275, pruned_loss=0.06819, over 7278.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2654, pruned_loss=0.04588, over 1422707.93 frames.], batch size: 24, lr: 6.36e-04
+2022-05-14 12:59:22,490 INFO [train.py:812] (7/8) Epoch 12, batch 2650, loss[loss=0.1726, simple_loss=0.2609, pruned_loss=0.04217, over 7262.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2658, pruned_loss=0.04603, over 1419220.71 frames.], batch size: 19, lr: 6.36e-04
+2022-05-14 13:00:21,670 INFO [train.py:812] (7/8) Epoch 12, batch 2700, loss[loss=0.2104, simple_loss=0.2933, pruned_loss=0.06368, over 7285.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2655, pruned_loss=0.04582, over 1422705.35 frames.], batch size: 25, lr: 6.35e-04
+2022-05-14 13:01:21,331 INFO [train.py:812] (7/8) Epoch 12, batch 2750, loss[loss=0.1416, simple_loss=0.2299, pruned_loss=0.02668, over 7428.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2647, pruned_loss=0.04539, over 1425990.13 frames.], batch size: 20, lr: 6.35e-04
+2022-05-14 13:02:20,442 INFO [train.py:812] (7/8) Epoch 12, batch 2800, loss[loss=0.1985, simple_loss=0.2853, pruned_loss=0.05584, over 7109.00 frames.], tot_loss[loss=0.178, simple_loss=0.265, pruned_loss=0.04556, over 1427082.89 frames.], batch size: 21, lr: 6.35e-04
+2022-05-14 13:03:19,827 INFO [train.py:812] (7/8) Epoch 12, batch 2850, loss[loss=0.1767, simple_loss=0.2716, pruned_loss=0.04089, over 7322.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2654, pruned_loss=0.0459, over 1429440.11 frames.], batch size: 21, lr: 6.34e-04
+2022-05-14 13:04:18,971 INFO [train.py:812] (7/8) Epoch 12, batch 2900, loss[loss=0.1752, simple_loss=0.2665, pruned_loss=0.04194, over 7276.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2655, pruned_loss=0.04576, over 1426250.88 frames.], batch size: 24, lr: 6.34e-04
+2022-05-14 13:05:18,624 INFO [train.py:812] (7/8) Epoch 12, batch 2950, loss[loss=0.1672, simple_loss=0.2673, pruned_loss=0.03353, over 7228.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2661, pruned_loss=0.04652, over 1421444.84 frames.], batch size: 21, lr: 6.34e-04
+2022-05-14 13:06:17,626 INFO [train.py:812] (7/8) Epoch 12, batch 3000, loss[loss=0.183, simple_loss=0.2773, pruned_loss=0.0443, over 7308.00 frames.], tot_loss[loss=0.179, simple_loss=0.2654, pruned_loss=0.04628, over 1422848.61 frames.], batch size: 25, lr: 6.33e-04
+2022-05-14 13:06:17,627 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 13:06:26,033 INFO [train.py:841] (7/8) Epoch 12, validation: loss=0.1553, simple_loss=0.2571, pruned_loss=0.02678, over 698248.00 frames.
+2022-05-14 13:07:25,180 INFO [train.py:812] (7/8) Epoch 12, batch 3050, loss[loss=0.1933, simple_loss=0.2793, pruned_loss=0.05362, over 7375.00 frames.], tot_loss[loss=0.1805, simple_loss=0.267, pruned_loss=0.04697, over 1420167.70 frames.], batch size: 23, lr: 6.33e-04
+2022-05-14 13:08:24,613 INFO [train.py:812] (7/8) Epoch 12, batch 3100, loss[loss=0.1562, simple_loss=0.2359, pruned_loss=0.03825, over 7336.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2654, pruned_loss=0.04661, over 1422248.68 frames.], batch size: 20, lr: 6.33e-04
+2022-05-14 13:09:23,914 INFO [train.py:812] (7/8) Epoch 12, batch 3150, loss[loss=0.1852, simple_loss=0.2756, pruned_loss=0.04745, over 7377.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2655, pruned_loss=0.0468, over 1423959.65 frames.], batch size: 23, lr: 6.33e-04
+2022-05-14 13:10:22,885 INFO [train.py:812] (7/8) Epoch 12, batch 3200, loss[loss=0.1665, simple_loss=0.2655, pruned_loss=0.03375, over 7113.00 frames.], tot_loss[loss=0.1799, simple_loss=0.266, pruned_loss=0.04691, over 1423822.49 frames.], batch size: 21, lr: 6.32e-04
+2022-05-14 13:11:22,020 INFO [train.py:812] (7/8) Epoch 12, batch 3250, loss[loss=0.1793, simple_loss=0.2612, pruned_loss=0.04874, over 7425.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2648, pruned_loss=0.04594, over 1424669.30 frames.], batch size: 21, lr: 6.32e-04
+2022-05-14 13:12:21,140 INFO [train.py:812] (7/8) Epoch 12, batch 3300, loss[loss=0.1639, simple_loss=0.2465, pruned_loss=0.04062, over 7002.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2661, pruned_loss=0.04626, over 1425129.90 frames.], batch size: 16, lr: 6.32e-04
+2022-05-14 13:13:18,570 INFO [train.py:812] (7/8) Epoch 12, batch 3350, loss[loss=0.1656, simple_loss=0.2527, pruned_loss=0.03919, over 7286.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2664, pruned_loss=0.04599, over 1426208.46 frames.], batch size: 18, lr: 6.31e-04
+2022-05-14 13:14:17,048 INFO [train.py:812] (7/8) Epoch 12, batch 3400, loss[loss=0.1913, simple_loss=0.2688, pruned_loss=0.05689, over 6347.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2662, pruned_loss=0.04545, over 1421265.69 frames.], batch size: 37, lr: 6.31e-04
+2022-05-14 13:15:16,609 INFO [train.py:812] (7/8) Epoch 12, batch 3450, loss[loss=0.1771, simple_loss=0.267, pruned_loss=0.04364, over 7132.00 frames.], tot_loss[loss=0.1785, simple_loss=0.266, pruned_loss=0.04552, over 1419449.04 frames.], batch size: 21, lr: 6.31e-04
+2022-05-14 13:16:15,042 INFO [train.py:812] (7/8) Epoch 12, batch 3500, loss[loss=0.1825, simple_loss=0.2751, pruned_loss=0.0449, over 7322.00 frames.], tot_loss[loss=0.1785, simple_loss=0.266, pruned_loss=0.04553, over 1425586.50 frames.], batch size: 21, lr: 6.31e-04
+2022-05-14 13:17:13,784 INFO [train.py:812] (7/8) Epoch 12, batch 3550, loss[loss=0.1372, simple_loss=0.2205, pruned_loss=0.02694, over 7002.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2652, pruned_loss=0.04507, over 1424531.46 frames.], batch size: 16, lr: 6.30e-04
+2022-05-14 13:18:12,643 INFO [train.py:812] (7/8) Epoch 12, batch 3600, loss[loss=0.2064, simple_loss=0.2898, pruned_loss=0.06154, over 7236.00 frames.], tot_loss[loss=0.179, simple_loss=0.2665, pruned_loss=0.04579, over 1426060.27 frames.], batch size: 20, lr: 6.30e-04
+2022-05-14 13:19:11,494 INFO [train.py:812] (7/8) Epoch 12, batch 3650, loss[loss=0.1935, simple_loss=0.2848, pruned_loss=0.05114, over 7428.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2661, pruned_loss=0.04574, over 1424900.88 frames.], batch size: 20, lr: 6.30e-04
+2022-05-14 13:20:08,376 INFO [train.py:812] (7/8) Epoch 12, batch 3700, loss[loss=0.1696, simple_loss=0.2558, pruned_loss=0.04173, over 6825.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2657, pruned_loss=0.04597, over 1421646.59 frames.], batch size: 31, lr: 6.29e-04
+2022-05-14 13:21:06,302 INFO [train.py:812] (7/8) Epoch 12, batch 3750, loss[loss=0.208, simple_loss=0.3011, pruned_loss=0.05747, over 7359.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2648, pruned_loss=0.04546, over 1425555.19 frames.], batch size: 23, lr: 6.29e-04
+2022-05-14 13:22:05,739 INFO [train.py:812] (7/8) Epoch 12, batch 3800, loss[loss=0.1711, simple_loss=0.2615, pruned_loss=0.04035, over 7169.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2641, pruned_loss=0.04484, over 1428191.81 frames.], batch size: 26, lr: 6.29e-04
+2022-05-14 13:23:04,560 INFO [train.py:812] (7/8) Epoch 12, batch 3850, loss[loss=0.1701, simple_loss=0.2652, pruned_loss=0.03751, over 7107.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2642, pruned_loss=0.04497, over 1428918.12 frames.], batch size: 21, lr: 6.29e-04
+2022-05-14 13:24:03,561 INFO [train.py:812] (7/8) Epoch 12, batch 3900, loss[loss=0.1535, simple_loss=0.2353, pruned_loss=0.03584, over 7429.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2642, pruned_loss=0.04506, over 1429882.51 frames.], batch size: 20, lr: 6.28e-04
+2022-05-14 13:25:02,822 INFO [train.py:812] (7/8) Epoch 12, batch 3950, loss[loss=0.1804, simple_loss=0.271, pruned_loss=0.0449, over 7228.00 frames.], tot_loss[loss=0.177, simple_loss=0.2638, pruned_loss=0.04511, over 1431240.48 frames.], batch size: 20, lr: 6.28e-04
+2022-05-14 13:26:01,762 INFO [train.py:812] (7/8) Epoch 12, batch 4000, loss[loss=0.1727, simple_loss=0.2632, pruned_loss=0.04111, over 7413.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2646, pruned_loss=0.04548, over 1425651.52 frames.], batch size: 21, lr: 6.28e-04
+2022-05-14 13:27:01,254 INFO [train.py:812] (7/8) Epoch 12, batch 4050, loss[loss=0.1948, simple_loss=0.2813, pruned_loss=0.05408, over 7433.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2639, pruned_loss=0.04534, over 1424185.41 frames.], batch size: 20, lr: 6.27e-04
+2022-05-14 13:28:00,411 INFO [train.py:812] (7/8) Epoch 12, batch 4100, loss[loss=0.1922, simple_loss=0.2787, pruned_loss=0.05281, over 7333.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2644, pruned_loss=0.04519, over 1421841.28 frames.], batch size: 20, lr: 6.27e-04
+2022-05-14 13:28:59,935 INFO [train.py:812] (7/8) Epoch 12, batch 4150, loss[loss=0.1761, simple_loss=0.2674, pruned_loss=0.04239, over 7241.00 frames.], tot_loss[loss=0.178, simple_loss=0.2648, pruned_loss=0.04555, over 1421452.61 frames.], batch size: 20, lr: 6.27e-04
+2022-05-14 13:29:59,301 INFO [train.py:812] (7/8) Epoch 12, batch 4200, loss[loss=0.1556, simple_loss=0.2488, pruned_loss=0.03121, over 7329.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2645, pruned_loss=0.04502, over 1421291.09 frames.], batch size: 22, lr: 6.27e-04
+2022-05-14 13:30:59,194 INFO [train.py:812] (7/8) Epoch 12, batch 4250, loss[loss=0.1663, simple_loss=0.2449, pruned_loss=0.0439, over 7414.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2641, pruned_loss=0.04485, over 1424569.65 frames.], batch size: 18, lr: 6.26e-04
+2022-05-14 13:31:58,508 INFO [train.py:812] (7/8) Epoch 12, batch 4300, loss[loss=0.1639, simple_loss=0.2587, pruned_loss=0.0346, over 7220.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2635, pruned_loss=0.04511, over 1418430.08 frames.], batch size: 20, lr: 6.26e-04
+2022-05-14 13:32:57,483 INFO [train.py:812] (7/8) Epoch 12, batch 4350, loss[loss=0.2047, simple_loss=0.2864, pruned_loss=0.06147, over 7209.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2625, pruned_loss=0.04509, over 1420186.45 frames.], batch size: 22, lr: 6.26e-04
+2022-05-14 13:33:56,612 INFO [train.py:812] (7/8) Epoch 12, batch 4400, loss[loss=0.2209, simple_loss=0.3098, pruned_loss=0.06596, over 7326.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2624, pruned_loss=0.04486, over 1418542.66 frames.], batch size: 21, lr: 6.25e-04
+2022-05-14 13:34:56,740 INFO [train.py:812] (7/8) Epoch 12, batch 4450, loss[loss=0.2046, simple_loss=0.2968, pruned_loss=0.0562, over 6396.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2617, pruned_loss=0.045, over 1405119.98 frames.], batch size: 38, lr: 6.25e-04
+2022-05-14 13:35:55,774 INFO [train.py:812] (7/8) Epoch 12, batch 4500, loss[loss=0.1746, simple_loss=0.268, pruned_loss=0.04057, over 6631.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2625, pruned_loss=0.04601, over 1389717.87 frames.], batch size: 38, lr: 6.25e-04
+2022-05-14 13:36:54,598 INFO [train.py:812] (7/8) Epoch 12, batch 4550, loss[loss=0.2316, simple_loss=0.2878, pruned_loss=0.08768, over 5285.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2644, pruned_loss=0.04739, over 1350689.41 frames.], batch size: 52, lr: 6.25e-04
+2022-05-14 13:38:08,630 INFO [train.py:812] (7/8) Epoch 13, batch 0, loss[loss=0.1649, simple_loss=0.2534, pruned_loss=0.03815, over 7142.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2534, pruned_loss=0.03815, over 7142.00 frames.], batch size: 20, lr: 6.03e-04
+2022-05-14 13:39:08,107 INFO [train.py:812] (7/8) Epoch 13, batch 50, loss[loss=0.1718, simple_loss=0.2577, pruned_loss=0.04298, over 7243.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2617, pruned_loss=0.04442, over 319155.80 frames.], batch size: 20, lr: 6.03e-04
+2022-05-14 13:40:06,205 INFO [train.py:812] (7/8) Epoch 13, batch 100, loss[loss=0.1704, simple_loss=0.2594, pruned_loss=0.04071, over 7207.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2622, pruned_loss=0.04346, over 565153.00 frames.], batch size: 23, lr: 6.03e-04
+2022-05-14 13:41:05,037 INFO [train.py:812] (7/8) Epoch 13, batch 150, loss[loss=0.17, simple_loss=0.2558, pruned_loss=0.04209, over 7149.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2638, pruned_loss=0.0437, over 754313.06 frames.], batch size: 20, lr: 6.03e-04
+2022-05-14 13:42:04,255 INFO [train.py:812] (7/8) Epoch 13, batch 200, loss[loss=0.1684, simple_loss=0.2648, pruned_loss=0.03603, over 7143.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2636, pruned_loss=0.0441, over 901064.06 frames.], batch size: 20, lr: 6.02e-04
+2022-05-14 13:43:03,758 INFO [train.py:812] (7/8) Epoch 13, batch 250, loss[loss=0.1272, simple_loss=0.2097, pruned_loss=0.02234, over 7218.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2635, pruned_loss=0.04457, over 1014887.78 frames.], batch size: 16, lr: 6.02e-04
+2022-05-14 13:44:02,541 INFO [train.py:812] (7/8) Epoch 13, batch 300, loss[loss=0.1795, simple_loss=0.2511, pruned_loss=0.05398, over 7142.00 frames.], tot_loss[loss=0.176, simple_loss=0.263, pruned_loss=0.04451, over 1105078.90 frames.], batch size: 20, lr: 6.02e-04
+2022-05-14 13:45:01,903 INFO [train.py:812] (7/8) Epoch 13, batch 350, loss[loss=0.1737, simple_loss=0.2656, pruned_loss=0.04093, over 7071.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2634, pruned_loss=0.04439, over 1177004.27 frames.], batch size: 28, lr: 6.01e-04
+2022-05-14 13:46:00,678 INFO [train.py:812] (7/8) Epoch 13, batch 400, loss[loss=0.1545, simple_loss=0.2496, pruned_loss=0.02972, over 7355.00 frames.], tot_loss[loss=0.1753, simple_loss=0.263, pruned_loss=0.04381, over 1234118.66 frames.], batch size: 19, lr: 6.01e-04
+2022-05-14 13:46:57,924 INFO [train.py:812] (7/8) Epoch 13, batch 450, loss[loss=0.1728, simple_loss=0.2707, pruned_loss=0.03739, over 7328.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2626, pruned_loss=0.04361, over 1277563.78 frames.], batch size: 21, lr: 6.01e-04
+2022-05-14 13:47:55,570 INFO [train.py:812] (7/8) Epoch 13, batch 500, loss[loss=0.1613, simple_loss=0.259, pruned_loss=0.03178, over 6286.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2614, pruned_loss=0.04338, over 1310451.50 frames.], batch size: 37, lr: 6.01e-04
+2022-05-14 13:48:55,171 INFO [train.py:812] (7/8) Epoch 13, batch 550, loss[loss=0.1996, simple_loss=0.2934, pruned_loss=0.05296, over 7403.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2625, pruned_loss=0.04403, over 1332533.15 frames.], batch size: 23, lr: 6.00e-04
+2022-05-14 13:49:54,048 INFO [train.py:812] (7/8) Epoch 13, batch 600, loss[loss=0.1477, simple_loss=0.2287, pruned_loss=0.03332, over 7197.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2614, pruned_loss=0.0437, over 1346753.46 frames.], batch size: 16, lr: 6.00e-04
+2022-05-14 13:50:53,029 INFO [train.py:812] (7/8) Epoch 13, batch 650, loss[loss=0.1775, simple_loss=0.2586, pruned_loss=0.04819, over 7275.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2622, pruned_loss=0.04383, over 1366348.88 frames.], batch size: 18, lr: 6.00e-04
+2022-05-14 13:51:52,338 INFO [train.py:812] (7/8) Epoch 13, batch 700, loss[loss=0.1738, simple_loss=0.2422, pruned_loss=0.05275, over 6840.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2633, pruned_loss=0.04413, over 1383907.05 frames.], batch size: 15, lr: 6.00e-04
+2022-05-14 13:52:51,796 INFO [train.py:812] (7/8) Epoch 13, batch 750, loss[loss=0.2439, simple_loss=0.3149, pruned_loss=0.08646, over 7216.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2642, pruned_loss=0.04457, over 1396250.19 frames.], batch size: 23, lr: 5.99e-04
+2022-05-14 13:53:50,425 INFO [train.py:812] (7/8) Epoch 13, batch 800, loss[loss=0.1782, simple_loss=0.2667, pruned_loss=0.04482, over 7214.00 frames.], tot_loss[loss=0.1768, simple_loss=0.264, pruned_loss=0.04481, over 1405154.25 frames.], batch size: 22, lr: 5.99e-04
+2022-05-14 13:54:49,226 INFO [train.py:812] (7/8) Epoch 13, batch 850, loss[loss=0.1433, simple_loss=0.2254, pruned_loss=0.0306, over 7126.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2647, pruned_loss=0.04498, over 1412440.44 frames.], batch size: 17, lr: 5.99e-04
+2022-05-14 13:55:48,217 INFO [train.py:812] (7/8) Epoch 13, batch 900, loss[loss=0.1733, simple_loss=0.2609, pruned_loss=0.04283, over 7324.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2635, pruned_loss=0.04448, over 1415567.47 frames.], batch size: 20, lr: 5.99e-04
+2022-05-14 13:56:53,018 INFO [train.py:812] (7/8) Epoch 13, batch 950, loss[loss=0.1844, simple_loss=0.2792, pruned_loss=0.04479, over 7135.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2632, pruned_loss=0.04413, over 1415750.45 frames.], batch size: 26, lr: 5.98e-04
+2022-05-14 13:57:52,251 INFO [train.py:812] (7/8) Epoch 13, batch 1000, loss[loss=0.1798, simple_loss=0.2719, pruned_loss=0.04383, over 6524.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2635, pruned_loss=0.04406, over 1416249.56 frames.], batch size: 38, lr: 5.98e-04
+2022-05-14 13:58:51,893 INFO [train.py:812] (7/8) Epoch 13, batch 1050, loss[loss=0.1726, simple_loss=0.2569, pruned_loss=0.04418, over 7246.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2633, pruned_loss=0.04468, over 1417040.55 frames.], batch size: 19, lr: 5.98e-04
+2022-05-14 13:59:49,651 INFO [train.py:812] (7/8) Epoch 13, batch 1100, loss[loss=0.1715, simple_loss=0.2632, pruned_loss=0.03985, over 7380.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2635, pruned_loss=0.04465, over 1423023.42 frames.], batch size: 23, lr: 5.97e-04
+2022-05-14 14:00:49,279 INFO [train.py:812] (7/8) Epoch 13, batch 1150, loss[loss=0.1927, simple_loss=0.2776, pruned_loss=0.05388, over 7333.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2636, pruned_loss=0.04464, over 1425421.18 frames.], batch size: 20, lr: 5.97e-04
+2022-05-14 14:01:48,665 INFO [train.py:812] (7/8) Epoch 13, batch 1200, loss[loss=0.2191, simple_loss=0.2942, pruned_loss=0.07202, over 5281.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2632, pruned_loss=0.04472, over 1422473.78 frames.], batch size: 53, lr: 5.97e-04
+2022-05-14 14:02:48,281 INFO [train.py:812] (7/8) Epoch 13, batch 1250, loss[loss=0.1954, simple_loss=0.2748, pruned_loss=0.05803, over 7161.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2634, pruned_loss=0.04475, over 1419540.88 frames.], batch size: 19, lr: 5.97e-04
+2022-05-14 14:03:47,362 INFO [train.py:812] (7/8) Epoch 13, batch 1300, loss[loss=0.1588, simple_loss=0.2446, pruned_loss=0.03652, over 7071.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2622, pruned_loss=0.04404, over 1420337.36 frames.], batch size: 18, lr: 5.96e-04
+2022-05-14 14:04:46,596 INFO [train.py:812] (7/8) Epoch 13, batch 1350, loss[loss=0.2189, simple_loss=0.2936, pruned_loss=0.07217, over 4934.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2634, pruned_loss=0.04437, over 1417590.36 frames.], batch size: 52, lr: 5.96e-04
+2022-05-14 14:05:45,518 INFO [train.py:812] (7/8) Epoch 13, batch 1400, loss[loss=0.1635, simple_loss=0.2571, pruned_loss=0.03494, over 7252.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2642, pruned_loss=0.04457, over 1416729.55 frames.], batch size: 25, lr: 5.96e-04
+2022-05-14 14:06:43,994 INFO [train.py:812] (7/8) Epoch 13, batch 1450, loss[loss=0.1843, simple_loss=0.2852, pruned_loss=0.04169, over 7320.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2638, pruned_loss=0.04428, over 1414083.05 frames.], batch size: 21, lr: 5.96e-04
+2022-05-14 14:07:42,563 INFO [train.py:812] (7/8) Epoch 13, batch 1500, loss[loss=0.1817, simple_loss=0.2672, pruned_loss=0.04815, over 7216.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2633, pruned_loss=0.04413, over 1417571.55 frames.], batch size: 23, lr: 5.95e-04
+2022-05-14 14:08:42,643 INFO [train.py:812] (7/8) Epoch 13, batch 1550, loss[loss=0.1975, simple_loss=0.2956, pruned_loss=0.04974, over 7036.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2628, pruned_loss=0.04419, over 1419147.19 frames.], batch size: 28, lr: 5.95e-04
+2022-05-14 14:09:41,297 INFO [train.py:812] (7/8) Epoch 13, batch 1600, loss[loss=0.183, simple_loss=0.2655, pruned_loss=0.0502, over 7311.00 frames.], tot_loss[loss=0.1758, simple_loss=0.263, pruned_loss=0.04426, over 1417896.86 frames.], batch size: 25, lr: 5.95e-04
+2022-05-14 14:10:39,378 INFO [train.py:812] (7/8) Epoch 13, batch 1650, loss[loss=0.1877, simple_loss=0.2868, pruned_loss=0.04433, over 7315.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2628, pruned_loss=0.04412, over 1421148.98 frames.], batch size: 24, lr: 5.95e-04
+2022-05-14 14:11:36,477 INFO [train.py:812] (7/8) Epoch 13, batch 1700, loss[loss=0.1626, simple_loss=0.238, pruned_loss=0.04358, over 7124.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2628, pruned_loss=0.04446, over 1417897.29 frames.], batch size: 17, lr: 5.94e-04
+2022-05-14 14:12:34,793 INFO [train.py:812] (7/8) Epoch 13, batch 1750, loss[loss=0.1839, simple_loss=0.2725, pruned_loss=0.04765, over 7180.00 frames.], tot_loss[loss=0.175, simple_loss=0.262, pruned_loss=0.04407, over 1421478.33 frames.], batch size: 26, lr: 5.94e-04
+2022-05-14 14:13:34,207 INFO [train.py:812] (7/8) Epoch 13, batch 1800, loss[loss=0.1683, simple_loss=0.2502, pruned_loss=0.0432, over 7006.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2629, pruned_loss=0.04436, over 1426716.50 frames.], batch size: 16, lr: 5.94e-04
+2022-05-14 14:14:33,831 INFO [train.py:812] (7/8) Epoch 13, batch 1850, loss[loss=0.1837, simple_loss=0.2736, pruned_loss=0.04692, over 7339.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2627, pruned_loss=0.04412, over 1427343.41 frames.], batch size: 22, lr: 5.94e-04
+2022-05-14 14:15:33,222 INFO [train.py:812] (7/8) Epoch 13, batch 1900, loss[loss=0.1641, simple_loss=0.2572, pruned_loss=0.03545, over 7226.00 frames.], tot_loss[loss=0.1756, simple_loss=0.263, pruned_loss=0.04405, over 1427902.38 frames.], batch size: 20, lr: 5.93e-04
+2022-05-14 14:16:32,259 INFO [train.py:812] (7/8) Epoch 13, batch 1950, loss[loss=0.1634, simple_loss=0.2407, pruned_loss=0.04308, over 7286.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2631, pruned_loss=0.04419, over 1428009.88 frames.], batch size: 17, lr: 5.93e-04
+2022-05-14 14:17:31,545 INFO [train.py:812] (7/8) Epoch 13, batch 2000, loss[loss=0.1631, simple_loss=0.2381, pruned_loss=0.04402, over 6993.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2616, pruned_loss=0.04349, over 1427961.38 frames.], batch size: 16, lr: 5.93e-04
+2022-05-14 14:18:40,092 INFO [train.py:812] (7/8) Epoch 13, batch 2050, loss[loss=0.1769, simple_loss=0.2558, pruned_loss=0.049, over 7165.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2612, pruned_loss=0.04356, over 1421204.24 frames.], batch size: 19, lr: 5.93e-04
+2022-05-14 14:19:39,677 INFO [train.py:812] (7/8) Epoch 13, batch 2100, loss[loss=0.1885, simple_loss=0.2745, pruned_loss=0.05124, over 7159.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2613, pruned_loss=0.04383, over 1422112.85 frames.], batch size: 19, lr: 5.92e-04
+2022-05-14 14:20:39,454 INFO [train.py:812] (7/8) Epoch 13, batch 2150, loss[loss=0.1538, simple_loss=0.2351, pruned_loss=0.03626, over 7265.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2615, pruned_loss=0.0436, over 1421986.80 frames.], batch size: 18, lr: 5.92e-04
+2022-05-14 14:21:36,910 INFO [train.py:812] (7/8) Epoch 13, batch 2200, loss[loss=0.1811, simple_loss=0.2692, pruned_loss=0.04656, over 7324.00 frames.], tot_loss[loss=0.174, simple_loss=0.2614, pruned_loss=0.04334, over 1422794.01 frames.], batch size: 20, lr: 5.92e-04
+2022-05-14 14:22:35,552 INFO [train.py:812] (7/8) Epoch 13, batch 2250, loss[loss=0.1848, simple_loss=0.2804, pruned_loss=0.04458, over 7041.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2609, pruned_loss=0.04322, over 1420819.10 frames.], batch size: 28, lr: 5.91e-04
+2022-05-14 14:23:34,282 INFO [train.py:812] (7/8) Epoch 13, batch 2300, loss[loss=0.1666, simple_loss=0.2619, pruned_loss=0.03565, over 7104.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2617, pruned_loss=0.0436, over 1424788.73 frames.], batch size: 21, lr: 5.91e-04
+2022-05-14 14:24:34,084 INFO [train.py:812] (7/8) Epoch 13, batch 2350, loss[loss=0.1733, simple_loss=0.2537, pruned_loss=0.04644, over 7160.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2618, pruned_loss=0.04379, over 1425854.45 frames.], batch size: 19, lr: 5.91e-04
+2022-05-14 14:25:33,571 INFO [train.py:812] (7/8) Epoch 13, batch 2400, loss[loss=0.1663, simple_loss=0.2528, pruned_loss=0.03996, over 7148.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2611, pruned_loss=0.04338, over 1426242.77 frames.], batch size: 17, lr: 5.91e-04
+2022-05-14 14:26:31,992 INFO [train.py:812] (7/8) Epoch 13, batch 2450, loss[loss=0.1769, simple_loss=0.2732, pruned_loss=0.04034, over 7226.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2615, pruned_loss=0.04318, over 1425391.32 frames.], batch size: 21, lr: 5.90e-04
+2022-05-14 14:27:30,771 INFO [train.py:812] (7/8) Epoch 13, batch 2500, loss[loss=0.1785, simple_loss=0.2678, pruned_loss=0.04456, over 7275.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2622, pruned_loss=0.0435, over 1426166.47 frames.], batch size: 18, lr: 5.90e-04
+2022-05-14 14:28:30,434 INFO [train.py:812] (7/8) Epoch 13, batch 2550, loss[loss=0.157, simple_loss=0.2347, pruned_loss=0.0397, over 6843.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2618, pruned_loss=0.0436, over 1428224.18 frames.], batch size: 15, lr: 5.90e-04
+2022-05-14 14:29:29,661 INFO [train.py:812] (7/8) Epoch 13, batch 2600, loss[loss=0.1754, simple_loss=0.2624, pruned_loss=0.04422, over 7221.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2618, pruned_loss=0.04395, over 1424571.65 frames.], batch size: 16, lr: 5.90e-04
+2022-05-14 14:30:29,037 INFO [train.py:812] (7/8) Epoch 13, batch 2650, loss[loss=0.1482, simple_loss=0.2301, pruned_loss=0.03315, over 7000.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2621, pruned_loss=0.04416, over 1423049.80 frames.], batch size: 16, lr: 5.89e-04
+2022-05-14 14:31:27,722 INFO [train.py:812] (7/8) Epoch 13, batch 2700, loss[loss=0.147, simple_loss=0.2326, pruned_loss=0.03064, over 6991.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2624, pruned_loss=0.04399, over 1424176.39 frames.], batch size: 16, lr: 5.89e-04
+2022-05-14 14:32:27,083 INFO [train.py:812] (7/8) Epoch 13, batch 2750, loss[loss=0.1671, simple_loss=0.2579, pruned_loss=0.03817, over 7115.00 frames.], tot_loss[loss=0.175, simple_loss=0.262, pruned_loss=0.04396, over 1421687.54 frames.], batch size: 21, lr: 5.89e-04
+2022-05-14 14:33:24,894 INFO [train.py:812] (7/8) Epoch 13, batch 2800, loss[loss=0.1701, simple_loss=0.2396, pruned_loss=0.05026, over 7124.00 frames.], tot_loss[loss=0.1755, simple_loss=0.263, pruned_loss=0.04405, over 1421395.94 frames.], batch size: 17, lr: 5.89e-04
+2022-05-14 14:34:24,920 INFO [train.py:812] (7/8) Epoch 13, batch 2850, loss[loss=0.1765, simple_loss=0.2688, pruned_loss=0.04206, over 7377.00 frames.], tot_loss[loss=0.176, simple_loss=0.2635, pruned_loss=0.04428, over 1426800.65 frames.], batch size: 23, lr: 5.88e-04
+2022-05-14 14:35:22,608 INFO [train.py:812] (7/8) Epoch 13, batch 2900, loss[loss=0.1693, simple_loss=0.2586, pruned_loss=0.04004, over 7363.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2644, pruned_loss=0.04445, over 1425196.78 frames.], batch size: 19, lr: 5.88e-04
+2022-05-14 14:36:21,984 INFO [train.py:812] (7/8) Epoch 13, batch 2950, loss[loss=0.1755, simple_loss=0.2611, pruned_loss=0.04494, over 7123.00 frames.], tot_loss[loss=0.1765, simple_loss=0.264, pruned_loss=0.04453, over 1426709.33 frames.], batch size: 21, lr: 5.88e-04
+2022-05-14 14:37:20,749 INFO [train.py:812] (7/8) Epoch 13, batch 3000, loss[loss=0.1518, simple_loss=0.2357, pruned_loss=0.03394, over 7274.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2638, pruned_loss=0.04436, over 1428159.47 frames.], batch size: 17, lr: 5.88e-04
+2022-05-14 14:37:20,751 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 14:37:28,227 INFO [train.py:841] (7/8) Epoch 13, validation: loss=0.1549, simple_loss=0.2559, pruned_loss=0.02694, over 698248.00 frames.
+2022-05-14 14:38:28,342 INFO [train.py:812] (7/8) Epoch 13, batch 3050, loss[loss=0.1522, simple_loss=0.2343, pruned_loss=0.03506, over 7116.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2627, pruned_loss=0.04375, over 1428735.95 frames.], batch size: 17, lr: 5.87e-04
+2022-05-14 14:39:27,863 INFO [train.py:812] (7/8) Epoch 13, batch 3100, loss[loss=0.1892, simple_loss=0.2778, pruned_loss=0.0503, over 7114.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2619, pruned_loss=0.04341, over 1428207.01 frames.], batch size: 21, lr: 5.87e-04
+2022-05-14 14:40:36,471 INFO [train.py:812] (7/8) Epoch 13, batch 3150, loss[loss=0.1775, simple_loss=0.2668, pruned_loss=0.04407, over 7276.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2636, pruned_loss=0.04403, over 1425481.33 frames.], batch size: 25, lr: 5.87e-04
+2022-05-14 14:41:35,481 INFO [train.py:812] (7/8) Epoch 13, batch 3200, loss[loss=0.2309, simple_loss=0.2969, pruned_loss=0.08249, over 5319.00 frames.], tot_loss[loss=0.1762, simple_loss=0.264, pruned_loss=0.04422, over 1426803.04 frames.], batch size: 52, lr: 5.87e-04
+2022-05-14 14:42:44,513 INFO [train.py:812] (7/8) Epoch 13, batch 3250, loss[loss=0.139, simple_loss=0.2218, pruned_loss=0.02811, over 7278.00 frames.], tot_loss[loss=0.1754, simple_loss=0.263, pruned_loss=0.04394, over 1428298.93 frames.], batch size: 17, lr: 5.86e-04
+2022-05-14 14:43:53,117 INFO [train.py:812] (7/8) Epoch 13, batch 3300, loss[loss=0.1884, simple_loss=0.2656, pruned_loss=0.05557, over 7330.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2627, pruned_loss=0.04424, over 1428056.82 frames.], batch size: 20, lr: 5.86e-04
+2022-05-14 14:44:51,613 INFO [train.py:812] (7/8) Epoch 13, batch 3350, loss[loss=0.1512, simple_loss=0.2256, pruned_loss=0.03839, over 7012.00 frames.], tot_loss[loss=0.1751, simple_loss=0.262, pruned_loss=0.04414, over 1420279.78 frames.], batch size: 16, lr: 5.86e-04
+2022-05-14 14:46:18,941 INFO [train.py:812] (7/8) Epoch 13, batch 3400, loss[loss=0.1771, simple_loss=0.2604, pruned_loss=0.04689, over 7378.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2626, pruned_loss=0.044, over 1424607.14 frames.], batch size: 23, lr: 5.86e-04
+2022-05-14 14:47:27,749 INFO [train.py:812] (7/8) Epoch 13, batch 3450, loss[loss=0.1487, simple_loss=0.2419, pruned_loss=0.02779, over 7420.00 frames.], tot_loss[loss=0.1755, simple_loss=0.263, pruned_loss=0.04398, over 1414207.96 frames.], batch size: 18, lr: 5.85e-04
+2022-05-14 14:48:26,523 INFO [train.py:812] (7/8) Epoch 13, batch 3500, loss[loss=0.1816, simple_loss=0.2693, pruned_loss=0.04692, over 6768.00 frames.], tot_loss[loss=0.176, simple_loss=0.2635, pruned_loss=0.04424, over 1416504.41 frames.], batch size: 31, lr: 5.85e-04
+2022-05-14 14:49:26,059 INFO [train.py:812] (7/8) Epoch 13, batch 3550, loss[loss=0.1565, simple_loss=0.2424, pruned_loss=0.03534, over 6989.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2635, pruned_loss=0.04387, over 1421815.40 frames.], batch size: 16, lr: 5.85e-04
+2022-05-14 14:50:24,028 INFO [train.py:812] (7/8) Epoch 13, batch 3600, loss[loss=0.1589, simple_loss=0.2475, pruned_loss=0.03517, over 7290.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2628, pruned_loss=0.04383, over 1421838.86 frames.], batch size: 18, lr: 5.85e-04
+2022-05-14 14:51:22,141 INFO [train.py:812] (7/8) Epoch 13, batch 3650, loss[loss=0.2189, simple_loss=0.3089, pruned_loss=0.06443, over 7409.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2623, pruned_loss=0.0434, over 1424459.26 frames.], batch size: 21, lr: 5.84e-04
+2022-05-14 14:52:20,938 INFO [train.py:812] (7/8) Epoch 13, batch 3700, loss[loss=0.1731, simple_loss=0.2611, pruned_loss=0.04255, over 7260.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2611, pruned_loss=0.04293, over 1425231.76 frames.], batch size: 19, lr: 5.84e-04
+2022-05-14 14:53:20,300 INFO [train.py:812] (7/8) Epoch 13, batch 3750, loss[loss=0.1905, simple_loss=0.2821, pruned_loss=0.04948, over 7419.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2612, pruned_loss=0.04288, over 1424980.87 frames.], batch size: 21, lr: 5.84e-04
+2022-05-14 14:54:19,206 INFO [train.py:812] (7/8) Epoch 13, batch 3800, loss[loss=0.1914, simple_loss=0.2779, pruned_loss=0.05248, over 7008.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2615, pruned_loss=0.043, over 1428695.54 frames.], batch size: 28, lr: 5.84e-04
+2022-05-14 14:55:18,401 INFO [train.py:812] (7/8) Epoch 13, batch 3850, loss[loss=0.1844, simple_loss=0.2854, pruned_loss=0.04167, over 7197.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2637, pruned_loss=0.04408, over 1426058.47 frames.], batch size: 22, lr: 5.83e-04
+2022-05-14 14:56:17,075 INFO [train.py:812] (7/8) Epoch 13, batch 3900, loss[loss=0.1884, simple_loss=0.276, pruned_loss=0.05035, over 7300.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2631, pruned_loss=0.04377, over 1424953.51 frames.], batch size: 24, lr: 5.83e-04
+2022-05-14 14:57:16,840 INFO [train.py:812] (7/8) Epoch 13, batch 3950, loss[loss=0.1762, simple_loss=0.255, pruned_loss=0.04869, over 7183.00 frames.], tot_loss[loss=0.175, simple_loss=0.2627, pruned_loss=0.0437, over 1423814.39 frames.], batch size: 23, lr: 5.83e-04
+2022-05-14 14:58:15,093 INFO [train.py:812] (7/8) Epoch 13, batch 4000, loss[loss=0.1451, simple_loss=0.2274, pruned_loss=0.03136, over 7138.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2626, pruned_loss=0.04346, over 1423058.45 frames.], batch size: 17, lr: 5.83e-04
+2022-05-14 14:59:14,587 INFO [train.py:812] (7/8) Epoch 13, batch 4050, loss[loss=0.157, simple_loss=0.248, pruned_loss=0.03306, over 7239.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2623, pruned_loss=0.0434, over 1424997.53 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:00:14,106 INFO [train.py:812] (7/8) Epoch 13, batch 4100, loss[loss=0.2107, simple_loss=0.3088, pruned_loss=0.05632, over 7138.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2615, pruned_loss=0.04343, over 1424591.42 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:01:13,286 INFO [train.py:812] (7/8) Epoch 13, batch 4150, loss[loss=0.1493, simple_loss=0.2412, pruned_loss=0.02868, over 7444.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2619, pruned_loss=0.04353, over 1419367.33 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:02:11,359 INFO [train.py:812] (7/8) Epoch 13, batch 4200, loss[loss=0.189, simple_loss=0.2751, pruned_loss=0.05143, over 7148.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2609, pruned_loss=0.04305, over 1420664.13 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:03:10,147 INFO [train.py:812] (7/8) Epoch 13, batch 4250, loss[loss=0.1819, simple_loss=0.2677, pruned_loss=0.04809, over 7189.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2607, pruned_loss=0.04302, over 1418472.50 frames.], batch size: 26, lr: 5.81e-04
+2022-05-14 15:04:08,207 INFO [train.py:812] (7/8) Epoch 13, batch 4300, loss[loss=0.1618, simple_loss=0.2536, pruned_loss=0.035, over 7432.00 frames.], tot_loss[loss=0.175, simple_loss=0.2624, pruned_loss=0.04383, over 1415108.85 frames.], batch size: 20, lr: 5.81e-04
+2022-05-14 15:05:06,787 INFO [train.py:812] (7/8) Epoch 13, batch 4350, loss[loss=0.1493, simple_loss=0.226, pruned_loss=0.03632, over 6991.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2618, pruned_loss=0.04371, over 1409119.68 frames.], batch size: 16, lr: 5.81e-04
+2022-05-14 15:06:06,065 INFO [train.py:812] (7/8) Epoch 13, batch 4400, loss[loss=0.1971, simple_loss=0.2717, pruned_loss=0.06118, over 5231.00 frames.], tot_loss[loss=0.174, simple_loss=0.2607, pruned_loss=0.04363, over 1408184.51 frames.], batch size: 53, lr: 5.81e-04
+2022-05-14 15:07:04,961 INFO [train.py:812] (7/8) Epoch 13, batch 4450, loss[loss=0.2086, simple_loss=0.2991, pruned_loss=0.05901, over 7293.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2613, pruned_loss=0.04393, over 1405335.15 frames.], batch size: 24, lr: 5.81e-04
+2022-05-14 15:08:03,296 INFO [train.py:812] (7/8) Epoch 13, batch 4500, loss[loss=0.1641, simple_loss=0.2569, pruned_loss=0.03568, over 7406.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2627, pruned_loss=0.04474, over 1386071.55 frames.], batch size: 21, lr: 5.80e-04
+2022-05-14 15:09:01,473 INFO [train.py:812] (7/8) Epoch 13, batch 4550, loss[loss=0.1918, simple_loss=0.2734, pruned_loss=0.0551, over 4875.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2648, pruned_loss=0.04608, over 1352018.31 frames.], batch size: 52, lr: 5.80e-04
+2022-05-14 15:10:14,182 INFO [train.py:812] (7/8) Epoch 14, batch 0, loss[loss=0.2186, simple_loss=0.3066, pruned_loss=0.06534, over 7378.00 frames.], tot_loss[loss=0.2186, simple_loss=0.3066, pruned_loss=0.06534, over 7378.00 frames.], batch size: 23, lr: 5.61e-04
+2022-05-14 15:11:14,059 INFO [train.py:812] (7/8) Epoch 14, batch 50, loss[loss=0.1726, simple_loss=0.274, pruned_loss=0.0356, over 7111.00 frames.], tot_loss[loss=0.1709, simple_loss=0.257, pruned_loss=0.04242, over 322084.90 frames.], batch size: 21, lr: 5.61e-04
+2022-05-14 15:12:13,766 INFO [train.py:812] (7/8) Epoch 14, batch 100, loss[loss=0.1905, simple_loss=0.2826, pruned_loss=0.0492, over 7148.00 frames.], tot_loss[loss=0.173, simple_loss=0.2607, pruned_loss=0.04267, over 572264.25 frames.], batch size: 20, lr: 5.61e-04
+2022-05-14 15:13:13,211 INFO [train.py:812] (7/8) Epoch 14, batch 150, loss[loss=0.1438, simple_loss=0.2308, pruned_loss=0.02841, over 7010.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2604, pruned_loss=0.04253, over 763162.37 frames.], batch size: 16, lr: 5.61e-04
+2022-05-14 15:14:11,627 INFO [train.py:812] (7/8) Epoch 14, batch 200, loss[loss=0.1918, simple_loss=0.2762, pruned_loss=0.05364, over 7217.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2602, pruned_loss=0.04221, over 910067.59 frames.], batch size: 22, lr: 5.60e-04
+2022-05-14 15:15:09,305 INFO [train.py:812] (7/8) Epoch 14, batch 250, loss[loss=0.1987, simple_loss=0.2831, pruned_loss=0.05713, over 7208.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2606, pruned_loss=0.04226, over 1026403.15 frames.], batch size: 22, lr: 5.60e-04
+2022-05-14 15:16:07,617 INFO [train.py:812] (7/8) Epoch 14, batch 300, loss[loss=0.1968, simple_loss=0.2869, pruned_loss=0.05336, over 7400.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2616, pruned_loss=0.04209, over 1113120.42 frames.], batch size: 21, lr: 5.60e-04
+2022-05-14 15:17:06,845 INFO [train.py:812] (7/8) Epoch 14, batch 350, loss[loss=0.1944, simple_loss=0.2871, pruned_loss=0.05088, over 7433.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2609, pruned_loss=0.04238, over 1180498.93 frames.], batch size: 20, lr: 5.60e-04
+2022-05-14 15:18:11,737 INFO [train.py:812] (7/8) Epoch 14, batch 400, loss[loss=0.1695, simple_loss=0.2673, pruned_loss=0.03587, over 7050.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2605, pruned_loss=0.04229, over 1230622.30 frames.], batch size: 28, lr: 5.59e-04
+2022-05-14 15:19:10,186 INFO [train.py:812] (7/8) Epoch 14, batch 450, loss[loss=0.1996, simple_loss=0.2886, pruned_loss=0.05531, over 6341.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2612, pruned_loss=0.04286, over 1272956.43 frames.], batch size: 37, lr: 5.59e-04
+2022-05-14 15:20:09,628 INFO [train.py:812] (7/8) Epoch 14, batch 500, loss[loss=0.1984, simple_loss=0.2904, pruned_loss=0.05316, over 7057.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2609, pruned_loss=0.04287, over 1300653.44 frames.], batch size: 28, lr: 5.59e-04
+2022-05-14 15:21:08,798 INFO [train.py:812] (7/8) Epoch 14, batch 550, loss[loss=0.181, simple_loss=0.2745, pruned_loss=0.04377, over 6614.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2616, pruned_loss=0.04303, over 1326745.88 frames.], batch size: 38, lr: 5.59e-04
+2022-05-14 15:22:08,338 INFO [train.py:812] (7/8) Epoch 14, batch 600, loss[loss=0.1844, simple_loss=0.2713, pruned_loss=0.04877, over 7326.00 frames.], tot_loss[loss=0.174, simple_loss=0.2612, pruned_loss=0.04336, over 1349495.45 frames.], batch size: 21, lr: 5.59e-04
+2022-05-14 15:23:07,055 INFO [train.py:812] (7/8) Epoch 14, batch 650, loss[loss=0.1773, simple_loss=0.2564, pruned_loss=0.04914, over 7459.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2617, pruned_loss=0.04354, over 1362224.34 frames.], batch size: 19, lr: 5.58e-04
+2022-05-14 15:24:06,568 INFO [train.py:812] (7/8) Epoch 14, batch 700, loss[loss=0.1658, simple_loss=0.2431, pruned_loss=0.04419, over 7276.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2619, pruned_loss=0.04374, over 1377463.34 frames.], batch size: 18, lr: 5.58e-04
+2022-05-14 15:25:05,465 INFO [train.py:812] (7/8) Epoch 14, batch 750, loss[loss=0.2045, simple_loss=0.2845, pruned_loss=0.0622, over 7212.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2617, pruned_loss=0.04331, over 1383802.39 frames.], batch size: 23, lr: 5.58e-04
+2022-05-14 15:26:04,482 INFO [train.py:812] (7/8) Epoch 14, batch 800, loss[loss=0.1799, simple_loss=0.2727, pruned_loss=0.04358, over 7309.00 frames.], tot_loss[loss=0.174, simple_loss=0.262, pruned_loss=0.04297, over 1393009.68 frames.], batch size: 25, lr: 5.58e-04
+2022-05-14 15:27:03,680 INFO [train.py:812] (7/8) Epoch 14, batch 850, loss[loss=0.156, simple_loss=0.2558, pruned_loss=0.02804, over 7220.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2615, pruned_loss=0.04277, over 1400667.42 frames.], batch size: 21, lr: 5.57e-04
+2022-05-14 15:28:02,947 INFO [train.py:812] (7/8) Epoch 14, batch 900, loss[loss=0.144, simple_loss=0.2361, pruned_loss=0.02593, over 7174.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2612, pruned_loss=0.04265, over 1403288.45 frames.], batch size: 18, lr: 5.57e-04
+2022-05-14 15:29:01,748 INFO [train.py:812] (7/8) Epoch 14, batch 950, loss[loss=0.1695, simple_loss=0.2695, pruned_loss=0.03477, over 7221.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2613, pruned_loss=0.04282, over 1403779.19 frames.], batch size: 21, lr: 5.57e-04
+2022-05-14 15:30:01,422 INFO [train.py:812] (7/8) Epoch 14, batch 1000, loss[loss=0.1899, simple_loss=0.28, pruned_loss=0.04995, over 7201.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2606, pruned_loss=0.0425, over 1411194.74 frames.], batch size: 22, lr: 5.57e-04
+2022-05-14 15:31:00,138 INFO [train.py:812] (7/8) Epoch 14, batch 1050, loss[loss=0.1804, simple_loss=0.2692, pruned_loss=0.04584, over 7413.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2601, pruned_loss=0.0421, over 1412168.26 frames.], batch size: 21, lr: 5.56e-04
+2022-05-14 15:31:57,377 INFO [train.py:812] (7/8) Epoch 14, batch 1100, loss[loss=0.1919, simple_loss=0.2784, pruned_loss=0.05271, over 6803.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2596, pruned_loss=0.04196, over 1411503.18 frames.], batch size: 31, lr: 5.56e-04
+2022-05-14 15:32:55,056 INFO [train.py:812] (7/8) Epoch 14, batch 1150, loss[loss=0.168, simple_loss=0.2553, pruned_loss=0.04036, over 7331.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2609, pruned_loss=0.04181, over 1411332.96 frames.], batch size: 22, lr: 5.56e-04
+2022-05-14 15:33:54,484 INFO [train.py:812] (7/8) Epoch 14, batch 1200, loss[loss=0.1647, simple_loss=0.2503, pruned_loss=0.0396, over 4869.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2605, pruned_loss=0.04162, over 1409890.62 frames.], batch size: 53, lr: 5.56e-04
+2022-05-14 15:34:52,769 INFO [train.py:812] (7/8) Epoch 14, batch 1250, loss[loss=0.1634, simple_loss=0.2532, pruned_loss=0.03676, over 7429.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2614, pruned_loss=0.04213, over 1415207.77 frames.], batch size: 20, lr: 5.56e-04
+2022-05-14 15:35:51,089 INFO [train.py:812] (7/8) Epoch 14, batch 1300, loss[loss=0.1601, simple_loss=0.2425, pruned_loss=0.03879, over 7267.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2618, pruned_loss=0.04187, over 1418531.29 frames.], batch size: 19, lr: 5.55e-04
+2022-05-14 15:36:49,482 INFO [train.py:812] (7/8) Epoch 14, batch 1350, loss[loss=0.1441, simple_loss=0.2345, pruned_loss=0.02687, over 7277.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2612, pruned_loss=0.04194, over 1422124.87 frames.], batch size: 18, lr: 5.55e-04
+2022-05-14 15:37:48,242 INFO [train.py:812] (7/8) Epoch 14, batch 1400, loss[loss=0.1562, simple_loss=0.2352, pruned_loss=0.03862, over 7166.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2618, pruned_loss=0.0423, over 1418509.78 frames.], batch size: 18, lr: 5.55e-04
+2022-05-14 15:38:45,055 INFO [train.py:812] (7/8) Epoch 14, batch 1450, loss[loss=0.1618, simple_loss=0.249, pruned_loss=0.03734, over 7272.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2619, pruned_loss=0.04215, over 1422037.34 frames.], batch size: 17, lr: 5.55e-04
+2022-05-14 15:39:43,883 INFO [train.py:812] (7/8) Epoch 14, batch 1500, loss[loss=0.1642, simple_loss=0.2361, pruned_loss=0.04622, over 7266.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2609, pruned_loss=0.04214, over 1423156.90 frames.], batch size: 17, lr: 5.54e-04
+2022-05-14 15:40:41,999 INFO [train.py:812] (7/8) Epoch 14, batch 1550, loss[loss=0.1823, simple_loss=0.2687, pruned_loss=0.04795, over 6395.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2618, pruned_loss=0.04256, over 1418823.72 frames.], batch size: 37, lr: 5.54e-04
+2022-05-14 15:41:40,147 INFO [train.py:812] (7/8) Epoch 14, batch 1600, loss[loss=0.1665, simple_loss=0.2602, pruned_loss=0.0364, over 7416.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2618, pruned_loss=0.04286, over 1418569.35 frames.], batch size: 21, lr: 5.54e-04
+2022-05-14 15:42:38,944 INFO [train.py:812] (7/8) Epoch 14, batch 1650, loss[loss=0.1979, simple_loss=0.2939, pruned_loss=0.051, over 7230.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2621, pruned_loss=0.04275, over 1420711.04 frames.], batch size: 20, lr: 5.54e-04
+2022-05-14 15:43:38,151 INFO [train.py:812] (7/8) Epoch 14, batch 1700, loss[loss=0.162, simple_loss=0.2537, pruned_loss=0.03518, over 6461.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2619, pruned_loss=0.0424, over 1419579.12 frames.], batch size: 38, lr: 5.54e-04
+2022-05-14 15:44:37,165 INFO [train.py:812] (7/8) Epoch 14, batch 1750, loss[loss=0.1617, simple_loss=0.2451, pruned_loss=0.03916, over 7284.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2613, pruned_loss=0.04203, over 1422143.66 frames.], batch size: 17, lr: 5.53e-04
+2022-05-14 15:45:37,342 INFO [train.py:812] (7/8) Epoch 14, batch 1800, loss[loss=0.188, simple_loss=0.2663, pruned_loss=0.05487, over 7148.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2607, pruned_loss=0.04179, over 1427162.58 frames.], batch size: 20, lr: 5.53e-04
+2022-05-14 15:46:35,107 INFO [train.py:812] (7/8) Epoch 14, batch 1850, loss[loss=0.1853, simple_loss=0.273, pruned_loss=0.04881, over 7287.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2616, pruned_loss=0.04235, over 1426533.73 frames.], batch size: 25, lr: 5.53e-04
+2022-05-14 15:47:33,743 INFO [train.py:812] (7/8) Epoch 14, batch 1900, loss[loss=0.1901, simple_loss=0.2857, pruned_loss=0.04719, over 6412.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2614, pruned_loss=0.04236, over 1421690.67 frames.], batch size: 38, lr: 5.53e-04
+2022-05-14 15:48:32,650 INFO [train.py:812] (7/8) Epoch 14, batch 1950, loss[loss=0.1429, simple_loss=0.229, pruned_loss=0.02843, over 7251.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2626, pruned_loss=0.04259, over 1422883.17 frames.], batch size: 19, lr: 5.52e-04
+2022-05-14 15:49:32,377 INFO [train.py:812] (7/8) Epoch 14, batch 2000, loss[loss=0.1682, simple_loss=0.2669, pruned_loss=0.03476, over 7348.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2619, pruned_loss=0.04219, over 1424758.31 frames.], batch size: 22, lr: 5.52e-04
+2022-05-14 15:50:31,379 INFO [train.py:812] (7/8) Epoch 14, batch 2050, loss[loss=0.1818, simple_loss=0.2777, pruned_loss=0.04292, over 7377.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2618, pruned_loss=0.04251, over 1426186.02 frames.], batch size: 23, lr: 5.52e-04
+2022-05-14 15:51:31,110 INFO [train.py:812] (7/8) Epoch 14, batch 2100, loss[loss=0.1692, simple_loss=0.2665, pruned_loss=0.03598, over 7228.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2631, pruned_loss=0.04288, over 1426261.58 frames.], batch size: 20, lr: 5.52e-04
+2022-05-14 15:52:30,506 INFO [train.py:812] (7/8) Epoch 14, batch 2150, loss[loss=0.1752, simple_loss=0.2635, pruned_loss=0.04341, over 7214.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2627, pruned_loss=0.04279, over 1428964.56 frames.], batch size: 26, lr: 5.52e-04
+2022-05-14 15:53:29,915 INFO [train.py:812] (7/8) Epoch 14, batch 2200, loss[loss=0.1577, simple_loss=0.2487, pruned_loss=0.03335, over 7428.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2621, pruned_loss=0.04253, over 1427718.88 frames.], batch size: 20, lr: 5.51e-04
+2022-05-14 15:54:28,299 INFO [train.py:812] (7/8) Epoch 14, batch 2250, loss[loss=0.1631, simple_loss=0.2541, pruned_loss=0.03602, over 7234.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2612, pruned_loss=0.04233, over 1428130.06 frames.], batch size: 20, lr: 5.51e-04
+2022-05-14 15:55:26,918 INFO [train.py:812] (7/8) Epoch 14, batch 2300, loss[loss=0.1871, simple_loss=0.2795, pruned_loss=0.04739, over 7102.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2594, pruned_loss=0.04148, over 1428624.78 frames.], batch size: 28, lr: 5.51e-04
+2022-05-14 15:56:25,025 INFO [train.py:812] (7/8) Epoch 14, batch 2350, loss[loss=0.206, simple_loss=0.2892, pruned_loss=0.06133, over 5114.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2606, pruned_loss=0.04201, over 1427671.78 frames.], batch size: 52, lr: 5.51e-04
+2022-05-14 15:57:24,268 INFO [train.py:812] (7/8) Epoch 14, batch 2400, loss[loss=0.1593, simple_loss=0.2393, pruned_loss=0.03964, over 7289.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2607, pruned_loss=0.04203, over 1428807.08 frames.], batch size: 17, lr: 5.50e-04
+2022-05-14 15:58:23,299 INFO [train.py:812] (7/8) Epoch 14, batch 2450, loss[loss=0.1634, simple_loss=0.2577, pruned_loss=0.03459, over 6789.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2615, pruned_loss=0.04254, over 1431041.49 frames.], batch size: 31, lr: 5.50e-04
+2022-05-14 15:59:21,615 INFO [train.py:812] (7/8) Epoch 14, batch 2500, loss[loss=0.1566, simple_loss=0.2371, pruned_loss=0.03809, over 7288.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2616, pruned_loss=0.04274, over 1427270.20 frames.], batch size: 17, lr: 5.50e-04
+2022-05-14 16:00:19,979 INFO [train.py:812] (7/8) Epoch 14, batch 2550, loss[loss=0.1654, simple_loss=0.2643, pruned_loss=0.03319, over 7286.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2618, pruned_loss=0.04296, over 1424348.64 frames.], batch size: 25, lr: 5.50e-04
+2022-05-14 16:01:19,248 INFO [train.py:812] (7/8) Epoch 14, batch 2600, loss[loss=0.1906, simple_loss=0.2751, pruned_loss=0.05309, over 7405.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2618, pruned_loss=0.04283, over 1420417.46 frames.], batch size: 21, lr: 5.50e-04
+2022-05-14 16:02:16,365 INFO [train.py:812] (7/8) Epoch 14, batch 2650, loss[loss=0.1588, simple_loss=0.2567, pruned_loss=0.03044, over 7109.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2616, pruned_loss=0.04287, over 1418279.94 frames.], batch size: 21, lr: 5.49e-04
+2022-05-14 16:03:15,388 INFO [train.py:812] (7/8) Epoch 14, batch 2700, loss[loss=0.158, simple_loss=0.2372, pruned_loss=0.0394, over 6998.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2615, pruned_loss=0.04272, over 1422828.95 frames.], batch size: 16, lr: 5.49e-04
+2022-05-14 16:04:13,513 INFO [train.py:812] (7/8) Epoch 14, batch 2750, loss[loss=0.21, simple_loss=0.2893, pruned_loss=0.06537, over 7304.00 frames.], tot_loss[loss=0.1731, simple_loss=0.261, pruned_loss=0.04264, over 1427318.82 frames.], batch size: 24, lr: 5.49e-04
+2022-05-14 16:05:11,606 INFO [train.py:812] (7/8) Epoch 14, batch 2800, loss[loss=0.1381, simple_loss=0.2175, pruned_loss=0.02934, over 7145.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2604, pruned_loss=0.04248, over 1425282.82 frames.], batch size: 17, lr: 5.49e-04
+2022-05-14 16:06:10,672 INFO [train.py:812] (7/8) Epoch 14, batch 2850, loss[loss=0.1888, simple_loss=0.2814, pruned_loss=0.04809, over 7414.00 frames.], tot_loss[loss=0.1722, simple_loss=0.26, pruned_loss=0.04218, over 1426259.74 frames.], batch size: 21, lr: 5.48e-04
+2022-05-14 16:07:10,207 INFO [train.py:812] (7/8) Epoch 14, batch 2900, loss[loss=0.1496, simple_loss=0.2493, pruned_loss=0.02496, over 7110.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2607, pruned_loss=0.04236, over 1427283.10 frames.], batch size: 21, lr: 5.48e-04
+2022-05-14 16:08:08,897 INFO [train.py:812] (7/8) Epoch 14, batch 2950, loss[loss=0.1993, simple_loss=0.2846, pruned_loss=0.05694, over 7206.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2609, pruned_loss=0.0423, over 1428724.28 frames.], batch size: 23, lr: 5.48e-04
+2022-05-14 16:09:07,596 INFO [train.py:812] (7/8) Epoch 14, batch 3000, loss[loss=0.1932, simple_loss=0.285, pruned_loss=0.05069, over 7299.00 frames.], tot_loss[loss=0.1721, simple_loss=0.26, pruned_loss=0.04207, over 1430353.41 frames.], batch size: 24, lr: 5.48e-04
+2022-05-14 16:09:07,598 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 16:09:15,055 INFO [train.py:841] (7/8) Epoch 14, validation: loss=0.1549, simple_loss=0.2556, pruned_loss=0.02713, over 698248.00 frames.
+2022-05-14 16:10:14,227 INFO [train.py:812] (7/8) Epoch 14, batch 3050, loss[loss=0.1484, simple_loss=0.2245, pruned_loss=0.03617, over 7277.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2603, pruned_loss=0.04244, over 1430807.20 frames.], batch size: 17, lr: 5.48e-04
+2022-05-14 16:11:13,782 INFO [train.py:812] (7/8) Epoch 14, batch 3100, loss[loss=0.1824, simple_loss=0.2649, pruned_loss=0.05, over 7203.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2609, pruned_loss=0.04263, over 1431876.21 frames.], batch size: 23, lr: 5.47e-04
+2022-05-14 16:12:13,399 INFO [train.py:812] (7/8) Epoch 14, batch 3150, loss[loss=0.2074, simple_loss=0.2861, pruned_loss=0.06433, over 5083.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2601, pruned_loss=0.04221, over 1430931.76 frames.], batch size: 53, lr: 5.47e-04
+2022-05-14 16:13:13,732 INFO [train.py:812] (7/8) Epoch 14, batch 3200, loss[loss=0.1744, simple_loss=0.2649, pruned_loss=0.04195, over 7332.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2603, pruned_loss=0.04212, over 1430520.30 frames.], batch size: 22, lr: 5.47e-04
+2022-05-14 16:14:11,618 INFO [train.py:812] (7/8) Epoch 14, batch 3250, loss[loss=0.2015, simple_loss=0.2813, pruned_loss=0.06089, over 7181.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2608, pruned_loss=0.04238, over 1427131.04 frames.], batch size: 26, lr: 5.47e-04
+2022-05-14 16:15:10,538 INFO [train.py:812] (7/8) Epoch 14, batch 3300, loss[loss=0.1307, simple_loss=0.2195, pruned_loss=0.02098, over 7173.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2604, pruned_loss=0.04247, over 1424461.27 frames.], batch size: 18, lr: 5.46e-04
+2022-05-14 16:16:09,548 INFO [train.py:812] (7/8) Epoch 14, batch 3350, loss[loss=0.1547, simple_loss=0.241, pruned_loss=0.03422, over 7409.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2601, pruned_loss=0.04211, over 1426056.04 frames.], batch size: 18, lr: 5.46e-04
+2022-05-14 16:17:08,409 INFO [train.py:812] (7/8) Epoch 14, batch 3400, loss[loss=0.1871, simple_loss=0.2748, pruned_loss=0.04975, over 7164.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2599, pruned_loss=0.04179, over 1426862.01 frames.], batch size: 18, lr: 5.46e-04
+2022-05-14 16:18:17,672 INFO [train.py:812] (7/8) Epoch 14, batch 3450, loss[loss=0.1574, simple_loss=0.2501, pruned_loss=0.03232, over 7125.00 frames.], tot_loss[loss=0.1718, simple_loss=0.26, pruned_loss=0.04178, over 1425849.67 frames.], batch size: 21, lr: 5.46e-04
+2022-05-14 16:19:16,740 INFO [train.py:812] (7/8) Epoch 14, batch 3500, loss[loss=0.1782, simple_loss=0.279, pruned_loss=0.03868, over 7333.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2597, pruned_loss=0.04169, over 1427182.79 frames.], batch size: 22, lr: 5.46e-04
+2022-05-14 16:20:15,535 INFO [train.py:812] (7/8) Epoch 14, batch 3550, loss[loss=0.1826, simple_loss=0.2802, pruned_loss=0.04256, over 7312.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2597, pruned_loss=0.04154, over 1427410.42 frames.], batch size: 21, lr: 5.45e-04
+2022-05-14 16:21:14,210 INFO [train.py:812] (7/8) Epoch 14, batch 3600, loss[loss=0.1582, simple_loss=0.2461, pruned_loss=0.03516, over 7364.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2585, pruned_loss=0.04094, over 1431013.53 frames.], batch size: 19, lr: 5.45e-04
+2022-05-14 16:22:13,062 INFO [train.py:812] (7/8) Epoch 14, batch 3650, loss[loss=0.1911, simple_loss=0.2834, pruned_loss=0.04946, over 7235.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2583, pruned_loss=0.04101, over 1430250.11 frames.], batch size: 20, lr: 5.45e-04
+2022-05-14 16:23:12,499 INFO [train.py:812] (7/8) Epoch 14, batch 3700, loss[loss=0.2097, simple_loss=0.297, pruned_loss=0.06121, over 7298.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2605, pruned_loss=0.04253, over 1422741.19 frames.], batch size: 24, lr: 5.45e-04
+2022-05-14 16:24:11,526 INFO [train.py:812] (7/8) Epoch 14, batch 3750, loss[loss=0.1808, simple_loss=0.2553, pruned_loss=0.05312, over 5065.00 frames.], tot_loss[loss=0.1732, simple_loss=0.261, pruned_loss=0.04274, over 1421094.53 frames.], batch size: 52, lr: 5.45e-04
+2022-05-14 16:25:11,078 INFO [train.py:812] (7/8) Epoch 14, batch 3800, loss[loss=0.1529, simple_loss=0.2356, pruned_loss=0.03508, over 7434.00 frames.], tot_loss[loss=0.1732, simple_loss=0.261, pruned_loss=0.04271, over 1420806.60 frames.], batch size: 17, lr: 5.44e-04
+2022-05-14 16:26:09,772 INFO [train.py:812] (7/8) Epoch 14, batch 3850, loss[loss=0.1773, simple_loss=0.2706, pruned_loss=0.04197, over 7198.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2611, pruned_loss=0.04274, over 1420790.97 frames.], batch size: 22, lr: 5.44e-04
+2022-05-14 16:27:08,453 INFO [train.py:812] (7/8) Epoch 14, batch 3900, loss[loss=0.1475, simple_loss=0.2442, pruned_loss=0.02543, over 7309.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2616, pruned_loss=0.04269, over 1421914.84 frames.], batch size: 21, lr: 5.44e-04
+2022-05-14 16:28:07,632 INFO [train.py:812] (7/8) Epoch 14, batch 3950, loss[loss=0.2149, simple_loss=0.2905, pruned_loss=0.06969, over 5183.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2606, pruned_loss=0.04248, over 1420627.36 frames.], batch size: 52, lr: 5.44e-04
+2022-05-14 16:29:06,453 INFO [train.py:812] (7/8) Epoch 14, batch 4000, loss[loss=0.189, simple_loss=0.2863, pruned_loss=0.04578, over 7342.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2614, pruned_loss=0.04265, over 1422548.72 frames.], batch size: 22, lr: 5.43e-04
+2022-05-14 16:30:03,967 INFO [train.py:812] (7/8) Epoch 14, batch 4050, loss[loss=0.1369, simple_loss=0.2168, pruned_loss=0.0285, over 6797.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2607, pruned_loss=0.04253, over 1423484.17 frames.], batch size: 15, lr: 5.43e-04
+2022-05-14 16:31:03,570 INFO [train.py:812] (7/8) Epoch 14, batch 4100, loss[loss=0.1735, simple_loss=0.2593, pruned_loss=0.0439, over 6706.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2606, pruned_loss=0.04289, over 1421717.27 frames.], batch size: 31, lr: 5.43e-04
+2022-05-14 16:32:02,277 INFO [train.py:812] (7/8) Epoch 14, batch 4150, loss[loss=0.1603, simple_loss=0.2621, pruned_loss=0.02922, over 7228.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2603, pruned_loss=0.04256, over 1421093.43 frames.], batch size: 21, lr: 5.43e-04
+2022-05-14 16:33:01,735 INFO [train.py:812] (7/8) Epoch 14, batch 4200, loss[loss=0.1396, simple_loss=0.2237, pruned_loss=0.02774, over 7273.00 frames.], tot_loss[loss=0.1715, simple_loss=0.259, pruned_loss=0.04195, over 1422109.86 frames.], batch size: 17, lr: 5.43e-04
+2022-05-14 16:34:00,303 INFO [train.py:812] (7/8) Epoch 14, batch 4250, loss[loss=0.1891, simple_loss=0.2757, pruned_loss=0.05125, over 6251.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2592, pruned_loss=0.0419, over 1416042.67 frames.], batch size: 37, lr: 5.42e-04
+2022-05-14 16:34:59,105 INFO [train.py:812] (7/8) Epoch 14, batch 4300, loss[loss=0.1901, simple_loss=0.2826, pruned_loss=0.04881, over 7226.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2597, pruned_loss=0.04232, over 1411389.52 frames.], batch size: 21, lr: 5.42e-04
+2022-05-14 16:35:56,859 INFO [train.py:812] (7/8) Epoch 14, batch 4350, loss[loss=0.1561, simple_loss=0.2346, pruned_loss=0.03883, over 6803.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2595, pruned_loss=0.0421, over 1407760.28 frames.], batch size: 15, lr: 5.42e-04
+2022-05-14 16:37:01,608 INFO [train.py:812] (7/8) Epoch 14, batch 4400, loss[loss=0.1532, simple_loss=0.2442, pruned_loss=0.0311, over 7147.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2593, pruned_loss=0.0422, over 1401296.32 frames.], batch size: 20, lr: 5.42e-04
+2022-05-14 16:38:00,497 INFO [train.py:812] (7/8) Epoch 14, batch 4450, loss[loss=0.2105, simple_loss=0.2929, pruned_loss=0.06407, over 5265.00 frames.], tot_loss[loss=0.1716, simple_loss=0.26, pruned_loss=0.04161, over 1393299.78 frames.], batch size: 52, lr: 5.42e-04
+2022-05-14 16:38:59,704 INFO [train.py:812] (7/8) Epoch 14, batch 4500, loss[loss=0.1861, simple_loss=0.2618, pruned_loss=0.05515, over 5033.00 frames.], tot_loss[loss=0.173, simple_loss=0.2607, pruned_loss=0.0427, over 1379366.63 frames.], batch size: 53, lr: 5.41e-04
+2022-05-14 16:40:07,846 INFO [train.py:812] (7/8) Epoch 14, batch 4550, loss[loss=0.1923, simple_loss=0.2787, pruned_loss=0.05297, over 6807.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2608, pruned_loss=0.04297, over 1369367.44 frames.], batch size: 31, lr: 5.41e-04
+2022-05-14 16:41:16,739 INFO [train.py:812] (7/8) Epoch 15, batch 0, loss[loss=0.1718, simple_loss=0.2648, pruned_loss=0.03936, over 7087.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2648, pruned_loss=0.03936, over 7087.00 frames.], batch size: 28, lr: 5.25e-04
+2022-05-14 16:42:15,496 INFO [train.py:812] (7/8) Epoch 15, batch 50, loss[loss=0.1919, simple_loss=0.2725, pruned_loss=0.05558, over 5202.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2604, pruned_loss=0.04219, over 321987.79 frames.], batch size: 52, lr: 5.24e-04
+2022-05-14 16:43:15,434 INFO [train.py:812] (7/8) Epoch 15, batch 100, loss[loss=0.1916, simple_loss=0.2713, pruned_loss=0.05598, over 7172.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2614, pruned_loss=0.04266, over 568306.83 frames.], batch size: 18, lr: 5.24e-04
+2022-05-14 16:44:31,114 INFO [train.py:812] (7/8) Epoch 15, batch 150, loss[loss=0.1642, simple_loss=0.2575, pruned_loss=0.03544, over 7110.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2629, pruned_loss=0.04278, over 758265.12 frames.], batch size: 21, lr: 5.24e-04
+2022-05-14 16:45:30,999 INFO [train.py:812] (7/8) Epoch 15, batch 200, loss[loss=0.1831, simple_loss=0.2626, pruned_loss=0.05177, over 7325.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2642, pruned_loss=0.04372, over 902911.17 frames.], batch size: 20, lr: 5.24e-04
+2022-05-14 16:46:49,174 INFO [train.py:812] (7/8) Epoch 15, batch 250, loss[loss=0.1773, simple_loss=0.2699, pruned_loss=0.04232, over 6396.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2622, pruned_loss=0.04244, over 1020647.93 frames.], batch size: 37, lr: 5.24e-04
+2022-05-14 16:48:07,513 INFO [train.py:812] (7/8) Epoch 15, batch 300, loss[loss=0.1545, simple_loss=0.2314, pruned_loss=0.03883, over 7141.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2606, pruned_loss=0.04159, over 1110630.63 frames.], batch size: 17, lr: 5.23e-04
+2022-05-14 16:49:06,813 INFO [train.py:812] (7/8) Epoch 15, batch 350, loss[loss=0.1714, simple_loss=0.25, pruned_loss=0.04637, over 6857.00 frames.], tot_loss[loss=0.171, simple_loss=0.2595, pruned_loss=0.04127, over 1173365.96 frames.], batch size: 15, lr: 5.23e-04
+2022-05-14 16:50:06,803 INFO [train.py:812] (7/8) Epoch 15, batch 400, loss[loss=0.1716, simple_loss=0.2615, pruned_loss=0.04085, over 7139.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2587, pruned_loss=0.04126, over 1228755.53 frames.], batch size: 20, lr: 5.23e-04
+2022-05-14 16:51:05,903 INFO [train.py:812] (7/8) Epoch 15, batch 450, loss[loss=0.161, simple_loss=0.2352, pruned_loss=0.04345, over 7160.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2584, pruned_loss=0.04111, over 1273168.97 frames.], batch size: 19, lr: 5.23e-04
+2022-05-14 16:52:05,410 INFO [train.py:812] (7/8) Epoch 15, batch 500, loss[loss=0.1477, simple_loss=0.2397, pruned_loss=0.02783, over 7438.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2589, pruned_loss=0.04123, over 1304947.12 frames.], batch size: 20, lr: 5.23e-04
+2022-05-14 16:53:04,898 INFO [train.py:812] (7/8) Epoch 15, batch 550, loss[loss=0.1544, simple_loss=0.2372, pruned_loss=0.03575, over 7276.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2586, pruned_loss=0.04093, over 1332797.71 frames.], batch size: 18, lr: 5.22e-04
+2022-05-14 16:54:04,534 INFO [train.py:812] (7/8) Epoch 15, batch 600, loss[loss=0.1469, simple_loss=0.234, pruned_loss=0.02995, over 7229.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2582, pruned_loss=0.0408, over 1355503.52 frames.], batch size: 20, lr: 5.22e-04
+2022-05-14 16:55:03,742 INFO [train.py:812] (7/8) Epoch 15, batch 650, loss[loss=0.2033, simple_loss=0.2942, pruned_loss=0.05622, over 7319.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2587, pruned_loss=0.04085, over 1369785.63 frames.], batch size: 22, lr: 5.22e-04
+2022-05-14 16:56:03,061 INFO [train.py:812] (7/8) Epoch 15, batch 700, loss[loss=0.1586, simple_loss=0.2464, pruned_loss=0.03538, over 7327.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2589, pruned_loss=0.04088, over 1382453.82 frames.], batch size: 20, lr: 5.22e-04
+2022-05-14 16:57:02,270 INFO [train.py:812] (7/8) Epoch 15, batch 750, loss[loss=0.1709, simple_loss=0.2634, pruned_loss=0.03921, over 7353.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2587, pruned_loss=0.04038, over 1391185.57 frames.], batch size: 22, lr: 5.22e-04
+2022-05-14 16:58:01,684 INFO [train.py:812] (7/8) Epoch 15, batch 800, loss[loss=0.1486, simple_loss=0.2449, pruned_loss=0.02617, over 7337.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2593, pruned_loss=0.04066, over 1398963.46 frames.], batch size: 22, lr: 5.21e-04
+2022-05-14 16:59:01,012 INFO [train.py:812] (7/8) Epoch 15, batch 850, loss[loss=0.153, simple_loss=0.2345, pruned_loss=0.03577, over 7116.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2589, pruned_loss=0.04089, over 1402193.56 frames.], batch size: 17, lr: 5.21e-04
+2022-05-14 17:00:00,552 INFO [train.py:812] (7/8) Epoch 15, batch 900, loss[loss=0.1884, simple_loss=0.2631, pruned_loss=0.05685, over 7266.00 frames.], tot_loss[loss=0.171, simple_loss=0.2593, pruned_loss=0.04129, over 1397672.17 frames.], batch size: 19, lr: 5.21e-04
+2022-05-14 17:00:59,842 INFO [train.py:812] (7/8) Epoch 15, batch 950, loss[loss=0.1608, simple_loss=0.2634, pruned_loss=0.02903, over 7330.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2591, pruned_loss=0.04115, over 1406541.75 frames.], batch size: 22, lr: 5.21e-04
+2022-05-14 17:01:59,724 INFO [train.py:812] (7/8) Epoch 15, batch 1000, loss[loss=0.199, simple_loss=0.2886, pruned_loss=0.05465, over 7029.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2591, pruned_loss=0.04094, over 1407197.72 frames.], batch size: 28, lr: 5.21e-04
+2022-05-14 17:02:57,933 INFO [train.py:812] (7/8) Epoch 15, batch 1050, loss[loss=0.1502, simple_loss=0.2402, pruned_loss=0.03006, over 7288.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2593, pruned_loss=0.04098, over 1413409.53 frames.], batch size: 18, lr: 5.20e-04
+2022-05-14 17:03:56,838 INFO [train.py:812] (7/8) Epoch 15, batch 1100, loss[loss=0.1769, simple_loss=0.2562, pruned_loss=0.04878, over 7286.00 frames.], tot_loss[loss=0.171, simple_loss=0.2595, pruned_loss=0.04127, over 1416916.01 frames.], batch size: 17, lr: 5.20e-04
+2022-05-14 17:04:54,422 INFO [train.py:812] (7/8) Epoch 15, batch 1150, loss[loss=0.1601, simple_loss=0.2587, pruned_loss=0.03072, over 7412.00 frames.], tot_loss[loss=0.1693, simple_loss=0.258, pruned_loss=0.04029, over 1421812.85 frames.], batch size: 21, lr: 5.20e-04
+2022-05-14 17:05:54,095 INFO [train.py:812] (7/8) Epoch 15, batch 1200, loss[loss=0.1541, simple_loss=0.2385, pruned_loss=0.03487, over 7426.00 frames.], tot_loss[loss=0.1697, simple_loss=0.258, pruned_loss=0.04071, over 1423064.62 frames.], batch size: 20, lr: 5.20e-04
+2022-05-14 17:06:52,047 INFO [train.py:812] (7/8) Epoch 15, batch 1250, loss[loss=0.1813, simple_loss=0.2637, pruned_loss=0.04945, over 7359.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2579, pruned_loss=0.04038, over 1425716.78 frames.], batch size: 19, lr: 5.20e-04
+2022-05-14 17:07:51,364 INFO [train.py:812] (7/8) Epoch 15, batch 1300, loss[loss=0.1852, simple_loss=0.273, pruned_loss=0.04867, over 6298.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2588, pruned_loss=0.04102, over 1420374.25 frames.], batch size: 37, lr: 5.19e-04
+2022-05-14 17:08:51,364 INFO [train.py:812] (7/8) Epoch 15, batch 1350, loss[loss=0.1412, simple_loss=0.2238, pruned_loss=0.02927, over 7005.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2592, pruned_loss=0.04099, over 1421687.57 frames.], batch size: 16, lr: 5.19e-04
+2022-05-14 17:09:50,472 INFO [train.py:812] (7/8) Epoch 15, batch 1400, loss[loss=0.1866, simple_loss=0.2821, pruned_loss=0.04562, over 7267.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2584, pruned_loss=0.04091, over 1420734.34 frames.], batch size: 24, lr: 5.19e-04
+2022-05-14 17:10:49,148 INFO [train.py:812] (7/8) Epoch 15, batch 1450, loss[loss=0.1719, simple_loss=0.2596, pruned_loss=0.04214, over 7394.00 frames.], tot_loss[loss=0.1704, simple_loss=0.259, pruned_loss=0.04091, over 1417297.55 frames.], batch size: 23, lr: 5.19e-04
+2022-05-14 17:11:46,410 INFO [train.py:812] (7/8) Epoch 15, batch 1500, loss[loss=0.1717, simple_loss=0.257, pruned_loss=0.0432, over 7150.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2604, pruned_loss=0.04186, over 1411957.25 frames.], batch size: 20, lr: 5.19e-04
+2022-05-14 17:12:45,425 INFO [train.py:812] (7/8) Epoch 15, batch 1550, loss[loss=0.1636, simple_loss=0.2582, pruned_loss=0.03454, over 7126.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2591, pruned_loss=0.04154, over 1416556.35 frames.], batch size: 21, lr: 5.18e-04
+2022-05-14 17:13:44,524 INFO [train.py:812] (7/8) Epoch 15, batch 1600, loss[loss=0.1614, simple_loss=0.2505, pruned_loss=0.03617, over 7419.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2587, pruned_loss=0.0413, over 1418985.55 frames.], batch size: 21, lr: 5.18e-04
+2022-05-14 17:14:43,379 INFO [train.py:812] (7/8) Epoch 15, batch 1650, loss[loss=0.194, simple_loss=0.2863, pruned_loss=0.0508, over 7198.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2585, pruned_loss=0.0409, over 1424342.67 frames.], batch size: 23, lr: 5.18e-04
+2022-05-14 17:15:42,335 INFO [train.py:812] (7/8) Epoch 15, batch 1700, loss[loss=0.1985, simple_loss=0.2869, pruned_loss=0.05508, over 7298.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2581, pruned_loss=0.04069, over 1428216.85 frames.], batch size: 25, lr: 5.18e-04
+2022-05-14 17:16:41,875 INFO [train.py:812] (7/8) Epoch 15, batch 1750, loss[loss=0.2045, simple_loss=0.2937, pruned_loss=0.0577, over 7137.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2582, pruned_loss=0.04041, over 1431440.85 frames.], batch size: 28, lr: 5.18e-04
+2022-05-14 17:17:41,433 INFO [train.py:812] (7/8) Epoch 15, batch 1800, loss[loss=0.1406, simple_loss=0.2175, pruned_loss=0.0319, over 7275.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2576, pruned_loss=0.04043, over 1428298.79 frames.], batch size: 17, lr: 5.17e-04
+2022-05-14 17:18:41,044 INFO [train.py:812] (7/8) Epoch 15, batch 1850, loss[loss=0.1758, simple_loss=0.2606, pruned_loss=0.04557, over 7168.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2576, pruned_loss=0.04035, over 1432590.79 frames.], batch size: 18, lr: 5.17e-04
+2022-05-14 17:19:41,002 INFO [train.py:812] (7/8) Epoch 15, batch 1900, loss[loss=0.1817, simple_loss=0.2659, pruned_loss=0.04872, over 7123.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2571, pruned_loss=0.04058, over 1431393.29 frames.], batch size: 21, lr: 5.17e-04
+2022-05-14 17:20:40,346 INFO [train.py:812] (7/8) Epoch 15, batch 1950, loss[loss=0.1803, simple_loss=0.2781, pruned_loss=0.04128, over 7292.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2567, pruned_loss=0.04046, over 1431956.41 frames.], batch size: 18, lr: 5.17e-04
+2022-05-14 17:21:39,089 INFO [train.py:812] (7/8) Epoch 15, batch 2000, loss[loss=0.1789, simple_loss=0.2647, pruned_loss=0.0466, over 6494.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2571, pruned_loss=0.0408, over 1428252.27 frames.], batch size: 38, lr: 5.17e-04
+2022-05-14 17:22:38,306 INFO [train.py:812] (7/8) Epoch 15, batch 2050, loss[loss=0.2111, simple_loss=0.2949, pruned_loss=0.06368, over 7313.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2578, pruned_loss=0.04069, over 1429491.64 frames.], batch size: 25, lr: 5.16e-04
+2022-05-14 17:23:37,413 INFO [train.py:812] (7/8) Epoch 15, batch 2100, loss[loss=0.1473, simple_loss=0.2332, pruned_loss=0.03071, over 7395.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2577, pruned_loss=0.04107, over 1422665.23 frames.], batch size: 18, lr: 5.16e-04
+2022-05-14 17:24:36,122 INFO [train.py:812] (7/8) Epoch 15, batch 2150, loss[loss=0.191, simple_loss=0.2733, pruned_loss=0.0543, over 7204.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2566, pruned_loss=0.04018, over 1420195.25 frames.], batch size: 22, lr: 5.16e-04
+2022-05-14 17:25:35,481 INFO [train.py:812] (7/8) Epoch 15, batch 2200, loss[loss=0.1805, simple_loss=0.2657, pruned_loss=0.04768, over 7431.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2576, pruned_loss=0.04036, over 1420401.27 frames.], batch size: 20, lr: 5.16e-04
+2022-05-14 17:26:33,961 INFO [train.py:812] (7/8) Epoch 15, batch 2250, loss[loss=0.1812, simple_loss=0.2754, pruned_loss=0.04348, over 7080.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2572, pruned_loss=0.03996, over 1421455.24 frames.], batch size: 28, lr: 5.16e-04
+2022-05-14 17:27:32,334 INFO [train.py:812] (7/8) Epoch 15, batch 2300, loss[loss=0.1251, simple_loss=0.2074, pruned_loss=0.02141, over 6791.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2577, pruned_loss=0.04066, over 1420852.38 frames.], batch size: 15, lr: 5.15e-04
+2022-05-14 17:28:30,802 INFO [train.py:812] (7/8) Epoch 15, batch 2350, loss[loss=0.1661, simple_loss=0.2442, pruned_loss=0.04398, over 7403.00 frames.], tot_loss[loss=0.169, simple_loss=0.2576, pruned_loss=0.04025, over 1423800.92 frames.], batch size: 18, lr: 5.15e-04
+2022-05-14 17:29:30,898 INFO [train.py:812] (7/8) Epoch 15, batch 2400, loss[loss=0.1552, simple_loss=0.2423, pruned_loss=0.0341, over 7413.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2593, pruned_loss=0.04083, over 1422227.86 frames.], batch size: 18, lr: 5.15e-04
+2022-05-14 17:30:30,123 INFO [train.py:812] (7/8) Epoch 15, batch 2450, loss[loss=0.1779, simple_loss=0.2698, pruned_loss=0.04294, over 7410.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2604, pruned_loss=0.04155, over 1423772.66 frames.], batch size: 21, lr: 5.15e-04
+2022-05-14 17:31:29,574 INFO [train.py:812] (7/8) Epoch 15, batch 2500, loss[loss=0.1701, simple_loss=0.2613, pruned_loss=0.03945, over 7327.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2607, pruned_loss=0.04151, over 1425696.97 frames.], batch size: 21, lr: 5.15e-04
+2022-05-14 17:32:27,902 INFO [train.py:812] (7/8) Epoch 15, batch 2550, loss[loss=0.1925, simple_loss=0.2791, pruned_loss=0.053, over 7171.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2601, pruned_loss=0.04112, over 1428073.60 frames.], batch size: 18, lr: 5.14e-04
+2022-05-14 17:33:27,570 INFO [train.py:812] (7/8) Epoch 15, batch 2600, loss[loss=0.1553, simple_loss=0.2449, pruned_loss=0.03289, over 7201.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2609, pruned_loss=0.04194, over 1422349.53 frames.], batch size: 23, lr: 5.14e-04
+2022-05-14 17:34:25,791 INFO [train.py:812] (7/8) Epoch 15, batch 2650, loss[loss=0.1779, simple_loss=0.2807, pruned_loss=0.03756, over 7252.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2597, pruned_loss=0.04125, over 1421980.76 frames.], batch size: 25, lr: 5.14e-04
+2022-05-14 17:35:25,143 INFO [train.py:812] (7/8) Epoch 15, batch 2700, loss[loss=0.1669, simple_loss=0.2563, pruned_loss=0.03874, over 7320.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2602, pruned_loss=0.04121, over 1424658.02 frames.], batch size: 21, lr: 5.14e-04
+2022-05-14 17:36:24,217 INFO [train.py:812] (7/8) Epoch 15, batch 2750, loss[loss=0.1831, simple_loss=0.2798, pruned_loss=0.04326, over 7282.00 frames.], tot_loss[loss=0.1711, simple_loss=0.26, pruned_loss=0.04111, over 1424686.45 frames.], batch size: 24, lr: 5.14e-04
+2022-05-14 17:37:23,486 INFO [train.py:812] (7/8) Epoch 15, batch 2800, loss[loss=0.1512, simple_loss=0.2351, pruned_loss=0.03361, over 7145.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2598, pruned_loss=0.0408, over 1427226.62 frames.], batch size: 20, lr: 5.14e-04
+2022-05-14 17:38:20,873 INFO [train.py:812] (7/8) Epoch 15, batch 2850, loss[loss=0.1859, simple_loss=0.2669, pruned_loss=0.05249, over 6809.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2606, pruned_loss=0.0415, over 1427051.09 frames.], batch size: 15, lr: 5.13e-04
+2022-05-14 17:39:21,027 INFO [train.py:812] (7/8) Epoch 15, batch 2900, loss[loss=0.1801, simple_loss=0.2609, pruned_loss=0.04959, over 7365.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2612, pruned_loss=0.04202, over 1423307.86 frames.], batch size: 23, lr: 5.13e-04
+2022-05-14 17:40:20,010 INFO [train.py:812] (7/8) Epoch 15, batch 2950, loss[loss=0.176, simple_loss=0.2527, pruned_loss=0.04965, over 7443.00 frames.], tot_loss[loss=0.1716, simple_loss=0.26, pruned_loss=0.04161, over 1424690.51 frames.], batch size: 20, lr: 5.13e-04
+2022-05-14 17:41:19,173 INFO [train.py:812] (7/8) Epoch 15, batch 3000, loss[loss=0.1478, simple_loss=0.2439, pruned_loss=0.02582, over 7163.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2598, pruned_loss=0.04135, over 1422456.77 frames.], batch size: 19, lr: 5.13e-04
+2022-05-14 17:41:19,174 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 17:41:26,768 INFO [train.py:841] (7/8) Epoch 15, validation: loss=0.1543, simple_loss=0.2544, pruned_loss=0.02713, over 698248.00 frames.
+2022-05-14 17:42:25,637 INFO [train.py:812] (7/8) Epoch 15, batch 3050, loss[loss=0.1886, simple_loss=0.2606, pruned_loss=0.05836, over 6741.00 frames.], tot_loss[loss=0.171, simple_loss=0.2597, pruned_loss=0.04111, over 1425411.85 frames.], batch size: 15, lr: 5.13e-04
+2022-05-14 17:43:23,129 INFO [train.py:812] (7/8) Epoch 15, batch 3100, loss[loss=0.1739, simple_loss=0.2624, pruned_loss=0.04273, over 7323.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2605, pruned_loss=0.04122, over 1421803.83 frames.], batch size: 20, lr: 5.12e-04
+2022-05-14 17:44:21,963 INFO [train.py:812] (7/8) Epoch 15, batch 3150, loss[loss=0.1281, simple_loss=0.2073, pruned_loss=0.02446, over 7279.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2594, pruned_loss=0.0411, over 1426347.47 frames.], batch size: 17, lr: 5.12e-04
+2022-05-14 17:45:20,647 INFO [train.py:812] (7/8) Epoch 15, batch 3200, loss[loss=0.1725, simple_loss=0.2709, pruned_loss=0.03705, over 7036.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2587, pruned_loss=0.04094, over 1427494.57 frames.], batch size: 28, lr: 5.12e-04
+2022-05-14 17:46:20,219 INFO [train.py:812] (7/8) Epoch 15, batch 3250, loss[loss=0.1662, simple_loss=0.2591, pruned_loss=0.03668, over 7452.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2582, pruned_loss=0.04068, over 1427792.63 frames.], batch size: 19, lr: 5.12e-04
+2022-05-14 17:47:18,767 INFO [train.py:812] (7/8) Epoch 15, batch 3300, loss[loss=0.1417, simple_loss=0.2254, pruned_loss=0.02899, over 7274.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2573, pruned_loss=0.04047, over 1426305.18 frames.], batch size: 17, lr: 5.12e-04
+2022-05-14 17:48:17,439 INFO [train.py:812] (7/8) Epoch 15, batch 3350, loss[loss=0.1699, simple_loss=0.2607, pruned_loss=0.03958, over 7213.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2581, pruned_loss=0.04061, over 1426743.53 frames.], batch size: 23, lr: 5.11e-04
+2022-05-14 17:49:14,715 INFO [train.py:812] (7/8) Epoch 15, batch 3400, loss[loss=0.1827, simple_loss=0.2699, pruned_loss=0.04776, over 7223.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2584, pruned_loss=0.04065, over 1423575.47 frames.], batch size: 21, lr: 5.11e-04
+2022-05-14 17:50:13,379 INFO [train.py:812] (7/8) Epoch 15, batch 3450, loss[loss=0.1739, simple_loss=0.2717, pruned_loss=0.03804, over 7058.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2602, pruned_loss=0.04178, over 1420992.16 frames.], batch size: 28, lr: 5.11e-04
+2022-05-14 17:51:13,204 INFO [train.py:812] (7/8) Epoch 15, batch 3500, loss[loss=0.197, simple_loss=0.2831, pruned_loss=0.05542, over 7162.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2589, pruned_loss=0.04109, over 1425842.44 frames.], batch size: 26, lr: 5.11e-04
+2022-05-14 17:52:12,843 INFO [train.py:812] (7/8) Epoch 15, batch 3550, loss[loss=0.1941, simple_loss=0.2872, pruned_loss=0.05053, over 7229.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2592, pruned_loss=0.04104, over 1427797.13 frames.], batch size: 20, lr: 5.11e-04
+2022-05-14 17:53:11,391 INFO [train.py:812] (7/8) Epoch 15, batch 3600, loss[loss=0.1612, simple_loss=0.2505, pruned_loss=0.03591, over 7317.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2592, pruned_loss=0.04115, over 1423704.71 frames.], batch size: 21, lr: 5.11e-04
+2022-05-14 17:54:10,565 INFO [train.py:812] (7/8) Epoch 15, batch 3650, loss[loss=0.1826, simple_loss=0.2757, pruned_loss=0.04474, over 7264.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2587, pruned_loss=0.04087, over 1424826.98 frames.], batch size: 19, lr: 5.10e-04
+2022-05-14 17:55:10,214 INFO [train.py:812] (7/8) Epoch 15, batch 3700, loss[loss=0.1464, simple_loss=0.2342, pruned_loss=0.02929, over 7424.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2598, pruned_loss=0.04142, over 1422266.73 frames.], batch size: 20, lr: 5.10e-04
+2022-05-14 17:56:09,487 INFO [train.py:812] (7/8) Epoch 15, batch 3750, loss[loss=0.2229, simple_loss=0.3012, pruned_loss=0.0723, over 5199.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2596, pruned_loss=0.04137, over 1424092.46 frames.], batch size: 52, lr: 5.10e-04
+2022-05-14 17:57:14,327 INFO [train.py:812] (7/8) Epoch 15, batch 3800, loss[loss=0.1444, simple_loss=0.2363, pruned_loss=0.02626, over 7447.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2593, pruned_loss=0.04098, over 1426307.73 frames.], batch size: 19, lr: 5.10e-04
+2022-05-14 17:58:12,060 INFO [train.py:812] (7/8) Epoch 15, batch 3850, loss[loss=0.1751, simple_loss=0.2723, pruned_loss=0.03892, over 7239.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2589, pruned_loss=0.04048, over 1428958.98 frames.], batch size: 20, lr: 5.10e-04
+2022-05-14 17:59:11,808 INFO [train.py:812] (7/8) Epoch 15, batch 3900, loss[loss=0.1716, simple_loss=0.2637, pruned_loss=0.03972, over 7256.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2583, pruned_loss=0.04038, over 1426551.53 frames.], batch size: 19, lr: 5.09e-04
+2022-05-14 18:00:10,996 INFO [train.py:812] (7/8) Epoch 15, batch 3950, loss[loss=0.1742, simple_loss=0.2648, pruned_loss=0.0418, over 7355.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2575, pruned_loss=0.03998, over 1423428.62 frames.], batch size: 19, lr: 5.09e-04
+2022-05-14 18:01:10,536 INFO [train.py:812] (7/8) Epoch 15, batch 4000, loss[loss=0.1816, simple_loss=0.2752, pruned_loss=0.04403, over 7218.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2579, pruned_loss=0.04017, over 1423478.86 frames.], batch size: 21, lr: 5.09e-04
+2022-05-14 18:02:09,536 INFO [train.py:812] (7/8) Epoch 15, batch 4050, loss[loss=0.2183, simple_loss=0.3044, pruned_loss=0.06612, over 7208.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2587, pruned_loss=0.04001, over 1427245.46 frames.], batch size: 21, lr: 5.09e-04
+2022-05-14 18:03:08,737 INFO [train.py:812] (7/8) Epoch 15, batch 4100, loss[loss=0.193, simple_loss=0.2786, pruned_loss=0.05365, over 7200.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2591, pruned_loss=0.04097, over 1419052.94 frames.], batch size: 23, lr: 5.09e-04
+2022-05-14 18:04:07,555 INFO [train.py:812] (7/8) Epoch 15, batch 4150, loss[loss=0.1888, simple_loss=0.2644, pruned_loss=0.05662, over 5249.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2593, pruned_loss=0.04138, over 1413678.41 frames.], batch size: 52, lr: 5.08e-04
+2022-05-14 18:05:07,030 INFO [train.py:812] (7/8) Epoch 15, batch 4200, loss[loss=0.1904, simple_loss=0.2736, pruned_loss=0.05359, over 7234.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2585, pruned_loss=0.04138, over 1412479.55 frames.], batch size: 20, lr: 5.08e-04
+2022-05-14 18:06:05,975 INFO [train.py:812] (7/8) Epoch 15, batch 4250, loss[loss=0.1474, simple_loss=0.2357, pruned_loss=0.02957, over 7069.00 frames.], tot_loss[loss=0.17, simple_loss=0.2579, pruned_loss=0.04105, over 1410009.15 frames.], batch size: 18, lr: 5.08e-04
+2022-05-14 18:07:05,158 INFO [train.py:812] (7/8) Epoch 15, batch 4300, loss[loss=0.1268, simple_loss=0.2037, pruned_loss=0.02497, over 7269.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2583, pruned_loss=0.04096, over 1405705.40 frames.], batch size: 16, lr: 5.08e-04
+2022-05-14 18:08:04,088 INFO [train.py:812] (7/8) Epoch 15, batch 4350, loss[loss=0.1659, simple_loss=0.2573, pruned_loss=0.03724, over 7311.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2585, pruned_loss=0.04067, over 1409133.00 frames.], batch size: 21, lr: 5.08e-04
+2022-05-14 18:09:03,521 INFO [train.py:812] (7/8) Epoch 15, batch 4400, loss[loss=0.1499, simple_loss=0.2473, pruned_loss=0.02624, over 7146.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2571, pruned_loss=0.03972, over 1411597.41 frames.], batch size: 19, lr: 5.08e-04
+2022-05-14 18:10:02,448 INFO [train.py:812] (7/8) Epoch 15, batch 4450, loss[loss=0.1671, simple_loss=0.2561, pruned_loss=0.03902, over 7158.00 frames.], tot_loss[loss=0.1666, simple_loss=0.255, pruned_loss=0.03908, over 1403796.19 frames.], batch size: 18, lr: 5.07e-04
+2022-05-14 18:11:01,298 INFO [train.py:812] (7/8) Epoch 15, batch 4500, loss[loss=0.1376, simple_loss=0.2261, pruned_loss=0.02455, over 7071.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2551, pruned_loss=0.03916, over 1395128.57 frames.], batch size: 18, lr: 5.07e-04
+2022-05-14 18:11:59,599 INFO [train.py:812] (7/8) Epoch 15, batch 4550, loss[loss=0.2263, simple_loss=0.3178, pruned_loss=0.06739, over 4762.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2571, pruned_loss=0.04065, over 1367538.48 frames.], batch size: 52, lr: 5.07e-04
+2022-05-14 18:13:08,756 INFO [train.py:812] (7/8) Epoch 16, batch 0, loss[loss=0.1866, simple_loss=0.2713, pruned_loss=0.05098, over 7302.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2713, pruned_loss=0.05098, over 7302.00 frames.], batch size: 24, lr: 4.92e-04
+2022-05-14 18:14:08,004 INFO [train.py:812] (7/8) Epoch 16, batch 50, loss[loss=0.1534, simple_loss=0.2407, pruned_loss=0.0331, over 7425.00 frames.], tot_loss[loss=0.17, simple_loss=0.2586, pruned_loss=0.04066, over 321200.36 frames.], batch size: 18, lr: 4.92e-04
+2022-05-14 18:15:07,136 INFO [train.py:812] (7/8) Epoch 16, batch 100, loss[loss=0.1967, simple_loss=0.2688, pruned_loss=0.06229, over 7324.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2573, pruned_loss=0.04025, over 563777.89 frames.], batch size: 20, lr: 4.92e-04
+2022-05-14 18:16:06,292 INFO [train.py:812] (7/8) Epoch 16, batch 150, loss[loss=0.1649, simple_loss=0.2616, pruned_loss=0.0341, over 7146.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2571, pruned_loss=0.0402, over 753422.84 frames.], batch size: 20, lr: 4.92e-04
+2022-05-14 18:17:15,060 INFO [train.py:812] (7/8) Epoch 16, batch 200, loss[loss=0.1804, simple_loss=0.2791, pruned_loss=0.04089, over 7130.00 frames.], tot_loss[loss=0.167, simple_loss=0.2556, pruned_loss=0.03917, over 897300.78 frames.], batch size: 21, lr: 4.91e-04
+2022-05-14 18:18:13,091 INFO [train.py:812] (7/8) Epoch 16, batch 250, loss[loss=0.1457, simple_loss=0.2341, pruned_loss=0.02862, over 7162.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2563, pruned_loss=0.03921, over 1014632.29 frames.], batch size: 19, lr: 4.91e-04
+2022-05-14 18:19:12,344 INFO [train.py:812] (7/8) Epoch 16, batch 300, loss[loss=0.15, simple_loss=0.2465, pruned_loss=0.02672, over 7159.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2556, pruned_loss=0.03891, over 1108651.07 frames.], batch size: 19, lr: 4.91e-04
+2022-05-14 18:20:11,403 INFO [train.py:812] (7/8) Epoch 16, batch 350, loss[loss=0.1396, simple_loss=0.2191, pruned_loss=0.03005, over 7293.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2561, pruned_loss=0.03962, over 1180615.60 frames.], batch size: 18, lr: 4.91e-04
+2022-05-14 18:21:11,314 INFO [train.py:812] (7/8) Epoch 16, batch 400, loss[loss=0.17, simple_loss=0.2574, pruned_loss=0.04133, over 7264.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2569, pruned_loss=0.0397, over 1234462.56 frames.], batch size: 19, lr: 4.91e-04
+2022-05-14 18:22:10,153 INFO [train.py:812] (7/8) Epoch 16, batch 450, loss[loss=0.1609, simple_loss=0.2564, pruned_loss=0.0327, over 7418.00 frames.], tot_loss[loss=0.169, simple_loss=0.2577, pruned_loss=0.04014, over 1281681.00 frames.], batch size: 20, lr: 4.91e-04
+2022-05-14 18:23:09,275 INFO [train.py:812] (7/8) Epoch 16, batch 500, loss[loss=0.1792, simple_loss=0.2714, pruned_loss=0.04352, over 7198.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2587, pruned_loss=0.04002, over 1319015.90 frames.], batch size: 23, lr: 4.90e-04
+2022-05-14 18:24:07,799 INFO [train.py:812] (7/8) Epoch 16, batch 550, loss[loss=0.1591, simple_loss=0.2431, pruned_loss=0.03758, over 7269.00 frames.], tot_loss[loss=0.1688, simple_loss=0.258, pruned_loss=0.03977, over 1346285.61 frames.], batch size: 18, lr: 4.90e-04
+2022-05-14 18:25:07,666 INFO [train.py:812] (7/8) Epoch 16, batch 600, loss[loss=0.1649, simple_loss=0.2521, pruned_loss=0.03882, over 7159.00 frames.], tot_loss[loss=0.1675, simple_loss=0.257, pruned_loss=0.039, over 1361333.71 frames.], batch size: 19, lr: 4.90e-04
+2022-05-14 18:26:06,760 INFO [train.py:812] (7/8) Epoch 16, batch 650, loss[loss=0.1599, simple_loss=0.2517, pruned_loss=0.03404, over 6541.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2572, pruned_loss=0.03915, over 1374255.35 frames.], batch size: 38, lr: 4.90e-04
+2022-05-14 18:27:05,490 INFO [train.py:812] (7/8) Epoch 16, batch 700, loss[loss=0.1577, simple_loss=0.253, pruned_loss=0.03123, over 7051.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2578, pruned_loss=0.03933, over 1385901.12 frames.], batch size: 28, lr: 4.90e-04
+2022-05-14 18:28:04,374 INFO [train.py:812] (7/8) Epoch 16, batch 750, loss[loss=0.1763, simple_loss=0.2539, pruned_loss=0.04939, over 7142.00 frames.], tot_loss[loss=0.168, simple_loss=0.2573, pruned_loss=0.0394, over 1395216.56 frames.], batch size: 19, lr: 4.89e-04
+2022-05-14 18:29:03,826 INFO [train.py:812] (7/8) Epoch 16, batch 800, loss[loss=0.1586, simple_loss=0.2498, pruned_loss=0.03371, over 7266.00 frames.], tot_loss[loss=0.168, simple_loss=0.2571, pruned_loss=0.03949, over 1402555.69 frames.], batch size: 19, lr: 4.89e-04
+2022-05-14 18:30:02,526 INFO [train.py:812] (7/8) Epoch 16, batch 850, loss[loss=0.2085, simple_loss=0.2985, pruned_loss=0.05925, over 7157.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2578, pruned_loss=0.03986, over 1405168.31 frames.], batch size: 20, lr: 4.89e-04
+2022-05-14 18:31:02,388 INFO [train.py:812] (7/8) Epoch 16, batch 900, loss[loss=0.1449, simple_loss=0.2346, pruned_loss=0.0276, over 7356.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2575, pruned_loss=0.03972, over 1404054.99 frames.], batch size: 19, lr: 4.89e-04
+2022-05-14 18:32:01,925 INFO [train.py:812] (7/8) Epoch 16, batch 950, loss[loss=0.1603, simple_loss=0.2453, pruned_loss=0.03764, over 7436.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2566, pruned_loss=0.03952, over 1407582.71 frames.], batch size: 20, lr: 4.89e-04
+2022-05-14 18:33:00,805 INFO [train.py:812] (7/8) Epoch 16, batch 1000, loss[loss=0.1501, simple_loss=0.252, pruned_loss=0.02414, over 7301.00 frames.], tot_loss[loss=0.167, simple_loss=0.256, pruned_loss=0.03904, over 1412064.85 frames.], batch size: 25, lr: 4.89e-04
+2022-05-14 18:33:59,625 INFO [train.py:812] (7/8) Epoch 16, batch 1050, loss[loss=0.141, simple_loss=0.2271, pruned_loss=0.02746, over 7330.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2569, pruned_loss=0.0394, over 1417625.42 frames.], batch size: 20, lr: 4.88e-04
+2022-05-14 18:34:59,580 INFO [train.py:812] (7/8) Epoch 16, batch 1100, loss[loss=0.1713, simple_loss=0.2556, pruned_loss=0.04356, over 7345.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2564, pruned_loss=0.03932, over 1420476.90 frames.], batch size: 19, lr: 4.88e-04
+2022-05-14 18:35:59,322 INFO [train.py:812] (7/8) Epoch 16, batch 1150, loss[loss=0.2007, simple_loss=0.2794, pruned_loss=0.06097, over 4867.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2556, pruned_loss=0.03887, over 1421503.71 frames.], batch size: 53, lr: 4.88e-04
+2022-05-14 18:36:59,246 INFO [train.py:812] (7/8) Epoch 16, batch 1200, loss[loss=0.1628, simple_loss=0.2548, pruned_loss=0.03542, over 7117.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2561, pruned_loss=0.03913, over 1419242.83 frames.], batch size: 21, lr: 4.88e-04
+2022-05-14 18:37:58,869 INFO [train.py:812] (7/8) Epoch 16, batch 1250, loss[loss=0.1734, simple_loss=0.2515, pruned_loss=0.04769, over 6805.00 frames.], tot_loss[loss=0.167, simple_loss=0.2555, pruned_loss=0.03927, over 1420853.65 frames.], batch size: 15, lr: 4.88e-04
+2022-05-14 18:38:58,802 INFO [train.py:812] (7/8) Epoch 16, batch 1300, loss[loss=0.1735, simple_loss=0.2657, pruned_loss=0.04065, over 7201.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2564, pruned_loss=0.03953, over 1426544.99 frames.], batch size: 22, lr: 4.88e-04
+2022-05-14 18:39:58,326 INFO [train.py:812] (7/8) Epoch 16, batch 1350, loss[loss=0.1506, simple_loss=0.2377, pruned_loss=0.03178, over 7163.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2568, pruned_loss=0.04009, over 1419366.21 frames.], batch size: 19, lr: 4.87e-04
+2022-05-14 18:40:58,022 INFO [train.py:812] (7/8) Epoch 16, batch 1400, loss[loss=0.1537, simple_loss=0.253, pruned_loss=0.02718, over 7349.00 frames.], tot_loss[loss=0.169, simple_loss=0.2577, pruned_loss=0.0402, over 1417011.99 frames.], batch size: 22, lr: 4.87e-04
+2022-05-14 18:41:57,531 INFO [train.py:812] (7/8) Epoch 16, batch 1450, loss[loss=0.2005, simple_loss=0.288, pruned_loss=0.05649, over 7419.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2579, pruned_loss=0.04002, over 1422818.60 frames.], batch size: 21, lr: 4.87e-04
+2022-05-14 18:43:06,595 INFO [train.py:812] (7/8) Epoch 16, batch 1500, loss[loss=0.1719, simple_loss=0.2592, pruned_loss=0.04231, over 7199.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2579, pruned_loss=0.03975, over 1422410.39 frames.], batch size: 23, lr: 4.87e-04
+2022-05-14 18:44:06,057 INFO [train.py:812] (7/8) Epoch 16, batch 1550, loss[loss=0.1423, simple_loss=0.2319, pruned_loss=0.02637, over 6824.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2568, pruned_loss=0.03952, over 1420421.40 frames.], batch size: 15, lr: 4.87e-04
+2022-05-14 18:45:05,985 INFO [train.py:812] (7/8) Epoch 16, batch 1600, loss[loss=0.144, simple_loss=0.2238, pruned_loss=0.03206, over 7241.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2576, pruned_loss=0.0401, over 1423180.81 frames.], batch size: 16, lr: 4.87e-04
+2022-05-14 18:46:05,475 INFO [train.py:812] (7/8) Epoch 16, batch 1650, loss[loss=0.1614, simple_loss=0.2549, pruned_loss=0.03397, over 7150.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2575, pruned_loss=0.04015, over 1424428.73 frames.], batch size: 20, lr: 4.86e-04
+2022-05-14 18:47:14,912 INFO [train.py:812] (7/8) Epoch 16, batch 1700, loss[loss=0.1772, simple_loss=0.2621, pruned_loss=0.04613, over 7414.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2564, pruned_loss=0.03953, over 1423968.70 frames.], batch size: 18, lr: 4.86e-04
+2022-05-14 18:48:31,565 INFO [train.py:812] (7/8) Epoch 16, batch 1750, loss[loss=0.1588, simple_loss=0.2629, pruned_loss=0.02735, over 7373.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2572, pruned_loss=0.04018, over 1423759.42 frames.], batch size: 23, lr: 4.86e-04
+2022-05-14 18:49:49,366 INFO [train.py:812] (7/8) Epoch 16, batch 1800, loss[loss=0.1533, simple_loss=0.2457, pruned_loss=0.03043, over 7360.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2574, pruned_loss=0.04002, over 1422008.75 frames.], batch size: 19, lr: 4.86e-04
+2022-05-14 18:50:57,680 INFO [train.py:812] (7/8) Epoch 16, batch 1850, loss[loss=0.1966, simple_loss=0.2895, pruned_loss=0.05189, over 7139.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2567, pruned_loss=0.03973, over 1425077.39 frames.], batch size: 20, lr: 4.86e-04
+2022-05-14 18:51:57,536 INFO [train.py:812] (7/8) Epoch 16, batch 1900, loss[loss=0.1789, simple_loss=0.2862, pruned_loss=0.03583, over 7316.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2564, pruned_loss=0.03946, over 1429166.78 frames.], batch size: 25, lr: 4.86e-04
+2022-05-14 18:52:55,129 INFO [train.py:812] (7/8) Epoch 16, batch 1950, loss[loss=0.1947, simple_loss=0.291, pruned_loss=0.04916, over 7197.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2575, pruned_loss=0.03967, over 1430490.40 frames.], batch size: 23, lr: 4.85e-04
+2022-05-14 18:53:54,425 INFO [train.py:812] (7/8) Epoch 16, batch 2000, loss[loss=0.1783, simple_loss=0.2658, pruned_loss=0.04536, over 5115.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2579, pruned_loss=0.0398, over 1423306.56 frames.], batch size: 52, lr: 4.85e-04
+2022-05-14 18:54:53,373 INFO [train.py:812] (7/8) Epoch 16, batch 2050, loss[loss=0.1735, simple_loss=0.2647, pruned_loss=0.04113, over 6593.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2583, pruned_loss=0.0402, over 1422358.59 frames.], batch size: 38, lr: 4.85e-04
+2022-05-14 18:55:52,734 INFO [train.py:812] (7/8) Epoch 16, batch 2100, loss[loss=0.166, simple_loss=0.2624, pruned_loss=0.03473, over 7448.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2582, pruned_loss=0.04011, over 1423582.89 frames.], batch size: 22, lr: 4.85e-04
+2022-05-14 18:56:51,677 INFO [train.py:812] (7/8) Epoch 16, batch 2150, loss[loss=0.1701, simple_loss=0.2713, pruned_loss=0.03441, over 7253.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2576, pruned_loss=0.03997, over 1418907.82 frames.], batch size: 19, lr: 4.85e-04
+2022-05-14 18:57:51,009 INFO [train.py:812] (7/8) Epoch 16, batch 2200, loss[loss=0.1972, simple_loss=0.2844, pruned_loss=0.055, over 7203.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2575, pruned_loss=0.04013, over 1416210.47 frames.], batch size: 22, lr: 4.84e-04
+2022-05-14 18:58:50,195 INFO [train.py:812] (7/8) Epoch 16, batch 2250, loss[loss=0.1686, simple_loss=0.2594, pruned_loss=0.03884, over 7410.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2578, pruned_loss=0.04019, over 1418173.89 frames.], batch size: 21, lr: 4.84e-04
+2022-05-14 18:59:49,577 INFO [train.py:812] (7/8) Epoch 16, batch 2300, loss[loss=0.1568, simple_loss=0.2536, pruned_loss=0.03004, over 7197.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2581, pruned_loss=0.04013, over 1419805.62 frames.], batch size: 23, lr: 4.84e-04
+2022-05-14 19:00:48,705 INFO [train.py:812] (7/8) Epoch 16, batch 2350, loss[loss=0.1863, simple_loss=0.2699, pruned_loss=0.05133, over 7302.00 frames.], tot_loss[loss=0.1689, simple_loss=0.258, pruned_loss=0.03989, over 1421947.97 frames.], batch size: 25, lr: 4.84e-04
+2022-05-14 19:01:48,370 INFO [train.py:812] (7/8) Epoch 16, batch 2400, loss[loss=0.1851, simple_loss=0.2782, pruned_loss=0.04601, over 7290.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2574, pruned_loss=0.03998, over 1425024.98 frames.], batch size: 25, lr: 4.84e-04
+2022-05-14 19:02:47,271 INFO [train.py:812] (7/8) Epoch 16, batch 2450, loss[loss=0.1636, simple_loss=0.2556, pruned_loss=0.03581, over 6759.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2578, pruned_loss=0.0398, over 1424492.65 frames.], batch size: 31, lr: 4.84e-04
+2022-05-14 19:03:46,851 INFO [train.py:812] (7/8) Epoch 16, batch 2500, loss[loss=0.1566, simple_loss=0.2526, pruned_loss=0.03034, over 7221.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2572, pruned_loss=0.03957, over 1427573.34 frames.], batch size: 21, lr: 4.83e-04
+2022-05-14 19:04:46,126 INFO [train.py:812] (7/8) Epoch 16, batch 2550, loss[loss=0.1598, simple_loss=0.2516, pruned_loss=0.03398, over 7146.00 frames.], tot_loss[loss=0.1677, simple_loss=0.257, pruned_loss=0.03919, over 1424202.23 frames.], batch size: 20, lr: 4.83e-04
+2022-05-14 19:05:45,658 INFO [train.py:812] (7/8) Epoch 16, batch 2600, loss[loss=0.1474, simple_loss=0.2382, pruned_loss=0.02836, over 7366.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2566, pruned_loss=0.03905, over 1422777.32 frames.], batch size: 19, lr: 4.83e-04
+2022-05-14 19:06:45,286 INFO [train.py:812] (7/8) Epoch 16, batch 2650, loss[loss=0.1655, simple_loss=0.2608, pruned_loss=0.03512, over 7391.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2568, pruned_loss=0.03894, over 1423385.47 frames.], batch size: 23, lr: 4.83e-04
+2022-05-14 19:07:45,172 INFO [train.py:812] (7/8) Epoch 16, batch 2700, loss[loss=0.2051, simple_loss=0.2974, pruned_loss=0.0564, over 7164.00 frames.], tot_loss[loss=0.1677, simple_loss=0.257, pruned_loss=0.03917, over 1420827.02 frames.], batch size: 26, lr: 4.83e-04
+2022-05-14 19:08:44,252 INFO [train.py:812] (7/8) Epoch 16, batch 2750, loss[loss=0.1725, simple_loss=0.2582, pruned_loss=0.04335, over 7288.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2575, pruned_loss=0.03938, over 1424979.90 frames.], batch size: 18, lr: 4.83e-04
+2022-05-14 19:09:44,134 INFO [train.py:812] (7/8) Epoch 16, batch 2800, loss[loss=0.1664, simple_loss=0.259, pruned_loss=0.03694, over 7211.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2573, pruned_loss=0.03917, over 1427301.48 frames.], batch size: 21, lr: 4.82e-04
+2022-05-14 19:10:43,397 INFO [train.py:812] (7/8) Epoch 16, batch 2850, loss[loss=0.1518, simple_loss=0.239, pruned_loss=0.0323, over 7158.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2579, pruned_loss=0.03956, over 1425911.23 frames.], batch size: 18, lr: 4.82e-04
+2022-05-14 19:11:42,850 INFO [train.py:812] (7/8) Epoch 16, batch 2900, loss[loss=0.1711, simple_loss=0.2658, pruned_loss=0.03825, over 7174.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2576, pruned_loss=0.03951, over 1428112.75 frames.], batch size: 18, lr: 4.82e-04
+2022-05-14 19:12:41,644 INFO [train.py:812] (7/8) Epoch 16, batch 2950, loss[loss=0.157, simple_loss=0.2569, pruned_loss=0.02861, over 7336.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2568, pruned_loss=0.03902, over 1425063.29 frames.], batch size: 22, lr: 4.82e-04
+2022-05-14 19:13:40,852 INFO [train.py:812] (7/8) Epoch 16, batch 3000, loss[loss=0.1697, simple_loss=0.2615, pruned_loss=0.03896, over 7408.00 frames.], tot_loss[loss=0.1676, simple_loss=0.257, pruned_loss=0.03906, over 1429250.38 frames.], batch size: 21, lr: 4.82e-04
+2022-05-14 19:13:40,854 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 19:13:48,992 INFO [train.py:841] (7/8) Epoch 16, validation: loss=0.1537, simple_loss=0.2535, pruned_loss=0.02695, over 698248.00 frames.
+2022-05-14 19:14:47,158 INFO [train.py:812] (7/8) Epoch 16, batch 3050, loss[loss=0.1402, simple_loss=0.2199, pruned_loss=0.03032, over 7397.00 frames.], tot_loss[loss=0.1678, simple_loss=0.257, pruned_loss=0.03932, over 1427964.54 frames.], batch size: 18, lr: 4.82e-04
+2022-05-14 19:15:46,692 INFO [train.py:812] (7/8) Epoch 16, batch 3100, loss[loss=0.1835, simple_loss=0.2849, pruned_loss=0.04102, over 7204.00 frames.], tot_loss[loss=0.1682, simple_loss=0.257, pruned_loss=0.03974, over 1427101.92 frames.], batch size: 23, lr: 4.81e-04
+2022-05-14 19:16:44,997 INFO [train.py:812] (7/8) Epoch 16, batch 3150, loss[loss=0.1396, simple_loss=0.2248, pruned_loss=0.0272, over 7167.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2561, pruned_loss=0.03921, over 1424446.28 frames.], batch size: 18, lr: 4.81e-04
+2022-05-14 19:17:47,881 INFO [train.py:812] (7/8) Epoch 16, batch 3200, loss[loss=0.1909, simple_loss=0.2757, pruned_loss=0.05304, over 7317.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2575, pruned_loss=0.04003, over 1424344.83 frames.], batch size: 24, lr: 4.81e-04
+2022-05-14 19:18:47,187 INFO [train.py:812] (7/8) Epoch 16, batch 3250, loss[loss=0.1947, simple_loss=0.2834, pruned_loss=0.05298, over 7329.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2564, pruned_loss=0.03961, over 1425997.41 frames.], batch size: 21, lr: 4.81e-04
+2022-05-14 19:19:45,430 INFO [train.py:812] (7/8) Epoch 16, batch 3300, loss[loss=0.2165, simple_loss=0.3085, pruned_loss=0.06224, over 7245.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2565, pruned_loss=0.03905, over 1429632.01 frames.], batch size: 25, lr: 4.81e-04
+2022-05-14 19:20:42,571 INFO [train.py:812] (7/8) Epoch 16, batch 3350, loss[loss=0.1928, simple_loss=0.2884, pruned_loss=0.04857, over 7231.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2564, pruned_loss=0.03907, over 1431926.74 frames.], batch size: 20, lr: 4.81e-04
+2022-05-14 19:21:41,209 INFO [train.py:812] (7/8) Epoch 16, batch 3400, loss[loss=0.1528, simple_loss=0.242, pruned_loss=0.03177, over 7066.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2569, pruned_loss=0.03911, over 1428769.62 frames.], batch size: 28, lr: 4.80e-04
+2022-05-14 19:22:40,346 INFO [train.py:812] (7/8) Epoch 16, batch 3450, loss[loss=0.152, simple_loss=0.2414, pruned_loss=0.03136, over 7359.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2566, pruned_loss=0.03883, over 1430257.68 frames.], batch size: 19, lr: 4.80e-04
+2022-05-14 19:23:40,293 INFO [train.py:812] (7/8) Epoch 16, batch 3500, loss[loss=0.1598, simple_loss=0.2553, pruned_loss=0.03218, over 7333.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2567, pruned_loss=0.03913, over 1428674.02 frames.], batch size: 21, lr: 4.80e-04
+2022-05-14 19:24:39,245 INFO [train.py:812] (7/8) Epoch 16, batch 3550, loss[loss=0.2025, simple_loss=0.2886, pruned_loss=0.05821, over 7170.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2575, pruned_loss=0.03941, over 1423694.72 frames.], batch size: 26, lr: 4.80e-04
+2022-05-14 19:25:38,838 INFO [train.py:812] (7/8) Epoch 16, batch 3600, loss[loss=0.1912, simple_loss=0.2917, pruned_loss=0.04539, over 7315.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2576, pruned_loss=0.03939, over 1425519.00 frames.], batch size: 21, lr: 4.80e-04
+2022-05-14 19:26:37,942 INFO [train.py:812] (7/8) Epoch 16, batch 3650, loss[loss=0.1544, simple_loss=0.2349, pruned_loss=0.03698, over 7288.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2573, pruned_loss=0.0396, over 1425686.84 frames.], batch size: 18, lr: 4.80e-04
+2022-05-14 19:27:36,143 INFO [train.py:812] (7/8) Epoch 16, batch 3700, loss[loss=0.1175, simple_loss=0.2047, pruned_loss=0.01519, over 6786.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2568, pruned_loss=0.03979, over 1424010.14 frames.], batch size: 15, lr: 4.79e-04
+2022-05-14 19:28:35,335 INFO [train.py:812] (7/8) Epoch 16, batch 3750, loss[loss=0.2169, simple_loss=0.2989, pruned_loss=0.06746, over 7253.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2571, pruned_loss=0.04014, over 1422010.44 frames.], batch size: 25, lr: 4.79e-04
+2022-05-14 19:29:33,359 INFO [train.py:812] (7/8) Epoch 16, batch 3800, loss[loss=0.1498, simple_loss=0.2311, pruned_loss=0.03426, over 7137.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2575, pruned_loss=0.03983, over 1425684.85 frames.], batch size: 17, lr: 4.79e-04
+2022-05-14 19:30:31,508 INFO [train.py:812] (7/8) Epoch 16, batch 3850, loss[loss=0.1624, simple_loss=0.2432, pruned_loss=0.04075, over 7270.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2571, pruned_loss=0.03979, over 1421175.34 frames.], batch size: 18, lr: 4.79e-04
+2022-05-14 19:31:29,719 INFO [train.py:812] (7/8) Epoch 16, batch 3900, loss[loss=0.1591, simple_loss=0.254, pruned_loss=0.0321, over 7219.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2575, pruned_loss=0.03995, over 1422800.74 frames.], batch size: 21, lr: 4.79e-04
+2022-05-14 19:32:28,925 INFO [train.py:812] (7/8) Epoch 16, batch 3950, loss[loss=0.1653, simple_loss=0.2607, pruned_loss=0.03501, over 7252.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2578, pruned_loss=0.03996, over 1421191.45 frames.], batch size: 20, lr: 4.79e-04
+2022-05-14 19:33:27,651 INFO [train.py:812] (7/8) Epoch 16, batch 4000, loss[loss=0.199, simple_loss=0.2852, pruned_loss=0.0564, over 7312.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2581, pruned_loss=0.04017, over 1419092.75 frames.], batch size: 21, lr: 4.79e-04
+2022-05-14 19:34:27,181 INFO [train.py:812] (7/8) Epoch 16, batch 4050, loss[loss=0.1649, simple_loss=0.248, pruned_loss=0.04084, over 7157.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2582, pruned_loss=0.0401, over 1418258.84 frames.], batch size: 18, lr: 4.78e-04
+2022-05-14 19:35:27,362 INFO [train.py:812] (7/8) Epoch 16, batch 4100, loss[loss=0.174, simple_loss=0.2651, pruned_loss=0.04148, over 7159.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2577, pruned_loss=0.04004, over 1423234.86 frames.], batch size: 18, lr: 4.78e-04
+2022-05-14 19:36:26,234 INFO [train.py:812] (7/8) Epoch 16, batch 4150, loss[loss=0.1562, simple_loss=0.2517, pruned_loss=0.03039, over 7132.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2584, pruned_loss=0.04025, over 1418280.90 frames.], batch size: 28, lr: 4.78e-04
+2022-05-14 19:37:25,140 INFO [train.py:812] (7/8) Epoch 16, batch 4200, loss[loss=0.166, simple_loss=0.2373, pruned_loss=0.04739, over 7421.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2576, pruned_loss=0.04031, over 1417737.60 frames.], batch size: 17, lr: 4.78e-04
+2022-05-14 19:38:24,460 INFO [train.py:812] (7/8) Epoch 16, batch 4250, loss[loss=0.1671, simple_loss=0.2523, pruned_loss=0.04096, over 7169.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2562, pruned_loss=0.04018, over 1417617.73 frames.], batch size: 18, lr: 4.78e-04
+2022-05-14 19:39:23,855 INFO [train.py:812] (7/8) Epoch 16, batch 4300, loss[loss=0.1792, simple_loss=0.2693, pruned_loss=0.04455, over 6783.00 frames.], tot_loss[loss=0.1682, simple_loss=0.256, pruned_loss=0.0402, over 1412857.71 frames.], batch size: 31, lr: 4.78e-04
+2022-05-14 19:40:22,748 INFO [train.py:812] (7/8) Epoch 16, batch 4350, loss[loss=0.1553, simple_loss=0.249, pruned_loss=0.0308, over 7167.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2563, pruned_loss=0.03971, over 1415999.69 frames.], batch size: 18, lr: 4.77e-04
+2022-05-14 19:41:21,993 INFO [train.py:812] (7/8) Epoch 16, batch 4400, loss[loss=0.1733, simple_loss=0.2703, pruned_loss=0.03811, over 7112.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2558, pruned_loss=0.03932, over 1416151.47 frames.], batch size: 21, lr: 4.77e-04
+2022-05-14 19:42:18,630 INFO [train.py:812] (7/8) Epoch 16, batch 4450, loss[loss=0.1778, simple_loss=0.2682, pruned_loss=0.04367, over 7207.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2565, pruned_loss=0.03984, over 1410880.72 frames.], batch size: 22, lr: 4.77e-04
+2022-05-14 19:43:16,048 INFO [train.py:812] (7/8) Epoch 16, batch 4500, loss[loss=0.1399, simple_loss=0.2276, pruned_loss=0.02613, over 7125.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2563, pruned_loss=0.03954, over 1401696.19 frames.], batch size: 17, lr: 4.77e-04
+2022-05-14 19:44:12,856 INFO [train.py:812] (7/8) Epoch 16, batch 4550, loss[loss=0.2202, simple_loss=0.2957, pruned_loss=0.07231, over 5195.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2597, pruned_loss=0.04165, over 1350714.15 frames.], batch size: 52, lr: 4.77e-04
+2022-05-14 19:45:27,035 INFO [train.py:812] (7/8) Epoch 17, batch 0, loss[loss=0.1718, simple_loss=0.2654, pruned_loss=0.03907, over 7107.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2654, pruned_loss=0.03907, over 7107.00 frames.], batch size: 21, lr: 4.63e-04
+2022-05-14 19:46:26,176 INFO [train.py:812] (7/8) Epoch 17, batch 50, loss[loss=0.1765, simple_loss=0.2744, pruned_loss=0.03925, over 7308.00 frames.], tot_loss[loss=0.1712, simple_loss=0.261, pruned_loss=0.04069, over 317397.58 frames.], batch size: 21, lr: 4.63e-04
+2022-05-14 19:47:25,038 INFO [train.py:812] (7/8) Epoch 17, batch 100, loss[loss=0.172, simple_loss=0.258, pruned_loss=0.04298, over 7138.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2592, pruned_loss=0.03984, over 559321.53 frames.], batch size: 20, lr: 4.63e-04
+2022-05-14 19:48:23,540 INFO [train.py:812] (7/8) Epoch 17, batch 150, loss[loss=0.1625, simple_loss=0.2455, pruned_loss=0.03971, over 7012.00 frames.], tot_loss[loss=0.169, simple_loss=0.2585, pruned_loss=0.03974, over 747409.98 frames.], batch size: 16, lr: 4.63e-04
+2022-05-14 19:49:23,018 INFO [train.py:812] (7/8) Epoch 17, batch 200, loss[loss=0.1508, simple_loss=0.2336, pruned_loss=0.03397, over 7145.00 frames.], tot_loss[loss=0.17, simple_loss=0.2595, pruned_loss=0.04022, over 896257.74 frames.], batch size: 17, lr: 4.63e-04
+2022-05-14 19:50:21,384 INFO [train.py:812] (7/8) Epoch 17, batch 250, loss[loss=0.1597, simple_loss=0.2489, pruned_loss=0.03523, over 7268.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2604, pruned_loss=0.04097, over 1015523.11 frames.], batch size: 19, lr: 4.63e-04
+2022-05-14 19:51:20,299 INFO [train.py:812] (7/8) Epoch 17, batch 300, loss[loss=0.1563, simple_loss=0.2379, pruned_loss=0.03737, over 7070.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2604, pruned_loss=0.04095, over 1102092.17 frames.], batch size: 18, lr: 4.62e-04
+2022-05-14 19:52:19,501 INFO [train.py:812] (7/8) Epoch 17, batch 350, loss[loss=0.1466, simple_loss=0.2308, pruned_loss=0.03123, over 6811.00 frames.], tot_loss[loss=0.17, simple_loss=0.2591, pruned_loss=0.04046, over 1173142.82 frames.], batch size: 15, lr: 4.62e-04
+2022-05-14 19:53:18,640 INFO [train.py:812] (7/8) Epoch 17, batch 400, loss[loss=0.2007, simple_loss=0.2682, pruned_loss=0.06661, over 5208.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2591, pruned_loss=0.04004, over 1228941.88 frames.], batch size: 52, lr: 4.62e-04
+2022-05-14 19:54:16,214 INFO [train.py:812] (7/8) Epoch 17, batch 450, loss[loss=0.1582, simple_loss=0.2483, pruned_loss=0.03407, over 7359.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2581, pruned_loss=0.03945, over 1269702.75 frames.], batch size: 19, lr: 4.62e-04
+2022-05-14 19:55:14,857 INFO [train.py:812] (7/8) Epoch 17, batch 500, loss[loss=0.1511, simple_loss=0.2396, pruned_loss=0.03129, over 7161.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2574, pruned_loss=0.0389, over 1303156.05 frames.], batch size: 18, lr: 4.62e-04
+2022-05-14 19:56:13,722 INFO [train.py:812] (7/8) Epoch 17, batch 550, loss[loss=0.1429, simple_loss=0.2287, pruned_loss=0.02855, over 7155.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2569, pruned_loss=0.03874, over 1328398.36 frames.], batch size: 17, lr: 4.62e-04
+2022-05-14 19:57:12,607 INFO [train.py:812] (7/8) Epoch 17, batch 600, loss[loss=0.1569, simple_loss=0.2578, pruned_loss=0.028, over 7118.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2564, pruned_loss=0.03874, over 1342951.68 frames.], batch size: 28, lr: 4.62e-04
+2022-05-14 19:58:11,580 INFO [train.py:812] (7/8) Epoch 17, batch 650, loss[loss=0.1618, simple_loss=0.257, pruned_loss=0.03332, over 7326.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2576, pruned_loss=0.03906, over 1361661.97 frames.], batch size: 20, lr: 4.61e-04
+2022-05-14 19:59:10,290 INFO [train.py:812] (7/8) Epoch 17, batch 700, loss[loss=0.1534, simple_loss=0.2459, pruned_loss=0.03048, over 7252.00 frames.], tot_loss[loss=0.168, simple_loss=0.2578, pruned_loss=0.03911, over 1368173.74 frames.], batch size: 19, lr: 4.61e-04
+2022-05-14 20:00:09,369 INFO [train.py:812] (7/8) Epoch 17, batch 750, loss[loss=0.1523, simple_loss=0.2325, pruned_loss=0.0361, over 7154.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2582, pruned_loss=0.0394, over 1376177.06 frames.], batch size: 20, lr: 4.61e-04
+2022-05-14 20:01:08,225 INFO [train.py:812] (7/8) Epoch 17, batch 800, loss[loss=0.1517, simple_loss=0.2391, pruned_loss=0.03213, over 7165.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2576, pruned_loss=0.03881, over 1387421.21 frames.], batch size: 19, lr: 4.61e-04
+2022-05-14 20:02:07,182 INFO [train.py:812] (7/8) Epoch 17, batch 850, loss[loss=0.1645, simple_loss=0.2633, pruned_loss=0.03287, over 6363.00 frames.], tot_loss[loss=0.1671, simple_loss=0.257, pruned_loss=0.03864, over 1395790.23 frames.], batch size: 38, lr: 4.61e-04
+2022-05-14 20:03:05,154 INFO [train.py:812] (7/8) Epoch 17, batch 900, loss[loss=0.159, simple_loss=0.2571, pruned_loss=0.03044, over 7327.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2566, pruned_loss=0.0383, over 1407172.09 frames.], batch size: 20, lr: 4.61e-04
+2022-05-14 20:04:03,167 INFO [train.py:812] (7/8) Epoch 17, batch 950, loss[loss=0.1509, simple_loss=0.2305, pruned_loss=0.03564, over 7123.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2559, pruned_loss=0.03797, over 1412078.51 frames.], batch size: 17, lr: 4.60e-04
+2022-05-14 20:05:01,770 INFO [train.py:812] (7/8) Epoch 17, batch 1000, loss[loss=0.1566, simple_loss=0.2529, pruned_loss=0.03018, over 7113.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2559, pruned_loss=0.03788, over 1415986.04 frames.], batch size: 21, lr: 4.60e-04
+2022-05-14 20:06:00,372 INFO [train.py:812] (7/8) Epoch 17, batch 1050, loss[loss=0.1867, simple_loss=0.2832, pruned_loss=0.04505, over 7342.00 frames.], tot_loss[loss=0.1655, simple_loss=0.255, pruned_loss=0.03797, over 1420801.50 frames.], batch size: 22, lr: 4.60e-04
+2022-05-14 20:06:59,603 INFO [train.py:812] (7/8) Epoch 17, batch 1100, loss[loss=0.169, simple_loss=0.2643, pruned_loss=0.0369, over 7282.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2554, pruned_loss=0.03812, over 1421807.46 frames.], batch size: 24, lr: 4.60e-04
+2022-05-14 20:07:58,290 INFO [train.py:812] (7/8) Epoch 17, batch 1150, loss[loss=0.1766, simple_loss=0.2775, pruned_loss=0.03784, over 7301.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2556, pruned_loss=0.03805, over 1422626.91 frames.], batch size: 24, lr: 4.60e-04
+2022-05-14 20:08:57,648 INFO [train.py:812] (7/8) Epoch 17, batch 1200, loss[loss=0.2601, simple_loss=0.3511, pruned_loss=0.08455, over 7299.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2561, pruned_loss=0.03871, over 1420056.63 frames.], batch size: 25, lr: 4.60e-04
+2022-05-14 20:09:55,634 INFO [train.py:812] (7/8) Epoch 17, batch 1250, loss[loss=0.1526, simple_loss=0.2324, pruned_loss=0.03647, over 7261.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2565, pruned_loss=0.03895, over 1415970.76 frames.], batch size: 18, lr: 4.60e-04
+2022-05-14 20:10:53,546 INFO [train.py:812] (7/8) Epoch 17, batch 1300, loss[loss=0.1672, simple_loss=0.2618, pruned_loss=0.03633, over 7333.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2567, pruned_loss=0.03923, over 1415725.18 frames.], batch size: 22, lr: 4.59e-04
+2022-05-14 20:11:51,671 INFO [train.py:812] (7/8) Epoch 17, batch 1350, loss[loss=0.1591, simple_loss=0.2345, pruned_loss=0.0418, over 6982.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2566, pruned_loss=0.03887, over 1420967.99 frames.], batch size: 16, lr: 4.59e-04
+2022-05-14 20:12:51,115 INFO [train.py:812] (7/8) Epoch 17, batch 1400, loss[loss=0.1588, simple_loss=0.2481, pruned_loss=0.03477, over 7152.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2557, pruned_loss=0.03877, over 1422060.63 frames.], batch size: 20, lr: 4.59e-04
+2022-05-14 20:13:49,607 INFO [train.py:812] (7/8) Epoch 17, batch 1450, loss[loss=0.1812, simple_loss=0.2731, pruned_loss=0.04468, over 7333.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2563, pruned_loss=0.03944, over 1420749.71 frames.], batch size: 22, lr: 4.59e-04
+2022-05-14 20:14:48,961 INFO [train.py:812] (7/8) Epoch 17, batch 1500, loss[loss=0.1591, simple_loss=0.2453, pruned_loss=0.03648, over 7258.00 frames.], tot_loss[loss=0.1664, simple_loss=0.255, pruned_loss=0.03891, over 1426536.08 frames.], batch size: 19, lr: 4.59e-04
+2022-05-14 20:15:57,380 INFO [train.py:812] (7/8) Epoch 17, batch 1550, loss[loss=0.1693, simple_loss=0.2594, pruned_loss=0.03955, over 7221.00 frames.], tot_loss[loss=0.167, simple_loss=0.2556, pruned_loss=0.03927, over 1423444.54 frames.], batch size: 21, lr: 4.59e-04
+2022-05-14 20:16:56,771 INFO [train.py:812] (7/8) Epoch 17, batch 1600, loss[loss=0.1543, simple_loss=0.2522, pruned_loss=0.02823, over 7438.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2546, pruned_loss=0.0384, over 1427351.28 frames.], batch size: 20, lr: 4.58e-04
+2022-05-14 20:17:55,373 INFO [train.py:812] (7/8) Epoch 17, batch 1650, loss[loss=0.1697, simple_loss=0.2591, pruned_loss=0.04018, over 7423.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2553, pruned_loss=0.0385, over 1428959.05 frames.], batch size: 21, lr: 4.58e-04
+2022-05-14 20:18:53,705 INFO [train.py:812] (7/8) Epoch 17, batch 1700, loss[loss=0.2171, simple_loss=0.2854, pruned_loss=0.07442, over 4702.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2566, pruned_loss=0.03898, over 1421549.56 frames.], batch size: 52, lr: 4.58e-04
+2022-05-14 20:19:52,423 INFO [train.py:812] (7/8) Epoch 17, batch 1750, loss[loss=0.1844, simple_loss=0.2713, pruned_loss=0.04876, over 7371.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2575, pruned_loss=0.039, over 1414154.01 frames.], batch size: 23, lr: 4.58e-04
+2022-05-14 20:20:51,567 INFO [train.py:812] (7/8) Epoch 17, batch 1800, loss[loss=0.1553, simple_loss=0.2498, pruned_loss=0.03037, over 7180.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2574, pruned_loss=0.03884, over 1414853.77 frames.], batch size: 23, lr: 4.58e-04
+2022-05-14 20:21:48,777 INFO [train.py:812] (7/8) Epoch 17, batch 1850, loss[loss=0.1883, simple_loss=0.2775, pruned_loss=0.04959, over 6483.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2567, pruned_loss=0.03858, over 1416045.70 frames.], batch size: 37, lr: 4.58e-04
+2022-05-14 20:22:47,391 INFO [train.py:812] (7/8) Epoch 17, batch 1900, loss[loss=0.1526, simple_loss=0.2246, pruned_loss=0.04035, over 7428.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2558, pruned_loss=0.03828, over 1419792.00 frames.], batch size: 20, lr: 4.58e-04
+2022-05-14 20:23:46,087 INFO [train.py:812] (7/8) Epoch 17, batch 1950, loss[loss=0.164, simple_loss=0.2595, pruned_loss=0.03426, over 7321.00 frames.], tot_loss[loss=0.1667, simple_loss=0.256, pruned_loss=0.03869, over 1422480.20 frames.], batch size: 21, lr: 4.57e-04
+2022-05-14 20:24:44,632 INFO [train.py:812] (7/8) Epoch 17, batch 2000, loss[loss=0.158, simple_loss=0.2443, pruned_loss=0.03581, over 7265.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2567, pruned_loss=0.03891, over 1423933.22 frames.], batch size: 19, lr: 4.57e-04
+2022-05-14 20:25:43,677 INFO [train.py:812] (7/8) Epoch 17, batch 2050, loss[loss=0.1448, simple_loss=0.2295, pruned_loss=0.03005, over 7401.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2557, pruned_loss=0.03878, over 1426824.03 frames.], batch size: 18, lr: 4.57e-04
+2022-05-14 20:26:43,376 INFO [train.py:812] (7/8) Epoch 17, batch 2100, loss[loss=0.1551, simple_loss=0.2471, pruned_loss=0.03157, over 7430.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2557, pruned_loss=0.0384, over 1428064.76 frames.], batch size: 21, lr: 4.57e-04
+2022-05-14 20:27:42,681 INFO [train.py:812] (7/8) Epoch 17, batch 2150, loss[loss=0.1841, simple_loss=0.265, pruned_loss=0.05162, over 7363.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2567, pruned_loss=0.03919, over 1424345.78 frames.], batch size: 19, lr: 4.57e-04
+2022-05-14 20:28:40,087 INFO [train.py:812] (7/8) Epoch 17, batch 2200, loss[loss=0.1721, simple_loss=0.2767, pruned_loss=0.0338, over 7337.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2563, pruned_loss=0.03877, over 1422090.53 frames.], batch size: 22, lr: 4.57e-04
+2022-05-14 20:29:39,230 INFO [train.py:812] (7/8) Epoch 17, batch 2250, loss[loss=0.1583, simple_loss=0.2554, pruned_loss=0.03064, over 7409.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2567, pruned_loss=0.03909, over 1423993.91 frames.], batch size: 21, lr: 4.56e-04
+2022-05-14 20:30:37,993 INFO [train.py:812] (7/8) Epoch 17, batch 2300, loss[loss=0.1457, simple_loss=0.2389, pruned_loss=0.02627, over 7305.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2557, pruned_loss=0.03871, over 1423524.82 frames.], batch size: 24, lr: 4.56e-04
+2022-05-14 20:31:36,723 INFO [train.py:812] (7/8) Epoch 17, batch 2350, loss[loss=0.1787, simple_loss=0.2717, pruned_loss=0.04281, over 7381.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2556, pruned_loss=0.03844, over 1426556.71 frames.], batch size: 23, lr: 4.56e-04
+2022-05-14 20:32:36,117 INFO [train.py:812] (7/8) Epoch 17, batch 2400, loss[loss=0.1778, simple_loss=0.2523, pruned_loss=0.05163, over 7016.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2547, pruned_loss=0.03821, over 1424601.76 frames.], batch size: 16, lr: 4.56e-04
+2022-05-14 20:33:34,535 INFO [train.py:812] (7/8) Epoch 17, batch 2450, loss[loss=0.1617, simple_loss=0.2556, pruned_loss=0.03388, over 7330.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2538, pruned_loss=0.03779, over 1422735.82 frames.], batch size: 22, lr: 4.56e-04
+2022-05-14 20:34:34,279 INFO [train.py:812] (7/8) Epoch 17, batch 2500, loss[loss=0.2079, simple_loss=0.291, pruned_loss=0.06241, over 7217.00 frames.], tot_loss[loss=0.1642, simple_loss=0.253, pruned_loss=0.03767, over 1422743.50 frames.], batch size: 21, lr: 4.56e-04
+2022-05-14 20:35:31,580 INFO [train.py:812] (7/8) Epoch 17, batch 2550, loss[loss=0.1486, simple_loss=0.2423, pruned_loss=0.02746, over 7218.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2535, pruned_loss=0.03795, over 1418375.62 frames.], batch size: 21, lr: 4.56e-04
+2022-05-14 20:36:37,563 INFO [train.py:812] (7/8) Epoch 17, batch 2600, loss[loss=0.1627, simple_loss=0.2615, pruned_loss=0.03201, over 7134.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2556, pruned_loss=0.03862, over 1421083.29 frames.], batch size: 28, lr: 4.55e-04
+2022-05-14 20:37:36,773 INFO [train.py:812] (7/8) Epoch 17, batch 2650, loss[loss=0.1411, simple_loss=0.2293, pruned_loss=0.02643, over 7357.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2564, pruned_loss=0.03897, over 1419083.50 frames.], batch size: 19, lr: 4.55e-04
+2022-05-14 20:38:34,803 INFO [train.py:812] (7/8) Epoch 17, batch 2700, loss[loss=0.1871, simple_loss=0.2859, pruned_loss=0.0442, over 7347.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2551, pruned_loss=0.03838, over 1421694.86 frames.], batch size: 22, lr: 4.55e-04
+2022-05-14 20:39:32,834 INFO [train.py:812] (7/8) Epoch 17, batch 2750, loss[loss=0.1564, simple_loss=0.2495, pruned_loss=0.03162, over 7164.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2544, pruned_loss=0.03842, over 1421765.06 frames.], batch size: 19, lr: 4.55e-04
+2022-05-14 20:40:31,902 INFO [train.py:812] (7/8) Epoch 17, batch 2800, loss[loss=0.1942, simple_loss=0.271, pruned_loss=0.05876, over 5078.00 frames.], tot_loss[loss=0.1654, simple_loss=0.254, pruned_loss=0.03843, over 1421533.01 frames.], batch size: 52, lr: 4.55e-04
+2022-05-14 20:41:30,573 INFO [train.py:812] (7/8) Epoch 17, batch 2850, loss[loss=0.1711, simple_loss=0.2731, pruned_loss=0.03452, over 7312.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2549, pruned_loss=0.03872, over 1421804.60 frames.], batch size: 21, lr: 4.55e-04
+2022-05-14 20:42:28,913 INFO [train.py:812] (7/8) Epoch 17, batch 2900, loss[loss=0.1546, simple_loss=0.2497, pruned_loss=0.02976, over 7238.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2553, pruned_loss=0.0389, over 1416852.35 frames.], batch size: 20, lr: 4.55e-04
+2022-05-14 20:43:27,776 INFO [train.py:812] (7/8) Epoch 17, batch 2950, loss[loss=0.1557, simple_loss=0.2379, pruned_loss=0.03673, over 7279.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2566, pruned_loss=0.03932, over 1417844.55 frames.], batch size: 18, lr: 4.54e-04
+2022-05-14 20:44:36,181 INFO [train.py:812] (7/8) Epoch 17, batch 3000, loss[loss=0.1843, simple_loss=0.2768, pruned_loss=0.04588, over 7154.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2578, pruned_loss=0.03973, over 1423022.79 frames.], batch size: 20, lr: 4.54e-04
+2022-05-14 20:44:36,183 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 20:44:43,902 INFO [train.py:841] (7/8) Epoch 17, validation: loss=0.1538, simple_loss=0.2534, pruned_loss=0.02708, over 698248.00 frames.
+2022-05-14 20:45:42,810 INFO [train.py:812] (7/8) Epoch 17, batch 3050, loss[loss=0.1873, simple_loss=0.2775, pruned_loss=0.04857, over 6379.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2571, pruned_loss=0.03936, over 1422744.15 frames.], batch size: 37, lr: 4.54e-04
+2022-05-14 20:46:41,094 INFO [train.py:812] (7/8) Epoch 17, batch 3100, loss[loss=0.1987, simple_loss=0.2833, pruned_loss=0.05705, over 7264.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2573, pruned_loss=0.03932, over 1418956.42 frames.], batch size: 25, lr: 4.54e-04
+2022-05-14 20:47:58,638 INFO [train.py:812] (7/8) Epoch 17, batch 3150, loss[loss=0.1392, simple_loss=0.2296, pruned_loss=0.02442, over 7335.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2564, pruned_loss=0.03908, over 1418776.99 frames.], batch size: 20, lr: 4.54e-04
+2022-05-14 20:49:07,292 INFO [train.py:812] (7/8) Epoch 17, batch 3200, loss[loss=0.154, simple_loss=0.2461, pruned_loss=0.03092, over 7362.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2562, pruned_loss=0.03936, over 1418652.95 frames.], batch size: 19, lr: 4.54e-04
+2022-05-14 20:50:25,551 INFO [train.py:812] (7/8) Epoch 17, batch 3250, loss[loss=0.1492, simple_loss=0.2382, pruned_loss=0.0301, over 7062.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2566, pruned_loss=0.03938, over 1424256.70 frames.], batch size: 18, lr: 4.54e-04
+2022-05-14 20:51:34,421 INFO [train.py:812] (7/8) Epoch 17, batch 3300, loss[loss=0.1975, simple_loss=0.2875, pruned_loss=0.05373, over 7166.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2572, pruned_loss=0.03976, over 1424969.79 frames.], batch size: 19, lr: 4.53e-04
+2022-05-14 20:52:33,333 INFO [train.py:812] (7/8) Epoch 17, batch 3350, loss[loss=0.1602, simple_loss=0.2536, pruned_loss=0.03336, over 7337.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2573, pruned_loss=0.03975, over 1425822.40 frames.], batch size: 22, lr: 4.53e-04
+2022-05-14 20:53:32,430 INFO [train.py:812] (7/8) Epoch 17, batch 3400, loss[loss=0.1567, simple_loss=0.2543, pruned_loss=0.02956, over 7151.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2569, pruned_loss=0.03969, over 1422500.27 frames.], batch size: 20, lr: 4.53e-04
+2022-05-14 20:54:31,705 INFO [train.py:812] (7/8) Epoch 17, batch 3450, loss[loss=0.1703, simple_loss=0.2489, pruned_loss=0.04587, over 7339.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2558, pruned_loss=0.03943, over 1423894.02 frames.], batch size: 20, lr: 4.53e-04
+2022-05-14 20:55:30,362 INFO [train.py:812] (7/8) Epoch 17, batch 3500, loss[loss=0.1655, simple_loss=0.2517, pruned_loss=0.03968, over 7191.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2551, pruned_loss=0.03894, over 1423592.71 frames.], batch size: 22, lr: 4.53e-04
+2022-05-14 20:56:29,302 INFO [train.py:812] (7/8) Epoch 17, batch 3550, loss[loss=0.1537, simple_loss=0.2507, pruned_loss=0.02836, over 7123.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2554, pruned_loss=0.03863, over 1425854.52 frames.], batch size: 21, lr: 4.53e-04
+2022-05-14 20:57:28,834 INFO [train.py:812] (7/8) Epoch 17, batch 3600, loss[loss=0.1432, simple_loss=0.2263, pruned_loss=0.03008, over 7288.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2556, pruned_loss=0.03853, over 1427556.64 frames.], batch size: 18, lr: 4.52e-04
+2022-05-14 20:58:27,796 INFO [train.py:812] (7/8) Epoch 17, batch 3650, loss[loss=0.1741, simple_loss=0.2676, pruned_loss=0.04028, over 7315.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2547, pruned_loss=0.03825, over 1431426.51 frames.], batch size: 21, lr: 4.52e-04
+2022-05-14 20:59:27,718 INFO [train.py:812] (7/8) Epoch 17, batch 3700, loss[loss=0.1516, simple_loss=0.2445, pruned_loss=0.02931, over 7154.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2545, pruned_loss=0.03826, over 1430361.06 frames.], batch size: 20, lr: 4.52e-04
+2022-05-14 21:00:26,364 INFO [train.py:812] (7/8) Epoch 17, batch 3750, loss[loss=0.1713, simple_loss=0.2754, pruned_loss=0.03359, over 6188.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2546, pruned_loss=0.03812, over 1427522.67 frames.], batch size: 37, lr: 4.52e-04
+2022-05-14 21:01:24,393 INFO [train.py:812] (7/8) Epoch 17, batch 3800, loss[loss=0.1691, simple_loss=0.2549, pruned_loss=0.04163, over 6411.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2547, pruned_loss=0.03799, over 1425915.84 frames.], batch size: 37, lr: 4.52e-04
+2022-05-14 21:02:23,112 INFO [train.py:812] (7/8) Epoch 17, batch 3850, loss[loss=0.154, simple_loss=0.2346, pruned_loss=0.03668, over 7002.00 frames.], tot_loss[loss=0.165, simple_loss=0.2544, pruned_loss=0.03779, over 1425618.41 frames.], batch size: 16, lr: 4.52e-04
+2022-05-14 21:03:22,499 INFO [train.py:812] (7/8) Epoch 17, batch 3900, loss[loss=0.1593, simple_loss=0.2548, pruned_loss=0.03188, over 7216.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2529, pruned_loss=0.03735, over 1428219.13 frames.], batch size: 22, lr: 4.52e-04
+2022-05-14 21:04:21,514 INFO [train.py:812] (7/8) Epoch 17, batch 3950, loss[loss=0.1773, simple_loss=0.2722, pruned_loss=0.04125, over 7205.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2548, pruned_loss=0.03801, over 1427513.96 frames.], batch size: 23, lr: 4.51e-04
+2022-05-14 21:05:20,865 INFO [train.py:812] (7/8) Epoch 17, batch 4000, loss[loss=0.1476, simple_loss=0.2329, pruned_loss=0.03119, over 7277.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2551, pruned_loss=0.03857, over 1428424.68 frames.], batch size: 18, lr: 4.51e-04
+2022-05-14 21:06:19,950 INFO [train.py:812] (7/8) Epoch 17, batch 4050, loss[loss=0.1782, simple_loss=0.2709, pruned_loss=0.04271, over 6661.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2552, pruned_loss=0.03879, over 1425409.79 frames.], batch size: 31, lr: 4.51e-04
+2022-05-14 21:07:19,016 INFO [train.py:812] (7/8) Epoch 17, batch 4100, loss[loss=0.1788, simple_loss=0.2719, pruned_loss=0.04282, over 6357.00 frames.], tot_loss[loss=0.1667, simple_loss=0.256, pruned_loss=0.0387, over 1423991.39 frames.], batch size: 37, lr: 4.51e-04
+2022-05-14 21:08:18,291 INFO [train.py:812] (7/8) Epoch 17, batch 4150, loss[loss=0.1619, simple_loss=0.2512, pruned_loss=0.03629, over 7130.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2559, pruned_loss=0.03871, over 1423168.84 frames.], batch size: 17, lr: 4.51e-04
+2022-05-14 21:09:17,072 INFO [train.py:812] (7/8) Epoch 17, batch 4200, loss[loss=0.1801, simple_loss=0.2807, pruned_loss=0.03978, over 7116.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2563, pruned_loss=0.0388, over 1421848.12 frames.], batch size: 26, lr: 4.51e-04
+2022-05-14 21:10:16,242 INFO [train.py:812] (7/8) Epoch 17, batch 4250, loss[loss=0.1586, simple_loss=0.2498, pruned_loss=0.03369, over 7265.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2562, pruned_loss=0.03848, over 1423458.42 frames.], batch size: 18, lr: 4.51e-04
+2022-05-14 21:11:15,289 INFO [train.py:812] (7/8) Epoch 17, batch 4300, loss[loss=0.1466, simple_loss=0.2309, pruned_loss=0.03122, over 7063.00 frames.], tot_loss[loss=0.1654, simple_loss=0.255, pruned_loss=0.03786, over 1421842.89 frames.], batch size: 18, lr: 4.50e-04
+2022-05-14 21:12:14,042 INFO [train.py:812] (7/8) Epoch 17, batch 4350, loss[loss=0.159, simple_loss=0.2444, pruned_loss=0.03681, over 7166.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2551, pruned_loss=0.03817, over 1420629.53 frames.], batch size: 18, lr: 4.50e-04
+2022-05-14 21:13:12,870 INFO [train.py:812] (7/8) Epoch 17, batch 4400, loss[loss=0.1641, simple_loss=0.2664, pruned_loss=0.03085, over 7214.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2548, pruned_loss=0.03825, over 1418981.19 frames.], batch size: 21, lr: 4.50e-04
+2022-05-14 21:14:12,353 INFO [train.py:812] (7/8) Epoch 17, batch 4450, loss[loss=0.1446, simple_loss=0.2315, pruned_loss=0.02886, over 7156.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2571, pruned_loss=0.03894, over 1415059.19 frames.], batch size: 17, lr: 4.50e-04
+2022-05-14 21:15:12,260 INFO [train.py:812] (7/8) Epoch 17, batch 4500, loss[loss=0.1595, simple_loss=0.2497, pruned_loss=0.03462, over 7238.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2553, pruned_loss=0.03839, over 1413028.69 frames.], batch size: 20, lr: 4.50e-04
+2022-05-14 21:16:11,556 INFO [train.py:812] (7/8) Epoch 17, batch 4550, loss[loss=0.2059, simple_loss=0.2874, pruned_loss=0.06225, over 5184.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2551, pruned_loss=0.03934, over 1379676.87 frames.], batch size: 52, lr: 4.50e-04
+2022-05-14 21:17:18,374 INFO [train.py:812] (7/8) Epoch 18, batch 0, loss[loss=0.1667, simple_loss=0.2533, pruned_loss=0.04004, over 7236.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2533, pruned_loss=0.04004, over 7236.00 frames.], batch size: 20, lr: 4.38e-04
+2022-05-14 21:18:18,252 INFO [train.py:812] (7/8) Epoch 18, batch 50, loss[loss=0.1603, simple_loss=0.2462, pruned_loss=0.03722, over 6994.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2528, pruned_loss=0.0371, over 324085.98 frames.], batch size: 16, lr: 4.38e-04
+2022-05-14 21:19:17,392 INFO [train.py:812] (7/8) Epoch 18, batch 100, loss[loss=0.135, simple_loss=0.2261, pruned_loss=0.02194, over 7171.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2551, pruned_loss=0.0372, over 565684.93 frames.], batch size: 18, lr: 4.37e-04
+2022-05-14 21:20:15,740 INFO [train.py:812] (7/8) Epoch 18, batch 150, loss[loss=0.169, simple_loss=0.2634, pruned_loss=0.03726, over 7149.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2566, pruned_loss=0.03836, over 753691.86 frames.], batch size: 20, lr: 4.37e-04
+2022-05-14 21:21:13,528 INFO [train.py:812] (7/8) Epoch 18, batch 200, loss[loss=0.1469, simple_loss=0.2311, pruned_loss=0.03135, over 7161.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2573, pruned_loss=0.03872, over 904543.96 frames.], batch size: 18, lr: 4.37e-04
+2022-05-14 21:22:12,925 INFO [train.py:812] (7/8) Epoch 18, batch 250, loss[loss=0.1597, simple_loss=0.2531, pruned_loss=0.0332, over 6791.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2568, pruned_loss=0.03831, over 1022062.73 frames.], batch size: 31, lr: 4.37e-04
+2022-05-14 21:23:11,937 INFO [train.py:812] (7/8) Epoch 18, batch 300, loss[loss=0.1806, simple_loss=0.2691, pruned_loss=0.04604, over 7057.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2564, pruned_loss=0.03828, over 1106585.93 frames.], batch size: 28, lr: 4.37e-04
+2022-05-14 21:24:11,102 INFO [train.py:812] (7/8) Epoch 18, batch 350, loss[loss=0.16, simple_loss=0.2556, pruned_loss=0.0322, over 7331.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2551, pruned_loss=0.03794, over 1173979.75 frames.], batch size: 22, lr: 4.37e-04
+2022-05-14 21:25:08,919 INFO [train.py:812] (7/8) Epoch 18, batch 400, loss[loss=0.1477, simple_loss=0.2333, pruned_loss=0.03106, over 7237.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2551, pruned_loss=0.03769, over 1234092.56 frames.], batch size: 16, lr: 4.37e-04
+2022-05-14 21:26:06,631 INFO [train.py:812] (7/8) Epoch 18, batch 450, loss[loss=0.1644, simple_loss=0.2606, pruned_loss=0.03413, over 7216.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2559, pruned_loss=0.03794, over 1276966.24 frames.], batch size: 22, lr: 4.36e-04
+2022-05-14 21:27:06,299 INFO [train.py:812] (7/8) Epoch 18, batch 500, loss[loss=0.174, simple_loss=0.2696, pruned_loss=0.03914, over 7335.00 frames.], tot_loss[loss=0.1662, simple_loss=0.256, pruned_loss=0.03818, over 1313474.70 frames.], batch size: 22, lr: 4.36e-04
+2022-05-14 21:28:04,646 INFO [train.py:812] (7/8) Epoch 18, batch 550, loss[loss=0.1677, simple_loss=0.2534, pruned_loss=0.04096, over 7139.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2553, pruned_loss=0.03793, over 1340350.72 frames.], batch size: 17, lr: 4.36e-04
+2022-05-14 21:29:02,279 INFO [train.py:812] (7/8) Epoch 18, batch 600, loss[loss=0.1493, simple_loss=0.2478, pruned_loss=0.02536, over 6408.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2563, pruned_loss=0.03838, over 1356937.45 frames.], batch size: 37, lr: 4.36e-04
+2022-05-14 21:30:01,263 INFO [train.py:812] (7/8) Epoch 18, batch 650, loss[loss=0.1757, simple_loss=0.2636, pruned_loss=0.04394, over 5403.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2563, pruned_loss=0.0384, over 1370010.86 frames.], batch size: 52, lr: 4.36e-04
+2022-05-14 21:30:59,643 INFO [train.py:812] (7/8) Epoch 18, batch 700, loss[loss=0.1618, simple_loss=0.2569, pruned_loss=0.03341, over 7311.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2552, pruned_loss=0.03795, over 1380987.22 frames.], batch size: 21, lr: 4.36e-04
+2022-05-14 21:31:59,641 INFO [train.py:812] (7/8) Epoch 18, batch 750, loss[loss=0.1257, simple_loss=0.2081, pruned_loss=0.02162, over 7417.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2537, pruned_loss=0.03763, over 1391324.76 frames.], batch size: 18, lr: 4.36e-04
+2022-05-14 21:32:57,592 INFO [train.py:812] (7/8) Epoch 18, batch 800, loss[loss=0.1788, simple_loss=0.2702, pruned_loss=0.0437, over 7315.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2544, pruned_loss=0.03775, over 1403573.90 frames.], batch size: 21, lr: 4.36e-04
+2022-05-14 21:33:57,276 INFO [train.py:812] (7/8) Epoch 18, batch 850, loss[loss=0.149, simple_loss=0.2567, pruned_loss=0.02064, over 7420.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2534, pruned_loss=0.037, over 1407178.79 frames.], batch size: 21, lr: 4.35e-04
+2022-05-14 21:34:56,193 INFO [train.py:812] (7/8) Epoch 18, batch 900, loss[loss=0.186, simple_loss=0.2723, pruned_loss=0.04985, over 7197.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2559, pruned_loss=0.03796, over 1406369.46 frames.], batch size: 22, lr: 4.35e-04
+2022-05-14 21:35:54,626 INFO [train.py:812] (7/8) Epoch 18, batch 950, loss[loss=0.1576, simple_loss=0.2532, pruned_loss=0.03099, over 7253.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2558, pruned_loss=0.03786, over 1409716.29 frames.], batch size: 19, lr: 4.35e-04
+2022-05-14 21:36:52,284 INFO [train.py:812] (7/8) Epoch 18, batch 1000, loss[loss=0.199, simple_loss=0.2882, pruned_loss=0.05492, over 7289.00 frames.], tot_loss[loss=0.1648, simple_loss=0.255, pruned_loss=0.03733, over 1415143.93 frames.], batch size: 24, lr: 4.35e-04
+2022-05-14 21:37:51,934 INFO [train.py:812] (7/8) Epoch 18, batch 1050, loss[loss=0.1505, simple_loss=0.2239, pruned_loss=0.03849, over 7286.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2546, pruned_loss=0.03756, over 1418233.60 frames.], batch size: 17, lr: 4.35e-04
+2022-05-14 21:38:50,501 INFO [train.py:812] (7/8) Epoch 18, batch 1100, loss[loss=0.1724, simple_loss=0.2739, pruned_loss=0.0354, over 7265.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2552, pruned_loss=0.03768, over 1421204.68 frames.], batch size: 25, lr: 4.35e-04
+2022-05-14 21:39:48,109 INFO [train.py:812] (7/8) Epoch 18, batch 1150, loss[loss=0.1697, simple_loss=0.2572, pruned_loss=0.04112, over 7381.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2556, pruned_loss=0.03815, over 1419264.21 frames.], batch size: 23, lr: 4.35e-04
+2022-05-14 21:40:45,363 INFO [train.py:812] (7/8) Epoch 18, batch 1200, loss[loss=0.1842, simple_loss=0.2673, pruned_loss=0.0506, over 7285.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2549, pruned_loss=0.03813, over 1416023.18 frames.], batch size: 18, lr: 4.34e-04
+2022-05-14 21:41:44,627 INFO [train.py:812] (7/8) Epoch 18, batch 1250, loss[loss=0.1596, simple_loss=0.2548, pruned_loss=0.03217, over 7401.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2542, pruned_loss=0.03777, over 1418681.93 frames.], batch size: 21, lr: 4.34e-04
+2022-05-14 21:42:42,185 INFO [train.py:812] (7/8) Epoch 18, batch 1300, loss[loss=0.1898, simple_loss=0.2813, pruned_loss=0.04912, over 7180.00 frames.], tot_loss[loss=0.165, simple_loss=0.2541, pruned_loss=0.03792, over 1420160.20 frames.], batch size: 26, lr: 4.34e-04
+2022-05-14 21:43:41,345 INFO [train.py:812] (7/8) Epoch 18, batch 1350, loss[loss=0.1432, simple_loss=0.2168, pruned_loss=0.03478, over 6996.00 frames.], tot_loss[loss=0.165, simple_loss=0.2543, pruned_loss=0.03782, over 1422267.16 frames.], batch size: 16, lr: 4.34e-04
+2022-05-14 21:44:39,606 INFO [train.py:812] (7/8) Epoch 18, batch 1400, loss[loss=0.1711, simple_loss=0.2721, pruned_loss=0.03503, over 7116.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2555, pruned_loss=0.03782, over 1424096.42 frames.], batch size: 21, lr: 4.34e-04
+2022-05-14 21:45:38,221 INFO [train.py:812] (7/8) Epoch 18, batch 1450, loss[loss=0.1794, simple_loss=0.2724, pruned_loss=0.04317, over 7146.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2553, pruned_loss=0.0377, over 1422098.99 frames.], batch size: 20, lr: 4.34e-04
+2022-05-14 21:46:36,927 INFO [train.py:812] (7/8) Epoch 18, batch 1500, loss[loss=0.1813, simple_loss=0.281, pruned_loss=0.04085, over 7304.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2555, pruned_loss=0.03783, over 1413731.76 frames.], batch size: 25, lr: 4.34e-04
+2022-05-14 21:47:35,848 INFO [train.py:812] (7/8) Epoch 18, batch 1550, loss[loss=0.1723, simple_loss=0.2518, pruned_loss=0.04636, over 7156.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2548, pruned_loss=0.03742, over 1421075.11 frames.], batch size: 19, lr: 4.33e-04
+2022-05-14 21:48:33,698 INFO [train.py:812] (7/8) Epoch 18, batch 1600, loss[loss=0.1526, simple_loss=0.2359, pruned_loss=0.03463, over 7448.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2543, pruned_loss=0.03695, over 1421911.69 frames.], batch size: 20, lr: 4.33e-04
+2022-05-14 21:49:33,296 INFO [train.py:812] (7/8) Epoch 18, batch 1650, loss[loss=0.1511, simple_loss=0.2374, pruned_loss=0.03247, over 7283.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2546, pruned_loss=0.03727, over 1421708.73 frames.], batch size: 17, lr: 4.33e-04
+2022-05-14 21:50:30,822 INFO [train.py:812] (7/8) Epoch 18, batch 1700, loss[loss=0.1332, simple_loss=0.2248, pruned_loss=0.02083, over 7370.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2537, pruned_loss=0.03677, over 1425161.15 frames.], batch size: 19, lr: 4.33e-04
+2022-05-14 21:51:29,649 INFO [train.py:812] (7/8) Epoch 18, batch 1750, loss[loss=0.1614, simple_loss=0.2552, pruned_loss=0.03382, over 7319.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2542, pruned_loss=0.03748, over 1425002.81 frames.], batch size: 21, lr: 4.33e-04
+2022-05-14 21:52:27,498 INFO [train.py:812] (7/8) Epoch 18, batch 1800, loss[loss=0.1429, simple_loss=0.2421, pruned_loss=0.02181, over 7246.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2538, pruned_loss=0.03731, over 1428356.90 frames.], batch size: 20, lr: 4.33e-04
+2022-05-14 21:53:27,333 INFO [train.py:812] (7/8) Epoch 18, batch 1850, loss[loss=0.1672, simple_loss=0.2649, pruned_loss=0.03476, over 5307.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2527, pruned_loss=0.03696, over 1426741.40 frames.], batch size: 53, lr: 4.33e-04
+2022-05-14 21:54:25,920 INFO [train.py:812] (7/8) Epoch 18, batch 1900, loss[loss=0.1646, simple_loss=0.2651, pruned_loss=0.03205, over 7320.00 frames.], tot_loss[loss=0.165, simple_loss=0.2549, pruned_loss=0.03756, over 1427261.60 frames.], batch size: 21, lr: 4.33e-04
+2022-05-14 21:55:25,290 INFO [train.py:812] (7/8) Epoch 18, batch 1950, loss[loss=0.1728, simple_loss=0.2608, pruned_loss=0.04244, over 7326.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2563, pruned_loss=0.03818, over 1424241.52 frames.], batch size: 21, lr: 4.32e-04
+2022-05-14 21:56:23,586 INFO [train.py:812] (7/8) Epoch 18, batch 2000, loss[loss=0.1874, simple_loss=0.2767, pruned_loss=0.04899, over 4914.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2553, pruned_loss=0.0379, over 1424672.89 frames.], batch size: 53, lr: 4.32e-04
+2022-05-14 21:57:27,203 INFO [train.py:812] (7/8) Epoch 18, batch 2050, loss[loss=0.1571, simple_loss=0.2491, pruned_loss=0.03259, over 7117.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2555, pruned_loss=0.03809, over 1420415.15 frames.], batch size: 21, lr: 4.32e-04
+2022-05-14 21:58:25,561 INFO [train.py:812] (7/8) Epoch 18, batch 2100, loss[loss=0.2189, simple_loss=0.2973, pruned_loss=0.07027, over 6809.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2558, pruned_loss=0.03829, over 1416229.70 frames.], batch size: 31, lr: 4.32e-04
+2022-05-14 21:59:24,631 INFO [train.py:812] (7/8) Epoch 18, batch 2150, loss[loss=0.1794, simple_loss=0.2795, pruned_loss=0.03964, over 7217.00 frames.], tot_loss[loss=0.166, simple_loss=0.2558, pruned_loss=0.03811, over 1418359.14 frames.], batch size: 21, lr: 4.32e-04
+2022-05-14 22:00:22,644 INFO [train.py:812] (7/8) Epoch 18, batch 2200, loss[loss=0.161, simple_loss=0.2449, pruned_loss=0.03851, over 6809.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2548, pruned_loss=0.03768, over 1421094.04 frames.], batch size: 15, lr: 4.32e-04
+2022-05-14 22:01:22,015 INFO [train.py:812] (7/8) Epoch 18, batch 2250, loss[loss=0.1653, simple_loss=0.2541, pruned_loss=0.0382, over 7010.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2549, pruned_loss=0.03801, over 1424468.14 frames.], batch size: 16, lr: 4.32e-04
+2022-05-14 22:02:21,518 INFO [train.py:812] (7/8) Epoch 18, batch 2300, loss[loss=0.1886, simple_loss=0.276, pruned_loss=0.05055, over 7142.00 frames.], tot_loss[loss=0.166, simple_loss=0.2556, pruned_loss=0.03816, over 1427312.75 frames.], batch size: 20, lr: 4.31e-04
+2022-05-14 22:03:21,234 INFO [train.py:812] (7/8) Epoch 18, batch 2350, loss[loss=0.1891, simple_loss=0.2962, pruned_loss=0.04103, over 7175.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2546, pruned_loss=0.03787, over 1426786.32 frames.], batch size: 26, lr: 4.31e-04
+2022-05-14 22:04:20,419 INFO [train.py:812] (7/8) Epoch 18, batch 2400, loss[loss=0.1665, simple_loss=0.2644, pruned_loss=0.03425, over 6330.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2548, pruned_loss=0.038, over 1425095.69 frames.], batch size: 38, lr: 4.31e-04
+2022-05-14 22:05:18,796 INFO [train.py:812] (7/8) Epoch 18, batch 2450, loss[loss=0.1491, simple_loss=0.2355, pruned_loss=0.0313, over 7159.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2545, pruned_loss=0.03785, over 1426665.11 frames.], batch size: 19, lr: 4.31e-04
+2022-05-14 22:06:16,660 INFO [train.py:812] (7/8) Epoch 18, batch 2500, loss[loss=0.1806, simple_loss=0.2806, pruned_loss=0.04028, over 7126.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2563, pruned_loss=0.03845, over 1418364.76 frames.], batch size: 21, lr: 4.31e-04
+2022-05-14 22:07:15,294 INFO [train.py:812] (7/8) Epoch 18, batch 2550, loss[loss=0.1612, simple_loss=0.2649, pruned_loss=0.0288, over 7311.00 frames.], tot_loss[loss=0.166, simple_loss=0.2556, pruned_loss=0.03822, over 1418712.21 frames.], batch size: 21, lr: 4.31e-04
+2022-05-14 22:08:14,583 INFO [train.py:812] (7/8) Epoch 18, batch 2600, loss[loss=0.1438, simple_loss=0.227, pruned_loss=0.03029, over 6809.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2555, pruned_loss=0.03812, over 1418137.35 frames.], batch size: 15, lr: 4.31e-04
+2022-05-14 22:09:14,565 INFO [train.py:812] (7/8) Epoch 18, batch 2650, loss[loss=0.1593, simple_loss=0.2448, pruned_loss=0.0369, over 7363.00 frames.], tot_loss[loss=0.1653, simple_loss=0.255, pruned_loss=0.03779, over 1419542.76 frames.], batch size: 19, lr: 4.31e-04
+2022-05-14 22:10:13,369 INFO [train.py:812] (7/8) Epoch 18, batch 2700, loss[loss=0.1399, simple_loss=0.228, pruned_loss=0.02592, over 7289.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2545, pruned_loss=0.03794, over 1418801.84 frames.], batch size: 18, lr: 4.30e-04
+2022-05-14 22:11:12,920 INFO [train.py:812] (7/8) Epoch 18, batch 2750, loss[loss=0.1426, simple_loss=0.2394, pruned_loss=0.02285, over 7147.00 frames.], tot_loss[loss=0.1646, simple_loss=0.254, pruned_loss=0.03759, over 1416974.89 frames.], batch size: 20, lr: 4.30e-04
+2022-05-14 22:12:10,449 INFO [train.py:812] (7/8) Epoch 18, batch 2800, loss[loss=0.1518, simple_loss=0.2421, pruned_loss=0.03078, over 7319.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2534, pruned_loss=0.03753, over 1416338.57 frames.], batch size: 21, lr: 4.30e-04
+2022-05-14 22:13:09,227 INFO [train.py:812] (7/8) Epoch 18, batch 2850, loss[loss=0.1676, simple_loss=0.253, pruned_loss=0.04111, over 7300.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2546, pruned_loss=0.03791, over 1418841.52 frames.], batch size: 25, lr: 4.30e-04
+2022-05-14 22:14:17,898 INFO [train.py:812] (7/8) Epoch 18, batch 2900, loss[loss=0.2005, simple_loss=0.286, pruned_loss=0.0575, over 7185.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2552, pruned_loss=0.03829, over 1422231.19 frames.], batch size: 22, lr: 4.30e-04
+2022-05-14 22:15:17,299 INFO [train.py:812] (7/8) Epoch 18, batch 2950, loss[loss=0.1807, simple_loss=0.2772, pruned_loss=0.04205, over 6254.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2553, pruned_loss=0.03825, over 1418410.24 frames.], batch size: 37, lr: 4.30e-04
+2022-05-14 22:16:16,225 INFO [train.py:812] (7/8) Epoch 18, batch 3000, loss[loss=0.1941, simple_loss=0.2754, pruned_loss=0.05645, over 7299.00 frames.], tot_loss[loss=0.166, simple_loss=0.2555, pruned_loss=0.03831, over 1417077.62 frames.], batch size: 25, lr: 4.30e-04
+2022-05-14 22:16:16,226 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 22:16:23,834 INFO [train.py:841] (7/8) Epoch 18, validation: loss=0.153, simple_loss=0.2523, pruned_loss=0.02686, over 698248.00 frames.
+2022-05-14 22:17:22,929 INFO [train.py:812] (7/8) Epoch 18, batch 3050, loss[loss=0.194, simple_loss=0.2891, pruned_loss=0.04949, over 7101.00 frames.], tot_loss[loss=0.166, simple_loss=0.255, pruned_loss=0.03852, over 1416847.12 frames.], batch size: 21, lr: 4.29e-04
+2022-05-14 22:18:21,096 INFO [train.py:812] (7/8) Epoch 18, batch 3100, loss[loss=0.1661, simple_loss=0.2671, pruned_loss=0.03255, over 7234.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2552, pruned_loss=0.03866, over 1417295.37 frames.], batch size: 20, lr: 4.29e-04
+2022-05-14 22:19:19,590 INFO [train.py:812] (7/8) Epoch 18, batch 3150, loss[loss=0.1618, simple_loss=0.2589, pruned_loss=0.03236, over 7272.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2548, pruned_loss=0.03841, over 1420927.88 frames.], batch size: 19, lr: 4.29e-04
+2022-05-14 22:20:18,629 INFO [train.py:812] (7/8) Epoch 18, batch 3200, loss[loss=0.2005, simple_loss=0.2853, pruned_loss=0.05791, over 6964.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2547, pruned_loss=0.03838, over 1419020.59 frames.], batch size: 32, lr: 4.29e-04
+2022-05-14 22:21:17,388 INFO [train.py:812] (7/8) Epoch 18, batch 3250, loss[loss=0.1574, simple_loss=0.2535, pruned_loss=0.0306, over 7393.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2546, pruned_loss=0.03855, over 1421901.65 frames.], batch size: 23, lr: 4.29e-04
+2022-05-14 22:22:16,113 INFO [train.py:812] (7/8) Epoch 18, batch 3300, loss[loss=0.1441, simple_loss=0.232, pruned_loss=0.02811, over 7162.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2547, pruned_loss=0.03869, over 1426485.22 frames.], batch size: 18, lr: 4.29e-04
+2022-05-14 22:23:15,295 INFO [train.py:812] (7/8) Epoch 18, batch 3350, loss[loss=0.1533, simple_loss=0.2324, pruned_loss=0.03707, over 7417.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2549, pruned_loss=0.03834, over 1426170.83 frames.], batch size: 18, lr: 4.29e-04
+2022-05-14 22:24:13,581 INFO [train.py:812] (7/8) Epoch 18, batch 3400, loss[loss=0.1666, simple_loss=0.2617, pruned_loss=0.03577, over 7379.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2552, pruned_loss=0.03824, over 1429943.31 frames.], batch size: 23, lr: 4.29e-04
+2022-05-14 22:25:13,438 INFO [train.py:812] (7/8) Epoch 18, batch 3450, loss[loss=0.1415, simple_loss=0.2267, pruned_loss=0.02813, over 7403.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2555, pruned_loss=0.03781, over 1430490.59 frames.], batch size: 18, lr: 4.28e-04
+2022-05-14 22:26:12,127 INFO [train.py:812] (7/8) Epoch 18, batch 3500, loss[loss=0.1912, simple_loss=0.2749, pruned_loss=0.05382, over 6315.00 frames.], tot_loss[loss=0.1652, simple_loss=0.255, pruned_loss=0.03766, over 1432684.09 frames.], batch size: 37, lr: 4.28e-04
+2022-05-14 22:27:09,623 INFO [train.py:812] (7/8) Epoch 18, batch 3550, loss[loss=0.1846, simple_loss=0.2672, pruned_loss=0.05099, over 7194.00 frames.], tot_loss[loss=0.165, simple_loss=0.2546, pruned_loss=0.03768, over 1430887.58 frames.], batch size: 23, lr: 4.28e-04
+2022-05-14 22:28:09,195 INFO [train.py:812] (7/8) Epoch 18, batch 3600, loss[loss=0.1811, simple_loss=0.2671, pruned_loss=0.04751, over 7218.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2541, pruned_loss=0.03748, over 1431821.36 frames.], batch size: 21, lr: 4.28e-04
+2022-05-14 22:29:08,023 INFO [train.py:812] (7/8) Epoch 18, batch 3650, loss[loss=0.178, simple_loss=0.2715, pruned_loss=0.04222, over 7319.00 frames.], tot_loss[loss=0.165, simple_loss=0.2543, pruned_loss=0.03789, over 1423232.11 frames.], batch size: 22, lr: 4.28e-04
+2022-05-14 22:30:06,393 INFO [train.py:812] (7/8) Epoch 18, batch 3700, loss[loss=0.1386, simple_loss=0.2205, pruned_loss=0.02835, over 6993.00 frames.], tot_loss[loss=0.166, simple_loss=0.2554, pruned_loss=0.03825, over 1424365.74 frames.], batch size: 16, lr: 4.28e-04
+2022-05-14 22:31:03,731 INFO [train.py:812] (7/8) Epoch 18, batch 3750, loss[loss=0.1866, simple_loss=0.275, pruned_loss=0.04912, over 7323.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2559, pruned_loss=0.03816, over 1426639.19 frames.], batch size: 25, lr: 4.28e-04
+2022-05-14 22:32:02,202 INFO [train.py:812] (7/8) Epoch 18, batch 3800, loss[loss=0.1738, simple_loss=0.2708, pruned_loss=0.03838, over 7351.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2549, pruned_loss=0.0377, over 1426743.01 frames.], batch size: 19, lr: 4.28e-04
+2022-05-14 22:33:01,957 INFO [train.py:812] (7/8) Epoch 18, batch 3850, loss[loss=0.1619, simple_loss=0.254, pruned_loss=0.03488, over 7400.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2542, pruned_loss=0.03738, over 1424964.31 frames.], batch size: 18, lr: 4.27e-04
+2022-05-14 22:34:01,005 INFO [train.py:812] (7/8) Epoch 18, batch 3900, loss[loss=0.1634, simple_loss=0.2548, pruned_loss=0.03599, over 7117.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2547, pruned_loss=0.03779, over 1421303.02 frames.], batch size: 21, lr: 4.27e-04
+2022-05-14 22:35:00,697 INFO [train.py:812] (7/8) Epoch 18, batch 3950, loss[loss=0.1542, simple_loss=0.2506, pruned_loss=0.0289, over 7044.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2548, pruned_loss=0.03789, over 1422710.27 frames.], batch size: 28, lr: 4.27e-04
+2022-05-14 22:35:58,157 INFO [train.py:812] (7/8) Epoch 18, batch 4000, loss[loss=0.152, simple_loss=0.2236, pruned_loss=0.04023, over 7209.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2551, pruned_loss=0.03827, over 1423806.23 frames.], batch size: 16, lr: 4.27e-04
+2022-05-14 22:36:56,555 INFO [train.py:812] (7/8) Epoch 18, batch 4050, loss[loss=0.1803, simple_loss=0.2574, pruned_loss=0.05158, over 7050.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2561, pruned_loss=0.03853, over 1426962.80 frames.], batch size: 28, lr: 4.27e-04
+2022-05-14 22:37:55,358 INFO [train.py:812] (7/8) Epoch 18, batch 4100, loss[loss=0.1872, simple_loss=0.2641, pruned_loss=0.05513, over 7149.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2554, pruned_loss=0.03879, over 1423777.03 frames.], batch size: 20, lr: 4.27e-04
+2022-05-14 22:38:54,586 INFO [train.py:812] (7/8) Epoch 18, batch 4150, loss[loss=0.1442, simple_loss=0.2425, pruned_loss=0.02294, over 7327.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2556, pruned_loss=0.03894, over 1422938.92 frames.], batch size: 20, lr: 4.27e-04
+2022-05-14 22:39:53,795 INFO [train.py:812] (7/8) Epoch 18, batch 4200, loss[loss=0.146, simple_loss=0.2331, pruned_loss=0.02941, over 6997.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2538, pruned_loss=0.03834, over 1422199.44 frames.], batch size: 16, lr: 4.26e-04
+2022-05-14 22:40:53,087 INFO [train.py:812] (7/8) Epoch 18, batch 4250, loss[loss=0.1734, simple_loss=0.2658, pruned_loss=0.04054, over 6761.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2535, pruned_loss=0.03835, over 1417453.72 frames.], batch size: 31, lr: 4.26e-04
+2022-05-14 22:41:52,069 INFO [train.py:812] (7/8) Epoch 18, batch 4300, loss[loss=0.1406, simple_loss=0.2322, pruned_loss=0.02456, over 6997.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2521, pruned_loss=0.03753, over 1418756.99 frames.], batch size: 16, lr: 4.26e-04
+2022-05-14 22:42:51,549 INFO [train.py:812] (7/8) Epoch 18, batch 4350, loss[loss=0.1801, simple_loss=0.274, pruned_loss=0.04307, over 7225.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2522, pruned_loss=0.03773, over 1407216.40 frames.], batch size: 21, lr: 4.26e-04
+2022-05-14 22:43:50,357 INFO [train.py:812] (7/8) Epoch 18, batch 4400, loss[loss=0.1554, simple_loss=0.2426, pruned_loss=0.03405, over 7068.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2542, pruned_loss=0.03858, over 1401292.59 frames.], batch size: 18, lr: 4.26e-04
+2022-05-14 22:44:47,973 INFO [train.py:812] (7/8) Epoch 18, batch 4450, loss[loss=0.1509, simple_loss=0.2467, pruned_loss=0.02758, over 6503.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2555, pruned_loss=0.03916, over 1392615.84 frames.], batch size: 38, lr: 4.26e-04
+2022-05-14 22:45:55,881 INFO [train.py:812] (7/8) Epoch 18, batch 4500, loss[loss=0.1489, simple_loss=0.2336, pruned_loss=0.03214, over 6991.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2564, pruned_loss=0.03948, over 1379733.02 frames.], batch size: 16, lr: 4.26e-04
+2022-05-14 22:46:55,074 INFO [train.py:812] (7/8) Epoch 18, batch 4550, loss[loss=0.178, simple_loss=0.2739, pruned_loss=0.04104, over 7145.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2558, pruned_loss=0.0395, over 1370320.08 frames.], batch size: 19, lr: 4.26e-04
+2022-05-14 22:48:10,104 INFO [train.py:812] (7/8) Epoch 19, batch 0, loss[loss=0.171, simple_loss=0.2618, pruned_loss=0.04013, over 7287.00 frames.], tot_loss[loss=0.171, simple_loss=0.2618, pruned_loss=0.04013, over 7287.00 frames.], batch size: 25, lr: 4.15e-04
+2022-05-14 22:49:27,413 INFO [train.py:812] (7/8) Epoch 19, batch 50, loss[loss=0.1627, simple_loss=0.2593, pruned_loss=0.03303, over 7320.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2553, pruned_loss=0.03842, over 325007.96 frames.], batch size: 22, lr: 4.15e-04
+2022-05-14 22:50:35,577 INFO [train.py:812] (7/8) Epoch 19, batch 100, loss[loss=0.1704, simple_loss=0.2543, pruned_loss=0.04321, over 7345.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2542, pruned_loss=0.03804, over 574680.30 frames.], batch size: 22, lr: 4.14e-04
+2022-05-14 22:51:34,817 INFO [train.py:812] (7/8) Epoch 19, batch 150, loss[loss=0.1766, simple_loss=0.27, pruned_loss=0.04153, over 7218.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2534, pruned_loss=0.03751, over 763989.09 frames.], batch size: 21, lr: 4.14e-04
+2022-05-14 22:53:02,407 INFO [train.py:812] (7/8) Epoch 19, batch 200, loss[loss=0.157, simple_loss=0.2307, pruned_loss=0.04166, over 7267.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2534, pruned_loss=0.03706, over 909158.44 frames.], batch size: 17, lr: 4.14e-04
+2022-05-14 22:54:01,892 INFO [train.py:812] (7/8) Epoch 19, batch 250, loss[loss=0.161, simple_loss=0.2517, pruned_loss=0.0352, over 6737.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2534, pruned_loss=0.03714, over 1025630.85 frames.], batch size: 31, lr: 4.14e-04
+2022-05-14 22:55:01,107 INFO [train.py:812] (7/8) Epoch 19, batch 300, loss[loss=0.1549, simple_loss=0.2514, pruned_loss=0.02927, over 7234.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2537, pruned_loss=0.0377, over 1115356.16 frames.], batch size: 20, lr: 4.14e-04
+2022-05-14 22:56:01,001 INFO [train.py:812] (7/8) Epoch 19, batch 350, loss[loss=0.1611, simple_loss=0.2469, pruned_loss=0.03765, over 6702.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2523, pruned_loss=0.03711, over 1181892.35 frames.], batch size: 31, lr: 4.14e-04
+2022-05-14 22:56:59,198 INFO [train.py:812] (7/8) Epoch 19, batch 400, loss[loss=0.1468, simple_loss=0.2309, pruned_loss=0.03137, over 7064.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2537, pruned_loss=0.0375, over 1234076.38 frames.], batch size: 18, lr: 4.14e-04
+2022-05-14 22:57:58,736 INFO [train.py:812] (7/8) Epoch 19, batch 450, loss[loss=0.1415, simple_loss=0.2291, pruned_loss=0.02697, over 7328.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2539, pruned_loss=0.03738, over 1275700.75 frames.], batch size: 22, lr: 4.14e-04
+2022-05-14 22:58:57,698 INFO [train.py:812] (7/8) Epoch 19, batch 500, loss[loss=0.1543, simple_loss=0.2297, pruned_loss=0.03944, over 7133.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2552, pruned_loss=0.03775, over 1307059.29 frames.], batch size: 17, lr: 4.13e-04
+2022-05-14 22:59:57,508 INFO [train.py:812] (7/8) Epoch 19, batch 550, loss[loss=0.1778, simple_loss=0.2494, pruned_loss=0.05305, over 7292.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2546, pruned_loss=0.03723, over 1336193.14 frames.], batch size: 17, lr: 4.13e-04
+2022-05-14 23:00:56,167 INFO [train.py:812] (7/8) Epoch 19, batch 600, loss[loss=0.1407, simple_loss=0.226, pruned_loss=0.02768, over 7289.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2547, pruned_loss=0.03748, over 1357258.19 frames.], batch size: 18, lr: 4.13e-04
+2022-05-14 23:01:55,605 INFO [train.py:812] (7/8) Epoch 19, batch 650, loss[loss=0.1658, simple_loss=0.2559, pruned_loss=0.03785, over 7108.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2535, pruned_loss=0.03685, over 1376815.09 frames.], batch size: 21, lr: 4.13e-04
+2022-05-14 23:02:54,283 INFO [train.py:812] (7/8) Epoch 19, batch 700, loss[loss=0.2365, simple_loss=0.3019, pruned_loss=0.08555, over 4755.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2538, pruned_loss=0.03701, over 1386509.10 frames.], batch size: 52, lr: 4.13e-04
+2022-05-14 23:03:53,365 INFO [train.py:812] (7/8) Epoch 19, batch 750, loss[loss=0.1484, simple_loss=0.2459, pruned_loss=0.02542, over 7154.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2536, pruned_loss=0.03673, over 1394481.57 frames.], batch size: 19, lr: 4.13e-04
+2022-05-14 23:04:52,321 INFO [train.py:812] (7/8) Epoch 19, batch 800, loss[loss=0.1604, simple_loss=0.2542, pruned_loss=0.0333, over 6703.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2543, pruned_loss=0.03696, over 1396918.83 frames.], batch size: 31, lr: 4.13e-04
+2022-05-14 23:05:50,887 INFO [train.py:812] (7/8) Epoch 19, batch 850, loss[loss=0.1499, simple_loss=0.24, pruned_loss=0.02992, over 7072.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2543, pruned_loss=0.03694, over 1404471.81 frames.], batch size: 18, lr: 4.13e-04
+2022-05-14 23:06:49,952 INFO [train.py:812] (7/8) Epoch 19, batch 900, loss[loss=0.1344, simple_loss=0.2185, pruned_loss=0.02517, over 6797.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2553, pruned_loss=0.03722, over 1409638.63 frames.], batch size: 15, lr: 4.12e-04
+2022-05-14 23:07:49,385 INFO [train.py:812] (7/8) Epoch 19, batch 950, loss[loss=0.1862, simple_loss=0.2732, pruned_loss=0.04955, over 7384.00 frames.], tot_loss[loss=0.164, simple_loss=0.2543, pruned_loss=0.03688, over 1412469.19 frames.], batch size: 23, lr: 4.12e-04
+2022-05-14 23:08:48,652 INFO [train.py:812] (7/8) Epoch 19, batch 1000, loss[loss=0.1387, simple_loss=0.2442, pruned_loss=0.01659, over 7140.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2548, pruned_loss=0.03702, over 1420140.70 frames.], batch size: 20, lr: 4.12e-04
+2022-05-14 23:09:47,752 INFO [train.py:812] (7/8) Epoch 19, batch 1050, loss[loss=0.1776, simple_loss=0.2674, pruned_loss=0.0439, over 7262.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2546, pruned_loss=0.03755, over 1418905.10 frames.], batch size: 25, lr: 4.12e-04
+2022-05-14 23:10:45,919 INFO [train.py:812] (7/8) Epoch 19, batch 1100, loss[loss=0.1536, simple_loss=0.2485, pruned_loss=0.02936, over 7322.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2532, pruned_loss=0.03686, over 1420216.86 frames.], batch size: 20, lr: 4.12e-04
+2022-05-14 23:11:43,641 INFO [train.py:812] (7/8) Epoch 19, batch 1150, loss[loss=0.1979, simple_loss=0.2844, pruned_loss=0.05576, over 7309.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2538, pruned_loss=0.0369, over 1420242.60 frames.], batch size: 24, lr: 4.12e-04
+2022-05-14 23:12:42,341 INFO [train.py:812] (7/8) Epoch 19, batch 1200, loss[loss=0.222, simple_loss=0.293, pruned_loss=0.07551, over 4943.00 frames.], tot_loss[loss=0.164, simple_loss=0.2535, pruned_loss=0.03725, over 1413604.69 frames.], batch size: 52, lr: 4.12e-04
+2022-05-14 23:13:40,395 INFO [train.py:812] (7/8) Epoch 19, batch 1250, loss[loss=0.1611, simple_loss=0.2578, pruned_loss=0.0322, over 7119.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2543, pruned_loss=0.03755, over 1413964.69 frames.], batch size: 21, lr: 4.12e-04
+2022-05-14 23:14:39,590 INFO [train.py:812] (7/8) Epoch 19, batch 1300, loss[loss=0.1577, simple_loss=0.2505, pruned_loss=0.03242, over 7171.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2552, pruned_loss=0.03768, over 1413560.74 frames.], batch size: 19, lr: 4.12e-04
+2022-05-14 23:15:38,808 INFO [train.py:812] (7/8) Epoch 19, batch 1350, loss[loss=0.1802, simple_loss=0.2678, pruned_loss=0.04634, over 7062.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2558, pruned_loss=0.03797, over 1411885.59 frames.], batch size: 28, lr: 4.11e-04
+2022-05-14 23:16:38,091 INFO [train.py:812] (7/8) Epoch 19, batch 1400, loss[loss=0.1586, simple_loss=0.2525, pruned_loss=0.0324, over 7454.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2551, pruned_loss=0.03787, over 1410512.89 frames.], batch size: 19, lr: 4.11e-04
+2022-05-14 23:17:42,376 INFO [train.py:812] (7/8) Epoch 19, batch 1450, loss[loss=0.1889, simple_loss=0.2789, pruned_loss=0.04949, over 7325.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2542, pruned_loss=0.03727, over 1417774.47 frames.], batch size: 21, lr: 4.11e-04
+2022-05-14 23:18:41,313 INFO [train.py:812] (7/8) Epoch 19, batch 1500, loss[loss=0.1662, simple_loss=0.2473, pruned_loss=0.04259, over 7264.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2547, pruned_loss=0.03732, over 1421638.63 frames.], batch size: 19, lr: 4.11e-04
+2022-05-14 23:19:40,464 INFO [train.py:812] (7/8) Epoch 19, batch 1550, loss[loss=0.1467, simple_loss=0.2519, pruned_loss=0.0208, over 7415.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2545, pruned_loss=0.0372, over 1425132.92 frames.], batch size: 21, lr: 4.11e-04
+2022-05-14 23:20:39,996 INFO [train.py:812] (7/8) Epoch 19, batch 1600, loss[loss=0.1748, simple_loss=0.2615, pruned_loss=0.04401, over 7205.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2536, pruned_loss=0.03676, over 1423446.74 frames.], batch size: 22, lr: 4.11e-04
+2022-05-14 23:21:39,540 INFO [train.py:812] (7/8) Epoch 19, batch 1650, loss[loss=0.1407, simple_loss=0.2303, pruned_loss=0.02558, over 7166.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2535, pruned_loss=0.03666, over 1422016.40 frames.], batch size: 18, lr: 4.11e-04
+2022-05-14 23:22:38,879 INFO [train.py:812] (7/8) Epoch 19, batch 1700, loss[loss=0.1698, simple_loss=0.2479, pruned_loss=0.04585, over 7182.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2537, pruned_loss=0.03665, over 1423295.50 frames.], batch size: 18, lr: 4.11e-04
+2022-05-14 23:23:37,813 INFO [train.py:812] (7/8) Epoch 19, batch 1750, loss[loss=0.1587, simple_loss=0.2608, pruned_loss=0.02833, over 7150.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2546, pruned_loss=0.03682, over 1416560.64 frames.], batch size: 20, lr: 4.10e-04
+2022-05-14 23:24:36,375 INFO [train.py:812] (7/8) Epoch 19, batch 1800, loss[loss=0.1562, simple_loss=0.2452, pruned_loss=0.0336, over 7263.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2555, pruned_loss=0.03697, over 1417439.48 frames.], batch size: 19, lr: 4.10e-04
+2022-05-14 23:25:35,731 INFO [train.py:812] (7/8) Epoch 19, batch 1850, loss[loss=0.1842, simple_loss=0.2736, pruned_loss=0.04742, over 7300.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2556, pruned_loss=0.03682, over 1422962.88 frames.], batch size: 24, lr: 4.10e-04
+2022-05-14 23:26:34,591 INFO [train.py:812] (7/8) Epoch 19, batch 1900, loss[loss=0.1653, simple_loss=0.2533, pruned_loss=0.03862, over 6958.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2562, pruned_loss=0.03753, over 1419756.50 frames.], batch size: 28, lr: 4.10e-04
+2022-05-14 23:27:34,109 INFO [train.py:812] (7/8) Epoch 19, batch 1950, loss[loss=0.1398, simple_loss=0.2191, pruned_loss=0.03019, over 6994.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2565, pruned_loss=0.0373, over 1420395.84 frames.], batch size: 16, lr: 4.10e-04
+2022-05-14 23:28:32,917 INFO [train.py:812] (7/8) Epoch 19, batch 2000, loss[loss=0.1836, simple_loss=0.2835, pruned_loss=0.0418, over 7148.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2555, pruned_loss=0.03687, over 1423846.72 frames.], batch size: 20, lr: 4.10e-04
+2022-05-14 23:29:32,698 INFO [train.py:812] (7/8) Epoch 19, batch 2050, loss[loss=0.17, simple_loss=0.2674, pruned_loss=0.03633, over 7300.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2555, pruned_loss=0.03758, over 1423701.49 frames.], batch size: 25, lr: 4.10e-04
+2022-05-14 23:30:30,677 INFO [train.py:812] (7/8) Epoch 19, batch 2100, loss[loss=0.1411, simple_loss=0.2271, pruned_loss=0.02761, over 7159.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2549, pruned_loss=0.03727, over 1424429.04 frames.], batch size: 19, lr: 4.10e-04
+2022-05-14 23:31:30,593 INFO [train.py:812] (7/8) Epoch 19, batch 2150, loss[loss=0.1467, simple_loss=0.2429, pruned_loss=0.02529, over 7219.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2544, pruned_loss=0.03727, over 1422042.99 frames.], batch size: 21, lr: 4.09e-04
+2022-05-14 23:32:29,969 INFO [train.py:812] (7/8) Epoch 19, batch 2200, loss[loss=0.1767, simple_loss=0.2782, pruned_loss=0.03758, over 7119.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2539, pruned_loss=0.03714, over 1425662.95 frames.], batch size: 21, lr: 4.09e-04
+2022-05-14 23:33:29,304 INFO [train.py:812] (7/8) Epoch 19, batch 2250, loss[loss=0.1551, simple_loss=0.2644, pruned_loss=0.02289, over 6475.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2547, pruned_loss=0.03715, over 1423785.00 frames.], batch size: 38, lr: 4.09e-04
+2022-05-14 23:34:27,817 INFO [train.py:812] (7/8) Epoch 19, batch 2300, loss[loss=0.1938, simple_loss=0.2888, pruned_loss=0.04936, over 7376.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2542, pruned_loss=0.03703, over 1425620.99 frames.], batch size: 23, lr: 4.09e-04
+2022-05-14 23:35:25,983 INFO [train.py:812] (7/8) Epoch 19, batch 2350, loss[loss=0.1541, simple_loss=0.2428, pruned_loss=0.03264, over 7283.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2539, pruned_loss=0.03663, over 1422529.97 frames.], batch size: 17, lr: 4.09e-04
+2022-05-14 23:36:25,363 INFO [train.py:812] (7/8) Epoch 19, batch 2400, loss[loss=0.1676, simple_loss=0.26, pruned_loss=0.03757, over 7143.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2545, pruned_loss=0.03687, over 1419025.01 frames.], batch size: 20, lr: 4.09e-04
+2022-05-14 23:37:24,227 INFO [train.py:812] (7/8) Epoch 19, batch 2450, loss[loss=0.1653, simple_loss=0.2512, pruned_loss=0.03969, over 7146.00 frames.], tot_loss[loss=0.164, simple_loss=0.2545, pruned_loss=0.03671, over 1421533.09 frames.], batch size: 20, lr: 4.09e-04
+2022-05-14 23:38:23,536 INFO [train.py:812] (7/8) Epoch 19, batch 2500, loss[loss=0.1809, simple_loss=0.2643, pruned_loss=0.04876, over 7185.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2539, pruned_loss=0.03672, over 1421296.37 frames.], batch size: 26, lr: 4.09e-04
+2022-05-14 23:39:23,004 INFO [train.py:812] (7/8) Epoch 19, batch 2550, loss[loss=0.1818, simple_loss=0.2764, pruned_loss=0.04359, over 7328.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2526, pruned_loss=0.03615, over 1421028.54 frames.], batch size: 24, lr: 4.08e-04
+2022-05-14 23:40:21,766 INFO [train.py:812] (7/8) Epoch 19, batch 2600, loss[loss=0.1424, simple_loss=0.2298, pruned_loss=0.02754, over 7008.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2532, pruned_loss=0.03627, over 1424613.62 frames.], batch size: 16, lr: 4.08e-04
+2022-05-14 23:41:21,040 INFO [train.py:812] (7/8) Epoch 19, batch 2650, loss[loss=0.1799, simple_loss=0.2681, pruned_loss=0.04589, over 7280.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2546, pruned_loss=0.03724, over 1427293.14 frames.], batch size: 24, lr: 4.08e-04
+2022-05-14 23:42:20,858 INFO [train.py:812] (7/8) Epoch 19, batch 2700, loss[loss=0.1628, simple_loss=0.2655, pruned_loss=0.03006, over 7316.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2533, pruned_loss=0.03667, over 1431385.44 frames.], batch size: 25, lr: 4.08e-04
+2022-05-14 23:43:20,369 INFO [train.py:812] (7/8) Epoch 19, batch 2750, loss[loss=0.1746, simple_loss=0.2783, pruned_loss=0.03551, over 7407.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2538, pruned_loss=0.03629, over 1430587.64 frames.], batch size: 21, lr: 4.08e-04
+2022-05-14 23:44:19,833 INFO [train.py:812] (7/8) Epoch 19, batch 2800, loss[loss=0.1577, simple_loss=0.2482, pruned_loss=0.03355, over 7066.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2528, pruned_loss=0.03606, over 1430770.29 frames.], batch size: 18, lr: 4.08e-04
+2022-05-14 23:45:18,650 INFO [train.py:812] (7/8) Epoch 19, batch 2850, loss[loss=0.1677, simple_loss=0.2652, pruned_loss=0.03511, over 7160.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2533, pruned_loss=0.03612, over 1427921.68 frames.], batch size: 19, lr: 4.08e-04
+2022-05-14 23:46:17,175 INFO [train.py:812] (7/8) Epoch 19, batch 2900, loss[loss=0.2023, simple_loss=0.2934, pruned_loss=0.05557, over 7164.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2534, pruned_loss=0.03637, over 1425294.40 frames.], batch size: 26, lr: 4.08e-04
+2022-05-14 23:47:15,897 INFO [train.py:812] (7/8) Epoch 19, batch 2950, loss[loss=0.1357, simple_loss=0.2127, pruned_loss=0.02938, over 7280.00 frames.], tot_loss[loss=0.1627, simple_loss=0.253, pruned_loss=0.03613, over 1431205.06 frames.], batch size: 17, lr: 4.08e-04
+2022-05-14 23:48:15,132 INFO [train.py:812] (7/8) Epoch 19, batch 3000, loss[loss=0.2067, simple_loss=0.285, pruned_loss=0.06418, over 5213.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2525, pruned_loss=0.03603, over 1430800.61 frames.], batch size: 52, lr: 4.07e-04
+2022-05-14 23:48:15,134 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-14 23:48:22,686 INFO [train.py:841] (7/8) Epoch 19, validation: loss=0.1531, simple_loss=0.2523, pruned_loss=0.02694, over 698248.00 frames.
+2022-05-14 23:49:22,413 INFO [train.py:812] (7/8) Epoch 19, batch 3050, loss[loss=0.1786, simple_loss=0.2595, pruned_loss=0.04886, over 7227.00 frames.], tot_loss[loss=0.1625, simple_loss=0.253, pruned_loss=0.03597, over 1431628.25 frames.], batch size: 23, lr: 4.07e-04
+2022-05-14 23:50:21,374 INFO [train.py:812] (7/8) Epoch 19, batch 3100, loss[loss=0.1819, simple_loss=0.2682, pruned_loss=0.04786, over 6535.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2536, pruned_loss=0.03634, over 1432321.56 frames.], batch size: 38, lr: 4.07e-04
+2022-05-14 23:51:20,064 INFO [train.py:812] (7/8) Epoch 19, batch 3150, loss[loss=0.1241, simple_loss=0.2193, pruned_loss=0.01447, over 7288.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2543, pruned_loss=0.03692, over 1429565.29 frames.], batch size: 18, lr: 4.07e-04
+2022-05-14 23:52:18,579 INFO [train.py:812] (7/8) Epoch 19, batch 3200, loss[loss=0.158, simple_loss=0.2518, pruned_loss=0.0321, over 7152.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2545, pruned_loss=0.03699, over 1428026.68 frames.], batch size: 19, lr: 4.07e-04
+2022-05-14 23:53:18,033 INFO [train.py:812] (7/8) Epoch 19, batch 3250, loss[loss=0.17, simple_loss=0.2552, pruned_loss=0.04235, over 7355.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2553, pruned_loss=0.03708, over 1424737.50 frames.], batch size: 19, lr: 4.07e-04
+2022-05-14 23:54:16,331 INFO [train.py:812] (7/8) Epoch 19, batch 3300, loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.03021, over 6346.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2552, pruned_loss=0.0371, over 1424924.05 frames.], batch size: 37, lr: 4.07e-04
+2022-05-14 23:55:15,336 INFO [train.py:812] (7/8) Epoch 19, batch 3350, loss[loss=0.1562, simple_loss=0.2485, pruned_loss=0.03194, over 7108.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2543, pruned_loss=0.03693, over 1424269.04 frames.], batch size: 21, lr: 4.07e-04
+2022-05-14 23:56:14,437 INFO [train.py:812] (7/8) Epoch 19, batch 3400, loss[loss=0.1649, simple_loss=0.2547, pruned_loss=0.03753, over 7278.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2544, pruned_loss=0.03703, over 1425130.57 frames.], batch size: 18, lr: 4.06e-04
+2022-05-14 23:57:14,028 INFO [train.py:812] (7/8) Epoch 19, batch 3450, loss[loss=0.1552, simple_loss=0.2329, pruned_loss=0.0387, over 7366.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2526, pruned_loss=0.03664, over 1421303.32 frames.], batch size: 19, lr: 4.06e-04
+2022-05-14 23:58:13,027 INFO [train.py:812] (7/8) Epoch 19, batch 3500, loss[loss=0.1756, simple_loss=0.2582, pruned_loss=0.04651, over 7285.00 frames.], tot_loss[loss=0.1631, simple_loss=0.253, pruned_loss=0.03662, over 1423557.20 frames.], batch size: 18, lr: 4.06e-04
+2022-05-14 23:59:12,624 INFO [train.py:812] (7/8) Epoch 19, batch 3550, loss[loss=0.1341, simple_loss=0.2189, pruned_loss=0.02464, over 7137.00 frames.], tot_loss[loss=0.1632, simple_loss=0.253, pruned_loss=0.03672, over 1423130.92 frames.], batch size: 17, lr: 4.06e-04
+2022-05-15 00:00:11,619 INFO [train.py:812] (7/8) Epoch 19, batch 3600, loss[loss=0.215, simple_loss=0.3032, pruned_loss=0.06336, over 7194.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2533, pruned_loss=0.03677, over 1420705.43 frames.], batch size: 23, lr: 4.06e-04
+2022-05-15 00:01:11,013 INFO [train.py:812] (7/8) Epoch 19, batch 3650, loss[loss=0.1534, simple_loss=0.2434, pruned_loss=0.03173, over 7330.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2535, pruned_loss=0.03681, over 1414238.35 frames.], batch size: 20, lr: 4.06e-04
+2022-05-15 00:02:10,026 INFO [train.py:812] (7/8) Epoch 19, batch 3700, loss[loss=0.1502, simple_loss=0.2392, pruned_loss=0.03059, over 7408.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2545, pruned_loss=0.03721, over 1416679.93 frames.], batch size: 21, lr: 4.06e-04
+2022-05-15 00:03:09,374 INFO [train.py:812] (7/8) Epoch 19, batch 3750, loss[loss=0.1635, simple_loss=0.254, pruned_loss=0.03643, over 7376.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2544, pruned_loss=0.0376, over 1413018.86 frames.], batch size: 23, lr: 4.06e-04
+2022-05-15 00:04:08,166 INFO [train.py:812] (7/8) Epoch 19, batch 3800, loss[loss=0.1474, simple_loss=0.2336, pruned_loss=0.0306, over 7360.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2546, pruned_loss=0.03743, over 1418802.93 frames.], batch size: 19, lr: 4.06e-04
+2022-05-15 00:05:06,765 INFO [train.py:812] (7/8) Epoch 19, batch 3850, loss[loss=0.1457, simple_loss=0.2308, pruned_loss=0.03032, over 7165.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2548, pruned_loss=0.03782, over 1416663.89 frames.], batch size: 18, lr: 4.05e-04
+2022-05-15 00:06:04,390 INFO [train.py:812] (7/8) Epoch 19, batch 3900, loss[loss=0.167, simple_loss=0.2682, pruned_loss=0.03292, over 7117.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2552, pruned_loss=0.03797, over 1413746.43 frames.], batch size: 21, lr: 4.05e-04
+2022-05-15 00:07:04,162 INFO [train.py:812] (7/8) Epoch 19, batch 3950, loss[loss=0.1923, simple_loss=0.2839, pruned_loss=0.05031, over 7166.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2555, pruned_loss=0.03792, over 1416030.96 frames.], batch size: 18, lr: 4.05e-04
+2022-05-15 00:08:03,292 INFO [train.py:812] (7/8) Epoch 19, batch 4000, loss[loss=0.1798, simple_loss=0.2604, pruned_loss=0.04964, over 5109.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2549, pruned_loss=0.03793, over 1416637.86 frames.], batch size: 52, lr: 4.05e-04
+2022-05-15 00:09:00,812 INFO [train.py:812] (7/8) Epoch 19, batch 4050, loss[loss=0.1573, simple_loss=0.229, pruned_loss=0.0428, over 7237.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2546, pruned_loss=0.03787, over 1415732.29 frames.], batch size: 16, lr: 4.05e-04
+2022-05-15 00:09:59,496 INFO [train.py:812] (7/8) Epoch 19, batch 4100, loss[loss=0.1912, simple_loss=0.2707, pruned_loss=0.0558, over 5296.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2549, pruned_loss=0.03777, over 1416321.51 frames.], batch size: 52, lr: 4.05e-04
+2022-05-15 00:10:57,238 INFO [train.py:812] (7/8) Epoch 19, batch 4150, loss[loss=0.1707, simple_loss=0.269, pruned_loss=0.03619, over 7389.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2541, pruned_loss=0.03721, over 1421891.81 frames.], batch size: 23, lr: 4.05e-04
+2022-05-15 00:11:56,848 INFO [train.py:812] (7/8) Epoch 19, batch 4200, loss[loss=0.1855, simple_loss=0.2781, pruned_loss=0.04639, over 7213.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2541, pruned_loss=0.0372, over 1421285.35 frames.], batch size: 23, lr: 4.05e-04
+2022-05-15 00:12:56,162 INFO [train.py:812] (7/8) Epoch 19, batch 4250, loss[loss=0.1338, simple_loss=0.2116, pruned_loss=0.02802, over 6836.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2535, pruned_loss=0.03691, over 1420905.39 frames.], batch size: 15, lr: 4.04e-04
+2022-05-15 00:14:05,123 INFO [train.py:812] (7/8) Epoch 19, batch 4300, loss[loss=0.1729, simple_loss=0.2576, pruned_loss=0.04406, over 7200.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2538, pruned_loss=0.03661, over 1420533.05 frames.], batch size: 26, lr: 4.04e-04
+2022-05-15 00:15:04,961 INFO [train.py:812] (7/8) Epoch 19, batch 4350, loss[loss=0.1683, simple_loss=0.2545, pruned_loss=0.04105, over 7163.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2532, pruned_loss=0.03649, over 1417812.67 frames.], batch size: 18, lr: 4.04e-04
+2022-05-15 00:16:03,327 INFO [train.py:812] (7/8) Epoch 19, batch 4400, loss[loss=0.1509, simple_loss=0.2477, pruned_loss=0.02707, over 6476.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2525, pruned_loss=0.0362, over 1412999.87 frames.], batch size: 38, lr: 4.04e-04
+2022-05-15 00:17:02,542 INFO [train.py:812] (7/8) Epoch 19, batch 4450, loss[loss=0.1578, simple_loss=0.24, pruned_loss=0.03783, over 6823.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2521, pruned_loss=0.03655, over 1407092.46 frames.], batch size: 15, lr: 4.04e-04
+2022-05-15 00:18:02,112 INFO [train.py:812] (7/8) Epoch 19, batch 4500, loss[loss=0.1684, simple_loss=0.2681, pruned_loss=0.03433, over 7144.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2528, pruned_loss=0.03725, over 1394010.89 frames.], batch size: 20, lr: 4.04e-04
+2022-05-15 00:19:01,082 INFO [train.py:812] (7/8) Epoch 19, batch 4550, loss[loss=0.1717, simple_loss=0.2569, pruned_loss=0.0432, over 6420.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2526, pruned_loss=0.03776, over 1366541.10 frames.], batch size: 37, lr: 4.04e-04
+2022-05-15 00:20:09,425 INFO [train.py:812] (7/8) Epoch 20, batch 0, loss[loss=0.1501, simple_loss=0.2392, pruned_loss=0.03048, over 7356.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2392, pruned_loss=0.03048, over 7356.00 frames.], batch size: 19, lr: 3.94e-04
+2022-05-15 00:21:09,545 INFO [train.py:812] (7/8) Epoch 20, batch 50, loss[loss=0.1467, simple_loss=0.2323, pruned_loss=0.03055, over 7279.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2501, pruned_loss=0.03433, over 320761.18 frames.], batch size: 18, lr: 3.94e-04
+2022-05-15 00:22:08,848 INFO [train.py:812] (7/8) Epoch 20, batch 100, loss[loss=0.1915, simple_loss=0.2759, pruned_loss=0.05352, over 5241.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2519, pruned_loss=0.03541, over 565603.27 frames.], batch size: 53, lr: 3.94e-04
+2022-05-15 00:23:08,502 INFO [train.py:812] (7/8) Epoch 20, batch 150, loss[loss=0.1614, simple_loss=0.2615, pruned_loss=0.03064, over 7320.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2548, pruned_loss=0.03643, over 755595.45 frames.], batch size: 21, lr: 3.94e-04
+2022-05-15 00:24:07,764 INFO [train.py:812] (7/8) Epoch 20, batch 200, loss[loss=0.1489, simple_loss=0.2458, pruned_loss=0.02598, over 7349.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2541, pruned_loss=0.03644, over 902738.78 frames.], batch size: 22, lr: 3.93e-04
+2022-05-15 00:25:08,012 INFO [train.py:812] (7/8) Epoch 20, batch 250, loss[loss=0.1802, simple_loss=0.2718, pruned_loss=0.04426, over 7322.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2528, pruned_loss=0.03583, over 1022353.77 frames.], batch size: 22, lr: 3.93e-04
+2022-05-15 00:26:07,283 INFO [train.py:812] (7/8) Epoch 20, batch 300, loss[loss=0.1969, simple_loss=0.285, pruned_loss=0.05441, over 7222.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2533, pruned_loss=0.03588, over 1111809.37 frames.], batch size: 23, lr: 3.93e-04
+2022-05-15 00:27:07,191 INFO [train.py:812] (7/8) Epoch 20, batch 350, loss[loss=0.1717, simple_loss=0.2689, pruned_loss=0.03727, over 7144.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2544, pruned_loss=0.03618, over 1184055.96 frames.], batch size: 20, lr: 3.93e-04
+2022-05-15 00:28:05,136 INFO [train.py:812] (7/8) Epoch 20, batch 400, loss[loss=0.1528, simple_loss=0.243, pruned_loss=0.03131, over 7140.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2557, pruned_loss=0.03663, over 1237604.18 frames.], batch size: 20, lr: 3.93e-04
+2022-05-15 00:29:03,608 INFO [train.py:812] (7/8) Epoch 20, batch 450, loss[loss=0.1812, simple_loss=0.2759, pruned_loss=0.04328, over 7374.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2557, pruned_loss=0.03665, over 1275143.62 frames.], batch size: 23, lr: 3.93e-04
+2022-05-15 00:30:01,870 INFO [train.py:812] (7/8) Epoch 20, batch 500, loss[loss=0.1637, simple_loss=0.2694, pruned_loss=0.02896, over 7227.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2562, pruned_loss=0.03656, over 1307130.41 frames.], batch size: 21, lr: 3.93e-04
+2022-05-15 00:31:00,477 INFO [train.py:812] (7/8) Epoch 20, batch 550, loss[loss=0.1775, simple_loss=0.2787, pruned_loss=0.03815, over 6742.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2556, pruned_loss=0.03631, over 1332436.66 frames.], batch size: 31, lr: 3.93e-04
+2022-05-15 00:32:00,177 INFO [train.py:812] (7/8) Epoch 20, batch 600, loss[loss=0.1386, simple_loss=0.2274, pruned_loss=0.02491, over 7160.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2552, pruned_loss=0.03659, over 1354953.29 frames.], batch size: 18, lr: 3.93e-04
+2022-05-15 00:32:59,187 INFO [train.py:812] (7/8) Epoch 20, batch 650, loss[loss=0.1376, simple_loss=0.2307, pruned_loss=0.02225, over 7177.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2543, pruned_loss=0.03616, over 1369613.46 frames.], batch size: 18, lr: 3.92e-04
+2022-05-15 00:33:55,683 INFO [train.py:812] (7/8) Epoch 20, batch 700, loss[loss=0.1629, simple_loss=0.2651, pruned_loss=0.03038, over 7232.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2543, pruned_loss=0.03594, over 1383346.19 frames.], batch size: 20, lr: 3.92e-04
+2022-05-15 00:34:54,572 INFO [train.py:812] (7/8) Epoch 20, batch 750, loss[loss=0.1728, simple_loss=0.2642, pruned_loss=0.04073, over 7312.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2528, pruned_loss=0.03519, over 1393736.43 frames.], batch size: 25, lr: 3.92e-04
+2022-05-15 00:35:51,750 INFO [train.py:812] (7/8) Epoch 20, batch 800, loss[loss=0.1702, simple_loss=0.2456, pruned_loss=0.04739, over 7410.00 frames.], tot_loss[loss=0.1611, simple_loss=0.252, pruned_loss=0.03509, over 1403228.96 frames.], batch size: 18, lr: 3.92e-04
+2022-05-15 00:36:56,577 INFO [train.py:812] (7/8) Epoch 20, batch 850, loss[loss=0.1692, simple_loss=0.2596, pruned_loss=0.03943, over 7100.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2519, pruned_loss=0.03527, over 1411168.94 frames.], batch size: 28, lr: 3.92e-04
+2022-05-15 00:37:55,379 INFO [train.py:812] (7/8) Epoch 20, batch 900, loss[loss=0.1598, simple_loss=0.2434, pruned_loss=0.03807, over 7357.00 frames.], tot_loss[loss=0.161, simple_loss=0.2512, pruned_loss=0.03536, over 1416569.54 frames.], batch size: 19, lr: 3.92e-04
+2022-05-15 00:38:53,721 INFO [train.py:812] (7/8) Epoch 20, batch 950, loss[loss=0.1525, simple_loss=0.2527, pruned_loss=0.02615, over 7232.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2527, pruned_loss=0.03612, over 1420166.80 frames.], batch size: 20, lr: 3.92e-04
+2022-05-15 00:39:52,456 INFO [train.py:812] (7/8) Epoch 20, batch 1000, loss[loss=0.1892, simple_loss=0.287, pruned_loss=0.0457, over 7282.00 frames.], tot_loss[loss=0.163, simple_loss=0.2533, pruned_loss=0.03639, over 1421665.63 frames.], batch size: 24, lr: 3.92e-04
+2022-05-15 00:40:51,855 INFO [train.py:812] (7/8) Epoch 20, batch 1050, loss[loss=0.1764, simple_loss=0.265, pruned_loss=0.04389, over 7198.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2537, pruned_loss=0.03646, over 1420162.42 frames.], batch size: 22, lr: 3.92e-04
+2022-05-15 00:41:50,569 INFO [train.py:812] (7/8) Epoch 20, batch 1100, loss[loss=0.1928, simple_loss=0.2749, pruned_loss=0.05531, over 7210.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2545, pruned_loss=0.03722, over 1416581.81 frames.], batch size: 22, lr: 3.91e-04
+2022-05-15 00:42:49,037 INFO [train.py:812] (7/8) Epoch 20, batch 1150, loss[loss=0.2086, simple_loss=0.2977, pruned_loss=0.05977, over 7296.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2554, pruned_loss=0.03744, over 1420467.87 frames.], batch size: 24, lr: 3.91e-04
+2022-05-15 00:43:48,239 INFO [train.py:812] (7/8) Epoch 20, batch 1200, loss[loss=0.1663, simple_loss=0.2641, pruned_loss=0.03428, over 7337.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2536, pruned_loss=0.03643, over 1426228.53 frames.], batch size: 22, lr: 3.91e-04
+2022-05-15 00:44:47,705 INFO [train.py:812] (7/8) Epoch 20, batch 1250, loss[loss=0.1382, simple_loss=0.2246, pruned_loss=0.02591, over 7138.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2534, pruned_loss=0.03659, over 1427474.31 frames.], batch size: 17, lr: 3.91e-04
+2022-05-15 00:45:46,823 INFO [train.py:812] (7/8) Epoch 20, batch 1300, loss[loss=0.1577, simple_loss=0.247, pruned_loss=0.03418, over 7116.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2522, pruned_loss=0.036, over 1429244.28 frames.], batch size: 21, lr: 3.91e-04
+2022-05-15 00:46:46,932 INFO [train.py:812] (7/8) Epoch 20, batch 1350, loss[loss=0.1745, simple_loss=0.2816, pruned_loss=0.03373, over 7208.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2531, pruned_loss=0.03621, over 1430970.82 frames.], batch size: 22, lr: 3.91e-04
+2022-05-15 00:47:55,916 INFO [train.py:812] (7/8) Epoch 20, batch 1400, loss[loss=0.1705, simple_loss=0.2585, pruned_loss=0.04128, over 7191.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2527, pruned_loss=0.03592, over 1432330.92 frames.], batch size: 26, lr: 3.91e-04
+2022-05-15 00:48:55,568 INFO [train.py:812] (7/8) Epoch 20, batch 1450, loss[loss=0.1826, simple_loss=0.2729, pruned_loss=0.0462, over 7235.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2538, pruned_loss=0.03645, over 1430597.22 frames.], batch size: 26, lr: 3.91e-04
+2022-05-15 00:49:54,756 INFO [train.py:812] (7/8) Epoch 20, batch 1500, loss[loss=0.1806, simple_loss=0.2786, pruned_loss=0.04128, over 7365.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2551, pruned_loss=0.03697, over 1427861.40 frames.], batch size: 23, lr: 3.91e-04
+2022-05-15 00:51:04,155 INFO [train.py:812] (7/8) Epoch 20, batch 1550, loss[loss=0.1539, simple_loss=0.2354, pruned_loss=0.03621, over 7423.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2544, pruned_loss=0.03662, over 1429590.97 frames.], batch size: 20, lr: 3.91e-04
+2022-05-15 00:52:22,087 INFO [train.py:812] (7/8) Epoch 20, batch 1600, loss[loss=0.1605, simple_loss=0.2533, pruned_loss=0.03387, over 7324.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2542, pruned_loss=0.03651, over 1424468.31 frames.], batch size: 22, lr: 3.90e-04
+2022-05-15 00:53:19,560 INFO [train.py:812] (7/8) Epoch 20, batch 1650, loss[loss=0.185, simple_loss=0.2749, pruned_loss=0.04758, over 7213.00 frames.], tot_loss[loss=0.1646, simple_loss=0.255, pruned_loss=0.0371, over 1421617.41 frames.], batch size: 23, lr: 3.90e-04
+2022-05-15 00:54:36,084 INFO [train.py:812] (7/8) Epoch 20, batch 1700, loss[loss=0.1739, simple_loss=0.2658, pruned_loss=0.04099, over 7160.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2547, pruned_loss=0.03673, over 1420898.92 frames.], batch size: 19, lr: 3.90e-04
+2022-05-15 00:55:43,702 INFO [train.py:812] (7/8) Epoch 20, batch 1750, loss[loss=0.1578, simple_loss=0.256, pruned_loss=0.02984, over 7327.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2539, pruned_loss=0.03647, over 1427020.47 frames.], batch size: 22, lr: 3.90e-04
+2022-05-15 00:56:42,608 INFO [train.py:812] (7/8) Epoch 20, batch 1800, loss[loss=0.1717, simple_loss=0.2623, pruned_loss=0.04055, over 7331.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2537, pruned_loss=0.03643, over 1427052.61 frames.], batch size: 25, lr: 3.90e-04
+2022-05-15 00:57:42,346 INFO [train.py:812] (7/8) Epoch 20, batch 1850, loss[loss=0.1567, simple_loss=0.2447, pruned_loss=0.03435, over 7072.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2532, pruned_loss=0.03631, over 1429792.80 frames.], batch size: 18, lr: 3.90e-04
+2022-05-15 00:58:41,693 INFO [train.py:812] (7/8) Epoch 20, batch 1900, loss[loss=0.1626, simple_loss=0.2538, pruned_loss=0.03566, over 7239.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2537, pruned_loss=0.03592, over 1430543.55 frames.], batch size: 20, lr: 3.90e-04
+2022-05-15 00:59:40,083 INFO [train.py:812] (7/8) Epoch 20, batch 1950, loss[loss=0.1815, simple_loss=0.2634, pruned_loss=0.04978, over 6484.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2525, pruned_loss=0.03602, over 1430542.44 frames.], batch size: 38, lr: 3.90e-04
+2022-05-15 01:00:37,517 INFO [train.py:812] (7/8) Epoch 20, batch 2000, loss[loss=0.1399, simple_loss=0.2359, pruned_loss=0.02192, over 7220.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2513, pruned_loss=0.03561, over 1431451.12 frames.], batch size: 20, lr: 3.90e-04
+2022-05-15 01:01:35,479 INFO [train.py:812] (7/8) Epoch 20, batch 2050, loss[loss=0.1473, simple_loss=0.2396, pruned_loss=0.02749, over 7229.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2513, pruned_loss=0.0355, over 1430918.80 frames.], batch size: 21, lr: 3.89e-04
+2022-05-15 01:02:33,062 INFO [train.py:812] (7/8) Epoch 20, batch 2100, loss[loss=0.1467, simple_loss=0.2411, pruned_loss=0.02611, over 7421.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2516, pruned_loss=0.03577, over 1432832.28 frames.], batch size: 20, lr: 3.89e-04
+2022-05-15 01:03:30,985 INFO [train.py:812] (7/8) Epoch 20, batch 2150, loss[loss=0.1916, simple_loss=0.2766, pruned_loss=0.05323, over 7202.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2516, pruned_loss=0.0359, over 1426261.46 frames.], batch size: 22, lr: 3.89e-04
+2022-05-15 01:04:30,289 INFO [train.py:812] (7/8) Epoch 20, batch 2200, loss[loss=0.154, simple_loss=0.2346, pruned_loss=0.03667, over 6851.00 frames.], tot_loss[loss=0.1622, simple_loss=0.252, pruned_loss=0.03627, over 1421994.12 frames.], batch size: 15, lr: 3.89e-04
+2022-05-15 01:05:28,889 INFO [train.py:812] (7/8) Epoch 20, batch 2250, loss[loss=0.1494, simple_loss=0.2488, pruned_loss=0.02496, over 7144.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2513, pruned_loss=0.03561, over 1424626.12 frames.], batch size: 20, lr: 3.89e-04
+2022-05-15 01:06:27,830 INFO [train.py:812] (7/8) Epoch 20, batch 2300, loss[loss=0.1782, simple_loss=0.2631, pruned_loss=0.04662, over 7375.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2511, pruned_loss=0.03534, over 1425346.34 frames.], batch size: 23, lr: 3.89e-04
+2022-05-15 01:07:25,480 INFO [train.py:812] (7/8) Epoch 20, batch 2350, loss[loss=0.1597, simple_loss=0.2566, pruned_loss=0.03137, over 7322.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2525, pruned_loss=0.0358, over 1424052.72 frames.], batch size: 21, lr: 3.89e-04
+2022-05-15 01:08:24,221 INFO [train.py:812] (7/8) Epoch 20, batch 2400, loss[loss=0.1521, simple_loss=0.25, pruned_loss=0.02712, over 7422.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2523, pruned_loss=0.03565, over 1425927.12 frames.], batch size: 20, lr: 3.89e-04
+2022-05-15 01:09:23,917 INFO [train.py:812] (7/8) Epoch 20, batch 2450, loss[loss=0.158, simple_loss=0.2533, pruned_loss=0.03135, over 7103.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2517, pruned_loss=0.0354, over 1428113.80 frames.], batch size: 28, lr: 3.89e-04
+2022-05-15 01:10:23,031 INFO [train.py:812] (7/8) Epoch 20, batch 2500, loss[loss=0.1673, simple_loss=0.2543, pruned_loss=0.04016, over 7150.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2508, pruned_loss=0.03546, over 1425779.60 frames.], batch size: 26, lr: 3.88e-04
+2022-05-15 01:11:22,838 INFO [train.py:812] (7/8) Epoch 20, batch 2550, loss[loss=0.1694, simple_loss=0.2592, pruned_loss=0.03978, over 7338.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2509, pruned_loss=0.03562, over 1424621.93 frames.], batch size: 20, lr: 3.88e-04
+2022-05-15 01:12:22,079 INFO [train.py:812] (7/8) Epoch 20, batch 2600, loss[loss=0.2011, simple_loss=0.2777, pruned_loss=0.06231, over 6783.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2513, pruned_loss=0.03595, over 1425306.82 frames.], batch size: 31, lr: 3.88e-04
+2022-05-15 01:13:22,194 INFO [train.py:812] (7/8) Epoch 20, batch 2650, loss[loss=0.1299, simple_loss=0.2098, pruned_loss=0.02499, over 6988.00 frames.], tot_loss[loss=0.161, simple_loss=0.2507, pruned_loss=0.03566, over 1427193.77 frames.], batch size: 16, lr: 3.88e-04
+2022-05-15 01:14:21,669 INFO [train.py:812] (7/8) Epoch 20, batch 2700, loss[loss=0.1711, simple_loss=0.2654, pruned_loss=0.03838, over 7386.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2507, pruned_loss=0.03573, over 1428118.45 frames.], batch size: 23, lr: 3.88e-04
+2022-05-15 01:15:21,516 INFO [train.py:812] (7/8) Epoch 20, batch 2750, loss[loss=0.1895, simple_loss=0.282, pruned_loss=0.0485, over 7191.00 frames.], tot_loss[loss=0.1613, simple_loss=0.251, pruned_loss=0.03585, over 1427259.47 frames.], batch size: 23, lr: 3.88e-04
+2022-05-15 01:16:20,999 INFO [train.py:812] (7/8) Epoch 20, batch 2800, loss[loss=0.1395, simple_loss=0.2222, pruned_loss=0.02835, over 7167.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2514, pruned_loss=0.0359, over 1430773.33 frames.], batch size: 18, lr: 3.88e-04
+2022-05-15 01:17:20,844 INFO [train.py:812] (7/8) Epoch 20, batch 2850, loss[loss=0.1646, simple_loss=0.2576, pruned_loss=0.03581, over 7422.00 frames.], tot_loss[loss=0.1608, simple_loss=0.251, pruned_loss=0.03533, over 1432529.44 frames.], batch size: 21, lr: 3.88e-04
+2022-05-15 01:18:20,035 INFO [train.py:812] (7/8) Epoch 20, batch 2900, loss[loss=0.1781, simple_loss=0.2738, pruned_loss=0.04119, over 7202.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2513, pruned_loss=0.03581, over 1427905.21 frames.], batch size: 26, lr: 3.88e-04
+2022-05-15 01:19:19,551 INFO [train.py:812] (7/8) Epoch 20, batch 2950, loss[loss=0.173, simple_loss=0.2528, pruned_loss=0.04657, over 7227.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2521, pruned_loss=0.03616, over 1432006.00 frames.], batch size: 20, lr: 3.87e-04
+2022-05-15 01:20:18,549 INFO [train.py:812] (7/8) Epoch 20, batch 3000, loss[loss=0.2053, simple_loss=0.2996, pruned_loss=0.05546, over 7389.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2532, pruned_loss=0.03628, over 1430970.89 frames.], batch size: 23, lr: 3.87e-04
+2022-05-15 01:20:18,550 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 01:20:27,133 INFO [train.py:841] (7/8) Epoch 20, validation: loss=0.1532, simple_loss=0.2519, pruned_loss=0.02723, over 698248.00 frames.
+2022-05-15 01:21:26,382 INFO [train.py:812] (7/8) Epoch 20, batch 3050, loss[loss=0.1507, simple_loss=0.2436, pruned_loss=0.02887, over 7171.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2539, pruned_loss=0.03664, over 1432670.63 frames.], batch size: 19, lr: 3.87e-04
+2022-05-15 01:22:25,338 INFO [train.py:812] (7/8) Epoch 20, batch 3100, loss[loss=0.1528, simple_loss=0.2372, pruned_loss=0.0342, over 7100.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2539, pruned_loss=0.03663, over 1431395.83 frames.], batch size: 21, lr: 3.87e-04
+2022-05-15 01:23:24,553 INFO [train.py:812] (7/8) Epoch 20, batch 3150, loss[loss=0.1302, simple_loss=0.2164, pruned_loss=0.02201, over 7276.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2534, pruned_loss=0.03659, over 1432139.06 frames.], batch size: 18, lr: 3.87e-04
+2022-05-15 01:24:21,348 INFO [train.py:812] (7/8) Epoch 20, batch 3200, loss[loss=0.1803, simple_loss=0.282, pruned_loss=0.03933, over 6710.00 frames.], tot_loss[loss=0.1629, simple_loss=0.253, pruned_loss=0.0364, over 1431265.23 frames.], batch size: 31, lr: 3.87e-04
+2022-05-15 01:25:18,760 INFO [train.py:812] (7/8) Epoch 20, batch 3250, loss[loss=0.141, simple_loss=0.2327, pruned_loss=0.02467, over 7073.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2529, pruned_loss=0.03633, over 1428078.91 frames.], batch size: 18, lr: 3.87e-04
+2022-05-15 01:26:16,486 INFO [train.py:812] (7/8) Epoch 20, batch 3300, loss[loss=0.154, simple_loss=0.2422, pruned_loss=0.03294, over 7134.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2525, pruned_loss=0.03624, over 1427623.41 frames.], batch size: 17, lr: 3.87e-04
+2022-05-15 01:27:14,083 INFO [train.py:812] (7/8) Epoch 20, batch 3350, loss[loss=0.1393, simple_loss=0.2478, pruned_loss=0.01539, over 7143.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2527, pruned_loss=0.03639, over 1427543.12 frames.], batch size: 20, lr: 3.87e-04
+2022-05-15 01:28:13,213 INFO [train.py:812] (7/8) Epoch 20, batch 3400, loss[loss=0.1391, simple_loss=0.218, pruned_loss=0.03013, over 7276.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2528, pruned_loss=0.03649, over 1426841.51 frames.], batch size: 17, lr: 3.87e-04
+2022-05-15 01:29:12,318 INFO [train.py:812] (7/8) Epoch 20, batch 3450, loss[loss=0.1658, simple_loss=0.2635, pruned_loss=0.03407, over 7234.00 frames.], tot_loss[loss=0.164, simple_loss=0.2542, pruned_loss=0.03688, over 1425295.22 frames.], batch size: 20, lr: 3.86e-04
+2022-05-15 01:30:11,802 INFO [train.py:812] (7/8) Epoch 20, batch 3500, loss[loss=0.1326, simple_loss=0.2272, pruned_loss=0.01901, over 7263.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2528, pruned_loss=0.03611, over 1423637.52 frames.], batch size: 19, lr: 3.86e-04
+2022-05-15 01:31:11,515 INFO [train.py:812] (7/8) Epoch 20, batch 3550, loss[loss=0.1697, simple_loss=0.267, pruned_loss=0.03619, over 7120.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2533, pruned_loss=0.03646, over 1425962.47 frames.], batch size: 21, lr: 3.86e-04
+2022-05-15 01:32:11,020 INFO [train.py:812] (7/8) Epoch 20, batch 3600, loss[loss=0.1711, simple_loss=0.2764, pruned_loss=0.03291, over 7201.00 frames.], tot_loss[loss=0.1628, simple_loss=0.253, pruned_loss=0.03634, over 1428398.35 frames.], batch size: 23, lr: 3.86e-04
+2022-05-15 01:33:10,994 INFO [train.py:812] (7/8) Epoch 20, batch 3650, loss[loss=0.1855, simple_loss=0.2689, pruned_loss=0.05108, over 7309.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2526, pruned_loss=0.03629, over 1429593.12 frames.], batch size: 21, lr: 3.86e-04
+2022-05-15 01:34:09,111 INFO [train.py:812] (7/8) Epoch 20, batch 3700, loss[loss=0.1571, simple_loss=0.2474, pruned_loss=0.03334, over 7166.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2527, pruned_loss=0.03582, over 1431618.60 frames.], batch size: 18, lr: 3.86e-04
+2022-05-15 01:35:08,021 INFO [train.py:812] (7/8) Epoch 20, batch 3750, loss[loss=0.196, simple_loss=0.281, pruned_loss=0.05551, over 7126.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2515, pruned_loss=0.03536, over 1425735.86 frames.], batch size: 28, lr: 3.86e-04
+2022-05-15 01:36:06,457 INFO [train.py:812] (7/8) Epoch 20, batch 3800, loss[loss=0.1552, simple_loss=0.2557, pruned_loss=0.02729, over 7336.00 frames.], tot_loss[loss=0.161, simple_loss=0.251, pruned_loss=0.0355, over 1421620.41 frames.], batch size: 20, lr: 3.86e-04
+2022-05-15 01:37:04,418 INFO [train.py:812] (7/8) Epoch 20, batch 3850, loss[loss=0.1413, simple_loss=0.2227, pruned_loss=0.02993, over 7283.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2509, pruned_loss=0.03537, over 1420843.16 frames.], batch size: 17, lr: 3.86e-04
+2022-05-15 01:38:02,190 INFO [train.py:812] (7/8) Epoch 20, batch 3900, loss[loss=0.1544, simple_loss=0.2473, pruned_loss=0.03079, over 7113.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2522, pruned_loss=0.03577, over 1417933.08 frames.], batch size: 21, lr: 3.85e-04
+2022-05-15 01:39:01,308 INFO [train.py:812] (7/8) Epoch 20, batch 3950, loss[loss=0.1572, simple_loss=0.2534, pruned_loss=0.03051, over 7338.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2519, pruned_loss=0.03583, over 1411984.18 frames.], batch size: 20, lr: 3.85e-04
+2022-05-15 01:39:59,120 INFO [train.py:812] (7/8) Epoch 20, batch 4000, loss[loss=0.1485, simple_loss=0.2365, pruned_loss=0.03031, over 7166.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2516, pruned_loss=0.03563, over 1409293.55 frames.], batch size: 18, lr: 3.85e-04
+2022-05-15 01:40:58,332 INFO [train.py:812] (7/8) Epoch 20, batch 4050, loss[loss=0.158, simple_loss=0.2474, pruned_loss=0.03424, over 7326.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2513, pruned_loss=0.03566, over 1406391.41 frames.], batch size: 20, lr: 3.85e-04
+2022-05-15 01:41:57,228 INFO [train.py:812] (7/8) Epoch 20, batch 4100, loss[loss=0.1571, simple_loss=0.2418, pruned_loss=0.03613, over 7294.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2511, pruned_loss=0.03572, over 1407081.11 frames.], batch size: 18, lr: 3.85e-04
+2022-05-15 01:42:56,576 INFO [train.py:812] (7/8) Epoch 20, batch 4150, loss[loss=0.1528, simple_loss=0.253, pruned_loss=0.02628, over 7065.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2505, pruned_loss=0.03538, over 1411383.64 frames.], batch size: 18, lr: 3.85e-04
+2022-05-15 01:43:53,660 INFO [train.py:812] (7/8) Epoch 20, batch 4200, loss[loss=0.1797, simple_loss=0.25, pruned_loss=0.05466, over 6829.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2511, pruned_loss=0.03556, over 1405823.28 frames.], batch size: 15, lr: 3.85e-04
+2022-05-15 01:44:52,616 INFO [train.py:812] (7/8) Epoch 20, batch 4250, loss[loss=0.1701, simple_loss=0.2644, pruned_loss=0.0379, over 7198.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2505, pruned_loss=0.03531, over 1403691.62 frames.], batch size: 23, lr: 3.85e-04
+2022-05-15 01:45:49,912 INFO [train.py:812] (7/8) Epoch 20, batch 4300, loss[loss=0.1708, simple_loss=0.2731, pruned_loss=0.03428, over 7218.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2511, pruned_loss=0.03554, over 1400945.60 frames.], batch size: 21, lr: 3.85e-04
+2022-05-15 01:46:48,997 INFO [train.py:812] (7/8) Epoch 20, batch 4350, loss[loss=0.2, simple_loss=0.2895, pruned_loss=0.05523, over 4643.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2493, pruned_loss=0.03494, over 1403024.15 frames.], batch size: 52, lr: 3.84e-04
+2022-05-15 01:47:48,042 INFO [train.py:812] (7/8) Epoch 20, batch 4400, loss[loss=0.1463, simple_loss=0.2362, pruned_loss=0.02825, over 7152.00 frames.], tot_loss[loss=0.1594, simple_loss=0.249, pruned_loss=0.03492, over 1398124.86 frames.], batch size: 19, lr: 3.84e-04
+2022-05-15 01:48:47,186 INFO [train.py:812] (7/8) Epoch 20, batch 4450, loss[loss=0.1211, simple_loss=0.2078, pruned_loss=0.01718, over 7213.00 frames.], tot_loss[loss=0.1598, simple_loss=0.249, pruned_loss=0.03529, over 1390093.59 frames.], batch size: 16, lr: 3.84e-04
+2022-05-15 01:49:45,798 INFO [train.py:812] (7/8) Epoch 20, batch 4500, loss[loss=0.1667, simple_loss=0.2656, pruned_loss=0.03386, over 7210.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2502, pruned_loss=0.03604, over 1383558.37 frames.], batch size: 23, lr: 3.84e-04
+2022-05-15 01:50:44,412 INFO [train.py:812] (7/8) Epoch 20, batch 4550, loss[loss=0.1711, simple_loss=0.2617, pruned_loss=0.04026, over 6273.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2527, pruned_loss=0.03759, over 1339897.51 frames.], batch size: 37, lr: 3.84e-04
+2022-05-15 01:51:55,240 INFO [train.py:812] (7/8) Epoch 21, batch 0, loss[loss=0.1476, simple_loss=0.246, pruned_loss=0.02462, over 6996.00 frames.], tot_loss[loss=0.1476, simple_loss=0.246, pruned_loss=0.02462, over 6996.00 frames.], batch size: 16, lr: 3.75e-04
+2022-05-15 01:52:54,970 INFO [train.py:812] (7/8) Epoch 21, batch 50, loss[loss=0.1468, simple_loss=0.2448, pruned_loss=0.02441, over 6333.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2517, pruned_loss=0.03631, over 322782.37 frames.], batch size: 37, lr: 3.75e-04
+2022-05-15 01:53:53,848 INFO [train.py:812] (7/8) Epoch 21, batch 100, loss[loss=0.1811, simple_loss=0.2606, pruned_loss=0.05079, over 6836.00 frames.], tot_loss[loss=0.163, simple_loss=0.2531, pruned_loss=0.0364, over 565797.57 frames.], batch size: 15, lr: 3.75e-04
+2022-05-15 01:54:52,710 INFO [train.py:812] (7/8) Epoch 21, batch 150, loss[loss=0.1568, simple_loss=0.2529, pruned_loss=0.03033, over 7166.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2516, pruned_loss=0.03563, over 755515.23 frames.], batch size: 18, lr: 3.75e-04
+2022-05-15 01:55:51,335 INFO [train.py:812] (7/8) Epoch 21, batch 200, loss[loss=0.1895, simple_loss=0.2907, pruned_loss=0.04419, over 6801.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2529, pruned_loss=0.03668, over 900205.47 frames.], batch size: 31, lr: 3.75e-04
+2022-05-15 01:56:53,970 INFO [train.py:812] (7/8) Epoch 21, batch 250, loss[loss=0.1531, simple_loss=0.2365, pruned_loss=0.03479, over 7168.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2526, pruned_loss=0.0366, over 1012287.16 frames.], batch size: 19, lr: 3.75e-04
+2022-05-15 01:57:52,834 INFO [train.py:812] (7/8) Epoch 21, batch 300, loss[loss=0.141, simple_loss=0.2296, pruned_loss=0.02626, over 7262.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2525, pruned_loss=0.03668, over 1101079.51 frames.], batch size: 18, lr: 3.75e-04
+2022-05-15 01:58:49,841 INFO [train.py:812] (7/8) Epoch 21, batch 350, loss[loss=0.1493, simple_loss=0.2405, pruned_loss=0.02905, over 7249.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2525, pruned_loss=0.03624, over 1169009.63 frames.], batch size: 19, lr: 3.74e-04
+2022-05-15 01:59:47,346 INFO [train.py:812] (7/8) Epoch 21, batch 400, loss[loss=0.1427, simple_loss=0.2316, pruned_loss=0.02694, over 7076.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2516, pruned_loss=0.03541, over 1228028.90 frames.], batch size: 18, lr: 3.74e-04
+2022-05-15 02:00:46,730 INFO [train.py:812] (7/8) Epoch 21, batch 450, loss[loss=0.1754, simple_loss=0.2604, pruned_loss=0.04519, over 7058.00 frames.], tot_loss[loss=0.162, simple_loss=0.2522, pruned_loss=0.03589, over 1270411.56 frames.], batch size: 18, lr: 3.74e-04
+2022-05-15 02:01:45,896 INFO [train.py:812] (7/8) Epoch 21, batch 500, loss[loss=0.1591, simple_loss=0.2569, pruned_loss=0.03062, over 7013.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2523, pruned_loss=0.03594, over 1309355.17 frames.], batch size: 28, lr: 3.74e-04
+2022-05-15 02:02:44,641 INFO [train.py:812] (7/8) Epoch 21, batch 550, loss[loss=0.1538, simple_loss=0.2325, pruned_loss=0.03756, over 6826.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2515, pruned_loss=0.03568, over 1335845.98 frames.], batch size: 15, lr: 3.74e-04
+2022-05-15 02:03:42,734 INFO [train.py:812] (7/8) Epoch 21, batch 600, loss[loss=0.224, simple_loss=0.3072, pruned_loss=0.07046, over 7204.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2524, pruned_loss=0.0361, over 1355222.80 frames.], batch size: 22, lr: 3.74e-04
+2022-05-15 02:04:42,177 INFO [train.py:812] (7/8) Epoch 21, batch 650, loss[loss=0.1307, simple_loss=0.2222, pruned_loss=0.01961, over 7134.00 frames.], tot_loss[loss=0.161, simple_loss=0.251, pruned_loss=0.03545, over 1370031.40 frames.], batch size: 17, lr: 3.74e-04
+2022-05-15 02:05:41,136 INFO [train.py:812] (7/8) Epoch 21, batch 700, loss[loss=0.1563, simple_loss=0.2531, pruned_loss=0.02979, over 7234.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2522, pruned_loss=0.03537, over 1380060.11 frames.], batch size: 20, lr: 3.74e-04
+2022-05-15 02:06:40,220 INFO [train.py:812] (7/8) Epoch 21, batch 750, loss[loss=0.1425, simple_loss=0.2282, pruned_loss=0.02845, over 7410.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2531, pruned_loss=0.03596, over 1386489.55 frames.], batch size: 18, lr: 3.74e-04
+2022-05-15 02:07:37,531 INFO [train.py:812] (7/8) Epoch 21, batch 800, loss[loss=0.1465, simple_loss=0.2381, pruned_loss=0.02744, over 7236.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2527, pruned_loss=0.03576, over 1385196.02 frames.], batch size: 20, lr: 3.73e-04
+2022-05-15 02:08:37,267 INFO [train.py:812] (7/8) Epoch 21, batch 850, loss[loss=0.1735, simple_loss=0.26, pruned_loss=0.04346, over 7317.00 frames.], tot_loss[loss=0.1616, simple_loss=0.252, pruned_loss=0.03562, over 1392028.62 frames.], batch size: 25, lr: 3.73e-04
+2022-05-15 02:09:36,871 INFO [train.py:812] (7/8) Epoch 21, batch 900, loss[loss=0.1563, simple_loss=0.2465, pruned_loss=0.03311, over 7237.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2511, pruned_loss=0.03515, over 1400440.42 frames.], batch size: 20, lr: 3.73e-04
+2022-05-15 02:10:36,713 INFO [train.py:812] (7/8) Epoch 21, batch 950, loss[loss=0.1541, simple_loss=0.2575, pruned_loss=0.02541, over 7333.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2515, pruned_loss=0.03544, over 1405889.08 frames.], batch size: 22, lr: 3.73e-04
+2022-05-15 02:11:34,919 INFO [train.py:812] (7/8) Epoch 21, batch 1000, loss[loss=0.1943, simple_loss=0.2731, pruned_loss=0.05777, over 7199.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2519, pruned_loss=0.03561, over 1405250.97 frames.], batch size: 23, lr: 3.73e-04
+2022-05-15 02:12:42,519 INFO [train.py:812] (7/8) Epoch 21, batch 1050, loss[loss=0.165, simple_loss=0.2633, pruned_loss=0.03333, over 7410.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2528, pruned_loss=0.03568, over 1406999.73 frames.], batch size: 21, lr: 3.73e-04
+2022-05-15 02:13:41,822 INFO [train.py:812] (7/8) Epoch 21, batch 1100, loss[loss=0.1579, simple_loss=0.2451, pruned_loss=0.03536, over 6798.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2524, pruned_loss=0.03549, over 1409048.47 frames.], batch size: 15, lr: 3.73e-04
+2022-05-15 02:14:40,555 INFO [train.py:812] (7/8) Epoch 21, batch 1150, loss[loss=0.1917, simple_loss=0.2914, pruned_loss=0.04599, over 7295.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2519, pruned_loss=0.03523, over 1413826.46 frames.], batch size: 24, lr: 3.73e-04
+2022-05-15 02:15:37,809 INFO [train.py:812] (7/8) Epoch 21, batch 1200, loss[loss=0.1586, simple_loss=0.2389, pruned_loss=0.03917, over 7276.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2522, pruned_loss=0.03557, over 1415830.69 frames.], batch size: 18, lr: 3.73e-04
+2022-05-15 02:16:37,279 INFO [train.py:812] (7/8) Epoch 21, batch 1250, loss[loss=0.1904, simple_loss=0.291, pruned_loss=0.04489, over 7280.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2507, pruned_loss=0.03498, over 1417702.93 frames.], batch size: 24, lr: 3.73e-04
+2022-05-15 02:17:36,479 INFO [train.py:812] (7/8) Epoch 21, batch 1300, loss[loss=0.159, simple_loss=0.247, pruned_loss=0.03546, over 7067.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2499, pruned_loss=0.03494, over 1417285.35 frames.], batch size: 18, lr: 3.72e-04
+2022-05-15 02:18:34,108 INFO [train.py:812] (7/8) Epoch 21, batch 1350, loss[loss=0.1796, simple_loss=0.2746, pruned_loss=0.04226, over 7339.00 frames.], tot_loss[loss=0.1599, simple_loss=0.25, pruned_loss=0.03488, over 1424410.25 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:19:32,918 INFO [train.py:812] (7/8) Epoch 21, batch 1400, loss[loss=0.1631, simple_loss=0.259, pruned_loss=0.03357, over 7391.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2495, pruned_loss=0.0348, over 1427031.51 frames.], batch size: 23, lr: 3.72e-04
+2022-05-15 02:20:31,816 INFO [train.py:812] (7/8) Epoch 21, batch 1450, loss[loss=0.1857, simple_loss=0.27, pruned_loss=0.05072, over 5061.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2494, pruned_loss=0.03494, over 1421460.80 frames.], batch size: 52, lr: 3.72e-04
+2022-05-15 02:21:30,190 INFO [train.py:812] (7/8) Epoch 21, batch 1500, loss[loss=0.1497, simple_loss=0.2485, pruned_loss=0.02546, over 7337.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2508, pruned_loss=0.03579, over 1419233.59 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:22:29,865 INFO [train.py:812] (7/8) Epoch 21, batch 1550, loss[loss=0.1778, simple_loss=0.272, pruned_loss=0.0418, over 6878.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2517, pruned_loss=0.03626, over 1420968.10 frames.], batch size: 31, lr: 3.72e-04
+2022-05-15 02:23:26,760 INFO [train.py:812] (7/8) Epoch 21, batch 1600, loss[loss=0.1459, simple_loss=0.2414, pruned_loss=0.02515, over 7337.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2518, pruned_loss=0.03621, over 1422000.45 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:24:25,710 INFO [train.py:812] (7/8) Epoch 21, batch 1650, loss[loss=0.1356, simple_loss=0.228, pruned_loss=0.02166, over 7327.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2521, pruned_loss=0.03643, over 1422611.31 frames.], batch size: 20, lr: 3.72e-04
+2022-05-15 02:25:24,272 INFO [train.py:812] (7/8) Epoch 21, batch 1700, loss[loss=0.1709, simple_loss=0.2618, pruned_loss=0.03993, over 7345.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2513, pruned_loss=0.03625, over 1422524.24 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:26:22,329 INFO [train.py:812] (7/8) Epoch 21, batch 1750, loss[loss=0.1216, simple_loss=0.2077, pruned_loss=0.01773, over 7384.00 frames.], tot_loss[loss=0.1616, simple_loss=0.251, pruned_loss=0.0361, over 1422551.33 frames.], batch size: 18, lr: 3.72e-04
+2022-05-15 02:27:21,204 INFO [train.py:812] (7/8) Epoch 21, batch 1800, loss[loss=0.1694, simple_loss=0.2553, pruned_loss=0.04176, over 7189.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2512, pruned_loss=0.03593, over 1423814.21 frames.], batch size: 23, lr: 3.71e-04
+2022-05-15 02:28:20,374 INFO [train.py:812] (7/8) Epoch 21, batch 1850, loss[loss=0.1432, simple_loss=0.234, pruned_loss=0.02615, over 7417.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2515, pruned_loss=0.0361, over 1423032.98 frames.], batch size: 18, lr: 3.71e-04
+2022-05-15 02:29:19,121 INFO [train.py:812] (7/8) Epoch 21, batch 1900, loss[loss=0.1469, simple_loss=0.232, pruned_loss=0.03095, over 7159.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2517, pruned_loss=0.0361, over 1424099.74 frames.], batch size: 19, lr: 3.71e-04
+2022-05-15 02:30:18,957 INFO [train.py:812] (7/8) Epoch 21, batch 1950, loss[loss=0.1546, simple_loss=0.2362, pruned_loss=0.0365, over 7251.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2525, pruned_loss=0.03638, over 1428262.10 frames.], batch size: 19, lr: 3.71e-04
+2022-05-15 02:31:18,453 INFO [train.py:812] (7/8) Epoch 21, batch 2000, loss[loss=0.1563, simple_loss=0.2489, pruned_loss=0.03184, over 6860.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2517, pruned_loss=0.03587, over 1424592.50 frames.], batch size: 31, lr: 3.71e-04
+2022-05-15 02:32:18,170 INFO [train.py:812] (7/8) Epoch 21, batch 2050, loss[loss=0.166, simple_loss=0.2636, pruned_loss=0.0342, over 7220.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2519, pruned_loss=0.03595, over 1424396.45 frames.], batch size: 21, lr: 3.71e-04
+2022-05-15 02:33:17,380 INFO [train.py:812] (7/8) Epoch 21, batch 2100, loss[loss=0.1709, simple_loss=0.2615, pruned_loss=0.04016, over 7068.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2515, pruned_loss=0.03573, over 1423306.16 frames.], batch size: 18, lr: 3.71e-04
+2022-05-15 02:34:16,887 INFO [train.py:812] (7/8) Epoch 21, batch 2150, loss[loss=0.1272, simple_loss=0.219, pruned_loss=0.01772, over 6770.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2517, pruned_loss=0.03564, over 1421934.66 frames.], batch size: 15, lr: 3.71e-04
+2022-05-15 02:35:14,513 INFO [train.py:812] (7/8) Epoch 21, batch 2200, loss[loss=0.2063, simple_loss=0.3095, pruned_loss=0.05157, over 7208.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2519, pruned_loss=0.03588, over 1423538.81 frames.], batch size: 22, lr: 3.71e-04
+2022-05-15 02:36:12,445 INFO [train.py:812] (7/8) Epoch 21, batch 2250, loss[loss=0.164, simple_loss=0.2558, pruned_loss=0.03612, over 7205.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2526, pruned_loss=0.03603, over 1424801.59 frames.], batch size: 22, lr: 3.71e-04
+2022-05-15 02:37:12,599 INFO [train.py:812] (7/8) Epoch 21, batch 2300, loss[loss=0.1967, simple_loss=0.2813, pruned_loss=0.056, over 4919.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2518, pruned_loss=0.03601, over 1422245.48 frames.], batch size: 52, lr: 3.71e-04
+2022-05-15 02:38:11,412 INFO [train.py:812] (7/8) Epoch 21, batch 2350, loss[loss=0.1776, simple_loss=0.2724, pruned_loss=0.04141, over 7290.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2534, pruned_loss=0.03656, over 1417223.10 frames.], batch size: 24, lr: 3.70e-04
+2022-05-15 02:39:10,749 INFO [train.py:812] (7/8) Epoch 21, batch 2400, loss[loss=0.1715, simple_loss=0.2639, pruned_loss=0.0396, over 7197.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2518, pruned_loss=0.03587, over 1420352.64 frames.], batch size: 23, lr: 3.70e-04
+2022-05-15 02:40:10,466 INFO [train.py:812] (7/8) Epoch 21, batch 2450, loss[loss=0.1414, simple_loss=0.2276, pruned_loss=0.02766, over 7165.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2514, pruned_loss=0.03564, over 1421522.25 frames.], batch size: 19, lr: 3.70e-04
+2022-05-15 02:41:09,444 INFO [train.py:812] (7/8) Epoch 21, batch 2500, loss[loss=0.1688, simple_loss=0.2536, pruned_loss=0.04196, over 7413.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2511, pruned_loss=0.0354, over 1422564.25 frames.], batch size: 21, lr: 3.70e-04
+2022-05-15 02:42:07,867 INFO [train.py:812] (7/8) Epoch 21, batch 2550, loss[loss=0.1784, simple_loss=0.2672, pruned_loss=0.04482, over 5178.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2515, pruned_loss=0.03552, over 1420181.92 frames.], batch size: 52, lr: 3.70e-04
+2022-05-15 02:43:06,234 INFO [train.py:812] (7/8) Epoch 21, batch 2600, loss[loss=0.1401, simple_loss=0.2305, pruned_loss=0.02486, over 7064.00 frames.], tot_loss[loss=0.162, simple_loss=0.2524, pruned_loss=0.03583, over 1421047.30 frames.], batch size: 18, lr: 3.70e-04
+2022-05-15 02:44:05,943 INFO [train.py:812] (7/8) Epoch 21, batch 2650, loss[loss=0.1615, simple_loss=0.2528, pruned_loss=0.03511, over 7333.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2529, pruned_loss=0.03643, over 1416367.83 frames.], batch size: 20, lr: 3.70e-04
+2022-05-15 02:45:04,676 INFO [train.py:812] (7/8) Epoch 21, batch 2700, loss[loss=0.1522, simple_loss=0.2356, pruned_loss=0.03446, over 7406.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2524, pruned_loss=0.03603, over 1419949.75 frames.], batch size: 18, lr: 3.70e-04
+2022-05-15 02:46:03,796 INFO [train.py:812] (7/8) Epoch 21, batch 2750, loss[loss=0.1515, simple_loss=0.2401, pruned_loss=0.03144, over 7157.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2524, pruned_loss=0.03602, over 1422329.11 frames.], batch size: 18, lr: 3.70e-04
+2022-05-15 02:47:03,063 INFO [train.py:812] (7/8) Epoch 21, batch 2800, loss[loss=0.173, simple_loss=0.266, pruned_loss=0.04001, over 7381.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2516, pruned_loss=0.03577, over 1425756.88 frames.], batch size: 23, lr: 3.70e-04
+2022-05-15 02:48:12,169 INFO [train.py:812] (7/8) Epoch 21, batch 2850, loss[loss=0.1517, simple_loss=0.253, pruned_loss=0.0252, over 7190.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2518, pruned_loss=0.03566, over 1421377.07 frames.], batch size: 23, lr: 3.69e-04
+2022-05-15 02:49:11,157 INFO [train.py:812] (7/8) Epoch 21, batch 2900, loss[loss=0.1515, simple_loss=0.248, pruned_loss=0.02746, over 7103.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2516, pruned_loss=0.03566, over 1416647.38 frames.], batch size: 28, lr: 3.69e-04
+2022-05-15 02:50:09,829 INFO [train.py:812] (7/8) Epoch 21, batch 2950, loss[loss=0.1547, simple_loss=0.2408, pruned_loss=0.0343, over 7352.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2517, pruned_loss=0.03568, over 1414624.27 frames.], batch size: 19, lr: 3.69e-04
+2022-05-15 02:51:09,059 INFO [train.py:812] (7/8) Epoch 21, batch 3000, loss[loss=0.179, simple_loss=0.2736, pruned_loss=0.04225, over 6754.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2521, pruned_loss=0.03558, over 1414175.38 frames.], batch size: 31, lr: 3.69e-04
+2022-05-15 02:51:09,061 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 02:51:16,350 INFO [train.py:841] (7/8) Epoch 21, validation: loss=0.153, simple_loss=0.2519, pruned_loss=0.02704, over 698248.00 frames.
+2022-05-15 02:52:35,389 INFO [train.py:812] (7/8) Epoch 21, batch 3050, loss[loss=0.154, simple_loss=0.2405, pruned_loss=0.03375, over 7282.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2517, pruned_loss=0.03547, over 1414946.67 frames.], batch size: 18, lr: 3.69e-04
+2022-05-15 02:53:32,986 INFO [train.py:812] (7/8) Epoch 21, batch 3100, loss[loss=0.1643, simple_loss=0.2557, pruned_loss=0.03641, over 7372.00 frames.], tot_loss[loss=0.163, simple_loss=0.2533, pruned_loss=0.0364, over 1413599.75 frames.], batch size: 23, lr: 3.69e-04
+2022-05-15 02:55:01,551 INFO [train.py:812] (7/8) Epoch 21, batch 3150, loss[loss=0.1809, simple_loss=0.2718, pruned_loss=0.04498, over 7303.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2529, pruned_loss=0.03645, over 1418854.14 frames.], batch size: 24, lr: 3.69e-04
+2022-05-15 02:56:00,675 INFO [train.py:812] (7/8) Epoch 21, batch 3200, loss[loss=0.1704, simple_loss=0.2665, pruned_loss=0.03711, over 7319.00 frames.], tot_loss[loss=0.163, simple_loss=0.2532, pruned_loss=0.0364, over 1423164.03 frames.], batch size: 21, lr: 3.69e-04
+2022-05-15 02:57:00,408 INFO [train.py:812] (7/8) Epoch 21, batch 3250, loss[loss=0.1479, simple_loss=0.2444, pruned_loss=0.02564, over 7056.00 frames.], tot_loss[loss=0.1629, simple_loss=0.253, pruned_loss=0.03645, over 1421836.79 frames.], batch size: 18, lr: 3.69e-04
+2022-05-15 02:58:08,782 INFO [train.py:812] (7/8) Epoch 21, batch 3300, loss[loss=0.1274, simple_loss=0.2133, pruned_loss=0.02079, over 7128.00 frames.], tot_loss[loss=0.162, simple_loss=0.2522, pruned_loss=0.03591, over 1423729.28 frames.], batch size: 17, lr: 3.69e-04
+2022-05-15 02:59:08,393 INFO [train.py:812] (7/8) Epoch 21, batch 3350, loss[loss=0.1537, simple_loss=0.2475, pruned_loss=0.02997, over 7222.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2521, pruned_loss=0.03569, over 1420478.84 frames.], batch size: 20, lr: 3.68e-04
+2022-05-15 03:00:06,821 INFO [train.py:812] (7/8) Epoch 21, batch 3400, loss[loss=0.1727, simple_loss=0.2635, pruned_loss=0.04098, over 6308.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2522, pruned_loss=0.03568, over 1416321.95 frames.], batch size: 38, lr: 3.68e-04
+2022-05-15 03:01:06,193 INFO [train.py:812] (7/8) Epoch 21, batch 3450, loss[loss=0.1334, simple_loss=0.2384, pruned_loss=0.01424, over 7318.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2526, pruned_loss=0.03546, over 1414773.78 frames.], batch size: 21, lr: 3.68e-04
+2022-05-15 03:02:05,088 INFO [train.py:812] (7/8) Epoch 21, batch 3500, loss[loss=0.1725, simple_loss=0.2624, pruned_loss=0.04134, over 7074.00 frames.], tot_loss[loss=0.1619, simple_loss=0.253, pruned_loss=0.03546, over 1410539.86 frames.], batch size: 28, lr: 3.68e-04
+2022-05-15 03:03:04,144 INFO [train.py:812] (7/8) Epoch 21, batch 3550, loss[loss=0.1403, simple_loss=0.2313, pruned_loss=0.0246, over 7268.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2519, pruned_loss=0.03469, over 1414047.04 frames.], batch size: 17, lr: 3.68e-04
+2022-05-15 03:04:02,928 INFO [train.py:812] (7/8) Epoch 21, batch 3600, loss[loss=0.1701, simple_loss=0.2616, pruned_loss=0.03935, over 7362.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2529, pruned_loss=0.03543, over 1411708.35 frames.], batch size: 23, lr: 3.68e-04
+2022-05-15 03:05:02,895 INFO [train.py:812] (7/8) Epoch 21, batch 3650, loss[loss=0.1682, simple_loss=0.2666, pruned_loss=0.03493, over 7228.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2525, pruned_loss=0.03544, over 1413807.91 frames.], batch size: 26, lr: 3.68e-04
+2022-05-15 03:06:01,360 INFO [train.py:812] (7/8) Epoch 21, batch 3700, loss[loss=0.1444, simple_loss=0.2459, pruned_loss=0.02142, over 7314.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2525, pruned_loss=0.03513, over 1414668.99 frames.], batch size: 21, lr: 3.68e-04
+2022-05-15 03:07:01,133 INFO [train.py:812] (7/8) Epoch 21, batch 3750, loss[loss=0.1781, simple_loss=0.2666, pruned_loss=0.04477, over 7294.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2523, pruned_loss=0.03536, over 1418087.74 frames.], batch size: 25, lr: 3.68e-04
+2022-05-15 03:07:59,625 INFO [train.py:812] (7/8) Epoch 21, batch 3800, loss[loss=0.1515, simple_loss=0.2536, pruned_loss=0.0247, over 7187.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2513, pruned_loss=0.0351, over 1418718.23 frames.], batch size: 26, lr: 3.68e-04
+2022-05-15 03:08:58,711 INFO [train.py:812] (7/8) Epoch 21, batch 3850, loss[loss=0.1564, simple_loss=0.254, pruned_loss=0.02938, over 7332.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2511, pruned_loss=0.03471, over 1419374.75 frames.], batch size: 20, lr: 3.68e-04
+2022-05-15 03:09:55,553 INFO [train.py:812] (7/8) Epoch 21, batch 3900, loss[loss=0.1576, simple_loss=0.2514, pruned_loss=0.03192, over 7259.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2513, pruned_loss=0.035, over 1422679.10 frames.], batch size: 19, lr: 3.67e-04
+2022-05-15 03:10:53,492 INFO [train.py:812] (7/8) Epoch 21, batch 3950, loss[loss=0.1515, simple_loss=0.2314, pruned_loss=0.03575, over 7415.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2522, pruned_loss=0.03525, over 1417406.77 frames.], batch size: 18, lr: 3.67e-04
+2022-05-15 03:11:51,935 INFO [train.py:812] (7/8) Epoch 21, batch 4000, loss[loss=0.148, simple_loss=0.2283, pruned_loss=0.03383, over 7368.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2516, pruned_loss=0.03486, over 1421429.73 frames.], batch size: 19, lr: 3.67e-04
+2022-05-15 03:12:50,977 INFO [train.py:812] (7/8) Epoch 21, batch 4050, loss[loss=0.1878, simple_loss=0.2758, pruned_loss=0.04986, over 5188.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2503, pruned_loss=0.03458, over 1419423.95 frames.], batch size: 52, lr: 3.67e-04
+2022-05-15 03:13:49,301 INFO [train.py:812] (7/8) Epoch 21, batch 4100, loss[loss=0.1722, simple_loss=0.2659, pruned_loss=0.03922, over 7211.00 frames.], tot_loss[loss=0.161, simple_loss=0.2513, pruned_loss=0.0354, over 1410931.27 frames.], batch size: 21, lr: 3.67e-04
+2022-05-15 03:14:46,158 INFO [train.py:812] (7/8) Epoch 21, batch 4150, loss[loss=0.1357, simple_loss=0.2245, pruned_loss=0.0234, over 7070.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2519, pruned_loss=0.03544, over 1412208.93 frames.], batch size: 18, lr: 3.67e-04
+2022-05-15 03:15:43,943 INFO [train.py:812] (7/8) Epoch 21, batch 4200, loss[loss=0.1558, simple_loss=0.2495, pruned_loss=0.03107, over 6789.00 frames.], tot_loss[loss=0.161, simple_loss=0.2516, pruned_loss=0.03521, over 1413002.91 frames.], batch size: 31, lr: 3.67e-04
+2022-05-15 03:16:47,825 INFO [train.py:812] (7/8) Epoch 21, batch 4250, loss[loss=0.149, simple_loss=0.2549, pruned_loss=0.02157, over 7224.00 frames.], tot_loss[loss=0.161, simple_loss=0.2514, pruned_loss=0.03527, over 1417964.69 frames.], batch size: 21, lr: 3.67e-04
+2022-05-15 03:17:46,907 INFO [train.py:812] (7/8) Epoch 21, batch 4300, loss[loss=0.1697, simple_loss=0.256, pruned_loss=0.04175, over 7313.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2511, pruned_loss=0.03507, over 1419531.03 frames.], batch size: 24, lr: 3.67e-04
+2022-05-15 03:18:45,871 INFO [train.py:812] (7/8) Epoch 21, batch 4350, loss[loss=0.1626, simple_loss=0.2596, pruned_loss=0.03279, over 7222.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2509, pruned_loss=0.03473, over 1418709.01 frames.], batch size: 21, lr: 3.67e-04
+2022-05-15 03:19:43,057 INFO [train.py:812] (7/8) Epoch 21, batch 4400, loss[loss=0.1398, simple_loss=0.2198, pruned_loss=0.02992, over 7158.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2509, pruned_loss=0.03463, over 1417401.52 frames.], batch size: 18, lr: 3.66e-04
+2022-05-15 03:20:42,019 INFO [train.py:812] (7/8) Epoch 21, batch 4450, loss[loss=0.1369, simple_loss=0.2142, pruned_loss=0.02985, over 6984.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2509, pruned_loss=0.0349, over 1409271.91 frames.], batch size: 16, lr: 3.66e-04
+2022-05-15 03:21:40,303 INFO [train.py:812] (7/8) Epoch 21, batch 4500, loss[loss=0.1542, simple_loss=0.2321, pruned_loss=0.03818, over 6976.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2513, pruned_loss=0.03494, over 1411168.40 frames.], batch size: 16, lr: 3.66e-04
+2022-05-15 03:22:39,963 INFO [train.py:812] (7/8) Epoch 21, batch 4550, loss[loss=0.1939, simple_loss=0.2752, pruned_loss=0.05633, over 4900.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2505, pruned_loss=0.03533, over 1395560.57 frames.], batch size: 52, lr: 3.66e-04
+2022-05-15 03:23:52,303 INFO [train.py:812] (7/8) Epoch 22, batch 0, loss[loss=0.1809, simple_loss=0.2843, pruned_loss=0.03876, over 7294.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2843, pruned_loss=0.03876, over 7294.00 frames.], batch size: 25, lr: 3.58e-04
+2022-05-15 03:24:50,161 INFO [train.py:812] (7/8) Epoch 22, batch 50, loss[loss=0.1551, simple_loss=0.2456, pruned_loss=0.03227, over 7173.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2522, pruned_loss=0.03522, over 317634.73 frames.], batch size: 18, lr: 3.58e-04
+2022-05-15 03:25:49,163 INFO [train.py:812] (7/8) Epoch 22, batch 100, loss[loss=0.181, simple_loss=0.2774, pruned_loss=0.04232, over 7437.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2509, pruned_loss=0.03468, over 563948.36 frames.], batch size: 22, lr: 3.58e-04
+2022-05-15 03:26:47,203 INFO [train.py:812] (7/8) Epoch 22, batch 150, loss[loss=0.1487, simple_loss=0.2448, pruned_loss=0.02631, over 7320.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2503, pruned_loss=0.03451, over 753653.63 frames.], batch size: 21, lr: 3.58e-04
+2022-05-15 03:27:46,024 INFO [train.py:812] (7/8) Epoch 22, batch 200, loss[loss=0.1669, simple_loss=0.263, pruned_loss=0.0354, over 7342.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2503, pruned_loss=0.0344, over 901627.78 frames.], batch size: 22, lr: 3.58e-04
+2022-05-15 03:28:43,657 INFO [train.py:812] (7/8) Epoch 22, batch 250, loss[loss=0.1515, simple_loss=0.2456, pruned_loss=0.02867, over 7259.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2507, pruned_loss=0.03477, over 1014368.83 frames.], batch size: 19, lr: 3.57e-04
+2022-05-15 03:29:41,583 INFO [train.py:812] (7/8) Epoch 22, batch 300, loss[loss=0.1404, simple_loss=0.2294, pruned_loss=0.0257, over 7241.00 frames.], tot_loss[loss=0.1605, simple_loss=0.251, pruned_loss=0.035, over 1107205.00 frames.], batch size: 20, lr: 3.57e-04
+2022-05-15 03:30:39,483 INFO [train.py:812] (7/8) Epoch 22, batch 350, loss[loss=0.1561, simple_loss=0.2418, pruned_loss=0.03519, over 7162.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2508, pruned_loss=0.03484, over 1177639.92 frames.], batch size: 19, lr: 3.57e-04
+2022-05-15 03:31:38,313 INFO [train.py:812] (7/8) Epoch 22, batch 400, loss[loss=0.1708, simple_loss=0.2725, pruned_loss=0.03453, over 7218.00 frames.], tot_loss[loss=0.16, simple_loss=0.2509, pruned_loss=0.03456, over 1230119.19 frames.], batch size: 21, lr: 3.57e-04
+2022-05-15 03:32:37,225 INFO [train.py:812] (7/8) Epoch 22, batch 450, loss[loss=0.2244, simple_loss=0.3092, pruned_loss=0.06983, over 5051.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2499, pruned_loss=0.03445, over 1273454.12 frames.], batch size: 52, lr: 3.57e-04
+2022-05-15 03:33:36,446 INFO [train.py:812] (7/8) Epoch 22, batch 500, loss[loss=0.1948, simple_loss=0.2897, pruned_loss=0.04999, over 7320.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2512, pruned_loss=0.03493, over 1309535.29 frames.], batch size: 25, lr: 3.57e-04
+2022-05-15 03:34:33,250 INFO [train.py:812] (7/8) Epoch 22, batch 550, loss[loss=0.1873, simple_loss=0.2711, pruned_loss=0.05174, over 7413.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2512, pruned_loss=0.03476, over 1332388.76 frames.], batch size: 20, lr: 3.57e-04
+2022-05-15 03:35:32,172 INFO [train.py:812] (7/8) Epoch 22, batch 600, loss[loss=0.1587, simple_loss=0.2552, pruned_loss=0.0311, over 7346.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2502, pruned_loss=0.03443, over 1353871.51 frames.], batch size: 22, lr: 3.57e-04
+2022-05-15 03:36:31,026 INFO [train.py:812] (7/8) Epoch 22, batch 650, loss[loss=0.1486, simple_loss=0.2474, pruned_loss=0.02494, over 7328.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2512, pruned_loss=0.03465, over 1369865.75 frames.], batch size: 22, lr: 3.57e-04
+2022-05-15 03:37:30,499 INFO [train.py:812] (7/8) Epoch 22, batch 700, loss[loss=0.1916, simple_loss=0.287, pruned_loss=0.04809, over 7336.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2507, pruned_loss=0.03418, over 1377738.70 frames.], batch size: 25, lr: 3.57e-04
+2022-05-15 03:38:28,405 INFO [train.py:812] (7/8) Epoch 22, batch 750, loss[loss=0.1573, simple_loss=0.2382, pruned_loss=0.03822, over 7165.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2503, pruned_loss=0.0342, over 1386518.20 frames.], batch size: 18, lr: 3.57e-04
+2022-05-15 03:39:28,274 INFO [train.py:812] (7/8) Epoch 22, batch 800, loss[loss=0.1938, simple_loss=0.2847, pruned_loss=0.05151, over 7279.00 frames.], tot_loss[loss=0.16, simple_loss=0.251, pruned_loss=0.03446, over 1399237.20 frames.], batch size: 25, lr: 3.56e-04
+2022-05-15 03:40:27,704 INFO [train.py:812] (7/8) Epoch 22, batch 850, loss[loss=0.1609, simple_loss=0.254, pruned_loss=0.03385, over 7402.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2513, pruned_loss=0.03462, over 1405361.63 frames.], batch size: 18, lr: 3.56e-04
+2022-05-15 03:41:26,084 INFO [train.py:812] (7/8) Epoch 22, batch 900, loss[loss=0.1453, simple_loss=0.2414, pruned_loss=0.02462, over 6173.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2518, pruned_loss=0.0348, over 1408030.27 frames.], batch size: 37, lr: 3.56e-04
+2022-05-15 03:42:25,465 INFO [train.py:812] (7/8) Epoch 22, batch 950, loss[loss=0.1673, simple_loss=0.2516, pruned_loss=0.0415, over 7288.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2505, pruned_loss=0.03458, over 1410078.92 frames.], batch size: 18, lr: 3.56e-04
+2022-05-15 03:43:24,223 INFO [train.py:812] (7/8) Epoch 22, batch 1000, loss[loss=0.1438, simple_loss=0.2415, pruned_loss=0.02305, over 7155.00 frames.], tot_loss[loss=0.1604, simple_loss=0.251, pruned_loss=0.03486, over 1410301.19 frames.], batch size: 19, lr: 3.56e-04
+2022-05-15 03:44:23,463 INFO [train.py:812] (7/8) Epoch 22, batch 1050, loss[loss=0.1477, simple_loss=0.25, pruned_loss=0.02269, over 7330.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2506, pruned_loss=0.03495, over 1414315.43 frames.], batch size: 22, lr: 3.56e-04
+2022-05-15 03:45:23,021 INFO [train.py:812] (7/8) Epoch 22, batch 1100, loss[loss=0.1818, simple_loss=0.268, pruned_loss=0.04786, over 6366.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2508, pruned_loss=0.03502, over 1418075.66 frames.], batch size: 38, lr: 3.56e-04
+2022-05-15 03:46:20,356 INFO [train.py:812] (7/8) Epoch 22, batch 1150, loss[loss=0.152, simple_loss=0.2472, pruned_loss=0.02845, over 7253.00 frames.], tot_loss[loss=0.1606, simple_loss=0.251, pruned_loss=0.03513, over 1419766.51 frames.], batch size: 19, lr: 3.56e-04
+2022-05-15 03:47:19,450 INFO [train.py:812] (7/8) Epoch 22, batch 1200, loss[loss=0.169, simple_loss=0.2622, pruned_loss=0.03793, over 7305.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2509, pruned_loss=0.03549, over 1421475.83 frames.], batch size: 25, lr: 3.56e-04
+2022-05-15 03:48:18,965 INFO [train.py:812] (7/8) Epoch 22, batch 1250, loss[loss=0.1534, simple_loss=0.2314, pruned_loss=0.03765, over 7006.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2507, pruned_loss=0.03509, over 1420780.09 frames.], batch size: 16, lr: 3.56e-04
+2022-05-15 03:49:19,181 INFO [train.py:812] (7/8) Epoch 22, batch 1300, loss[loss=0.1584, simple_loss=0.2533, pruned_loss=0.03178, over 7155.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2512, pruned_loss=0.03535, over 1419194.73 frames.], batch size: 19, lr: 3.56e-04
+2022-05-15 03:50:16,187 INFO [train.py:812] (7/8) Epoch 22, batch 1350, loss[loss=0.1912, simple_loss=0.2772, pruned_loss=0.05255, over 7418.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2505, pruned_loss=0.03503, over 1422988.12 frames.], batch size: 21, lr: 3.55e-04
+2022-05-15 03:51:15,345 INFO [train.py:812] (7/8) Epoch 22, batch 1400, loss[loss=0.1549, simple_loss=0.2515, pruned_loss=0.0292, over 7219.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2504, pruned_loss=0.035, over 1419806.96 frames.], batch size: 22, lr: 3.55e-04
+2022-05-15 03:52:14,151 INFO [train.py:812] (7/8) Epoch 22, batch 1450, loss[loss=0.169, simple_loss=0.2586, pruned_loss=0.03964, over 7432.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2506, pruned_loss=0.03488, over 1424577.28 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:53:13,836 INFO [train.py:812] (7/8) Epoch 22, batch 1500, loss[loss=0.1399, simple_loss=0.2379, pruned_loss=0.02097, over 7230.00 frames.], tot_loss[loss=0.1593, simple_loss=0.25, pruned_loss=0.03427, over 1425836.48 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:54:13,344 INFO [train.py:812] (7/8) Epoch 22, batch 1550, loss[loss=0.1572, simple_loss=0.2522, pruned_loss=0.03114, over 7234.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2495, pruned_loss=0.0342, over 1428385.47 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:55:12,263 INFO [train.py:812] (7/8) Epoch 22, batch 1600, loss[loss=0.1301, simple_loss=0.2104, pruned_loss=0.02489, over 6846.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2498, pruned_loss=0.0343, over 1429211.09 frames.], batch size: 15, lr: 3.55e-04
+2022-05-15 03:56:09,002 INFO [train.py:812] (7/8) Epoch 22, batch 1650, loss[loss=0.1476, simple_loss=0.2426, pruned_loss=0.02623, over 6725.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2504, pruned_loss=0.03431, over 1431308.97 frames.], batch size: 31, lr: 3.55e-04
+2022-05-15 03:57:07,065 INFO [train.py:812] (7/8) Epoch 22, batch 1700, loss[loss=0.172, simple_loss=0.2772, pruned_loss=0.03337, over 7325.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2489, pruned_loss=0.0337, over 1433340.40 frames.], batch size: 22, lr: 3.55e-04
+2022-05-15 03:58:03,892 INFO [train.py:812] (7/8) Epoch 22, batch 1750, loss[loss=0.1717, simple_loss=0.262, pruned_loss=0.04066, over 7232.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2491, pruned_loss=0.03366, over 1432965.14 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:59:03,638 INFO [train.py:812] (7/8) Epoch 22, batch 1800, loss[loss=0.1345, simple_loss=0.2177, pruned_loss=0.02567, over 7289.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2489, pruned_loss=0.03372, over 1430298.50 frames.], batch size: 17, lr: 3.55e-04
+2022-05-15 04:00:02,123 INFO [train.py:812] (7/8) Epoch 22, batch 1850, loss[loss=0.1655, simple_loss=0.2657, pruned_loss=0.03264, over 6495.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2488, pruned_loss=0.03394, over 1425868.07 frames.], batch size: 38, lr: 3.55e-04
+2022-05-15 04:01:00,869 INFO [train.py:812] (7/8) Epoch 22, batch 1900, loss[loss=0.2094, simple_loss=0.2898, pruned_loss=0.06449, over 4971.00 frames.], tot_loss[loss=0.159, simple_loss=0.2494, pruned_loss=0.03435, over 1424607.05 frames.], batch size: 52, lr: 3.54e-04
+2022-05-15 04:02:00,151 INFO [train.py:812] (7/8) Epoch 22, batch 1950, loss[loss=0.1543, simple_loss=0.2365, pruned_loss=0.0361, over 7267.00 frames.], tot_loss[loss=0.1588, simple_loss=0.249, pruned_loss=0.03428, over 1425578.91 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:02:59,585 INFO [train.py:812] (7/8) Epoch 22, batch 2000, loss[loss=0.1559, simple_loss=0.2594, pruned_loss=0.02623, over 7337.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2498, pruned_loss=0.03425, over 1427330.77 frames.], batch size: 20, lr: 3.54e-04
+2022-05-15 04:03:58,520 INFO [train.py:812] (7/8) Epoch 22, batch 2050, loss[loss=0.1434, simple_loss=0.2276, pruned_loss=0.02958, over 7286.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2502, pruned_loss=0.03428, over 1428369.10 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:04:58,120 INFO [train.py:812] (7/8) Epoch 22, batch 2100, loss[loss=0.1545, simple_loss=0.2393, pruned_loss=0.03483, over 7422.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2504, pruned_loss=0.0344, over 1426820.13 frames.], batch size: 18, lr: 3.54e-04
+2022-05-15 04:05:56,591 INFO [train.py:812] (7/8) Epoch 22, batch 2150, loss[loss=0.1449, simple_loss=0.2355, pruned_loss=0.02712, over 7171.00 frames.], tot_loss[loss=0.159, simple_loss=0.2497, pruned_loss=0.03413, over 1423437.42 frames.], batch size: 18, lr: 3.54e-04
+2022-05-15 04:06:54,955 INFO [train.py:812] (7/8) Epoch 22, batch 2200, loss[loss=0.2067, simple_loss=0.2899, pruned_loss=0.06173, over 7119.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2497, pruned_loss=0.03422, over 1426486.50 frames.], batch size: 21, lr: 3.54e-04
+2022-05-15 04:07:52,636 INFO [train.py:812] (7/8) Epoch 22, batch 2250, loss[loss=0.1414, simple_loss=0.2219, pruned_loss=0.03041, over 7201.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2503, pruned_loss=0.03448, over 1423798.20 frames.], batch size: 16, lr: 3.54e-04
+2022-05-15 04:08:49,596 INFO [train.py:812] (7/8) Epoch 22, batch 2300, loss[loss=0.2198, simple_loss=0.2974, pruned_loss=0.07103, over 5063.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2512, pruned_loss=0.03482, over 1424979.85 frames.], batch size: 53, lr: 3.54e-04
+2022-05-15 04:09:47,988 INFO [train.py:812] (7/8) Epoch 22, batch 2350, loss[loss=0.1767, simple_loss=0.2622, pruned_loss=0.04563, over 6447.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2512, pruned_loss=0.03514, over 1427829.62 frames.], batch size: 38, lr: 3.54e-04
+2022-05-15 04:10:57,223 INFO [train.py:812] (7/8) Epoch 22, batch 2400, loss[loss=0.1231, simple_loss=0.2029, pruned_loss=0.02161, over 7143.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2507, pruned_loss=0.03504, over 1426517.65 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:11:56,433 INFO [train.py:812] (7/8) Epoch 22, batch 2450, loss[loss=0.156, simple_loss=0.2323, pruned_loss=0.03984, over 7278.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2509, pruned_loss=0.03498, over 1424582.70 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:12:56,118 INFO [train.py:812] (7/8) Epoch 22, batch 2500, loss[loss=0.1573, simple_loss=0.2529, pruned_loss=0.03084, over 7420.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2505, pruned_loss=0.03443, over 1421951.65 frames.], batch size: 21, lr: 3.53e-04
+2022-05-15 04:13:55,282 INFO [train.py:812] (7/8) Epoch 22, batch 2550, loss[loss=0.1981, simple_loss=0.2776, pruned_loss=0.05934, over 7071.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2512, pruned_loss=0.03483, over 1420225.14 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:14:54,445 INFO [train.py:812] (7/8) Epoch 22, batch 2600, loss[loss=0.1489, simple_loss=0.2403, pruned_loss=0.02873, over 7161.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2517, pruned_loss=0.03462, over 1416622.32 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:15:53,335 INFO [train.py:812] (7/8) Epoch 22, batch 2650, loss[loss=0.1639, simple_loss=0.2468, pruned_loss=0.04055, over 7266.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2505, pruned_loss=0.03439, over 1420259.31 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:16:52,256 INFO [train.py:812] (7/8) Epoch 22, batch 2700, loss[loss=0.1438, simple_loss=0.2304, pruned_loss=0.02864, over 7155.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2492, pruned_loss=0.03381, over 1418942.34 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:17:51,023 INFO [train.py:812] (7/8) Epoch 22, batch 2750, loss[loss=0.1477, simple_loss=0.2408, pruned_loss=0.02736, over 7057.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2495, pruned_loss=0.03362, over 1419099.36 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:18:49,843 INFO [train.py:812] (7/8) Epoch 22, batch 2800, loss[loss=0.1259, simple_loss=0.2094, pruned_loss=0.02119, over 7291.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2496, pruned_loss=0.0338, over 1419693.88 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:19:48,500 INFO [train.py:812] (7/8) Epoch 22, batch 2850, loss[loss=0.1531, simple_loss=0.2455, pruned_loss=0.03034, over 7164.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2492, pruned_loss=0.03397, over 1417815.30 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:20:47,867 INFO [train.py:812] (7/8) Epoch 22, batch 2900, loss[loss=0.1399, simple_loss=0.2326, pruned_loss=0.02359, over 7162.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2489, pruned_loss=0.0341, over 1420636.03 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:21:47,238 INFO [train.py:812] (7/8) Epoch 22, batch 2950, loss[loss=0.167, simple_loss=0.256, pruned_loss=0.03897, over 7401.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2488, pruned_loss=0.03425, over 1421857.02 frames.], batch size: 21, lr: 3.53e-04
+2022-05-15 04:22:47,064 INFO [train.py:812] (7/8) Epoch 22, batch 3000, loss[loss=0.1356, simple_loss=0.2165, pruned_loss=0.02735, over 7157.00 frames.], tot_loss[loss=0.159, simple_loss=0.2491, pruned_loss=0.03438, over 1425683.55 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:22:47,065 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 04:22:54,482 INFO [train.py:841] (7/8) Epoch 22, validation: loss=0.1529, simple_loss=0.2512, pruned_loss=0.02731, over 698248.00 frames.
+2022-05-15 04:23:53,749 INFO [train.py:812] (7/8) Epoch 22, batch 3050, loss[loss=0.1805, simple_loss=0.2744, pruned_loss=0.04328, over 7047.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2493, pruned_loss=0.03443, over 1427442.24 frames.], batch size: 28, lr: 3.52e-04
+2022-05-15 04:24:53,810 INFO [train.py:812] (7/8) Epoch 22, batch 3100, loss[loss=0.2191, simple_loss=0.2939, pruned_loss=0.07212, over 5465.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2491, pruned_loss=0.03432, over 1427469.08 frames.], batch size: 54, lr: 3.52e-04
+2022-05-15 04:25:52,403 INFO [train.py:812] (7/8) Epoch 22, batch 3150, loss[loss=0.1903, simple_loss=0.2765, pruned_loss=0.05207, over 7412.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2488, pruned_loss=0.03428, over 1426132.21 frames.], batch size: 21, lr: 3.52e-04
+2022-05-15 04:26:51,019 INFO [train.py:812] (7/8) Epoch 22, batch 3200, loss[loss=0.1585, simple_loss=0.2489, pruned_loss=0.03406, over 7062.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2488, pruned_loss=0.03473, over 1426674.72 frames.], batch size: 18, lr: 3.52e-04
+2022-05-15 04:27:50,227 INFO [train.py:812] (7/8) Epoch 22, batch 3250, loss[loss=0.1323, simple_loss=0.2225, pruned_loss=0.021, over 7428.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2497, pruned_loss=0.03479, over 1428210.70 frames.], batch size: 17, lr: 3.52e-04
+2022-05-15 04:28:47,796 INFO [train.py:812] (7/8) Epoch 22, batch 3300, loss[loss=0.1366, simple_loss=0.229, pruned_loss=0.02214, over 7434.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2508, pruned_loss=0.03495, over 1430909.86 frames.], batch size: 20, lr: 3.52e-04
+2022-05-15 04:29:46,935 INFO [train.py:812] (7/8) Epoch 22, batch 3350, loss[loss=0.1424, simple_loss=0.2312, pruned_loss=0.02685, over 7357.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2511, pruned_loss=0.03465, over 1429175.24 frames.], batch size: 19, lr: 3.52e-04
+2022-05-15 04:30:46,421 INFO [train.py:812] (7/8) Epoch 22, batch 3400, loss[loss=0.1653, simple_loss=0.2577, pruned_loss=0.03639, over 7141.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2506, pruned_loss=0.03421, over 1426066.16 frames.], batch size: 17, lr: 3.52e-04
+2022-05-15 04:31:45,565 INFO [train.py:812] (7/8) Epoch 22, batch 3450, loss[loss=0.1621, simple_loss=0.2659, pruned_loss=0.02916, over 7338.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2503, pruned_loss=0.03422, over 1427223.73 frames.], batch size: 22, lr: 3.52e-04
+2022-05-15 04:32:45,132 INFO [train.py:812] (7/8) Epoch 22, batch 3500, loss[loss=0.1611, simple_loss=0.2562, pruned_loss=0.03302, over 7349.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2503, pruned_loss=0.03417, over 1429569.03 frames.], batch size: 22, lr: 3.52e-04
+2022-05-15 04:33:44,177 INFO [train.py:812] (7/8) Epoch 22, batch 3550, loss[loss=0.1641, simple_loss=0.2599, pruned_loss=0.0341, over 6694.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2507, pruned_loss=0.03447, over 1427444.95 frames.], batch size: 31, lr: 3.52e-04
+2022-05-15 04:34:43,581 INFO [train.py:812] (7/8) Epoch 22, batch 3600, loss[loss=0.1291, simple_loss=0.2145, pruned_loss=0.02187, over 7289.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2506, pruned_loss=0.0345, over 1421647.31 frames.], batch size: 17, lr: 3.51e-04
+2022-05-15 04:35:42,274 INFO [train.py:812] (7/8) Epoch 22, batch 3650, loss[loss=0.1929, simple_loss=0.2751, pruned_loss=0.05536, over 7372.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2514, pruned_loss=0.03519, over 1423844.15 frames.], batch size: 23, lr: 3.51e-04
+2022-05-15 04:36:47,205 INFO [train.py:812] (7/8) Epoch 22, batch 3700, loss[loss=0.1696, simple_loss=0.2578, pruned_loss=0.04074, over 7219.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2509, pruned_loss=0.03482, over 1426157.86 frames.], batch size: 21, lr: 3.51e-04
+2022-05-15 04:37:46,516 INFO [train.py:812] (7/8) Epoch 22, batch 3750, loss[loss=0.1544, simple_loss=0.23, pruned_loss=0.03943, over 7005.00 frames.], tot_loss[loss=0.1605, simple_loss=0.251, pruned_loss=0.03495, over 1430598.87 frames.], batch size: 16, lr: 3.51e-04
+2022-05-15 04:38:46,137 INFO [train.py:812] (7/8) Epoch 22, batch 3800, loss[loss=0.1844, simple_loss=0.2704, pruned_loss=0.04922, over 4956.00 frames.], tot_loss[loss=0.16, simple_loss=0.2504, pruned_loss=0.03482, over 1424951.88 frames.], batch size: 52, lr: 3.51e-04
+2022-05-15 04:39:43,968 INFO [train.py:812] (7/8) Epoch 22, batch 3850, loss[loss=0.1783, simple_loss=0.2716, pruned_loss=0.04246, over 7238.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2499, pruned_loss=0.03421, over 1427146.36 frames.], batch size: 20, lr: 3.51e-04
+2022-05-15 04:40:43,543 INFO [train.py:812] (7/8) Epoch 22, batch 3900, loss[loss=0.1583, simple_loss=0.2491, pruned_loss=0.0337, over 6348.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2489, pruned_loss=0.03371, over 1427876.96 frames.], batch size: 38, lr: 3.51e-04
+2022-05-15 04:41:41,348 INFO [train.py:812] (7/8) Epoch 22, batch 3950, loss[loss=0.1619, simple_loss=0.2318, pruned_loss=0.04598, over 7291.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2492, pruned_loss=0.03425, over 1425724.18 frames.], batch size: 17, lr: 3.51e-04
+2022-05-15 04:42:39,875 INFO [train.py:812] (7/8) Epoch 22, batch 4000, loss[loss=0.1612, simple_loss=0.267, pruned_loss=0.02774, over 7325.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2507, pruned_loss=0.03493, over 1425871.56 frames.], batch size: 21, lr: 3.51e-04
+2022-05-15 04:43:37,324 INFO [train.py:812] (7/8) Epoch 22, batch 4050, loss[loss=0.1478, simple_loss=0.234, pruned_loss=0.03079, over 7350.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2499, pruned_loss=0.03429, over 1424074.88 frames.], batch size: 19, lr: 3.51e-04
+2022-05-15 04:44:35,641 INFO [train.py:812] (7/8) Epoch 22, batch 4100, loss[loss=0.1439, simple_loss=0.2326, pruned_loss=0.02759, over 7335.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2504, pruned_loss=0.03445, over 1425655.42 frames.], batch size: 20, lr: 3.51e-04
+2022-05-15 04:45:34,822 INFO [train.py:812] (7/8) Epoch 22, batch 4150, loss[loss=0.1443, simple_loss=0.2326, pruned_loss=0.02796, over 7067.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2496, pruned_loss=0.03425, over 1421190.07 frames.], batch size: 18, lr: 3.51e-04
+2022-05-15 04:46:33,531 INFO [train.py:812] (7/8) Epoch 22, batch 4200, loss[loss=0.1644, simple_loss=0.2526, pruned_loss=0.03813, over 7144.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2507, pruned_loss=0.03484, over 1416183.77 frames.], batch size: 20, lr: 3.50e-04
+2022-05-15 04:47:30,311 INFO [train.py:812] (7/8) Epoch 22, batch 4250, loss[loss=0.1575, simple_loss=0.2544, pruned_loss=0.03027, over 6709.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2523, pruned_loss=0.03558, over 1409467.81 frames.], batch size: 31, lr: 3.50e-04
+2022-05-15 04:48:27,313 INFO [train.py:812] (7/8) Epoch 22, batch 4300, loss[loss=0.2007, simple_loss=0.2971, pruned_loss=0.0522, over 7294.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2528, pruned_loss=0.03549, over 1411144.69 frames.], batch size: 24, lr: 3.50e-04
+2022-05-15 04:49:26,549 INFO [train.py:812] (7/8) Epoch 22, batch 4350, loss[loss=0.1596, simple_loss=0.2616, pruned_loss=0.02887, over 7326.00 frames.], tot_loss[loss=0.1617, simple_loss=0.253, pruned_loss=0.03526, over 1407530.44 frames.], batch size: 22, lr: 3.50e-04
+2022-05-15 04:50:35,290 INFO [train.py:812] (7/8) Epoch 22, batch 4400, loss[loss=0.1392, simple_loss=0.234, pruned_loss=0.02221, over 7127.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2528, pruned_loss=0.03515, over 1401824.92 frames.], batch size: 21, lr: 3.50e-04
+2022-05-15 04:51:33,792 INFO [train.py:812] (7/8) Epoch 22, batch 4450, loss[loss=0.1499, simple_loss=0.2483, pruned_loss=0.02571, over 7335.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2533, pruned_loss=0.03542, over 1399509.41 frames.], batch size: 22, lr: 3.50e-04
+2022-05-15 04:52:33,309 INFO [train.py:812] (7/8) Epoch 22, batch 4500, loss[loss=0.1709, simple_loss=0.2737, pruned_loss=0.03398, over 7068.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2544, pruned_loss=0.03588, over 1389409.98 frames.], batch size: 28, lr: 3.50e-04
+2022-05-15 04:53:50,578 INFO [train.py:812] (7/8) Epoch 22, batch 4550, loss[loss=0.224, simple_loss=0.294, pruned_loss=0.07696, over 4985.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2557, pruned_loss=0.03722, over 1347233.88 frames.], batch size: 52, lr: 3.50e-04
+2022-05-15 04:55:29,977 INFO [train.py:812] (7/8) Epoch 23, batch 0, loss[loss=0.1449, simple_loss=0.2264, pruned_loss=0.03171, over 6771.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2264, pruned_loss=0.03171, over 6771.00 frames.], batch size: 15, lr: 3.42e-04
+2022-05-15 04:56:28,555 INFO [train.py:812] (7/8) Epoch 23, batch 50, loss[loss=0.1404, simple_loss=0.2411, pruned_loss=0.01985, over 7150.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2482, pruned_loss=0.03319, over 318936.21 frames.], batch size: 19, lr: 3.42e-04
+2022-05-15 04:57:26,802 INFO [train.py:812] (7/8) Epoch 23, batch 100, loss[loss=0.1752, simple_loss=0.2608, pruned_loss=0.04477, over 7279.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2498, pruned_loss=0.03349, over 565232.94 frames.], batch size: 18, lr: 3.42e-04
+2022-05-15 04:58:25,177 INFO [train.py:812] (7/8) Epoch 23, batch 150, loss[loss=0.199, simple_loss=0.282, pruned_loss=0.05803, over 7302.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2506, pruned_loss=0.03413, over 754018.87 frames.], batch size: 24, lr: 3.42e-04
+2022-05-15 04:59:34,202 INFO [train.py:812] (7/8) Epoch 23, batch 200, loss[loss=0.1561, simple_loss=0.2571, pruned_loss=0.02756, over 6304.00 frames.], tot_loss[loss=0.158, simple_loss=0.2498, pruned_loss=0.03308, over 902429.45 frames.], batch size: 37, lr: 3.42e-04
+2022-05-15 05:00:33,226 INFO [train.py:812] (7/8) Epoch 23, batch 250, loss[loss=0.1715, simple_loss=0.2601, pruned_loss=0.04145, over 7206.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2509, pruned_loss=0.03394, over 1017218.43 frames.], batch size: 23, lr: 3.42e-04
+2022-05-15 05:01:30,520 INFO [train.py:812] (7/8) Epoch 23, batch 300, loss[loss=0.1437, simple_loss=0.2378, pruned_loss=0.02476, over 7162.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2506, pruned_loss=0.03428, over 1102881.36 frames.], batch size: 19, lr: 3.42e-04
+2022-05-15 05:02:29,220 INFO [train.py:812] (7/8) Epoch 23, batch 350, loss[loss=0.1655, simple_loss=0.2644, pruned_loss=0.03331, over 7323.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2505, pruned_loss=0.03435, over 1177303.48 frames.], batch size: 22, lr: 3.42e-04
+2022-05-15 05:03:27,324 INFO [train.py:812] (7/8) Epoch 23, batch 400, loss[loss=0.1597, simple_loss=0.2472, pruned_loss=0.03611, over 7208.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2495, pruned_loss=0.03373, over 1230138.95 frames.], batch size: 23, lr: 3.42e-04
+2022-05-15 05:04:26,546 INFO [train.py:812] (7/8) Epoch 23, batch 450, loss[loss=0.1911, simple_loss=0.2809, pruned_loss=0.05068, over 7276.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2505, pruned_loss=0.0343, over 1271540.78 frames.], batch size: 24, lr: 3.42e-04
+2022-05-15 05:05:24,828 INFO [train.py:812] (7/8) Epoch 23, batch 500, loss[loss=0.1474, simple_loss=0.2337, pruned_loss=0.0305, over 6759.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2511, pruned_loss=0.03436, over 1306512.83 frames.], batch size: 15, lr: 3.41e-04
+2022-05-15 05:06:22,003 INFO [train.py:812] (7/8) Epoch 23, batch 550, loss[loss=0.1609, simple_loss=0.2503, pruned_loss=0.03574, over 7320.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2498, pruned_loss=0.03421, over 1336983.65 frames.], batch size: 24, lr: 3.41e-04
+2022-05-15 05:07:20,830 INFO [train.py:812] (7/8) Epoch 23, batch 600, loss[loss=0.178, simple_loss=0.2693, pruned_loss=0.04336, over 7114.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2505, pruned_loss=0.03432, over 1359353.17 frames.], batch size: 21, lr: 3.41e-04
+2022-05-15 05:08:19,875 INFO [train.py:812] (7/8) Epoch 23, batch 650, loss[loss=0.1503, simple_loss=0.2453, pruned_loss=0.02764, over 6841.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2509, pruned_loss=0.03438, over 1374622.36 frames.], batch size: 31, lr: 3.41e-04
+2022-05-15 05:09:19,438 INFO [train.py:812] (7/8) Epoch 23, batch 700, loss[loss=0.1848, simple_loss=0.2705, pruned_loss=0.04952, over 4657.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2512, pruned_loss=0.03464, over 1380624.23 frames.], batch size: 52, lr: 3.41e-04
+2022-05-15 05:10:18,471 INFO [train.py:812] (7/8) Epoch 23, batch 750, loss[loss=0.1487, simple_loss=0.2474, pruned_loss=0.02503, over 7209.00 frames.], tot_loss[loss=0.1597, simple_loss=0.251, pruned_loss=0.03416, over 1391879.82 frames.], batch size: 23, lr: 3.41e-04
+2022-05-15 05:11:17,844 INFO [train.py:812] (7/8) Epoch 23, batch 800, loss[loss=0.1645, simple_loss=0.2492, pruned_loss=0.0399, over 7361.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2512, pruned_loss=0.03433, over 1395431.72 frames.], batch size: 19, lr: 3.41e-04
+2022-05-15 05:12:15,531 INFO [train.py:812] (7/8) Epoch 23, batch 850, loss[loss=0.1548, simple_loss=0.2455, pruned_loss=0.03208, over 7431.00 frames.], tot_loss[loss=0.1599, simple_loss=0.251, pruned_loss=0.03436, over 1403998.98 frames.], batch size: 20, lr: 3.41e-04
+2022-05-15 05:13:14,548 INFO [train.py:812] (7/8) Epoch 23, batch 900, loss[loss=0.1536, simple_loss=0.2435, pruned_loss=0.03187, over 7144.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2506, pruned_loss=0.03403, over 1408364.14 frames.], batch size: 19, lr: 3.41e-04
+2022-05-15 05:14:13,249 INFO [train.py:812] (7/8) Epoch 23, batch 950, loss[loss=0.1972, simple_loss=0.2952, pruned_loss=0.04962, over 7050.00 frames.], tot_loss[loss=0.1594, simple_loss=0.251, pruned_loss=0.03395, over 1410568.31 frames.], batch size: 28, lr: 3.41e-04
+2022-05-15 05:15:13,131 INFO [train.py:812] (7/8) Epoch 23, batch 1000, loss[loss=0.1371, simple_loss=0.2239, pruned_loss=0.02511, over 7362.00 frames.], tot_loss[loss=0.159, simple_loss=0.2505, pruned_loss=0.03372, over 1417540.06 frames.], batch size: 19, lr: 3.41e-04
+2022-05-15 05:16:12,083 INFO [train.py:812] (7/8) Epoch 23, batch 1050, loss[loss=0.1968, simple_loss=0.2833, pruned_loss=0.05519, over 5329.00 frames.], tot_loss[loss=0.159, simple_loss=0.2503, pruned_loss=0.03388, over 1418430.09 frames.], batch size: 52, lr: 3.41e-04
+2022-05-15 05:17:10,939 INFO [train.py:812] (7/8) Epoch 23, batch 1100, loss[loss=0.1385, simple_loss=0.2283, pruned_loss=0.0244, over 7282.00 frames.], tot_loss[loss=0.16, simple_loss=0.2514, pruned_loss=0.03427, over 1417995.07 frames.], batch size: 17, lr: 3.40e-04
+2022-05-15 05:18:09,898 INFO [train.py:812] (7/8) Epoch 23, batch 1150, loss[loss=0.1532, simple_loss=0.2492, pruned_loss=0.02857, over 7427.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2522, pruned_loss=0.03448, over 1422006.13 frames.], batch size: 20, lr: 3.40e-04
+2022-05-15 05:19:09,559 INFO [train.py:812] (7/8) Epoch 23, batch 1200, loss[loss=0.1479, simple_loss=0.2466, pruned_loss=0.02458, over 7277.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2514, pruned_loss=0.03473, over 1422058.00 frames.], batch size: 18, lr: 3.40e-04
+2022-05-15 05:20:07,313 INFO [train.py:812] (7/8) Epoch 23, batch 1250, loss[loss=0.1442, simple_loss=0.2242, pruned_loss=0.03211, over 7196.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2504, pruned_loss=0.03426, over 1425475.55 frames.], batch size: 16, lr: 3.40e-04
+2022-05-15 05:21:05,567 INFO [train.py:812] (7/8) Epoch 23, batch 1300, loss[loss=0.177, simple_loss=0.2703, pruned_loss=0.04189, over 7188.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2509, pruned_loss=0.03489, over 1427576.69 frames.], batch size: 23, lr: 3.40e-04
+2022-05-15 05:22:03,031 INFO [train.py:812] (7/8) Epoch 23, batch 1350, loss[loss=0.1552, simple_loss=0.2447, pruned_loss=0.0328, over 7266.00 frames.], tot_loss[loss=0.1596, simple_loss=0.25, pruned_loss=0.03458, over 1428385.37 frames.], batch size: 18, lr: 3.40e-04
+2022-05-15 05:23:02,494 INFO [train.py:812] (7/8) Epoch 23, batch 1400, loss[loss=0.1856, simple_loss=0.2742, pruned_loss=0.04851, over 7110.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2511, pruned_loss=0.03477, over 1427559.48 frames.], batch size: 21, lr: 3.40e-04
+2022-05-15 05:24:01,091 INFO [train.py:812] (7/8) Epoch 23, batch 1450, loss[loss=0.1325, simple_loss=0.2259, pruned_loss=0.01954, over 7433.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2506, pruned_loss=0.03457, over 1421490.11 frames.], batch size: 18, lr: 3.40e-04
+2022-05-15 05:24:59,744 INFO [train.py:812] (7/8) Epoch 23, batch 1500, loss[loss=0.155, simple_loss=0.2426, pruned_loss=0.03373, over 7046.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2488, pruned_loss=0.03421, over 1422347.19 frames.], batch size: 28, lr: 3.40e-04
+2022-05-15 05:25:58,368 INFO [train.py:812] (7/8) Epoch 23, batch 1550, loss[loss=0.1436, simple_loss=0.2307, pruned_loss=0.02819, over 7365.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2489, pruned_loss=0.0341, over 1413155.40 frames.], batch size: 19, lr: 3.40e-04
+2022-05-15 05:26:57,187 INFO [train.py:812] (7/8) Epoch 23, batch 1600, loss[loss=0.1618, simple_loss=0.2611, pruned_loss=0.03129, over 7215.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2497, pruned_loss=0.0345, over 1411114.69 frames.], batch size: 21, lr: 3.40e-04
+2022-05-15 05:27:55,194 INFO [train.py:812] (7/8) Epoch 23, batch 1650, loss[loss=0.1602, simple_loss=0.2592, pruned_loss=0.03062, over 7368.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2491, pruned_loss=0.03431, over 1414881.59 frames.], batch size: 23, lr: 3.40e-04
+2022-05-15 05:28:54,121 INFO [train.py:812] (7/8) Epoch 23, batch 1700, loss[loss=0.1374, simple_loss=0.2195, pruned_loss=0.02767, over 7397.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2489, pruned_loss=0.03406, over 1416342.08 frames.], batch size: 18, lr: 3.39e-04
+2022-05-15 05:29:50,578 INFO [train.py:812] (7/8) Epoch 23, batch 1750, loss[loss=0.1854, simple_loss=0.2783, pruned_loss=0.04625, over 7161.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2496, pruned_loss=0.03429, over 1415392.29 frames.], batch size: 26, lr: 3.39e-04
+2022-05-15 05:30:48,724 INFO [train.py:812] (7/8) Epoch 23, batch 1800, loss[loss=0.2048, simple_loss=0.2911, pruned_loss=0.05923, over 5257.00 frames.], tot_loss[loss=0.1594, simple_loss=0.25, pruned_loss=0.03436, over 1412108.12 frames.], batch size: 52, lr: 3.39e-04
+2022-05-15 05:31:46,108 INFO [train.py:812] (7/8) Epoch 23, batch 1850, loss[loss=0.141, simple_loss=0.2345, pruned_loss=0.02374, over 7444.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2487, pruned_loss=0.03381, over 1417123.41 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:32:44,012 INFO [train.py:812] (7/8) Epoch 23, batch 1900, loss[loss=0.1791, simple_loss=0.2697, pruned_loss=0.04423, over 7148.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2486, pruned_loss=0.03382, over 1420904.44 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:33:42,370 INFO [train.py:812] (7/8) Epoch 23, batch 1950, loss[loss=0.1708, simple_loss=0.2637, pruned_loss=0.03894, over 7152.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2493, pruned_loss=0.03432, over 1417895.69 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:34:41,211 INFO [train.py:812] (7/8) Epoch 23, batch 2000, loss[loss=0.1408, simple_loss=0.231, pruned_loss=0.02527, over 7254.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2509, pruned_loss=0.0346, over 1421499.30 frames.], batch size: 19, lr: 3.39e-04
+2022-05-15 05:35:40,309 INFO [train.py:812] (7/8) Epoch 23, batch 2050, loss[loss=0.1689, simple_loss=0.2629, pruned_loss=0.03741, over 7232.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2507, pruned_loss=0.03448, over 1425430.35 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:36:39,486 INFO [train.py:812] (7/8) Epoch 23, batch 2100, loss[loss=0.1742, simple_loss=0.2654, pruned_loss=0.04147, over 7179.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2505, pruned_loss=0.03456, over 1420475.00 frames.], batch size: 23, lr: 3.39e-04
+2022-05-15 05:37:37,967 INFO [train.py:812] (7/8) Epoch 23, batch 2150, loss[loss=0.1619, simple_loss=0.2532, pruned_loss=0.0353, over 7155.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2494, pruned_loss=0.03418, over 1421028.47 frames.], batch size: 19, lr: 3.39e-04
+2022-05-15 05:38:37,653 INFO [train.py:812] (7/8) Epoch 23, batch 2200, loss[loss=0.1472, simple_loss=0.2472, pruned_loss=0.02355, over 7151.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2491, pruned_loss=0.03436, over 1415328.16 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:39:36,714 INFO [train.py:812] (7/8) Epoch 23, batch 2250, loss[loss=0.1895, simple_loss=0.2627, pruned_loss=0.05819, over 7157.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2492, pruned_loss=0.03427, over 1411564.30 frames.], batch size: 19, lr: 3.39e-04
+2022-05-15 05:40:35,598 INFO [train.py:812] (7/8) Epoch 23, batch 2300, loss[loss=0.1837, simple_loss=0.2815, pruned_loss=0.0429, over 7314.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2495, pruned_loss=0.03444, over 1414455.66 frames.], batch size: 21, lr: 3.38e-04
+2022-05-15 05:41:34,400 INFO [train.py:812] (7/8) Epoch 23, batch 2350, loss[loss=0.1602, simple_loss=0.251, pruned_loss=0.03475, over 7338.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2501, pruned_loss=0.03447, over 1415916.98 frames.], batch size: 22, lr: 3.38e-04
+2022-05-15 05:42:33,227 INFO [train.py:812] (7/8) Epoch 23, batch 2400, loss[loss=0.1664, simple_loss=0.2575, pruned_loss=0.03765, over 7264.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2505, pruned_loss=0.03456, over 1418141.16 frames.], batch size: 24, lr: 3.38e-04
+2022-05-15 05:43:31,245 INFO [train.py:812] (7/8) Epoch 23, batch 2450, loss[loss=0.1537, simple_loss=0.2436, pruned_loss=0.0319, over 7208.00 frames.], tot_loss[loss=0.16, simple_loss=0.251, pruned_loss=0.03453, over 1422309.12 frames.], batch size: 22, lr: 3.38e-04
+2022-05-15 05:44:30,357 INFO [train.py:812] (7/8) Epoch 23, batch 2500, loss[loss=0.148, simple_loss=0.2437, pruned_loss=0.02613, over 6443.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2485, pruned_loss=0.03365, over 1420465.12 frames.], batch size: 38, lr: 3.38e-04
+2022-05-15 05:45:29,348 INFO [train.py:812] (7/8) Epoch 23, batch 2550, loss[loss=0.1726, simple_loss=0.2724, pruned_loss=0.03643, over 7382.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2488, pruned_loss=0.03352, over 1421985.86 frames.], batch size: 23, lr: 3.38e-04
+2022-05-15 05:46:26,785 INFO [train.py:812] (7/8) Epoch 23, batch 2600, loss[loss=0.1472, simple_loss=0.238, pruned_loss=0.0282, over 7338.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2495, pruned_loss=0.03374, over 1427368.57 frames.], batch size: 22, lr: 3.38e-04
+2022-05-15 05:47:25,328 INFO [train.py:812] (7/8) Epoch 23, batch 2650, loss[loss=0.1621, simple_loss=0.2621, pruned_loss=0.03103, over 7323.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2483, pruned_loss=0.03375, over 1424156.49 frames.], batch size: 25, lr: 3.38e-04
+2022-05-15 05:48:25,327 INFO [train.py:812] (7/8) Epoch 23, batch 2700, loss[loss=0.1637, simple_loss=0.2518, pruned_loss=0.03778, over 7157.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2485, pruned_loss=0.03399, over 1422904.42 frames.], batch size: 19, lr: 3.38e-04
+2022-05-15 05:49:24,368 INFO [train.py:812] (7/8) Epoch 23, batch 2750, loss[loss=0.1536, simple_loss=0.2378, pruned_loss=0.03476, over 7170.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2487, pruned_loss=0.03423, over 1420893.31 frames.], batch size: 18, lr: 3.38e-04
+2022-05-15 05:50:23,667 INFO [train.py:812] (7/8) Epoch 23, batch 2800, loss[loss=0.1511, simple_loss=0.2382, pruned_loss=0.03194, over 7163.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2488, pruned_loss=0.03423, over 1420159.92 frames.], batch size: 18, lr: 3.38e-04
+2022-05-15 05:51:22,643 INFO [train.py:812] (7/8) Epoch 23, batch 2850, loss[loss=0.1852, simple_loss=0.2828, pruned_loss=0.04386, over 7110.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2487, pruned_loss=0.03386, over 1421545.57 frames.], batch size: 28, lr: 3.38e-04
+2022-05-15 05:52:22,330 INFO [train.py:812] (7/8) Epoch 23, batch 2900, loss[loss=0.1692, simple_loss=0.2604, pruned_loss=0.03899, over 7334.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2491, pruned_loss=0.03426, over 1423370.90 frames.], batch size: 25, lr: 3.37e-04
+2022-05-15 05:53:20,368 INFO [train.py:812] (7/8) Epoch 23, batch 2950, loss[loss=0.1905, simple_loss=0.282, pruned_loss=0.04948, over 7199.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2505, pruned_loss=0.03494, over 1423900.72 frames.], batch size: 22, lr: 3.37e-04
+2022-05-15 05:54:18,738 INFO [train.py:812] (7/8) Epoch 23, batch 3000, loss[loss=0.143, simple_loss=0.228, pruned_loss=0.02898, over 6996.00 frames.], tot_loss[loss=0.1596, simple_loss=0.25, pruned_loss=0.03463, over 1423092.33 frames.], batch size: 16, lr: 3.37e-04
+2022-05-15 05:54:18,739 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 05:54:28,115 INFO [train.py:841] (7/8) Epoch 23, validation: loss=0.153, simple_loss=0.251, pruned_loss=0.02752, over 698248.00 frames.
+2022-05-15 05:55:26,711 INFO [train.py:812] (7/8) Epoch 23, batch 3050, loss[loss=0.1384, simple_loss=0.2218, pruned_loss=0.02754, over 7154.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2494, pruned_loss=0.0339, over 1425176.98 frames.], batch size: 19, lr: 3.37e-04
+2022-05-15 05:56:31,556 INFO [train.py:812] (7/8) Epoch 23, batch 3100, loss[loss=0.1575, simple_loss=0.2533, pruned_loss=0.03087, over 7239.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2488, pruned_loss=0.03377, over 1424912.35 frames.], batch size: 20, lr: 3.37e-04
+2022-05-15 05:57:30,957 INFO [train.py:812] (7/8) Epoch 23, batch 3150, loss[loss=0.1441, simple_loss=0.2441, pruned_loss=0.02211, over 7324.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2489, pruned_loss=0.03398, over 1425976.82 frames.], batch size: 20, lr: 3.37e-04
+2022-05-15 05:58:30,553 INFO [train.py:812] (7/8) Epoch 23, batch 3200, loss[loss=0.1639, simple_loss=0.2661, pruned_loss=0.03082, over 7114.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2491, pruned_loss=0.03393, over 1427309.60 frames.], batch size: 21, lr: 3.37e-04
+2022-05-15 05:59:29,525 INFO [train.py:812] (7/8) Epoch 23, batch 3250, loss[loss=0.154, simple_loss=0.25, pruned_loss=0.02905, over 6421.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2502, pruned_loss=0.0342, over 1422518.76 frames.], batch size: 38, lr: 3.37e-04
+2022-05-15 06:00:29,721 INFO [train.py:812] (7/8) Epoch 23, batch 3300, loss[loss=0.1584, simple_loss=0.2511, pruned_loss=0.03289, over 7299.00 frames.], tot_loss[loss=0.159, simple_loss=0.2502, pruned_loss=0.03394, over 1422923.61 frames.], batch size: 24, lr: 3.37e-04
+2022-05-15 06:01:29,049 INFO [train.py:812] (7/8) Epoch 23, batch 3350, loss[loss=0.1743, simple_loss=0.27, pruned_loss=0.0393, over 7120.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2494, pruned_loss=0.03394, over 1426894.00 frames.], batch size: 26, lr: 3.37e-04
+2022-05-15 06:02:28,596 INFO [train.py:812] (7/8) Epoch 23, batch 3400, loss[loss=0.1514, simple_loss=0.2406, pruned_loss=0.03108, over 7161.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2492, pruned_loss=0.03389, over 1428162.98 frames.], batch size: 19, lr: 3.37e-04
+2022-05-15 06:03:27,798 INFO [train.py:812] (7/8) Epoch 23, batch 3450, loss[loss=0.1735, simple_loss=0.2517, pruned_loss=0.04758, over 6817.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2483, pruned_loss=0.03375, over 1429902.38 frames.], batch size: 15, lr: 3.37e-04
+2022-05-15 06:04:27,382 INFO [train.py:812] (7/8) Epoch 23, batch 3500, loss[loss=0.1529, simple_loss=0.2283, pruned_loss=0.03869, over 7194.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2488, pruned_loss=0.034, over 1430844.26 frames.], batch size: 16, lr: 3.37e-04
+2022-05-15 06:05:25,914 INFO [train.py:812] (7/8) Epoch 23, batch 3550, loss[loss=0.1335, simple_loss=0.2196, pruned_loss=0.02371, over 7399.00 frames.], tot_loss[loss=0.158, simple_loss=0.2488, pruned_loss=0.0336, over 1430641.15 frames.], batch size: 18, lr: 3.36e-04
+2022-05-15 06:06:25,057 INFO [train.py:812] (7/8) Epoch 23, batch 3600, loss[loss=0.143, simple_loss=0.2292, pruned_loss=0.02838, over 7273.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2491, pruned_loss=0.03338, over 1431198.74 frames.], batch size: 17, lr: 3.36e-04
+2022-05-15 06:07:24,146 INFO [train.py:812] (7/8) Epoch 23, batch 3650, loss[loss=0.1626, simple_loss=0.2482, pruned_loss=0.03846, over 6521.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2493, pruned_loss=0.03365, over 1431297.71 frames.], batch size: 38, lr: 3.36e-04
+2022-05-15 06:08:33,480 INFO [train.py:812] (7/8) Epoch 23, batch 3700, loss[loss=0.1716, simple_loss=0.2633, pruned_loss=0.03998, over 7149.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2491, pruned_loss=0.03369, over 1430143.85 frames.], batch size: 19, lr: 3.36e-04
+2022-05-15 06:09:32,141 INFO [train.py:812] (7/8) Epoch 23, batch 3750, loss[loss=0.1372, simple_loss=0.2289, pruned_loss=0.02271, over 7299.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2491, pruned_loss=0.03356, over 1428071.15 frames.], batch size: 17, lr: 3.36e-04
+2022-05-15 06:10:31,421 INFO [train.py:812] (7/8) Epoch 23, batch 3800, loss[loss=0.162, simple_loss=0.2605, pruned_loss=0.0318, over 7366.00 frames.], tot_loss[loss=0.159, simple_loss=0.2496, pruned_loss=0.03416, over 1429265.03 frames.], batch size: 23, lr: 3.36e-04
+2022-05-15 06:11:30,141 INFO [train.py:812] (7/8) Epoch 23, batch 3850, loss[loss=0.1808, simple_loss=0.2794, pruned_loss=0.04108, over 7063.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2495, pruned_loss=0.03407, over 1430130.36 frames.], batch size: 28, lr: 3.36e-04
+2022-05-15 06:12:28,299 INFO [train.py:812] (7/8) Epoch 23, batch 3900, loss[loss=0.1458, simple_loss=0.2358, pruned_loss=0.02787, over 7117.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2497, pruned_loss=0.03452, over 1430621.02 frames.], batch size: 21, lr: 3.36e-04
+2022-05-15 06:13:25,781 INFO [train.py:812] (7/8) Epoch 23, batch 3950, loss[loss=0.1673, simple_loss=0.2646, pruned_loss=0.03501, over 7164.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2507, pruned_loss=0.03472, over 1430543.01 frames.], batch size: 19, lr: 3.36e-04
+2022-05-15 06:14:23,011 INFO [train.py:812] (7/8) Epoch 23, batch 4000, loss[loss=0.1156, simple_loss=0.1991, pruned_loss=0.01607, over 7295.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2498, pruned_loss=0.0343, over 1427297.80 frames.], batch size: 17, lr: 3.36e-04
+2022-05-15 06:15:21,474 INFO [train.py:812] (7/8) Epoch 23, batch 4050, loss[loss=0.1339, simple_loss=0.2198, pruned_loss=0.02395, over 6852.00 frames.], tot_loss[loss=0.16, simple_loss=0.2507, pruned_loss=0.03468, over 1422317.74 frames.], batch size: 15, lr: 3.36e-04
+2022-05-15 06:16:21,838 INFO [train.py:812] (7/8) Epoch 23, batch 4100, loss[loss=0.1427, simple_loss=0.2247, pruned_loss=0.03032, over 7272.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2502, pruned_loss=0.03475, over 1419225.30 frames.], batch size: 16, lr: 3.36e-04
+2022-05-15 06:17:19,484 INFO [train.py:812] (7/8) Epoch 23, batch 4150, loss[loss=0.1538, simple_loss=0.2493, pruned_loss=0.02918, over 7324.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2511, pruned_loss=0.03453, over 1418509.70 frames.], batch size: 21, lr: 3.35e-04
+2022-05-15 06:18:18,889 INFO [train.py:812] (7/8) Epoch 23, batch 4200, loss[loss=0.127, simple_loss=0.2126, pruned_loss=0.02072, over 6998.00 frames.], tot_loss[loss=0.16, simple_loss=0.2516, pruned_loss=0.03423, over 1422511.09 frames.], batch size: 16, lr: 3.35e-04
+2022-05-15 06:19:17,864 INFO [train.py:812] (7/8) Epoch 23, batch 4250, loss[loss=0.1515, simple_loss=0.2516, pruned_loss=0.0257, over 7238.00 frames.], tot_loss[loss=0.159, simple_loss=0.2507, pruned_loss=0.03365, over 1424423.69 frames.], batch size: 20, lr: 3.35e-04
+2022-05-15 06:20:16,286 INFO [train.py:812] (7/8) Epoch 23, batch 4300, loss[loss=0.1452, simple_loss=0.2329, pruned_loss=0.0288, over 7155.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2495, pruned_loss=0.0338, over 1421943.39 frames.], batch size: 18, lr: 3.35e-04
+2022-05-15 06:21:15,795 INFO [train.py:812] (7/8) Epoch 23, batch 4350, loss[loss=0.1572, simple_loss=0.2396, pruned_loss=0.03737, over 6822.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2485, pruned_loss=0.03363, over 1422595.20 frames.], batch size: 15, lr: 3.35e-04
+2022-05-15 06:22:15,656 INFO [train.py:812] (7/8) Epoch 23, batch 4400, loss[loss=0.1368, simple_loss=0.2306, pruned_loss=0.02155, over 7060.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2476, pruned_loss=0.03353, over 1420074.86 frames.], batch size: 18, lr: 3.35e-04
+2022-05-15 06:23:14,881 INFO [train.py:812] (7/8) Epoch 23, batch 4450, loss[loss=0.1925, simple_loss=0.2784, pruned_loss=0.05328, over 5140.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2483, pruned_loss=0.03406, over 1414198.59 frames.], batch size: 52, lr: 3.35e-04
+2022-05-15 06:24:12,969 INFO [train.py:812] (7/8) Epoch 23, batch 4500, loss[loss=0.1447, simple_loss=0.2271, pruned_loss=0.03109, over 7065.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2484, pruned_loss=0.03401, over 1413328.78 frames.], batch size: 18, lr: 3.35e-04
+2022-05-15 06:25:11,020 INFO [train.py:812] (7/8) Epoch 23, batch 4550, loss[loss=0.1867, simple_loss=0.2567, pruned_loss=0.05833, over 4859.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2512, pruned_loss=0.03564, over 1357015.65 frames.], batch size: 52, lr: 3.35e-04
+2022-05-15 06:26:16,426 INFO [train.py:812] (7/8) Epoch 24, batch 0, loss[loss=0.1366, simple_loss=0.2263, pruned_loss=0.02345, over 6827.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2263, pruned_loss=0.02345, over 6827.00 frames.], batch size: 15, lr: 3.28e-04
+2022-05-15 06:27:14,065 INFO [train.py:812] (7/8) Epoch 24, batch 50, loss[loss=0.1348, simple_loss=0.222, pruned_loss=0.02379, over 7286.00 frames.], tot_loss[loss=0.1585, simple_loss=0.25, pruned_loss=0.03348, over 316348.48 frames.], batch size: 17, lr: 3.28e-04
+2022-05-15 06:28:13,410 INFO [train.py:812] (7/8) Epoch 24, batch 100, loss[loss=0.1362, simple_loss=0.2242, pruned_loss=0.02411, over 7332.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2494, pruned_loss=0.03325, over 567311.41 frames.], batch size: 20, lr: 3.28e-04
+2022-05-15 06:29:11,057 INFO [train.py:812] (7/8) Epoch 24, batch 150, loss[loss=0.1504, simple_loss=0.2488, pruned_loss=0.02606, over 7370.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2497, pruned_loss=0.03393, over 753454.60 frames.], batch size: 23, lr: 3.28e-04
+2022-05-15 06:30:10,096 INFO [train.py:812] (7/8) Epoch 24, batch 200, loss[loss=0.1445, simple_loss=0.2399, pruned_loss=0.02452, over 7205.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2497, pruned_loss=0.03427, over 904150.41 frames.], batch size: 22, lr: 3.28e-04
+2022-05-15 06:31:07,659 INFO [train.py:812] (7/8) Epoch 24, batch 250, loss[loss=0.1479, simple_loss=0.2412, pruned_loss=0.02733, over 7412.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2499, pruned_loss=0.03431, over 1016462.50 frames.], batch size: 21, lr: 3.28e-04
+2022-05-15 06:32:07,202 INFO [train.py:812] (7/8) Epoch 24, batch 300, loss[loss=0.161, simple_loss=0.2462, pruned_loss=0.03795, over 7149.00 frames.], tot_loss[loss=0.159, simple_loss=0.2496, pruned_loss=0.03423, over 1107346.91 frames.], batch size: 20, lr: 3.27e-04
+2022-05-15 06:33:04,014 INFO [train.py:812] (7/8) Epoch 24, batch 350, loss[loss=0.1703, simple_loss=0.255, pruned_loss=0.04281, over 7260.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2488, pruned_loss=0.0339, over 1179047.40 frames.], batch size: 25, lr: 3.27e-04
+2022-05-15 06:34:01,098 INFO [train.py:812] (7/8) Epoch 24, batch 400, loss[loss=0.1867, simple_loss=0.2744, pruned_loss=0.04951, over 7277.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2489, pruned_loss=0.03403, over 1230497.64 frames.], batch size: 24, lr: 3.27e-04
+2022-05-15 06:34:58,902 INFO [train.py:812] (7/8) Epoch 24, batch 450, loss[loss=0.1638, simple_loss=0.2578, pruned_loss=0.0349, over 7147.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2496, pruned_loss=0.03392, over 1275948.55 frames.], batch size: 20, lr: 3.27e-04
+2022-05-15 06:35:57,445 INFO [train.py:812] (7/8) Epoch 24, batch 500, loss[loss=0.1567, simple_loss=0.2403, pruned_loss=0.03657, over 7342.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2499, pruned_loss=0.03396, over 1307882.36 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:36:55,910 INFO [train.py:812] (7/8) Epoch 24, batch 550, loss[loss=0.175, simple_loss=0.2694, pruned_loss=0.04028, over 7213.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2498, pruned_loss=0.03385, over 1336136.97 frames.], batch size: 22, lr: 3.27e-04
+2022-05-15 06:37:55,379 INFO [train.py:812] (7/8) Epoch 24, batch 600, loss[loss=0.1527, simple_loss=0.241, pruned_loss=0.03222, over 7350.00 frames.], tot_loss[loss=0.1583, simple_loss=0.249, pruned_loss=0.03377, over 1353163.30 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:38:54,672 INFO [train.py:812] (7/8) Epoch 24, batch 650, loss[loss=0.1443, simple_loss=0.2246, pruned_loss=0.032, over 7367.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2489, pruned_loss=0.034, over 1363861.96 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:39:54,731 INFO [train.py:812] (7/8) Epoch 24, batch 700, loss[loss=0.177, simple_loss=0.2675, pruned_loss=0.04321, over 7189.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2473, pruned_loss=0.03351, over 1381943.52 frames.], batch size: 26, lr: 3.27e-04
+2022-05-15 06:40:53,860 INFO [train.py:812] (7/8) Epoch 24, batch 750, loss[loss=0.1483, simple_loss=0.223, pruned_loss=0.03677, over 7416.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2484, pruned_loss=0.03349, over 1393408.53 frames.], batch size: 17, lr: 3.27e-04
+2022-05-15 06:41:53,038 INFO [train.py:812] (7/8) Epoch 24, batch 800, loss[loss=0.1302, simple_loss=0.2257, pruned_loss=0.01738, over 7249.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2475, pruned_loss=0.03339, over 1399329.92 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:42:52,224 INFO [train.py:812] (7/8) Epoch 24, batch 850, loss[loss=0.1422, simple_loss=0.2349, pruned_loss=0.02473, over 6678.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2473, pruned_loss=0.03309, over 1406352.66 frames.], batch size: 31, lr: 3.27e-04
+2022-05-15 06:43:51,482 INFO [train.py:812] (7/8) Epoch 24, batch 900, loss[loss=0.1441, simple_loss=0.236, pruned_loss=0.02614, over 7418.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2478, pruned_loss=0.03331, over 1411611.00 frames.], batch size: 20, lr: 3.27e-04
+2022-05-15 06:44:50,527 INFO [train.py:812] (7/8) Epoch 24, batch 950, loss[loss=0.1625, simple_loss=0.2604, pruned_loss=0.03226, over 6479.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2472, pruned_loss=0.03317, over 1416467.39 frames.], batch size: 38, lr: 3.26e-04
+2022-05-15 06:45:49,561 INFO [train.py:812] (7/8) Epoch 24, batch 1000, loss[loss=0.1746, simple_loss=0.2686, pruned_loss=0.04032, over 7316.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2469, pruned_loss=0.03325, over 1418065.04 frames.], batch size: 21, lr: 3.26e-04
+2022-05-15 06:46:47,326 INFO [train.py:812] (7/8) Epoch 24, batch 1050, loss[loss=0.1506, simple_loss=0.2405, pruned_loss=0.0304, over 7241.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2478, pruned_loss=0.0338, over 1411410.81 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:47:46,431 INFO [train.py:812] (7/8) Epoch 24, batch 1100, loss[loss=0.145, simple_loss=0.2361, pruned_loss=0.02699, over 7145.00 frames.], tot_loss[loss=0.1579, simple_loss=0.248, pruned_loss=0.03383, over 1411744.33 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:48:44,906 INFO [train.py:812] (7/8) Epoch 24, batch 1150, loss[loss=0.1579, simple_loss=0.2558, pruned_loss=0.02997, over 6251.00 frames.], tot_loss[loss=0.1568, simple_loss=0.247, pruned_loss=0.0333, over 1415290.79 frames.], batch size: 38, lr: 3.26e-04
+2022-05-15 06:49:42,966 INFO [train.py:812] (7/8) Epoch 24, batch 1200, loss[loss=0.1602, simple_loss=0.264, pruned_loss=0.0282, over 7157.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2472, pruned_loss=0.03308, over 1418187.17 frames.], batch size: 18, lr: 3.26e-04
+2022-05-15 06:50:50,724 INFO [train.py:812] (7/8) Epoch 24, batch 1250, loss[loss=0.1556, simple_loss=0.2448, pruned_loss=0.03323, over 7332.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2472, pruned_loss=0.03336, over 1418979.53 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:51:49,917 INFO [train.py:812] (7/8) Epoch 24, batch 1300, loss[loss=0.153, simple_loss=0.2464, pruned_loss=0.0298, over 6756.00 frames.], tot_loss[loss=0.1576, simple_loss=0.248, pruned_loss=0.03358, over 1420558.17 frames.], batch size: 31, lr: 3.26e-04
+2022-05-15 06:52:48,840 INFO [train.py:812] (7/8) Epoch 24, batch 1350, loss[loss=0.1311, simple_loss=0.2201, pruned_loss=0.02104, over 7391.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2488, pruned_loss=0.03375, over 1426314.59 frames.], batch size: 18, lr: 3.26e-04
+2022-05-15 06:53:46,311 INFO [train.py:812] (7/8) Epoch 24, batch 1400, loss[loss=0.1791, simple_loss=0.272, pruned_loss=0.04307, over 7162.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2486, pruned_loss=0.03365, over 1424205.37 frames.], batch size: 26, lr: 3.26e-04
+2022-05-15 06:55:13,464 INFO [train.py:812] (7/8) Epoch 24, batch 1450, loss[loss=0.1799, simple_loss=0.2702, pruned_loss=0.04482, over 7144.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2489, pruned_loss=0.03368, over 1421637.62 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:56:21,957 INFO [train.py:812] (7/8) Epoch 24, batch 1500, loss[loss=0.1716, simple_loss=0.2638, pruned_loss=0.0397, over 7137.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2486, pruned_loss=0.03387, over 1419605.87 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:57:21,247 INFO [train.py:812] (7/8) Epoch 24, batch 1550, loss[loss=0.1898, simple_loss=0.2911, pruned_loss=0.04422, over 6778.00 frames.], tot_loss[loss=0.158, simple_loss=0.2484, pruned_loss=0.03378, over 1420112.56 frames.], batch size: 31, lr: 3.26e-04
+2022-05-15 06:58:39,414 INFO [train.py:812] (7/8) Epoch 24, batch 1600, loss[loss=0.1479, simple_loss=0.244, pruned_loss=0.02594, over 7333.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2483, pruned_loss=0.03352, over 1422117.79 frames.], batch size: 20, lr: 3.25e-04
+2022-05-15 06:59:37,744 INFO [train.py:812] (7/8) Epoch 24, batch 1650, loss[loss=0.1431, simple_loss=0.2217, pruned_loss=0.03219, over 6793.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2488, pruned_loss=0.03372, over 1414009.55 frames.], batch size: 15, lr: 3.25e-04
+2022-05-15 07:00:36,807 INFO [train.py:812] (7/8) Epoch 24, batch 1700, loss[loss=0.1524, simple_loss=0.2471, pruned_loss=0.02886, over 7321.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2481, pruned_loss=0.03344, over 1418232.98 frames.], batch size: 21, lr: 3.25e-04
+2022-05-15 07:01:34,528 INFO [train.py:812] (7/8) Epoch 24, batch 1750, loss[loss=0.1421, simple_loss=0.2273, pruned_loss=0.02841, over 7065.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2485, pruned_loss=0.03384, over 1419695.58 frames.], batch size: 18, lr: 3.25e-04
+2022-05-15 07:02:33,295 INFO [train.py:812] (7/8) Epoch 24, batch 1800, loss[loss=0.1465, simple_loss=0.2431, pruned_loss=0.02488, over 7335.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2487, pruned_loss=0.03346, over 1420176.27 frames.], batch size: 22, lr: 3.25e-04
+2022-05-15 07:03:31,350 INFO [train.py:812] (7/8) Epoch 24, batch 1850, loss[loss=0.1582, simple_loss=0.2489, pruned_loss=0.03372, over 7282.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2489, pruned_loss=0.03337, over 1423772.33 frames.], batch size: 24, lr: 3.25e-04
+2022-05-15 07:04:30,239 INFO [train.py:812] (7/8) Epoch 24, batch 1900, loss[loss=0.1617, simple_loss=0.2512, pruned_loss=0.03613, over 7070.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2488, pruned_loss=0.03332, over 1421684.00 frames.], batch size: 28, lr: 3.25e-04
+2022-05-15 07:05:29,107 INFO [train.py:812] (7/8) Epoch 24, batch 1950, loss[loss=0.1596, simple_loss=0.2508, pruned_loss=0.03419, over 7121.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2489, pruned_loss=0.03327, over 1423259.84 frames.], batch size: 21, lr: 3.25e-04
+2022-05-15 07:06:27,384 INFO [train.py:812] (7/8) Epoch 24, batch 2000, loss[loss=0.185, simple_loss=0.2679, pruned_loss=0.05103, over 5188.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2503, pruned_loss=0.03357, over 1421324.48 frames.], batch size: 52, lr: 3.25e-04
+2022-05-15 07:07:25,829 INFO [train.py:812] (7/8) Epoch 24, batch 2050, loss[loss=0.1303, simple_loss=0.2216, pruned_loss=0.01955, over 7425.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2497, pruned_loss=0.03344, over 1420753.01 frames.], batch size: 20, lr: 3.25e-04
+2022-05-15 07:08:23,668 INFO [train.py:812] (7/8) Epoch 24, batch 2100, loss[loss=0.1362, simple_loss=0.2329, pruned_loss=0.01978, over 6998.00 frames.], tot_loss[loss=0.1576, simple_loss=0.249, pruned_loss=0.03311, over 1422454.68 frames.], batch size: 16, lr: 3.25e-04
+2022-05-15 07:09:22,566 INFO [train.py:812] (7/8) Epoch 24, batch 2150, loss[loss=0.1765, simple_loss=0.2686, pruned_loss=0.04224, over 4984.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2482, pruned_loss=0.03312, over 1420196.68 frames.], batch size: 52, lr: 3.25e-04
+2022-05-15 07:10:21,869 INFO [train.py:812] (7/8) Epoch 24, batch 2200, loss[loss=0.1176, simple_loss=0.2024, pruned_loss=0.01644, over 7120.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2481, pruned_loss=0.03318, over 1419679.89 frames.], batch size: 17, lr: 3.25e-04
+2022-05-15 07:11:20,866 INFO [train.py:812] (7/8) Epoch 24, batch 2250, loss[loss=0.1575, simple_loss=0.2531, pruned_loss=0.03097, over 7320.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2485, pruned_loss=0.03365, over 1408410.89 frames.], batch size: 25, lr: 3.24e-04
+2022-05-15 07:12:19,968 INFO [train.py:812] (7/8) Epoch 24, batch 2300, loss[loss=0.129, simple_loss=0.217, pruned_loss=0.02051, over 7267.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2472, pruned_loss=0.03301, over 1415986.60 frames.], batch size: 17, lr: 3.24e-04
+2022-05-15 07:13:18,789 INFO [train.py:812] (7/8) Epoch 24, batch 2350, loss[loss=0.1528, simple_loss=0.2431, pruned_loss=0.03122, over 7355.00 frames.], tot_loss[loss=0.1573, simple_loss=0.248, pruned_loss=0.03331, over 1418059.13 frames.], batch size: 22, lr: 3.24e-04
+2022-05-15 07:14:18,409 INFO [train.py:812] (7/8) Epoch 24, batch 2400, loss[loss=0.1492, simple_loss=0.229, pruned_loss=0.03469, over 7245.00 frames.], tot_loss[loss=0.158, simple_loss=0.249, pruned_loss=0.03348, over 1421112.57 frames.], batch size: 16, lr: 3.24e-04
+2022-05-15 07:15:15,776 INFO [train.py:812] (7/8) Epoch 24, batch 2450, loss[loss=0.1721, simple_loss=0.2622, pruned_loss=0.04102, over 7230.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2494, pruned_loss=0.03371, over 1417299.50 frames.], batch size: 20, lr: 3.24e-04
+2022-05-15 07:16:21,396 INFO [train.py:812] (7/8) Epoch 24, batch 2500, loss[loss=0.1556, simple_loss=0.2495, pruned_loss=0.03087, over 7318.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2491, pruned_loss=0.03355, over 1417589.63 frames.], batch size: 21, lr: 3.24e-04
+2022-05-15 07:17:19,948 INFO [train.py:812] (7/8) Epoch 24, batch 2550, loss[loss=0.1662, simple_loss=0.255, pruned_loss=0.0387, over 5240.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2479, pruned_loss=0.03323, over 1413858.15 frames.], batch size: 52, lr: 3.24e-04
+2022-05-15 07:18:18,717 INFO [train.py:812] (7/8) Epoch 24, batch 2600, loss[loss=0.1375, simple_loss=0.2353, pruned_loss=0.01988, over 7279.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2493, pruned_loss=0.03383, over 1418041.56 frames.], batch size: 18, lr: 3.24e-04
+2022-05-15 07:19:17,337 INFO [train.py:812] (7/8) Epoch 24, batch 2650, loss[loss=0.1543, simple_loss=0.2509, pruned_loss=0.02882, over 7325.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2484, pruned_loss=0.03337, over 1417431.99 frames.], batch size: 21, lr: 3.24e-04
+2022-05-15 07:20:16,632 INFO [train.py:812] (7/8) Epoch 24, batch 2700, loss[loss=0.1502, simple_loss=0.2441, pruned_loss=0.02813, over 7326.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2488, pruned_loss=0.03324, over 1422677.70 frames.], batch size: 22, lr: 3.24e-04
+2022-05-15 07:21:15,988 INFO [train.py:812] (7/8) Epoch 24, batch 2750, loss[loss=0.1578, simple_loss=0.2431, pruned_loss=0.03624, over 7415.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2488, pruned_loss=0.03294, over 1426408.62 frames.], batch size: 21, lr: 3.24e-04
+2022-05-15 07:22:15,063 INFO [train.py:812] (7/8) Epoch 24, batch 2800, loss[loss=0.158, simple_loss=0.2488, pruned_loss=0.03365, over 7224.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2498, pruned_loss=0.03324, over 1422235.18 frames.], batch size: 20, lr: 3.24e-04
+2022-05-15 07:23:13,170 INFO [train.py:812] (7/8) Epoch 24, batch 2850, loss[loss=0.177, simple_loss=0.2709, pruned_loss=0.04152, over 7364.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2508, pruned_loss=0.03355, over 1422361.31 frames.], batch size: 19, lr: 3.24e-04
+2022-05-15 07:24:12,113 INFO [train.py:812] (7/8) Epoch 24, batch 2900, loss[loss=0.1748, simple_loss=0.2722, pruned_loss=0.03866, over 7283.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2508, pruned_loss=0.03363, over 1421300.90 frames.], batch size: 25, lr: 3.24e-04
+2022-05-15 07:25:09,887 INFO [train.py:812] (7/8) Epoch 24, batch 2950, loss[loss=0.1555, simple_loss=0.2389, pruned_loss=0.03601, over 7280.00 frames.], tot_loss[loss=0.158, simple_loss=0.2497, pruned_loss=0.03312, over 1425264.04 frames.], batch size: 17, lr: 3.23e-04
+2022-05-15 07:26:08,050 INFO [train.py:812] (7/8) Epoch 24, batch 3000, loss[loss=0.1525, simple_loss=0.2396, pruned_loss=0.03274, over 7109.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2491, pruned_loss=0.03315, over 1421585.34 frames.], batch size: 21, lr: 3.23e-04
+2022-05-15 07:26:08,051 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 07:26:15,600 INFO [train.py:841] (7/8) Epoch 24, validation: loss=0.1537, simple_loss=0.2513, pruned_loss=0.02802, over 698248.00 frames.
+2022-05-15 07:27:15,017 INFO [train.py:812] (7/8) Epoch 24, batch 3050, loss[loss=0.1465, simple_loss=0.2285, pruned_loss=0.03226, over 7310.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2486, pruned_loss=0.03321, over 1416454.88 frames.], batch size: 18, lr: 3.23e-04
+2022-05-15 07:28:13,654 INFO [train.py:812] (7/8) Epoch 24, batch 3100, loss[loss=0.1502, simple_loss=0.2388, pruned_loss=0.03081, over 6794.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2486, pruned_loss=0.03318, over 1419399.35 frames.], batch size: 31, lr: 3.23e-04
+2022-05-15 07:29:12,203 INFO [train.py:812] (7/8) Epoch 24, batch 3150, loss[loss=0.1286, simple_loss=0.2218, pruned_loss=0.01775, over 6985.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2484, pruned_loss=0.03319, over 1420653.65 frames.], batch size: 16, lr: 3.23e-04
+2022-05-15 07:30:11,707 INFO [train.py:812] (7/8) Epoch 24, batch 3200, loss[loss=0.1904, simple_loss=0.2794, pruned_loss=0.0507, over 7320.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2487, pruned_loss=0.03332, over 1425725.11 frames.], batch size: 21, lr: 3.23e-04
+2022-05-15 07:31:10,243 INFO [train.py:812] (7/8) Epoch 24, batch 3250, loss[loss=0.1436, simple_loss=0.2317, pruned_loss=0.02775, over 7156.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2483, pruned_loss=0.03348, over 1426998.50 frames.], batch size: 18, lr: 3.23e-04
+2022-05-15 07:32:09,052 INFO [train.py:812] (7/8) Epoch 24, batch 3300, loss[loss=0.1822, simple_loss=0.2842, pruned_loss=0.04005, over 7286.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2491, pruned_loss=0.03384, over 1427538.34 frames.], batch size: 24, lr: 3.23e-04
+2022-05-15 07:33:06,629 INFO [train.py:812] (7/8) Epoch 24, batch 3350, loss[loss=0.1501, simple_loss=0.2456, pruned_loss=0.0273, over 7311.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2497, pruned_loss=0.03402, over 1423999.57 frames.], batch size: 24, lr: 3.23e-04
+2022-05-15 07:34:04,989 INFO [train.py:812] (7/8) Epoch 24, batch 3400, loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02959, over 7346.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2494, pruned_loss=0.03369, over 1427928.26 frames.], batch size: 19, lr: 3.23e-04
+2022-05-15 07:35:03,144 INFO [train.py:812] (7/8) Epoch 24, batch 3450, loss[loss=0.1654, simple_loss=0.2636, pruned_loss=0.03356, over 7337.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2497, pruned_loss=0.03346, over 1423475.55 frames.], batch size: 22, lr: 3.23e-04
+2022-05-15 07:36:01,796 INFO [train.py:812] (7/8) Epoch 24, batch 3500, loss[loss=0.1263, simple_loss=0.21, pruned_loss=0.02133, over 6850.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2484, pruned_loss=0.03303, over 1422026.28 frames.], batch size: 15, lr: 3.23e-04
+2022-05-15 07:37:00,376 INFO [train.py:812] (7/8) Epoch 24, batch 3550, loss[loss=0.1625, simple_loss=0.2617, pruned_loss=0.03166, over 7111.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2487, pruned_loss=0.03329, over 1423200.89 frames.], batch size: 21, lr: 3.23e-04
+2022-05-15 07:38:00,127 INFO [train.py:812] (7/8) Epoch 24, batch 3600, loss[loss=0.1441, simple_loss=0.2328, pruned_loss=0.02773, over 7061.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2495, pruned_loss=0.03375, over 1422794.67 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:38:57,483 INFO [train.py:812] (7/8) Epoch 24, batch 3650, loss[loss=0.1616, simple_loss=0.2499, pruned_loss=0.03665, over 7361.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2508, pruned_loss=0.03436, over 1423808.79 frames.], batch size: 19, lr: 3.22e-04
+2022-05-15 07:39:55,875 INFO [train.py:812] (7/8) Epoch 24, batch 3700, loss[loss=0.1532, simple_loss=0.2463, pruned_loss=0.03006, over 6589.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2517, pruned_loss=0.03472, over 1421447.41 frames.], batch size: 38, lr: 3.22e-04
+2022-05-15 07:40:52,887 INFO [train.py:812] (7/8) Epoch 24, batch 3750, loss[loss=0.1399, simple_loss=0.2289, pruned_loss=0.02549, over 7276.00 frames.], tot_loss[loss=0.1603, simple_loss=0.251, pruned_loss=0.03478, over 1422873.92 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:41:51,916 INFO [train.py:812] (7/8) Epoch 24, batch 3800, loss[loss=0.1519, simple_loss=0.2451, pruned_loss=0.02937, over 7429.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2495, pruned_loss=0.03416, over 1424741.74 frames.], batch size: 20, lr: 3.22e-04
+2022-05-15 07:42:51,162 INFO [train.py:812] (7/8) Epoch 24, batch 3850, loss[loss=0.1669, simple_loss=0.2601, pruned_loss=0.03686, over 4964.00 frames.], tot_loss[loss=0.1593, simple_loss=0.25, pruned_loss=0.03427, over 1420530.65 frames.], batch size: 52, lr: 3.22e-04
+2022-05-15 07:43:50,696 INFO [train.py:812] (7/8) Epoch 24, batch 3900, loss[loss=0.1402, simple_loss=0.2304, pruned_loss=0.02497, over 6760.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2496, pruned_loss=0.03434, over 1417531.21 frames.], batch size: 31, lr: 3.22e-04
+2022-05-15 07:44:49,686 INFO [train.py:812] (7/8) Epoch 24, batch 3950, loss[loss=0.1487, simple_loss=0.2279, pruned_loss=0.03475, over 7131.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2501, pruned_loss=0.03442, over 1417710.62 frames.], batch size: 17, lr: 3.22e-04
+2022-05-15 07:45:48,736 INFO [train.py:812] (7/8) Epoch 24, batch 4000, loss[loss=0.143, simple_loss=0.2319, pruned_loss=0.02709, over 7201.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2505, pruned_loss=0.03464, over 1415447.83 frames.], batch size: 22, lr: 3.22e-04
+2022-05-15 07:46:47,083 INFO [train.py:812] (7/8) Epoch 24, batch 4050, loss[loss=0.1834, simple_loss=0.2699, pruned_loss=0.04851, over 5175.00 frames.], tot_loss[loss=0.1593, simple_loss=0.25, pruned_loss=0.03427, over 1416596.15 frames.], batch size: 55, lr: 3.22e-04
+2022-05-15 07:47:46,744 INFO [train.py:812] (7/8) Epoch 24, batch 4100, loss[loss=0.1374, simple_loss=0.2376, pruned_loss=0.01859, over 7284.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2499, pruned_loss=0.03429, over 1417163.52 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:48:45,774 INFO [train.py:812] (7/8) Epoch 24, batch 4150, loss[loss=0.1389, simple_loss=0.2244, pruned_loss=0.02667, over 7005.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2495, pruned_loss=0.03443, over 1418528.98 frames.], batch size: 16, lr: 3.22e-04
+2022-05-15 07:49:44,886 INFO [train.py:812] (7/8) Epoch 24, batch 4200, loss[loss=0.1672, simple_loss=0.2597, pruned_loss=0.03737, over 7281.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2506, pruned_loss=0.03477, over 1418646.85 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:50:44,118 INFO [train.py:812] (7/8) Epoch 24, batch 4250, loss[loss=0.1806, simple_loss=0.2708, pruned_loss=0.04518, over 7383.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2499, pruned_loss=0.03445, over 1416696.35 frames.], batch size: 23, lr: 3.22e-04
+2022-05-15 07:51:43,371 INFO [train.py:812] (7/8) Epoch 24, batch 4300, loss[loss=0.1362, simple_loss=0.2164, pruned_loss=0.02794, over 6806.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2486, pruned_loss=0.03351, over 1415833.75 frames.], batch size: 15, lr: 3.21e-04
+2022-05-15 07:52:41,825 INFO [train.py:812] (7/8) Epoch 24, batch 4350, loss[loss=0.1518, simple_loss=0.2457, pruned_loss=0.02893, over 6810.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2501, pruned_loss=0.03401, over 1412742.51 frames.], batch size: 31, lr: 3.21e-04
+2022-05-15 07:53:40,627 INFO [train.py:812] (7/8) Epoch 24, batch 4400, loss[loss=0.1834, simple_loss=0.2761, pruned_loss=0.04534, over 6400.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2514, pruned_loss=0.03483, over 1406482.06 frames.], batch size: 38, lr: 3.21e-04
+2022-05-15 07:54:38,531 INFO [train.py:812] (7/8) Epoch 24, batch 4450, loss[loss=0.1643, simple_loss=0.2572, pruned_loss=0.03567, over 6393.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2506, pruned_loss=0.03459, over 1408926.27 frames.], batch size: 38, lr: 3.21e-04
+2022-05-15 07:55:37,577 INFO [train.py:812] (7/8) Epoch 24, batch 4500, loss[loss=0.1577, simple_loss=0.2456, pruned_loss=0.03495, over 6154.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2512, pruned_loss=0.03505, over 1395448.46 frames.], batch size: 37, lr: 3.21e-04
+2022-05-15 07:56:36,626 INFO [train.py:812] (7/8) Epoch 24, batch 4550, loss[loss=0.1491, simple_loss=0.2478, pruned_loss=0.02519, over 7279.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2514, pruned_loss=0.03514, over 1385660.14 frames.], batch size: 24, lr: 3.21e-04
+2022-05-15 07:57:47,767 INFO [train.py:812] (7/8) Epoch 25, batch 0, loss[loss=0.1579, simple_loss=0.2564, pruned_loss=0.02968, over 7061.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2564, pruned_loss=0.02968, over 7061.00 frames.], batch size: 18, lr: 3.15e-04
+2022-05-15 07:58:47,081 INFO [train.py:812] (7/8) Epoch 25, batch 50, loss[loss=0.1395, simple_loss=0.2259, pruned_loss=0.02653, over 7245.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2487, pruned_loss=0.03382, over 322027.44 frames.], batch size: 19, lr: 3.15e-04
+2022-05-15 07:59:46,742 INFO [train.py:812] (7/8) Epoch 25, batch 100, loss[loss=0.154, simple_loss=0.2471, pruned_loss=0.03049, over 7330.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2484, pruned_loss=0.03359, over 570110.52 frames.], batch size: 20, lr: 3.15e-04
+2022-05-15 08:00:45,707 INFO [train.py:812] (7/8) Epoch 25, batch 150, loss[loss=0.1445, simple_loss=0.2392, pruned_loss=0.02486, over 7319.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2481, pruned_loss=0.0334, over 761861.01 frames.], batch size: 21, lr: 3.14e-04
+2022-05-15 08:01:45,475 INFO [train.py:812] (7/8) Epoch 25, batch 200, loss[loss=0.1389, simple_loss=0.2237, pruned_loss=0.02703, over 6739.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2474, pruned_loss=0.03308, over 906343.63 frames.], batch size: 15, lr: 3.14e-04
+2022-05-15 08:02:44,413 INFO [train.py:812] (7/8) Epoch 25, batch 250, loss[loss=0.1521, simple_loss=0.2457, pruned_loss=0.02923, over 7239.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2468, pruned_loss=0.03318, over 1018770.43 frames.], batch size: 20, lr: 3.14e-04
+2022-05-15 08:03:43,906 INFO [train.py:812] (7/8) Epoch 25, batch 300, loss[loss=0.1529, simple_loss=0.2411, pruned_loss=0.03234, over 7156.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2486, pruned_loss=0.03381, over 1112156.15 frames.], batch size: 19, lr: 3.14e-04
+2022-05-15 08:04:42,736 INFO [train.py:812] (7/8) Epoch 25, batch 350, loss[loss=0.1586, simple_loss=0.2543, pruned_loss=0.03143, over 7211.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2491, pruned_loss=0.03438, over 1181028.96 frames.], batch size: 23, lr: 3.14e-04
+2022-05-15 08:05:50,934 INFO [train.py:812] (7/8) Epoch 25, batch 400, loss[loss=0.1698, simple_loss=0.2587, pruned_loss=0.04047, over 7244.00 frames.], tot_loss[loss=0.1578, simple_loss=0.248, pruned_loss=0.03375, over 1236259.88 frames.], batch size: 20, lr: 3.14e-04
+2022-05-15 08:06:49,161 INFO [train.py:812] (7/8) Epoch 25, batch 450, loss[loss=0.1754, simple_loss=0.2721, pruned_loss=0.03935, over 7079.00 frames.], tot_loss[loss=0.157, simple_loss=0.2475, pruned_loss=0.03327, over 1277696.02 frames.], batch size: 28, lr: 3.14e-04
+2022-05-15 08:07:48,560 INFO [train.py:812] (7/8) Epoch 25, batch 500, loss[loss=0.1776, simple_loss=0.261, pruned_loss=0.04713, over 7164.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2481, pruned_loss=0.0333, over 1312602.96 frames.], batch size: 18, lr: 3.14e-04
+2022-05-15 08:08:47,679 INFO [train.py:812] (7/8) Epoch 25, batch 550, loss[loss=0.1454, simple_loss=0.2346, pruned_loss=0.02807, over 7167.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2479, pruned_loss=0.03284, over 1339406.59 frames.], batch size: 18, lr: 3.14e-04
+2022-05-15 08:09:45,635 INFO [train.py:812] (7/8) Epoch 25, batch 600, loss[loss=0.1779, simple_loss=0.2676, pruned_loss=0.04407, over 7203.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2478, pruned_loss=0.033, over 1359181.66 frames.], batch size: 23, lr: 3.14e-04
+2022-05-15 08:10:45,021 INFO [train.py:812] (7/8) Epoch 25, batch 650, loss[loss=0.1319, simple_loss=0.2099, pruned_loss=0.02696, over 7259.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2475, pruned_loss=0.0333, over 1371305.62 frames.], batch size: 17, lr: 3.14e-04
+2022-05-15 08:11:43,803 INFO [train.py:812] (7/8) Epoch 25, batch 700, loss[loss=0.1271, simple_loss=0.2106, pruned_loss=0.02178, over 6804.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2473, pruned_loss=0.03313, over 1387550.27 frames.], batch size: 15, lr: 3.14e-04
+2022-05-15 08:12:42,969 INFO [train.py:812] (7/8) Epoch 25, batch 750, loss[loss=0.162, simple_loss=0.2633, pruned_loss=0.03039, over 7235.00 frames.], tot_loss[loss=0.1573, simple_loss=0.248, pruned_loss=0.03336, over 1398791.63 frames.], batch size: 20, lr: 3.14e-04
+2022-05-15 08:13:42,705 INFO [train.py:812] (7/8) Epoch 25, batch 800, loss[loss=0.194, simple_loss=0.2818, pruned_loss=0.05308, over 7415.00 frames.], tot_loss[loss=0.157, simple_loss=0.2479, pruned_loss=0.03309, over 1406942.27 frames.], batch size: 21, lr: 3.14e-04
+2022-05-15 08:14:42,198 INFO [train.py:812] (7/8) Epoch 25, batch 850, loss[loss=0.1631, simple_loss=0.2588, pruned_loss=0.03369, over 7325.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2479, pruned_loss=0.03326, over 1408229.49 frames.], batch size: 21, lr: 3.13e-04
+2022-05-15 08:15:39,819 INFO [train.py:812] (7/8) Epoch 25, batch 900, loss[loss=0.1673, simple_loss=0.2662, pruned_loss=0.03422, over 7316.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2487, pruned_loss=0.03347, over 1410638.35 frames.], batch size: 25, lr: 3.13e-04
+2022-05-15 08:16:38,357 INFO [train.py:812] (7/8) Epoch 25, batch 950, loss[loss=0.1636, simple_loss=0.2593, pruned_loss=0.03394, over 5082.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2485, pruned_loss=0.03339, over 1405738.89 frames.], batch size: 52, lr: 3.13e-04
+2022-05-15 08:17:38,366 INFO [train.py:812] (7/8) Epoch 25, batch 1000, loss[loss=0.1488, simple_loss=0.2451, pruned_loss=0.02623, over 7411.00 frames.], tot_loss[loss=0.157, simple_loss=0.2481, pruned_loss=0.03293, over 1412165.45 frames.], batch size: 21, lr: 3.13e-04
+2022-05-15 08:18:37,761 INFO [train.py:812] (7/8) Epoch 25, batch 1050, loss[loss=0.1284, simple_loss=0.2151, pruned_loss=0.02091, over 7329.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2479, pruned_loss=0.03287, over 1418746.38 frames.], batch size: 20, lr: 3.13e-04
+2022-05-15 08:19:35,317 INFO [train.py:812] (7/8) Epoch 25, batch 1100, loss[loss=0.1413, simple_loss=0.2385, pruned_loss=0.02207, over 7335.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2477, pruned_loss=0.03276, over 1421008.01 frames.], batch size: 22, lr: 3.13e-04
+2022-05-15 08:20:32,140 INFO [train.py:812] (7/8) Epoch 25, batch 1150, loss[loss=0.1612, simple_loss=0.2544, pruned_loss=0.03402, over 7211.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2484, pruned_loss=0.03313, over 1423799.49 frames.], batch size: 23, lr: 3.13e-04
+2022-05-15 08:21:31,813 INFO [train.py:812] (7/8) Epoch 25, batch 1200, loss[loss=0.1928, simple_loss=0.2769, pruned_loss=0.0544, over 7379.00 frames.], tot_loss[loss=0.1572, simple_loss=0.248, pruned_loss=0.03316, over 1422683.82 frames.], batch size: 23, lr: 3.13e-04
+2022-05-15 08:22:29,904 INFO [train.py:812] (7/8) Epoch 25, batch 1250, loss[loss=0.1295, simple_loss=0.2221, pruned_loss=0.01844, over 7149.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2481, pruned_loss=0.03316, over 1421067.82 frames.], batch size: 20, lr: 3.13e-04
+2022-05-15 08:23:28,194 INFO [train.py:812] (7/8) Epoch 25, batch 1300, loss[loss=0.1379, simple_loss=0.2315, pruned_loss=0.02219, over 7172.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2476, pruned_loss=0.03284, over 1421181.54 frames.], batch size: 16, lr: 3.13e-04
+2022-05-15 08:24:27,546 INFO [train.py:812] (7/8) Epoch 25, batch 1350, loss[loss=0.1623, simple_loss=0.2559, pruned_loss=0.03439, over 6467.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2473, pruned_loss=0.03262, over 1421148.99 frames.], batch size: 38, lr: 3.13e-04
+2022-05-15 08:25:27,007 INFO [train.py:812] (7/8) Epoch 25, batch 1400, loss[loss=0.1422, simple_loss=0.2291, pruned_loss=0.02759, over 7269.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2477, pruned_loss=0.03239, over 1426323.89 frames.], batch size: 17, lr: 3.13e-04
+2022-05-15 08:26:26,013 INFO [train.py:812] (7/8) Epoch 25, batch 1450, loss[loss=0.1735, simple_loss=0.279, pruned_loss=0.03396, over 7151.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2476, pruned_loss=0.03256, over 1422756.07 frames.], batch size: 20, lr: 3.13e-04
+2022-05-15 08:27:24,408 INFO [train.py:812] (7/8) Epoch 25, batch 1500, loss[loss=0.1767, simple_loss=0.2771, pruned_loss=0.03811, over 6793.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2479, pruned_loss=0.03284, over 1421741.67 frames.], batch size: 31, lr: 3.13e-04
+2022-05-15 08:28:23,107 INFO [train.py:812] (7/8) Epoch 25, batch 1550, loss[loss=0.1489, simple_loss=0.224, pruned_loss=0.03691, over 7277.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2488, pruned_loss=0.03306, over 1422971.74 frames.], batch size: 18, lr: 3.12e-04
+2022-05-15 08:29:22,778 INFO [train.py:812] (7/8) Epoch 25, batch 1600, loss[loss=0.1625, simple_loss=0.2439, pruned_loss=0.04049, over 6856.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2481, pruned_loss=0.03306, over 1421624.48 frames.], batch size: 15, lr: 3.12e-04
+2022-05-15 08:30:21,932 INFO [train.py:812] (7/8) Epoch 25, batch 1650, loss[loss=0.1487, simple_loss=0.245, pruned_loss=0.02626, over 7215.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2475, pruned_loss=0.03293, over 1422628.42 frames.], batch size: 21, lr: 3.12e-04
+2022-05-15 08:31:21,088 INFO [train.py:812] (7/8) Epoch 25, batch 1700, loss[loss=0.1654, simple_loss=0.2656, pruned_loss=0.03261, over 7380.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2476, pruned_loss=0.03296, over 1421672.02 frames.], batch size: 23, lr: 3.12e-04
+2022-05-15 08:32:19,172 INFO [train.py:812] (7/8) Epoch 25, batch 1750, loss[loss=0.131, simple_loss=0.2179, pruned_loss=0.02211, over 7139.00 frames.], tot_loss[loss=0.1567, simple_loss=0.248, pruned_loss=0.0327, over 1424033.17 frames.], batch size: 17, lr: 3.12e-04
+2022-05-15 08:33:18,573 INFO [train.py:812] (7/8) Epoch 25, batch 1800, loss[loss=0.1518, simple_loss=0.2346, pruned_loss=0.03448, over 7007.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2481, pruned_loss=0.03249, over 1423972.11 frames.], batch size: 16, lr: 3.12e-04
+2022-05-15 08:34:17,247 INFO [train.py:812] (7/8) Epoch 25, batch 1850, loss[loss=0.1379, simple_loss=0.2202, pruned_loss=0.02782, over 6808.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2478, pruned_loss=0.03261, over 1419986.83 frames.], batch size: 15, lr: 3.12e-04
+2022-05-15 08:35:20,970 INFO [train.py:812] (7/8) Epoch 25, batch 1900, loss[loss=0.1679, simple_loss=0.2703, pruned_loss=0.03272, over 7336.00 frames.], tot_loss[loss=0.157, simple_loss=0.2484, pruned_loss=0.03284, over 1422111.61 frames.], batch size: 25, lr: 3.12e-04
+2022-05-15 08:36:19,553 INFO [train.py:812] (7/8) Epoch 25, batch 1950, loss[loss=0.1503, simple_loss=0.2488, pruned_loss=0.02583, over 7254.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2485, pruned_loss=0.03307, over 1423697.87 frames.], batch size: 19, lr: 3.12e-04
+2022-05-15 08:37:18,273 INFO [train.py:812] (7/8) Epoch 25, batch 2000, loss[loss=0.1535, simple_loss=0.2378, pruned_loss=0.03458, over 7161.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2476, pruned_loss=0.03287, over 1423559.17 frames.], batch size: 18, lr: 3.12e-04
+2022-05-15 08:38:16,627 INFO [train.py:812] (7/8) Epoch 25, batch 2050, loss[loss=0.1846, simple_loss=0.284, pruned_loss=0.04261, over 7314.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2466, pruned_loss=0.03261, over 1426154.14 frames.], batch size: 21, lr: 3.12e-04
+2022-05-15 08:39:15,915 INFO [train.py:812] (7/8) Epoch 25, batch 2100, loss[loss=0.1328, simple_loss=0.2228, pruned_loss=0.02142, over 7260.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2469, pruned_loss=0.03268, over 1422722.80 frames.], batch size: 19, lr: 3.12e-04
+2022-05-15 08:40:13,588 INFO [train.py:812] (7/8) Epoch 25, batch 2150, loss[loss=0.1686, simple_loss=0.2507, pruned_loss=0.04323, over 7448.00 frames.], tot_loss[loss=0.157, simple_loss=0.248, pruned_loss=0.03298, over 1421516.64 frames.], batch size: 20, lr: 3.12e-04
+2022-05-15 08:41:13,385 INFO [train.py:812] (7/8) Epoch 25, batch 2200, loss[loss=0.1305, simple_loss=0.2114, pruned_loss=0.02484, over 7187.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2467, pruned_loss=0.03252, over 1420662.34 frames.], batch size: 16, lr: 3.12e-04
+2022-05-15 08:42:11,797 INFO [train.py:812] (7/8) Epoch 25, batch 2250, loss[loss=0.1362, simple_loss=0.228, pruned_loss=0.02218, over 7060.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2472, pruned_loss=0.03288, over 1416884.36 frames.], batch size: 18, lr: 3.12e-04
+2022-05-15 08:43:09,238 INFO [train.py:812] (7/8) Epoch 25, batch 2300, loss[loss=0.1297, simple_loss=0.2165, pruned_loss=0.02143, over 7187.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2463, pruned_loss=0.03244, over 1418503.63 frames.], batch size: 16, lr: 3.11e-04
+2022-05-15 08:44:06,027 INFO [train.py:812] (7/8) Epoch 25, batch 2350, loss[loss=0.1543, simple_loss=0.2521, pruned_loss=0.02827, over 7330.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2453, pruned_loss=0.03215, over 1419112.63 frames.], batch size: 21, lr: 3.11e-04
+2022-05-15 08:45:05,396 INFO [train.py:812] (7/8) Epoch 25, batch 2400, loss[loss=0.1774, simple_loss=0.2616, pruned_loss=0.04663, over 7365.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2474, pruned_loss=0.03274, over 1423731.15 frames.], batch size: 19, lr: 3.11e-04
+2022-05-15 08:46:04,732 INFO [train.py:812] (7/8) Epoch 25, batch 2450, loss[loss=0.1334, simple_loss=0.2199, pruned_loss=0.0234, over 7138.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2474, pruned_loss=0.03257, over 1423783.42 frames.], batch size: 17, lr: 3.11e-04
+2022-05-15 08:47:04,394 INFO [train.py:812] (7/8) Epoch 25, batch 2500, loss[loss=0.1534, simple_loss=0.2554, pruned_loss=0.02574, over 7407.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2475, pruned_loss=0.0324, over 1423894.29 frames.], batch size: 21, lr: 3.11e-04
+2022-05-15 08:48:03,405 INFO [train.py:812] (7/8) Epoch 25, batch 2550, loss[loss=0.1664, simple_loss=0.2666, pruned_loss=0.03307, over 7429.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2478, pruned_loss=0.03269, over 1426076.68 frames.], batch size: 20, lr: 3.11e-04
+2022-05-15 08:49:03,074 INFO [train.py:812] (7/8) Epoch 25, batch 2600, loss[loss=0.1564, simple_loss=0.2339, pruned_loss=0.03942, over 7131.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2486, pruned_loss=0.03332, over 1423403.77 frames.], batch size: 17, lr: 3.11e-04
+2022-05-15 08:50:01,854 INFO [train.py:812] (7/8) Epoch 25, batch 2650, loss[loss=0.1455, simple_loss=0.2447, pruned_loss=0.02311, over 7216.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2493, pruned_loss=0.0331, over 1425508.73 frames.], batch size: 22, lr: 3.11e-04
+2022-05-15 08:51:09,502 INFO [train.py:812] (7/8) Epoch 25, batch 2700, loss[loss=0.1581, simple_loss=0.2454, pruned_loss=0.03536, over 7059.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2482, pruned_loss=0.03262, over 1427256.79 frames.], batch size: 18, lr: 3.11e-04
+2022-05-15 08:52:06,920 INFO [train.py:812] (7/8) Epoch 25, batch 2750, loss[loss=0.187, simple_loss=0.277, pruned_loss=0.04857, over 7147.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2477, pruned_loss=0.03242, over 1421468.97 frames.], batch size: 20, lr: 3.11e-04
+2022-05-15 08:53:06,504 INFO [train.py:812] (7/8) Epoch 25, batch 2800, loss[loss=0.1589, simple_loss=0.2504, pruned_loss=0.03366, over 7251.00 frames.], tot_loss[loss=0.1566, simple_loss=0.248, pruned_loss=0.03254, over 1421436.03 frames.], batch size: 19, lr: 3.11e-04
+2022-05-15 08:54:05,465 INFO [train.py:812] (7/8) Epoch 25, batch 2850, loss[loss=0.1582, simple_loss=0.2412, pruned_loss=0.03756, over 7431.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2474, pruned_loss=0.03226, over 1419761.88 frames.], batch size: 20, lr: 3.11e-04
+2022-05-15 08:55:04,589 INFO [train.py:812] (7/8) Epoch 25, batch 2900, loss[loss=0.1714, simple_loss=0.2807, pruned_loss=0.03102, over 7191.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2475, pruned_loss=0.0322, over 1420151.85 frames.], batch size: 23, lr: 3.11e-04
+2022-05-15 08:56:02,094 INFO [train.py:812] (7/8) Epoch 25, batch 2950, loss[loss=0.1389, simple_loss=0.2264, pruned_loss=0.02567, over 7105.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2476, pruned_loss=0.03239, over 1425244.53 frames.], batch size: 21, lr: 3.11e-04
+2022-05-15 08:57:29,016 INFO [train.py:812] (7/8) Epoch 25, batch 3000, loss[loss=0.1749, simple_loss=0.274, pruned_loss=0.03784, over 6869.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2466, pruned_loss=0.03219, over 1427964.87 frames.], batch size: 31, lr: 3.10e-04
+2022-05-15 08:57:29,017 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 08:57:46,643 INFO [train.py:841] (7/8) Epoch 25, validation: loss=0.1532, simple_loss=0.2507, pruned_loss=0.02787, over 698248.00 frames.
+2022-05-15 08:58:45,941 INFO [train.py:812] (7/8) Epoch 25, batch 3050, loss[loss=0.138, simple_loss=0.2346, pruned_loss=0.02066, over 7112.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2468, pruned_loss=0.03232, over 1427698.17 frames.], batch size: 21, lr: 3.10e-04
+2022-05-15 08:59:53,877 INFO [train.py:812] (7/8) Epoch 25, batch 3100, loss[loss=0.1713, simple_loss=0.2549, pruned_loss=0.04387, over 6832.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2469, pruned_loss=0.03261, over 1429263.67 frames.], batch size: 15, lr: 3.10e-04
+2022-05-15 09:01:01,455 INFO [train.py:812] (7/8) Epoch 25, batch 3150, loss[loss=0.1439, simple_loss=0.2328, pruned_loss=0.02753, over 7251.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2484, pruned_loss=0.03313, over 1430713.20 frames.], batch size: 19, lr: 3.10e-04
+2022-05-15 09:02:01,450 INFO [train.py:812] (7/8) Epoch 25, batch 3200, loss[loss=0.1755, simple_loss=0.2586, pruned_loss=0.04626, over 5109.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2481, pruned_loss=0.03321, over 1429015.16 frames.], batch size: 52, lr: 3.10e-04
+2022-05-15 09:03:00,365 INFO [train.py:812] (7/8) Epoch 25, batch 3250, loss[loss=0.1925, simple_loss=0.2918, pruned_loss=0.04659, over 7236.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2487, pruned_loss=0.03379, over 1426654.14 frames.], batch size: 20, lr: 3.10e-04
+2022-05-15 09:03:59,294 INFO [train.py:812] (7/8) Epoch 25, batch 3300, loss[loss=0.1513, simple_loss=0.2486, pruned_loss=0.02698, over 7170.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2484, pruned_loss=0.03308, over 1426022.04 frames.], batch size: 19, lr: 3.10e-04
+2022-05-15 09:04:58,429 INFO [train.py:812] (7/8) Epoch 25, batch 3350, loss[loss=0.1402, simple_loss=0.2263, pruned_loss=0.02707, over 7248.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2476, pruned_loss=0.03299, over 1422634.64 frames.], batch size: 19, lr: 3.10e-04
+2022-05-15 09:05:57,562 INFO [train.py:812] (7/8) Epoch 25, batch 3400, loss[loss=0.1278, simple_loss=0.2068, pruned_loss=0.02444, over 7275.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2473, pruned_loss=0.03307, over 1424111.56 frames.], batch size: 17, lr: 3.10e-04
+2022-05-15 09:06:56,037 INFO [train.py:812] (7/8) Epoch 25, batch 3450, loss[loss=0.1606, simple_loss=0.2505, pruned_loss=0.03533, over 7219.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2475, pruned_loss=0.03304, over 1421299.45 frames.], batch size: 21, lr: 3.10e-04
+2022-05-15 09:07:54,105 INFO [train.py:812] (7/8) Epoch 25, batch 3500, loss[loss=0.1274, simple_loss=0.2101, pruned_loss=0.02237, over 7155.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2479, pruned_loss=0.03328, over 1422697.01 frames.], batch size: 17, lr: 3.10e-04
+2022-05-15 09:08:53,545 INFO [train.py:812] (7/8) Epoch 25, batch 3550, loss[loss=0.1477, simple_loss=0.2351, pruned_loss=0.03017, over 7335.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2485, pruned_loss=0.03357, over 1423617.74 frames.], batch size: 20, lr: 3.10e-04
+2022-05-15 09:09:52,761 INFO [train.py:812] (7/8) Epoch 25, batch 3600, loss[loss=0.1714, simple_loss=0.2606, pruned_loss=0.04108, over 7216.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2488, pruned_loss=0.0334, over 1421988.92 frames.], batch size: 23, lr: 3.10e-04
+2022-05-15 09:10:51,688 INFO [train.py:812] (7/8) Epoch 25, batch 3650, loss[loss=0.1445, simple_loss=0.2445, pruned_loss=0.02228, over 6432.00 frames.], tot_loss[loss=0.157, simple_loss=0.2478, pruned_loss=0.0331, over 1418122.06 frames.], batch size: 37, lr: 3.10e-04
+2022-05-15 09:11:51,282 INFO [train.py:812] (7/8) Epoch 25, batch 3700, loss[loss=0.1592, simple_loss=0.2494, pruned_loss=0.03447, over 7437.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2475, pruned_loss=0.03307, over 1420944.63 frames.], batch size: 20, lr: 3.10e-04
+2022-05-15 09:12:50,515 INFO [train.py:812] (7/8) Epoch 25, batch 3750, loss[loss=0.1734, simple_loss=0.269, pruned_loss=0.03891, over 7383.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2472, pruned_loss=0.03303, over 1423823.12 frames.], batch size: 23, lr: 3.09e-04
+2022-05-15 09:13:50,136 INFO [train.py:812] (7/8) Epoch 25, batch 3800, loss[loss=0.1827, simple_loss=0.2754, pruned_loss=0.04501, over 5118.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2476, pruned_loss=0.03291, over 1421653.76 frames.], batch size: 52, lr: 3.09e-04
+2022-05-15 09:14:48,023 INFO [train.py:812] (7/8) Epoch 25, batch 3850, loss[loss=0.1466, simple_loss=0.2364, pruned_loss=0.0284, over 7294.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2477, pruned_loss=0.03274, over 1421719.08 frames.], batch size: 18, lr: 3.09e-04
+2022-05-15 09:15:47,063 INFO [train.py:812] (7/8) Epoch 25, batch 3900, loss[loss=0.1505, simple_loss=0.2391, pruned_loss=0.03095, over 7262.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2477, pruned_loss=0.03259, over 1421012.22 frames.], batch size: 19, lr: 3.09e-04
+2022-05-15 09:16:44,731 INFO [train.py:812] (7/8) Epoch 25, batch 3950, loss[loss=0.1346, simple_loss=0.2202, pruned_loss=0.02451, over 7412.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2476, pruned_loss=0.03247, over 1423079.43 frames.], batch size: 18, lr: 3.09e-04
+2022-05-15 09:17:43,615 INFO [train.py:812] (7/8) Epoch 25, batch 4000, loss[loss=0.1595, simple_loss=0.2524, pruned_loss=0.03334, over 7326.00 frames.], tot_loss[loss=0.157, simple_loss=0.2484, pruned_loss=0.03281, over 1422746.77 frames.], batch size: 21, lr: 3.09e-04
+2022-05-15 09:18:42,658 INFO [train.py:812] (7/8) Epoch 25, batch 4050, loss[loss=0.1502, simple_loss=0.2371, pruned_loss=0.03166, over 7433.00 frames.], tot_loss[loss=0.1568, simple_loss=0.248, pruned_loss=0.03279, over 1421910.49 frames.], batch size: 20, lr: 3.09e-04
+2022-05-15 09:19:41,957 INFO [train.py:812] (7/8) Epoch 25, batch 4100, loss[loss=0.1792, simple_loss=0.2667, pruned_loss=0.04589, over 6127.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2486, pruned_loss=0.03264, over 1422207.79 frames.], batch size: 37, lr: 3.09e-04
+2022-05-15 09:20:41,060 INFO [train.py:812] (7/8) Epoch 25, batch 4150, loss[loss=0.1752, simple_loss=0.2681, pruned_loss=0.04118, over 7210.00 frames.], tot_loss[loss=0.1564, simple_loss=0.248, pruned_loss=0.03237, over 1419234.59 frames.], batch size: 21, lr: 3.09e-04
+2022-05-15 09:21:39,859 INFO [train.py:812] (7/8) Epoch 25, batch 4200, loss[loss=0.1657, simple_loss=0.2625, pruned_loss=0.03441, over 7196.00 frames.], tot_loss[loss=0.1579, simple_loss=0.25, pruned_loss=0.03289, over 1420762.40 frames.], batch size: 23, lr: 3.09e-04
+2022-05-15 09:22:38,439 INFO [train.py:812] (7/8) Epoch 25, batch 4250, loss[loss=0.1483, simple_loss=0.2501, pruned_loss=0.02328, over 6536.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2492, pruned_loss=0.03268, over 1415685.91 frames.], batch size: 37, lr: 3.09e-04
+2022-05-15 09:23:37,047 INFO [train.py:812] (7/8) Epoch 25, batch 4300, loss[loss=0.143, simple_loss=0.2313, pruned_loss=0.02734, over 7160.00 frames.], tot_loss[loss=0.1574, simple_loss=0.249, pruned_loss=0.03287, over 1415109.89 frames.], batch size: 19, lr: 3.09e-04
+2022-05-15 09:24:36,176 INFO [train.py:812] (7/8) Epoch 25, batch 4350, loss[loss=0.1815, simple_loss=0.2792, pruned_loss=0.04192, over 7274.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2481, pruned_loss=0.03313, over 1414716.64 frames.], batch size: 25, lr: 3.09e-04
+2022-05-15 09:25:35,391 INFO [train.py:812] (7/8) Epoch 25, batch 4400, loss[loss=0.1828, simple_loss=0.2786, pruned_loss=0.04349, over 7279.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2488, pruned_loss=0.03319, over 1413603.48 frames.], batch size: 24, lr: 3.09e-04
+2022-05-15 09:26:34,048 INFO [train.py:812] (7/8) Epoch 25, batch 4450, loss[loss=0.1605, simple_loss=0.2618, pruned_loss=0.02958, over 7297.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2497, pruned_loss=0.03341, over 1405144.85 frames.], batch size: 25, lr: 3.09e-04
+2022-05-15 09:27:33,027 INFO [train.py:812] (7/8) Epoch 25, batch 4500, loss[loss=0.1764, simple_loss=0.2597, pruned_loss=0.04651, over 5330.00 frames.], tot_loss[loss=0.1593, simple_loss=0.251, pruned_loss=0.0338, over 1389319.14 frames.], batch size: 52, lr: 3.08e-04
+2022-05-15 09:28:30,333 INFO [train.py:812] (7/8) Epoch 25, batch 4550, loss[loss=0.1822, simple_loss=0.2679, pruned_loss=0.04828, over 4928.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2525, pruned_loss=0.03424, over 1352404.12 frames.], batch size: 52, lr: 3.08e-04
+2022-05-15 09:29:36,559 INFO [train.py:812] (7/8) Epoch 26, batch 0, loss[loss=0.1666, simple_loss=0.262, pruned_loss=0.03554, over 7222.00 frames.], tot_loss[loss=0.1666, simple_loss=0.262, pruned_loss=0.03554, over 7222.00 frames.], batch size: 21, lr: 3.02e-04
+2022-05-15 09:30:35,869 INFO [train.py:812] (7/8) Epoch 26, batch 50, loss[loss=0.1479, simple_loss=0.2415, pruned_loss=0.02715, over 7318.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2435, pruned_loss=0.03064, over 322029.42 frames.], batch size: 21, lr: 3.02e-04
+2022-05-15 09:31:35,519 INFO [train.py:812] (7/8) Epoch 26, batch 100, loss[loss=0.1851, simple_loss=0.2697, pruned_loss=0.05028, over 5261.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.03178, over 566462.72 frames.], batch size: 53, lr: 3.02e-04
+2022-05-15 09:32:35,409 INFO [train.py:812] (7/8) Epoch 26, batch 150, loss[loss=0.1181, simple_loss=0.1959, pruned_loss=0.02009, over 7282.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2465, pruned_loss=0.03203, over 760555.85 frames.], batch size: 17, lr: 3.02e-04
+2022-05-15 09:33:34,924 INFO [train.py:812] (7/8) Epoch 26, batch 200, loss[loss=0.1699, simple_loss=0.2642, pruned_loss=0.03776, over 7378.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2461, pruned_loss=0.03187, over 907509.86 frames.], batch size: 23, lr: 3.02e-04
+2022-05-15 09:34:32,565 INFO [train.py:812] (7/8) Epoch 26, batch 250, loss[loss=0.1602, simple_loss=0.2643, pruned_loss=0.02803, over 7193.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2468, pruned_loss=0.03197, over 1020048.20 frames.], batch size: 22, lr: 3.02e-04
+2022-05-15 09:35:31,880 INFO [train.py:812] (7/8) Epoch 26, batch 300, loss[loss=0.1493, simple_loss=0.2508, pruned_loss=0.02392, over 7326.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2484, pruned_loss=0.03258, over 1106618.48 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:36:29,860 INFO [train.py:812] (7/8) Epoch 26, batch 350, loss[loss=0.185, simple_loss=0.2728, pruned_loss=0.04863, over 7169.00 frames.], tot_loss[loss=0.156, simple_loss=0.2473, pruned_loss=0.03236, over 1176330.71 frames.], batch size: 18, lr: 3.02e-04
+2022-05-15 09:37:29,717 INFO [train.py:812] (7/8) Epoch 26, batch 400, loss[loss=0.1547, simple_loss=0.2313, pruned_loss=0.03901, over 7411.00 frames.], tot_loss[loss=0.157, simple_loss=0.2483, pruned_loss=0.03284, over 1234380.35 frames.], batch size: 18, lr: 3.02e-04
+2022-05-15 09:38:28,220 INFO [train.py:812] (7/8) Epoch 26, batch 450, loss[loss=0.1793, simple_loss=0.2687, pruned_loss=0.04498, over 7416.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2493, pruned_loss=0.03327, over 1274943.83 frames.], batch size: 21, lr: 3.02e-04
+2022-05-15 09:39:25,663 INFO [train.py:812] (7/8) Epoch 26, batch 500, loss[loss=0.152, simple_loss=0.2487, pruned_loss=0.0276, over 7394.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2494, pruned_loss=0.0331, over 1303111.90 frames.], batch size: 23, lr: 3.02e-04
+2022-05-15 09:40:22,362 INFO [train.py:812] (7/8) Epoch 26, batch 550, loss[loss=0.148, simple_loss=0.2367, pruned_loss=0.02966, over 7237.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2476, pruned_loss=0.03258, over 1329306.90 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:41:20,627 INFO [train.py:812] (7/8) Epoch 26, batch 600, loss[loss=0.1847, simple_loss=0.271, pruned_loss=0.04919, over 7050.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2478, pruned_loss=0.03253, over 1347249.94 frames.], batch size: 28, lr: 3.02e-04
+2022-05-15 09:42:19,358 INFO [train.py:812] (7/8) Epoch 26, batch 650, loss[loss=0.1535, simple_loss=0.2526, pruned_loss=0.02725, over 7330.00 frames.], tot_loss[loss=0.156, simple_loss=0.2472, pruned_loss=0.03244, over 1361510.32 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:43:17,915 INFO [train.py:812] (7/8) Epoch 26, batch 700, loss[loss=0.1817, simple_loss=0.2765, pruned_loss=0.04346, over 7146.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2472, pruned_loss=0.03248, over 1374835.90 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:44:17,570 INFO [train.py:812] (7/8) Epoch 26, batch 750, loss[loss=0.1553, simple_loss=0.248, pruned_loss=0.03127, over 7418.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2477, pruned_loss=0.03244, over 1390204.86 frames.], batch size: 20, lr: 3.01e-04
+2022-05-15 09:45:17,301 INFO [train.py:812] (7/8) Epoch 26, batch 800, loss[loss=0.1634, simple_loss=0.2591, pruned_loss=0.03388, over 6719.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2475, pruned_loss=0.03212, over 1395317.65 frames.], batch size: 31, lr: 3.01e-04
+2022-05-15 09:46:14,839 INFO [train.py:812] (7/8) Epoch 26, batch 850, loss[loss=0.1465, simple_loss=0.2387, pruned_loss=0.02715, over 7107.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2476, pruned_loss=0.0318, over 1405710.95 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:47:13,164 INFO [train.py:812] (7/8) Epoch 26, batch 900, loss[loss=0.1377, simple_loss=0.2249, pruned_loss=0.02532, over 6824.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2475, pruned_loss=0.03202, over 1405528.69 frames.], batch size: 15, lr: 3.01e-04
+2022-05-15 09:48:12,087 INFO [train.py:812] (7/8) Epoch 26, batch 950, loss[loss=0.1376, simple_loss=0.2214, pruned_loss=0.02683, over 7285.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2469, pruned_loss=0.03184, over 1412418.29 frames.], batch size: 17, lr: 3.01e-04
+2022-05-15 09:49:11,096 INFO [train.py:812] (7/8) Epoch 26, batch 1000, loss[loss=0.1877, simple_loss=0.2788, pruned_loss=0.04833, over 7119.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2477, pruned_loss=0.03244, over 1411322.64 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:50:10,521 INFO [train.py:812] (7/8) Epoch 26, batch 1050, loss[loss=0.1877, simple_loss=0.2607, pruned_loss=0.05734, over 5304.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2485, pruned_loss=0.03249, over 1412447.96 frames.], batch size: 52, lr: 3.01e-04
+2022-05-15 09:51:08,592 INFO [train.py:812] (7/8) Epoch 26, batch 1100, loss[loss=0.166, simple_loss=0.2676, pruned_loss=0.03223, over 7124.00 frames.], tot_loss[loss=0.157, simple_loss=0.2488, pruned_loss=0.0326, over 1413576.58 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:52:08,150 INFO [train.py:812] (7/8) Epoch 26, batch 1150, loss[loss=0.1444, simple_loss=0.2398, pruned_loss=0.02453, over 7374.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2484, pruned_loss=0.03257, over 1417214.45 frames.], batch size: 23, lr: 3.01e-04
+2022-05-15 09:53:08,271 INFO [train.py:812] (7/8) Epoch 26, batch 1200, loss[loss=0.1498, simple_loss=0.2394, pruned_loss=0.03016, over 7149.00 frames.], tot_loss[loss=0.1566, simple_loss=0.248, pruned_loss=0.03261, over 1421165.07 frames.], batch size: 17, lr: 3.01e-04
+2022-05-15 09:54:07,377 INFO [train.py:812] (7/8) Epoch 26, batch 1250, loss[loss=0.1673, simple_loss=0.2618, pruned_loss=0.03635, over 7319.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2482, pruned_loss=0.03243, over 1423343.36 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:55:11,150 INFO [train.py:812] (7/8) Epoch 26, batch 1300, loss[loss=0.1512, simple_loss=0.2421, pruned_loss=0.03012, over 7431.00 frames.], tot_loss[loss=0.1564, simple_loss=0.248, pruned_loss=0.03245, over 1426343.97 frames.], batch size: 20, lr: 3.01e-04
+2022-05-15 09:56:09,561 INFO [train.py:812] (7/8) Epoch 26, batch 1350, loss[loss=0.1556, simple_loss=0.255, pruned_loss=0.02815, over 7318.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2486, pruned_loss=0.03231, over 1426682.09 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:57:07,845 INFO [train.py:812] (7/8) Epoch 26, batch 1400, loss[loss=0.1604, simple_loss=0.2576, pruned_loss=0.03156, over 7340.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2488, pruned_loss=0.03293, over 1427209.78 frames.], batch size: 22, lr: 3.01e-04
+2022-05-15 09:58:05,659 INFO [train.py:812] (7/8) Epoch 26, batch 1450, loss[loss=0.1205, simple_loss=0.2055, pruned_loss=0.01777, over 6997.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2492, pruned_loss=0.03302, over 1428975.53 frames.], batch size: 16, lr: 3.01e-04
+2022-05-15 09:59:03,812 INFO [train.py:812] (7/8) Epoch 26, batch 1500, loss[loss=0.1579, simple_loss=0.252, pruned_loss=0.0319, over 7231.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2485, pruned_loss=0.03284, over 1428105.03 frames.], batch size: 21, lr: 3.00e-04
+2022-05-15 10:00:02,505 INFO [train.py:812] (7/8) Epoch 26, batch 1550, loss[loss=0.1478, simple_loss=0.2273, pruned_loss=0.03415, over 7127.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2481, pruned_loss=0.03263, over 1427410.96 frames.], batch size: 17, lr: 3.00e-04
+2022-05-15 10:01:01,530 INFO [train.py:812] (7/8) Epoch 26, batch 1600, loss[loss=0.1382, simple_loss=0.2408, pruned_loss=0.01781, over 7143.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2485, pruned_loss=0.0326, over 1424515.64 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:02:00,527 INFO [train.py:812] (7/8) Epoch 26, batch 1650, loss[loss=0.1843, simple_loss=0.2748, pruned_loss=0.04689, over 7098.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2471, pruned_loss=0.03239, over 1425318.69 frames.], batch size: 28, lr: 3.00e-04
+2022-05-15 10:02:59,736 INFO [train.py:812] (7/8) Epoch 26, batch 1700, loss[loss=0.1637, simple_loss=0.2548, pruned_loss=0.03628, over 7320.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03225, over 1425046.89 frames.], batch size: 21, lr: 3.00e-04
+2022-05-15 10:04:07,551 INFO [train.py:812] (7/8) Epoch 26, batch 1750, loss[loss=0.1305, simple_loss=0.2191, pruned_loss=0.02096, over 7141.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2468, pruned_loss=0.0319, over 1424706.12 frames.], batch size: 17, lr: 3.00e-04
+2022-05-15 10:05:06,535 INFO [train.py:812] (7/8) Epoch 26, batch 1800, loss[loss=0.1558, simple_loss=0.2449, pruned_loss=0.03338, over 7146.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2463, pruned_loss=0.03207, over 1420690.75 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:06:05,275 INFO [train.py:812] (7/8) Epoch 26, batch 1850, loss[loss=0.1541, simple_loss=0.2515, pruned_loss=0.02841, over 7443.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.03181, over 1421390.05 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:07:04,833 INFO [train.py:812] (7/8) Epoch 26, batch 1900, loss[loss=0.1192, simple_loss=0.2017, pruned_loss=0.01831, over 7140.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2474, pruned_loss=0.03242, over 1422104.55 frames.], batch size: 17, lr: 3.00e-04
+2022-05-15 10:08:02,603 INFO [train.py:812] (7/8) Epoch 26, batch 1950, loss[loss=0.1735, simple_loss=0.2615, pruned_loss=0.04276, over 4865.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2474, pruned_loss=0.03254, over 1419591.55 frames.], batch size: 53, lr: 3.00e-04
+2022-05-15 10:09:00,918 INFO [train.py:812] (7/8) Epoch 26, batch 2000, loss[loss=0.1399, simple_loss=0.224, pruned_loss=0.02789, over 7155.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03267, over 1417386.78 frames.], batch size: 19, lr: 3.00e-04
+2022-05-15 10:10:00,138 INFO [train.py:812] (7/8) Epoch 26, batch 2050, loss[loss=0.1627, simple_loss=0.2626, pruned_loss=0.03144, over 7318.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03265, over 1418959.98 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:10:59,287 INFO [train.py:812] (7/8) Epoch 26, batch 2100, loss[loss=0.1496, simple_loss=0.243, pruned_loss=0.02814, over 7216.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2481, pruned_loss=0.03308, over 1418048.51 frames.], batch size: 22, lr: 3.00e-04
+2022-05-15 10:11:58,159 INFO [train.py:812] (7/8) Epoch 26, batch 2150, loss[loss=0.1341, simple_loss=0.2247, pruned_loss=0.0217, over 7170.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2483, pruned_loss=0.03259, over 1420464.39 frames.], batch size: 18, lr: 3.00e-04
+2022-05-15 10:12:57,697 INFO [train.py:812] (7/8) Epoch 26, batch 2200, loss[loss=0.1478, simple_loss=0.2461, pruned_loss=0.0247, over 7050.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2481, pruned_loss=0.03223, over 1422629.19 frames.], batch size: 28, lr: 3.00e-04
+2022-05-15 10:13:56,449 INFO [train.py:812] (7/8) Epoch 26, batch 2250, loss[loss=0.1708, simple_loss=0.2624, pruned_loss=0.03958, over 7369.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2473, pruned_loss=0.03166, over 1424904.68 frames.], batch size: 23, lr: 3.00e-04
+2022-05-15 10:14:54,822 INFO [train.py:812] (7/8) Epoch 26, batch 2300, loss[loss=0.1514, simple_loss=0.2385, pruned_loss=0.03213, over 7064.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2484, pruned_loss=0.03238, over 1424935.44 frames.], batch size: 18, lr: 2.99e-04
+2022-05-15 10:15:54,099 INFO [train.py:812] (7/8) Epoch 26, batch 2350, loss[loss=0.1704, simple_loss=0.2571, pruned_loss=0.0418, over 7251.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2471, pruned_loss=0.0319, over 1425851.98 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:16:53,718 INFO [train.py:812] (7/8) Epoch 26, batch 2400, loss[loss=0.1777, simple_loss=0.2722, pruned_loss=0.04165, over 7386.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2472, pruned_loss=0.03219, over 1423457.35 frames.], batch size: 23, lr: 2.99e-04
+2022-05-15 10:17:52,722 INFO [train.py:812] (7/8) Epoch 26, batch 2450, loss[loss=0.1474, simple_loss=0.2432, pruned_loss=0.02585, over 6744.00 frames.], tot_loss[loss=0.156, simple_loss=0.247, pruned_loss=0.03246, over 1421897.63 frames.], batch size: 31, lr: 2.99e-04
+2022-05-15 10:18:50,844 INFO [train.py:812] (7/8) Epoch 26, batch 2500, loss[loss=0.1481, simple_loss=0.2473, pruned_loss=0.02447, over 7353.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2455, pruned_loss=0.03172, over 1424367.37 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:19:48,028 INFO [train.py:812] (7/8) Epoch 26, batch 2550, loss[loss=0.1335, simple_loss=0.2255, pruned_loss=0.02078, over 7408.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2455, pruned_loss=0.03173, over 1426554.28 frames.], batch size: 18, lr: 2.99e-04
+2022-05-15 10:20:46,867 INFO [train.py:812] (7/8) Epoch 26, batch 2600, loss[loss=0.1458, simple_loss=0.2288, pruned_loss=0.03139, over 7158.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2456, pruned_loss=0.03198, over 1423835.71 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:21:44,656 INFO [train.py:812] (7/8) Epoch 26, batch 2650, loss[loss=0.1778, simple_loss=0.265, pruned_loss=0.0453, over 7090.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2464, pruned_loss=0.03229, over 1419474.03 frames.], batch size: 28, lr: 2.99e-04
+2022-05-15 10:22:43,744 INFO [train.py:812] (7/8) Epoch 26, batch 2700, loss[loss=0.1356, simple_loss=0.2287, pruned_loss=0.02122, over 7254.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2459, pruned_loss=0.03229, over 1420732.28 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:23:42,382 INFO [train.py:812] (7/8) Epoch 26, batch 2750, loss[loss=0.1718, simple_loss=0.276, pruned_loss=0.03382, over 7305.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2464, pruned_loss=0.03246, over 1413609.73 frames.], batch size: 25, lr: 2.99e-04
+2022-05-15 10:24:40,508 INFO [train.py:812] (7/8) Epoch 26, batch 2800, loss[loss=0.1398, simple_loss=0.2346, pruned_loss=0.02251, over 7279.00 frames.], tot_loss[loss=0.1553, simple_loss=0.246, pruned_loss=0.03227, over 1416366.99 frames.], batch size: 18, lr: 2.99e-04
+2022-05-15 10:25:38,094 INFO [train.py:812] (7/8) Epoch 26, batch 2850, loss[loss=0.1463, simple_loss=0.2362, pruned_loss=0.02826, over 7417.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2457, pruned_loss=0.03231, over 1411930.29 frames.], batch size: 21, lr: 2.99e-04
+2022-05-15 10:26:37,782 INFO [train.py:812] (7/8) Epoch 26, batch 2900, loss[loss=0.1436, simple_loss=0.246, pruned_loss=0.02061, over 7154.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2462, pruned_loss=0.03233, over 1418370.23 frames.], batch size: 20, lr: 2.99e-04
+2022-05-15 10:27:35,293 INFO [train.py:812] (7/8) Epoch 26, batch 2950, loss[loss=0.1494, simple_loss=0.2467, pruned_loss=0.02606, over 7309.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2474, pruned_loss=0.03268, over 1418459.07 frames.], batch size: 20, lr: 2.99e-04
+2022-05-15 10:28:33,153 INFO [train.py:812] (7/8) Epoch 26, batch 3000, loss[loss=0.1881, simple_loss=0.2689, pruned_loss=0.05363, over 6516.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2481, pruned_loss=0.03264, over 1423054.60 frames.], batch size: 38, lr: 2.99e-04
+2022-05-15 10:28:33,154 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 10:28:40,783 INFO [train.py:841] (7/8) Epoch 26, validation: loss=0.1534, simple_loss=0.2507, pruned_loss=0.02805, over 698248.00 frames.
+2022-05-15 10:29:38,773 INFO [train.py:812] (7/8) Epoch 26, batch 3050, loss[loss=0.1544, simple_loss=0.247, pruned_loss=0.0309, over 7333.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2482, pruned_loss=0.0326, over 1421873.00 frames.], batch size: 22, lr: 2.99e-04
+2022-05-15 10:30:38,724 INFO [train.py:812] (7/8) Epoch 26, batch 3100, loss[loss=0.1491, simple_loss=0.243, pruned_loss=0.02757, over 7257.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2478, pruned_loss=0.03241, over 1419230.38 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:31:36,301 INFO [train.py:812] (7/8) Epoch 26, batch 3150, loss[loss=0.1436, simple_loss=0.2252, pruned_loss=0.03101, over 7161.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2475, pruned_loss=0.03269, over 1418333.17 frames.], batch size: 17, lr: 2.98e-04
+2022-05-15 10:32:35,724 INFO [train.py:812] (7/8) Epoch 26, batch 3200, loss[loss=0.1478, simple_loss=0.2439, pruned_loss=0.02586, over 7141.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2475, pruned_loss=0.03258, over 1421186.42 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:33:35,069 INFO [train.py:812] (7/8) Epoch 26, batch 3250, loss[loss=0.1408, simple_loss=0.2316, pruned_loss=0.02506, over 7267.00 frames.], tot_loss[loss=0.155, simple_loss=0.246, pruned_loss=0.03196, over 1424812.69 frames.], batch size: 18, lr: 2.98e-04
+2022-05-15 10:34:33,029 INFO [train.py:812] (7/8) Epoch 26, batch 3300, loss[loss=0.1593, simple_loss=0.2599, pruned_loss=0.02933, over 7161.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2466, pruned_loss=0.03196, over 1417667.54 frames.], batch size: 26, lr: 2.98e-04
+2022-05-15 10:35:31,831 INFO [train.py:812] (7/8) Epoch 26, batch 3350, loss[loss=0.1555, simple_loss=0.2436, pruned_loss=0.03365, over 7319.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2467, pruned_loss=0.03223, over 1414270.47 frames.], batch size: 21, lr: 2.98e-04
+2022-05-15 10:36:31,839 INFO [train.py:812] (7/8) Epoch 26, batch 3400, loss[loss=0.1626, simple_loss=0.2628, pruned_loss=0.03116, over 6460.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2459, pruned_loss=0.0319, over 1418881.47 frames.], batch size: 37, lr: 2.98e-04
+2022-05-15 10:37:30,446 INFO [train.py:812] (7/8) Epoch 26, batch 3450, loss[loss=0.1363, simple_loss=0.2229, pruned_loss=0.0249, over 7162.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2453, pruned_loss=0.03181, over 1419137.00 frames.], batch size: 18, lr: 2.98e-04
+2022-05-15 10:38:29,770 INFO [train.py:812] (7/8) Epoch 26, batch 3500, loss[loss=0.1936, simple_loss=0.2859, pruned_loss=0.05063, over 7389.00 frames.], tot_loss[loss=0.1549, simple_loss=0.246, pruned_loss=0.03195, over 1418586.16 frames.], batch size: 23, lr: 2.98e-04
+2022-05-15 10:39:28,334 INFO [train.py:812] (7/8) Epoch 26, batch 3550, loss[loss=0.1699, simple_loss=0.2648, pruned_loss=0.03753, over 7406.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2462, pruned_loss=0.03201, over 1420959.95 frames.], batch size: 21, lr: 2.98e-04
+2022-05-15 10:40:26,343 INFO [train.py:812] (7/8) Epoch 26, batch 3600, loss[loss=0.1425, simple_loss=0.2385, pruned_loss=0.0232, over 7196.00 frames.], tot_loss[loss=0.1551, simple_loss=0.246, pruned_loss=0.0321, over 1425468.51 frames.], batch size: 23, lr: 2.98e-04
+2022-05-15 10:41:25,824 INFO [train.py:812] (7/8) Epoch 26, batch 3650, loss[loss=0.1444, simple_loss=0.2324, pruned_loss=0.02822, over 7263.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2476, pruned_loss=0.03287, over 1426857.09 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:42:23,904 INFO [train.py:812] (7/8) Epoch 26, batch 3700, loss[loss=0.1483, simple_loss=0.2372, pruned_loss=0.02973, over 7072.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2474, pruned_loss=0.03289, over 1424850.88 frames.], batch size: 18, lr: 2.98e-04
+2022-05-15 10:43:22,978 INFO [train.py:812] (7/8) Epoch 26, batch 3750, loss[loss=0.1645, simple_loss=0.2597, pruned_loss=0.03462, over 7155.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2474, pruned_loss=0.03273, over 1423916.13 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:44:21,251 INFO [train.py:812] (7/8) Epoch 26, batch 3800, loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02986, over 6311.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2472, pruned_loss=0.03279, over 1422290.33 frames.], batch size: 37, lr: 2.98e-04
+2022-05-15 10:45:20,419 INFO [train.py:812] (7/8) Epoch 26, batch 3850, loss[loss=0.1449, simple_loss=0.2358, pruned_loss=0.02702, over 7158.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2472, pruned_loss=0.03282, over 1419592.47 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:46:19,981 INFO [train.py:812] (7/8) Epoch 26, batch 3900, loss[loss=0.1409, simple_loss=0.2199, pruned_loss=0.03095, over 7404.00 frames.], tot_loss[loss=0.1569, simple_loss=0.248, pruned_loss=0.03287, over 1421791.71 frames.], batch size: 18, lr: 2.97e-04
+2022-05-15 10:47:17,440 INFO [train.py:812] (7/8) Epoch 26, batch 3950, loss[loss=0.1505, simple_loss=0.2557, pruned_loss=0.02264, over 7230.00 frames.], tot_loss[loss=0.157, simple_loss=0.2481, pruned_loss=0.03298, over 1426462.50 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:48:16,838 INFO [train.py:812] (7/8) Epoch 26, batch 4000, loss[loss=0.1521, simple_loss=0.2369, pruned_loss=0.03372, over 7433.00 frames.], tot_loss[loss=0.1571, simple_loss=0.248, pruned_loss=0.03303, over 1418888.56 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:49:15,517 INFO [train.py:812] (7/8) Epoch 26, batch 4050, loss[loss=0.1438, simple_loss=0.2343, pruned_loss=0.02662, over 7409.00 frames.], tot_loss[loss=0.157, simple_loss=0.2483, pruned_loss=0.03289, over 1420021.16 frames.], batch size: 21, lr: 2.97e-04
+2022-05-15 10:50:14,956 INFO [train.py:812] (7/8) Epoch 26, batch 4100, loss[loss=0.1567, simple_loss=0.2531, pruned_loss=0.03013, over 7422.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2482, pruned_loss=0.033, over 1418710.08 frames.], batch size: 21, lr: 2.97e-04
+2022-05-15 10:51:14,868 INFO [train.py:812] (7/8) Epoch 26, batch 4150, loss[loss=0.1509, simple_loss=0.2447, pruned_loss=0.02856, over 7256.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2478, pruned_loss=0.03271, over 1423468.01 frames.], batch size: 19, lr: 2.97e-04
+2022-05-15 10:52:13,204 INFO [train.py:812] (7/8) Epoch 26, batch 4200, loss[loss=0.1693, simple_loss=0.2684, pruned_loss=0.03514, over 7088.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2476, pruned_loss=0.03265, over 1419504.77 frames.], batch size: 28, lr: 2.97e-04
+2022-05-15 10:53:19,332 INFO [train.py:812] (7/8) Epoch 26, batch 4250, loss[loss=0.1368, simple_loss=0.2257, pruned_loss=0.02395, over 7157.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2477, pruned_loss=0.03288, over 1419450.36 frames.], batch size: 18, lr: 2.97e-04
+2022-05-15 10:54:17,968 INFO [train.py:812] (7/8) Epoch 26, batch 4300, loss[loss=0.1918, simple_loss=0.2856, pruned_loss=0.04901, over 7165.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2489, pruned_loss=0.03324, over 1423335.33 frames.], batch size: 26, lr: 2.97e-04
+2022-05-15 10:55:15,856 INFO [train.py:812] (7/8) Epoch 26, batch 4350, loss[loss=0.1511, simple_loss=0.2441, pruned_loss=0.02901, over 7239.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2484, pruned_loss=0.03315, over 1415614.41 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:56:15,076 INFO [train.py:812] (7/8) Epoch 26, batch 4400, loss[loss=0.1482, simple_loss=0.2344, pruned_loss=0.03106, over 7074.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2491, pruned_loss=0.03317, over 1414894.55 frames.], batch size: 18, lr: 2.97e-04
+2022-05-15 10:57:23,175 INFO [train.py:812] (7/8) Epoch 26, batch 4450, loss[loss=0.1666, simple_loss=0.261, pruned_loss=0.03606, over 7288.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2489, pruned_loss=0.03322, over 1413647.95 frames.], batch size: 24, lr: 2.97e-04
+2022-05-15 10:58:40,640 INFO [train.py:812] (7/8) Epoch 26, batch 4500, loss[loss=0.1594, simple_loss=0.2463, pruned_loss=0.03623, over 7322.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2494, pruned_loss=0.03349, over 1398768.10 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:59:48,374 INFO [train.py:812] (7/8) Epoch 26, batch 4550, loss[loss=0.1954, simple_loss=0.2717, pruned_loss=0.05952, over 4887.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2497, pruned_loss=0.0338, over 1389118.44 frames.], batch size: 52, lr: 2.97e-04
+2022-05-15 11:01:05,816 INFO [train.py:812] (7/8) Epoch 27, batch 0, loss[loss=0.1484, simple_loss=0.2328, pruned_loss=0.03196, over 7181.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2328, pruned_loss=0.03196, over 7181.00 frames.], batch size: 18, lr: 2.91e-04
+2022-05-15 11:02:14,211 INFO [train.py:812] (7/8) Epoch 27, batch 50, loss[loss=0.1431, simple_loss=0.2247, pruned_loss=0.03072, over 7281.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2464, pruned_loss=0.03204, over 318322.74 frames.], batch size: 17, lr: 2.91e-04
+2022-05-15 11:03:12,412 INFO [train.py:812] (7/8) Epoch 27, batch 100, loss[loss=0.1405, simple_loss=0.2234, pruned_loss=0.02884, over 7274.00 frames.], tot_loss[loss=0.1548, simple_loss=0.246, pruned_loss=0.0318, over 562467.95 frames.], batch size: 17, lr: 2.91e-04
+2022-05-15 11:04:11,571 INFO [train.py:812] (7/8) Epoch 27, batch 150, loss[loss=0.1534, simple_loss=0.2475, pruned_loss=0.02963, over 6491.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2469, pruned_loss=0.03226, over 751142.31 frames.], batch size: 38, lr: 2.91e-04
+2022-05-15 11:05:08,324 INFO [train.py:812] (7/8) Epoch 27, batch 200, loss[loss=0.1759, simple_loss=0.2656, pruned_loss=0.04315, over 7162.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03265, over 894587.02 frames.], batch size: 26, lr: 2.91e-04
+2022-05-15 11:06:06,639 INFO [train.py:812] (7/8) Epoch 27, batch 250, loss[loss=0.1525, simple_loss=0.2474, pruned_loss=0.02876, over 6456.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2477, pruned_loss=0.03247, over 1007667.25 frames.], batch size: 38, lr: 2.91e-04
+2022-05-15 11:07:05,751 INFO [train.py:812] (7/8) Epoch 27, batch 300, loss[loss=0.1753, simple_loss=0.2752, pruned_loss=0.0377, over 6609.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2471, pruned_loss=0.03197, over 1102071.36 frames.], batch size: 38, lr: 2.91e-04
+2022-05-15 11:08:04,247 INFO [train.py:812] (7/8) Epoch 27, batch 350, loss[loss=0.1623, simple_loss=0.2503, pruned_loss=0.03715, over 6742.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2458, pruned_loss=0.03181, over 1169284.06 frames.], batch size: 31, lr: 2.91e-04
+2022-05-15 11:09:03,288 INFO [train.py:812] (7/8) Epoch 27, batch 400, loss[loss=0.1541, simple_loss=0.2468, pruned_loss=0.03071, over 7143.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2457, pruned_loss=0.03151, over 1229005.49 frames.], batch size: 20, lr: 2.91e-04
+2022-05-15 11:10:01,872 INFO [train.py:812] (7/8) Epoch 27, batch 450, loss[loss=0.1479, simple_loss=0.2436, pruned_loss=0.0261, over 7232.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2464, pruned_loss=0.03188, over 1277303.43 frames.], batch size: 20, lr: 2.91e-04
+2022-05-15 11:10:59,691 INFO [train.py:812] (7/8) Epoch 27, batch 500, loss[loss=0.1549, simple_loss=0.2512, pruned_loss=0.02933, over 5522.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2461, pruned_loss=0.03183, over 1309407.35 frames.], batch size: 52, lr: 2.91e-04
+2022-05-15 11:11:59,510 INFO [train.py:812] (7/8) Epoch 27, batch 550, loss[loss=0.1645, simple_loss=0.2514, pruned_loss=0.03884, over 7204.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2464, pruned_loss=0.03222, over 1333505.11 frames.], batch size: 22, lr: 2.90e-04
+2022-05-15 11:12:58,992 INFO [train.py:812] (7/8) Epoch 27, batch 600, loss[loss=0.1369, simple_loss=0.2257, pruned_loss=0.02408, over 7263.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2466, pruned_loss=0.0323, over 1356229.63 frames.], batch size: 19, lr: 2.90e-04
+2022-05-15 11:13:58,673 INFO [train.py:812] (7/8) Epoch 27, batch 650, loss[loss=0.1298, simple_loss=0.2179, pruned_loss=0.02085, over 7286.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2459, pruned_loss=0.03164, over 1372610.83 frames.], batch size: 18, lr: 2.90e-04
+2022-05-15 11:14:57,637 INFO [train.py:812] (7/8) Epoch 27, batch 700, loss[loss=0.1552, simple_loss=0.254, pruned_loss=0.02825, over 7116.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2471, pruned_loss=0.03207, over 1381509.14 frames.], batch size: 21, lr: 2.90e-04
+2022-05-15 11:16:01,110 INFO [train.py:812] (7/8) Epoch 27, batch 750, loss[loss=0.1436, simple_loss=0.2382, pruned_loss=0.02452, over 7155.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2466, pruned_loss=0.03187, over 1389626.62 frames.], batch size: 20, lr: 2.90e-04
+2022-05-15 11:17:00,066 INFO [train.py:812] (7/8) Epoch 27, batch 800, loss[loss=0.1712, simple_loss=0.2703, pruned_loss=0.03606, over 7241.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2468, pruned_loss=0.03196, over 1396260.84 frames.], batch size: 20, lr: 2.90e-04
+2022-05-15 11:17:59,370 INFO [train.py:812] (7/8) Epoch 27, batch 850, loss[loss=0.1957, simple_loss=0.2775, pruned_loss=0.05693, over 5115.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2479, pruned_loss=0.03229, over 1399004.72 frames.], batch size: 52, lr: 2.90e-04
+2022-05-15 11:18:57,723 INFO [train.py:812] (7/8) Epoch 27, batch 900, loss[loss=0.1417, simple_loss=0.2305, pruned_loss=0.02651, over 7403.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2471, pruned_loss=0.03211, over 1408594.14 frames.], batch size: 18, lr: 2.90e-04
+2022-05-15 11:19:56,367 INFO [train.py:812] (7/8) Epoch 27, batch 950, loss[loss=0.1421, simple_loss=0.2297, pruned_loss=0.02719, over 6790.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2476, pruned_loss=0.03207, over 1409453.48 frames.], batch size: 15, lr: 2.90e-04
+2022-05-15 11:20:55,314 INFO [train.py:812] (7/8) Epoch 27, batch 1000, loss[loss=0.1913, simple_loss=0.2864, pruned_loss=0.04809, over 7306.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2484, pruned_loss=0.03253, over 1413269.83 frames.], batch size: 24, lr: 2.90e-04
+2022-05-15 11:21:53,198 INFO [train.py:812] (7/8) Epoch 27, batch 1050, loss[loss=0.1486, simple_loss=0.2432, pruned_loss=0.02703, over 7205.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2477, pruned_loss=0.03221, over 1419048.82 frames.], batch size: 23, lr: 2.90e-04
+2022-05-15 11:22:52,394 INFO [train.py:812] (7/8) Epoch 27, batch 1100, loss[loss=0.1704, simple_loss=0.2643, pruned_loss=0.0383, over 7188.00 frames.], tot_loss[loss=0.1555, simple_loss=0.247, pruned_loss=0.03202, over 1422889.49 frames.], batch size: 22, lr: 2.90e-04
+2022-05-15 11:23:52,091 INFO [train.py:812] (7/8) Epoch 27, batch 1150, loss[loss=0.1493, simple_loss=0.2239, pruned_loss=0.03738, over 7165.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2475, pruned_loss=0.0323, over 1423901.90 frames.], batch size: 19, lr: 2.90e-04
+2022-05-15 11:24:50,290 INFO [train.py:812] (7/8) Epoch 27, batch 1200, loss[loss=0.1486, simple_loss=0.2457, pruned_loss=0.02572, over 7311.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2478, pruned_loss=0.03251, over 1427617.35 frames.], batch size: 24, lr: 2.90e-04
+2022-05-15 11:25:49,818 INFO [train.py:812] (7/8) Epoch 27, batch 1250, loss[loss=0.1439, simple_loss=0.2447, pruned_loss=0.02155, over 6667.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2466, pruned_loss=0.03222, over 1426870.18 frames.], batch size: 38, lr: 2.90e-04
+2022-05-15 11:26:48,378 INFO [train.py:812] (7/8) Epoch 27, batch 1300, loss[loss=0.1257, simple_loss=0.2127, pruned_loss=0.01933, over 7284.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2468, pruned_loss=0.03253, over 1423526.99 frames.], batch size: 18, lr: 2.90e-04
+2022-05-15 11:27:46,520 INFO [train.py:812] (7/8) Epoch 27, batch 1350, loss[loss=0.1317, simple_loss=0.208, pruned_loss=0.02768, over 7416.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2454, pruned_loss=0.03236, over 1426806.63 frames.], batch size: 18, lr: 2.89e-04
+2022-05-15 11:28:44,294 INFO [train.py:812] (7/8) Epoch 27, batch 1400, loss[loss=0.1604, simple_loss=0.2519, pruned_loss=0.03442, over 7199.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2451, pruned_loss=0.032, over 1418999.96 frames.], batch size: 23, lr: 2.89e-04
+2022-05-15 11:29:43,183 INFO [train.py:812] (7/8) Epoch 27, batch 1450, loss[loss=0.1388, simple_loss=0.2301, pruned_loss=0.02375, over 7277.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2462, pruned_loss=0.0327, over 1420863.33 frames.], batch size: 18, lr: 2.89e-04
+2022-05-15 11:30:41,607 INFO [train.py:812] (7/8) Epoch 27, batch 1500, loss[loss=0.1553, simple_loss=0.2487, pruned_loss=0.03098, over 5391.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2456, pruned_loss=0.03212, over 1418329.93 frames.], batch size: 53, lr: 2.89e-04
+2022-05-15 11:31:41,163 INFO [train.py:812] (7/8) Epoch 27, batch 1550, loss[loss=0.1575, simple_loss=0.2578, pruned_loss=0.02854, over 7104.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2458, pruned_loss=0.03237, over 1422457.04 frames.], batch size: 21, lr: 2.89e-04
+2022-05-15 11:32:40,474 INFO [train.py:812] (7/8) Epoch 27, batch 1600, loss[loss=0.1272, simple_loss=0.209, pruned_loss=0.02268, over 7252.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2451, pruned_loss=0.0322, over 1425847.93 frames.], batch size: 19, lr: 2.89e-04
+2022-05-15 11:33:39,643 INFO [train.py:812] (7/8) Epoch 27, batch 1650, loss[loss=0.1583, simple_loss=0.259, pruned_loss=0.02878, over 7155.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2452, pruned_loss=0.03176, over 1429733.69 frames.], batch size: 26, lr: 2.89e-04
+2022-05-15 11:34:38,009 INFO [train.py:812] (7/8) Epoch 27, batch 1700, loss[loss=0.1685, simple_loss=0.2679, pruned_loss=0.03456, over 7327.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2458, pruned_loss=0.03192, over 1431291.13 frames.], batch size: 22, lr: 2.89e-04
+2022-05-15 11:35:35,796 INFO [train.py:812] (7/8) Epoch 27, batch 1750, loss[loss=0.1719, simple_loss=0.2638, pruned_loss=0.03999, over 7133.00 frames.], tot_loss[loss=0.155, simple_loss=0.2458, pruned_loss=0.03206, over 1431536.07 frames.], batch size: 26, lr: 2.89e-04
+2022-05-15 11:36:34,369 INFO [train.py:812] (7/8) Epoch 27, batch 1800, loss[loss=0.1454, simple_loss=0.2496, pruned_loss=0.02055, over 7095.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2467, pruned_loss=0.03257, over 1428836.95 frames.], batch size: 21, lr: 2.89e-04
+2022-05-15 11:37:32,455 INFO [train.py:812] (7/8) Epoch 27, batch 1850, loss[loss=0.2143, simple_loss=0.2843, pruned_loss=0.0722, over 5125.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2474, pruned_loss=0.03279, over 1429574.29 frames.], batch size: 52, lr: 2.89e-04
+2022-05-15 11:38:30,750 INFO [train.py:812] (7/8) Epoch 27, batch 1900, loss[loss=0.1532, simple_loss=0.2377, pruned_loss=0.03436, over 7361.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2465, pruned_loss=0.03245, over 1428878.22 frames.], batch size: 19, lr: 2.89e-04
+2022-05-15 11:39:30,063 INFO [train.py:812] (7/8) Epoch 27, batch 1950, loss[loss=0.1583, simple_loss=0.251, pruned_loss=0.03277, over 6420.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2466, pruned_loss=0.03242, over 1424934.25 frames.], batch size: 38, lr: 2.89e-04
+2022-05-15 11:40:29,370 INFO [train.py:812] (7/8) Epoch 27, batch 2000, loss[loss=0.1804, simple_loss=0.2676, pruned_loss=0.04656, over 6750.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2463, pruned_loss=0.03237, over 1422291.69 frames.], batch size: 31, lr: 2.89e-04
+2022-05-15 11:41:28,640 INFO [train.py:812] (7/8) Epoch 27, batch 2050, loss[loss=0.159, simple_loss=0.2453, pruned_loss=0.03631, over 7105.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2476, pruned_loss=0.03266, over 1426037.78 frames.], batch size: 26, lr: 2.89e-04
+2022-05-15 11:42:27,693 INFO [train.py:812] (7/8) Epoch 27, batch 2100, loss[loss=0.1704, simple_loss=0.2579, pruned_loss=0.04145, over 7204.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2474, pruned_loss=0.03259, over 1424283.05 frames.], batch size: 22, lr: 2.89e-04
+2022-05-15 11:43:25,362 INFO [train.py:812] (7/8) Epoch 27, batch 2150, loss[loss=0.1712, simple_loss=0.2634, pruned_loss=0.03947, over 7293.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2487, pruned_loss=0.03284, over 1427630.27 frames.], batch size: 25, lr: 2.89e-04
+2022-05-15 11:44:23,714 INFO [train.py:812] (7/8) Epoch 27, batch 2200, loss[loss=0.1555, simple_loss=0.2477, pruned_loss=0.03161, over 7228.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2476, pruned_loss=0.03228, over 1426399.09 frames.], batch size: 20, lr: 2.88e-04
+2022-05-15 11:45:23,015 INFO [train.py:812] (7/8) Epoch 27, batch 2250, loss[loss=0.134, simple_loss=0.2201, pruned_loss=0.02402, over 6995.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2479, pruned_loss=0.03237, over 1431508.99 frames.], batch size: 16, lr: 2.88e-04
+2022-05-15 11:46:21,541 INFO [train.py:812] (7/8) Epoch 27, batch 2300, loss[loss=0.1269, simple_loss=0.2139, pruned_loss=0.01999, over 7139.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2477, pruned_loss=0.0321, over 1432851.50 frames.], batch size: 17, lr: 2.88e-04
+2022-05-15 11:47:19,574 INFO [train.py:812] (7/8) Epoch 27, batch 2350, loss[loss=0.1585, simple_loss=0.2633, pruned_loss=0.02691, over 7156.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2486, pruned_loss=0.03257, over 1431485.91 frames.], batch size: 20, lr: 2.88e-04
+2022-05-15 11:48:16,551 INFO [train.py:812] (7/8) Epoch 27, batch 2400, loss[loss=0.1838, simple_loss=0.2765, pruned_loss=0.04561, over 7289.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2489, pruned_loss=0.03275, over 1433428.45 frames.], batch size: 24, lr: 2.88e-04
+2022-05-15 11:49:16,182 INFO [train.py:812] (7/8) Epoch 27, batch 2450, loss[loss=0.1765, simple_loss=0.269, pruned_loss=0.04202, over 7234.00 frames.], tot_loss[loss=0.156, simple_loss=0.2479, pruned_loss=0.03208, over 1435802.50 frames.], batch size: 20, lr: 2.88e-04
+2022-05-15 11:50:15,254 INFO [train.py:812] (7/8) Epoch 27, batch 2500, loss[loss=0.1757, simple_loss=0.2634, pruned_loss=0.044, over 7216.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2474, pruned_loss=0.03188, over 1437397.33 frames.], batch size: 21, lr: 2.88e-04
+2022-05-15 11:51:13,633 INFO [train.py:812] (7/8) Epoch 27, batch 2550, loss[loss=0.1494, simple_loss=0.2357, pruned_loss=0.03153, over 6754.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2463, pruned_loss=0.03122, over 1434447.74 frames.], batch size: 31, lr: 2.88e-04
+2022-05-15 11:52:12,752 INFO [train.py:812] (7/8) Epoch 27, batch 2600, loss[loss=0.1563, simple_loss=0.2436, pruned_loss=0.03452, over 6799.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2473, pruned_loss=0.03189, over 1434050.31 frames.], batch size: 15, lr: 2.88e-04
+2022-05-15 11:53:12,246 INFO [train.py:812] (7/8) Epoch 27, batch 2650, loss[loss=0.1699, simple_loss=0.2553, pruned_loss=0.0423, over 7274.00 frames.], tot_loss[loss=0.1552, simple_loss=0.247, pruned_loss=0.03168, over 1430529.06 frames.], batch size: 24, lr: 2.88e-04
+2022-05-15 11:54:11,615 INFO [train.py:812] (7/8) Epoch 27, batch 2700, loss[loss=0.1613, simple_loss=0.2562, pruned_loss=0.03313, over 7327.00 frames.], tot_loss[loss=0.155, simple_loss=0.247, pruned_loss=0.03154, over 1428137.71 frames.], batch size: 22, lr: 2.88e-04
+2022-05-15 11:55:10,429 INFO [train.py:812] (7/8) Epoch 27, batch 2750, loss[loss=0.133, simple_loss=0.2274, pruned_loss=0.0193, over 7156.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2469, pruned_loss=0.03145, over 1426821.48 frames.], batch size: 19, lr: 2.88e-04
+2022-05-15 11:56:08,602 INFO [train.py:812] (7/8) Epoch 27, batch 2800, loss[loss=0.1784, simple_loss=0.2688, pruned_loss=0.04402, over 7283.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2471, pruned_loss=0.03168, over 1426752.40 frames.], batch size: 25, lr: 2.88e-04
+2022-05-15 11:57:08,035 INFO [train.py:812] (7/8) Epoch 27, batch 2850, loss[loss=0.141, simple_loss=0.234, pruned_loss=0.02398, over 7262.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2471, pruned_loss=0.03161, over 1426899.49 frames.], batch size: 19, lr: 2.88e-04
+2022-05-15 11:58:06,938 INFO [train.py:812] (7/8) Epoch 27, batch 2900, loss[loss=0.1519, simple_loss=0.2318, pruned_loss=0.03602, over 7153.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2463, pruned_loss=0.03148, over 1426284.83 frames.], batch size: 19, lr: 2.88e-04
+2022-05-15 11:59:06,500 INFO [train.py:812] (7/8) Epoch 27, batch 2950, loss[loss=0.1487, simple_loss=0.2496, pruned_loss=0.02388, over 7126.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2472, pruned_loss=0.03199, over 1419436.79 frames.], batch size: 21, lr: 2.88e-04
+2022-05-15 12:00:05,440 INFO [train.py:812] (7/8) Epoch 27, batch 3000, loss[loss=0.1643, simple_loss=0.2634, pruned_loss=0.03259, over 7396.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2477, pruned_loss=0.0322, over 1418860.35 frames.], batch size: 21, lr: 2.88e-04
+2022-05-15 12:00:05,442 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 12:00:12,944 INFO [train.py:841] (7/8) Epoch 27, validation: loss=0.1528, simple_loss=0.25, pruned_loss=0.02785, over 698248.00 frames.
+2022-05-15 12:01:11,848 INFO [train.py:812] (7/8) Epoch 27, batch 3050, loss[loss=0.1736, simple_loss=0.2812, pruned_loss=0.03298, over 7106.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2465, pruned_loss=0.03227, over 1410104.96 frames.], batch size: 21, lr: 2.87e-04
+2022-05-15 12:02:10,787 INFO [train.py:812] (7/8) Epoch 27, batch 3100, loss[loss=0.162, simple_loss=0.2609, pruned_loss=0.03158, over 7334.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2479, pruned_loss=0.03271, over 1415973.44 frames.], batch size: 21, lr: 2.87e-04
+2022-05-15 12:03:20,264 INFO [train.py:812] (7/8) Epoch 27, batch 3150, loss[loss=0.1631, simple_loss=0.2575, pruned_loss=0.03432, over 7199.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2492, pruned_loss=0.03334, over 1416536.92 frames.], batch size: 22, lr: 2.87e-04
+2022-05-15 12:04:19,275 INFO [train.py:812] (7/8) Epoch 27, batch 3200, loss[loss=0.1714, simple_loss=0.2685, pruned_loss=0.03719, over 7223.00 frames.], tot_loss[loss=0.158, simple_loss=0.2494, pruned_loss=0.03332, over 1418628.63 frames.], batch size: 23, lr: 2.87e-04
+2022-05-15 12:05:18,867 INFO [train.py:812] (7/8) Epoch 27, batch 3250, loss[loss=0.1552, simple_loss=0.2519, pruned_loss=0.02923, over 6483.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2486, pruned_loss=0.03316, over 1420092.34 frames.], batch size: 38, lr: 2.87e-04
+2022-05-15 12:06:17,733 INFO [train.py:812] (7/8) Epoch 27, batch 3300, loss[loss=0.1577, simple_loss=0.254, pruned_loss=0.03076, over 6656.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2479, pruned_loss=0.03281, over 1419495.56 frames.], batch size: 31, lr: 2.87e-04
+2022-05-15 12:07:17,066 INFO [train.py:812] (7/8) Epoch 27, batch 3350, loss[loss=0.1509, simple_loss=0.2465, pruned_loss=0.02761, over 7346.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2488, pruned_loss=0.03303, over 1420533.79 frames.], batch size: 22, lr: 2.87e-04
+2022-05-15 12:08:16,189 INFO [train.py:812] (7/8) Epoch 27, batch 3400, loss[loss=0.1634, simple_loss=0.2723, pruned_loss=0.02728, over 7153.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2491, pruned_loss=0.03283, over 1417537.24 frames.], batch size: 20, lr: 2.87e-04
+2022-05-15 12:09:14,998 INFO [train.py:812] (7/8) Epoch 27, batch 3450, loss[loss=0.1783, simple_loss=0.2769, pruned_loss=0.03984, over 7354.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2483, pruned_loss=0.03227, over 1420948.85 frames.], batch size: 22, lr: 2.87e-04
+2022-05-15 12:10:13,351 INFO [train.py:812] (7/8) Epoch 27, batch 3500, loss[loss=0.1525, simple_loss=0.2385, pruned_loss=0.03323, over 6851.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2474, pruned_loss=0.03225, over 1423212.05 frames.], batch size: 15, lr: 2.87e-04
+2022-05-15 12:11:13,094 INFO [train.py:812] (7/8) Epoch 27, batch 3550, loss[loss=0.1711, simple_loss=0.259, pruned_loss=0.04161, over 4819.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2467, pruned_loss=0.03184, over 1416245.98 frames.], batch size: 52, lr: 2.87e-04
+2022-05-15 12:12:10,945 INFO [train.py:812] (7/8) Epoch 27, batch 3600, loss[loss=0.144, simple_loss=0.2369, pruned_loss=0.02556, over 7153.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2463, pruned_loss=0.03166, over 1413831.96 frames.], batch size: 19, lr: 2.87e-04
+2022-05-15 12:13:10,331 INFO [train.py:812] (7/8) Epoch 27, batch 3650, loss[loss=0.1479, simple_loss=0.2432, pruned_loss=0.02632, over 7066.00 frames.], tot_loss[loss=0.155, simple_loss=0.2463, pruned_loss=0.03181, over 1413280.21 frames.], batch size: 18, lr: 2.87e-04
+2022-05-15 12:14:09,342 INFO [train.py:812] (7/8) Epoch 27, batch 3700, loss[loss=0.1328, simple_loss=0.216, pruned_loss=0.02481, over 7272.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2464, pruned_loss=0.03239, over 1412647.85 frames.], batch size: 18, lr: 2.87e-04
+2022-05-15 12:15:08,334 INFO [train.py:812] (7/8) Epoch 27, batch 3750, loss[loss=0.1704, simple_loss=0.272, pruned_loss=0.03436, over 7217.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2456, pruned_loss=0.03239, over 1416379.85 frames.], batch size: 21, lr: 2.87e-04
+2022-05-15 12:16:08,066 INFO [train.py:812] (7/8) Epoch 27, batch 3800, loss[loss=0.1462, simple_loss=0.2376, pruned_loss=0.02738, over 7323.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2444, pruned_loss=0.03195, over 1420369.92 frames.], batch size: 20, lr: 2.87e-04
+2022-05-15 12:17:07,796 INFO [train.py:812] (7/8) Epoch 27, batch 3850, loss[loss=0.1263, simple_loss=0.2064, pruned_loss=0.0231, over 7387.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2462, pruned_loss=0.03226, over 1413399.25 frames.], batch size: 18, lr: 2.87e-04
+2022-05-15 12:18:06,267 INFO [train.py:812] (7/8) Epoch 27, batch 3900, loss[loss=0.186, simple_loss=0.283, pruned_loss=0.04446, over 7051.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2463, pruned_loss=0.03201, over 1415028.20 frames.], batch size: 28, lr: 2.86e-04
+2022-05-15 12:19:04,984 INFO [train.py:812] (7/8) Epoch 27, batch 3950, loss[loss=0.1656, simple_loss=0.2593, pruned_loss=0.03602, over 7368.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2474, pruned_loss=0.03247, over 1419374.56 frames.], batch size: 19, lr: 2.86e-04
+2022-05-15 12:20:04,236 INFO [train.py:812] (7/8) Epoch 27, batch 4000, loss[loss=0.1706, simple_loss=0.266, pruned_loss=0.03756, over 7070.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2468, pruned_loss=0.03214, over 1424554.92 frames.], batch size: 28, lr: 2.86e-04
+2022-05-15 12:21:04,124 INFO [train.py:812] (7/8) Epoch 27, batch 4050, loss[loss=0.1771, simple_loss=0.2627, pruned_loss=0.04579, over 7323.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2469, pruned_loss=0.03204, over 1425731.41 frames.], batch size: 20, lr: 2.86e-04
+2022-05-15 12:22:03,561 INFO [train.py:812] (7/8) Epoch 27, batch 4100, loss[loss=0.1554, simple_loss=0.2523, pruned_loss=0.0292, over 7340.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2463, pruned_loss=0.03193, over 1423644.87 frames.], batch size: 20, lr: 2.86e-04
+2022-05-15 12:23:02,375 INFO [train.py:812] (7/8) Epoch 27, batch 4150, loss[loss=0.1648, simple_loss=0.2614, pruned_loss=0.0341, over 7119.00 frames.], tot_loss[loss=0.1556, simple_loss=0.247, pruned_loss=0.03205, over 1421323.67 frames.], batch size: 21, lr: 2.86e-04
+2022-05-15 12:23:59,515 INFO [train.py:812] (7/8) Epoch 27, batch 4200, loss[loss=0.1703, simple_loss=0.2669, pruned_loss=0.03689, over 7335.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2469, pruned_loss=0.03218, over 1422364.20 frames.], batch size: 22, lr: 2.86e-04
+2022-05-15 12:24:57,523 INFO [train.py:812] (7/8) Epoch 27, batch 4250, loss[loss=0.1596, simple_loss=0.2497, pruned_loss=0.03476, over 7407.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2479, pruned_loss=0.0323, over 1415847.91 frames.], batch size: 21, lr: 2.86e-04
+2022-05-15 12:25:55,531 INFO [train.py:812] (7/8) Epoch 27, batch 4300, loss[loss=0.1913, simple_loss=0.2703, pruned_loss=0.05609, over 6816.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2482, pruned_loss=0.03217, over 1414203.35 frames.], batch size: 31, lr: 2.86e-04
+2022-05-15 12:26:54,788 INFO [train.py:812] (7/8) Epoch 27, batch 4350, loss[loss=0.1354, simple_loss=0.2239, pruned_loss=0.02348, over 6995.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2483, pruned_loss=0.03219, over 1414023.96 frames.], batch size: 16, lr: 2.86e-04
+2022-05-15 12:27:53,359 INFO [train.py:812] (7/8) Epoch 27, batch 4400, loss[loss=0.1532, simple_loss=0.2457, pruned_loss=0.03031, over 6545.00 frames.], tot_loss[loss=0.1566, simple_loss=0.248, pruned_loss=0.03254, over 1401128.19 frames.], batch size: 38, lr: 2.86e-04
+2022-05-15 12:28:51,285 INFO [train.py:812] (7/8) Epoch 27, batch 4450, loss[loss=0.1512, simple_loss=0.2503, pruned_loss=0.02606, over 7338.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2478, pruned_loss=0.03275, over 1395741.36 frames.], batch size: 22, lr: 2.86e-04
+2022-05-15 12:29:50,427 INFO [train.py:812] (7/8) Epoch 27, batch 4500, loss[loss=0.1652, simple_loss=0.2538, pruned_loss=0.03833, over 7162.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2479, pruned_loss=0.03272, over 1387052.82 frames.], batch size: 18, lr: 2.86e-04
+2022-05-15 12:30:49,312 INFO [train.py:812] (7/8) Epoch 27, batch 4550, loss[loss=0.1628, simple_loss=0.2515, pruned_loss=0.0371, over 4960.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2468, pruned_loss=0.03287, over 1369284.58 frames.], batch size: 52, lr: 2.86e-04
+2022-05-15 12:32:00,089 INFO [train.py:812] (7/8) Epoch 28, batch 0, loss[loss=0.1362, simple_loss=0.2258, pruned_loss=0.02327, over 7261.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2258, pruned_loss=0.02327, over 7261.00 frames.], batch size: 19, lr: 2.81e-04
+2022-05-15 12:32:59,378 INFO [train.py:812] (7/8) Epoch 28, batch 50, loss[loss=0.1319, simple_loss=0.2288, pruned_loss=0.01745, over 7261.00 frames.], tot_loss[loss=0.152, simple_loss=0.2437, pruned_loss=0.03017, over 321497.44 frames.], batch size: 19, lr: 2.81e-04
+2022-05-15 12:33:58,556 INFO [train.py:812] (7/8) Epoch 28, batch 100, loss[loss=0.1582, simple_loss=0.2548, pruned_loss=0.03078, over 7141.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2466, pruned_loss=0.0318, over 565928.55 frames.], batch size: 20, lr: 2.80e-04
+2022-05-15 12:35:03,242 INFO [train.py:812] (7/8) Epoch 28, batch 150, loss[loss=0.1517, simple_loss=0.2405, pruned_loss=0.03141, over 6443.00 frames.], tot_loss[loss=0.154, simple_loss=0.2457, pruned_loss=0.03117, over 754916.49 frames.], batch size: 38, lr: 2.80e-04
+2022-05-15 12:36:01,556 INFO [train.py:812] (7/8) Epoch 28, batch 200, loss[loss=0.1559, simple_loss=0.2525, pruned_loss=0.02967, over 7191.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2473, pruned_loss=0.03213, over 900907.51 frames.], batch size: 23, lr: 2.80e-04
+2022-05-15 12:36:59,635 INFO [train.py:812] (7/8) Epoch 28, batch 250, loss[loss=0.1654, simple_loss=0.2553, pruned_loss=0.03777, over 7270.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2472, pruned_loss=0.03177, over 1016580.68 frames.], batch size: 24, lr: 2.80e-04
+2022-05-15 12:37:58,331 INFO [train.py:812] (7/8) Epoch 28, batch 300, loss[loss=0.1499, simple_loss=0.2393, pruned_loss=0.03029, over 6710.00 frames.], tot_loss[loss=0.1549, simple_loss=0.247, pruned_loss=0.03141, over 1106687.70 frames.], batch size: 31, lr: 2.80e-04
+2022-05-15 12:38:57,264 INFO [train.py:812] (7/8) Epoch 28, batch 350, loss[loss=0.1572, simple_loss=0.2511, pruned_loss=0.03162, over 7167.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03136, over 1178609.34 frames.], batch size: 19, lr: 2.80e-04
+2022-05-15 12:39:55,306 INFO [train.py:812] (7/8) Epoch 28, batch 400, loss[loss=0.1676, simple_loss=0.256, pruned_loss=0.03957, over 7138.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2467, pruned_loss=0.03182, over 1234408.20 frames.], batch size: 17, lr: 2.80e-04
+2022-05-15 12:40:54,517 INFO [train.py:812] (7/8) Epoch 28, batch 450, loss[loss=0.1549, simple_loss=0.2535, pruned_loss=0.02814, over 7296.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2469, pruned_loss=0.03188, over 1271137.86 frames.], batch size: 25, lr: 2.80e-04
+2022-05-15 12:41:53,079 INFO [train.py:812] (7/8) Epoch 28, batch 500, loss[loss=0.1469, simple_loss=0.2458, pruned_loss=0.024, over 7311.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2475, pruned_loss=0.03168, over 1308115.39 frames.], batch size: 21, lr: 2.80e-04
+2022-05-15 12:42:52,362 INFO [train.py:812] (7/8) Epoch 28, batch 550, loss[loss=0.1431, simple_loss=0.2318, pruned_loss=0.02722, over 7453.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2469, pruned_loss=0.03167, over 1330933.69 frames.], batch size: 19, lr: 2.80e-04
+2022-05-15 12:43:51,401 INFO [train.py:812] (7/8) Epoch 28, batch 600, loss[loss=0.1488, simple_loss=0.2426, pruned_loss=0.0275, over 7328.00 frames.], tot_loss[loss=0.1546, simple_loss=0.246, pruned_loss=0.0316, over 1348662.70 frames.], batch size: 20, lr: 2.80e-04
+2022-05-15 12:44:49,196 INFO [train.py:812] (7/8) Epoch 28, batch 650, loss[loss=0.1669, simple_loss=0.2613, pruned_loss=0.03624, over 6978.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2467, pruned_loss=0.03177, over 1365718.08 frames.], batch size: 28, lr: 2.80e-04
+2022-05-15 12:45:47,960 INFO [train.py:812] (7/8) Epoch 28, batch 700, loss[loss=0.1439, simple_loss=0.2347, pruned_loss=0.02653, over 7066.00 frames.], tot_loss[loss=0.1543, simple_loss=0.246, pruned_loss=0.03127, over 1379888.55 frames.], batch size: 18, lr: 2.80e-04
+2022-05-15 12:46:48,103 INFO [train.py:812] (7/8) Epoch 28, batch 750, loss[loss=0.178, simple_loss=0.2677, pruned_loss=0.04412, over 7217.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2446, pruned_loss=0.03081, over 1391129.55 frames.], batch size: 21, lr: 2.80e-04
+2022-05-15 12:47:47,191 INFO [train.py:812] (7/8) Epoch 28, batch 800, loss[loss=0.1714, simple_loss=0.2621, pruned_loss=0.04038, over 7119.00 frames.], tot_loss[loss=0.1534, simple_loss=0.245, pruned_loss=0.03096, over 1397994.94 frames.], batch size: 28, lr: 2.80e-04
+2022-05-15 12:48:46,816 INFO [train.py:812] (7/8) Epoch 28, batch 850, loss[loss=0.1583, simple_loss=0.258, pruned_loss=0.02927, over 7317.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2456, pruned_loss=0.03103, over 1405771.08 frames.], batch size: 25, lr: 2.80e-04
+2022-05-15 12:49:45,728 INFO [train.py:812] (7/8) Epoch 28, batch 900, loss[loss=0.1314, simple_loss=0.2196, pruned_loss=0.02164, over 7003.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2464, pruned_loss=0.03137, over 1407698.55 frames.], batch size: 16, lr: 2.80e-04
+2022-05-15 12:50:45,014 INFO [train.py:812] (7/8) Epoch 28, batch 950, loss[loss=0.1425, simple_loss=0.2245, pruned_loss=0.0303, over 7159.00 frames.], tot_loss[loss=0.1552, simple_loss=0.247, pruned_loss=0.03175, over 1409661.06 frames.], batch size: 18, lr: 2.80e-04
+2022-05-15 12:51:43,956 INFO [train.py:812] (7/8) Epoch 28, batch 1000, loss[loss=0.1501, simple_loss=0.2385, pruned_loss=0.03083, over 7419.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2468, pruned_loss=0.0319, over 1415528.47 frames.], batch size: 20, lr: 2.79e-04
+2022-05-15 12:52:42,487 INFO [train.py:812] (7/8) Epoch 28, batch 1050, loss[loss=0.1631, simple_loss=0.2572, pruned_loss=0.03447, over 7416.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2469, pruned_loss=0.03217, over 1415585.38 frames.], batch size: 21, lr: 2.79e-04
+2022-05-15 12:53:50,431 INFO [train.py:812] (7/8) Epoch 28, batch 1100, loss[loss=0.134, simple_loss=0.2348, pruned_loss=0.01659, over 7067.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03227, over 1415521.34 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 12:54:49,780 INFO [train.py:812] (7/8) Epoch 28, batch 1150, loss[loss=0.1658, simple_loss=0.2536, pruned_loss=0.03899, over 7214.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2469, pruned_loss=0.03219, over 1420669.21 frames.], batch size: 23, lr: 2.79e-04
+2022-05-15 12:55:48,188 INFO [train.py:812] (7/8) Epoch 28, batch 1200, loss[loss=0.1385, simple_loss=0.2305, pruned_loss=0.02324, over 7138.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2461, pruned_loss=0.03173, over 1425468.85 frames.], batch size: 17, lr: 2.79e-04
+2022-05-15 12:56:47,584 INFO [train.py:812] (7/8) Epoch 28, batch 1250, loss[loss=0.1181, simple_loss=0.2033, pruned_loss=0.01646, over 7131.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2465, pruned_loss=0.03188, over 1423282.33 frames.], batch size: 17, lr: 2.79e-04
+2022-05-15 12:57:56,228 INFO [train.py:812] (7/8) Epoch 28, batch 1300, loss[loss=0.1361, simple_loss=0.2239, pruned_loss=0.02417, over 7283.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2468, pruned_loss=0.03223, over 1420406.74 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 12:58:55,627 INFO [train.py:812] (7/8) Epoch 28, batch 1350, loss[loss=0.1467, simple_loss=0.2299, pruned_loss=0.0318, over 7357.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2472, pruned_loss=0.03283, over 1419956.32 frames.], batch size: 19, lr: 2.79e-04
+2022-05-15 13:00:02,717 INFO [train.py:812] (7/8) Epoch 28, batch 1400, loss[loss=0.1507, simple_loss=0.239, pruned_loss=0.03123, over 7064.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2469, pruned_loss=0.03266, over 1420155.79 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 13:01:30,497 INFO [train.py:812] (7/8) Epoch 28, batch 1450, loss[loss=0.1599, simple_loss=0.2577, pruned_loss=0.03105, over 7314.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2458, pruned_loss=0.03227, over 1422150.79 frames.], batch size: 20, lr: 2.79e-04
+2022-05-15 13:02:27,781 INFO [train.py:812] (7/8) Epoch 28, batch 1500, loss[loss=0.1766, simple_loss=0.2875, pruned_loss=0.03288, over 7104.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03263, over 1423564.90 frames.], batch size: 21, lr: 2.79e-04
+2022-05-15 13:03:25,153 INFO [train.py:812] (7/8) Epoch 28, batch 1550, loss[loss=0.1508, simple_loss=0.2285, pruned_loss=0.03652, over 6808.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2469, pruned_loss=0.03249, over 1420377.62 frames.], batch size: 15, lr: 2.79e-04
+2022-05-15 13:04:33,697 INFO [train.py:812] (7/8) Epoch 28, batch 1600, loss[loss=0.1554, simple_loss=0.2479, pruned_loss=0.03146, over 7407.00 frames.], tot_loss[loss=0.155, simple_loss=0.2461, pruned_loss=0.03196, over 1424176.27 frames.], batch size: 21, lr: 2.79e-04
+2022-05-15 13:05:32,131 INFO [train.py:812] (7/8) Epoch 28, batch 1650, loss[loss=0.1541, simple_loss=0.2467, pruned_loss=0.03072, over 7059.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2457, pruned_loss=0.03194, over 1424696.03 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 13:06:30,589 INFO [train.py:812] (7/8) Epoch 28, batch 1700, loss[loss=0.1488, simple_loss=0.2404, pruned_loss=0.02867, over 7354.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2471, pruned_loss=0.03229, over 1426512.70 frames.], batch size: 19, lr: 2.79e-04
+2022-05-15 13:07:29,484 INFO [train.py:812] (7/8) Epoch 28, batch 1750, loss[loss=0.1685, simple_loss=0.2575, pruned_loss=0.03968, over 6704.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2467, pruned_loss=0.03212, over 1428147.37 frames.], batch size: 31, lr: 2.79e-04
+2022-05-15 13:08:28,885 INFO [train.py:812] (7/8) Epoch 28, batch 1800, loss[loss=0.1705, simple_loss=0.2656, pruned_loss=0.03771, over 7223.00 frames.], tot_loss[loss=0.1555, simple_loss=0.247, pruned_loss=0.032, over 1427387.37 frames.], batch size: 20, lr: 2.79e-04
+2022-05-15 13:09:27,187 INFO [train.py:812] (7/8) Epoch 28, batch 1850, loss[loss=0.1452, simple_loss=0.2395, pruned_loss=0.02545, over 7164.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2466, pruned_loss=0.03189, over 1430662.90 frames.], batch size: 19, lr: 2.79e-04
+2022-05-15 13:10:26,323 INFO [train.py:812] (7/8) Epoch 28, batch 1900, loss[loss=0.128, simple_loss=0.2119, pruned_loss=0.02206, over 7261.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2474, pruned_loss=0.03202, over 1430499.18 frames.], batch size: 17, lr: 2.78e-04
+2022-05-15 13:11:24,509 INFO [train.py:812] (7/8) Epoch 28, batch 1950, loss[loss=0.1397, simple_loss=0.2306, pruned_loss=0.02443, over 6190.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2475, pruned_loss=0.03238, over 1425274.76 frames.], batch size: 37, lr: 2.78e-04
+2022-05-15 13:12:23,354 INFO [train.py:812] (7/8) Epoch 28, batch 2000, loss[loss=0.1472, simple_loss=0.243, pruned_loss=0.02565, over 7216.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2471, pruned_loss=0.03204, over 1424862.93 frames.], batch size: 21, lr: 2.78e-04
+2022-05-15 13:13:21,549 INFO [train.py:812] (7/8) Epoch 28, batch 2050, loss[loss=0.1892, simple_loss=0.2801, pruned_loss=0.0492, over 7205.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2481, pruned_loss=0.03247, over 1423554.03 frames.], batch size: 23, lr: 2.78e-04
+2022-05-15 13:14:21,014 INFO [train.py:812] (7/8) Epoch 28, batch 2100, loss[loss=0.1648, simple_loss=0.2592, pruned_loss=0.03521, over 7297.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2477, pruned_loss=0.03201, over 1424071.62 frames.], batch size: 25, lr: 2.78e-04
+2022-05-15 13:15:20,672 INFO [train.py:812] (7/8) Epoch 28, batch 2150, loss[loss=0.1471, simple_loss=0.2303, pruned_loss=0.03197, over 7137.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2476, pruned_loss=0.03204, over 1422698.42 frames.], batch size: 17, lr: 2.78e-04
+2022-05-15 13:16:19,090 INFO [train.py:812] (7/8) Epoch 28, batch 2200, loss[loss=0.1844, simple_loss=0.2724, pruned_loss=0.0482, over 7293.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2471, pruned_loss=0.03207, over 1421233.77 frames.], batch size: 24, lr: 2.78e-04
+2022-05-15 13:17:18,188 INFO [train.py:812] (7/8) Epoch 28, batch 2250, loss[loss=0.1466, simple_loss=0.2422, pruned_loss=0.02555, over 7327.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2471, pruned_loss=0.0322, over 1424354.29 frames.], batch size: 22, lr: 2.78e-04
+2022-05-15 13:18:16,771 INFO [train.py:812] (7/8) Epoch 28, batch 2300, loss[loss=0.1626, simple_loss=0.2518, pruned_loss=0.0367, over 7149.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2471, pruned_loss=0.032, over 1421563.18 frames.], batch size: 20, lr: 2.78e-04
+2022-05-15 13:19:16,313 INFO [train.py:812] (7/8) Epoch 28, batch 2350, loss[loss=0.1483, simple_loss=0.2399, pruned_loss=0.02839, over 7158.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2468, pruned_loss=0.03205, over 1419804.60 frames.], batch size: 19, lr: 2.78e-04
+2022-05-15 13:20:14,245 INFO [train.py:812] (7/8) Epoch 28, batch 2400, loss[loss=0.1724, simple_loss=0.2639, pruned_loss=0.04042, over 7211.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2473, pruned_loss=0.03213, over 1423043.20 frames.], batch size: 23, lr: 2.78e-04
+2022-05-15 13:21:14,096 INFO [train.py:812] (7/8) Epoch 28, batch 2450, loss[loss=0.1696, simple_loss=0.2656, pruned_loss=0.03678, over 6392.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.0314, over 1423745.62 frames.], batch size: 37, lr: 2.78e-04
+2022-05-15 13:22:13,020 INFO [train.py:812] (7/8) Epoch 28, batch 2500, loss[loss=0.1495, simple_loss=0.2289, pruned_loss=0.03502, over 6828.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2457, pruned_loss=0.03167, over 1420922.97 frames.], batch size: 15, lr: 2.78e-04
+2022-05-15 13:23:12,426 INFO [train.py:812] (7/8) Epoch 28, batch 2550, loss[loss=0.1652, simple_loss=0.2567, pruned_loss=0.03682, over 7247.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2462, pruned_loss=0.0315, over 1421525.18 frames.], batch size: 19, lr: 2.78e-04
+2022-05-15 13:24:10,683 INFO [train.py:812] (7/8) Epoch 28, batch 2600, loss[loss=0.1495, simple_loss=0.2396, pruned_loss=0.02973, over 7239.00 frames.], tot_loss[loss=0.1544, simple_loss=0.246, pruned_loss=0.03143, over 1421787.53 frames.], batch size: 20, lr: 2.78e-04
+2022-05-15 13:25:09,898 INFO [train.py:812] (7/8) Epoch 28, batch 2650, loss[loss=0.1355, simple_loss=0.2279, pruned_loss=0.02158, over 6998.00 frames.], tot_loss[loss=0.1542, simple_loss=0.246, pruned_loss=0.03115, over 1420316.70 frames.], batch size: 16, lr: 2.78e-04
+2022-05-15 13:26:08,954 INFO [train.py:812] (7/8) Epoch 28, batch 2700, loss[loss=0.1504, simple_loss=0.2519, pruned_loss=0.02448, over 7313.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2463, pruned_loss=0.031, over 1422425.14 frames.], batch size: 21, lr: 2.78e-04
+2022-05-15 13:27:07,553 INFO [train.py:812] (7/8) Epoch 28, batch 2750, loss[loss=0.1383, simple_loss=0.2261, pruned_loss=0.02523, over 7253.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2473, pruned_loss=0.0316, over 1420732.99 frames.], batch size: 19, lr: 2.78e-04
+2022-05-15 13:28:05,921 INFO [train.py:812] (7/8) Epoch 28, batch 2800, loss[loss=0.175, simple_loss=0.2691, pruned_loss=0.04045, over 7236.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2473, pruned_loss=0.03172, over 1416645.31 frames.], batch size: 20, lr: 2.77e-04
+2022-05-15 13:29:05,103 INFO [train.py:812] (7/8) Epoch 28, batch 2850, loss[loss=0.1467, simple_loss=0.2222, pruned_loss=0.03566, over 7143.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2463, pruned_loss=0.0317, over 1420460.67 frames.], batch size: 17, lr: 2.77e-04
+2022-05-15 13:30:03,024 INFO [train.py:812] (7/8) Epoch 28, batch 2900, loss[loss=0.1561, simple_loss=0.2575, pruned_loss=0.02733, over 7286.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2468, pruned_loss=0.03125, over 1419913.40 frames.], batch size: 25, lr: 2.77e-04
+2022-05-15 13:31:01,419 INFO [train.py:812] (7/8) Epoch 28, batch 2950, loss[loss=0.1483, simple_loss=0.2471, pruned_loss=0.02475, over 7213.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2473, pruned_loss=0.03143, over 1423051.53 frames.], batch size: 23, lr: 2.77e-04
+2022-05-15 13:32:00,631 INFO [train.py:812] (7/8) Epoch 28, batch 3000, loss[loss=0.171, simple_loss=0.2656, pruned_loss=0.03819, over 7078.00 frames.], tot_loss[loss=0.155, simple_loss=0.2473, pruned_loss=0.03141, over 1424725.80 frames.], batch size: 28, lr: 2.77e-04
+2022-05-15 13:32:00,633 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 13:32:08,091 INFO [train.py:841] (7/8) Epoch 28, validation: loss=0.1523, simple_loss=0.2496, pruned_loss=0.02748, over 698248.00 frames.
+2022-05-15 13:33:05,930 INFO [train.py:812] (7/8) Epoch 28, batch 3050, loss[loss=0.1393, simple_loss=0.2198, pruned_loss=0.02938, over 7153.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2473, pruned_loss=0.03161, over 1426235.06 frames.], batch size: 17, lr: 2.77e-04
+2022-05-15 13:34:04,057 INFO [train.py:812] (7/8) Epoch 28, batch 3100, loss[loss=0.1563, simple_loss=0.246, pruned_loss=0.03332, over 7380.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2467, pruned_loss=0.03161, over 1424937.01 frames.], batch size: 23, lr: 2.77e-04
+2022-05-15 13:35:03,629 INFO [train.py:812] (7/8) Epoch 28, batch 3150, loss[loss=0.1476, simple_loss=0.2288, pruned_loss=0.03322, over 7417.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2463, pruned_loss=0.03154, over 1423304.68 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:36:02,646 INFO [train.py:812] (7/8) Epoch 28, batch 3200, loss[loss=0.1428, simple_loss=0.2372, pruned_loss=0.02413, over 7317.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2474, pruned_loss=0.03182, over 1423958.74 frames.], batch size: 21, lr: 2.77e-04
+2022-05-15 13:37:02,660 INFO [train.py:812] (7/8) Epoch 28, batch 3250, loss[loss=0.1371, simple_loss=0.2238, pruned_loss=0.02523, over 7170.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2469, pruned_loss=0.03181, over 1423407.42 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:37:59,667 INFO [train.py:812] (7/8) Epoch 28, batch 3300, loss[loss=0.1484, simple_loss=0.2239, pruned_loss=0.03649, over 6983.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2469, pruned_loss=0.03213, over 1422338.53 frames.], batch size: 16, lr: 2.77e-04
+2022-05-15 13:38:57,875 INFO [train.py:812] (7/8) Epoch 28, batch 3350, loss[loss=0.1491, simple_loss=0.2514, pruned_loss=0.02344, over 7389.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03222, over 1419217.23 frames.], batch size: 23, lr: 2.77e-04
+2022-05-15 13:39:56,949 INFO [train.py:812] (7/8) Epoch 28, batch 3400, loss[loss=0.135, simple_loss=0.2402, pruned_loss=0.01487, over 7320.00 frames.], tot_loss[loss=0.1563, simple_loss=0.248, pruned_loss=0.03233, over 1421642.77 frames.], batch size: 20, lr: 2.77e-04
+2022-05-15 13:40:56,442 INFO [train.py:812] (7/8) Epoch 28, batch 3450, loss[loss=0.1579, simple_loss=0.2525, pruned_loss=0.03162, over 7204.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2473, pruned_loss=0.03198, over 1423085.88 frames.], batch size: 22, lr: 2.77e-04
+2022-05-15 13:41:55,476 INFO [train.py:812] (7/8) Epoch 28, batch 3500, loss[loss=0.1426, simple_loss=0.2354, pruned_loss=0.02487, over 7061.00 frames.], tot_loss[loss=0.155, simple_loss=0.2466, pruned_loss=0.03168, over 1422036.35 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:42:54,619 INFO [train.py:812] (7/8) Epoch 28, batch 3550, loss[loss=0.1597, simple_loss=0.2521, pruned_loss=0.03362, over 7342.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2463, pruned_loss=0.03139, over 1422603.59 frames.], batch size: 22, lr: 2.77e-04
+2022-05-15 13:43:53,664 INFO [train.py:812] (7/8) Epoch 28, batch 3600, loss[loss=0.1485, simple_loss=0.2417, pruned_loss=0.02763, over 7077.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2462, pruned_loss=0.03097, over 1421673.58 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:44:53,088 INFO [train.py:812] (7/8) Epoch 28, batch 3650, loss[loss=0.1643, simple_loss=0.2587, pruned_loss=0.03496, over 7411.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2455, pruned_loss=0.03099, over 1423113.43 frames.], batch size: 21, lr: 2.77e-04
+2022-05-15 13:45:51,499 INFO [train.py:812] (7/8) Epoch 28, batch 3700, loss[loss=0.1394, simple_loss=0.2321, pruned_loss=0.02337, over 7436.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2453, pruned_loss=0.0308, over 1423305.72 frames.], batch size: 20, lr: 2.77e-04
+2022-05-15 13:46:50,221 INFO [train.py:812] (7/8) Epoch 28, batch 3750, loss[loss=0.1602, simple_loss=0.2588, pruned_loss=0.03077, over 4898.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03085, over 1418954.41 frames.], batch size: 53, lr: 2.76e-04
+2022-05-15 13:47:49,339 INFO [train.py:812] (7/8) Epoch 28, batch 3800, loss[loss=0.1225, simple_loss=0.2079, pruned_loss=0.01857, over 7284.00 frames.], tot_loss[loss=0.1531, simple_loss=0.245, pruned_loss=0.03064, over 1421182.79 frames.], batch size: 17, lr: 2.76e-04
+2022-05-15 13:48:48,437 INFO [train.py:812] (7/8) Epoch 28, batch 3850, loss[loss=0.1485, simple_loss=0.2508, pruned_loss=0.02309, over 7152.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2454, pruned_loss=0.03059, over 1425561.76 frames.], batch size: 19, lr: 2.76e-04
+2022-05-15 13:49:47,475 INFO [train.py:812] (7/8) Epoch 28, batch 3900, loss[loss=0.1728, simple_loss=0.2687, pruned_loss=0.03845, over 7212.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2462, pruned_loss=0.0308, over 1424605.07 frames.], batch size: 22, lr: 2.76e-04
+2022-05-15 13:50:47,250 INFO [train.py:812] (7/8) Epoch 28, batch 3950, loss[loss=0.1553, simple_loss=0.2485, pruned_loss=0.03106, over 7211.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2453, pruned_loss=0.03064, over 1425775.05 frames.], batch size: 22, lr: 2.76e-04
+2022-05-15 13:51:46,184 INFO [train.py:812] (7/8) Epoch 28, batch 4000, loss[loss=0.1559, simple_loss=0.2546, pruned_loss=0.0286, over 6700.00 frames.], tot_loss[loss=0.1525, simple_loss=0.244, pruned_loss=0.03049, over 1423926.26 frames.], batch size: 31, lr: 2.76e-04
+2022-05-15 13:52:45,740 INFO [train.py:812] (7/8) Epoch 28, batch 4050, loss[loss=0.1844, simple_loss=0.2659, pruned_loss=0.05147, over 5098.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2453, pruned_loss=0.03103, over 1416625.78 frames.], batch size: 53, lr: 2.76e-04
+2022-05-15 13:53:44,824 INFO [train.py:812] (7/8) Epoch 28, batch 4100, loss[loss=0.1406, simple_loss=0.2195, pruned_loss=0.03087, over 7134.00 frames.], tot_loss[loss=0.154, simple_loss=0.2452, pruned_loss=0.03142, over 1418958.04 frames.], batch size: 17, lr: 2.76e-04
+2022-05-15 13:54:49,296 INFO [train.py:812] (7/8) Epoch 28, batch 4150, loss[loss=0.1492, simple_loss=0.2432, pruned_loss=0.02756, over 7159.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2461, pruned_loss=0.03159, over 1424216.14 frames.], batch size: 19, lr: 2.76e-04
+2022-05-15 13:55:47,983 INFO [train.py:812] (7/8) Epoch 28, batch 4200, loss[loss=0.1881, simple_loss=0.2796, pruned_loss=0.04833, over 5163.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2472, pruned_loss=0.03225, over 1418030.72 frames.], batch size: 54, lr: 2.76e-04
+2022-05-15 13:56:46,309 INFO [train.py:812] (7/8) Epoch 28, batch 4250, loss[loss=0.1363, simple_loss=0.2265, pruned_loss=0.02305, over 7078.00 frames.], tot_loss[loss=0.1553, simple_loss=0.247, pruned_loss=0.03178, over 1415412.44 frames.], batch size: 18, lr: 2.76e-04
+2022-05-15 13:57:45,200 INFO [train.py:812] (7/8) Epoch 28, batch 4300, loss[loss=0.1461, simple_loss=0.2272, pruned_loss=0.0325, over 7130.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2462, pruned_loss=0.03157, over 1416966.33 frames.], batch size: 17, lr: 2.76e-04
+2022-05-15 13:58:44,160 INFO [train.py:812] (7/8) Epoch 28, batch 4350, loss[loss=0.1491, simple_loss=0.2436, pruned_loss=0.02723, over 7227.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2467, pruned_loss=0.03174, over 1416797.33 frames.], batch size: 21, lr: 2.76e-04
+2022-05-15 13:59:42,379 INFO [train.py:812] (7/8) Epoch 28, batch 4400, loss[loss=0.1596, simple_loss=0.2556, pruned_loss=0.03183, over 6583.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2469, pruned_loss=0.03171, over 1409612.58 frames.], batch size: 38, lr: 2.76e-04
+2022-05-15 14:00:51,469 INFO [train.py:812] (7/8) Epoch 28, batch 4450, loss[loss=0.121, simple_loss=0.2129, pruned_loss=0.0146, over 7207.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2472, pruned_loss=0.03222, over 1403536.39 frames.], batch size: 16, lr: 2.76e-04
+2022-05-15 14:01:50,429 INFO [train.py:812] (7/8) Epoch 28, batch 4500, loss[loss=0.1505, simple_loss=0.2487, pruned_loss=0.02612, over 7215.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2475, pruned_loss=0.03231, over 1391385.70 frames.], batch size: 21, lr: 2.76e-04
+2022-05-15 14:02:49,671 INFO [train.py:812] (7/8) Epoch 28, batch 4550, loss[loss=0.1567, simple_loss=0.2604, pruned_loss=0.02648, over 6475.00 frames.], tot_loss[loss=0.1568, simple_loss=0.248, pruned_loss=0.03283, over 1359555.10 frames.], batch size: 38, lr: 2.76e-04
+2022-05-15 14:04:01,565 INFO [train.py:812] (7/8) Epoch 29, batch 0, loss[loss=0.1477, simple_loss=0.2463, pruned_loss=0.02454, over 7084.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2463, pruned_loss=0.02454, over 7084.00 frames.], batch size: 28, lr: 2.71e-04
+2022-05-15 14:05:00,872 INFO [train.py:812] (7/8) Epoch 29, batch 50, loss[loss=0.1506, simple_loss=0.2399, pruned_loss=0.03066, over 7303.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2482, pruned_loss=0.03113, over 323714.01 frames.], batch size: 24, lr: 2.71e-04
+2022-05-15 14:05:59,938 INFO [train.py:812] (7/8) Epoch 29, batch 100, loss[loss=0.2016, simple_loss=0.296, pruned_loss=0.05355, over 7320.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2472, pruned_loss=0.03251, over 570024.06 frames.], batch size: 21, lr: 2.71e-04
+2022-05-15 14:06:58,576 INFO [train.py:812] (7/8) Epoch 29, batch 150, loss[loss=0.1462, simple_loss=0.2471, pruned_loss=0.0226, over 7238.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2478, pruned_loss=0.03197, over 760002.67 frames.], batch size: 20, lr: 2.71e-04
+2022-05-15 14:07:56,851 INFO [train.py:812] (7/8) Epoch 29, batch 200, loss[loss=0.154, simple_loss=0.237, pruned_loss=0.03554, over 7061.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2459, pruned_loss=0.03116, over 908907.92 frames.], batch size: 18, lr: 2.71e-04
+2022-05-15 14:08:56,111 INFO [train.py:812] (7/8) Epoch 29, batch 250, loss[loss=0.1737, simple_loss=0.2522, pruned_loss=0.04761, over 5331.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2447, pruned_loss=0.03041, over 1020292.13 frames.], batch size: 53, lr: 2.71e-04
+2022-05-15 14:09:54,931 INFO [train.py:812] (7/8) Epoch 29, batch 300, loss[loss=0.1626, simple_loss=0.2464, pruned_loss=0.03941, over 7175.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2457, pruned_loss=0.0309, over 1109839.70 frames.], batch size: 18, lr: 2.70e-04
+2022-05-15 14:10:53,127 INFO [train.py:812] (7/8) Epoch 29, batch 350, loss[loss=0.1415, simple_loss=0.2281, pruned_loss=0.02747, over 7058.00 frames.], tot_loss[loss=0.1537, simple_loss=0.246, pruned_loss=0.03067, over 1181426.88 frames.], batch size: 18, lr: 2.70e-04
+2022-05-15 14:11:51,426 INFO [train.py:812] (7/8) Epoch 29, batch 400, loss[loss=0.1481, simple_loss=0.2491, pruned_loss=0.02351, over 7151.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2453, pruned_loss=0.03049, over 1236691.09 frames.], batch size: 20, lr: 2.70e-04
+2022-05-15 14:12:49,846 INFO [train.py:812] (7/8) Epoch 29, batch 450, loss[loss=0.1527, simple_loss=0.2566, pruned_loss=0.02442, over 7120.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2451, pruned_loss=0.03076, over 1282496.90 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:13:47,262 INFO [train.py:812] (7/8) Epoch 29, batch 500, loss[loss=0.1871, simple_loss=0.2823, pruned_loss=0.04599, over 4957.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2456, pruned_loss=0.03075, over 1309613.48 frames.], batch size: 52, lr: 2.70e-04
+2022-05-15 14:14:46,086 INFO [train.py:812] (7/8) Epoch 29, batch 550, loss[loss=0.1633, simple_loss=0.2619, pruned_loss=0.03239, over 7230.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2452, pruned_loss=0.03067, over 1332039.04 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:15:44,291 INFO [train.py:812] (7/8) Epoch 29, batch 600, loss[loss=0.1382, simple_loss=0.2344, pruned_loss=0.02096, over 7244.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2446, pruned_loss=0.03059, over 1348671.29 frames.], batch size: 19, lr: 2.70e-04
+2022-05-15 14:16:43,612 INFO [train.py:812] (7/8) Epoch 29, batch 650, loss[loss=0.1332, simple_loss=0.2185, pruned_loss=0.02392, over 7069.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.03025, over 1366852.17 frames.], batch size: 18, lr: 2.70e-04
+2022-05-15 14:17:43,417 INFO [train.py:812] (7/8) Epoch 29, batch 700, loss[loss=0.1912, simple_loss=0.2698, pruned_loss=0.05635, over 4881.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2446, pruned_loss=0.03092, over 1375414.34 frames.], batch size: 54, lr: 2.70e-04
+2022-05-15 14:18:41,568 INFO [train.py:812] (7/8) Epoch 29, batch 750, loss[loss=0.1608, simple_loss=0.2535, pruned_loss=0.03404, over 7420.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2447, pruned_loss=0.03094, over 1382189.01 frames.], batch size: 20, lr: 2.70e-04
+2022-05-15 14:19:40,285 INFO [train.py:812] (7/8) Epoch 29, batch 800, loss[loss=0.1648, simple_loss=0.2641, pruned_loss=0.03276, over 7115.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2453, pruned_loss=0.03103, over 1388119.46 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:20:39,311 INFO [train.py:812] (7/8) Epoch 29, batch 850, loss[loss=0.1604, simple_loss=0.2509, pruned_loss=0.03491, over 6512.00 frames.], tot_loss[loss=0.154, simple_loss=0.2456, pruned_loss=0.03121, over 1393075.27 frames.], batch size: 38, lr: 2.70e-04
+2022-05-15 14:21:38,062 INFO [train.py:812] (7/8) Epoch 29, batch 900, loss[loss=0.163, simple_loss=0.2582, pruned_loss=0.03391, over 6953.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2456, pruned_loss=0.03111, over 1399885.60 frames.], batch size: 32, lr: 2.70e-04
+2022-05-15 14:22:37,116 INFO [train.py:812] (7/8) Epoch 29, batch 950, loss[loss=0.1606, simple_loss=0.2477, pruned_loss=0.03672, over 7203.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2451, pruned_loss=0.03102, over 1409195.20 frames.], batch size: 22, lr: 2.70e-04
+2022-05-15 14:23:36,656 INFO [train.py:812] (7/8) Epoch 29, batch 1000, loss[loss=0.1437, simple_loss=0.2308, pruned_loss=0.02832, over 6853.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2443, pruned_loss=0.03091, over 1415609.13 frames.], batch size: 15, lr: 2.70e-04
+2022-05-15 14:24:36,137 INFO [train.py:812] (7/8) Epoch 29, batch 1050, loss[loss=0.139, simple_loss=0.2329, pruned_loss=0.02252, over 7413.00 frames.], tot_loss[loss=0.153, simple_loss=0.2445, pruned_loss=0.03071, over 1420937.41 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:25:35,423 INFO [train.py:812] (7/8) Epoch 29, batch 1100, loss[loss=0.1445, simple_loss=0.2233, pruned_loss=0.03286, over 7286.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2442, pruned_loss=0.03074, over 1423866.95 frames.], batch size: 17, lr: 2.70e-04
+2022-05-15 14:26:34,894 INFO [train.py:812] (7/8) Epoch 29, batch 1150, loss[loss=0.1675, simple_loss=0.2611, pruned_loss=0.03698, over 7079.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2449, pruned_loss=0.0311, over 1422685.48 frames.], batch size: 28, lr: 2.70e-04
+2022-05-15 14:27:33,685 INFO [train.py:812] (7/8) Epoch 29, batch 1200, loss[loss=0.1559, simple_loss=0.251, pruned_loss=0.03041, over 6991.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2458, pruned_loss=0.03132, over 1424413.70 frames.], batch size: 28, lr: 2.70e-04
+2022-05-15 14:28:32,497 INFO [train.py:812] (7/8) Epoch 29, batch 1250, loss[loss=0.1825, simple_loss=0.2747, pruned_loss=0.04515, over 7210.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2452, pruned_loss=0.03148, over 1417757.84 frames.], batch size: 22, lr: 2.70e-04
+2022-05-15 14:29:29,518 INFO [train.py:812] (7/8) Epoch 29, batch 1300, loss[loss=0.1492, simple_loss=0.2404, pruned_loss=0.02904, over 7155.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2445, pruned_loss=0.03132, over 1420907.58 frames.], batch size: 20, lr: 2.69e-04
+2022-05-15 14:30:28,435 INFO [train.py:812] (7/8) Epoch 29, batch 1350, loss[loss=0.1672, simple_loss=0.2701, pruned_loss=0.03213, over 7114.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2436, pruned_loss=0.03065, over 1426084.30 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:31:27,379 INFO [train.py:812] (7/8) Epoch 29, batch 1400, loss[loss=0.1421, simple_loss=0.2232, pruned_loss=0.03048, over 7258.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2442, pruned_loss=0.03077, over 1427727.46 frames.], batch size: 17, lr: 2.69e-04
+2022-05-15 14:32:26,356 INFO [train.py:812] (7/8) Epoch 29, batch 1450, loss[loss=0.1721, simple_loss=0.2634, pruned_loss=0.04036, over 7296.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2444, pruned_loss=0.03096, over 1431821.64 frames.], batch size: 24, lr: 2.69e-04
+2022-05-15 14:33:24,408 INFO [train.py:812] (7/8) Epoch 29, batch 1500, loss[loss=0.14, simple_loss=0.2305, pruned_loss=0.02473, over 7331.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2449, pruned_loss=0.03129, over 1428159.90 frames.], batch size: 20, lr: 2.69e-04
+2022-05-15 14:34:23,862 INFO [train.py:812] (7/8) Epoch 29, batch 1550, loss[loss=0.1742, simple_loss=0.2774, pruned_loss=0.03556, over 7222.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2453, pruned_loss=0.0313, over 1430256.41 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:35:22,654 INFO [train.py:812] (7/8) Epoch 29, batch 1600, loss[loss=0.138, simple_loss=0.2211, pruned_loss=0.02745, over 6880.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03136, over 1426339.43 frames.], batch size: 15, lr: 2.69e-04
+2022-05-15 14:36:22,737 INFO [train.py:812] (7/8) Epoch 29, batch 1650, loss[loss=0.1515, simple_loss=0.2339, pruned_loss=0.03456, over 6769.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2455, pruned_loss=0.03109, over 1428290.93 frames.], batch size: 15, lr: 2.69e-04
+2022-05-15 14:37:22,122 INFO [train.py:812] (7/8) Epoch 29, batch 1700, loss[loss=0.1256, simple_loss=0.2101, pruned_loss=0.0205, over 7262.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2449, pruned_loss=0.03099, over 1430648.74 frames.], batch size: 19, lr: 2.69e-04
+2022-05-15 14:38:21,747 INFO [train.py:812] (7/8) Epoch 29, batch 1750, loss[loss=0.1323, simple_loss=0.2262, pruned_loss=0.01925, over 7114.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2444, pruned_loss=0.03068, over 1432985.28 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:39:20,845 INFO [train.py:812] (7/8) Epoch 29, batch 1800, loss[loss=0.1418, simple_loss=0.2237, pruned_loss=0.03, over 6992.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2439, pruned_loss=0.03076, over 1422592.01 frames.], batch size: 16, lr: 2.69e-04
+2022-05-15 14:40:20,289 INFO [train.py:812] (7/8) Epoch 29, batch 1850, loss[loss=0.1395, simple_loss=0.2314, pruned_loss=0.02382, over 7400.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2453, pruned_loss=0.03111, over 1425155.20 frames.], batch size: 18, lr: 2.69e-04
+2022-05-15 14:41:18,739 INFO [train.py:812] (7/8) Epoch 29, batch 1900, loss[loss=0.1409, simple_loss=0.2338, pruned_loss=0.02402, over 7152.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2448, pruned_loss=0.03097, over 1425556.62 frames.], batch size: 26, lr: 2.69e-04
+2022-05-15 14:42:17,759 INFO [train.py:812] (7/8) Epoch 29, batch 1950, loss[loss=0.1927, simple_loss=0.2847, pruned_loss=0.05033, over 7298.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.0308, over 1427996.32 frames.], batch size: 25, lr: 2.69e-04
+2022-05-15 14:43:16,673 INFO [train.py:812] (7/8) Epoch 29, batch 2000, loss[loss=0.1708, simple_loss=0.2649, pruned_loss=0.03837, over 7198.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2445, pruned_loss=0.03087, over 1430472.06 frames.], batch size: 23, lr: 2.69e-04
+2022-05-15 14:44:14,160 INFO [train.py:812] (7/8) Epoch 29, batch 2050, loss[loss=0.1536, simple_loss=0.2509, pruned_loss=0.02814, over 7322.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2449, pruned_loss=0.03111, over 1424351.25 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:45:12,015 INFO [train.py:812] (7/8) Epoch 29, batch 2100, loss[loss=0.1617, simple_loss=0.2634, pruned_loss=0.02994, over 7318.00 frames.], tot_loss[loss=0.153, simple_loss=0.2443, pruned_loss=0.03084, over 1426390.07 frames.], batch size: 25, lr: 2.69e-04
+2022-05-15 14:46:11,712 INFO [train.py:812] (7/8) Epoch 29, batch 2150, loss[loss=0.1448, simple_loss=0.2514, pruned_loss=0.01908, over 7210.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2443, pruned_loss=0.03033, over 1427966.12 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:47:09,943 INFO [train.py:812] (7/8) Epoch 29, batch 2200, loss[loss=0.1455, simple_loss=0.2419, pruned_loss=0.02454, over 7278.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2446, pruned_loss=0.03063, over 1422024.06 frames.], batch size: 25, lr: 2.69e-04
+2022-05-15 14:48:08,327 INFO [train.py:812] (7/8) Epoch 29, batch 2250, loss[loss=0.1503, simple_loss=0.2527, pruned_loss=0.024, over 7111.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2451, pruned_loss=0.03078, over 1426353.91 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 14:49:05,773 INFO [train.py:812] (7/8) Epoch 29, batch 2300, loss[loss=0.1724, simple_loss=0.2678, pruned_loss=0.03852, over 7278.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2453, pruned_loss=0.03094, over 1427300.85 frames.], batch size: 24, lr: 2.68e-04
+2022-05-15 14:50:03,899 INFO [train.py:812] (7/8) Epoch 29, batch 2350, loss[loss=0.1372, simple_loss=0.2267, pruned_loss=0.02387, over 7069.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.03079, over 1424860.66 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:51:02,225 INFO [train.py:812] (7/8) Epoch 29, batch 2400, loss[loss=0.14, simple_loss=0.2353, pruned_loss=0.02231, over 7350.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2446, pruned_loss=0.03052, over 1425620.97 frames.], batch size: 19, lr: 2.68e-04
+2022-05-15 14:51:59,594 INFO [train.py:812] (7/8) Epoch 29, batch 2450, loss[loss=0.1574, simple_loss=0.2494, pruned_loss=0.03265, over 7119.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2459, pruned_loss=0.03143, over 1415902.78 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 14:52:57,625 INFO [train.py:812] (7/8) Epoch 29, batch 2500, loss[loss=0.1253, simple_loss=0.2089, pruned_loss=0.02083, over 7404.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2442, pruned_loss=0.03047, over 1419252.37 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:53:56,713 INFO [train.py:812] (7/8) Epoch 29, batch 2550, loss[loss=0.1543, simple_loss=0.2395, pruned_loss=0.03457, over 7173.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03086, over 1416864.00 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:54:55,332 INFO [train.py:812] (7/8) Epoch 29, batch 2600, loss[loss=0.166, simple_loss=0.2616, pruned_loss=0.0352, over 7204.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2449, pruned_loss=0.03114, over 1415028.79 frames.], batch size: 23, lr: 2.68e-04
+2022-05-15 14:56:04,304 INFO [train.py:812] (7/8) Epoch 29, batch 2650, loss[loss=0.1418, simple_loss=0.2286, pruned_loss=0.02751, over 7404.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2452, pruned_loss=0.03121, over 1418386.34 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:57:02,569 INFO [train.py:812] (7/8) Epoch 29, batch 2700, loss[loss=0.1678, simple_loss=0.2557, pruned_loss=0.03998, over 4944.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2443, pruned_loss=0.03104, over 1419044.84 frames.], batch size: 52, lr: 2.68e-04
+2022-05-15 14:58:00,046 INFO [train.py:812] (7/8) Epoch 29, batch 2750, loss[loss=0.1567, simple_loss=0.2524, pruned_loss=0.03055, over 7307.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2452, pruned_loss=0.03132, over 1415527.98 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 14:59:07,992 INFO [train.py:812] (7/8) Epoch 29, batch 2800, loss[loss=0.1394, simple_loss=0.2409, pruned_loss=0.01898, over 7350.00 frames.], tot_loss[loss=0.1534, simple_loss=0.245, pruned_loss=0.03091, over 1418178.29 frames.], batch size: 22, lr: 2.68e-04
+2022-05-15 15:00:06,429 INFO [train.py:812] (7/8) Epoch 29, batch 2850, loss[loss=0.1417, simple_loss=0.2377, pruned_loss=0.02278, over 7256.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2447, pruned_loss=0.03105, over 1418809.86 frames.], batch size: 19, lr: 2.68e-04
+2022-05-15 15:01:14,271 INFO [train.py:812] (7/8) Epoch 29, batch 2900, loss[loss=0.147, simple_loss=0.2261, pruned_loss=0.03398, over 7288.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2444, pruned_loss=0.03106, over 1418229.84 frames.], batch size: 17, lr: 2.68e-04
+2022-05-15 15:02:42,679 INFO [train.py:812] (7/8) Epoch 29, batch 2950, loss[loss=0.1204, simple_loss=0.2099, pruned_loss=0.01546, over 7143.00 frames.], tot_loss[loss=0.153, simple_loss=0.2436, pruned_loss=0.03119, over 1418510.58 frames.], batch size: 17, lr: 2.68e-04
+2022-05-15 15:03:40,352 INFO [train.py:812] (7/8) Epoch 29, batch 3000, loss[loss=0.1355, simple_loss=0.2319, pruned_loss=0.01952, over 7245.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2442, pruned_loss=0.03112, over 1419283.63 frames.], batch size: 20, lr: 2.68e-04
+2022-05-15 15:03:40,353 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 15:03:47,851 INFO [train.py:841] (7/8) Epoch 29, validation: loss=0.153, simple_loss=0.2498, pruned_loss=0.02809, over 698248.00 frames.
+2022-05-15 15:04:46,873 INFO [train.py:812] (7/8) Epoch 29, batch 3050, loss[loss=0.1317, simple_loss=0.2194, pruned_loss=0.02199, over 7164.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2443, pruned_loss=0.03108, over 1422575.66 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 15:05:54,550 INFO [train.py:812] (7/8) Epoch 29, batch 3100, loss[loss=0.1512, simple_loss=0.2443, pruned_loss=0.02904, over 7254.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2438, pruned_loss=0.03093, over 1419507.22 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 15:06:53,612 INFO [train.py:812] (7/8) Epoch 29, batch 3150, loss[loss=0.1658, simple_loss=0.2589, pruned_loss=0.03638, over 7226.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2448, pruned_loss=0.03123, over 1422675.08 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 15:07:52,403 INFO [train.py:812] (7/8) Epoch 29, batch 3200, loss[loss=0.1432, simple_loss=0.2436, pruned_loss=0.02135, over 7440.00 frames.], tot_loss[loss=0.154, simple_loss=0.2452, pruned_loss=0.03134, over 1422869.07 frames.], batch size: 22, lr: 2.68e-04
+2022-05-15 15:08:52,067 INFO [train.py:812] (7/8) Epoch 29, batch 3250, loss[loss=0.1411, simple_loss=0.2237, pruned_loss=0.02928, over 6778.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2447, pruned_loss=0.03114, over 1422685.09 frames.], batch size: 15, lr: 2.67e-04
+2022-05-15 15:09:50,387 INFO [train.py:812] (7/8) Epoch 29, batch 3300, loss[loss=0.1769, simple_loss=0.2723, pruned_loss=0.0407, over 7225.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2462, pruned_loss=0.03171, over 1421390.92 frames.], batch size: 21, lr: 2.67e-04
+2022-05-15 15:10:48,366 INFO [train.py:812] (7/8) Epoch 29, batch 3350, loss[loss=0.1686, simple_loss=0.2538, pruned_loss=0.04171, over 7047.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2457, pruned_loss=0.03165, over 1417845.91 frames.], batch size: 28, lr: 2.67e-04
+2022-05-15 15:11:47,224 INFO [train.py:812] (7/8) Epoch 29, batch 3400, loss[loss=0.129, simple_loss=0.2162, pruned_loss=0.02085, over 7068.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2455, pruned_loss=0.03161, over 1416567.25 frames.], batch size: 18, lr: 2.67e-04
+2022-05-15 15:12:46,929 INFO [train.py:812] (7/8) Epoch 29, batch 3450, loss[loss=0.1249, simple_loss=0.2059, pruned_loss=0.02196, over 7278.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2449, pruned_loss=0.03145, over 1419713.11 frames.], batch size: 17, lr: 2.67e-04
+2022-05-15 15:13:45,927 INFO [train.py:812] (7/8) Epoch 29, batch 3500, loss[loss=0.1534, simple_loss=0.2544, pruned_loss=0.02615, over 6744.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2451, pruned_loss=0.03119, over 1419697.03 frames.], batch size: 31, lr: 2.67e-04
+2022-05-15 15:14:51,729 INFO [train.py:812] (7/8) Epoch 29, batch 3550, loss[loss=0.1598, simple_loss=0.2471, pruned_loss=0.03623, over 7288.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2445, pruned_loss=0.03086, over 1423135.26 frames.], batch size: 18, lr: 2.67e-04
+2022-05-15 15:15:51,052 INFO [train.py:812] (7/8) Epoch 29, batch 3600, loss[loss=0.1475, simple_loss=0.231, pruned_loss=0.03202, over 7208.00 frames.], tot_loss[loss=0.154, simple_loss=0.2451, pruned_loss=0.03144, over 1424001.26 frames.], batch size: 16, lr: 2.67e-04
+2022-05-15 15:16:50,751 INFO [train.py:812] (7/8) Epoch 29, batch 3650, loss[loss=0.1612, simple_loss=0.2611, pruned_loss=0.03068, over 7344.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2453, pruned_loss=0.03152, over 1427451.21 frames.], batch size: 22, lr: 2.67e-04
+2022-05-15 15:17:49,918 INFO [train.py:812] (7/8) Epoch 29, batch 3700, loss[loss=0.1654, simple_loss=0.2591, pruned_loss=0.0358, over 7209.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2446, pruned_loss=0.03126, over 1427070.84 frames.], batch size: 23, lr: 2.67e-04
+2022-05-15 15:18:49,057 INFO [train.py:812] (7/8) Epoch 29, batch 3750, loss[loss=0.2052, simple_loss=0.2887, pruned_loss=0.06082, over 4917.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2443, pruned_loss=0.03106, over 1426313.35 frames.], batch size: 52, lr: 2.67e-04
+2022-05-15 15:19:48,085 INFO [train.py:812] (7/8) Epoch 29, batch 3800, loss[loss=0.1651, simple_loss=0.2547, pruned_loss=0.03774, over 7436.00 frames.], tot_loss[loss=0.1537, simple_loss=0.245, pruned_loss=0.03119, over 1426797.29 frames.], batch size: 20, lr: 2.67e-04
+2022-05-15 15:20:46,953 INFO [train.py:812] (7/8) Epoch 29, batch 3850, loss[loss=0.1842, simple_loss=0.2746, pruned_loss=0.04687, over 7382.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2453, pruned_loss=0.03101, over 1427405.97 frames.], batch size: 23, lr: 2.67e-04
+2022-05-15 15:21:44,980 INFO [train.py:812] (7/8) Epoch 29, batch 3900, loss[loss=0.1753, simple_loss=0.2632, pruned_loss=0.04375, over 7288.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2466, pruned_loss=0.03137, over 1429950.27 frames.], batch size: 24, lr: 2.67e-04
+2022-05-15 15:22:44,193 INFO [train.py:812] (7/8) Epoch 29, batch 3950, loss[loss=0.1351, simple_loss=0.2187, pruned_loss=0.0257, over 7421.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2479, pruned_loss=0.03178, over 1430620.62 frames.], batch size: 18, lr: 2.67e-04
+2022-05-15 15:23:43,026 INFO [train.py:812] (7/8) Epoch 29, batch 4000, loss[loss=0.1484, simple_loss=0.2518, pruned_loss=0.02246, over 7333.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2478, pruned_loss=0.03198, over 1430467.62 frames.], batch size: 22, lr: 2.67e-04
+2022-05-15 15:24:42,309 INFO [train.py:812] (7/8) Epoch 29, batch 4050, loss[loss=0.1237, simple_loss=0.2081, pruned_loss=0.01967, over 7279.00 frames.], tot_loss[loss=0.156, simple_loss=0.2481, pruned_loss=0.03192, over 1429239.77 frames.], batch size: 17, lr: 2.67e-04
+2022-05-15 15:25:40,998 INFO [train.py:812] (7/8) Epoch 29, batch 4100, loss[loss=0.1603, simple_loss=0.2588, pruned_loss=0.03088, over 7351.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2481, pruned_loss=0.03171, over 1430213.40 frames.], batch size: 22, lr: 2.67e-04
+2022-05-15 15:26:40,408 INFO [train.py:812] (7/8) Epoch 29, batch 4150, loss[loss=0.1556, simple_loss=0.2521, pruned_loss=0.02957, over 7320.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2472, pruned_loss=0.03163, over 1423864.18 frames.], batch size: 21, lr: 2.67e-04
+2022-05-15 15:27:39,260 INFO [train.py:812] (7/8) Epoch 29, batch 4200, loss[loss=0.1548, simple_loss=0.236, pruned_loss=0.03679, over 7255.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2476, pruned_loss=0.03178, over 1419886.70 frames.], batch size: 19, lr: 2.66e-04
+2022-05-15 15:28:38,689 INFO [train.py:812] (7/8) Epoch 29, batch 4250, loss[loss=0.1536, simple_loss=0.2529, pruned_loss=0.02713, over 6854.00 frames.], tot_loss[loss=0.155, simple_loss=0.2471, pruned_loss=0.03145, over 1421943.25 frames.], batch size: 31, lr: 2.66e-04
+2022-05-15 15:29:36,735 INFO [train.py:812] (7/8) Epoch 29, batch 4300, loss[loss=0.1407, simple_loss=0.2281, pruned_loss=0.02671, over 7165.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2468, pruned_loss=0.03122, over 1417962.58 frames.], batch size: 18, lr: 2.66e-04
+2022-05-15 15:30:35,690 INFO [train.py:812] (7/8) Epoch 29, batch 4350, loss[loss=0.1563, simple_loss=0.2572, pruned_loss=0.02774, over 7322.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2461, pruned_loss=0.03125, over 1419524.02 frames.], batch size: 21, lr: 2.66e-04
+2022-05-15 15:31:34,609 INFO [train.py:812] (7/8) Epoch 29, batch 4400, loss[loss=0.1917, simple_loss=0.2818, pruned_loss=0.05076, over 7290.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2462, pruned_loss=0.03104, over 1411022.88 frames.], batch size: 24, lr: 2.66e-04
+2022-05-15 15:32:33,471 INFO [train.py:812] (7/8) Epoch 29, batch 4450, loss[loss=0.1573, simple_loss=0.2507, pruned_loss=0.03199, over 6256.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2459, pruned_loss=0.03151, over 1400835.26 frames.], batch size: 38, lr: 2.66e-04
+2022-05-15 15:33:31,931 INFO [train.py:812] (7/8) Epoch 29, batch 4500, loss[loss=0.1621, simple_loss=0.2653, pruned_loss=0.02946, over 7219.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2465, pruned_loss=0.03183, over 1378128.04 frames.], batch size: 22, lr: 2.66e-04
+2022-05-15 15:34:29,717 INFO [train.py:812] (7/8) Epoch 29, batch 4550, loss[loss=0.1976, simple_loss=0.2842, pruned_loss=0.05546, over 4815.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2483, pruned_loss=0.03249, over 1361104.69 frames.], batch size: 52, lr: 2.66e-04
+2022-05-15 15:35:40,754 INFO [train.py:812] (7/8) Epoch 30, batch 0, loss[loss=0.1361, simple_loss=0.2288, pruned_loss=0.02166, over 7324.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2288, pruned_loss=0.02166, over 7324.00 frames.], batch size: 20, lr: 2.62e-04
+2022-05-15 15:36:39,975 INFO [train.py:812] (7/8) Epoch 30, batch 50, loss[loss=0.1325, simple_loss=0.2238, pruned_loss=0.02063, over 7276.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2473, pruned_loss=0.03023, over 324433.70 frames.], batch size: 18, lr: 2.62e-04
+2022-05-15 15:37:39,103 INFO [train.py:812] (7/8) Epoch 30, batch 100, loss[loss=0.1254, simple_loss=0.2181, pruned_loss=0.01632, over 7267.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2431, pruned_loss=0.02992, over 572365.03 frames.], batch size: 17, lr: 2.62e-04
+2022-05-15 15:38:38,769 INFO [train.py:812] (7/8) Epoch 30, batch 150, loss[loss=0.1666, simple_loss=0.2775, pruned_loss=0.02783, over 7315.00 frames.], tot_loss[loss=0.153, simple_loss=0.2453, pruned_loss=0.03033, over 750159.61 frames.], batch size: 24, lr: 2.62e-04
+2022-05-15 15:39:36,213 INFO [train.py:812] (7/8) Epoch 30, batch 200, loss[loss=0.1567, simple_loss=0.2386, pruned_loss=0.03738, over 7352.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2453, pruned_loss=0.03081, over 899847.52 frames.], batch size: 19, lr: 2.61e-04
+2022-05-15 15:40:35,867 INFO [train.py:812] (7/8) Epoch 30, batch 250, loss[loss=0.1394, simple_loss=0.2176, pruned_loss=0.03061, over 6850.00 frames.], tot_loss[loss=0.153, simple_loss=0.2452, pruned_loss=0.03045, over 1015334.76 frames.], batch size: 15, lr: 2.61e-04
+2022-05-15 15:41:34,911 INFO [train.py:812] (7/8) Epoch 30, batch 300, loss[loss=0.1384, simple_loss=0.2283, pruned_loss=0.0242, over 7280.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2465, pruned_loss=0.03105, over 1108726.83 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:42:33,948 INFO [train.py:812] (7/8) Epoch 30, batch 350, loss[loss=0.1453, simple_loss=0.229, pruned_loss=0.03081, over 7334.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2449, pruned_loss=0.03044, over 1181384.22 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:43:32,171 INFO [train.py:812] (7/8) Epoch 30, batch 400, loss[loss=0.1697, simple_loss=0.2543, pruned_loss=0.04259, over 7285.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2453, pruned_loss=0.03059, over 1237188.30 frames.], batch size: 24, lr: 2.61e-04
+2022-05-15 15:44:30,902 INFO [train.py:812] (7/8) Epoch 30, batch 450, loss[loss=0.1493, simple_loss=0.2544, pruned_loss=0.02213, over 7414.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2448, pruned_loss=0.03064, over 1279564.53 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:45:28,651 INFO [train.py:812] (7/8) Epoch 30, batch 500, loss[loss=0.1563, simple_loss=0.2529, pruned_loss=0.02982, over 7330.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2453, pruned_loss=0.03067, over 1307820.50 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:46:27,350 INFO [train.py:812] (7/8) Epoch 30, batch 550, loss[loss=0.1644, simple_loss=0.261, pruned_loss=0.03391, over 7296.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2461, pruned_loss=0.0311, over 1335583.06 frames.], batch size: 24, lr: 2.61e-04
+2022-05-15 15:47:24,866 INFO [train.py:812] (7/8) Epoch 30, batch 600, loss[loss=0.1631, simple_loss=0.2628, pruned_loss=0.0317, over 7213.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2464, pruned_loss=0.03135, over 1351542.14 frames.], batch size: 22, lr: 2.61e-04
+2022-05-15 15:48:22,477 INFO [train.py:812] (7/8) Epoch 30, batch 650, loss[loss=0.1285, simple_loss=0.2133, pruned_loss=0.0218, over 7447.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2464, pruned_loss=0.03114, over 1366728.48 frames.], batch size: 19, lr: 2.61e-04
+2022-05-15 15:49:20,322 INFO [train.py:812] (7/8) Epoch 30, batch 700, loss[loss=0.131, simple_loss=0.2261, pruned_loss=0.01792, over 7329.00 frames.], tot_loss[loss=0.1549, simple_loss=0.247, pruned_loss=0.03136, over 1375611.55 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:50:18,884 INFO [train.py:812] (7/8) Epoch 30, batch 750, loss[loss=0.1482, simple_loss=0.2378, pruned_loss=0.02933, over 7231.00 frames.], tot_loss[loss=0.1551, simple_loss=0.247, pruned_loss=0.03155, over 1381852.65 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:51:17,506 INFO [train.py:812] (7/8) Epoch 30, batch 800, loss[loss=0.1607, simple_loss=0.2595, pruned_loss=0.03095, over 7344.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2465, pruned_loss=0.03132, over 1387727.68 frames.], batch size: 22, lr: 2.61e-04
+2022-05-15 15:52:16,536 INFO [train.py:812] (7/8) Epoch 30, batch 850, loss[loss=0.1497, simple_loss=0.2471, pruned_loss=0.02615, over 7063.00 frames.], tot_loss[loss=0.154, simple_loss=0.2458, pruned_loss=0.03113, over 1396477.57 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:53:14,197 INFO [train.py:812] (7/8) Epoch 30, batch 900, loss[loss=0.1638, simple_loss=0.2619, pruned_loss=0.03292, over 7227.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2452, pruned_loss=0.03114, over 1400700.82 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:54:13,182 INFO [train.py:812] (7/8) Epoch 30, batch 950, loss[loss=0.147, simple_loss=0.2314, pruned_loss=0.03135, over 7106.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2456, pruned_loss=0.0309, over 1406808.08 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:55:11,594 INFO [train.py:812] (7/8) Epoch 30, batch 1000, loss[loss=0.1546, simple_loss=0.2494, pruned_loss=0.02988, over 7142.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2466, pruned_loss=0.03125, over 1410855.90 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:56:10,074 INFO [train.py:812] (7/8) Epoch 30, batch 1050, loss[loss=0.1339, simple_loss=0.2214, pruned_loss=0.02318, over 7280.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2472, pruned_loss=0.03151, over 1407398.43 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:57:08,285 INFO [train.py:812] (7/8) Epoch 30, batch 1100, loss[loss=0.1704, simple_loss=0.2679, pruned_loss=0.03644, over 7310.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2478, pruned_loss=0.03161, over 1416850.76 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:58:07,705 INFO [train.py:812] (7/8) Epoch 30, batch 1150, loss[loss=0.1227, simple_loss=0.2017, pruned_loss=0.02186, over 6971.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2475, pruned_loss=0.03147, over 1417368.40 frames.], batch size: 16, lr: 2.61e-04
+2022-05-15 15:59:06,115 INFO [train.py:812] (7/8) Epoch 30, batch 1200, loss[loss=0.1561, simple_loss=0.2463, pruned_loss=0.03296, over 7161.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2476, pruned_loss=0.0318, over 1422127.46 frames.], batch size: 19, lr: 2.61e-04
+2022-05-15 16:00:14,967 INFO [train.py:812] (7/8) Epoch 30, batch 1250, loss[loss=0.1773, simple_loss=0.2644, pruned_loss=0.04512, over 4916.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2471, pruned_loss=0.03159, over 1417019.74 frames.], batch size: 52, lr: 2.60e-04
+2022-05-15 16:01:13,741 INFO [train.py:812] (7/8) Epoch 30, batch 1300, loss[loss=0.1577, simple_loss=0.264, pruned_loss=0.02568, over 7338.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2467, pruned_loss=0.03149, over 1418145.73 frames.], batch size: 22, lr: 2.60e-04
+2022-05-15 16:02:13,363 INFO [train.py:812] (7/8) Epoch 30, batch 1350, loss[loss=0.1559, simple_loss=0.2531, pruned_loss=0.02937, over 6648.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2468, pruned_loss=0.03149, over 1419616.38 frames.], batch size: 38, lr: 2.60e-04
+2022-05-15 16:03:12,438 INFO [train.py:812] (7/8) Epoch 30, batch 1400, loss[loss=0.1295, simple_loss=0.2147, pruned_loss=0.02212, over 6893.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2458, pruned_loss=0.03127, over 1420466.28 frames.], batch size: 15, lr: 2.60e-04
+2022-05-15 16:04:10,795 INFO [train.py:812] (7/8) Epoch 30, batch 1450, loss[loss=0.1342, simple_loss=0.2351, pruned_loss=0.01661, over 7103.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2451, pruned_loss=0.03076, over 1418930.25 frames.], batch size: 21, lr: 2.60e-04
+2022-05-15 16:05:09,043 INFO [train.py:812] (7/8) Epoch 30, batch 1500, loss[loss=0.1698, simple_loss=0.2528, pruned_loss=0.04342, over 7249.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2455, pruned_loss=0.03121, over 1418041.54 frames.], batch size: 19, lr: 2.60e-04
+2022-05-15 16:06:06,409 INFO [train.py:812] (7/8) Epoch 30, batch 1550, loss[loss=0.1589, simple_loss=0.261, pruned_loss=0.02843, over 7212.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2453, pruned_loss=0.03076, over 1418781.49 frames.], batch size: 23, lr: 2.60e-04
+2022-05-15 16:07:03,145 INFO [train.py:812] (7/8) Epoch 30, batch 1600, loss[loss=0.1597, simple_loss=0.2543, pruned_loss=0.03256, over 7323.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2461, pruned_loss=0.03118, over 1419619.44 frames.], batch size: 21, lr: 2.60e-04
+2022-05-15 16:08:02,748 INFO [train.py:812] (7/8) Epoch 30, batch 1650, loss[loss=0.1532, simple_loss=0.2507, pruned_loss=0.0278, over 7157.00 frames.], tot_loss[loss=0.154, simple_loss=0.246, pruned_loss=0.03095, over 1423872.31 frames.], batch size: 26, lr: 2.60e-04
+2022-05-15 16:09:00,142 INFO [train.py:812] (7/8) Epoch 30, batch 1700, loss[loss=0.1653, simple_loss=0.2494, pruned_loss=0.04061, over 7129.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2464, pruned_loss=0.03122, over 1426684.06 frames.], batch size: 17, lr: 2.60e-04
+2022-05-15 16:09:58,759 INFO [train.py:812] (7/8) Epoch 30, batch 1750, loss[loss=0.1699, simple_loss=0.27, pruned_loss=0.03489, over 7151.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2463, pruned_loss=0.03123, over 1423260.75 frames.], batch size: 20, lr: 2.60e-04
+2022-05-15 16:10:56,877 INFO [train.py:812] (7/8) Epoch 30, batch 1800, loss[loss=0.198, simple_loss=0.2909, pruned_loss=0.05253, over 5072.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2463, pruned_loss=0.03106, over 1420983.72 frames.], batch size: 52, lr: 2.60e-04
+2022-05-15 16:11:55,143 INFO [train.py:812] (7/8) Epoch 30, batch 1850, loss[loss=0.1554, simple_loss=0.2492, pruned_loss=0.03077, over 7106.00 frames.], tot_loss[loss=0.154, simple_loss=0.2456, pruned_loss=0.0312, over 1424820.43 frames.], batch size: 21, lr: 2.60e-04
+2022-05-15 16:12:53,281 INFO [train.py:812] (7/8) Epoch 30, batch 1900, loss[loss=0.1536, simple_loss=0.2381, pruned_loss=0.03454, over 6851.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2451, pruned_loss=0.03103, over 1427397.49 frames.], batch size: 15, lr: 2.60e-04
+2022-05-15 16:13:52,787 INFO [train.py:812] (7/8) Epoch 30, batch 1950, loss[loss=0.1288, simple_loss=0.2096, pruned_loss=0.02403, over 7267.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2452, pruned_loss=0.03106, over 1428595.73 frames.], batch size: 17, lr: 2.60e-04
+2022-05-15 16:14:51,475 INFO [train.py:812] (7/8) Epoch 30, batch 2000, loss[loss=0.139, simple_loss=0.2381, pruned_loss=0.02, over 7330.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2455, pruned_loss=0.03083, over 1431051.96 frames.], batch size: 22, lr: 2.60e-04
+2022-05-15 16:15:50,906 INFO [train.py:812] (7/8) Epoch 30, batch 2050, loss[loss=0.1751, simple_loss=0.2691, pruned_loss=0.04059, over 7179.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2454, pruned_loss=0.03076, over 1432036.93 frames.], batch size: 23, lr: 2.60e-04
+2022-05-15 16:16:49,870 INFO [train.py:812] (7/8) Epoch 30, batch 2100, loss[loss=0.1619, simple_loss=0.2576, pruned_loss=0.03316, over 7140.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2453, pruned_loss=0.03089, over 1430980.90 frames.], batch size: 20, lr: 2.60e-04
+2022-05-15 16:17:48,138 INFO [train.py:812] (7/8) Epoch 30, batch 2150, loss[loss=0.1296, simple_loss=0.2172, pruned_loss=0.02097, over 7141.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2451, pruned_loss=0.03064, over 1429403.51 frames.], batch size: 17, lr: 2.60e-04
+2022-05-15 16:18:47,092 INFO [train.py:812] (7/8) Epoch 30, batch 2200, loss[loss=0.1475, simple_loss=0.2403, pruned_loss=0.02731, over 7268.00 frames.], tot_loss[loss=0.1535, simple_loss=0.245, pruned_loss=0.03101, over 1424849.79 frames.], batch size: 24, lr: 2.60e-04
+2022-05-15 16:19:45,907 INFO [train.py:812] (7/8) Epoch 30, batch 2250, loss[loss=0.1786, simple_loss=0.2859, pruned_loss=0.0357, over 7175.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2451, pruned_loss=0.03104, over 1423507.27 frames.], batch size: 26, lr: 2.59e-04
+2022-05-15 16:20:43,587 INFO [train.py:812] (7/8) Epoch 30, batch 2300, loss[loss=0.1672, simple_loss=0.257, pruned_loss=0.03867, over 7327.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2452, pruned_loss=0.03077, over 1420021.19 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:21:42,634 INFO [train.py:812] (7/8) Epoch 30, batch 2350, loss[loss=0.1561, simple_loss=0.2557, pruned_loss=0.02825, over 7338.00 frames.], tot_loss[loss=0.153, simple_loss=0.2448, pruned_loss=0.03054, over 1421632.99 frames.], batch size: 22, lr: 2.59e-04
+2022-05-15 16:22:41,708 INFO [train.py:812] (7/8) Epoch 30, batch 2400, loss[loss=0.1629, simple_loss=0.2474, pruned_loss=0.03916, over 7279.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2446, pruned_loss=0.0304, over 1423583.71 frames.], batch size: 25, lr: 2.59e-04
+2022-05-15 16:23:41,331 INFO [train.py:812] (7/8) Epoch 30, batch 2450, loss[loss=0.1686, simple_loss=0.2687, pruned_loss=0.03425, over 7150.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2438, pruned_loss=0.03001, over 1427521.13 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:24:39,660 INFO [train.py:812] (7/8) Epoch 30, batch 2500, loss[loss=0.1551, simple_loss=0.2324, pruned_loss=0.03886, over 6788.00 frames.], tot_loss[loss=0.153, simple_loss=0.2445, pruned_loss=0.03079, over 1430846.69 frames.], batch size: 15, lr: 2.59e-04
+2022-05-15 16:25:38,974 INFO [train.py:812] (7/8) Epoch 30, batch 2550, loss[loss=0.1358, simple_loss=0.2276, pruned_loss=0.02196, over 7411.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2442, pruned_loss=0.03101, over 1428339.20 frames.], batch size: 18, lr: 2.59e-04
+2022-05-15 16:26:37,731 INFO [train.py:812] (7/8) Epoch 30, batch 2600, loss[loss=0.1525, simple_loss=0.2577, pruned_loss=0.02363, over 7119.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2446, pruned_loss=0.03105, over 1427659.69 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:27:37,218 INFO [train.py:812] (7/8) Epoch 30, batch 2650, loss[loss=0.1339, simple_loss=0.2139, pruned_loss=0.02697, over 7146.00 frames.], tot_loss[loss=0.1526, simple_loss=0.244, pruned_loss=0.03057, over 1429741.35 frames.], batch size: 17, lr: 2.59e-04
+2022-05-15 16:28:36,175 INFO [train.py:812] (7/8) Epoch 30, batch 2700, loss[loss=0.1585, simple_loss=0.2506, pruned_loss=0.03314, over 7112.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2448, pruned_loss=0.03082, over 1429464.93 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:29:34,419 INFO [train.py:812] (7/8) Epoch 30, batch 2750, loss[loss=0.1402, simple_loss=0.2326, pruned_loss=0.02388, over 7232.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.03079, over 1425297.70 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:30:32,072 INFO [train.py:812] (7/8) Epoch 30, batch 2800, loss[loss=0.1433, simple_loss=0.2366, pruned_loss=0.02495, over 7331.00 frames.], tot_loss[loss=0.1536, simple_loss=0.245, pruned_loss=0.0311, over 1424421.73 frames.], batch size: 22, lr: 2.59e-04
+2022-05-15 16:31:31,642 INFO [train.py:812] (7/8) Epoch 30, batch 2850, loss[loss=0.1581, simple_loss=0.2552, pruned_loss=0.03053, over 7232.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2447, pruned_loss=0.0314, over 1419069.80 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:32:29,842 INFO [train.py:812] (7/8) Epoch 30, batch 2900, loss[loss=0.137, simple_loss=0.2208, pruned_loss=0.02659, over 6999.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2444, pruned_loss=0.03117, over 1422162.01 frames.], batch size: 16, lr: 2.59e-04
+2022-05-15 16:33:36,414 INFO [train.py:812] (7/8) Epoch 30, batch 2950, loss[loss=0.147, simple_loss=0.2497, pruned_loss=0.02213, over 6425.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2441, pruned_loss=0.03105, over 1422913.92 frames.], batch size: 38, lr: 2.59e-04
+2022-05-15 16:34:35,508 INFO [train.py:812] (7/8) Epoch 30, batch 3000, loss[loss=0.1299, simple_loss=0.2261, pruned_loss=0.01681, over 7125.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2439, pruned_loss=0.0308, over 1425095.75 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:34:35,509 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 16:34:43,057 INFO [train.py:841] (7/8) Epoch 30, validation: loss=0.1528, simple_loss=0.2494, pruned_loss=0.02809, over 698248.00 frames.
+2022-05-15 16:35:41,804 INFO [train.py:812] (7/8) Epoch 30, batch 3050, loss[loss=0.1394, simple_loss=0.2345, pruned_loss=0.02218, over 7116.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03084, over 1426527.38 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:36:40,867 INFO [train.py:812] (7/8) Epoch 30, batch 3100, loss[loss=0.1569, simple_loss=0.2525, pruned_loss=0.0307, over 7400.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2456, pruned_loss=0.03105, over 1426939.77 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:37:40,517 INFO [train.py:812] (7/8) Epoch 30, batch 3150, loss[loss=0.1278, simple_loss=0.2118, pruned_loss=0.0219, over 7164.00 frames.], tot_loss[loss=0.153, simple_loss=0.2444, pruned_loss=0.03076, over 1422273.95 frames.], batch size: 18, lr: 2.59e-04
+2022-05-15 16:38:39,695 INFO [train.py:812] (7/8) Epoch 30, batch 3200, loss[loss=0.1607, simple_loss=0.2513, pruned_loss=0.03499, over 7251.00 frames.], tot_loss[loss=0.152, simple_loss=0.2431, pruned_loss=0.03047, over 1424937.58 frames.], batch size: 19, lr: 2.59e-04
+2022-05-15 16:39:38,900 INFO [train.py:812] (7/8) Epoch 30, batch 3250, loss[loss=0.1378, simple_loss=0.2354, pruned_loss=0.02014, over 7082.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2434, pruned_loss=0.03034, over 1419530.15 frames.], batch size: 28, lr: 2.59e-04
+2022-05-15 16:40:36,557 INFO [train.py:812] (7/8) Epoch 30, batch 3300, loss[loss=0.1335, simple_loss=0.2324, pruned_loss=0.01729, over 7324.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2439, pruned_loss=0.03028, over 1423202.20 frames.], batch size: 20, lr: 2.58e-04
+2022-05-15 16:41:35,389 INFO [train.py:812] (7/8) Epoch 30, batch 3350, loss[loss=0.122, simple_loss=0.1987, pruned_loss=0.02259, over 7277.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2432, pruned_loss=0.03028, over 1427126.08 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 16:42:33,363 INFO [train.py:812] (7/8) Epoch 30, batch 3400, loss[loss=0.1735, simple_loss=0.2615, pruned_loss=0.04279, over 4614.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2437, pruned_loss=0.03077, over 1422982.15 frames.], batch size: 52, lr: 2.58e-04
+2022-05-15 16:43:31,895 INFO [train.py:812] (7/8) Epoch 30, batch 3450, loss[loss=0.1571, simple_loss=0.2503, pruned_loss=0.03193, over 7275.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2437, pruned_loss=0.03087, over 1420558.96 frames.], batch size: 24, lr: 2.58e-04
+2022-05-15 16:44:30,309 INFO [train.py:812] (7/8) Epoch 30, batch 3500, loss[loss=0.1806, simple_loss=0.2799, pruned_loss=0.04064, over 7163.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2447, pruned_loss=0.03116, over 1422758.61 frames.], batch size: 26, lr: 2.58e-04
+2022-05-15 16:45:29,383 INFO [train.py:812] (7/8) Epoch 30, batch 3550, loss[loss=0.1384, simple_loss=0.2304, pruned_loss=0.02319, over 7174.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2443, pruned_loss=0.03059, over 1422747.90 frames.], batch size: 18, lr: 2.58e-04
+2022-05-15 16:46:28,189 INFO [train.py:812] (7/8) Epoch 30, batch 3600, loss[loss=0.1458, simple_loss=0.2409, pruned_loss=0.02532, over 7253.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2442, pruned_loss=0.03044, over 1428103.96 frames.], batch size: 19, lr: 2.58e-04
+2022-05-15 16:47:27,395 INFO [train.py:812] (7/8) Epoch 30, batch 3650, loss[loss=0.1554, simple_loss=0.2541, pruned_loss=0.02828, over 6784.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2444, pruned_loss=0.03048, over 1429352.09 frames.], batch size: 31, lr: 2.58e-04
+2022-05-15 16:48:25,025 INFO [train.py:812] (7/8) Epoch 30, batch 3700, loss[loss=0.1303, simple_loss=0.218, pruned_loss=0.02136, over 7281.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2434, pruned_loss=0.03008, over 1429504.01 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 16:49:23,825 INFO [train.py:812] (7/8) Epoch 30, batch 3750, loss[loss=0.1627, simple_loss=0.2556, pruned_loss=0.03486, over 7049.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.03005, over 1432443.71 frames.], batch size: 28, lr: 2.58e-04
+2022-05-15 16:50:21,213 INFO [train.py:812] (7/8) Epoch 30, batch 3800, loss[loss=0.1827, simple_loss=0.286, pruned_loss=0.03972, over 7209.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2455, pruned_loss=0.03042, over 1425483.01 frames.], batch size: 22, lr: 2.58e-04
+2022-05-15 16:51:18,883 INFO [train.py:812] (7/8) Epoch 30, batch 3850, loss[loss=0.1477, simple_loss=0.2318, pruned_loss=0.03181, over 6780.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2449, pruned_loss=0.03018, over 1426191.61 frames.], batch size: 15, lr: 2.58e-04
+2022-05-15 16:52:16,797 INFO [train.py:812] (7/8) Epoch 30, batch 3900, loss[loss=0.1461, simple_loss=0.2305, pruned_loss=0.03087, over 7130.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2454, pruned_loss=0.03062, over 1426778.19 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 16:53:15,092 INFO [train.py:812] (7/8) Epoch 30, batch 3950, loss[loss=0.1758, simple_loss=0.2689, pruned_loss=0.04136, over 7384.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2466, pruned_loss=0.03124, over 1420548.37 frames.], batch size: 23, lr: 2.58e-04
+2022-05-15 16:54:13,808 INFO [train.py:812] (7/8) Epoch 30, batch 4000, loss[loss=0.1545, simple_loss=0.2516, pruned_loss=0.02871, over 7305.00 frames.], tot_loss[loss=0.155, simple_loss=0.2472, pruned_loss=0.03142, over 1419960.20 frames.], batch size: 25, lr: 2.58e-04
+2022-05-15 16:55:12,888 INFO [train.py:812] (7/8) Epoch 30, batch 4050, loss[loss=0.1545, simple_loss=0.2496, pruned_loss=0.0297, over 7157.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2464, pruned_loss=0.03136, over 1419499.99 frames.], batch size: 28, lr: 2.58e-04
+2022-05-15 16:56:10,909 INFO [train.py:812] (7/8) Epoch 30, batch 4100, loss[loss=0.1623, simple_loss=0.261, pruned_loss=0.03176, over 7311.00 frames.], tot_loss[loss=0.154, simple_loss=0.2459, pruned_loss=0.03108, over 1421245.52 frames.], batch size: 21, lr: 2.58e-04
+2022-05-15 16:57:19,290 INFO [train.py:812] (7/8) Epoch 30, batch 4150, loss[loss=0.1635, simple_loss=0.2691, pruned_loss=0.02892, over 7218.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2448, pruned_loss=0.03098, over 1421939.40 frames.], batch size: 21, lr: 2.58e-04
+2022-05-15 16:58:17,945 INFO [train.py:812] (7/8) Epoch 30, batch 4200, loss[loss=0.1715, simple_loss=0.2689, pruned_loss=0.03703, over 7428.00 frames.], tot_loss[loss=0.154, simple_loss=0.2454, pruned_loss=0.0313, over 1422361.83 frames.], batch size: 20, lr: 2.58e-04
+2022-05-15 16:59:24,885 INFO [train.py:812] (7/8) Epoch 30, batch 4250, loss[loss=0.1741, simple_loss=0.2652, pruned_loss=0.04146, over 7382.00 frames.], tot_loss[loss=0.155, simple_loss=0.247, pruned_loss=0.03154, over 1416329.27 frames.], batch size: 23, lr: 2.58e-04
+2022-05-15 17:00:23,137 INFO [train.py:812] (7/8) Epoch 30, batch 4300, loss[loss=0.126, simple_loss=0.2125, pruned_loss=0.01971, over 7281.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2467, pruned_loss=0.03147, over 1419966.38 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 17:01:31,696 INFO [train.py:812] (7/8) Epoch 30, batch 4350, loss[loss=0.1399, simple_loss=0.2372, pruned_loss=0.02127, over 7237.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2451, pruned_loss=0.0309, over 1422878.86 frames.], batch size: 20, lr: 2.58e-04
+2022-05-15 17:02:30,814 INFO [train.py:812] (7/8) Epoch 30, batch 4400, loss[loss=0.1587, simple_loss=0.2564, pruned_loss=0.03046, over 7235.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03072, over 1418837.44 frames.], batch size: 20, lr: 2.57e-04
+2022-05-15 17:03:47,910 INFO [train.py:812] (7/8) Epoch 30, batch 4450, loss[loss=0.1521, simple_loss=0.2482, pruned_loss=0.02803, over 6593.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.03068, over 1413198.47 frames.], batch size: 38, lr: 2.57e-04
+2022-05-15 17:04:54,637 INFO [train.py:812] (7/8) Epoch 30, batch 4500, loss[loss=0.1962, simple_loss=0.2756, pruned_loss=0.05837, over 5323.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2457, pruned_loss=0.03093, over 1398079.06 frames.], batch size: 52, lr: 2.57e-04
+2022-05-15 17:05:52,220 INFO [train.py:812] (7/8) Epoch 30, batch 4550, loss[loss=0.2036, simple_loss=0.2764, pruned_loss=0.06533, over 5123.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2483, pruned_loss=0.03231, over 1358924.43 frames.], batch size: 52, lr: 2.57e-04
+2022-05-15 17:07:08,093 INFO [train.py:812] (7/8) Epoch 31, batch 0, loss[loss=0.1321, simple_loss=0.2212, pruned_loss=0.02146, over 7322.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2212, pruned_loss=0.02146, over 7322.00 frames.], batch size: 20, lr: 2.53e-04
+2022-05-15 17:08:07,426 INFO [train.py:812] (7/8) Epoch 31, batch 50, loss[loss=0.1546, simple_loss=0.2578, pruned_loss=0.02567, over 7258.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03044, over 317125.55 frames.], batch size: 19, lr: 2.53e-04
+2022-05-15 17:09:06,214 INFO [train.py:812] (7/8) Epoch 31, batch 100, loss[loss=0.1599, simple_loss=0.2549, pruned_loss=0.03241, over 7380.00 frames.], tot_loss[loss=0.1534, simple_loss=0.245, pruned_loss=0.03086, over 561019.36 frames.], batch size: 23, lr: 2.53e-04
+2022-05-15 17:10:05,019 INFO [train.py:812] (7/8) Epoch 31, batch 150, loss[loss=0.1884, simple_loss=0.2846, pruned_loss=0.04607, over 7203.00 frames.], tot_loss[loss=0.1526, simple_loss=0.244, pruned_loss=0.0306, over 756132.66 frames.], batch size: 22, lr: 2.53e-04
+2022-05-15 17:11:03,903 INFO [train.py:812] (7/8) Epoch 31, batch 200, loss[loss=0.1935, simple_loss=0.2668, pruned_loss=0.06007, over 5070.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2434, pruned_loss=0.03108, over 900682.88 frames.], batch size: 54, lr: 2.53e-04
+2022-05-15 17:12:02,414 INFO [train.py:812] (7/8) Epoch 31, batch 250, loss[loss=0.1738, simple_loss=0.2646, pruned_loss=0.0415, over 7268.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2456, pruned_loss=0.03138, over 1015457.18 frames.], batch size: 25, lr: 2.53e-04
+2022-05-15 17:13:01,767 INFO [train.py:812] (7/8) Epoch 31, batch 300, loss[loss=0.1468, simple_loss=0.2476, pruned_loss=0.02302, over 7330.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2454, pruned_loss=0.0316, over 1107348.92 frames.], batch size: 21, lr: 2.53e-04
+2022-05-15 17:13:59,745 INFO [train.py:812] (7/8) Epoch 31, batch 350, loss[loss=0.1573, simple_loss=0.2471, pruned_loss=0.03373, over 7161.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2459, pruned_loss=0.03175, over 1174195.03 frames.], batch size: 18, lr: 2.53e-04
+2022-05-15 17:14:57,257 INFO [train.py:812] (7/8) Epoch 31, batch 400, loss[loss=0.1391, simple_loss=0.2359, pruned_loss=0.02112, over 7220.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2459, pruned_loss=0.03154, over 1224087.12 frames.], batch size: 21, lr: 2.53e-04
+2022-05-15 17:15:56,109 INFO [train.py:812] (7/8) Epoch 31, batch 450, loss[loss=0.1823, simple_loss=0.2713, pruned_loss=0.04671, over 7173.00 frames.], tot_loss[loss=0.1553, simple_loss=0.247, pruned_loss=0.0318, over 1265141.10 frames.], batch size: 26, lr: 2.53e-04
+2022-05-15 17:16:55,566 INFO [train.py:812] (7/8) Epoch 31, batch 500, loss[loss=0.1429, simple_loss=0.228, pruned_loss=0.02896, over 7270.00 frames.], tot_loss[loss=0.155, simple_loss=0.2465, pruned_loss=0.03169, over 1300873.34 frames.], batch size: 17, lr: 2.53e-04
+2022-05-15 17:17:54,460 INFO [train.py:812] (7/8) Epoch 31, batch 550, loss[loss=0.1565, simple_loss=0.2592, pruned_loss=0.02686, over 7403.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2463, pruned_loss=0.03155, over 1328011.41 frames.], batch size: 21, lr: 2.53e-04
+2022-05-15 17:18:53,079 INFO [train.py:812] (7/8) Epoch 31, batch 600, loss[loss=0.1529, simple_loss=0.2436, pruned_loss=0.03112, over 7079.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2476, pruned_loss=0.03194, over 1347258.20 frames.], batch size: 18, lr: 2.53e-04
+2022-05-15 17:19:50,604 INFO [train.py:812] (7/8) Epoch 31, batch 650, loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.0296, over 7147.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2467, pruned_loss=0.03144, over 1368668.40 frames.], batch size: 20, lr: 2.53e-04
+2022-05-15 17:20:49,362 INFO [train.py:812] (7/8) Epoch 31, batch 700, loss[loss=0.1347, simple_loss=0.2098, pruned_loss=0.02983, over 6755.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2469, pruned_loss=0.03146, over 1378161.09 frames.], batch size: 15, lr: 2.52e-04
+2022-05-15 17:21:47,380 INFO [train.py:812] (7/8) Epoch 31, batch 750, loss[loss=0.147, simple_loss=0.2362, pruned_loss=0.02888, over 7243.00 frames.], tot_loss[loss=0.1539, simple_loss=0.246, pruned_loss=0.0309, over 1386853.86 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:22:46,105 INFO [train.py:812] (7/8) Epoch 31, batch 800, loss[loss=0.1393, simple_loss=0.2365, pruned_loss=0.02106, over 7330.00 frames.], tot_loss[loss=0.1537, simple_loss=0.246, pruned_loss=0.03072, over 1395485.00 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:23:44,741 INFO [train.py:812] (7/8) Epoch 31, batch 850, loss[loss=0.1609, simple_loss=0.2505, pruned_loss=0.03563, over 7426.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2442, pruned_loss=0.03019, over 1399919.99 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:24:43,303 INFO [train.py:812] (7/8) Epoch 31, batch 900, loss[loss=0.1326, simple_loss=0.2185, pruned_loss=0.02341, over 6821.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2443, pruned_loss=0.03019, over 1404645.43 frames.], batch size: 15, lr: 2.52e-04
+2022-05-15 17:25:42,283 INFO [train.py:812] (7/8) Epoch 31, batch 950, loss[loss=0.1519, simple_loss=0.2426, pruned_loss=0.03057, over 7050.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2439, pruned_loss=0.03033, over 1406321.67 frames.], batch size: 28, lr: 2.52e-04
+2022-05-15 17:26:41,340 INFO [train.py:812] (7/8) Epoch 31, batch 1000, loss[loss=0.1512, simple_loss=0.2462, pruned_loss=0.02807, over 7336.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03008, over 1408872.22 frames.], batch size: 22, lr: 2.52e-04
+2022-05-15 17:27:40,609 INFO [train.py:812] (7/8) Epoch 31, batch 1050, loss[loss=0.1606, simple_loss=0.2579, pruned_loss=0.0317, over 7044.00 frames.], tot_loss[loss=0.152, simple_loss=0.2438, pruned_loss=0.03006, over 1410780.17 frames.], batch size: 28, lr: 2.52e-04
+2022-05-15 17:28:39,420 INFO [train.py:812] (7/8) Epoch 31, batch 1100, loss[loss=0.1509, simple_loss=0.2494, pruned_loss=0.02619, over 7069.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2437, pruned_loss=0.03008, over 1415268.69 frames.], batch size: 18, lr: 2.52e-04
+2022-05-15 17:29:38,124 INFO [train.py:812] (7/8) Epoch 31, batch 1150, loss[loss=0.1354, simple_loss=0.225, pruned_loss=0.02286, over 7055.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2435, pruned_loss=0.03019, over 1416941.79 frames.], batch size: 18, lr: 2.52e-04
+2022-05-15 17:30:36,873 INFO [train.py:812] (7/8) Epoch 31, batch 1200, loss[loss=0.1788, simple_loss=0.2685, pruned_loss=0.04449, over 7203.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2432, pruned_loss=0.02995, over 1419467.12 frames.], batch size: 22, lr: 2.52e-04
+2022-05-15 17:31:36,143 INFO [train.py:812] (7/8) Epoch 31, batch 1250, loss[loss=0.1486, simple_loss=0.2377, pruned_loss=0.02977, over 7408.00 frames.], tot_loss[loss=0.152, simple_loss=0.2436, pruned_loss=0.03015, over 1418761.14 frames.], batch size: 18, lr: 2.52e-04
+2022-05-15 17:32:35,826 INFO [train.py:812] (7/8) Epoch 31, batch 1300, loss[loss=0.1859, simple_loss=0.2778, pruned_loss=0.04699, over 7168.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2446, pruned_loss=0.03046, over 1417584.04 frames.], batch size: 26, lr: 2.52e-04
+2022-05-15 17:33:34,103 INFO [train.py:812] (7/8) Epoch 31, batch 1350, loss[loss=0.1391, simple_loss=0.2244, pruned_loss=0.02693, over 7138.00 frames.], tot_loss[loss=0.154, simple_loss=0.2459, pruned_loss=0.03102, over 1415165.01 frames.], batch size: 17, lr: 2.52e-04
+2022-05-15 17:34:32,643 INFO [train.py:812] (7/8) Epoch 31, batch 1400, loss[loss=0.1752, simple_loss=0.2717, pruned_loss=0.03936, over 7332.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2462, pruned_loss=0.03112, over 1419122.99 frames.], batch size: 22, lr: 2.52e-04
+2022-05-15 17:35:31,412 INFO [train.py:812] (7/8) Epoch 31, batch 1450, loss[loss=0.1529, simple_loss=0.249, pruned_loss=0.02847, over 7144.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2459, pruned_loss=0.03084, over 1420337.82 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:36:30,391 INFO [train.py:812] (7/8) Epoch 31, batch 1500, loss[loss=0.1709, simple_loss=0.2615, pruned_loss=0.04015, over 7300.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2467, pruned_loss=0.03114, over 1425947.40 frames.], batch size: 25, lr: 2.52e-04
+2022-05-15 17:37:27,943 INFO [train.py:812] (7/8) Epoch 31, batch 1550, loss[loss=0.1516, simple_loss=0.2492, pruned_loss=0.02702, over 7297.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2453, pruned_loss=0.03098, over 1427167.21 frames.], batch size: 25, lr: 2.52e-04
+2022-05-15 17:38:27,314 INFO [train.py:812] (7/8) Epoch 31, batch 1600, loss[loss=0.1709, simple_loss=0.2589, pruned_loss=0.0415, over 7257.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2445, pruned_loss=0.03091, over 1428109.54 frames.], batch size: 19, lr: 2.52e-04
+2022-05-15 17:39:26,059 INFO [train.py:812] (7/8) Epoch 31, batch 1650, loss[loss=0.1512, simple_loss=0.2525, pruned_loss=0.02493, over 7113.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2452, pruned_loss=0.03099, over 1428312.08 frames.], batch size: 21, lr: 2.52e-04
+2022-05-15 17:40:24,547 INFO [train.py:812] (7/8) Epoch 31, batch 1700, loss[loss=0.1764, simple_loss=0.2723, pruned_loss=0.04025, over 7282.00 frames.], tot_loss[loss=0.1526, simple_loss=0.244, pruned_loss=0.03065, over 1425247.64 frames.], batch size: 24, lr: 2.52e-04
+2022-05-15 17:41:22,591 INFO [train.py:812] (7/8) Epoch 31, batch 1750, loss[loss=0.1771, simple_loss=0.2652, pruned_loss=0.04451, over 7373.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2447, pruned_loss=0.03083, over 1427417.63 frames.], batch size: 23, lr: 2.52e-04
+2022-05-15 17:42:21,659 INFO [train.py:812] (7/8) Epoch 31, batch 1800, loss[loss=0.1476, simple_loss=0.2495, pruned_loss=0.02288, over 7442.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03091, over 1423048.78 frames.], batch size: 20, lr: 2.51e-04
+2022-05-15 17:43:20,027 INFO [train.py:812] (7/8) Epoch 31, batch 1850, loss[loss=0.1217, simple_loss=0.2086, pruned_loss=0.01741, over 7134.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2442, pruned_loss=0.03072, over 1421790.24 frames.], batch size: 17, lr: 2.51e-04
+2022-05-15 17:44:19,027 INFO [train.py:812] (7/8) Epoch 31, batch 1900, loss[loss=0.1623, simple_loss=0.257, pruned_loss=0.03383, over 7333.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2445, pruned_loss=0.03044, over 1425270.70 frames.], batch size: 20, lr: 2.51e-04
+2022-05-15 17:45:17,766 INFO [train.py:812] (7/8) Epoch 31, batch 1950, loss[loss=0.1503, simple_loss=0.2448, pruned_loss=0.02786, over 7382.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2442, pruned_loss=0.0302, over 1424837.84 frames.], batch size: 23, lr: 2.51e-04
+2022-05-15 17:46:16,478 INFO [train.py:812] (7/8) Epoch 31, batch 2000, loss[loss=0.1635, simple_loss=0.2559, pruned_loss=0.03553, over 7159.00 frames.], tot_loss[loss=0.1514, simple_loss=0.243, pruned_loss=0.02989, over 1426218.01 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:47:15,255 INFO [train.py:812] (7/8) Epoch 31, batch 2050, loss[loss=0.166, simple_loss=0.2491, pruned_loss=0.04147, over 7189.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2426, pruned_loss=0.0301, over 1423639.35 frames.], batch size: 22, lr: 2.51e-04
+2022-05-15 17:48:13,837 INFO [train.py:812] (7/8) Epoch 31, batch 2100, loss[loss=0.1575, simple_loss=0.2458, pruned_loss=0.03464, over 7168.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2435, pruned_loss=0.03011, over 1422548.28 frames.], batch size: 19, lr: 2.51e-04
+2022-05-15 17:49:12,936 INFO [train.py:812] (7/8) Epoch 31, batch 2150, loss[loss=0.1477, simple_loss=0.2415, pruned_loss=0.02693, over 7165.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2434, pruned_loss=0.02975, over 1426220.20 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:50:11,061 INFO [train.py:812] (7/8) Epoch 31, batch 2200, loss[loss=0.1499, simple_loss=0.2454, pruned_loss=0.02715, over 7061.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2445, pruned_loss=0.02998, over 1427775.78 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:51:08,624 INFO [train.py:812] (7/8) Epoch 31, batch 2250, loss[loss=0.2074, simple_loss=0.2863, pruned_loss=0.06425, over 7188.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2457, pruned_loss=0.03052, over 1427009.44 frames.], batch size: 23, lr: 2.51e-04
+2022-05-15 17:52:08,133 INFO [train.py:812] (7/8) Epoch 31, batch 2300, loss[loss=0.1345, simple_loss=0.2231, pruned_loss=0.02298, over 7256.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2451, pruned_loss=0.0303, over 1429409.76 frames.], batch size: 19, lr: 2.51e-04
+2022-05-15 17:53:06,342 INFO [train.py:812] (7/8) Epoch 31, batch 2350, loss[loss=0.1542, simple_loss=0.2474, pruned_loss=0.03051, over 7070.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2451, pruned_loss=0.03065, over 1429023.94 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:54:10,981 INFO [train.py:812] (7/8) Epoch 31, batch 2400, loss[loss=0.1495, simple_loss=0.2456, pruned_loss=0.0267, over 7223.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2456, pruned_loss=0.03088, over 1428481.15 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 17:55:08,421 INFO [train.py:812] (7/8) Epoch 31, batch 2450, loss[loss=0.1872, simple_loss=0.2777, pruned_loss=0.04832, over 7208.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2462, pruned_loss=0.03083, over 1423957.74 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 17:56:07,161 INFO [train.py:812] (7/8) Epoch 31, batch 2500, loss[loss=0.1539, simple_loss=0.2546, pruned_loss=0.02665, over 7327.00 frames.], tot_loss[loss=0.1535, simple_loss=0.246, pruned_loss=0.0305, over 1426538.65 frames.], batch size: 22, lr: 2.51e-04
+2022-05-15 17:57:05,830 INFO [train.py:812] (7/8) Epoch 31, batch 2550, loss[loss=0.1545, simple_loss=0.2481, pruned_loss=0.03046, over 7220.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2453, pruned_loss=0.03047, over 1428330.84 frames.], batch size: 23, lr: 2.51e-04
+2022-05-15 17:58:14,114 INFO [train.py:812] (7/8) Epoch 31, batch 2600, loss[loss=0.1307, simple_loss=0.2155, pruned_loss=0.02295, over 7406.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2449, pruned_loss=0.03064, over 1427399.99 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:59:11,581 INFO [train.py:812] (7/8) Epoch 31, batch 2650, loss[loss=0.1692, simple_loss=0.2736, pruned_loss=0.03236, over 7410.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2452, pruned_loss=0.03072, over 1424778.96 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 18:00:10,482 INFO [train.py:812] (7/8) Epoch 31, batch 2700, loss[loss=0.1625, simple_loss=0.2537, pruned_loss=0.03567, over 7311.00 frames.], tot_loss[loss=0.153, simple_loss=0.245, pruned_loss=0.03049, over 1418636.70 frames.], batch size: 25, lr: 2.51e-04
+2022-05-15 18:01:09,686 INFO [train.py:812] (7/8) Epoch 31, batch 2750, loss[loss=0.1688, simple_loss=0.2632, pruned_loss=0.03718, over 7148.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2455, pruned_loss=0.03092, over 1419259.45 frames.], batch size: 20, lr: 2.51e-04
+2022-05-15 18:02:08,952 INFO [train.py:812] (7/8) Epoch 31, batch 2800, loss[loss=0.1299, simple_loss=0.2242, pruned_loss=0.01785, over 7172.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2456, pruned_loss=0.03055, over 1421665.54 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 18:03:06,865 INFO [train.py:812] (7/8) Epoch 31, batch 2850, loss[loss=0.1792, simple_loss=0.2622, pruned_loss=0.04816, over 7210.00 frames.], tot_loss[loss=0.154, simple_loss=0.2462, pruned_loss=0.03095, over 1419352.78 frames.], batch size: 22, lr: 2.51e-04
+2022-05-15 18:04:06,662 INFO [train.py:812] (7/8) Epoch 31, batch 2900, loss[loss=0.1466, simple_loss=0.2423, pruned_loss=0.02542, over 7118.00 frames.], tot_loss[loss=0.153, simple_loss=0.2451, pruned_loss=0.03043, over 1423185.78 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 18:05:04,912 INFO [train.py:812] (7/8) Epoch 31, batch 2950, loss[loss=0.1504, simple_loss=0.2381, pruned_loss=0.03138, over 7256.00 frames.], tot_loss[loss=0.1529, simple_loss=0.245, pruned_loss=0.03037, over 1423056.18 frames.], batch size: 19, lr: 2.50e-04
+2022-05-15 18:06:03,460 INFO [train.py:812] (7/8) Epoch 31, batch 3000, loss[loss=0.1455, simple_loss=0.2442, pruned_loss=0.02336, over 7320.00 frames.], tot_loss[loss=0.1531, simple_loss=0.245, pruned_loss=0.03053, over 1423444.84 frames.], batch size: 20, lr: 2.50e-04
+2022-05-15 18:06:03,462 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 18:06:10,971 INFO [train.py:841] (7/8) Epoch 31, validation: loss=0.1541, simple_loss=0.25, pruned_loss=0.02913, over 698248.00 frames.
+2022-05-15 18:07:09,528 INFO [train.py:812] (7/8) Epoch 31, batch 3050, loss[loss=0.1284, simple_loss=0.2103, pruned_loss=0.02328, over 7021.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2453, pruned_loss=0.03068, over 1422911.89 frames.], batch size: 16, lr: 2.50e-04
+2022-05-15 18:08:09,159 INFO [train.py:812] (7/8) Epoch 31, batch 3100, loss[loss=0.156, simple_loss=0.245, pruned_loss=0.03347, over 7307.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2445, pruned_loss=0.0305, over 1426201.38 frames.], batch size: 25, lr: 2.50e-04
+2022-05-15 18:09:08,167 INFO [train.py:812] (7/8) Epoch 31, batch 3150, loss[loss=0.1273, simple_loss=0.2236, pruned_loss=0.01553, over 7008.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2446, pruned_loss=0.03059, over 1425485.45 frames.], batch size: 16, lr: 2.50e-04
+2022-05-15 18:10:05,078 INFO [train.py:812] (7/8) Epoch 31, batch 3200, loss[loss=0.1621, simple_loss=0.2594, pruned_loss=0.03235, over 7180.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2443, pruned_loss=0.03048, over 1416141.86 frames.], batch size: 23, lr: 2.50e-04
+2022-05-15 18:11:03,083 INFO [train.py:812] (7/8) Epoch 31, batch 3250, loss[loss=0.187, simple_loss=0.2953, pruned_loss=0.03937, over 7149.00 frames.], tot_loss[loss=0.153, simple_loss=0.245, pruned_loss=0.03054, over 1416040.65 frames.], batch size: 20, lr: 2.50e-04
+2022-05-15 18:12:02,673 INFO [train.py:812] (7/8) Epoch 31, batch 3300, loss[loss=0.1276, simple_loss=0.2141, pruned_loss=0.02052, over 7285.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2447, pruned_loss=0.03015, over 1422290.08 frames.], batch size: 17, lr: 2.50e-04
+2022-05-15 18:13:01,605 INFO [train.py:812] (7/8) Epoch 31, batch 3350, loss[loss=0.1433, simple_loss=0.2366, pruned_loss=0.02498, over 7223.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2447, pruned_loss=0.03044, over 1421256.06 frames.], batch size: 21, lr: 2.50e-04
+2022-05-15 18:14:00,876 INFO [train.py:812] (7/8) Epoch 31, batch 3400, loss[loss=0.1534, simple_loss=0.2437, pruned_loss=0.03154, over 7300.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2436, pruned_loss=0.03005, over 1421705.75 frames.], batch size: 25, lr: 2.50e-04
+2022-05-15 18:14:57,865 INFO [train.py:812] (7/8) Epoch 31, batch 3450, loss[loss=0.154, simple_loss=0.247, pruned_loss=0.03049, over 6516.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.03021, over 1425618.83 frames.], batch size: 38, lr: 2.50e-04
+2022-05-15 18:15:56,025 INFO [train.py:812] (7/8) Epoch 31, batch 3500, loss[loss=0.1867, simple_loss=0.2807, pruned_loss=0.04636, over 7383.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2444, pruned_loss=0.03005, over 1427370.91 frames.], batch size: 23, lr: 2.50e-04
+2022-05-15 18:16:54,992 INFO [train.py:812] (7/8) Epoch 31, batch 3550, loss[loss=0.1678, simple_loss=0.2568, pruned_loss=0.03939, over 7423.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2451, pruned_loss=0.03028, over 1428702.76 frames.], batch size: 20, lr: 2.50e-04
+2022-05-15 18:17:52,444 INFO [train.py:812] (7/8) Epoch 31, batch 3600, loss[loss=0.1645, simple_loss=0.2569, pruned_loss=0.03607, over 7293.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2465, pruned_loss=0.03103, over 1423289.98 frames.], batch size: 24, lr: 2.50e-04
+2022-05-15 18:18:51,264 INFO [train.py:812] (7/8) Epoch 31, batch 3650, loss[loss=0.1297, simple_loss=0.2181, pruned_loss=0.02068, over 7153.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2451, pruned_loss=0.03037, over 1422921.74 frames.], batch size: 17, lr: 2.50e-04
+2022-05-15 18:19:50,501 INFO [train.py:812] (7/8) Epoch 31, batch 3700, loss[loss=0.1031, simple_loss=0.1933, pruned_loss=0.006424, over 7274.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2435, pruned_loss=0.02986, over 1425374.15 frames.], batch size: 17, lr: 2.50e-04
+2022-05-15 18:20:49,323 INFO [train.py:812] (7/8) Epoch 31, batch 3750, loss[loss=0.1373, simple_loss=0.2267, pruned_loss=0.02391, over 7252.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2436, pruned_loss=0.03006, over 1423898.51 frames.], batch size: 19, lr: 2.50e-04
+2022-05-15 18:21:49,301 INFO [train.py:812] (7/8) Epoch 31, batch 3800, loss[loss=0.1326, simple_loss=0.2177, pruned_loss=0.02373, over 7261.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2436, pruned_loss=0.02998, over 1426755.69 frames.], batch size: 18, lr: 2.50e-04
+2022-05-15 18:22:47,401 INFO [train.py:812] (7/8) Epoch 31, batch 3850, loss[loss=0.1511, simple_loss=0.2383, pruned_loss=0.03194, over 7069.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2445, pruned_loss=0.03004, over 1426495.71 frames.], batch size: 18, lr: 2.50e-04
+2022-05-15 18:23:45,731 INFO [train.py:812] (7/8) Epoch 31, batch 3900, loss[loss=0.1767, simple_loss=0.2756, pruned_loss=0.03886, over 7284.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.02967, over 1430169.98 frames.], batch size: 24, lr: 2.50e-04
+2022-05-15 18:24:43,618 INFO [train.py:812] (7/8) Epoch 31, batch 3950, loss[loss=0.1749, simple_loss=0.2565, pruned_loss=0.04666, over 7362.00 frames.], tot_loss[loss=0.1523, simple_loss=0.244, pruned_loss=0.03029, over 1430370.47 frames.], batch size: 19, lr: 2.50e-04
+2022-05-15 18:25:41,725 INFO [train.py:812] (7/8) Epoch 31, batch 4000, loss[loss=0.1366, simple_loss=0.2308, pruned_loss=0.02123, over 7154.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2454, pruned_loss=0.03099, over 1427833.57 frames.], batch size: 18, lr: 2.50e-04
+2022-05-15 18:26:41,081 INFO [train.py:812] (7/8) Epoch 31, batch 4050, loss[loss=0.1679, simple_loss=0.2678, pruned_loss=0.03403, over 7313.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2457, pruned_loss=0.03104, over 1426833.41 frames.], batch size: 24, lr: 2.49e-04
+2022-05-15 18:27:40,602 INFO [train.py:812] (7/8) Epoch 31, batch 4100, loss[loss=0.1523, simple_loss=0.2466, pruned_loss=0.02899, over 7151.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2457, pruned_loss=0.03098, over 1427985.80 frames.], batch size: 19, lr: 2.49e-04
+2022-05-15 18:28:39,544 INFO [train.py:812] (7/8) Epoch 31, batch 4150, loss[loss=0.1745, simple_loss=0.2779, pruned_loss=0.03558, over 7101.00 frames.], tot_loss[loss=0.153, simple_loss=0.2452, pruned_loss=0.03033, over 1430494.26 frames.], batch size: 21, lr: 2.49e-04
+2022-05-15 18:29:38,568 INFO [train.py:812] (7/8) Epoch 31, batch 4200, loss[loss=0.1224, simple_loss=0.204, pruned_loss=0.02044, over 6804.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.03002, over 1432945.84 frames.], batch size: 15, lr: 2.49e-04
+2022-05-15 18:30:36,518 INFO [train.py:812] (7/8) Epoch 31, batch 4250, loss[loss=0.187, simple_loss=0.2934, pruned_loss=0.04027, over 7210.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2444, pruned_loss=0.0302, over 1429361.53 frames.], batch size: 26, lr: 2.49e-04
+2022-05-15 18:31:35,783 INFO [train.py:812] (7/8) Epoch 31, batch 4300, loss[loss=0.1799, simple_loss=0.2663, pruned_loss=0.04679, over 7307.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2433, pruned_loss=0.02977, over 1431553.31 frames.], batch size: 24, lr: 2.49e-04
+2022-05-15 18:32:33,414 INFO [train.py:812] (7/8) Epoch 31, batch 4350, loss[loss=0.142, simple_loss=0.2396, pruned_loss=0.02224, over 7116.00 frames.], tot_loss[loss=0.152, simple_loss=0.2438, pruned_loss=0.03007, over 1422569.02 frames.], batch size: 21, lr: 2.49e-04
+2022-05-15 18:33:32,245 INFO [train.py:812] (7/8) Epoch 31, batch 4400, loss[loss=0.1863, simple_loss=0.2777, pruned_loss=0.04741, over 7106.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2441, pruned_loss=0.03033, over 1412444.15 frames.], batch size: 21, lr: 2.49e-04
+2022-05-15 18:34:30,899 INFO [train.py:812] (7/8) Epoch 31, batch 4450, loss[loss=0.1406, simple_loss=0.2381, pruned_loss=0.02155, over 6536.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03069, over 1411944.90 frames.], batch size: 38, lr: 2.49e-04
+2022-05-15 18:35:30,068 INFO [train.py:812] (7/8) Epoch 31, batch 4500, loss[loss=0.1406, simple_loss=0.2374, pruned_loss=0.02196, over 6412.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2456, pruned_loss=0.03134, over 1387672.32 frames.], batch size: 38, lr: 2.49e-04
+2022-05-15 18:36:28,956 INFO [train.py:812] (7/8) Epoch 31, batch 4550, loss[loss=0.1748, simple_loss=0.2665, pruned_loss=0.04152, over 5103.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2471, pruned_loss=0.03218, over 1357850.00 frames.], batch size: 54, lr: 2.49e-04
+2022-05-15 18:37:36,646 INFO [train.py:812] (7/8) Epoch 32, batch 0, loss[loss=0.1702, simple_loss=0.2666, pruned_loss=0.03686, over 4804.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2666, pruned_loss=0.03686, over 4804.00 frames.], batch size: 52, lr: 2.45e-04
+2022-05-15 18:38:34,892 INFO [train.py:812] (7/8) Epoch 32, batch 50, loss[loss=0.1595, simple_loss=0.2506, pruned_loss=0.03421, over 6420.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2522, pruned_loss=0.03127, over 319227.21 frames.], batch size: 38, lr: 2.45e-04
+2022-05-15 18:39:33,424 INFO [train.py:812] (7/8) Epoch 32, batch 100, loss[loss=0.1515, simple_loss=0.2499, pruned_loss=0.02652, over 7282.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2497, pruned_loss=0.03151, over 566328.33 frames.], batch size: 25, lr: 2.45e-04
+2022-05-15 18:40:32,490 INFO [train.py:812] (7/8) Epoch 32, batch 150, loss[loss=0.1507, simple_loss=0.2514, pruned_loss=0.02501, over 7200.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2479, pruned_loss=0.03121, over 758268.19 frames.], batch size: 26, lr: 2.45e-04
+2022-05-15 18:41:31,083 INFO [train.py:812] (7/8) Epoch 32, batch 200, loss[loss=0.1425, simple_loss=0.2272, pruned_loss=0.02887, over 6999.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2458, pruned_loss=0.03057, over 903230.52 frames.], batch size: 16, lr: 2.45e-04
+2022-05-15 18:42:29,434 INFO [train.py:812] (7/8) Epoch 32, batch 250, loss[loss=0.1548, simple_loss=0.2538, pruned_loss=0.02792, over 7274.00 frames.], tot_loss[loss=0.1535, simple_loss=0.246, pruned_loss=0.03053, over 1022916.48 frames.], batch size: 24, lr: 2.45e-04
+2022-05-15 18:43:28,947 INFO [train.py:812] (7/8) Epoch 32, batch 300, loss[loss=0.1664, simple_loss=0.2577, pruned_loss=0.03753, over 7284.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2464, pruned_loss=0.03061, over 1113481.60 frames.], batch size: 24, lr: 2.45e-04
+2022-05-15 18:44:28,381 INFO [train.py:812] (7/8) Epoch 32, batch 350, loss[loss=0.1533, simple_loss=0.2511, pruned_loss=0.0278, over 7094.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2453, pruned_loss=0.03054, over 1181741.05 frames.], batch size: 28, lr: 2.45e-04
+2022-05-15 18:45:27,077 INFO [train.py:812] (7/8) Epoch 32, batch 400, loss[loss=0.1719, simple_loss=0.2745, pruned_loss=0.03459, over 7187.00 frames.], tot_loss[loss=0.153, simple_loss=0.2453, pruned_loss=0.03031, over 1236599.71 frames.], batch size: 26, lr: 2.45e-04
+2022-05-15 18:46:25,917 INFO [train.py:812] (7/8) Epoch 32, batch 450, loss[loss=0.1529, simple_loss=0.2442, pruned_loss=0.03076, over 7318.00 frames.], tot_loss[loss=0.152, simple_loss=0.2443, pruned_loss=0.02988, over 1277434.39 frames.], batch size: 21, lr: 2.45e-04
+2022-05-15 18:47:25,100 INFO [train.py:812] (7/8) Epoch 32, batch 500, loss[loss=0.1482, simple_loss=0.2492, pruned_loss=0.02355, over 7334.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02983, over 1313002.71 frames.], batch size: 22, lr: 2.45e-04
+2022-05-15 18:48:23,096 INFO [train.py:812] (7/8) Epoch 32, batch 550, loss[loss=0.165, simple_loss=0.2694, pruned_loss=0.03032, over 7330.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2429, pruned_loss=0.02943, over 1341697.24 frames.], batch size: 22, lr: 2.45e-04
+2022-05-15 18:49:22,869 INFO [train.py:812] (7/8) Epoch 32, batch 600, loss[loss=0.1459, simple_loss=0.236, pruned_loss=0.02788, over 7142.00 frames.], tot_loss[loss=0.1509, simple_loss=0.243, pruned_loss=0.02937, over 1364062.58 frames.], batch size: 17, lr: 2.45e-04
+2022-05-15 18:50:21,239 INFO [train.py:812] (7/8) Epoch 32, batch 650, loss[loss=0.1255, simple_loss=0.2094, pruned_loss=0.02082, over 6988.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2433, pruned_loss=0.02955, over 1379321.55 frames.], batch size: 16, lr: 2.45e-04
+2022-05-15 18:51:18,835 INFO [train.py:812] (7/8) Epoch 32, batch 700, loss[loss=0.1519, simple_loss=0.2427, pruned_loss=0.03059, over 7186.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2431, pruned_loss=0.02955, over 1388537.90 frames.], batch size: 23, lr: 2.45e-04
+2022-05-15 18:52:17,804 INFO [train.py:812] (7/8) Epoch 32, batch 750, loss[loss=0.1611, simple_loss=0.2551, pruned_loss=0.03359, over 7105.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2433, pruned_loss=0.02997, over 1397021.40 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 18:53:17,326 INFO [train.py:812] (7/8) Epoch 32, batch 800, loss[loss=0.1491, simple_loss=0.2338, pruned_loss=0.03221, over 7276.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2431, pruned_loss=0.02972, over 1401466.01 frames.], batch size: 18, lr: 2.44e-04
+2022-05-15 18:54:15,845 INFO [train.py:812] (7/8) Epoch 32, batch 850, loss[loss=0.1526, simple_loss=0.2527, pruned_loss=0.02623, over 7284.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.02948, over 1409205.03 frames.], batch size: 25, lr: 2.44e-04
+2022-05-15 18:55:14,234 INFO [train.py:812] (7/8) Epoch 32, batch 900, loss[loss=0.1528, simple_loss=0.2536, pruned_loss=0.02595, over 7326.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2444, pruned_loss=0.02954, over 1411611.37 frames.], batch size: 22, lr: 2.44e-04
+2022-05-15 18:56:22,080 INFO [train.py:812] (7/8) Epoch 32, batch 950, loss[loss=0.1218, simple_loss=0.1993, pruned_loss=0.02218, over 7199.00 frames.], tot_loss[loss=0.151, simple_loss=0.2432, pruned_loss=0.02944, over 1413662.60 frames.], batch size: 16, lr: 2.44e-04
+2022-05-15 18:57:31,066 INFO [train.py:812] (7/8) Epoch 32, batch 1000, loss[loss=0.1376, simple_loss=0.2333, pruned_loss=0.02098, over 7420.00 frames.], tot_loss[loss=0.1508, simple_loss=0.243, pruned_loss=0.02931, over 1417403.99 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 18:58:30,379 INFO [train.py:812] (7/8) Epoch 32, batch 1050, loss[loss=0.1547, simple_loss=0.2591, pruned_loss=0.02517, over 7229.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2426, pruned_loss=0.02925, over 1420913.78 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 18:59:29,302 INFO [train.py:812] (7/8) Epoch 32, batch 1100, loss[loss=0.1584, simple_loss=0.2495, pruned_loss=0.03368, over 7204.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2419, pruned_loss=0.02917, over 1419178.03 frames.], batch size: 22, lr: 2.44e-04
+2022-05-15 19:00:36,754 INFO [train.py:812] (7/8) Epoch 32, batch 1150, loss[loss=0.1538, simple_loss=0.2445, pruned_loss=0.03153, over 7144.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2432, pruned_loss=0.02966, over 1422670.09 frames.], batch size: 17, lr: 2.44e-04
+2022-05-15 19:01:36,502 INFO [train.py:812] (7/8) Epoch 32, batch 1200, loss[loss=0.1516, simple_loss=0.2545, pruned_loss=0.02438, over 7422.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2424, pruned_loss=0.02945, over 1425000.41 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 19:02:45,199 INFO [train.py:812] (7/8) Epoch 32, batch 1250, loss[loss=0.1649, simple_loss=0.269, pruned_loss=0.03044, over 7198.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2434, pruned_loss=0.03022, over 1418713.23 frames.], batch size: 23, lr: 2.44e-04
+2022-05-15 19:03:53,745 INFO [train.py:812] (7/8) Epoch 32, batch 1300, loss[loss=0.1663, simple_loss=0.2698, pruned_loss=0.03145, over 7143.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2435, pruned_loss=0.03002, over 1423958.09 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:05:00,955 INFO [train.py:812] (7/8) Epoch 32, batch 1350, loss[loss=0.1532, simple_loss=0.2449, pruned_loss=0.03077, over 7331.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.03016, over 1421275.86 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:05:59,750 INFO [train.py:812] (7/8) Epoch 32, batch 1400, loss[loss=0.1303, simple_loss=0.2188, pruned_loss=0.02095, over 7246.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2429, pruned_loss=0.02972, over 1421333.84 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:06:57,278 INFO [train.py:812] (7/8) Epoch 32, batch 1450, loss[loss=0.1323, simple_loss=0.2242, pruned_loss=0.02015, over 7340.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2436, pruned_loss=0.03006, over 1423750.47 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:08:05,757 INFO [train.py:812] (7/8) Epoch 32, batch 1500, loss[loss=0.166, simple_loss=0.248, pruned_loss=0.04197, over 5441.00 frames.], tot_loss[loss=0.151, simple_loss=0.2431, pruned_loss=0.02946, over 1423113.66 frames.], batch size: 52, lr: 2.44e-04
+2022-05-15 19:09:04,142 INFO [train.py:812] (7/8) Epoch 32, batch 1550, loss[loss=0.1355, simple_loss=0.2109, pruned_loss=0.03003, over 7405.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2429, pruned_loss=0.02942, over 1422443.97 frames.], batch size: 18, lr: 2.44e-04
+2022-05-15 19:10:03,435 INFO [train.py:812] (7/8) Epoch 32, batch 1600, loss[loss=0.1531, simple_loss=0.2431, pruned_loss=0.03151, over 7195.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2431, pruned_loss=0.02978, over 1418413.60 frames.], batch size: 23, lr: 2.44e-04
+2022-05-15 19:11:01,517 INFO [train.py:812] (7/8) Epoch 32, batch 1650, loss[loss=0.1448, simple_loss=0.2512, pruned_loss=0.01921, over 7406.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2444, pruned_loss=0.03015, over 1417913.46 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 19:12:00,710 INFO [train.py:812] (7/8) Epoch 32, batch 1700, loss[loss=0.1412, simple_loss=0.2411, pruned_loss=0.02068, over 7110.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2446, pruned_loss=0.03038, over 1412896.95 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 19:12:59,721 INFO [train.py:812] (7/8) Epoch 32, batch 1750, loss[loss=0.1906, simple_loss=0.275, pruned_loss=0.05316, over 5200.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2444, pruned_loss=0.0303, over 1410321.44 frames.], batch size: 52, lr: 2.44e-04
+2022-05-15 19:14:04,622 INFO [train.py:812] (7/8) Epoch 32, batch 1800, loss[loss=0.144, simple_loss=0.2315, pruned_loss=0.02831, over 7229.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.0303, over 1412012.56 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:15:03,174 INFO [train.py:812] (7/8) Epoch 32, batch 1850, loss[loss=0.1296, simple_loss=0.2114, pruned_loss=0.02386, over 6992.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2454, pruned_loss=0.03044, over 1406833.52 frames.], batch size: 16, lr: 2.44e-04
+2022-05-15 19:16:02,098 INFO [train.py:812] (7/8) Epoch 32, batch 1900, loss[loss=0.1347, simple_loss=0.2184, pruned_loss=0.02552, over 7362.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.0302, over 1413670.48 frames.], batch size: 19, lr: 2.44e-04
+2022-05-15 19:17:00,609 INFO [train.py:812] (7/8) Epoch 32, batch 1950, loss[loss=0.147, simple_loss=0.2473, pruned_loss=0.0234, over 7361.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2429, pruned_loss=0.02983, over 1419302.55 frames.], batch size: 19, lr: 2.43e-04
+2022-05-15 19:18:00,449 INFO [train.py:812] (7/8) Epoch 32, batch 2000, loss[loss=0.1276, simple_loss=0.2158, pruned_loss=0.01969, over 7278.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2434, pruned_loss=0.02992, over 1420232.65 frames.], batch size: 18, lr: 2.43e-04
+2022-05-15 19:18:57,520 INFO [train.py:812] (7/8) Epoch 32, batch 2050, loss[loss=0.1478, simple_loss=0.2386, pruned_loss=0.02854, over 7153.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2429, pruned_loss=0.02989, over 1416875.48 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:19:56,228 INFO [train.py:812] (7/8) Epoch 32, batch 2100, loss[loss=0.1377, simple_loss=0.22, pruned_loss=0.02771, over 7189.00 frames.], tot_loss[loss=0.1521, simple_loss=0.244, pruned_loss=0.03009, over 1417234.50 frames.], batch size: 16, lr: 2.43e-04
+2022-05-15 19:20:54,984 INFO [train.py:812] (7/8) Epoch 32, batch 2150, loss[loss=0.1789, simple_loss=0.2842, pruned_loss=0.03677, over 7213.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.03003, over 1420751.43 frames.], batch size: 21, lr: 2.43e-04
+2022-05-15 19:21:53,694 INFO [train.py:812] (7/8) Epoch 32, batch 2200, loss[loss=0.1688, simple_loss=0.2632, pruned_loss=0.03724, over 7183.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2436, pruned_loss=0.02968, over 1423488.09 frames.], batch size: 26, lr: 2.43e-04
+2022-05-15 19:22:52,765 INFO [train.py:812] (7/8) Epoch 32, batch 2250, loss[loss=0.1404, simple_loss=0.2308, pruned_loss=0.02497, over 7069.00 frames.], tot_loss[loss=0.1516, simple_loss=0.244, pruned_loss=0.02962, over 1424488.91 frames.], batch size: 18, lr: 2.43e-04
+2022-05-15 19:23:52,323 INFO [train.py:812] (7/8) Epoch 32, batch 2300, loss[loss=0.1639, simple_loss=0.2621, pruned_loss=0.03286, over 7343.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02955, over 1422382.47 frames.], batch size: 22, lr: 2.43e-04
+2022-05-15 19:24:49,730 INFO [train.py:812] (7/8) Epoch 32, batch 2350, loss[loss=0.1345, simple_loss=0.2146, pruned_loss=0.02718, over 7268.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2447, pruned_loss=0.02988, over 1425916.11 frames.], batch size: 17, lr: 2.43e-04
+2022-05-15 19:25:48,458 INFO [train.py:812] (7/8) Epoch 32, batch 2400, loss[loss=0.1428, simple_loss=0.2389, pruned_loss=0.02331, over 7327.00 frames.], tot_loss[loss=0.1527, simple_loss=0.245, pruned_loss=0.03021, over 1421576.08 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:26:47,734 INFO [train.py:812] (7/8) Epoch 32, batch 2450, loss[loss=0.1846, simple_loss=0.2862, pruned_loss=0.04152, over 7176.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2455, pruned_loss=0.03052, over 1423304.13 frames.], batch size: 26, lr: 2.43e-04
+2022-05-15 19:27:46,293 INFO [train.py:812] (7/8) Epoch 32, batch 2500, loss[loss=0.1364, simple_loss=0.2244, pruned_loss=0.0242, over 7301.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2451, pruned_loss=0.03036, over 1426031.23 frames.], batch size: 17, lr: 2.43e-04
+2022-05-15 19:28:44,171 INFO [train.py:812] (7/8) Epoch 32, batch 2550, loss[loss=0.1414, simple_loss=0.243, pruned_loss=0.01984, over 7322.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2448, pruned_loss=0.03015, over 1423567.64 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:29:41,357 INFO [train.py:812] (7/8) Epoch 32, batch 2600, loss[loss=0.1127, simple_loss=0.1974, pruned_loss=0.01403, over 7137.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2449, pruned_loss=0.03007, over 1421656.96 frames.], batch size: 17, lr: 2.43e-04
+2022-05-15 19:30:39,827 INFO [train.py:812] (7/8) Epoch 32, batch 2650, loss[loss=0.1575, simple_loss=0.2491, pruned_loss=0.03297, over 7180.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2437, pruned_loss=0.02943, over 1423698.51 frames.], batch size: 26, lr: 2.43e-04
+2022-05-15 19:31:39,444 INFO [train.py:812] (7/8) Epoch 32, batch 2700, loss[loss=0.1331, simple_loss=0.2235, pruned_loss=0.02133, over 7331.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02951, over 1421913.31 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:32:37,318 INFO [train.py:812] (7/8) Epoch 32, batch 2750, loss[loss=0.1591, simple_loss=0.2517, pruned_loss=0.03322, over 7159.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.02941, over 1423762.07 frames.], batch size: 28, lr: 2.43e-04
+2022-05-15 19:33:35,477 INFO [train.py:812] (7/8) Epoch 32, batch 2800, loss[loss=0.1312, simple_loss=0.2158, pruned_loss=0.0233, over 7400.00 frames.], tot_loss[loss=0.151, simple_loss=0.2429, pruned_loss=0.02953, over 1422951.04 frames.], batch size: 18, lr: 2.43e-04
+2022-05-15 19:34:34,373 INFO [train.py:812] (7/8) Epoch 32, batch 2850, loss[loss=0.1557, simple_loss=0.2621, pruned_loss=0.02465, over 6264.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2439, pruned_loss=0.02995, over 1420077.45 frames.], batch size: 37, lr: 2.43e-04
+2022-05-15 19:35:32,686 INFO [train.py:812] (7/8) Epoch 32, batch 2900, loss[loss=0.132, simple_loss=0.2286, pruned_loss=0.01774, over 7233.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2454, pruned_loss=0.03054, over 1424090.60 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:36:30,957 INFO [train.py:812] (7/8) Epoch 32, batch 2950, loss[loss=0.1499, simple_loss=0.2426, pruned_loss=0.02865, over 7204.00 frames.], tot_loss[loss=0.153, simple_loss=0.2453, pruned_loss=0.03039, over 1417535.68 frames.], batch size: 23, lr: 2.43e-04
+2022-05-15 19:37:29,706 INFO [train.py:812] (7/8) Epoch 32, batch 3000, loss[loss=0.1642, simple_loss=0.266, pruned_loss=0.03119, over 7427.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2459, pruned_loss=0.03072, over 1418209.19 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:37:29,707 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 19:37:37,094 INFO [train.py:841] (7/8) Epoch 32, validation: loss=0.1532, simple_loss=0.2494, pruned_loss=0.02852, over 698248.00 frames.
+2022-05-15 19:38:35,495 INFO [train.py:812] (7/8) Epoch 32, batch 3050, loss[loss=0.1517, simple_loss=0.2529, pruned_loss=0.02519, over 7305.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2456, pruned_loss=0.03072, over 1422404.33 frames.], batch size: 25, lr: 2.43e-04
+2022-05-15 19:39:34,752 INFO [train.py:812] (7/8) Epoch 32, batch 3100, loss[loss=0.1784, simple_loss=0.2711, pruned_loss=0.04279, over 7090.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2463, pruned_loss=0.03132, over 1425731.29 frames.], batch size: 28, lr: 2.42e-04
+2022-05-15 19:40:34,150 INFO [train.py:812] (7/8) Epoch 32, batch 3150, loss[loss=0.1431, simple_loss=0.2202, pruned_loss=0.033, over 7277.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2455, pruned_loss=0.03142, over 1423434.01 frames.], batch size: 17, lr: 2.42e-04
+2022-05-15 19:41:32,556 INFO [train.py:812] (7/8) Epoch 32, batch 3200, loss[loss=0.1492, simple_loss=0.25, pruned_loss=0.02424, over 7111.00 frames.], tot_loss[loss=0.154, simple_loss=0.2458, pruned_loss=0.03115, over 1426699.50 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 19:42:31,650 INFO [train.py:812] (7/8) Epoch 32, batch 3250, loss[loss=0.1486, simple_loss=0.2446, pruned_loss=0.02632, over 7332.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2456, pruned_loss=0.03071, over 1427837.97 frames.], batch size: 22, lr: 2.42e-04
+2022-05-15 19:43:31,269 INFO [train.py:812] (7/8) Epoch 32, batch 3300, loss[loss=0.1478, simple_loss=0.2344, pruned_loss=0.03061, over 7431.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2447, pruned_loss=0.03031, over 1424156.78 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:44:30,454 INFO [train.py:812] (7/8) Epoch 32, batch 3350, loss[loss=0.1568, simple_loss=0.2532, pruned_loss=0.03022, over 7337.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2428, pruned_loss=0.02971, over 1425237.52 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 19:45:29,633 INFO [train.py:812] (7/8) Epoch 32, batch 3400, loss[loss=0.1591, simple_loss=0.2526, pruned_loss=0.03283, over 7321.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2444, pruned_loss=0.03024, over 1421791.85 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:46:27,594 INFO [train.py:812] (7/8) Epoch 32, batch 3450, loss[loss=0.1712, simple_loss=0.2615, pruned_loss=0.0404, over 7204.00 frames.], tot_loss[loss=0.1537, simple_loss=0.246, pruned_loss=0.03075, over 1424854.62 frames.], batch size: 22, lr: 2.42e-04
+2022-05-15 19:47:26,363 INFO [train.py:812] (7/8) Epoch 32, batch 3500, loss[loss=0.154, simple_loss=0.2467, pruned_loss=0.03059, over 7296.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2463, pruned_loss=0.03076, over 1428308.37 frames.], batch size: 24, lr: 2.42e-04
+2022-05-15 19:48:25,231 INFO [train.py:812] (7/8) Epoch 32, batch 3550, loss[loss=0.1628, simple_loss=0.2592, pruned_loss=0.03326, over 7376.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2454, pruned_loss=0.03061, over 1430895.77 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:49:24,704 INFO [train.py:812] (7/8) Epoch 32, batch 3600, loss[loss=0.1446, simple_loss=0.2495, pruned_loss=0.01989, over 6376.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2453, pruned_loss=0.03047, over 1428051.58 frames.], batch size: 38, lr: 2.42e-04
+2022-05-15 19:50:24,047 INFO [train.py:812] (7/8) Epoch 32, batch 3650, loss[loss=0.1487, simple_loss=0.2459, pruned_loss=0.02578, over 7225.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2455, pruned_loss=0.03033, over 1428780.29 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:51:24,214 INFO [train.py:812] (7/8) Epoch 32, batch 3700, loss[loss=0.1299, simple_loss=0.2132, pruned_loss=0.02328, over 7121.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2447, pruned_loss=0.03041, over 1429999.40 frames.], batch size: 17, lr: 2.42e-04
+2022-05-15 19:52:22,820 INFO [train.py:812] (7/8) Epoch 32, batch 3750, loss[loss=0.1543, simple_loss=0.2484, pruned_loss=0.03016, over 7203.00 frames.], tot_loss[loss=0.153, simple_loss=0.2449, pruned_loss=0.03052, over 1423833.86 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:53:21,641 INFO [train.py:812] (7/8) Epoch 32, batch 3800, loss[loss=0.1374, simple_loss=0.2335, pruned_loss=0.02071, over 7366.00 frames.], tot_loss[loss=0.1519, simple_loss=0.244, pruned_loss=0.02992, over 1424984.99 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:54:19,367 INFO [train.py:812] (7/8) Epoch 32, batch 3850, loss[loss=0.1537, simple_loss=0.2564, pruned_loss=0.02553, over 7419.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.0297, over 1427455.45 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:55:27,960 INFO [train.py:812] (7/8) Epoch 32, batch 3900, loss[loss=0.1445, simple_loss=0.2337, pruned_loss=0.02764, over 7168.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2434, pruned_loss=0.02957, over 1428526.21 frames.], batch size: 18, lr: 2.42e-04
+2022-05-15 19:56:25,330 INFO [train.py:812] (7/8) Epoch 32, batch 3950, loss[loss=0.1572, simple_loss=0.2544, pruned_loss=0.02997, over 7214.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2441, pruned_loss=0.02989, over 1423800.73 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 19:57:24,506 INFO [train.py:812] (7/8) Epoch 32, batch 4000, loss[loss=0.1385, simple_loss=0.2236, pruned_loss=0.02673, over 7408.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.03016, over 1420902.09 frames.], batch size: 18, lr: 2.42e-04
+2022-05-15 19:58:22,829 INFO [train.py:812] (7/8) Epoch 32, batch 4050, loss[loss=0.1871, simple_loss=0.2879, pruned_loss=0.04318, over 7387.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2439, pruned_loss=0.03012, over 1419831.72 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:59:20,931 INFO [train.py:812] (7/8) Epoch 32, batch 4100, loss[loss=0.1677, simple_loss=0.2572, pruned_loss=0.03904, over 7202.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.02998, over 1417381.50 frames.], batch size: 22, lr: 2.42e-04
+2022-05-15 20:00:19,831 INFO [train.py:812] (7/8) Epoch 32, batch 4150, loss[loss=0.1708, simple_loss=0.2765, pruned_loss=0.03258, over 7226.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2437, pruned_loss=0.02993, over 1421723.39 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 20:01:19,546 INFO [train.py:812] (7/8) Epoch 32, batch 4200, loss[loss=0.1347, simple_loss=0.2252, pruned_loss=0.02208, over 7327.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2426, pruned_loss=0.0296, over 1421229.88 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 20:02:17,842 INFO [train.py:812] (7/8) Epoch 32, batch 4250, loss[loss=0.1495, simple_loss=0.2374, pruned_loss=0.03074, over 7255.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2432, pruned_loss=0.03008, over 1420001.98 frames.], batch size: 19, lr: 2.42e-04
+2022-05-15 20:03:17,426 INFO [train.py:812] (7/8) Epoch 32, batch 4300, loss[loss=0.1261, simple_loss=0.2165, pruned_loss=0.0179, over 7433.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2421, pruned_loss=0.02977, over 1419221.66 frames.], batch size: 18, lr: 2.42e-04
+2022-05-15 20:04:16,105 INFO [train.py:812] (7/8) Epoch 32, batch 4350, loss[loss=0.1563, simple_loss=0.2501, pruned_loss=0.03129, over 7160.00 frames.], tot_loss[loss=0.152, simple_loss=0.2435, pruned_loss=0.03029, over 1419847.22 frames.], batch size: 18, lr: 2.41e-04
+2022-05-15 20:05:14,968 INFO [train.py:812] (7/8) Epoch 32, batch 4400, loss[loss=0.1658, simple_loss=0.2536, pruned_loss=0.03894, over 7290.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2444, pruned_loss=0.03074, over 1405826.02 frames.], batch size: 25, lr: 2.41e-04
+2022-05-15 20:06:12,565 INFO [train.py:812] (7/8) Epoch 32, batch 4450, loss[loss=0.1157, simple_loss=0.2014, pruned_loss=0.01504, over 6793.00 frames.], tot_loss[loss=0.1528, simple_loss=0.244, pruned_loss=0.03082, over 1403214.27 frames.], batch size: 15, lr: 2.41e-04
+2022-05-15 20:07:11,405 INFO [train.py:812] (7/8) Epoch 32, batch 4500, loss[loss=0.1409, simple_loss=0.2355, pruned_loss=0.02313, over 6845.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2447, pruned_loss=0.03104, over 1395018.53 frames.], batch size: 31, lr: 2.41e-04
+2022-05-15 20:08:09,901 INFO [train.py:812] (7/8) Epoch 32, batch 4550, loss[loss=0.1701, simple_loss=0.2605, pruned_loss=0.03983, over 4806.00 frames.], tot_loss[loss=0.154, simple_loss=0.2446, pruned_loss=0.03174, over 1355340.24 frames.], batch size: 52, lr: 2.41e-04
+2022-05-15 20:09:17,621 INFO [train.py:812] (7/8) Epoch 33, batch 0, loss[loss=0.1437, simple_loss=0.2402, pruned_loss=0.02357, over 6677.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2402, pruned_loss=0.02357, over 6677.00 frames.], batch size: 31, lr: 2.38e-04
+2022-05-15 20:10:15,667 INFO [train.py:812] (7/8) Epoch 33, batch 50, loss[loss=0.1657, simple_loss=0.2571, pruned_loss=0.03712, over 4837.00 frames.], tot_loss[loss=0.1517, simple_loss=0.245, pruned_loss=0.02924, over 313986.19 frames.], batch size: 52, lr: 2.38e-04
+2022-05-15 20:11:14,531 INFO [train.py:812] (7/8) Epoch 33, batch 100, loss[loss=0.1599, simple_loss=0.2606, pruned_loss=0.02959, over 6476.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2447, pruned_loss=0.02924, over 559218.92 frames.], batch size: 38, lr: 2.38e-04
+2022-05-15 20:12:13,189 INFO [train.py:812] (7/8) Epoch 33, batch 150, loss[loss=0.1652, simple_loss=0.2618, pruned_loss=0.03433, over 7189.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2452, pruned_loss=0.02926, over 751996.92 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:13:12,830 INFO [train.py:812] (7/8) Epoch 33, batch 200, loss[loss=0.1626, simple_loss=0.247, pruned_loss=0.03916, over 7007.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2447, pruned_loss=0.03004, over 895736.83 frames.], batch size: 16, lr: 2.37e-04
+2022-05-15 20:14:10,219 INFO [train.py:812] (7/8) Epoch 33, batch 250, loss[loss=0.1551, simple_loss=0.2434, pruned_loss=0.03343, over 7229.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2452, pruned_loss=0.03026, over 1010757.62 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:15:09,002 INFO [train.py:812] (7/8) Epoch 33, batch 300, loss[loss=0.1733, simple_loss=0.2815, pruned_loss=0.03253, over 6911.00 frames.], tot_loss[loss=0.1545, simple_loss=0.247, pruned_loss=0.03102, over 1094276.25 frames.], batch size: 32, lr: 2.37e-04
+2022-05-15 20:16:07,559 INFO [train.py:812] (7/8) Epoch 33, batch 350, loss[loss=0.1295, simple_loss=0.2195, pruned_loss=0.01974, over 7398.00 frames.], tot_loss[loss=0.154, simple_loss=0.2462, pruned_loss=0.03084, over 1164004.26 frames.], batch size: 18, lr: 2.37e-04
+2022-05-15 20:17:07,125 INFO [train.py:812] (7/8) Epoch 33, batch 400, loss[loss=0.1361, simple_loss=0.2318, pruned_loss=0.02016, over 7438.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2443, pruned_loss=0.03032, over 1220725.62 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:18:06,470 INFO [train.py:812] (7/8) Epoch 33, batch 450, loss[loss=0.1606, simple_loss=0.2549, pruned_loss=0.03309, over 6898.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2434, pruned_loss=0.03021, over 1263132.32 frames.], batch size: 31, lr: 2.37e-04
+2022-05-15 20:19:06,098 INFO [train.py:812] (7/8) Epoch 33, batch 500, loss[loss=0.1671, simple_loss=0.2532, pruned_loss=0.0405, over 7205.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2448, pruned_loss=0.03066, over 1300995.87 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:20:04,306 INFO [train.py:812] (7/8) Epoch 33, batch 550, loss[loss=0.1456, simple_loss=0.2415, pruned_loss=0.02485, over 7323.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2459, pruned_loss=0.03052, over 1329266.83 frames.], batch size: 21, lr: 2.37e-04
+2022-05-15 20:21:03,134 INFO [train.py:812] (7/8) Epoch 33, batch 600, loss[loss=0.1585, simple_loss=0.2514, pruned_loss=0.0328, over 7270.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2457, pruned_loss=0.03049, over 1346925.76 frames.], batch size: 24, lr: 2.37e-04
+2022-05-15 20:22:00,756 INFO [train.py:812] (7/8) Epoch 33, batch 650, loss[loss=0.1697, simple_loss=0.2712, pruned_loss=0.03405, over 7204.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2457, pruned_loss=0.0309, over 1364427.23 frames.], batch size: 26, lr: 2.37e-04
+2022-05-15 20:23:00,281 INFO [train.py:812] (7/8) Epoch 33, batch 700, loss[loss=0.142, simple_loss=0.2217, pruned_loss=0.03115, over 7125.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.03077, over 1375136.92 frames.], batch size: 17, lr: 2.37e-04
+2022-05-15 20:23:58,673 INFO [train.py:812] (7/8) Epoch 33, batch 750, loss[loss=0.1846, simple_loss=0.2836, pruned_loss=0.04279, over 7215.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2451, pruned_loss=0.03066, over 1380719.15 frames.], batch size: 21, lr: 2.37e-04
+2022-05-15 20:24:57,941 INFO [train.py:812] (7/8) Epoch 33, batch 800, loss[loss=0.1592, simple_loss=0.254, pruned_loss=0.03218, over 7429.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2439, pruned_loss=0.03031, over 1392812.06 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:25:55,914 INFO [train.py:812] (7/8) Epoch 33, batch 850, loss[loss=0.1428, simple_loss=0.2395, pruned_loss=0.02301, over 7363.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2447, pruned_loss=0.03041, over 1400025.83 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:26:54,569 INFO [train.py:812] (7/8) Epoch 33, batch 900, loss[loss=0.1833, simple_loss=0.2755, pruned_loss=0.04554, over 7204.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2442, pruned_loss=0.0305, over 1409995.39 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:27:51,855 INFO [train.py:812] (7/8) Epoch 33, batch 950, loss[loss=0.1171, simple_loss=0.2048, pruned_loss=0.01473, over 7426.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2445, pruned_loss=0.03046, over 1414402.43 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:28:51,375 INFO [train.py:812] (7/8) Epoch 33, batch 1000, loss[loss=0.1704, simple_loss=0.2669, pruned_loss=0.03694, over 7189.00 frames.], tot_loss[loss=0.152, simple_loss=0.2435, pruned_loss=0.03029, over 1414033.72 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:29:49,417 INFO [train.py:812] (7/8) Epoch 33, batch 1050, loss[loss=0.1508, simple_loss=0.2465, pruned_loss=0.02755, over 7036.00 frames.], tot_loss[loss=0.152, simple_loss=0.2439, pruned_loss=0.03009, over 1413355.26 frames.], batch size: 28, lr: 2.37e-04
+2022-05-15 20:30:48,574 INFO [train.py:812] (7/8) Epoch 33, batch 1100, loss[loss=0.1657, simple_loss=0.2655, pruned_loss=0.03296, over 7279.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2441, pruned_loss=0.03025, over 1418150.18 frames.], batch size: 24, lr: 2.37e-04
+2022-05-15 20:31:47,048 INFO [train.py:812] (7/8) Epoch 33, batch 1150, loss[loss=0.1413, simple_loss=0.2394, pruned_loss=0.02159, over 7201.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.02953, over 1420601.29 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:32:51,463 INFO [train.py:812] (7/8) Epoch 33, batch 1200, loss[loss=0.1845, simple_loss=0.2884, pruned_loss=0.0403, over 7242.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2441, pruned_loss=0.02952, over 1423538.07 frames.], batch size: 26, lr: 2.37e-04
+2022-05-15 20:33:50,456 INFO [train.py:812] (7/8) Epoch 33, batch 1250, loss[loss=0.1563, simple_loss=0.2549, pruned_loss=0.0288, over 6595.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2439, pruned_loss=0.02957, over 1422342.45 frames.], batch size: 38, lr: 2.37e-04
+2022-05-15 20:34:50,220 INFO [train.py:812] (7/8) Epoch 33, batch 1300, loss[loss=0.1333, simple_loss=0.2382, pruned_loss=0.01425, over 7214.00 frames.], tot_loss[loss=0.1511, simple_loss=0.243, pruned_loss=0.0296, over 1422927.67 frames.], batch size: 21, lr: 2.37e-04
+2022-05-15 20:35:49,537 INFO [train.py:812] (7/8) Epoch 33, batch 1350, loss[loss=0.1406, simple_loss=0.2298, pruned_loss=0.02566, over 7282.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.0296, over 1421618.17 frames.], batch size: 17, lr: 2.37e-04
+2022-05-15 20:36:48,931 INFO [train.py:812] (7/8) Epoch 33, batch 1400, loss[loss=0.1586, simple_loss=0.2534, pruned_loss=0.03195, over 7139.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2432, pruned_loss=0.0296, over 1423179.65 frames.], batch size: 20, lr: 2.36e-04
+2022-05-15 20:37:47,514 INFO [train.py:812] (7/8) Epoch 33, batch 1450, loss[loss=0.1595, simple_loss=0.2418, pruned_loss=0.03861, over 6837.00 frames.], tot_loss[loss=0.151, simple_loss=0.2429, pruned_loss=0.02954, over 1426079.75 frames.], batch size: 31, lr: 2.36e-04
+2022-05-15 20:38:46,337 INFO [train.py:812] (7/8) Epoch 33, batch 1500, loss[loss=0.1539, simple_loss=0.2421, pruned_loss=0.03285, over 5130.00 frames.], tot_loss[loss=0.152, simple_loss=0.244, pruned_loss=0.03003, over 1423170.42 frames.], batch size: 53, lr: 2.36e-04
+2022-05-15 20:39:44,941 INFO [train.py:812] (7/8) Epoch 33, batch 1550, loss[loss=0.1447, simple_loss=0.2408, pruned_loss=0.02434, over 7223.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2446, pruned_loss=0.02991, over 1419573.83 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:40:43,858 INFO [train.py:812] (7/8) Epoch 33, batch 1600, loss[loss=0.149, simple_loss=0.2403, pruned_loss=0.02879, over 7410.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2447, pruned_loss=0.03013, over 1420993.72 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:41:42,733 INFO [train.py:812] (7/8) Epoch 33, batch 1650, loss[loss=0.1388, simple_loss=0.2318, pruned_loss=0.02287, over 7227.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.02999, over 1421519.42 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:42:41,766 INFO [train.py:812] (7/8) Epoch 33, batch 1700, loss[loss=0.1559, simple_loss=0.2564, pruned_loss=0.02766, over 7301.00 frames.], tot_loss[loss=0.1517, simple_loss=0.244, pruned_loss=0.02967, over 1423339.00 frames.], batch size: 24, lr: 2.36e-04
+2022-05-15 20:43:40,841 INFO [train.py:812] (7/8) Epoch 33, batch 1750, loss[loss=0.146, simple_loss=0.2466, pruned_loss=0.0227, over 7108.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2444, pruned_loss=0.03024, over 1416917.11 frames.], batch size: 28, lr: 2.36e-04
+2022-05-15 20:44:40,008 INFO [train.py:812] (7/8) Epoch 33, batch 1800, loss[loss=0.157, simple_loss=0.2476, pruned_loss=0.03323, over 7259.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2438, pruned_loss=0.02969, over 1421007.34 frames.], batch size: 19, lr: 2.36e-04
+2022-05-15 20:45:38,882 INFO [train.py:812] (7/8) Epoch 33, batch 1850, loss[loss=0.1505, simple_loss=0.2452, pruned_loss=0.02791, over 7325.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2442, pruned_loss=0.03009, over 1423234.45 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:46:37,357 INFO [train.py:812] (7/8) Epoch 33, batch 1900, loss[loss=0.185, simple_loss=0.2744, pruned_loss=0.04783, over 7376.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2443, pruned_loss=0.03027, over 1425675.97 frames.], batch size: 23, lr: 2.36e-04
+2022-05-15 20:47:35,907 INFO [train.py:812] (7/8) Epoch 33, batch 1950, loss[loss=0.1683, simple_loss=0.2717, pruned_loss=0.0324, over 7286.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2441, pruned_loss=0.03009, over 1423934.71 frames.], batch size: 24, lr: 2.36e-04
+2022-05-15 20:48:34,909 INFO [train.py:812] (7/8) Epoch 33, batch 2000, loss[loss=0.1402, simple_loss=0.2371, pruned_loss=0.0217, over 6371.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2437, pruned_loss=0.0303, over 1424922.48 frames.], batch size: 37, lr: 2.36e-04
+2022-05-15 20:49:32,722 INFO [train.py:812] (7/8) Epoch 33, batch 2050, loss[loss=0.1677, simple_loss=0.2546, pruned_loss=0.04041, over 7156.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2442, pruned_loss=0.03026, over 1426114.42 frames.], batch size: 18, lr: 2.36e-04
+2022-05-15 20:50:32,336 INFO [train.py:812] (7/8) Epoch 33, batch 2100, loss[loss=0.1206, simple_loss=0.2124, pruned_loss=0.01442, over 7152.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2437, pruned_loss=0.03029, over 1426758.31 frames.], batch size: 19, lr: 2.36e-04
+2022-05-15 20:51:30,245 INFO [train.py:812] (7/8) Epoch 33, batch 2150, loss[loss=0.1418, simple_loss=0.2335, pruned_loss=0.02509, over 7398.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2439, pruned_loss=0.02989, over 1427282.21 frames.], batch size: 18, lr: 2.36e-04
+2022-05-15 20:52:28,391 INFO [train.py:812] (7/8) Epoch 33, batch 2200, loss[loss=0.1948, simple_loss=0.2858, pruned_loss=0.05187, over 5036.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2443, pruned_loss=0.03016, over 1421299.76 frames.], batch size: 52, lr: 2.36e-04
+2022-05-15 20:53:26,631 INFO [train.py:812] (7/8) Epoch 33, batch 2250, loss[loss=0.1791, simple_loss=0.274, pruned_loss=0.04207, over 7126.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2439, pruned_loss=0.03024, over 1419126.52 frames.], batch size: 26, lr: 2.36e-04
+2022-05-15 20:54:25,527 INFO [train.py:812] (7/8) Epoch 33, batch 2300, loss[loss=0.1721, simple_loss=0.273, pruned_loss=0.03556, over 7191.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2431, pruned_loss=0.03004, over 1418083.07 frames.], batch size: 22, lr: 2.36e-04
+2022-05-15 20:55:24,381 INFO [train.py:812] (7/8) Epoch 33, batch 2350, loss[loss=0.1282, simple_loss=0.2088, pruned_loss=0.02378, over 6819.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2425, pruned_loss=0.02971, over 1421017.60 frames.], batch size: 15, lr: 2.36e-04
+2022-05-15 20:56:22,969 INFO [train.py:812] (7/8) Epoch 33, batch 2400, loss[loss=0.1828, simple_loss=0.2735, pruned_loss=0.04606, over 7435.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2425, pruned_loss=0.02993, over 1423783.74 frames.], batch size: 20, lr: 2.36e-04
+2022-05-15 20:57:40,455 INFO [train.py:812] (7/8) Epoch 33, batch 2450, loss[loss=0.1459, simple_loss=0.2367, pruned_loss=0.02753, over 7259.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2425, pruned_loss=0.02962, over 1425640.08 frames.], batch size: 19, lr: 2.36e-04
+2022-05-15 20:58:40,031 INFO [train.py:812] (7/8) Epoch 33, batch 2500, loss[loss=0.1397, simple_loss=0.2355, pruned_loss=0.02189, over 7322.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2422, pruned_loss=0.02934, over 1427125.89 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:59:48,305 INFO [train.py:812] (7/8) Epoch 33, batch 2550, loss[loss=0.1668, simple_loss=0.2721, pruned_loss=0.03072, over 7355.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2428, pruned_loss=0.02968, over 1426579.98 frames.], batch size: 23, lr: 2.36e-04
+2022-05-15 21:00:46,749 INFO [train.py:812] (7/8) Epoch 33, batch 2600, loss[loss=0.1792, simple_loss=0.2719, pruned_loss=0.04323, over 7182.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2427, pruned_loss=0.02976, over 1426999.12 frames.], batch size: 23, lr: 2.36e-04
+2022-05-15 21:01:44,977 INFO [train.py:812] (7/8) Epoch 33, batch 2650, loss[loss=0.1467, simple_loss=0.2266, pruned_loss=0.03345, over 7243.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2434, pruned_loss=0.02992, over 1422132.37 frames.], batch size: 16, lr: 2.35e-04
+2022-05-15 21:02:52,869 INFO [train.py:812] (7/8) Epoch 33, batch 2700, loss[loss=0.1423, simple_loss=0.2355, pruned_loss=0.02458, over 7428.00 frames.], tot_loss[loss=0.1521, simple_loss=0.244, pruned_loss=0.03011, over 1423765.37 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:04:10,610 INFO [train.py:812] (7/8) Epoch 33, batch 2750, loss[loss=0.1337, simple_loss=0.2199, pruned_loss=0.02376, over 7286.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2439, pruned_loss=0.02992, over 1424964.32 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:05:09,530 INFO [train.py:812] (7/8) Epoch 33, batch 2800, loss[loss=0.1663, simple_loss=0.263, pruned_loss=0.03475, over 7213.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02995, over 1424019.58 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:06:07,220 INFO [train.py:812] (7/8) Epoch 33, batch 2850, loss[loss=0.1478, simple_loss=0.2547, pruned_loss=0.02042, over 7327.00 frames.], tot_loss[loss=0.1513, simple_loss=0.243, pruned_loss=0.02975, over 1425319.19 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:07:06,367 INFO [train.py:812] (7/8) Epoch 33, batch 2900, loss[loss=0.1639, simple_loss=0.2598, pruned_loss=0.03398, over 7321.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2434, pruned_loss=0.03008, over 1424828.32 frames.], batch size: 25, lr: 2.35e-04
+2022-05-15 21:08:04,510 INFO [train.py:812] (7/8) Epoch 33, batch 2950, loss[loss=0.1387, simple_loss=0.2367, pruned_loss=0.02031, over 7425.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2448, pruned_loss=0.03024, over 1426948.90 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:09:12,211 INFO [train.py:812] (7/8) Epoch 33, batch 3000, loss[loss=0.1469, simple_loss=0.2384, pruned_loss=0.02767, over 7063.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.0302, over 1425486.45 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:09:12,212 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 21:09:19,691 INFO [train.py:841] (7/8) Epoch 33, validation: loss=0.1535, simple_loss=0.2493, pruned_loss=0.02886, over 698248.00 frames.
+2022-05-15 21:10:18,072 INFO [train.py:812] (7/8) Epoch 33, batch 3050, loss[loss=0.1548, simple_loss=0.2507, pruned_loss=0.02942, over 6435.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2436, pruned_loss=0.02974, over 1422503.47 frames.], batch size: 38, lr: 2.35e-04
+2022-05-15 21:11:15,935 INFO [train.py:812] (7/8) Epoch 33, batch 3100, loss[loss=0.1698, simple_loss=0.2666, pruned_loss=0.03652, over 7368.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02956, over 1422985.72 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:12:14,889 INFO [train.py:812] (7/8) Epoch 33, batch 3150, loss[loss=0.1484, simple_loss=0.2478, pruned_loss=0.02448, over 7066.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.02949, over 1420825.50 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:13:13,029 INFO [train.py:812] (7/8) Epoch 33, batch 3200, loss[loss=0.1366, simple_loss=0.2207, pruned_loss=0.02631, over 6771.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2437, pruned_loss=0.02972, over 1420461.18 frames.], batch size: 15, lr: 2.35e-04
+2022-05-15 21:14:11,712 INFO [train.py:812] (7/8) Epoch 33, batch 3250, loss[loss=0.1394, simple_loss=0.2184, pruned_loss=0.03018, over 7281.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02983, over 1418446.52 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:15:11,690 INFO [train.py:812] (7/8) Epoch 33, batch 3300, loss[loss=0.1524, simple_loss=0.2529, pruned_loss=0.02597, over 7238.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2432, pruned_loss=0.02968, over 1423787.50 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:16:10,463 INFO [train.py:812] (7/8) Epoch 33, batch 3350, loss[loss=0.1237, simple_loss=0.223, pruned_loss=0.01223, over 7321.00 frames.], tot_loss[loss=0.151, simple_loss=0.2433, pruned_loss=0.02934, over 1427674.60 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:17:09,961 INFO [train.py:812] (7/8) Epoch 33, batch 3400, loss[loss=0.1545, simple_loss=0.2456, pruned_loss=0.03168, over 7273.00 frames.], tot_loss[loss=0.151, simple_loss=0.243, pruned_loss=0.02945, over 1428399.95 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:18:09,833 INFO [train.py:812] (7/8) Epoch 33, batch 3450, loss[loss=0.1497, simple_loss=0.2502, pruned_loss=0.02465, over 7328.00 frames.], tot_loss[loss=0.151, simple_loss=0.2433, pruned_loss=0.02937, over 1432246.05 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:19:07,599 INFO [train.py:812] (7/8) Epoch 33, batch 3500, loss[loss=0.177, simple_loss=0.2774, pruned_loss=0.03833, over 7377.00 frames.], tot_loss[loss=0.1516, simple_loss=0.244, pruned_loss=0.02964, over 1428576.75 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:20:05,746 INFO [train.py:812] (7/8) Epoch 33, batch 3550, loss[loss=0.1434, simple_loss=0.2278, pruned_loss=0.02952, over 7426.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2436, pruned_loss=0.02938, over 1427549.53 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:21:04,491 INFO [train.py:812] (7/8) Epoch 33, batch 3600, loss[loss=0.1509, simple_loss=0.2445, pruned_loss=0.02867, over 7319.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2437, pruned_loss=0.02947, over 1423835.27 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:22:03,618 INFO [train.py:812] (7/8) Epoch 33, batch 3650, loss[loss=0.1568, simple_loss=0.2501, pruned_loss=0.03175, over 7326.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2424, pruned_loss=0.02921, over 1424060.31 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:23:02,553 INFO [train.py:812] (7/8) Epoch 33, batch 3700, loss[loss=0.1352, simple_loss=0.227, pruned_loss=0.02167, over 7290.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02963, over 1427675.61 frames.], batch size: 17, lr: 2.35e-04
+2022-05-15 21:24:01,188 INFO [train.py:812] (7/8) Epoch 33, batch 3750, loss[loss=0.1438, simple_loss=0.2391, pruned_loss=0.02422, over 7219.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2433, pruned_loss=0.02973, over 1427498.71 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:25:00,734 INFO [train.py:812] (7/8) Epoch 33, batch 3800, loss[loss=0.1667, simple_loss=0.2611, pruned_loss=0.03611, over 7193.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2433, pruned_loss=0.03, over 1428288.90 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:25:58,517 INFO [train.py:812] (7/8) Epoch 33, batch 3850, loss[loss=0.1543, simple_loss=0.256, pruned_loss=0.0263, over 7317.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2424, pruned_loss=0.02936, over 1429790.81 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:26:57,084 INFO [train.py:812] (7/8) Epoch 33, batch 3900, loss[loss=0.1432, simple_loss=0.2213, pruned_loss=0.03253, over 6792.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2443, pruned_loss=0.02997, over 1429659.87 frames.], batch size: 15, lr: 2.35e-04
+2022-05-15 21:27:55,719 INFO [train.py:812] (7/8) Epoch 33, batch 3950, loss[loss=0.1341, simple_loss=0.227, pruned_loss=0.0206, over 7425.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2449, pruned_loss=0.03026, over 1431474.64 frames.], batch size: 18, lr: 2.34e-04
+2022-05-15 21:28:55,492 INFO [train.py:812] (7/8) Epoch 33, batch 4000, loss[loss=0.1585, simple_loss=0.2521, pruned_loss=0.03243, over 6519.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2444, pruned_loss=0.03015, over 1431728.15 frames.], batch size: 38, lr: 2.34e-04
+2022-05-15 21:29:54,330 INFO [train.py:812] (7/8) Epoch 33, batch 4050, loss[loss=0.1456, simple_loss=0.2317, pruned_loss=0.02972, over 7282.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03027, over 1427937.87 frames.], batch size: 18, lr: 2.34e-04
+2022-05-15 21:30:52,681 INFO [train.py:812] (7/8) Epoch 33, batch 4100, loss[loss=0.1626, simple_loss=0.2465, pruned_loss=0.03932, over 7158.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2445, pruned_loss=0.03044, over 1421830.51 frames.], batch size: 26, lr: 2.34e-04
+2022-05-15 21:31:50,551 INFO [train.py:812] (7/8) Epoch 33, batch 4150, loss[loss=0.1395, simple_loss=0.2212, pruned_loss=0.0289, over 6802.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2442, pruned_loss=0.03008, over 1421828.02 frames.], batch size: 15, lr: 2.34e-04
+2022-05-15 21:32:49,116 INFO [train.py:812] (7/8) Epoch 33, batch 4200, loss[loss=0.1626, simple_loss=0.2619, pruned_loss=0.03167, over 7261.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02996, over 1420126.40 frames.], batch size: 19, lr: 2.34e-04
+2022-05-15 21:33:48,344 INFO [train.py:812] (7/8) Epoch 33, batch 4250, loss[loss=0.1215, simple_loss=0.2117, pruned_loss=0.01569, over 7425.00 frames.], tot_loss[loss=0.1519, simple_loss=0.244, pruned_loss=0.02986, over 1420262.28 frames.], batch size: 20, lr: 2.34e-04
+2022-05-15 21:34:46,578 INFO [train.py:812] (7/8) Epoch 33, batch 4300, loss[loss=0.1699, simple_loss=0.2685, pruned_loss=0.03571, over 6936.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2439, pruned_loss=0.02961, over 1419508.85 frames.], batch size: 32, lr: 2.34e-04
+2022-05-15 21:35:44,820 INFO [train.py:812] (7/8) Epoch 33, batch 4350, loss[loss=0.1486, simple_loss=0.2481, pruned_loss=0.02456, over 7221.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2429, pruned_loss=0.02937, over 1414801.47 frames.], batch size: 21, lr: 2.34e-04
+2022-05-15 21:36:43,634 INFO [train.py:812] (7/8) Epoch 33, batch 4400, loss[loss=0.1465, simple_loss=0.2499, pruned_loss=0.02156, over 7137.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.029, over 1414125.43 frames.], batch size: 20, lr: 2.34e-04
+2022-05-15 21:37:42,052 INFO [train.py:812] (7/8) Epoch 33, batch 4450, loss[loss=0.16, simple_loss=0.258, pruned_loss=0.03102, over 7330.00 frames.], tot_loss[loss=0.1508, simple_loss=0.243, pruned_loss=0.02928, over 1407124.64 frames.], batch size: 22, lr: 2.34e-04
+2022-05-15 21:38:41,231 INFO [train.py:812] (7/8) Epoch 33, batch 4500, loss[loss=0.1467, simple_loss=0.2472, pruned_loss=0.02314, over 7144.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2426, pruned_loss=0.0288, over 1396830.19 frames.], batch size: 20, lr: 2.34e-04
+2022-05-15 21:39:39,852 INFO [train.py:812] (7/8) Epoch 33, batch 4550, loss[loss=0.1694, simple_loss=0.2587, pruned_loss=0.04008, over 4860.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02918, over 1375209.99 frames.], batch size: 52, lr: 2.34e-04
+2022-05-15 21:40:52,186 INFO [train.py:812] (7/8) Epoch 34, batch 0, loss[loss=0.1529, simple_loss=0.2444, pruned_loss=0.03066, over 7436.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2444, pruned_loss=0.03066, over 7436.00 frames.], batch size: 20, lr: 2.31e-04
+2022-05-15 21:41:51,350 INFO [train.py:812] (7/8) Epoch 34, batch 50, loss[loss=0.1522, simple_loss=0.2419, pruned_loss=0.03126, over 7069.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2406, pruned_loss=0.02852, over 324630.75 frames.], batch size: 28, lr: 2.30e-04
+2022-05-15 21:42:51,084 INFO [train.py:812] (7/8) Epoch 34, batch 100, loss[loss=0.1653, simple_loss=0.269, pruned_loss=0.03085, over 7452.00 frames.], tot_loss[loss=0.152, simple_loss=0.2444, pruned_loss=0.0298, over 566765.47 frames.], batch size: 22, lr: 2.30e-04
+2022-05-15 21:43:50,314 INFO [train.py:812] (7/8) Epoch 34, batch 150, loss[loss=0.1366, simple_loss=0.2319, pruned_loss=0.02063, over 7068.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2416, pruned_loss=0.02893, over 756792.23 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:44:49,639 INFO [train.py:812] (7/8) Epoch 34, batch 200, loss[loss=0.1493, simple_loss=0.2481, pruned_loss=0.02521, over 7277.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2411, pruned_loss=0.02898, over 905939.80 frames.], batch size: 17, lr: 2.30e-04
+2022-05-15 21:45:48,787 INFO [train.py:812] (7/8) Epoch 34, batch 250, loss[loss=0.1727, simple_loss=0.2616, pruned_loss=0.04192, over 5318.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2416, pruned_loss=0.02924, over 1012965.02 frames.], batch size: 52, lr: 2.30e-04
+2022-05-15 21:46:48,783 INFO [train.py:812] (7/8) Epoch 34, batch 300, loss[loss=0.1501, simple_loss=0.2474, pruned_loss=0.02646, over 7382.00 frames.], tot_loss[loss=0.1511, simple_loss=0.243, pruned_loss=0.02959, over 1103954.36 frames.], batch size: 23, lr: 2.30e-04
+2022-05-15 21:47:46,242 INFO [train.py:812] (7/8) Epoch 34, batch 350, loss[loss=0.1134, simple_loss=0.2101, pruned_loss=0.008356, over 7109.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2444, pruned_loss=0.02991, over 1169170.23 frames.], batch size: 17, lr: 2.30e-04
+2022-05-15 21:48:46,305 INFO [train.py:812] (7/8) Epoch 34, batch 400, loss[loss=0.153, simple_loss=0.25, pruned_loss=0.02796, over 7414.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2441, pruned_loss=0.02985, over 1229839.69 frames.], batch size: 21, lr: 2.30e-04
+2022-05-15 21:49:44,756 INFO [train.py:812] (7/8) Epoch 34, batch 450, loss[loss=0.1432, simple_loss=0.2323, pruned_loss=0.02711, over 7410.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2441, pruned_loss=0.02948, over 1274178.54 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:50:44,146 INFO [train.py:812] (7/8) Epoch 34, batch 500, loss[loss=0.1562, simple_loss=0.2542, pruned_loss=0.02912, over 7290.00 frames.], tot_loss[loss=0.153, simple_loss=0.2453, pruned_loss=0.03031, over 1307453.16 frames.], batch size: 24, lr: 2.30e-04
+2022-05-15 21:51:42,516 INFO [train.py:812] (7/8) Epoch 34, batch 550, loss[loss=0.1509, simple_loss=0.2535, pruned_loss=0.02419, over 6419.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2444, pruned_loss=0.03001, over 1331056.48 frames.], batch size: 37, lr: 2.30e-04
+2022-05-15 21:52:57,397 INFO [train.py:812] (7/8) Epoch 34, batch 600, loss[loss=0.165, simple_loss=0.2636, pruned_loss=0.03322, over 7308.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2446, pruned_loss=0.02993, over 1353427.54 frames.], batch size: 25, lr: 2.30e-04
+2022-05-15 21:53:55,932 INFO [train.py:812] (7/8) Epoch 34, batch 650, loss[loss=0.1454, simple_loss=0.2317, pruned_loss=0.02956, over 7164.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2452, pruned_loss=0.03018, over 1371565.00 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:54:54,875 INFO [train.py:812] (7/8) Epoch 34, batch 700, loss[loss=0.1161, simple_loss=0.1939, pruned_loss=0.01916, over 7135.00 frames.], tot_loss[loss=0.151, simple_loss=0.2429, pruned_loss=0.02949, over 1378846.58 frames.], batch size: 17, lr: 2.30e-04
+2022-05-15 21:55:51,408 INFO [train.py:812] (7/8) Epoch 34, batch 750, loss[loss=0.1461, simple_loss=0.2358, pruned_loss=0.02819, over 7193.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.02944, over 1389910.12 frames.], batch size: 23, lr: 2.30e-04
+2022-05-15 21:56:50,481 INFO [train.py:812] (7/8) Epoch 34, batch 800, loss[loss=0.161, simple_loss=0.241, pruned_loss=0.04047, over 7280.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2438, pruned_loss=0.02969, over 1395017.63 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:57:49,846 INFO [train.py:812] (7/8) Epoch 34, batch 850, loss[loss=0.1575, simple_loss=0.2551, pruned_loss=0.02995, over 6397.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2439, pruned_loss=0.02957, over 1403972.35 frames.], batch size: 38, lr: 2.30e-04
+2022-05-15 21:58:48,185 INFO [train.py:812] (7/8) Epoch 34, batch 900, loss[loss=0.1677, simple_loss=0.2472, pruned_loss=0.04415, over 4989.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2424, pruned_loss=0.02922, over 1409332.09 frames.], batch size: 52, lr: 2.30e-04
+2022-05-15 21:59:45,330 INFO [train.py:812] (7/8) Epoch 34, batch 950, loss[loss=0.1784, simple_loss=0.2496, pruned_loss=0.05358, over 7288.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2422, pruned_loss=0.02948, over 1407696.26 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 22:00:43,725 INFO [train.py:812] (7/8) Epoch 34, batch 1000, loss[loss=0.1399, simple_loss=0.2315, pruned_loss=0.02417, over 7441.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2416, pruned_loss=0.02902, over 1409803.25 frames.], batch size: 20, lr: 2.30e-04
+2022-05-15 22:01:41,765 INFO [train.py:812] (7/8) Epoch 34, batch 1050, loss[loss=0.1405, simple_loss=0.2348, pruned_loss=0.02308, over 7156.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2418, pruned_loss=0.02914, over 1416260.75 frames.], batch size: 19, lr: 2.30e-04
+2022-05-15 22:02:40,812 INFO [train.py:812] (7/8) Epoch 34, batch 1100, loss[loss=0.1369, simple_loss=0.2404, pruned_loss=0.01667, over 6314.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2428, pruned_loss=0.02945, over 1414897.73 frames.], batch size: 38, lr: 2.30e-04
+2022-05-15 22:03:39,418 INFO [train.py:812] (7/8) Epoch 34, batch 1150, loss[loss=0.1353, simple_loss=0.2232, pruned_loss=0.02368, over 7423.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2427, pruned_loss=0.02981, over 1417505.89 frames.], batch size: 20, lr: 2.30e-04
+2022-05-15 22:04:38,159 INFO [train.py:812] (7/8) Epoch 34, batch 1200, loss[loss=0.1709, simple_loss=0.2667, pruned_loss=0.03752, over 7194.00 frames.], tot_loss[loss=0.151, simple_loss=0.2426, pruned_loss=0.02968, over 1421813.80 frames.], batch size: 23, lr: 2.30e-04
+2022-05-15 22:05:35,708 INFO [train.py:812] (7/8) Epoch 34, batch 1250, loss[loss=0.1477, simple_loss=0.2532, pruned_loss=0.02107, over 7335.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2426, pruned_loss=0.02956, over 1419555.33 frames.], batch size: 22, lr: 2.30e-04
+2022-05-15 22:06:34,744 INFO [train.py:812] (7/8) Epoch 34, batch 1300, loss[loss=0.1658, simple_loss=0.2605, pruned_loss=0.03559, over 7165.00 frames.], tot_loss[loss=0.151, simple_loss=0.2426, pruned_loss=0.02968, over 1418846.57 frames.], batch size: 26, lr: 2.30e-04
+2022-05-15 22:07:33,176 INFO [train.py:812] (7/8) Epoch 34, batch 1350, loss[loss=0.1575, simple_loss=0.2565, pruned_loss=0.0292, over 7219.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2421, pruned_loss=0.02949, over 1419133.46 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:08:32,153 INFO [train.py:812] (7/8) Epoch 34, batch 1400, loss[loss=0.158, simple_loss=0.2493, pruned_loss=0.03332, over 7258.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2419, pruned_loss=0.02955, over 1422275.74 frames.], batch size: 19, lr: 2.29e-04
+2022-05-15 22:09:31,099 INFO [train.py:812] (7/8) Epoch 34, batch 1450, loss[loss=0.178, simple_loss=0.2679, pruned_loss=0.04406, over 7415.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2421, pruned_loss=0.0292, over 1426146.08 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:10:29,321 INFO [train.py:812] (7/8) Epoch 34, batch 1500, loss[loss=0.1818, simple_loss=0.2767, pruned_loss=0.04342, over 7367.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02939, over 1424409.78 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:11:28,530 INFO [train.py:812] (7/8) Epoch 34, batch 1550, loss[loss=0.1448, simple_loss=0.2348, pruned_loss=0.02737, over 7277.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2433, pruned_loss=0.02963, over 1422247.23 frames.], batch size: 24, lr: 2.29e-04
+2022-05-15 22:12:27,931 INFO [train.py:812] (7/8) Epoch 34, batch 1600, loss[loss=0.1416, simple_loss=0.2343, pruned_loss=0.02447, over 7335.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02953, over 1423841.10 frames.], batch size: 20, lr: 2.29e-04
+2022-05-15 22:13:26,024 INFO [train.py:812] (7/8) Epoch 34, batch 1650, loss[loss=0.1452, simple_loss=0.2388, pruned_loss=0.02575, over 7206.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2447, pruned_loss=0.03015, over 1422773.85 frames.], batch size: 22, lr: 2.29e-04
+2022-05-15 22:14:25,169 INFO [train.py:812] (7/8) Epoch 34, batch 1700, loss[loss=0.1565, simple_loss=0.2481, pruned_loss=0.03252, over 7375.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2448, pruned_loss=0.0299, over 1426617.79 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:15:24,030 INFO [train.py:812] (7/8) Epoch 34, batch 1750, loss[loss=0.1567, simple_loss=0.2494, pruned_loss=0.03202, over 7022.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03024, over 1420780.00 frames.], batch size: 28, lr: 2.29e-04
+2022-05-15 22:16:22,646 INFO [train.py:812] (7/8) Epoch 34, batch 1800, loss[loss=0.1215, simple_loss=0.2068, pruned_loss=0.01807, over 7268.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2443, pruned_loss=0.03015, over 1422438.02 frames.], batch size: 17, lr: 2.29e-04
+2022-05-15 22:17:21,616 INFO [train.py:812] (7/8) Epoch 34, batch 1850, loss[loss=0.1789, simple_loss=0.2713, pruned_loss=0.04328, over 7322.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2439, pruned_loss=0.0299, over 1414535.64 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:18:20,758 INFO [train.py:812] (7/8) Epoch 34, batch 1900, loss[loss=0.1587, simple_loss=0.2569, pruned_loss=0.03021, over 6684.00 frames.], tot_loss[loss=0.1522, simple_loss=0.244, pruned_loss=0.03017, over 1409980.38 frames.], batch size: 31, lr: 2.29e-04
+2022-05-15 22:19:17,952 INFO [train.py:812] (7/8) Epoch 34, batch 1950, loss[loss=0.1285, simple_loss=0.2154, pruned_loss=0.02076, over 6983.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2433, pruned_loss=0.02957, over 1416241.50 frames.], batch size: 16, lr: 2.29e-04
+2022-05-15 22:20:16,791 INFO [train.py:812] (7/8) Epoch 34, batch 2000, loss[loss=0.1298, simple_loss=0.2233, pruned_loss=0.01814, over 7415.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2435, pruned_loss=0.02982, over 1420939.87 frames.], batch size: 18, lr: 2.29e-04
+2022-05-15 22:21:15,745 INFO [train.py:812] (7/8) Epoch 34, batch 2050, loss[loss=0.1593, simple_loss=0.2534, pruned_loss=0.0326, over 7176.00 frames.], tot_loss[loss=0.1512, simple_loss=0.243, pruned_loss=0.02966, over 1420009.00 frames.], batch size: 26, lr: 2.29e-04
+2022-05-15 22:22:14,749 INFO [train.py:812] (7/8) Epoch 34, batch 2100, loss[loss=0.1406, simple_loss=0.2313, pruned_loss=0.0249, over 7206.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2434, pruned_loss=0.02951, over 1423051.62 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:23:12,306 INFO [train.py:812] (7/8) Epoch 34, batch 2150, loss[loss=0.155, simple_loss=0.2424, pruned_loss=0.03384, over 7282.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2426, pruned_loss=0.02932, over 1422660.11 frames.], batch size: 24, lr: 2.29e-04
+2022-05-15 22:24:11,556 INFO [train.py:812] (7/8) Epoch 34, batch 2200, loss[loss=0.158, simple_loss=0.2521, pruned_loss=0.03194, over 7318.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02948, over 1426016.88 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:25:10,888 INFO [train.py:812] (7/8) Epoch 34, batch 2250, loss[loss=0.1393, simple_loss=0.2202, pruned_loss=0.02918, over 7278.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02985, over 1422966.18 frames.], batch size: 18, lr: 2.29e-04
+2022-05-15 22:26:09,593 INFO [train.py:812] (7/8) Epoch 34, batch 2300, loss[loss=0.1512, simple_loss=0.2265, pruned_loss=0.03799, over 7162.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2445, pruned_loss=0.02996, over 1423423.68 frames.], batch size: 19, lr: 2.29e-04
+2022-05-15 22:27:08,022 INFO [train.py:812] (7/8) Epoch 34, batch 2350, loss[loss=0.1505, simple_loss=0.2353, pruned_loss=0.03285, over 7165.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2443, pruned_loss=0.0301, over 1424512.77 frames.], batch size: 19, lr: 2.29e-04
+2022-05-15 22:28:06,490 INFO [train.py:812] (7/8) Epoch 34, batch 2400, loss[loss=0.165, simple_loss=0.2608, pruned_loss=0.03458, over 7384.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2434, pruned_loss=0.03001, over 1425604.20 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:29:04,657 INFO [train.py:812] (7/8) Epoch 34, batch 2450, loss[loss=0.1367, simple_loss=0.2391, pruned_loss=0.01714, over 7226.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2443, pruned_loss=0.0301, over 1420162.09 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:30:04,524 INFO [train.py:812] (7/8) Epoch 34, batch 2500, loss[loss=0.1376, simple_loss=0.2183, pruned_loss=0.02847, over 6987.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2448, pruned_loss=0.03023, over 1418324.20 frames.], batch size: 16, lr: 2.29e-04
+2022-05-15 22:31:02,277 INFO [train.py:812] (7/8) Epoch 34, batch 2550, loss[loss=0.1516, simple_loss=0.2524, pruned_loss=0.02541, over 7341.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2445, pruned_loss=0.03024, over 1419350.35 frames.], batch size: 22, lr: 2.29e-04
+2022-05-15 22:32:00,058 INFO [train.py:812] (7/8) Epoch 34, batch 2600, loss[loss=0.1436, simple_loss=0.2318, pruned_loss=0.02769, over 7076.00 frames.], tot_loss[loss=0.152, simple_loss=0.2441, pruned_loss=0.0299, over 1419913.89 frames.], batch size: 18, lr: 2.29e-04
+2022-05-15 22:32:58,107 INFO [train.py:812] (7/8) Epoch 34, batch 2650, loss[loss=0.1393, simple_loss=0.2411, pruned_loss=0.01874, over 7337.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2432, pruned_loss=0.02958, over 1420070.29 frames.], batch size: 22, lr: 2.29e-04
+2022-05-15 22:33:57,003 INFO [train.py:812] (7/8) Epoch 34, batch 2700, loss[loss=0.1449, simple_loss=0.2291, pruned_loss=0.03037, over 7266.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02933, over 1424828.61 frames.], batch size: 18, lr: 2.28e-04
+2022-05-15 22:34:55,314 INFO [train.py:812] (7/8) Epoch 34, batch 2750, loss[loss=0.1541, simple_loss=0.2485, pruned_loss=0.02991, over 7323.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.02927, over 1423801.48 frames.], batch size: 21, lr: 2.28e-04
+2022-05-15 22:35:54,079 INFO [train.py:812] (7/8) Epoch 34, batch 2800, loss[loss=0.1484, simple_loss=0.2332, pruned_loss=0.03175, over 7414.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2436, pruned_loss=0.0289, over 1428606.17 frames.], batch size: 18, lr: 2.28e-04
+2022-05-15 22:36:52,778 INFO [train.py:812] (7/8) Epoch 34, batch 2850, loss[loss=0.1653, simple_loss=0.2582, pruned_loss=0.03622, over 7196.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2438, pruned_loss=0.02882, over 1429499.93 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:37:50,517 INFO [train.py:812] (7/8) Epoch 34, batch 2900, loss[loss=0.1483, simple_loss=0.2505, pruned_loss=0.02304, over 7155.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2437, pruned_loss=0.02881, over 1426725.54 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:38:49,646 INFO [train.py:812] (7/8) Epoch 34, batch 2950, loss[loss=0.1668, simple_loss=0.2654, pruned_loss=0.03415, over 7139.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.02897, over 1427188.07 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:39:49,345 INFO [train.py:812] (7/8) Epoch 34, batch 3000, loss[loss=0.1393, simple_loss=0.2312, pruned_loss=0.02369, over 7364.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2426, pruned_loss=0.0288, over 1427774.51 frames.], batch size: 19, lr: 2.28e-04
+2022-05-15 22:39:49,346 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-15 22:39:56,836 INFO [train.py:841] (7/8) Epoch 34, validation: loss=0.1534, simple_loss=0.2492, pruned_loss=0.02878, over 698248.00 frames.
+2022-05-15 22:40:55,246 INFO [train.py:812] (7/8) Epoch 34, batch 3050, loss[loss=0.1591, simple_loss=0.2599, pruned_loss=0.02916, over 7355.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2441, pruned_loss=0.02923, over 1427836.62 frames.], batch size: 19, lr: 2.28e-04
+2022-05-15 22:41:53,747 INFO [train.py:812] (7/8) Epoch 34, batch 3100, loss[loss=0.1303, simple_loss=0.2085, pruned_loss=0.02607, over 7256.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2444, pruned_loss=0.02934, over 1430108.30 frames.], batch size: 16, lr: 2.28e-04
+2022-05-15 22:42:52,718 INFO [train.py:812] (7/8) Epoch 34, batch 3150, loss[loss=0.1279, simple_loss=0.2086, pruned_loss=0.02361, over 7294.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2436, pruned_loss=0.02929, over 1429756.78 frames.], batch size: 17, lr: 2.28e-04
+2022-05-15 22:43:51,469 INFO [train.py:812] (7/8) Epoch 34, batch 3200, loss[loss=0.1655, simple_loss=0.2491, pruned_loss=0.04092, over 5133.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2429, pruned_loss=0.0293, over 1425404.94 frames.], batch size: 52, lr: 2.28e-04
+2022-05-15 22:44:49,473 INFO [train.py:812] (7/8) Epoch 34, batch 3250, loss[loss=0.1671, simple_loss=0.2563, pruned_loss=0.03896, over 7140.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2432, pruned_loss=0.02969, over 1422559.27 frames.], batch size: 17, lr: 2.28e-04
+2022-05-15 22:45:48,036 INFO [train.py:812] (7/8) Epoch 34, batch 3300, loss[loss=0.1697, simple_loss=0.2542, pruned_loss=0.04253, over 7025.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2435, pruned_loss=0.03012, over 1419178.94 frames.], batch size: 28, lr: 2.28e-04
+2022-05-15 22:46:47,363 INFO [train.py:812] (7/8) Epoch 34, batch 3350, loss[loss=0.1465, simple_loss=0.2447, pruned_loss=0.0242, over 7154.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2424, pruned_loss=0.02967, over 1422235.68 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:47:45,318 INFO [train.py:812] (7/8) Epoch 34, batch 3400, loss[loss=0.1513, simple_loss=0.2479, pruned_loss=0.02742, over 7206.00 frames.], tot_loss[loss=0.151, simple_loss=0.2429, pruned_loss=0.02959, over 1422495.03 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:48:43,914 INFO [train.py:812] (7/8) Epoch 34, batch 3450, loss[loss=0.1279, simple_loss=0.2186, pruned_loss=0.01864, over 7008.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2423, pruned_loss=0.0296, over 1427959.99 frames.], batch size: 16, lr: 2.28e-04
+2022-05-15 22:49:41,446 INFO [train.py:812] (7/8) Epoch 34, batch 3500, loss[loss=0.1583, simple_loss=0.2468, pruned_loss=0.03491, over 7170.00 frames.], tot_loss[loss=0.152, simple_loss=0.2442, pruned_loss=0.02987, over 1429488.56 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:50:38,754 INFO [train.py:812] (7/8) Epoch 34, batch 3550, loss[loss=0.1188, simple_loss=0.206, pruned_loss=0.01585, over 7288.00 frames.], tot_loss[loss=0.1507, simple_loss=0.243, pruned_loss=0.02923, over 1430510.17 frames.], batch size: 17, lr: 2.28e-04
+2022-05-15 22:51:37,816 INFO [train.py:812] (7/8) Epoch 34, batch 3600, loss[loss=0.1574, simple_loss=0.2615, pruned_loss=0.02665, over 7317.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2426, pruned_loss=0.02923, over 1432486.00 frames.], batch size: 21, lr: 2.28e-04
+2022-05-15 22:52:35,110 INFO [train.py:812] (7/8) Epoch 34, batch 3650, loss[loss=0.1414, simple_loss=0.2367, pruned_loss=0.02304, over 6398.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02959, over 1427746.00 frames.], batch size: 37, lr: 2.28e-04
+2022-05-15 22:53:34,813 INFO [train.py:812] (7/8) Epoch 34, batch 3700, loss[loss=0.1547, simple_loss=0.257, pruned_loss=0.02618, over 7235.00 frames.], tot_loss[loss=0.151, simple_loss=0.2429, pruned_loss=0.02957, over 1423105.02 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:54:33,354 INFO [train.py:812] (7/8) Epoch 34, batch 3750, loss[loss=0.1491, simple_loss=0.2515, pruned_loss=0.02335, over 7298.00 frames.], tot_loss[loss=0.1511, simple_loss=0.243, pruned_loss=0.02965, over 1420211.55 frames.], batch size: 24, lr: 2.28e-04
+2022-05-15 22:55:32,423 INFO [train.py:812] (7/8) Epoch 34, batch 3800, loss[loss=0.1432, simple_loss=0.2381, pruned_loss=0.02412, over 7149.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.0294, over 1425014.41 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:56:31,649 INFO [train.py:812] (7/8) Epoch 34, batch 3850, loss[loss=0.1705, simple_loss=0.2553, pruned_loss=0.04287, over 7204.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2422, pruned_loss=0.02951, over 1427155.75 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:57:28,798 INFO [train.py:812] (7/8) Epoch 34, batch 3900, loss[loss=0.1622, simple_loss=0.2578, pruned_loss=0.03333, over 7216.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2424, pruned_loss=0.02944, over 1425659.12 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:58:46,461 INFO [train.py:812] (7/8) Epoch 34, batch 3950, loss[loss=0.1338, simple_loss=0.2228, pruned_loss=0.02244, over 7334.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2426, pruned_loss=0.02978, over 1423028.89 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:59:45,593 INFO [train.py:812] (7/8) Epoch 34, batch 4000, loss[loss=0.1388, simple_loss=0.2317, pruned_loss=0.02297, over 7064.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.02929, over 1423365.04 frames.], batch size: 18, lr: 2.28e-04
+2022-05-15 23:00:53,099 INFO [train.py:812] (7/8) Epoch 34, batch 4050, loss[loss=0.1606, simple_loss=0.25, pruned_loss=0.03563, over 7170.00 frames.], tot_loss[loss=0.151, simple_loss=0.2435, pruned_loss=0.02926, over 1418863.14 frames.], batch size: 26, lr: 2.27e-04
+2022-05-15 23:01:51,498 INFO [train.py:812] (7/8) Epoch 34, batch 4100, loss[loss=0.1443, simple_loss=0.2437, pruned_loss=0.02247, over 6267.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2441, pruned_loss=0.02942, over 1419274.05 frames.], batch size: 37, lr: 2.27e-04
+2022-05-15 23:02:49,346 INFO [train.py:812] (7/8) Epoch 34, batch 4150, loss[loss=0.1497, simple_loss=0.2363, pruned_loss=0.03154, over 7413.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2446, pruned_loss=0.03003, over 1417392.81 frames.], batch size: 18, lr: 2.27e-04
+2022-05-15 23:03:57,850 INFO [train.py:812] (7/8) Epoch 34, batch 4200, loss[loss=0.1318, simple_loss=0.2314, pruned_loss=0.01605, over 7237.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2443, pruned_loss=0.02977, over 1420303.02 frames.], batch size: 20, lr: 2.27e-04
+2022-05-15 23:05:06,382 INFO [train.py:812] (7/8) Epoch 34, batch 4250, loss[loss=0.1487, simple_loss=0.2322, pruned_loss=0.03259, over 7116.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2445, pruned_loss=0.03007, over 1420798.53 frames.], batch size: 17, lr: 2.27e-04
+2022-05-15 23:06:05,138 INFO [train.py:812] (7/8) Epoch 34, batch 4300, loss[loss=0.129, simple_loss=0.2172, pruned_loss=0.02038, over 7012.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2445, pruned_loss=0.03018, over 1421413.09 frames.], batch size: 16, lr: 2.27e-04
+2022-05-15 23:07:13,204 INFO [train.py:812] (7/8) Epoch 34, batch 4350, loss[loss=0.1198, simple_loss=0.1997, pruned_loss=0.01998, over 7208.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2445, pruned_loss=0.02998, over 1416505.88 frames.], batch size: 16, lr: 2.27e-04
+2022-05-15 23:08:12,775 INFO [train.py:812] (7/8) Epoch 34, batch 4400, loss[loss=0.1451, simple_loss=0.231, pruned_loss=0.02958, over 7160.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2432, pruned_loss=0.02971, over 1416420.64 frames.], batch size: 18, lr: 2.27e-04
+2022-05-15 23:09:11,159 INFO [train.py:812] (7/8) Epoch 34, batch 4450, loss[loss=0.1575, simple_loss=0.2494, pruned_loss=0.03277, over 7204.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2437, pruned_loss=0.03026, over 1401414.18 frames.], batch size: 23, lr: 2.27e-04
+2022-05-15 23:10:19,475 INFO [train.py:812] (7/8) Epoch 34, batch 4500, loss[loss=0.1939, simple_loss=0.2758, pruned_loss=0.05602, over 5247.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2437, pruned_loss=0.03046, over 1391938.13 frames.], batch size: 52, lr: 2.27e-04
+2022-05-15 23:11:16,033 INFO [train.py:812] (7/8) Epoch 34, batch 4550, loss[loss=0.1702, simple_loss=0.2661, pruned_loss=0.03719, over 4947.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2458, pruned_loss=0.0312, over 1351039.63 frames.], batch size: 52, lr: 2.27e-04
+2022-05-15 23:12:20,563 INFO [train.py:812] (7/8) Epoch 35, batch 0, loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.02924, over 7231.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.02924, over 7231.00 frames.], batch size: 20, lr: 2.24e-04
+2022-05-15 23:13:24,549 INFO [train.py:812] (7/8) Epoch 35, batch 50, loss[loss=0.1805, simple_loss=0.264, pruned_loss=0.04854, over 7295.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2452, pruned_loss=0.03027, over 318131.52 frames.], batch size: 24, lr: 2.24e-04
+2022-05-15 23:14:23,048 INFO [train.py:812] (7/8) Epoch 35, batch 100, loss[loss=0.1812, simple_loss=0.2664, pruned_loss=0.04803, over 7162.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2433, pruned_loss=0.02965, over 567694.99 frames.], batch size: 26, lr: 2.24e-04
+2022-05-15 23:15:22,508 INFO [train.py:812] (7/8) Epoch 35, batch 150, loss[loss=0.174, simple_loss=0.2641, pruned_loss=0.04196, over 7371.00 frames.], tot_loss[loss=0.153, simple_loss=0.2456, pruned_loss=0.03024, over 760119.39 frames.], batch size: 23, lr: 2.24e-04
+2022-05-15 23:16:21,271 INFO [train.py:812] (7/8) Epoch 35, batch 200, loss[loss=0.1492, simple_loss=0.2302, pruned_loss=0.03409, over 7064.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.0293, over 910208.91 frames.], batch size: 18, lr: 2.24e-04
+2022-05-15 23:17:21,154 INFO [train.py:812] (7/8) Epoch 35, batch 250, loss[loss=0.1573, simple_loss=0.2444, pruned_loss=0.03505, over 7232.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2433, pruned_loss=0.02967, over 1027812.85 frames.], batch size: 20, lr: 2.24e-04
+2022-05-15 23:18:18,854 INFO [train.py:812] (7/8) Epoch 35, batch 300, loss[loss=0.1368, simple_loss=0.231, pruned_loss=0.02127, over 7150.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2431, pruned_loss=0.02995, over 1114795.44 frames.], batch size: 19, lr: 2.24e-04
+2022-05-15 23:19:18,456 INFO [train.py:812] (7/8) Epoch 35, batch 350, loss[loss=0.1492, simple_loss=0.2379, pruned_loss=0.03023, over 7197.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2417, pruned_loss=0.02899, over 1186563.60 frames.], batch size: 23, lr: 2.24e-04
+2022-05-15 23:20:16,879 INFO [train.py:812] (7/8) Epoch 35, batch 400, loss[loss=0.1358, simple_loss=0.2372, pruned_loss=0.01719, over 7329.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2424, pruned_loss=0.02903, over 1241177.72 frames.], batch size: 20, lr: 2.24e-04
+2022-05-15 23:21:15,077 INFO [train.py:812] (7/8) Epoch 35, batch 450, loss[loss=0.153, simple_loss=0.251, pruned_loss=0.02751, over 6719.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2415, pruned_loss=0.02896, over 1285534.03 frames.], batch size: 31, lr: 2.24e-04
+2022-05-15 23:22:13,124 INFO [train.py:812] (7/8) Epoch 35, batch 500, loss[loss=0.1293, simple_loss=0.2203, pruned_loss=0.01917, over 7329.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2417, pruned_loss=0.02904, over 1313699.56 frames.], batch size: 20, lr: 2.23e-04
+2022-05-15 23:23:12,711 INFO [train.py:812] (7/8) Epoch 35, batch 550, loss[loss=0.1448, simple_loss=0.2329, pruned_loss=0.0284, over 7054.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2414, pruned_loss=0.02908, over 1334539.89 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:24:10,898 INFO [train.py:812] (7/8) Epoch 35, batch 600, loss[loss=0.1388, simple_loss=0.2308, pruned_loss=0.02335, over 7334.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2423, pruned_loss=0.02943, over 1353569.28 frames.], batch size: 22, lr: 2.23e-04
+2022-05-15 23:25:10,108 INFO [train.py:812] (7/8) Epoch 35, batch 650, loss[loss=0.1373, simple_loss=0.2236, pruned_loss=0.02546, over 7174.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2429, pruned_loss=0.02946, over 1372700.01 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:26:08,929 INFO [train.py:812] (7/8) Epoch 35, batch 700, loss[loss=0.1622, simple_loss=0.2455, pruned_loss=0.03942, over 7282.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02935, over 1387219.09 frames.], batch size: 17, lr: 2.23e-04
+2022-05-15 23:27:08,936 INFO [train.py:812] (7/8) Epoch 35, batch 750, loss[loss=0.1475, simple_loss=0.2393, pruned_loss=0.02785, over 7260.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.02895, over 1394122.73 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:28:07,104 INFO [train.py:812] (7/8) Epoch 35, batch 800, loss[loss=0.1506, simple_loss=0.2496, pruned_loss=0.02574, over 7226.00 frames.], tot_loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.02883, over 1403158.04 frames.], batch size: 21, lr: 2.23e-04
+2022-05-15 23:29:06,760 INFO [train.py:812] (7/8) Epoch 35, batch 850, loss[loss=0.1826, simple_loss=0.2787, pruned_loss=0.04318, over 7300.00 frames.], tot_loss[loss=0.1507, simple_loss=0.243, pruned_loss=0.02921, over 1402983.21 frames.], batch size: 24, lr: 2.23e-04
+2022-05-15 23:30:05,634 INFO [train.py:812] (7/8) Epoch 35, batch 900, loss[loss=0.175, simple_loss=0.2645, pruned_loss=0.0428, over 5088.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02917, over 1406571.91 frames.], batch size: 52, lr: 2.23e-04
+2022-05-15 23:31:04,523 INFO [train.py:812] (7/8) Epoch 35, batch 950, loss[loss=0.1445, simple_loss=0.2325, pruned_loss=0.02823, over 7250.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.02907, over 1410280.00 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:32:02,585 INFO [train.py:812] (7/8) Epoch 35, batch 1000, loss[loss=0.1469, simple_loss=0.2495, pruned_loss=0.02213, over 6882.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.02929, over 1411746.88 frames.], batch size: 31, lr: 2.23e-04
+2022-05-15 23:33:01,167 INFO [train.py:812] (7/8) Epoch 35, batch 1050, loss[loss=0.1928, simple_loss=0.2815, pruned_loss=0.05202, over 7412.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2423, pruned_loss=0.02965, over 1416530.99 frames.], batch size: 21, lr: 2.23e-04
+2022-05-15 23:33:59,699 INFO [train.py:812] (7/8) Epoch 35, batch 1100, loss[loss=0.1273, simple_loss=0.2212, pruned_loss=0.01671, over 7356.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2415, pruned_loss=0.02913, over 1420254.07 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:34:58,683 INFO [train.py:812] (7/8) Epoch 35, batch 1150, loss[loss=0.1755, simple_loss=0.2685, pruned_loss=0.0412, over 7191.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2425, pruned_loss=0.02914, over 1421656.66 frames.], batch size: 23, lr: 2.23e-04
+2022-05-15 23:35:56,581 INFO [train.py:812] (7/8) Epoch 35, batch 1200, loss[loss=0.1332, simple_loss=0.2203, pruned_loss=0.02308, over 7279.00 frames.], tot_loss[loss=0.1499, simple_loss=0.242, pruned_loss=0.02884, over 1425387.36 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:36:55,005 INFO [train.py:812] (7/8) Epoch 35, batch 1250, loss[loss=0.152, simple_loss=0.2529, pruned_loss=0.02562, over 7340.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2421, pruned_loss=0.02913, over 1424126.92 frames.], batch size: 22, lr: 2.23e-04
+2022-05-15 23:37:53,510 INFO [train.py:812] (7/8) Epoch 35, batch 1300, loss[loss=0.1546, simple_loss=0.2525, pruned_loss=0.02836, over 7019.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2431, pruned_loss=0.02961, over 1419177.76 frames.], batch size: 28, lr: 2.23e-04
+2022-05-15 23:38:52,854 INFO [train.py:812] (7/8) Epoch 35, batch 1350, loss[loss=0.1615, simple_loss=0.26, pruned_loss=0.03153, over 7042.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2432, pruned_loss=0.02987, over 1422480.89 frames.], batch size: 28, lr: 2.23e-04
+2022-05-15 23:39:51,265 INFO [train.py:812] (7/8) Epoch 35, batch 1400, loss[loss=0.1494, simple_loss=0.2462, pruned_loss=0.02632, over 7332.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2431, pruned_loss=0.02982, over 1420948.77 frames.], batch size: 20, lr: 2.23e-04
+2022-05-15 23:40:50,651 INFO [train.py:812] (7/8) Epoch 35, batch 1450, loss[loss=0.143, simple_loss=0.2265, pruned_loss=0.02972, over 7247.00 frames.], tot_loss[loss=0.151, simple_loss=0.2427, pruned_loss=0.02971, over 1418696.46 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:41:50,050 INFO [train.py:812] (7/8) Epoch 35, batch 1500, loss[loss=0.13, simple_loss=0.2133, pruned_loss=0.02332, over 7115.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2423, pruned_loss=0.02936, over 1419436.31 frames.], batch size: 17, lr: 2.23e-04
+2022-05-15 23:42:48,890 INFO [train.py:812] (7/8) Epoch 35, batch 1550, loss[loss=0.1899, simple_loss=0.2867, pruned_loss=0.0466, over 7223.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2433, pruned_loss=0.02967, over 1419869.52 frames.], batch size: 21, lr: 2.23e-04
+2022-05-15 23:43:47,296 INFO [train.py:812] (7/8) Epoch 35, batch 1600, loss[loss=0.1474, simple_loss=0.2462, pruned_loss=0.02425, over 7021.00 frames.], tot_loss[loss=0.151, simple_loss=0.2428, pruned_loss=0.02954, over 1421200.98 frames.], batch size: 28, lr: 2.23e-04
+2022-05-15 23:44:46,457 INFO [train.py:812] (7/8) Epoch 35, batch 1650, loss[loss=0.1383, simple_loss=0.2324, pruned_loss=0.02212, over 7408.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2428, pruned_loss=0.02951, over 1426465.80 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:45:45,308 INFO [train.py:812] (7/8) Epoch 35, batch 1700, loss[loss=0.1663, simple_loss=0.2523, pruned_loss=0.04016, over 5146.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2432, pruned_loss=0.02977, over 1426047.29 frames.], batch size: 53, lr: 2.23e-04
+2022-05-15 23:46:45,279 INFO [train.py:812] (7/8) Epoch 35, batch 1750, loss[loss=0.145, simple_loss=0.238, pruned_loss=0.02601, over 7160.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2427, pruned_loss=0.02946, over 1424820.53 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:47:44,622 INFO [train.py:812] (7/8) Epoch 35, batch 1800, loss[loss=0.1595, simple_loss=0.2594, pruned_loss=0.02982, over 7295.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2422, pruned_loss=0.02934, over 1428641.06 frames.], batch size: 25, lr: 2.23e-04
+2022-05-15 23:48:43,682 INFO [train.py:812] (7/8) Epoch 35, batch 1850, loss[loss=0.1404, simple_loss=0.2336, pruned_loss=0.02356, over 7073.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02909, over 1424617.16 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:49:42,156 INFO [train.py:812] (7/8) Epoch 35, batch 1900, loss[loss=0.1632, simple_loss=0.2543, pruned_loss=0.03603, over 7366.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2423, pruned_loss=0.02922, over 1424079.87 frames.], batch size: 23, lr: 2.22e-04
+2022-05-15 23:50:50,962 INFO [train.py:812] (7/8) Epoch 35, batch 1950, loss[loss=0.1321, simple_loss=0.2179, pruned_loss=0.02321, over 7160.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2422, pruned_loss=0.02959, over 1422902.65 frames.], batch size: 18, lr: 2.22e-04
+2022-05-15 23:51:48,123 INFO [train.py:812] (7/8) Epoch 35, batch 2000, loss[loss=0.1681, simple_loss=0.263, pruned_loss=0.0366, over 6592.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2429, pruned_loss=0.02968, over 1418430.51 frames.], batch size: 38, lr: 2.22e-04
+2022-05-15 23:52:46,839 INFO [train.py:812] (7/8) Epoch 35, batch 2050, loss[loss=0.1407, simple_loss=0.2362, pruned_loss=0.02261, over 7123.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2435, pruned_loss=0.02991, over 1420810.32 frames.], batch size: 21, lr: 2.22e-04
+2022-05-15 23:53:45,618 INFO [train.py:812] (7/8) Epoch 35, batch 2100, loss[loss=0.1612, simple_loss=0.2435, pruned_loss=0.0395, over 7420.00 frames.], tot_loss[loss=0.1523, simple_loss=0.244, pruned_loss=0.03027, over 1423601.14 frames.], batch size: 21, lr: 2.22e-04
+2022-05-15 23:54:43,320 INFO [train.py:812] (7/8) Epoch 35, batch 2150, loss[loss=0.1417, simple_loss=0.2396, pruned_loss=0.02186, over 6612.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2435, pruned_loss=0.02999, over 1427420.91 frames.], batch size: 38, lr: 2.22e-04
+2022-05-15 23:55:40,413 INFO [train.py:812] (7/8) Epoch 35, batch 2200, loss[loss=0.1596, simple_loss=0.2481, pruned_loss=0.03553, over 7434.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2434, pruned_loss=0.02995, over 1423546.59 frames.], batch size: 20, lr: 2.22e-04
+2022-05-15 23:56:39,601 INFO [train.py:812] (7/8) Epoch 35, batch 2250, loss[loss=0.1313, simple_loss=0.2184, pruned_loss=0.02208, over 7277.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2424, pruned_loss=0.02936, over 1421681.80 frames.], batch size: 18, lr: 2.22e-04
+2022-05-15 23:57:38,210 INFO [train.py:812] (7/8) Epoch 35, batch 2300, loss[loss=0.1553, simple_loss=0.2479, pruned_loss=0.03133, over 7189.00 frames.], tot_loss[loss=0.1503, simple_loss=0.242, pruned_loss=0.0293, over 1418163.42 frames.], batch size: 26, lr: 2.22e-04
+2022-05-15 23:58:36,536 INFO [train.py:812] (7/8) Epoch 35, batch 2350, loss[loss=0.1378, simple_loss=0.2347, pruned_loss=0.02041, over 7087.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2416, pruned_loss=0.02873, over 1416748.92 frames.], batch size: 28, lr: 2.22e-04
+2022-05-15 23:59:34,365 INFO [train.py:812] (7/8) Epoch 35, batch 2400, loss[loss=0.1226, simple_loss=0.2132, pruned_loss=0.01604, over 6982.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2417, pruned_loss=0.02879, over 1422084.90 frames.], batch size: 16, lr: 2.22e-04
+2022-05-16 00:00:32,018 INFO [train.py:812] (7/8) Epoch 35, batch 2450, loss[loss=0.1383, simple_loss=0.2269, pruned_loss=0.0248, over 7437.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2414, pruned_loss=0.02846, over 1422255.78 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:01:31,442 INFO [train.py:812] (7/8) Epoch 35, batch 2500, loss[loss=0.1631, simple_loss=0.2594, pruned_loss=0.03342, over 6243.00 frames.], tot_loss[loss=0.149, simple_loss=0.2407, pruned_loss=0.02861, over 1423942.87 frames.], batch size: 37, lr: 2.22e-04
+2022-05-16 00:02:30,485 INFO [train.py:812] (7/8) Epoch 35, batch 2550, loss[loss=0.1469, simple_loss=0.2448, pruned_loss=0.02451, over 7119.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2411, pruned_loss=0.02865, over 1423326.33 frames.], batch size: 21, lr: 2.22e-04
+2022-05-16 00:03:28,743 INFO [train.py:812] (7/8) Epoch 35, batch 2600, loss[loss=0.1648, simple_loss=0.2585, pruned_loss=0.03553, over 7212.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2413, pruned_loss=0.02872, over 1423939.05 frames.], batch size: 22, lr: 2.22e-04
+2022-05-16 00:04:26,550 INFO [train.py:812] (7/8) Epoch 35, batch 2650, loss[loss=0.1648, simple_loss=0.2596, pruned_loss=0.03498, over 7222.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02898, over 1422352.86 frames.], batch size: 23, lr: 2.22e-04
+2022-05-16 00:05:25,239 INFO [train.py:812] (7/8) Epoch 35, batch 2700, loss[loss=0.141, simple_loss=0.2323, pruned_loss=0.02485, over 7117.00 frames.], tot_loss[loss=0.15, simple_loss=0.2419, pruned_loss=0.02905, over 1424827.03 frames.], batch size: 21, lr: 2.22e-04
+2022-05-16 00:06:24,248 INFO [train.py:812] (7/8) Epoch 35, batch 2750, loss[loss=0.1513, simple_loss=0.2428, pruned_loss=0.02988, over 7318.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2423, pruned_loss=0.02918, over 1424287.63 frames.], batch size: 21, lr: 2.22e-04
+2022-05-16 00:07:23,051 INFO [train.py:812] (7/8) Epoch 35, batch 2800, loss[loss=0.1341, simple_loss=0.2354, pruned_loss=0.01642, over 7321.00 frames.], tot_loss[loss=0.151, simple_loss=0.2429, pruned_loss=0.02951, over 1425533.08 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:08:20,736 INFO [train.py:812] (7/8) Epoch 35, batch 2850, loss[loss=0.1447, simple_loss=0.236, pruned_loss=0.02667, over 7168.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2432, pruned_loss=0.02918, over 1424074.34 frames.], batch size: 19, lr: 2.22e-04
+2022-05-16 00:09:20,248 INFO [train.py:812] (7/8) Epoch 35, batch 2900, loss[loss=0.145, simple_loss=0.2449, pruned_loss=0.02257, over 6442.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2434, pruned_loss=0.02919, over 1423218.14 frames.], batch size: 37, lr: 2.22e-04
+2022-05-16 00:10:18,339 INFO [train.py:812] (7/8) Epoch 35, batch 2950, loss[loss=0.146, simple_loss=0.2289, pruned_loss=0.0315, over 7249.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2439, pruned_loss=0.02947, over 1416599.59 frames.], batch size: 16, lr: 2.22e-04
+2022-05-16 00:11:17,554 INFO [train.py:812] (7/8) Epoch 35, batch 3000, loss[loss=0.1747, simple_loss=0.2588, pruned_loss=0.04528, over 7395.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.02966, over 1420548.35 frames.], batch size: 23, lr: 2.22e-04
+2022-05-16 00:11:17,554 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-16 00:11:25,088 INFO [train.py:841] (7/8) Epoch 35, validation: loss=0.1528, simple_loss=0.2485, pruned_loss=0.02851, over 698248.00 frames.
+2022-05-16 00:12:24,409 INFO [train.py:812] (7/8) Epoch 35, batch 3050, loss[loss=0.1442, simple_loss=0.2364, pruned_loss=0.02597, over 7233.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2436, pruned_loss=0.02941, over 1423146.16 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:13:22,725 INFO [train.py:812] (7/8) Epoch 35, batch 3100, loss[loss=0.1542, simple_loss=0.2584, pruned_loss=0.02502, over 7390.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02913, over 1420598.81 frames.], batch size: 23, lr: 2.22e-04
+2022-05-16 00:14:22,599 INFO [train.py:812] (7/8) Epoch 35, batch 3150, loss[loss=0.1678, simple_loss=0.264, pruned_loss=0.03583, over 7209.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2423, pruned_loss=0.02918, over 1422848.83 frames.], batch size: 22, lr: 2.22e-04
+2022-05-16 00:15:21,761 INFO [train.py:812] (7/8) Epoch 35, batch 3200, loss[loss=0.1561, simple_loss=0.2489, pruned_loss=0.03162, over 7207.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2434, pruned_loss=0.02927, over 1427600.11 frames.], batch size: 22, lr: 2.22e-04
+2022-05-16 00:16:21,668 INFO [train.py:812] (7/8) Epoch 35, batch 3250, loss[loss=0.1422, simple_loss=0.2259, pruned_loss=0.02927, over 7436.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2434, pruned_loss=0.02919, over 1425627.44 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:17:21,174 INFO [train.py:812] (7/8) Epoch 35, batch 3300, loss[loss=0.1271, simple_loss=0.2097, pruned_loss=0.0222, over 7427.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2434, pruned_loss=0.02919, over 1426537.53 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:18:19,946 INFO [train.py:812] (7/8) Epoch 35, batch 3350, loss[loss=0.1516, simple_loss=0.2417, pruned_loss=0.03078, over 7430.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2437, pruned_loss=0.0294, over 1429425.34 frames.], batch size: 20, lr: 2.21e-04
+2022-05-16 00:19:17,065 INFO [train.py:812] (7/8) Epoch 35, batch 3400, loss[loss=0.1424, simple_loss=0.2214, pruned_loss=0.03167, over 7305.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.0296, over 1426180.12 frames.], batch size: 18, lr: 2.21e-04
+2022-05-16 00:20:15,919 INFO [train.py:812] (7/8) Epoch 35, batch 3450, loss[loss=0.1224, simple_loss=0.2064, pruned_loss=0.01922, over 6996.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2435, pruned_loss=0.02958, over 1429006.83 frames.], batch size: 16, lr: 2.21e-04
+2022-05-16 00:21:14,739 INFO [train.py:812] (7/8) Epoch 35, batch 3500, loss[loss=0.1599, simple_loss=0.2496, pruned_loss=0.03507, over 7349.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2438, pruned_loss=0.02979, over 1427751.39 frames.], batch size: 22, lr: 2.21e-04
+2022-05-16 00:22:12,841 INFO [train.py:812] (7/8) Epoch 35, batch 3550, loss[loss=0.1389, simple_loss=0.2346, pruned_loss=0.02164, over 6835.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2438, pruned_loss=0.02968, over 1420943.54 frames.], batch size: 31, lr: 2.21e-04
+2022-05-16 00:23:10,752 INFO [train.py:812] (7/8) Epoch 35, batch 3600, loss[loss=0.1768, simple_loss=0.2573, pruned_loss=0.04811, over 7205.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2444, pruned_loss=0.03003, over 1419993.28 frames.], batch size: 22, lr: 2.21e-04
+2022-05-16 00:24:08,639 INFO [train.py:812] (7/8) Epoch 35, batch 3650, loss[loss=0.1593, simple_loss=0.2545, pruned_loss=0.03205, over 7313.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2441, pruned_loss=0.02974, over 1421164.52 frames.], batch size: 25, lr: 2.21e-04
+2022-05-16 00:25:06,933 INFO [train.py:812] (7/8) Epoch 35, batch 3700, loss[loss=0.1587, simple_loss=0.2589, pruned_loss=0.02919, over 6303.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2438, pruned_loss=0.02955, over 1420346.71 frames.], batch size: 37, lr: 2.21e-04
+2022-05-16 00:26:05,717 INFO [train.py:812] (7/8) Epoch 35, batch 3750, loss[loss=0.1702, simple_loss=0.2537, pruned_loss=0.0434, over 4494.00 frames.], tot_loss[loss=0.151, simple_loss=0.2437, pruned_loss=0.02911, over 1417217.99 frames.], batch size: 52, lr: 2.21e-04
+2022-05-16 00:27:04,285 INFO [train.py:812] (7/8) Epoch 35, batch 3800, loss[loss=0.1528, simple_loss=0.2553, pruned_loss=0.0252, over 6764.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2434, pruned_loss=0.02906, over 1418159.87 frames.], batch size: 31, lr: 2.21e-04
+2022-05-16 00:28:02,121 INFO [train.py:812] (7/8) Epoch 35, batch 3850, loss[loss=0.1691, simple_loss=0.2536, pruned_loss=0.04227, over 7297.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2433, pruned_loss=0.02918, over 1421209.22 frames.], batch size: 24, lr: 2.21e-04
+2022-05-16 00:29:01,036 INFO [train.py:812] (7/8) Epoch 35, batch 3900, loss[loss=0.1537, simple_loss=0.2326, pruned_loss=0.03743, over 6836.00 frames.], tot_loss[loss=0.151, simple_loss=0.2433, pruned_loss=0.0293, over 1418672.63 frames.], batch size: 15, lr: 2.21e-04
+2022-05-16 00:30:00,087 INFO [train.py:812] (7/8) Epoch 35, batch 3950, loss[loss=0.1563, simple_loss=0.2487, pruned_loss=0.03198, over 7149.00 frames.], tot_loss[loss=0.151, simple_loss=0.2432, pruned_loss=0.02941, over 1418993.26 frames.], batch size: 17, lr: 2.21e-04
+2022-05-16 00:30:58,312 INFO [train.py:812] (7/8) Epoch 35, batch 4000, loss[loss=0.1315, simple_loss=0.2146, pruned_loss=0.02419, over 7010.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2426, pruned_loss=0.02924, over 1418111.84 frames.], batch size: 16, lr: 2.21e-04
+2022-05-16 00:32:02,102 INFO [train.py:812] (7/8) Epoch 35, batch 4050, loss[loss=0.1607, simple_loss=0.2551, pruned_loss=0.03316, over 6297.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02961, over 1420987.62 frames.], batch size: 37, lr: 2.21e-04
+2022-05-16 00:33:00,900 INFO [train.py:812] (7/8) Epoch 35, batch 4100, loss[loss=0.1549, simple_loss=0.2492, pruned_loss=0.03034, over 7217.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2436, pruned_loss=0.02946, over 1426084.37 frames.], batch size: 21, lr: 2.21e-04
+2022-05-16 00:33:59,532 INFO [train.py:812] (7/8) Epoch 35, batch 4150, loss[loss=0.1387, simple_loss=0.2348, pruned_loss=0.02128, over 7319.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2425, pruned_loss=0.02917, over 1424702.04 frames.], batch size: 21, lr: 2.21e-04
+2022-05-16 00:34:58,351 INFO [train.py:812] (7/8) Epoch 35, batch 4200, loss[loss=0.1354, simple_loss=0.236, pruned_loss=0.01743, over 7322.00 frames.], tot_loss[loss=0.1509, simple_loss=0.243, pruned_loss=0.02938, over 1423240.96 frames.], batch size: 21, lr: 2.21e-04
+2022-05-16 00:35:57,153 INFO [train.py:812] (7/8) Epoch 35, batch 4250, loss[loss=0.1525, simple_loss=0.2345, pruned_loss=0.03524, over 7283.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2426, pruned_loss=0.02925, over 1427370.42 frames.], batch size: 17, lr: 2.21e-04
+2022-05-16 00:36:55,262 INFO [train.py:812] (7/8) Epoch 35, batch 4300, loss[loss=0.165, simple_loss=0.2583, pruned_loss=0.0358, over 7162.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2417, pruned_loss=0.02909, over 1418396.02 frames.], batch size: 26, lr: 2.21e-04
+2022-05-16 00:37:53,259 INFO [train.py:812] (7/8) Epoch 35, batch 4350, loss[loss=0.1694, simple_loss=0.263, pruned_loss=0.03789, over 7277.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.0295, over 1414685.92 frames.], batch size: 24, lr: 2.21e-04
+2022-05-16 00:38:52,053 INFO [train.py:812] (7/8) Epoch 35, batch 4400, loss[loss=0.1366, simple_loss=0.222, pruned_loss=0.02563, over 7157.00 frames.], tot_loss[loss=0.1516, simple_loss=0.244, pruned_loss=0.02963, over 1408651.28 frames.], batch size: 19, lr: 2.21e-04
+2022-05-16 00:39:50,126 INFO [train.py:812] (7/8) Epoch 35, batch 4450, loss[loss=0.1674, simple_loss=0.2618, pruned_loss=0.03647, over 6798.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2443, pruned_loss=0.02966, over 1392618.20 frames.], batch size: 31, lr: 2.21e-04
+2022-05-16 00:40:48,511 INFO [train.py:812] (7/8) Epoch 35, batch 4500, loss[loss=0.1778, simple_loss=0.2718, pruned_loss=0.04192, over 7153.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03032, over 1378777.89 frames.], batch size: 26, lr: 2.21e-04
+2022-05-16 00:41:45,665 INFO [train.py:812] (7/8) Epoch 35, batch 4550, loss[loss=0.1904, simple_loss=0.278, pruned_loss=0.05142, over 5204.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2463, pruned_loss=0.03111, over 1353791.87 frames.], batch size: 53, lr: 2.21e-04
+2022-05-16 00:42:50,930 INFO [train.py:812] (7/8) Epoch 36, batch 0, loss[loss=0.1383, simple_loss=0.2339, pruned_loss=0.02134, over 7342.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2339, pruned_loss=0.02134, over 7342.00 frames.], batch size: 20, lr: 2.18e-04
+2022-05-16 00:43:50,540 INFO [train.py:812] (7/8) Epoch 36, batch 50, loss[loss=0.1585, simple_loss=0.2454, pruned_loss=0.03583, over 7440.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2426, pruned_loss=0.02907, over 316454.21 frames.], batch size: 20, lr: 2.18e-04
+2022-05-16 00:44:48,796 INFO [train.py:812] (7/8) Epoch 36, batch 100, loss[loss=0.1442, simple_loss=0.2367, pruned_loss=0.02582, over 4890.00 frames.], tot_loss[loss=0.15, simple_loss=0.2426, pruned_loss=0.02868, over 561223.73 frames.], batch size: 52, lr: 2.17e-04
+2022-05-16 00:45:47,237 INFO [train.py:812] (7/8) Epoch 36, batch 150, loss[loss=0.1381, simple_loss=0.2327, pruned_loss=0.02172, over 7247.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2414, pruned_loss=0.0291, over 750569.56 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 00:46:46,285 INFO [train.py:812] (7/8) Epoch 36, batch 200, loss[loss=0.1501, simple_loss=0.2538, pruned_loss=0.02316, over 7324.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2412, pruned_loss=0.02893, over 900508.25 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 00:47:45,339 INFO [train.py:812] (7/8) Epoch 36, batch 250, loss[loss=0.1447, simple_loss=0.2368, pruned_loss=0.02626, over 7157.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2406, pruned_loss=0.02909, over 1020223.06 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 00:48:43,661 INFO [train.py:812] (7/8) Epoch 36, batch 300, loss[loss=0.1711, simple_loss=0.2635, pruned_loss=0.03936, over 7132.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2408, pruned_loss=0.029, over 1105437.22 frames.], batch size: 26, lr: 2.17e-04
+2022-05-16 00:49:42,225 INFO [train.py:812] (7/8) Epoch 36, batch 350, loss[loss=0.1638, simple_loss=0.2582, pruned_loss=0.03472, over 6749.00 frames.], tot_loss[loss=0.15, simple_loss=0.2419, pruned_loss=0.02908, over 1174441.71 frames.], batch size: 31, lr: 2.17e-04
+2022-05-16 00:50:40,192 INFO [train.py:812] (7/8) Epoch 36, batch 400, loss[loss=0.1686, simple_loss=0.2577, pruned_loss=0.03972, over 7217.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02946, over 1229719.17 frames.], batch size: 22, lr: 2.17e-04
+2022-05-16 00:51:39,747 INFO [train.py:812] (7/8) Epoch 36, batch 450, loss[loss=0.1532, simple_loss=0.2453, pruned_loss=0.03051, over 7148.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02945, over 1277702.38 frames.], batch size: 26, lr: 2.17e-04
+2022-05-16 00:52:38,609 INFO [train.py:812] (7/8) Epoch 36, batch 500, loss[loss=0.1591, simple_loss=0.2523, pruned_loss=0.03299, over 7191.00 frames.], tot_loss[loss=0.151, simple_loss=0.2433, pruned_loss=0.02938, over 1309690.71 frames.], batch size: 23, lr: 2.17e-04
+2022-05-16 00:53:37,443 INFO [train.py:812] (7/8) Epoch 36, batch 550, loss[loss=0.1504, simple_loss=0.2448, pruned_loss=0.02796, over 7426.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2438, pruned_loss=0.02916, over 1336154.21 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 00:54:35,753 INFO [train.py:812] (7/8) Epoch 36, batch 600, loss[loss=0.1581, simple_loss=0.2512, pruned_loss=0.0325, over 7204.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2427, pruned_loss=0.02896, over 1358953.74 frames.], batch size: 23, lr: 2.17e-04
+2022-05-16 00:55:34,865 INFO [train.py:812] (7/8) Epoch 36, batch 650, loss[loss=0.1495, simple_loss=0.236, pruned_loss=0.03149, over 7156.00 frames.], tot_loss[loss=0.1498, simple_loss=0.242, pruned_loss=0.02878, over 1372949.29 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 00:56:33,817 INFO [train.py:812] (7/8) Epoch 36, batch 700, loss[loss=0.1406, simple_loss=0.2274, pruned_loss=0.02684, over 7261.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2413, pruned_loss=0.02853, over 1383857.47 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 00:57:42,571 INFO [train.py:812] (7/8) Epoch 36, batch 750, loss[loss=0.1263, simple_loss=0.22, pruned_loss=0.01626, over 7325.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2415, pruned_loss=0.02869, over 1384599.02 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 00:58:59,883 INFO [train.py:812] (7/8) Epoch 36, batch 800, loss[loss=0.1634, simple_loss=0.2636, pruned_loss=0.03163, over 7421.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2419, pruned_loss=0.02853, over 1393414.51 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 00:59:58,255 INFO [train.py:812] (7/8) Epoch 36, batch 850, loss[loss=0.1484, simple_loss=0.2474, pruned_loss=0.0247, over 7212.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2427, pruned_loss=0.02882, over 1394811.96 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 01:00:57,358 INFO [train.py:812] (7/8) Epoch 36, batch 900, loss[loss=0.1519, simple_loss=0.2539, pruned_loss=0.02494, over 6757.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2428, pruned_loss=0.02891, over 1401897.74 frames.], batch size: 31, lr: 2.17e-04
+2022-05-16 01:01:55,225 INFO [train.py:812] (7/8) Epoch 36, batch 950, loss[loss=0.1303, simple_loss=0.2062, pruned_loss=0.02716, over 6997.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2426, pruned_loss=0.02895, over 1404911.75 frames.], batch size: 16, lr: 2.17e-04
+2022-05-16 01:03:03,149 INFO [train.py:812] (7/8) Epoch 36, batch 1000, loss[loss=0.1293, simple_loss=0.2164, pruned_loss=0.02109, over 7271.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2429, pruned_loss=0.02911, over 1407326.65 frames.], batch size: 17, lr: 2.17e-04
+2022-05-16 01:04:02,095 INFO [train.py:812] (7/8) Epoch 36, batch 1050, loss[loss=0.1397, simple_loss=0.2317, pruned_loss=0.02387, over 7361.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2424, pruned_loss=0.02899, over 1407100.84 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 01:05:09,934 INFO [train.py:812] (7/8) Epoch 36, batch 1100, loss[loss=0.1719, simple_loss=0.2713, pruned_loss=0.03627, over 7213.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2432, pruned_loss=0.02917, over 1407674.79 frames.], batch size: 22, lr: 2.17e-04
+2022-05-16 01:06:19,100 INFO [train.py:812] (7/8) Epoch 36, batch 1150, loss[loss=0.1564, simple_loss=0.2582, pruned_loss=0.02728, over 7288.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02921, over 1413322.94 frames.], batch size: 24, lr: 2.17e-04
+2022-05-16 01:07:18,020 INFO [train.py:812] (7/8) Epoch 36, batch 1200, loss[loss=0.1259, simple_loss=0.2114, pruned_loss=0.02023, over 7289.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2439, pruned_loss=0.02948, over 1408889.46 frames.], batch size: 17, lr: 2.17e-04
+2022-05-16 01:08:17,012 INFO [train.py:812] (7/8) Epoch 36, batch 1250, loss[loss=0.1197, simple_loss=0.2037, pruned_loss=0.01785, over 7000.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02912, over 1410666.23 frames.], batch size: 16, lr: 2.17e-04
+2022-05-16 01:09:23,821 INFO [train.py:812] (7/8) Epoch 36, batch 1300, loss[loss=0.1214, simple_loss=0.211, pruned_loss=0.01586, over 7150.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02891, over 1414279.05 frames.], batch size: 17, lr: 2.17e-04
+2022-05-16 01:10:23,397 INFO [train.py:812] (7/8) Epoch 36, batch 1350, loss[loss=0.1446, simple_loss=0.2356, pruned_loss=0.02682, over 7271.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2422, pruned_loss=0.0292, over 1419076.05 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 01:11:21,655 INFO [train.py:812] (7/8) Epoch 36, batch 1400, loss[loss=0.1451, simple_loss=0.2308, pruned_loss=0.02975, over 7005.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2429, pruned_loss=0.02939, over 1417768.52 frames.], batch size: 16, lr: 2.17e-04
+2022-05-16 01:12:20,397 INFO [train.py:812] (7/8) Epoch 36, batch 1450, loss[loss=0.1409, simple_loss=0.2282, pruned_loss=0.02677, over 6796.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2431, pruned_loss=0.02959, over 1414940.42 frames.], batch size: 15, lr: 2.17e-04
+2022-05-16 01:13:19,137 INFO [train.py:812] (7/8) Epoch 36, batch 1500, loss[loss=0.1595, simple_loss=0.2597, pruned_loss=0.02965, over 7319.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2441, pruned_loss=0.02968, over 1419011.41 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 01:14:17,149 INFO [train.py:812] (7/8) Epoch 36, batch 1550, loss[loss=0.1416, simple_loss=0.2344, pruned_loss=0.02439, over 7224.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2434, pruned_loss=0.02961, over 1420132.86 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 01:15:14,913 INFO [train.py:812] (7/8) Epoch 36, batch 1600, loss[loss=0.1736, simple_loss=0.2601, pruned_loss=0.04353, over 7357.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02956, over 1420080.52 frames.], batch size: 23, lr: 2.16e-04
+2022-05-16 01:16:13,341 INFO [train.py:812] (7/8) Epoch 36, batch 1650, loss[loss=0.1424, simple_loss=0.2364, pruned_loss=0.02424, over 7163.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02938, over 1421566.91 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:17:10,688 INFO [train.py:812] (7/8) Epoch 36, batch 1700, loss[loss=0.1774, simple_loss=0.2727, pruned_loss=0.04105, over 7282.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.02972, over 1424299.05 frames.], batch size: 25, lr: 2.16e-04
+2022-05-16 01:18:09,661 INFO [train.py:812] (7/8) Epoch 36, batch 1750, loss[loss=0.1386, simple_loss=0.2269, pruned_loss=0.02513, over 7268.00 frames.], tot_loss[loss=0.151, simple_loss=0.243, pruned_loss=0.02953, over 1420386.20 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:19:07,107 INFO [train.py:812] (7/8) Epoch 36, batch 1800, loss[loss=0.1674, simple_loss=0.2703, pruned_loss=0.03224, over 7216.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.02927, over 1422219.59 frames.], batch size: 23, lr: 2.16e-04
+2022-05-16 01:20:05,581 INFO [train.py:812] (7/8) Epoch 36, batch 1850, loss[loss=0.1523, simple_loss=0.2529, pruned_loss=0.02586, over 7116.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02914, over 1424520.12 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:21:04,185 INFO [train.py:812] (7/8) Epoch 36, batch 1900, loss[loss=0.1731, simple_loss=0.2653, pruned_loss=0.04044, over 6785.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2426, pruned_loss=0.02903, over 1424408.76 frames.], batch size: 31, lr: 2.16e-04
+2022-05-16 01:22:03,028 INFO [train.py:812] (7/8) Epoch 36, batch 1950, loss[loss=0.1407, simple_loss=0.2363, pruned_loss=0.0225, over 7226.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2416, pruned_loss=0.0289, over 1421615.02 frames.], batch size: 20, lr: 2.16e-04
+2022-05-16 01:23:01,534 INFO [train.py:812] (7/8) Epoch 36, batch 2000, loss[loss=0.1263, simple_loss=0.2055, pruned_loss=0.02357, over 6994.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02931, over 1418376.82 frames.], batch size: 16, lr: 2.16e-04
+2022-05-16 01:24:00,274 INFO [train.py:812] (7/8) Epoch 36, batch 2050, loss[loss=0.1586, simple_loss=0.2585, pruned_loss=0.02935, over 7319.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2418, pruned_loss=0.02871, over 1423099.64 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:24:59,298 INFO [train.py:812] (7/8) Epoch 36, batch 2100, loss[loss=0.1308, simple_loss=0.2278, pruned_loss=0.01685, over 7414.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2415, pruned_loss=0.02865, over 1422563.80 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:25:59,221 INFO [train.py:812] (7/8) Epoch 36, batch 2150, loss[loss=0.1429, simple_loss=0.2238, pruned_loss=0.03095, over 7258.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02882, over 1424913.58 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:26:58,719 INFO [train.py:812] (7/8) Epoch 36, batch 2200, loss[loss=0.1464, simple_loss=0.2304, pruned_loss=0.03125, over 7400.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.02883, over 1425164.51 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:27:57,357 INFO [train.py:812] (7/8) Epoch 36, batch 2250, loss[loss=0.1474, simple_loss=0.2483, pruned_loss=0.02323, over 7335.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2426, pruned_loss=0.02885, over 1422188.39 frames.], batch size: 22, lr: 2.16e-04
+2022-05-16 01:28:55,644 INFO [train.py:812] (7/8) Epoch 36, batch 2300, loss[loss=0.1294, simple_loss=0.2144, pruned_loss=0.02225, over 7137.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2415, pruned_loss=0.02892, over 1424413.89 frames.], batch size: 17, lr: 2.16e-04
+2022-05-16 01:29:55,120 INFO [train.py:812] (7/8) Epoch 36, batch 2350, loss[loss=0.1956, simple_loss=0.2818, pruned_loss=0.05474, over 4989.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02918, over 1422711.37 frames.], batch size: 52, lr: 2.16e-04
+2022-05-16 01:30:54,430 INFO [train.py:812] (7/8) Epoch 36, batch 2400, loss[loss=0.1439, simple_loss=0.2293, pruned_loss=0.02932, over 7420.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.02893, over 1425858.44 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:31:54,055 INFO [train.py:812] (7/8) Epoch 36, batch 2450, loss[loss=0.1556, simple_loss=0.2281, pruned_loss=0.04159, over 7156.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02874, over 1421704.27 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:32:52,252 INFO [train.py:812] (7/8) Epoch 36, batch 2500, loss[loss=0.1528, simple_loss=0.2421, pruned_loss=0.03172, over 7141.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2417, pruned_loss=0.02879, over 1425397.41 frames.], batch size: 20, lr: 2.16e-04
+2022-05-16 01:33:51,453 INFO [train.py:812] (7/8) Epoch 36, batch 2550, loss[loss=0.1689, simple_loss=0.2487, pruned_loss=0.0445, over 7351.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02892, over 1423678.71 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:34:50,044 INFO [train.py:812] (7/8) Epoch 36, batch 2600, loss[loss=0.1547, simple_loss=0.241, pruned_loss=0.0342, over 7161.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.029, over 1424283.96 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:35:48,610 INFO [train.py:812] (7/8) Epoch 36, batch 2650, loss[loss=0.2157, simple_loss=0.299, pruned_loss=0.06615, over 5269.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.02911, over 1423759.92 frames.], batch size: 52, lr: 2.16e-04
+2022-05-16 01:36:47,005 INFO [train.py:812] (7/8) Epoch 36, batch 2700, loss[loss=0.1477, simple_loss=0.2451, pruned_loss=0.02517, over 7312.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2417, pruned_loss=0.02902, over 1423832.90 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:37:45,798 INFO [train.py:812] (7/8) Epoch 36, batch 2750, loss[loss=0.1392, simple_loss=0.2382, pruned_loss=0.02008, over 7116.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2418, pruned_loss=0.02901, over 1426029.77 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:38:44,972 INFO [train.py:812] (7/8) Epoch 36, batch 2800, loss[loss=0.1855, simple_loss=0.2788, pruned_loss=0.04609, over 7196.00 frames.], tot_loss[loss=0.15, simple_loss=0.2416, pruned_loss=0.0292, over 1428221.18 frames.], batch size: 22, lr: 2.16e-04
+2022-05-16 01:39:44,904 INFO [train.py:812] (7/8) Epoch 36, batch 2850, loss[loss=0.1309, simple_loss=0.2162, pruned_loss=0.02283, over 7285.00 frames.], tot_loss[loss=0.15, simple_loss=0.2413, pruned_loss=0.02934, over 1429197.83 frames.], batch size: 17, lr: 2.16e-04
+2022-05-16 01:40:43,914 INFO [train.py:812] (7/8) Epoch 36, batch 2900, loss[loss=0.1379, simple_loss=0.2291, pruned_loss=0.02338, over 7261.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2408, pruned_loss=0.02917, over 1427937.07 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:41:42,664 INFO [train.py:812] (7/8) Epoch 36, batch 2950, loss[loss=0.1352, simple_loss=0.2313, pruned_loss=0.01956, over 7175.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2419, pruned_loss=0.02921, over 1425723.45 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:42:41,203 INFO [train.py:812] (7/8) Epoch 36, batch 3000, loss[loss=0.1453, simple_loss=0.2504, pruned_loss=0.02013, over 7162.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2433, pruned_loss=0.02956, over 1422535.70 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:42:41,205 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-16 01:42:48,528 INFO [train.py:841] (7/8) Epoch 36, validation: loss=0.1533, simple_loss=0.2487, pruned_loss=0.02893, over 698248.00 frames.
+2022-05-16 01:43:48,428 INFO [train.py:812] (7/8) Epoch 36, batch 3050, loss[loss=0.1668, simple_loss=0.2647, pruned_loss=0.0344, over 7275.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2428, pruned_loss=0.02938, over 1425177.69 frames.], batch size: 24, lr: 2.16e-04
+2022-05-16 01:44:47,772 INFO [train.py:812] (7/8) Epoch 36, batch 3100, loss[loss=0.1757, simple_loss=0.2574, pruned_loss=0.047, over 7307.00 frames.], tot_loss[loss=0.1512, simple_loss=0.243, pruned_loss=0.02973, over 1429306.49 frames.], batch size: 25, lr: 2.15e-04
+2022-05-16 01:45:47,530 INFO [train.py:812] (7/8) Epoch 36, batch 3150, loss[loss=0.1699, simple_loss=0.2731, pruned_loss=0.03334, over 7379.00 frames.], tot_loss[loss=0.151, simple_loss=0.2431, pruned_loss=0.02948, over 1427707.47 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 01:46:46,148 INFO [train.py:812] (7/8) Epoch 36, batch 3200, loss[loss=0.1362, simple_loss=0.2288, pruned_loss=0.02179, over 7144.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2434, pruned_loss=0.02955, over 1421169.46 frames.], batch size: 17, lr: 2.15e-04
+2022-05-16 01:47:45,926 INFO [train.py:812] (7/8) Epoch 36, batch 3250, loss[loss=0.1729, simple_loss=0.2558, pruned_loss=0.04505, over 4917.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.02946, over 1418498.14 frames.], batch size: 53, lr: 2.15e-04
+2022-05-16 01:48:53,240 INFO [train.py:812] (7/8) Epoch 36, batch 3300, loss[loss=0.1462, simple_loss=0.2434, pruned_loss=0.0245, over 7202.00 frames.], tot_loss[loss=0.151, simple_loss=0.2437, pruned_loss=0.02919, over 1421984.33 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 01:49:52,264 INFO [train.py:812] (7/8) Epoch 36, batch 3350, loss[loss=0.1568, simple_loss=0.2532, pruned_loss=0.03014, over 7198.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2441, pruned_loss=0.02948, over 1425717.33 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 01:50:50,268 INFO [train.py:812] (7/8) Epoch 36, batch 3400, loss[loss=0.1414, simple_loss=0.2256, pruned_loss=0.02855, over 7246.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2433, pruned_loss=0.0295, over 1423849.38 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 01:51:53,861 INFO [train.py:812] (7/8) Epoch 36, batch 3450, loss[loss=0.141, simple_loss=0.2225, pruned_loss=0.02972, over 7281.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02913, over 1421741.14 frames.], batch size: 17, lr: 2.15e-04
+2022-05-16 01:52:52,289 INFO [train.py:812] (7/8) Epoch 36, batch 3500, loss[loss=0.1583, simple_loss=0.2603, pruned_loss=0.02814, over 7410.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2422, pruned_loss=0.02898, over 1419163.64 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 01:53:50,978 INFO [train.py:812] (7/8) Epoch 36, batch 3550, loss[loss=0.1627, simple_loss=0.2672, pruned_loss=0.02905, over 7063.00 frames.], tot_loss[loss=0.15, simple_loss=0.2418, pruned_loss=0.02907, over 1423434.42 frames.], batch size: 28, lr: 2.15e-04
+2022-05-16 01:54:49,028 INFO [train.py:812] (7/8) Epoch 36, batch 3600, loss[loss=0.1429, simple_loss=0.2452, pruned_loss=0.02027, over 7294.00 frames.], tot_loss[loss=0.1508, simple_loss=0.243, pruned_loss=0.02928, over 1422472.83 frames.], batch size: 25, lr: 2.15e-04
+2022-05-16 01:55:48,168 INFO [train.py:812] (7/8) Epoch 36, batch 3650, loss[loss=0.1687, simple_loss=0.2725, pruned_loss=0.03248, over 7282.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.02934, over 1424361.49 frames.], batch size: 24, lr: 2.15e-04
+2022-05-16 01:56:46,044 INFO [train.py:812] (7/8) Epoch 36, batch 3700, loss[loss=0.1474, simple_loss=0.2428, pruned_loss=0.02601, over 7114.00 frames.], tot_loss[loss=0.1502, simple_loss=0.242, pruned_loss=0.02917, over 1426508.65 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 01:57:44,772 INFO [train.py:812] (7/8) Epoch 36, batch 3750, loss[loss=0.1677, simple_loss=0.2587, pruned_loss=0.03836, over 7330.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02901, over 1426515.87 frames.], batch size: 22, lr: 2.15e-04
+2022-05-16 01:58:43,612 INFO [train.py:812] (7/8) Epoch 36, batch 3800, loss[loss=0.1366, simple_loss=0.2221, pruned_loss=0.02557, over 7357.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2436, pruned_loss=0.02954, over 1428583.89 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 01:59:42,783 INFO [train.py:812] (7/8) Epoch 36, batch 3850, loss[loss=0.1384, simple_loss=0.2263, pruned_loss=0.02526, over 6987.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02955, over 1424731.74 frames.], batch size: 16, lr: 2.15e-04
+2022-05-16 02:00:41,808 INFO [train.py:812] (7/8) Epoch 36, batch 3900, loss[loss=0.164, simple_loss=0.2452, pruned_loss=0.04135, over 7196.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2428, pruned_loss=0.02945, over 1426748.31 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 02:01:40,064 INFO [train.py:812] (7/8) Epoch 36, batch 3950, loss[loss=0.1416, simple_loss=0.248, pruned_loss=0.01754, over 6767.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.0296, over 1424598.87 frames.], batch size: 31, lr: 2.15e-04
+2022-05-16 02:02:38,486 INFO [train.py:812] (7/8) Epoch 36, batch 4000, loss[loss=0.1595, simple_loss=0.2562, pruned_loss=0.03142, over 7020.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2438, pruned_loss=0.02953, over 1424633.93 frames.], batch size: 28, lr: 2.15e-04
+2022-05-16 02:03:36,289 INFO [train.py:812] (7/8) Epoch 36, batch 4050, loss[loss=0.1621, simple_loss=0.2573, pruned_loss=0.03348, over 7225.00 frames.], tot_loss[loss=0.1505, simple_loss=0.243, pruned_loss=0.02904, over 1426627.17 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 02:04:34,920 INFO [train.py:812] (7/8) Epoch 36, batch 4100, loss[loss=0.1143, simple_loss=0.2051, pruned_loss=0.01174, over 7134.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02915, over 1426781.05 frames.], batch size: 17, lr: 2.15e-04
+2022-05-16 02:05:34,475 INFO [train.py:812] (7/8) Epoch 36, batch 4150, loss[loss=0.1566, simple_loss=0.2485, pruned_loss=0.03235, over 7201.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2426, pruned_loss=0.02922, over 1419040.45 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 02:06:32,921 INFO [train.py:812] (7/8) Epoch 36, batch 4200, loss[loss=0.1493, simple_loss=0.2436, pruned_loss=0.02746, over 7237.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2439, pruned_loss=0.02982, over 1417291.16 frames.], batch size: 20, lr: 2.15e-04
+2022-05-16 02:07:31,854 INFO [train.py:812] (7/8) Epoch 36, batch 4250, loss[loss=0.1528, simple_loss=0.2417, pruned_loss=0.03191, over 7202.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2434, pruned_loss=0.02976, over 1415448.30 frames.], batch size: 22, lr: 2.15e-04
+2022-05-16 02:08:31,018 INFO [train.py:812] (7/8) Epoch 36, batch 4300, loss[loss=0.1722, simple_loss=0.269, pruned_loss=0.03772, over 7199.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2434, pruned_loss=0.02979, over 1412187.11 frames.], batch size: 22, lr: 2.15e-04
+2022-05-16 02:09:30,600 INFO [train.py:812] (7/8) Epoch 36, batch 4350, loss[loss=0.1505, simple_loss=0.2357, pruned_loss=0.03269, over 7424.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2423, pruned_loss=0.02954, over 1411396.35 frames.], batch size: 20, lr: 2.15e-04
+2022-05-16 02:10:29,656 INFO [train.py:812] (7/8) Epoch 36, batch 4400, loss[loss=0.1363, simple_loss=0.2318, pruned_loss=0.02043, over 7358.00 frames.], tot_loss[loss=0.15, simple_loss=0.2417, pruned_loss=0.02913, over 1416130.92 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 02:11:29,756 INFO [train.py:812] (7/8) Epoch 36, batch 4450, loss[loss=0.178, simple_loss=0.2722, pruned_loss=0.04185, over 7217.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2415, pruned_loss=0.02897, over 1406908.20 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 02:12:28,160 INFO [train.py:812] (7/8) Epoch 36, batch 4500, loss[loss=0.1439, simple_loss=0.2361, pruned_loss=0.02582, over 7217.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2415, pruned_loss=0.0288, over 1394804.51 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 02:13:26,428 INFO [train.py:812] (7/8) Epoch 36, batch 4550, loss[loss=0.1396, simple_loss=0.2245, pruned_loss=0.02737, over 7254.00 frames.], tot_loss[loss=0.1503, simple_loss=0.242, pruned_loss=0.02925, over 1356211.42 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 02:14:35,982 INFO [train.py:812] (7/8) Epoch 37, batch 0, loss[loss=0.1614, simple_loss=0.255, pruned_loss=0.03387, over 7351.00 frames.], tot_loss[loss=0.1614, simple_loss=0.255, pruned_loss=0.03387, over 7351.00 frames.], batch size: 22, lr: 2.12e-04
+2022-05-16 02:15:35,012 INFO [train.py:812] (7/8) Epoch 37, batch 50, loss[loss=0.1583, simple_loss=0.2434, pruned_loss=0.03658, over 7065.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2417, pruned_loss=0.02869, over 320955.43 frames.], batch size: 18, lr: 2.12e-04
+2022-05-16 02:16:33,793 INFO [train.py:812] (7/8) Epoch 37, batch 100, loss[loss=0.137, simple_loss=0.2283, pruned_loss=0.02285, over 7330.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2417, pruned_loss=0.02942, over 566735.12 frames.], batch size: 20, lr: 2.12e-04
+2022-05-16 02:17:32,762 INFO [train.py:812] (7/8) Epoch 37, batch 150, loss[loss=0.1533, simple_loss=0.2365, pruned_loss=0.03505, over 7036.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2429, pruned_loss=0.03015, over 754306.88 frames.], batch size: 28, lr: 2.11e-04
+2022-05-16 02:18:31,131 INFO [train.py:812] (7/8) Epoch 37, batch 200, loss[loss=0.1665, simple_loss=0.2608, pruned_loss=0.03608, over 7310.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2454, pruned_loss=0.02994, over 905677.81 frames.], batch size: 21, lr: 2.11e-04
+2022-05-16 02:19:29,667 INFO [train.py:812] (7/8) Epoch 37, batch 250, loss[loss=0.1492, simple_loss=0.2377, pruned_loss=0.03038, over 7261.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2437, pruned_loss=0.02934, over 1017921.33 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:20:28,602 INFO [train.py:812] (7/8) Epoch 37, batch 300, loss[loss=0.141, simple_loss=0.2447, pruned_loss=0.01869, over 7353.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2434, pruned_loss=0.02945, over 1104581.91 frames.], batch size: 22, lr: 2.11e-04
+2022-05-16 02:21:27,116 INFO [train.py:812] (7/8) Epoch 37, batch 350, loss[loss=0.1375, simple_loss=0.2309, pruned_loss=0.02207, over 7152.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2435, pruned_loss=0.02965, over 1174018.95 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:22:25,691 INFO [train.py:812] (7/8) Epoch 37, batch 400, loss[loss=0.1556, simple_loss=0.246, pruned_loss=0.03265, over 7230.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2429, pruned_loss=0.02909, over 1232729.17 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:23:24,549 INFO [train.py:812] (7/8) Epoch 37, batch 450, loss[loss=0.1481, simple_loss=0.2549, pruned_loss=0.02064, over 7144.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2432, pruned_loss=0.02908, over 1276979.76 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:24:21,878 INFO [train.py:812] (7/8) Epoch 37, batch 500, loss[loss=0.1335, simple_loss=0.2263, pruned_loss=0.02037, over 7231.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.02894, over 1306891.61 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:25:21,129 INFO [train.py:812] (7/8) Epoch 37, batch 550, loss[loss=0.1482, simple_loss=0.2366, pruned_loss=0.02992, over 7446.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2432, pruned_loss=0.02907, over 1321936.37 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:26:19,471 INFO [train.py:812] (7/8) Epoch 37, batch 600, loss[loss=0.1397, simple_loss=0.2339, pruned_loss=0.02274, over 7429.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2418, pruned_loss=0.02856, over 1346961.91 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:27:18,126 INFO [train.py:812] (7/8) Epoch 37, batch 650, loss[loss=0.1114, simple_loss=0.1937, pruned_loss=0.01457, over 7129.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2404, pruned_loss=0.02806, over 1366635.87 frames.], batch size: 17, lr: 2.11e-04
+2022-05-16 02:28:16,744 INFO [train.py:812] (7/8) Epoch 37, batch 700, loss[loss=0.1427, simple_loss=0.2313, pruned_loss=0.02712, over 7230.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2407, pruned_loss=0.02837, over 1379937.78 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:29:16,763 INFO [train.py:812] (7/8) Epoch 37, batch 750, loss[loss=0.1476, simple_loss=0.2465, pruned_loss=0.02431, over 7163.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2405, pruned_loss=0.02835, over 1388162.71 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:30:15,265 INFO [train.py:812] (7/8) Epoch 37, batch 800, loss[loss=0.1506, simple_loss=0.2307, pruned_loss=0.03528, over 7408.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2403, pruned_loss=0.02844, over 1399635.70 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:31:14,051 INFO [train.py:812] (7/8) Epoch 37, batch 850, loss[loss=0.1515, simple_loss=0.2481, pruned_loss=0.0274, over 7262.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2413, pruned_loss=0.02877, over 1399347.62 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:32:12,873 INFO [train.py:812] (7/8) Epoch 37, batch 900, loss[loss=0.131, simple_loss=0.2223, pruned_loss=0.01984, over 7071.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2405, pruned_loss=0.0282, over 1407657.18 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:33:11,845 INFO [train.py:812] (7/8) Epoch 37, batch 950, loss[loss=0.1426, simple_loss=0.2266, pruned_loss=0.02932, over 7282.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2405, pruned_loss=0.02797, over 1411042.39 frames.], batch size: 17, lr: 2.11e-04
+2022-05-16 02:34:09,801 INFO [train.py:812] (7/8) Epoch 37, batch 1000, loss[loss=0.1603, simple_loss=0.2585, pruned_loss=0.03102, over 6857.00 frames.], tot_loss[loss=0.148, simple_loss=0.2404, pruned_loss=0.02779, over 1414185.62 frames.], batch size: 31, lr: 2.11e-04
+2022-05-16 02:35:08,661 INFO [train.py:812] (7/8) Epoch 37, batch 1050, loss[loss=0.1655, simple_loss=0.2666, pruned_loss=0.03218, over 7388.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2407, pruned_loss=0.02832, over 1417756.78 frames.], batch size: 23, lr: 2.11e-04
+2022-05-16 02:36:07,862 INFO [train.py:812] (7/8) Epoch 37, batch 1100, loss[loss=0.1498, simple_loss=0.2503, pruned_loss=0.02461, over 7212.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2411, pruned_loss=0.02866, over 1418771.87 frames.], batch size: 21, lr: 2.11e-04
+2022-05-16 02:37:06,633 INFO [train.py:812] (7/8) Epoch 37, batch 1150, loss[loss=0.1688, simple_loss=0.2564, pruned_loss=0.04063, over 5302.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2413, pruned_loss=0.02887, over 1418170.30 frames.], batch size: 52, lr: 2.11e-04
+2022-05-16 02:38:04,317 INFO [train.py:812] (7/8) Epoch 37, batch 1200, loss[loss=0.1437, simple_loss=0.245, pruned_loss=0.02115, over 7144.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2423, pruned_loss=0.0291, over 1420332.88 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:39:03,422 INFO [train.py:812] (7/8) Epoch 37, batch 1250, loss[loss=0.1548, simple_loss=0.2464, pruned_loss=0.03155, over 7183.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2427, pruned_loss=0.02872, over 1420249.49 frames.], batch size: 22, lr: 2.11e-04
+2022-05-16 02:40:01,902 INFO [train.py:812] (7/8) Epoch 37, batch 1300, loss[loss=0.1319, simple_loss=0.2166, pruned_loss=0.02364, over 7141.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2425, pruned_loss=0.0286, over 1422387.62 frames.], batch size: 17, lr: 2.11e-04
+2022-05-16 02:41:00,884 INFO [train.py:812] (7/8) Epoch 37, batch 1350, loss[loss=0.1182, simple_loss=0.209, pruned_loss=0.01369, over 7070.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2424, pruned_loss=0.02864, over 1418416.55 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:41:59,983 INFO [train.py:812] (7/8) Epoch 37, batch 1400, loss[loss=0.1281, simple_loss=0.222, pruned_loss=0.01707, over 6980.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2424, pruned_loss=0.02873, over 1418379.62 frames.], batch size: 16, lr: 2.11e-04
+2022-05-16 02:42:58,503 INFO [train.py:812] (7/8) Epoch 37, batch 1450, loss[loss=0.2322, simple_loss=0.3055, pruned_loss=0.07949, over 7304.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02896, over 1420023.19 frames.], batch size: 24, lr: 2.11e-04
+2022-05-16 02:43:56,646 INFO [train.py:812] (7/8) Epoch 37, batch 1500, loss[loss=0.1458, simple_loss=0.2492, pruned_loss=0.02126, over 7292.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2426, pruned_loss=0.0291, over 1416522.41 frames.], batch size: 24, lr: 2.11e-04
+2022-05-16 02:44:55,819 INFO [train.py:812] (7/8) Epoch 37, batch 1550, loss[loss=0.1743, simple_loss=0.2622, pruned_loss=0.04324, over 6891.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02897, over 1411157.51 frames.], batch size: 31, lr: 2.11e-04
+2022-05-16 02:45:54,016 INFO [train.py:812] (7/8) Epoch 37, batch 1600, loss[loss=0.166, simple_loss=0.2606, pruned_loss=0.0357, over 7385.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2411, pruned_loss=0.02877, over 1411781.46 frames.], batch size: 23, lr: 2.11e-04
+2022-05-16 02:46:52,167 INFO [train.py:812] (7/8) Epoch 37, batch 1650, loss[loss=0.1731, simple_loss=0.2686, pruned_loss=0.03874, over 7196.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2417, pruned_loss=0.02898, over 1415259.28 frames.], batch size: 22, lr: 2.11e-04
+2022-05-16 02:47:50,664 INFO [train.py:812] (7/8) Epoch 37, batch 1700, loss[loss=0.145, simple_loss=0.2346, pruned_loss=0.02773, over 7160.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2422, pruned_loss=0.02885, over 1414085.88 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:48:48,786 INFO [train.py:812] (7/8) Epoch 37, batch 1750, loss[loss=0.1295, simple_loss=0.2198, pruned_loss=0.01957, over 7355.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2421, pruned_loss=0.02877, over 1408978.19 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 02:49:47,226 INFO [train.py:812] (7/8) Epoch 37, batch 1800, loss[loss=0.1657, simple_loss=0.262, pruned_loss=0.03468, over 7300.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2433, pruned_loss=0.02901, over 1410755.59 frames.], batch size: 24, lr: 2.10e-04
+2022-05-16 02:50:46,359 INFO [train.py:812] (7/8) Epoch 37, batch 1850, loss[loss=0.1549, simple_loss=0.2411, pruned_loss=0.03433, over 7258.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2424, pruned_loss=0.02886, over 1410615.69 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 02:51:45,069 INFO [train.py:812] (7/8) Epoch 37, batch 1900, loss[loss=0.1611, simple_loss=0.2643, pruned_loss=0.02896, over 6744.00 frames.], tot_loss[loss=0.151, simple_loss=0.2435, pruned_loss=0.02928, over 1416616.64 frames.], batch size: 31, lr: 2.10e-04
+2022-05-16 02:52:44,059 INFO [train.py:812] (7/8) Epoch 37, batch 1950, loss[loss=0.1427, simple_loss=0.2415, pruned_loss=0.02192, over 7223.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2428, pruned_loss=0.02882, over 1420652.20 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 02:53:42,350 INFO [train.py:812] (7/8) Epoch 37, batch 2000, loss[loss=0.17, simple_loss=0.2706, pruned_loss=0.03467, over 7414.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2427, pruned_loss=0.02885, over 1417273.85 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 02:54:41,790 INFO [train.py:812] (7/8) Epoch 37, batch 2050, loss[loss=0.1484, simple_loss=0.2451, pruned_loss=0.02587, over 7226.00 frames.], tot_loss[loss=0.1496, simple_loss=0.242, pruned_loss=0.02865, over 1420300.01 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 02:55:38,587 INFO [train.py:812] (7/8) Epoch 37, batch 2100, loss[loss=0.1781, simple_loss=0.2623, pruned_loss=0.0469, over 7147.00 frames.], tot_loss[loss=0.15, simple_loss=0.2424, pruned_loss=0.02885, over 1420269.03 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 02:56:46,830 INFO [train.py:812] (7/8) Epoch 37, batch 2150, loss[loss=0.1449, simple_loss=0.2423, pruned_loss=0.0237, over 7415.00 frames.], tot_loss[loss=0.1505, simple_loss=0.243, pruned_loss=0.02893, over 1417081.34 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 02:57:45,119 INFO [train.py:812] (7/8) Epoch 37, batch 2200, loss[loss=0.1301, simple_loss=0.2213, pruned_loss=0.01945, over 7245.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2418, pruned_loss=0.02861, over 1419889.35 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 02:58:53,441 INFO [train.py:812] (7/8) Epoch 37, batch 2250, loss[loss=0.1502, simple_loss=0.2552, pruned_loss=0.02265, over 7144.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2426, pruned_loss=0.0289, over 1421050.56 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 03:00:01,346 INFO [train.py:812] (7/8) Epoch 37, batch 2300, loss[loss=0.1545, simple_loss=0.2555, pruned_loss=0.02675, over 7177.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2432, pruned_loss=0.02897, over 1420058.76 frames.], batch size: 23, lr: 2.10e-04
+2022-05-16 03:01:01,008 INFO [train.py:812] (7/8) Epoch 37, batch 2350, loss[loss=0.1265, simple_loss=0.2104, pruned_loss=0.02132, over 7275.00 frames.], tot_loss[loss=0.151, simple_loss=0.2437, pruned_loss=0.02917, over 1413701.15 frames.], batch size: 17, lr: 2.10e-04
+2022-05-16 03:01:59,228 INFO [train.py:812] (7/8) Epoch 37, batch 2400, loss[loss=0.1603, simple_loss=0.2533, pruned_loss=0.03358, over 7304.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2428, pruned_loss=0.02865, over 1420991.69 frames.], batch size: 25, lr: 2.10e-04
+2022-05-16 03:02:57,118 INFO [train.py:812] (7/8) Epoch 37, batch 2450, loss[loss=0.1415, simple_loss=0.232, pruned_loss=0.02547, over 7143.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2424, pruned_loss=0.02898, over 1425607.65 frames.], batch size: 26, lr: 2.10e-04
+2022-05-16 03:04:04,744 INFO [train.py:812] (7/8) Epoch 37, batch 2500, loss[loss=0.1471, simple_loss=0.2376, pruned_loss=0.02828, over 7158.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2418, pruned_loss=0.02851, over 1427960.61 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 03:05:04,402 INFO [train.py:812] (7/8) Epoch 37, batch 2550, loss[loss=0.1398, simple_loss=0.2361, pruned_loss=0.02178, over 7290.00 frames.], tot_loss[loss=0.1497, simple_loss=0.242, pruned_loss=0.0287, over 1428530.29 frames.], batch size: 24, lr: 2.10e-04
+2022-05-16 03:06:02,658 INFO [train.py:812] (7/8) Epoch 37, batch 2600, loss[loss=0.1516, simple_loss=0.2413, pruned_loss=0.03096, over 7237.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2426, pruned_loss=0.02882, over 1424618.04 frames.], batch size: 16, lr: 2.10e-04
+2022-05-16 03:07:21,596 INFO [train.py:812] (7/8) Epoch 37, batch 2650, loss[loss=0.1649, simple_loss=0.2507, pruned_loss=0.03956, over 7196.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2431, pruned_loss=0.02902, over 1428217.49 frames.], batch size: 22, lr: 2.10e-04
+2022-05-16 03:08:19,647 INFO [train.py:812] (7/8) Epoch 37, batch 2700, loss[loss=0.1481, simple_loss=0.2447, pruned_loss=0.02575, over 6413.00 frames.], tot_loss[loss=0.1507, simple_loss=0.243, pruned_loss=0.02922, over 1423885.97 frames.], batch size: 37, lr: 2.10e-04
+2022-05-16 03:09:18,882 INFO [train.py:812] (7/8) Epoch 37, batch 2750, loss[loss=0.1323, simple_loss=0.2226, pruned_loss=0.021, over 5036.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2432, pruned_loss=0.02888, over 1424335.44 frames.], batch size: 52, lr: 2.10e-04
+2022-05-16 03:10:17,016 INFO [train.py:812] (7/8) Epoch 37, batch 2800, loss[loss=0.1195, simple_loss=0.2038, pruned_loss=0.01764, over 7273.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2424, pruned_loss=0.02899, over 1429459.31 frames.], batch size: 18, lr: 2.10e-04
+2022-05-16 03:11:34,312 INFO [train.py:812] (7/8) Epoch 37, batch 2850, loss[loss=0.1335, simple_loss=0.2307, pruned_loss=0.0182, over 6168.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02907, over 1428078.55 frames.], batch size: 37, lr: 2.10e-04
+2022-05-16 03:12:32,652 INFO [train.py:812] (7/8) Epoch 37, batch 2900, loss[loss=0.1228, simple_loss=0.2068, pruned_loss=0.01939, over 7013.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.0291, over 1429217.61 frames.], batch size: 16, lr: 2.10e-04
+2022-05-16 03:13:31,850 INFO [train.py:812] (7/8) Epoch 37, batch 2950, loss[loss=0.132, simple_loss=0.2274, pruned_loss=0.01826, over 7423.00 frames.], tot_loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.02883, over 1426219.89 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 03:14:30,579 INFO [train.py:812] (7/8) Epoch 37, batch 3000, loss[loss=0.1411, simple_loss=0.2385, pruned_loss=0.02187, over 7215.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2423, pruned_loss=0.02846, over 1422593.98 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 03:14:30,580 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-16 03:14:38,087 INFO [train.py:841] (7/8) Epoch 37, validation: loss=0.1539, simple_loss=0.2491, pruned_loss=0.02931, over 698248.00 frames.
+2022-05-16 03:15:37,692 INFO [train.py:812] (7/8) Epoch 37, batch 3050, loss[loss=0.1326, simple_loss=0.2178, pruned_loss=0.02369, over 7249.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2422, pruned_loss=0.02884, over 1420916.46 frames.], batch size: 16, lr: 2.10e-04
+2022-05-16 03:16:36,461 INFO [train.py:812] (7/8) Epoch 37, batch 3100, loss[loss=0.134, simple_loss=0.2291, pruned_loss=0.01949, over 7064.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02899, over 1417968.73 frames.], batch size: 18, lr: 2.10e-04
+2022-05-16 03:17:34,884 INFO [train.py:812] (7/8) Epoch 37, batch 3150, loss[loss=0.1193, simple_loss=0.2086, pruned_loss=0.01501, over 6998.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2411, pruned_loss=0.02876, over 1417635.53 frames.], batch size: 16, lr: 2.10e-04
+2022-05-16 03:18:34,036 INFO [train.py:812] (7/8) Epoch 37, batch 3200, loss[loss=0.1646, simple_loss=0.253, pruned_loss=0.03816, over 5332.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2415, pruned_loss=0.02915, over 1417795.47 frames.], batch size: 52, lr: 2.10e-04
+2022-05-16 03:19:33,515 INFO [train.py:812] (7/8) Epoch 37, batch 3250, loss[loss=0.1658, simple_loss=0.2607, pruned_loss=0.03551, over 7203.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2418, pruned_loss=0.02899, over 1416941.11 frames.], batch size: 22, lr: 2.10e-04
+2022-05-16 03:20:31,437 INFO [train.py:812] (7/8) Epoch 37, batch 3300, loss[loss=0.1419, simple_loss=0.233, pruned_loss=0.02539, over 7423.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2426, pruned_loss=0.02912, over 1415355.73 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 03:21:29,321 INFO [train.py:812] (7/8) Epoch 37, batch 3350, loss[loss=0.1517, simple_loss=0.2412, pruned_loss=0.03107, over 7380.00 frames.], tot_loss[loss=0.152, simple_loss=0.2442, pruned_loss=0.02985, over 1411752.29 frames.], batch size: 23, lr: 2.09e-04
+2022-05-16 03:22:27,897 INFO [train.py:812] (7/8) Epoch 37, batch 3400, loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03071, over 7142.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2433, pruned_loss=0.02966, over 1416031.68 frames.], batch size: 17, lr: 2.09e-04
+2022-05-16 03:23:27,204 INFO [train.py:812] (7/8) Epoch 37, batch 3450, loss[loss=0.1243, simple_loss=0.203, pruned_loss=0.02278, over 7289.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02929, over 1418668.96 frames.], batch size: 17, lr: 2.09e-04
+2022-05-16 03:24:25,230 INFO [train.py:812] (7/8) Epoch 37, batch 3500, loss[loss=0.1584, simple_loss=0.2482, pruned_loss=0.03425, over 7351.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2427, pruned_loss=0.02932, over 1416429.38 frames.], batch size: 19, lr: 2.09e-04
+2022-05-16 03:25:24,383 INFO [train.py:812] (7/8) Epoch 37, batch 3550, loss[loss=0.1391, simple_loss=0.2235, pruned_loss=0.02731, over 6831.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.02927, over 1413944.78 frames.], batch size: 15, lr: 2.09e-04
+2022-05-16 03:26:23,201 INFO [train.py:812] (7/8) Epoch 37, batch 3600, loss[loss=0.1428, simple_loss=0.2249, pruned_loss=0.03036, over 6977.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2416, pruned_loss=0.02903, over 1420729.56 frames.], batch size: 16, lr: 2.09e-04
+2022-05-16 03:27:22,042 INFO [train.py:812] (7/8) Epoch 37, batch 3650, loss[loss=0.1483, simple_loss=0.2448, pruned_loss=0.02586, over 7168.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2409, pruned_loss=0.02867, over 1422530.74 frames.], batch size: 19, lr: 2.09e-04
+2022-05-16 03:28:20,580 INFO [train.py:812] (7/8) Epoch 37, batch 3700, loss[loss=0.1502, simple_loss=0.2346, pruned_loss=0.03288, over 7235.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2408, pruned_loss=0.02882, over 1426162.96 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:29:19,685 INFO [train.py:812] (7/8) Epoch 37, batch 3750, loss[loss=0.1664, simple_loss=0.2633, pruned_loss=0.03476, over 7265.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2417, pruned_loss=0.02891, over 1422664.82 frames.], batch size: 24, lr: 2.09e-04
+2022-05-16 03:30:17,111 INFO [train.py:812] (7/8) Epoch 37, batch 3800, loss[loss=0.1347, simple_loss=0.2161, pruned_loss=0.02671, over 7282.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2403, pruned_loss=0.02835, over 1424418.86 frames.], batch size: 17, lr: 2.09e-04
+2022-05-16 03:31:15,859 INFO [train.py:812] (7/8) Epoch 37, batch 3850, loss[loss=0.173, simple_loss=0.2651, pruned_loss=0.04047, over 5271.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2405, pruned_loss=0.0286, over 1424010.81 frames.], batch size: 53, lr: 2.09e-04
+2022-05-16 03:32:12,596 INFO [train.py:812] (7/8) Epoch 37, batch 3900, loss[loss=0.1346, simple_loss=0.2302, pruned_loss=0.01946, over 7342.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2405, pruned_loss=0.02859, over 1426268.45 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:33:11,483 INFO [train.py:812] (7/8) Epoch 37, batch 3950, loss[loss=0.1348, simple_loss=0.2343, pruned_loss=0.01768, over 7282.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2414, pruned_loss=0.02894, over 1427638.84 frames.], batch size: 18, lr: 2.09e-04
+2022-05-16 03:34:09,782 INFO [train.py:812] (7/8) Epoch 37, batch 4000, loss[loss=0.162, simple_loss=0.2644, pruned_loss=0.02974, over 7151.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2418, pruned_loss=0.02926, over 1428408.97 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:35:09,221 INFO [train.py:812] (7/8) Epoch 37, batch 4050, loss[loss=0.1461, simple_loss=0.2497, pruned_loss=0.02121, over 7141.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2415, pruned_loss=0.02913, over 1427480.91 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:36:06,890 INFO [train.py:812] (7/8) Epoch 37, batch 4100, loss[loss=0.1632, simple_loss=0.2467, pruned_loss=0.03978, over 7297.00 frames.], tot_loss[loss=0.1499, simple_loss=0.242, pruned_loss=0.02888, over 1424896.14 frames.], batch size: 25, lr: 2.09e-04
+2022-05-16 03:37:05,685 INFO [train.py:812] (7/8) Epoch 37, batch 4150, loss[loss=0.1687, simple_loss=0.2648, pruned_loss=0.0363, over 7223.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2416, pruned_loss=0.02855, over 1426509.91 frames.], batch size: 21, lr: 2.09e-04
+2022-05-16 03:38:03,000 INFO [train.py:812] (7/8) Epoch 37, batch 4200, loss[loss=0.1579, simple_loss=0.2527, pruned_loss=0.03155, over 7325.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2412, pruned_loss=0.0283, over 1428566.91 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:39:02,457 INFO [train.py:812] (7/8) Epoch 37, batch 4250, loss[loss=0.161, simple_loss=0.252, pruned_loss=0.03502, over 7195.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2416, pruned_loss=0.02853, over 1431340.96 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:40:00,858 INFO [train.py:812] (7/8) Epoch 37, batch 4300, loss[loss=0.1329, simple_loss=0.2286, pruned_loss=0.01855, over 7323.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02874, over 1425833.88 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:41:00,634 INFO [train.py:812] (7/8) Epoch 37, batch 4350, loss[loss=0.1663, simple_loss=0.2653, pruned_loss=0.03366, over 7325.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2417, pruned_loss=0.02843, over 1430509.07 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:41:59,298 INFO [train.py:812] (7/8) Epoch 37, batch 4400, loss[loss=0.1503, simple_loss=0.2505, pruned_loss=0.02506, over 7337.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2421, pruned_loss=0.02852, over 1422410.73 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:42:59,082 INFO [train.py:812] (7/8) Epoch 37, batch 4450, loss[loss=0.1323, simple_loss=0.2159, pruned_loss=0.02436, over 7419.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2425, pruned_loss=0.02846, over 1420900.62 frames.], batch size: 18, lr: 2.09e-04
+2022-05-16 03:43:58,041 INFO [train.py:812] (7/8) Epoch 37, batch 4500, loss[loss=0.1363, simple_loss=0.2189, pruned_loss=0.02687, over 7270.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2423, pruned_loss=0.02868, over 1416054.17 frames.], batch size: 18, lr: 2.09e-04
+2022-05-16 03:44:56,308 INFO [train.py:812] (7/8) Epoch 37, batch 4550, loss[loss=0.148, simple_loss=0.236, pruned_loss=0.03, over 6367.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2436, pruned_loss=0.02931, over 1392200.17 frames.], batch size: 38, lr: 2.09e-04
+2022-05-16 03:46:01,498 INFO [train.py:812] (7/8) Epoch 38, batch 0, loss[loss=0.1389, simple_loss=0.2301, pruned_loss=0.02385, over 7370.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2301, pruned_loss=0.02385, over 7370.00 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:47:10,816 INFO [train.py:812] (7/8) Epoch 38, batch 50, loss[loss=0.1387, simple_loss=0.2342, pruned_loss=0.02158, over 6497.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2376, pruned_loss=0.02667, over 322170.77 frames.], batch size: 37, lr: 2.06e-04
+2022-05-16 03:48:09,440 INFO [train.py:812] (7/8) Epoch 38, batch 100, loss[loss=0.138, simple_loss=0.2318, pruned_loss=0.02214, over 7268.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2412, pruned_loss=0.02761, over 559924.71 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:49:08,241 INFO [train.py:812] (7/8) Epoch 38, batch 150, loss[loss=0.1469, simple_loss=0.2333, pruned_loss=0.03028, over 7381.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2416, pruned_loss=0.02832, over 747991.84 frames.], batch size: 23, lr: 2.06e-04
+2022-05-16 03:50:07,535 INFO [train.py:812] (7/8) Epoch 38, batch 200, loss[loss=0.1394, simple_loss=0.2385, pruned_loss=0.02014, over 7404.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2406, pruned_loss=0.02824, over 897019.99 frames.], batch size: 21, lr: 2.06e-04
+2022-05-16 03:51:06,654 INFO [train.py:812] (7/8) Epoch 38, batch 250, loss[loss=0.1302, simple_loss=0.2258, pruned_loss=0.01732, over 7364.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2396, pruned_loss=0.02781, over 1015326.60 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:52:05,098 INFO [train.py:812] (7/8) Epoch 38, batch 300, loss[loss=0.1437, simple_loss=0.2448, pruned_loss=0.02125, over 7238.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2406, pruned_loss=0.02826, over 1105619.86 frames.], batch size: 20, lr: 2.06e-04
+2022-05-16 03:53:04,638 INFO [train.py:812] (7/8) Epoch 38, batch 350, loss[loss=0.1422, simple_loss=0.2394, pruned_loss=0.02251, over 7258.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2411, pruned_loss=0.02822, over 1172608.92 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:54:02,525 INFO [train.py:812] (7/8) Epoch 38, batch 400, loss[loss=0.1392, simple_loss=0.218, pruned_loss=0.03027, over 7271.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2409, pruned_loss=0.02826, over 1232269.20 frames.], batch size: 17, lr: 2.06e-04
+2022-05-16 03:55:02,014 INFO [train.py:812] (7/8) Epoch 38, batch 450, loss[loss=0.1479, simple_loss=0.2487, pruned_loss=0.02358, over 7119.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2402, pruned_loss=0.02828, over 1275261.77 frames.], batch size: 21, lr: 2.06e-04
+2022-05-16 03:56:00,742 INFO [train.py:812] (7/8) Epoch 38, batch 500, loss[loss=0.1544, simple_loss=0.2453, pruned_loss=0.03175, over 7277.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2402, pruned_loss=0.02811, over 1311324.03 frames.], batch size: 18, lr: 2.06e-04
+2022-05-16 03:56:58,598 INFO [train.py:812] (7/8) Epoch 38, batch 550, loss[loss=0.1375, simple_loss=0.2267, pruned_loss=0.0241, over 7322.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2409, pruned_loss=0.0285, over 1335207.26 frames.], batch size: 20, lr: 2.06e-04
+2022-05-16 03:57:56,259 INFO [train.py:812] (7/8) Epoch 38, batch 600, loss[loss=0.1553, simple_loss=0.2414, pruned_loss=0.03462, over 7362.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.02906, over 1356548.45 frames.], batch size: 23, lr: 2.06e-04
+2022-05-16 03:58:54,221 INFO [train.py:812] (7/8) Epoch 38, batch 650, loss[loss=0.1509, simple_loss=0.2444, pruned_loss=0.02866, over 7356.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2427, pruned_loss=0.02909, over 1373220.71 frames.], batch size: 22, lr: 2.06e-04
+2022-05-16 03:59:53,367 INFO [train.py:812] (7/8) Epoch 38, batch 700, loss[loss=0.1419, simple_loss=0.2339, pruned_loss=0.02495, over 7166.00 frames.], tot_loss[loss=0.15, simple_loss=0.2426, pruned_loss=0.02867, over 1386233.69 frames.], batch size: 18, lr: 2.06e-04
+2022-05-16 04:00:52,158 INFO [train.py:812] (7/8) Epoch 38, batch 750, loss[loss=0.1685, simple_loss=0.2651, pruned_loss=0.03593, over 7374.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2429, pruned_loss=0.02846, over 1400828.17 frames.], batch size: 23, lr: 2.05e-04
+2022-05-16 04:01:50,310 INFO [train.py:812] (7/8) Epoch 38, batch 800, loss[loss=0.1397, simple_loss=0.2227, pruned_loss=0.0283, over 7394.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2431, pruned_loss=0.02868, over 1409572.28 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:02:49,137 INFO [train.py:812] (7/8) Epoch 38, batch 850, loss[loss=0.1314, simple_loss=0.2233, pruned_loss=0.01978, over 7354.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2427, pruned_loss=0.02836, over 1411449.25 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:03:47,729 INFO [train.py:812] (7/8) Epoch 38, batch 900, loss[loss=0.1541, simple_loss=0.2579, pruned_loss=0.02519, over 7270.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2422, pruned_loss=0.02849, over 1413523.07 frames.], batch size: 24, lr: 2.05e-04
+2022-05-16 04:04:46,180 INFO [train.py:812] (7/8) Epoch 38, batch 950, loss[loss=0.1426, simple_loss=0.2327, pruned_loss=0.02627, over 7254.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2429, pruned_loss=0.02878, over 1418725.90 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:05:44,615 INFO [train.py:812] (7/8) Epoch 38, batch 1000, loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02942, over 7200.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2431, pruned_loss=0.02872, over 1421818.49 frames.], batch size: 22, lr: 2.05e-04
+2022-05-16 04:06:43,943 INFO [train.py:812] (7/8) Epoch 38, batch 1050, loss[loss=0.1483, simple_loss=0.2422, pruned_loss=0.02717, over 7339.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2428, pruned_loss=0.02852, over 1421840.60 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:07:41,774 INFO [train.py:812] (7/8) Epoch 38, batch 1100, loss[loss=0.1511, simple_loss=0.2364, pruned_loss=0.03286, over 7175.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2434, pruned_loss=0.02894, over 1424504.53 frames.], batch size: 16, lr: 2.05e-04
+2022-05-16 04:08:41,127 INFO [train.py:812] (7/8) Epoch 38, batch 1150, loss[loss=0.1291, simple_loss=0.2152, pruned_loss=0.02147, over 7285.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2438, pruned_loss=0.02897, over 1421407.04 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:09:40,658 INFO [train.py:812] (7/8) Epoch 38, batch 1200, loss[loss=0.1839, simple_loss=0.2797, pruned_loss=0.04412, over 7232.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2443, pruned_loss=0.02913, over 1423101.70 frames.], batch size: 26, lr: 2.05e-04
+2022-05-16 04:10:39,686 INFO [train.py:812] (7/8) Epoch 38, batch 1250, loss[loss=0.1482, simple_loss=0.2465, pruned_loss=0.02493, over 6344.00 frames.], tot_loss[loss=0.151, simple_loss=0.2437, pruned_loss=0.02912, over 1426337.06 frames.], batch size: 37, lr: 2.05e-04
+2022-05-16 04:11:38,501 INFO [train.py:812] (7/8) Epoch 38, batch 1300, loss[loss=0.1454, simple_loss=0.2308, pruned_loss=0.03005, over 7277.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2445, pruned_loss=0.02939, over 1426900.18 frames.], batch size: 17, lr: 2.05e-04
+2022-05-16 04:12:36,187 INFO [train.py:812] (7/8) Epoch 38, batch 1350, loss[loss=0.1508, simple_loss=0.2491, pruned_loss=0.02627, over 7103.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2433, pruned_loss=0.02914, over 1420872.86 frames.], batch size: 21, lr: 2.05e-04
+2022-05-16 04:13:33,900 INFO [train.py:812] (7/8) Epoch 38, batch 1400, loss[loss=0.1535, simple_loss=0.2505, pruned_loss=0.02829, over 7299.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2431, pruned_loss=0.02927, over 1420558.74 frames.], batch size: 24, lr: 2.05e-04
+2022-05-16 04:14:32,902 INFO [train.py:812] (7/8) Epoch 38, batch 1450, loss[loss=0.1845, simple_loss=0.2592, pruned_loss=0.05487, over 7199.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02961, over 1425210.44 frames.], batch size: 22, lr: 2.05e-04
+2022-05-16 04:15:31,406 INFO [train.py:812] (7/8) Epoch 38, batch 1500, loss[loss=0.1473, simple_loss=0.2437, pruned_loss=0.02539, over 7292.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02963, over 1425390.13 frames.], batch size: 25, lr: 2.05e-04
+2022-05-16 04:16:30,195 INFO [train.py:812] (7/8) Epoch 38, batch 1550, loss[loss=0.1406, simple_loss=0.2276, pruned_loss=0.02678, over 7243.00 frames.], tot_loss[loss=0.151, simple_loss=0.2434, pruned_loss=0.0293, over 1422775.70 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:17:27,404 INFO [train.py:812] (7/8) Epoch 38, batch 1600, loss[loss=0.1334, simple_loss=0.2215, pruned_loss=0.02263, over 7263.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2439, pruned_loss=0.0293, over 1425147.38 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:18:25,555 INFO [train.py:812] (7/8) Epoch 38, batch 1650, loss[loss=0.1706, simple_loss=0.2615, pruned_loss=0.03986, over 7083.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02903, over 1424344.29 frames.], batch size: 28, lr: 2.05e-04
+2022-05-16 04:19:24,171 INFO [train.py:812] (7/8) Epoch 38, batch 1700, loss[loss=0.1303, simple_loss=0.2067, pruned_loss=0.02695, over 7161.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2416, pruned_loss=0.02865, over 1422356.15 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:20:24,548 INFO [train.py:812] (7/8) Epoch 38, batch 1750, loss[loss=0.1947, simple_loss=0.2784, pruned_loss=0.05551, over 5386.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2426, pruned_loss=0.02905, over 1421979.31 frames.], batch size: 52, lr: 2.05e-04
+2022-05-16 04:21:23,206 INFO [train.py:812] (7/8) Epoch 38, batch 1800, loss[loss=0.1467, simple_loss=0.2466, pruned_loss=0.02341, over 7328.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2417, pruned_loss=0.02885, over 1419680.09 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:22:21,158 INFO [train.py:812] (7/8) Epoch 38, batch 1850, loss[loss=0.1279, simple_loss=0.2114, pruned_loss=0.02222, over 7282.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2414, pruned_loss=0.02893, over 1421663.33 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:23:20,153 INFO [train.py:812] (7/8) Epoch 38, batch 1900, loss[loss=0.14, simple_loss=0.2272, pruned_loss=0.02634, over 6793.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2429, pruned_loss=0.0293, over 1424392.81 frames.], batch size: 15, lr: 2.05e-04
+2022-05-16 04:24:18,781 INFO [train.py:812] (7/8) Epoch 38, batch 1950, loss[loss=0.137, simple_loss=0.2256, pruned_loss=0.02419, over 7267.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02943, over 1427369.55 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:25:17,633 INFO [train.py:812] (7/8) Epoch 38, batch 2000, loss[loss=0.127, simple_loss=0.2064, pruned_loss=0.02378, over 7413.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2424, pruned_loss=0.02908, over 1426150.13 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:26:16,393 INFO [train.py:812] (7/8) Epoch 38, batch 2050, loss[loss=0.1368, simple_loss=0.2287, pruned_loss=0.0224, over 7249.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2422, pruned_loss=0.02881, over 1423388.67 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:27:14,062 INFO [train.py:812] (7/8) Epoch 38, batch 2100, loss[loss=0.1657, simple_loss=0.2555, pruned_loss=0.038, over 7193.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2429, pruned_loss=0.02903, over 1417678.43 frames.], batch size: 26, lr: 2.05e-04
+2022-05-16 04:28:12,497 INFO [train.py:812] (7/8) Epoch 38, batch 2150, loss[loss=0.1373, simple_loss=0.2286, pruned_loss=0.023, over 7068.00 frames.], tot_loss[loss=0.15, simple_loss=0.2425, pruned_loss=0.02874, over 1418576.95 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:29:11,068 INFO [train.py:812] (7/8) Epoch 38, batch 2200, loss[loss=0.1344, simple_loss=0.2277, pruned_loss=0.02054, over 7061.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2436, pruned_loss=0.02881, over 1419532.04 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:30:15,090 INFO [train.py:812] (7/8) Epoch 38, batch 2250, loss[loss=0.1552, simple_loss=0.2571, pruned_loss=0.02662, over 6596.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2437, pruned_loss=0.02901, over 1417893.31 frames.], batch size: 38, lr: 2.05e-04
+2022-05-16 04:31:14,148 INFO [train.py:812] (7/8) Epoch 38, batch 2300, loss[loss=0.1224, simple_loss=0.2155, pruned_loss=0.01464, over 7060.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2435, pruned_loss=0.02879, over 1421477.00 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:32:13,300 INFO [train.py:812] (7/8) Epoch 38, batch 2350, loss[loss=0.1424, simple_loss=0.2261, pruned_loss=0.02935, over 7325.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2427, pruned_loss=0.02852, over 1419812.28 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:33:12,148 INFO [train.py:812] (7/8) Epoch 38, batch 2400, loss[loss=0.1564, simple_loss=0.2364, pruned_loss=0.0382, over 7416.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2425, pruned_loss=0.02851, over 1424779.32 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:34:10,725 INFO [train.py:812] (7/8) Epoch 38, batch 2450, loss[loss=0.1203, simple_loss=0.2139, pruned_loss=0.0134, over 7337.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2427, pruned_loss=0.02857, over 1427138.46 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:35:08,804 INFO [train.py:812] (7/8) Epoch 38, batch 2500, loss[loss=0.1473, simple_loss=0.234, pruned_loss=0.03031, over 7162.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2424, pruned_loss=0.0286, over 1426978.43 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:36:06,688 INFO [train.py:812] (7/8) Epoch 38, batch 2550, loss[loss=0.1363, simple_loss=0.2207, pruned_loss=0.02597, over 7167.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2425, pruned_loss=0.0286, over 1424331.77 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:37:05,297 INFO [train.py:812] (7/8) Epoch 38, batch 2600, loss[loss=0.1513, simple_loss=0.2463, pruned_loss=0.02816, over 7434.00 frames.], tot_loss[loss=0.1494, simple_loss=0.242, pruned_loss=0.02839, over 1424233.75 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:38:03,432 INFO [train.py:812] (7/8) Epoch 38, batch 2650, loss[loss=0.1482, simple_loss=0.2358, pruned_loss=0.03028, over 7176.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2419, pruned_loss=0.0286, over 1425529.01 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 04:39:01,023 INFO [train.py:812] (7/8) Epoch 38, batch 2700, loss[loss=0.138, simple_loss=0.2359, pruned_loss=0.02009, over 7233.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2409, pruned_loss=0.02801, over 1424141.07 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:39:59,861 INFO [train.py:812] (7/8) Epoch 38, batch 2750, loss[loss=0.1395, simple_loss=0.2371, pruned_loss=0.02096, over 7368.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2411, pruned_loss=0.02797, over 1425679.95 frames.], batch size: 19, lr: 2.04e-04
+2022-05-16 04:40:57,562 INFO [train.py:812] (7/8) Epoch 38, batch 2800, loss[loss=0.1739, simple_loss=0.2669, pruned_loss=0.04052, over 7294.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2415, pruned_loss=0.02804, over 1424201.52 frames.], batch size: 24, lr: 2.04e-04
+2022-05-16 04:41:55,582 INFO [train.py:812] (7/8) Epoch 38, batch 2850, loss[loss=0.1461, simple_loss=0.2422, pruned_loss=0.02501, over 7431.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2406, pruned_loss=0.02781, over 1424209.60 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 04:42:54,123 INFO [train.py:812] (7/8) Epoch 38, batch 2900, loss[loss=0.1213, simple_loss=0.2014, pruned_loss=0.02057, over 7135.00 frames.], tot_loss[loss=0.148, simple_loss=0.2402, pruned_loss=0.02792, over 1423912.99 frames.], batch size: 17, lr: 2.04e-04
+2022-05-16 04:43:53,050 INFO [train.py:812] (7/8) Epoch 38, batch 2950, loss[loss=0.1198, simple_loss=0.2067, pruned_loss=0.01646, over 7422.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2402, pruned_loss=0.02763, over 1428552.60 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:44:52,022 INFO [train.py:812] (7/8) Epoch 38, batch 3000, loss[loss=0.1549, simple_loss=0.244, pruned_loss=0.03294, over 7194.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2409, pruned_loss=0.0279, over 1428138.20 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 04:44:52,023 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-16 04:44:59,416 INFO [train.py:841] (7/8) Epoch 38, validation: loss=0.1532, simple_loss=0.2484, pruned_loss=0.02898, over 698248.00 frames.
+2022-05-16 04:45:58,546 INFO [train.py:812] (7/8) Epoch 38, batch 3050, loss[loss=0.1413, simple_loss=0.2302, pruned_loss=0.02618, over 7163.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.02826, over 1428970.42 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:46:56,214 INFO [train.py:812] (7/8) Epoch 38, batch 3100, loss[loss=0.1608, simple_loss=0.261, pruned_loss=0.03032, over 7200.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2426, pruned_loss=0.0283, over 1422447.20 frames.], batch size: 22, lr: 2.04e-04
+2022-05-16 04:47:54,534 INFO [train.py:812] (7/8) Epoch 38, batch 3150, loss[loss=0.1598, simple_loss=0.2527, pruned_loss=0.03347, over 7396.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.02821, over 1420406.55 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 04:48:52,466 INFO [train.py:812] (7/8) Epoch 38, batch 3200, loss[loss=0.1549, simple_loss=0.2542, pruned_loss=0.02777, over 7099.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2423, pruned_loss=0.02852, over 1425256.90 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 04:49:51,336 INFO [train.py:812] (7/8) Epoch 38, batch 3250, loss[loss=0.1303, simple_loss=0.211, pruned_loss=0.02483, over 7278.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.0284, over 1425945.06 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:50:49,206 INFO [train.py:812] (7/8) Epoch 38, batch 3300, loss[loss=0.1436, simple_loss=0.2335, pruned_loss=0.02683, over 7238.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2414, pruned_loss=0.02842, over 1425416.04 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:51:47,412 INFO [train.py:812] (7/8) Epoch 38, batch 3350, loss[loss=0.1722, simple_loss=0.2672, pruned_loss=0.03855, over 7202.00 frames.], tot_loss[loss=0.15, simple_loss=0.2429, pruned_loss=0.02855, over 1426329.33 frames.], batch size: 22, lr: 2.04e-04
+2022-05-16 04:52:45,613 INFO [train.py:812] (7/8) Epoch 38, batch 3400, loss[loss=0.1534, simple_loss=0.2485, pruned_loss=0.02912, over 6763.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2426, pruned_loss=0.02845, over 1430307.06 frames.], batch size: 31, lr: 2.04e-04
+2022-05-16 04:53:45,211 INFO [train.py:812] (7/8) Epoch 38, batch 3450, loss[loss=0.1349, simple_loss=0.2224, pruned_loss=0.02365, over 7427.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2424, pruned_loss=0.02839, over 1431328.24 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:54:43,564 INFO [train.py:812] (7/8) Epoch 38, batch 3500, loss[loss=0.1487, simple_loss=0.2498, pruned_loss=0.02378, over 7239.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.02831, over 1429878.51 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:55:41,796 INFO [train.py:812] (7/8) Epoch 38, batch 3550, loss[loss=0.1541, simple_loss=0.2558, pruned_loss=0.02617, over 7154.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2432, pruned_loss=0.02863, over 1430038.79 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:56:49,640 INFO [train.py:812] (7/8) Epoch 38, batch 3600, loss[loss=0.1531, simple_loss=0.2502, pruned_loss=0.02798, over 6885.00 frames.], tot_loss[loss=0.15, simple_loss=0.2427, pruned_loss=0.0286, over 1428604.73 frames.], batch size: 31, lr: 2.04e-04
+2022-05-16 04:57:48,358 INFO [train.py:812] (7/8) Epoch 38, batch 3650, loss[loss=0.1728, simple_loss=0.2693, pruned_loss=0.03815, over 7061.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2427, pruned_loss=0.02842, over 1431259.47 frames.], batch size: 28, lr: 2.04e-04
+2022-05-16 04:58:46,178 INFO [train.py:812] (7/8) Epoch 38, batch 3700, loss[loss=0.1741, simple_loss=0.2714, pruned_loss=0.03837, over 7317.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2424, pruned_loss=0.02865, over 1422569.80 frames.], batch size: 24, lr: 2.04e-04
+2022-05-16 05:00:03,413 INFO [train.py:812] (7/8) Epoch 38, batch 3750, loss[loss=0.1634, simple_loss=0.2598, pruned_loss=0.03348, over 7158.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2429, pruned_loss=0.02897, over 1418425.73 frames.], batch size: 19, lr: 2.04e-04
+2022-05-16 05:01:01,803 INFO [train.py:812] (7/8) Epoch 38, batch 3800, loss[loss=0.1604, simple_loss=0.2549, pruned_loss=0.03298, over 7374.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2423, pruned_loss=0.02866, over 1418393.51 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 05:02:01,302 INFO [train.py:812] (7/8) Epoch 38, batch 3850, loss[loss=0.159, simple_loss=0.2566, pruned_loss=0.03071, over 7125.00 frames.], tot_loss[loss=0.1495, simple_loss=0.242, pruned_loss=0.02851, over 1420712.96 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 05:03:01,111 INFO [train.py:812] (7/8) Epoch 38, batch 3900, loss[loss=0.1471, simple_loss=0.2414, pruned_loss=0.02636, over 7324.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2418, pruned_loss=0.0289, over 1422556.24 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 05:03:59,309 INFO [train.py:812] (7/8) Epoch 38, batch 3950, loss[loss=0.1578, simple_loss=0.2471, pruned_loss=0.03427, over 7214.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2418, pruned_loss=0.02898, over 1417674.22 frames.], batch size: 22, lr: 2.04e-04
+2022-05-16 05:04:56,855 INFO [train.py:812] (7/8) Epoch 38, batch 4000, loss[loss=0.1415, simple_loss=0.2194, pruned_loss=0.03173, over 7162.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2415, pruned_loss=0.02902, over 1418122.94 frames.], batch size: 19, lr: 2.04e-04
+2022-05-16 05:06:06,118 INFO [train.py:812] (7/8) Epoch 38, batch 4050, loss[loss=0.1343, simple_loss=0.222, pruned_loss=0.02336, over 7270.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2415, pruned_loss=0.02892, over 1410717.14 frames.], batch size: 17, lr: 2.04e-04
+2022-05-16 05:07:14,561 INFO [train.py:812] (7/8) Epoch 38, batch 4100, loss[loss=0.1502, simple_loss=0.238, pruned_loss=0.03113, over 7212.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.029, over 1412859.85 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 05:08:13,926 INFO [train.py:812] (7/8) Epoch 38, batch 4150, loss[loss=0.1399, simple_loss=0.2379, pruned_loss=0.02095, over 7246.00 frames.], tot_loss[loss=0.1488, simple_loss=0.241, pruned_loss=0.0283, over 1412237.61 frames.], batch size: 19, lr: 2.03e-04
+2022-05-16 05:09:21,222 INFO [train.py:812] (7/8) Epoch 38, batch 4200, loss[loss=0.1692, simple_loss=0.2644, pruned_loss=0.037, over 7293.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2408, pruned_loss=0.02797, over 1413650.19 frames.], batch size: 24, lr: 2.03e-04
+2022-05-16 05:10:29,491 INFO [train.py:812] (7/8) Epoch 38, batch 4250, loss[loss=0.1328, simple_loss=0.2267, pruned_loss=0.01944, over 7220.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2408, pruned_loss=0.02821, over 1413758.88 frames.], batch size: 20, lr: 2.03e-04
+2022-05-16 05:11:27,939 INFO [train.py:812] (7/8) Epoch 38, batch 4300, loss[loss=0.197, simple_loss=0.2877, pruned_loss=0.05321, over 4727.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2405, pruned_loss=0.02842, over 1411259.55 frames.], batch size: 52, lr: 2.03e-04
+2022-05-16 05:12:26,600 INFO [train.py:812] (7/8) Epoch 38, batch 4350, loss[loss=0.1271, simple_loss=0.2112, pruned_loss=0.02156, over 7416.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2397, pruned_loss=0.02806, over 1413379.64 frames.], batch size: 17, lr: 2.03e-04
+2022-05-16 05:13:26,171 INFO [train.py:812] (7/8) Epoch 38, batch 4400, loss[loss=0.1324, simple_loss=0.2112, pruned_loss=0.02682, over 7194.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2395, pruned_loss=0.02763, over 1414706.43 frames.], batch size: 16, lr: 2.03e-04
+2022-05-16 05:14:25,873 INFO [train.py:812] (7/8) Epoch 38, batch 4450, loss[loss=0.1433, simple_loss=0.2348, pruned_loss=0.02592, over 6746.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2384, pruned_loss=0.02755, over 1406466.24 frames.], batch size: 15, lr: 2.03e-04
+2022-05-16 05:15:24,213 INFO [train.py:812] (7/8) Epoch 38, batch 4500, loss[loss=0.1371, simple_loss=0.2372, pruned_loss=0.01857, over 6615.00 frames.], tot_loss[loss=0.1476, simple_loss=0.239, pruned_loss=0.02808, over 1381209.80 frames.], batch size: 38, lr: 2.03e-04
+2022-05-16 05:16:23,111 INFO [train.py:812] (7/8) Epoch 38, batch 4550, loss[loss=0.2347, simple_loss=0.306, pruned_loss=0.08168, over 5047.00 frames.], tot_loss[loss=0.1483, simple_loss=0.239, pruned_loss=0.02883, over 1353793.00 frames.], batch size: 52, lr: 2.03e-04
+2022-05-16 05:17:28,548 INFO [train.py:812] (7/8) Epoch 39, batch 0, loss[loss=0.1317, simple_loss=0.2271, pruned_loss=0.01809, over 7255.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2271, pruned_loss=0.01809, over 7255.00 frames.], batch size: 19, lr: 2.01e-04
+2022-05-16 05:18:26,921 INFO [train.py:812] (7/8) Epoch 39, batch 50, loss[loss=0.1411, simple_loss=0.2397, pruned_loss=0.02126, over 7143.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2438, pruned_loss=0.02738, over 320006.93 frames.], batch size: 20, lr: 2.01e-04
+2022-05-16 05:19:25,812 INFO [train.py:812] (7/8) Epoch 39, batch 100, loss[loss=0.1456, simple_loss=0.2485, pruned_loss=0.02135, over 6779.00 frames.], tot_loss[loss=0.149, simple_loss=0.2432, pruned_loss=0.02735, over 565470.54 frames.], batch size: 31, lr: 2.01e-04
+2022-05-16 05:20:24,103 INFO [train.py:812] (7/8) Epoch 39, batch 150, loss[loss=0.1346, simple_loss=0.2235, pruned_loss=0.02283, over 7155.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2403, pruned_loss=0.02733, over 754430.22 frames.], batch size: 18, lr: 2.01e-04
+2022-05-16 05:21:22,528 INFO [train.py:812] (7/8) Epoch 39, batch 200, loss[loss=0.1248, simple_loss=0.2177, pruned_loss=0.01591, over 7439.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2412, pruned_loss=0.02783, over 900731.70 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:22:20,448 INFO [train.py:812] (7/8) Epoch 39, batch 250, loss[loss=0.1409, simple_loss=0.2391, pruned_loss=0.02133, over 6259.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2424, pruned_loss=0.02817, over 1016352.24 frames.], batch size: 38, lr: 2.00e-04
+2022-05-16 05:23:19,082 INFO [train.py:812] (7/8) Epoch 39, batch 300, loss[loss=0.1437, simple_loss=0.2465, pruned_loss=0.02048, over 7437.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2422, pruned_loss=0.028, over 1111373.48 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:24:17,734 INFO [train.py:812] (7/8) Epoch 39, batch 350, loss[loss=0.1698, simple_loss=0.2628, pruned_loss=0.0384, over 7302.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2419, pruned_loss=0.02817, over 1178286.72 frames.], batch size: 24, lr: 2.00e-04
+2022-05-16 05:25:17,182 INFO [train.py:812] (7/8) Epoch 39, batch 400, loss[loss=0.16, simple_loss=0.2531, pruned_loss=0.03342, over 7214.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2414, pruned_loss=0.02807, over 1227516.89 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:26:16,287 INFO [train.py:812] (7/8) Epoch 39, batch 450, loss[loss=0.1631, simple_loss=0.2588, pruned_loss=0.03365, over 7186.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2415, pruned_loss=0.02846, over 1272597.70 frames.], batch size: 23, lr: 2.00e-04
+2022-05-16 05:27:15,054 INFO [train.py:812] (7/8) Epoch 39, batch 500, loss[loss=0.1275, simple_loss=0.228, pruned_loss=0.01352, over 7144.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2412, pruned_loss=0.02862, over 1299926.68 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:28:14,720 INFO [train.py:812] (7/8) Epoch 39, batch 550, loss[loss=0.1431, simple_loss=0.231, pruned_loss=0.02758, over 7429.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2409, pruned_loss=0.02846, over 1326176.38 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:29:14,900 INFO [train.py:812] (7/8) Epoch 39, batch 600, loss[loss=0.1422, simple_loss=0.2334, pruned_loss=0.02552, over 7165.00 frames.], tot_loss[loss=0.149, simple_loss=0.2411, pruned_loss=0.02848, over 1344691.99 frames.], batch size: 18, lr: 2.00e-04
+2022-05-16 05:30:14,596 INFO [train.py:812] (7/8) Epoch 39, batch 650, loss[loss=0.1204, simple_loss=0.2102, pruned_loss=0.01527, over 7285.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2412, pruned_loss=0.02863, over 1364527.30 frames.], batch size: 17, lr: 2.00e-04
+2022-05-16 05:31:13,708 INFO [train.py:812] (7/8) Epoch 39, batch 700, loss[loss=0.1454, simple_loss=0.225, pruned_loss=0.03287, over 6813.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2396, pruned_loss=0.02827, over 1377112.88 frames.], batch size: 15, lr: 2.00e-04
+2022-05-16 05:32:12,674 INFO [train.py:812] (7/8) Epoch 39, batch 750, loss[loss=0.1608, simple_loss=0.2589, pruned_loss=0.03138, over 6488.00 frames.], tot_loss[loss=0.1476, simple_loss=0.239, pruned_loss=0.02806, over 1386163.64 frames.], batch size: 38, lr: 2.00e-04
+2022-05-16 05:33:12,269 INFO [train.py:812] (7/8) Epoch 39, batch 800, loss[loss=0.1661, simple_loss=0.2715, pruned_loss=0.03036, over 7218.00 frames.], tot_loss[loss=0.1481, simple_loss=0.24, pruned_loss=0.0281, over 1399093.32 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:34:10,591 INFO [train.py:812] (7/8) Epoch 39, batch 850, loss[loss=0.1617, simple_loss=0.2481, pruned_loss=0.03769, over 7049.00 frames.], tot_loss[loss=0.148, simple_loss=0.2396, pruned_loss=0.02815, over 1405309.73 frames.], batch size: 28, lr: 2.00e-04
+2022-05-16 05:35:08,807 INFO [train.py:812] (7/8) Epoch 39, batch 900, loss[loss=0.1672, simple_loss=0.2623, pruned_loss=0.03606, over 7407.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2406, pruned_loss=0.02827, over 1403486.22 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:36:07,915 INFO [train.py:812] (7/8) Epoch 39, batch 950, loss[loss=0.1229, simple_loss=0.2027, pruned_loss=0.02153, over 7146.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2413, pruned_loss=0.0287, over 1405882.78 frames.], batch size: 17, lr: 2.00e-04
+2022-05-16 05:37:07,610 INFO [train.py:812] (7/8) Epoch 39, batch 1000, loss[loss=0.1691, simple_loss=0.2538, pruned_loss=0.04219, over 7358.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2411, pruned_loss=0.02839, over 1409312.46 frames.], batch size: 19, lr: 2.00e-04
+2022-05-16 05:38:06,535 INFO [train.py:812] (7/8) Epoch 39, batch 1050, loss[loss=0.1574, simple_loss=0.2572, pruned_loss=0.0288, over 6766.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2411, pruned_loss=0.02864, over 1411781.06 frames.], batch size: 31, lr: 2.00e-04
+2022-05-16 05:39:05,062 INFO [train.py:812] (7/8) Epoch 39, batch 1100, loss[loss=0.1394, simple_loss=0.2343, pruned_loss=0.02226, over 7382.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2406, pruned_loss=0.02814, over 1416001.03 frames.], batch size: 23, lr: 2.00e-04
+2022-05-16 05:40:03,866 INFO [train.py:812] (7/8) Epoch 39, batch 1150, loss[loss=0.1218, simple_loss=0.2066, pruned_loss=0.01852, over 7274.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2401, pruned_loss=0.02806, over 1419615.98 frames.], batch size: 18, lr: 2.00e-04
+2022-05-16 05:41:02,339 INFO [train.py:812] (7/8) Epoch 39, batch 1200, loss[loss=0.1467, simple_loss=0.2408, pruned_loss=0.02623, over 6739.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2402, pruned_loss=0.02827, over 1420838.09 frames.], batch size: 31, lr: 2.00e-04
+2022-05-16 05:42:00,525 INFO [train.py:812] (7/8) Epoch 39, batch 1250, loss[loss=0.1464, simple_loss=0.2468, pruned_loss=0.02303, over 7431.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2404, pruned_loss=0.02812, over 1422458.29 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:42:59,406 INFO [train.py:812] (7/8) Epoch 39, batch 1300, loss[loss=0.1314, simple_loss=0.2137, pruned_loss=0.02449, over 7271.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2399, pruned_loss=0.02815, over 1425319.32 frames.], batch size: 17, lr: 2.00e-04
+2022-05-16 05:43:56,606 INFO [train.py:812] (7/8) Epoch 39, batch 1350, loss[loss=0.1409, simple_loss=0.2447, pruned_loss=0.01853, over 7328.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2405, pruned_loss=0.02819, over 1425144.06 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:45:05,773 INFO [train.py:812] (7/8) Epoch 39, batch 1400, loss[loss=0.1324, simple_loss=0.2238, pruned_loss=0.02052, over 7151.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2405, pruned_loss=0.0279, over 1424904.63 frames.], batch size: 19, lr: 2.00e-04
+2022-05-16 05:46:03,943 INFO [train.py:812] (7/8) Epoch 39, batch 1450, loss[loss=0.177, simple_loss=0.2682, pruned_loss=0.04288, over 7282.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2418, pruned_loss=0.02834, over 1425688.80 frames.], batch size: 25, lr: 2.00e-04
+2022-05-16 05:47:01,554 INFO [train.py:812] (7/8) Epoch 39, batch 1500, loss[loss=0.1539, simple_loss=0.2508, pruned_loss=0.02853, over 7112.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2422, pruned_loss=0.02848, over 1424836.12 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:48:00,131 INFO [train.py:812] (7/8) Epoch 39, batch 1550, loss[loss=0.1588, simple_loss=0.265, pruned_loss=0.02631, over 7217.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2413, pruned_loss=0.0283, over 1424008.74 frames.], batch size: 22, lr: 2.00e-04
+2022-05-16 05:48:59,857 INFO [train.py:812] (7/8) Epoch 39, batch 1600, loss[loss=0.1735, simple_loss=0.2703, pruned_loss=0.0383, over 6754.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2412, pruned_loss=0.0281, over 1425767.27 frames.], batch size: 31, lr: 2.00e-04
+2022-05-16 05:49:57,811 INFO [train.py:812] (7/8) Epoch 39, batch 1650, loss[loss=0.1647, simple_loss=0.2622, pruned_loss=0.03357, over 7221.00 frames.], tot_loss[loss=0.149, simple_loss=0.2416, pruned_loss=0.02822, over 1425216.75 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:51:01,175 INFO [train.py:812] (7/8) Epoch 39, batch 1700, loss[loss=0.1447, simple_loss=0.2375, pruned_loss=0.02593, over 7077.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.02828, over 1426651.62 frames.], batch size: 28, lr: 2.00e-04
+2022-05-16 05:51:59,367 INFO [train.py:812] (7/8) Epoch 39, batch 1750, loss[loss=0.1476, simple_loss=0.2386, pruned_loss=0.02834, over 7428.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.02828, over 1425558.18 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:52:58,529 INFO [train.py:812] (7/8) Epoch 39, batch 1800, loss[loss=0.1647, simple_loss=0.2665, pruned_loss=0.03149, over 7208.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2426, pruned_loss=0.02859, over 1423345.20 frames.], batch size: 23, lr: 2.00e-04
+2022-05-16 05:53:57,510 INFO [train.py:812] (7/8) Epoch 39, batch 1850, loss[loss=0.1482, simple_loss=0.2343, pruned_loss=0.03106, over 7145.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2416, pruned_loss=0.02828, over 1420609.37 frames.], batch size: 19, lr: 2.00e-04
+2022-05-16 05:54:55,937 INFO [train.py:812] (7/8) Epoch 39, batch 1900, loss[loss=0.1255, simple_loss=0.2079, pruned_loss=0.02153, over 7285.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2409, pruned_loss=0.0283, over 1424154.95 frames.], batch size: 18, lr: 2.00e-04
+2022-05-16 05:55:54,024 INFO [train.py:812] (7/8) Epoch 39, batch 1950, loss[loss=0.1579, simple_loss=0.2608, pruned_loss=0.02746, over 7324.00 frames.], tot_loss[loss=0.149, simple_loss=0.2415, pruned_loss=0.02822, over 1424113.82 frames.], batch size: 21, lr: 1.99e-04
+2022-05-16 05:56:52,319 INFO [train.py:812] (7/8) Epoch 39, batch 2000, loss[loss=0.1493, simple_loss=0.2416, pruned_loss=0.02845, over 7251.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2413, pruned_loss=0.02804, over 1423096.07 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 05:57:50,333 INFO [train.py:812] (7/8) Epoch 39, batch 2050, loss[loss=0.15, simple_loss=0.2411, pruned_loss=0.0295, over 7327.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2417, pruned_loss=0.02849, over 1421249.42 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 05:58:49,553 INFO [train.py:812] (7/8) Epoch 39, batch 2100, loss[loss=0.1463, simple_loss=0.2209, pruned_loss=0.03579, over 7235.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2409, pruned_loss=0.02825, over 1422338.79 frames.], batch size: 16, lr: 1.99e-04
+2022-05-16 05:59:47,713 INFO [train.py:812] (7/8) Epoch 39, batch 2150, loss[loss=0.1333, simple_loss=0.2252, pruned_loss=0.02069, over 7267.00 frames.], tot_loss[loss=0.149, simple_loss=0.2415, pruned_loss=0.0283, over 1420235.15 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:00:46,908 INFO [train.py:812] (7/8) Epoch 39, batch 2200, loss[loss=0.1406, simple_loss=0.232, pruned_loss=0.02455, over 7210.00 frames.], tot_loss[loss=0.1484, simple_loss=0.241, pruned_loss=0.02787, over 1420800.53 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:01:45,970 INFO [train.py:812] (7/8) Epoch 39, batch 2250, loss[loss=0.1626, simple_loss=0.2649, pruned_loss=0.03019, over 7138.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2411, pruned_loss=0.02789, over 1423090.44 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:02:45,476 INFO [train.py:812] (7/8) Epoch 39, batch 2300, loss[loss=0.1403, simple_loss=0.2311, pruned_loss=0.0248, over 7158.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2411, pruned_loss=0.02809, over 1422559.47 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:03:45,500 INFO [train.py:812] (7/8) Epoch 39, batch 2350, loss[loss=0.1325, simple_loss=0.2292, pruned_loss=0.01788, over 7231.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2406, pruned_loss=0.02804, over 1424568.42 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:04:43,854 INFO [train.py:812] (7/8) Epoch 39, batch 2400, loss[loss=0.1488, simple_loss=0.2472, pruned_loss=0.02523, over 7140.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2402, pruned_loss=0.02814, over 1427403.15 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:05:41,803 INFO [train.py:812] (7/8) Epoch 39, batch 2450, loss[loss=0.1239, simple_loss=0.2059, pruned_loss=0.02095, over 7406.00 frames.], tot_loss[loss=0.147, simple_loss=0.239, pruned_loss=0.02745, over 1428175.75 frames.], batch size: 18, lr: 1.99e-04
+2022-05-16 06:06:40,899 INFO [train.py:812] (7/8) Epoch 39, batch 2500, loss[loss=0.1278, simple_loss=0.2154, pruned_loss=0.02014, over 7406.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2389, pruned_loss=0.02724, over 1426891.85 frames.], batch size: 18, lr: 1.99e-04
+2022-05-16 06:07:38,143 INFO [train.py:812] (7/8) Epoch 39, batch 2550, loss[loss=0.1451, simple_loss=0.2353, pruned_loss=0.02744, over 7433.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2389, pruned_loss=0.02743, over 1431542.10 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:08:37,373 INFO [train.py:812] (7/8) Epoch 39, batch 2600, loss[loss=0.1538, simple_loss=0.2502, pruned_loss=0.02869, over 7156.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2399, pruned_loss=0.02786, over 1429557.52 frames.], batch size: 26, lr: 1.99e-04
+2022-05-16 06:09:36,160 INFO [train.py:812] (7/8) Epoch 39, batch 2650, loss[loss=0.1407, simple_loss=0.2388, pruned_loss=0.02124, over 7084.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2403, pruned_loss=0.02819, over 1430807.43 frames.], batch size: 28, lr: 1.99e-04
+2022-05-16 06:10:34,105 INFO [train.py:812] (7/8) Epoch 39, batch 2700, loss[loss=0.181, simple_loss=0.2828, pruned_loss=0.03958, over 7294.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2405, pruned_loss=0.02799, over 1428830.13 frames.], batch size: 25, lr: 1.99e-04
+2022-05-16 06:11:32,685 INFO [train.py:812] (7/8) Epoch 39, batch 2750, loss[loss=0.1292, simple_loss=0.2166, pruned_loss=0.02092, over 7162.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2405, pruned_loss=0.02799, over 1429525.77 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:12:31,344 INFO [train.py:812] (7/8) Epoch 39, batch 2800, loss[loss=0.139, simple_loss=0.2409, pruned_loss=0.01861, over 7342.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2407, pruned_loss=0.02806, over 1426072.92 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:13:29,193 INFO [train.py:812] (7/8) Epoch 39, batch 2850, loss[loss=0.1334, simple_loss=0.233, pruned_loss=0.01684, over 6289.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2403, pruned_loss=0.02802, over 1426048.66 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:14:28,578 INFO [train.py:812] (7/8) Epoch 39, batch 2900, loss[loss=0.1394, simple_loss=0.2405, pruned_loss=0.01918, over 7316.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2406, pruned_loss=0.02838, over 1425934.08 frames.], batch size: 21, lr: 1.99e-04
+2022-05-16 06:15:27,576 INFO [train.py:812] (7/8) Epoch 39, batch 2950, loss[loss=0.1442, simple_loss=0.2374, pruned_loss=0.02552, over 7339.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2403, pruned_loss=0.02847, over 1428769.58 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:16:26,934 INFO [train.py:812] (7/8) Epoch 39, batch 3000, loss[loss=0.1587, simple_loss=0.2524, pruned_loss=0.03253, over 7232.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2413, pruned_loss=0.02866, over 1429297.69 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:16:26,935 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-16 06:16:34,437 INFO [train.py:841] (7/8) Epoch 39, validation: loss=0.153, simple_loss=0.2484, pruned_loss=0.02885, over 698248.00 frames.
+2022-05-16 06:17:33,446 INFO [train.py:812] (7/8) Epoch 39, batch 3050, loss[loss=0.1393, simple_loss=0.227, pruned_loss=0.02578, over 7123.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2414, pruned_loss=0.02886, over 1426549.00 frames.], batch size: 17, lr: 1.99e-04
+2022-05-16 06:18:32,171 INFO [train.py:812] (7/8) Epoch 39, batch 3100, loss[loss=0.1389, simple_loss=0.2341, pruned_loss=0.02184, over 6296.00 frames.], tot_loss[loss=0.15, simple_loss=0.2418, pruned_loss=0.02911, over 1418397.27 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:19:30,268 INFO [train.py:812] (7/8) Epoch 39, batch 3150, loss[loss=0.1722, simple_loss=0.2619, pruned_loss=0.04124, over 7407.00 frames.], tot_loss[loss=0.1499, simple_loss=0.242, pruned_loss=0.02892, over 1423793.12 frames.], batch size: 21, lr: 1.99e-04
+2022-05-16 06:20:28,883 INFO [train.py:812] (7/8) Epoch 39, batch 3200, loss[loss=0.1275, simple_loss=0.2265, pruned_loss=0.01426, over 6340.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2416, pruned_loss=0.02847, over 1424350.64 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:21:26,253 INFO [train.py:812] (7/8) Epoch 39, batch 3250, loss[loss=0.1655, simple_loss=0.2582, pruned_loss=0.03639, over 6363.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2415, pruned_loss=0.02797, over 1424568.84 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:22:25,467 INFO [train.py:812] (7/8) Epoch 39, batch 3300, loss[loss=0.141, simple_loss=0.2381, pruned_loss=0.02196, over 7159.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2413, pruned_loss=0.0282, over 1423923.23 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:23:24,299 INFO [train.py:812] (7/8) Epoch 39, batch 3350, loss[loss=0.1217, simple_loss=0.2109, pruned_loss=0.01621, over 7132.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2401, pruned_loss=0.02745, over 1425959.75 frames.], batch size: 17, lr: 1.99e-04
+2022-05-16 06:24:23,030 INFO [train.py:812] (7/8) Epoch 39, batch 3400, loss[loss=0.1605, simple_loss=0.2591, pruned_loss=0.03091, over 7352.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2402, pruned_loss=0.02764, over 1427188.29 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:25:22,247 INFO [train.py:812] (7/8) Epoch 39, batch 3450, loss[loss=0.1661, simple_loss=0.2601, pruned_loss=0.03604, over 7181.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2404, pruned_loss=0.02801, over 1419953.33 frames.], batch size: 23, lr: 1.99e-04
+2022-05-16 06:26:21,449 INFO [train.py:812] (7/8) Epoch 39, batch 3500, loss[loss=0.1268, simple_loss=0.2227, pruned_loss=0.01544, over 7153.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2412, pruned_loss=0.02826, over 1421080.63 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:27:20,256 INFO [train.py:812] (7/8) Epoch 39, batch 3550, loss[loss=0.1488, simple_loss=0.25, pruned_loss=0.02378, over 7333.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2411, pruned_loss=0.02829, over 1423166.50 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:28:19,552 INFO [train.py:812] (7/8) Epoch 39, batch 3600, loss[loss=0.1255, simple_loss=0.2131, pruned_loss=0.01897, over 7281.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2409, pruned_loss=0.02828, over 1423905.86 frames.], batch size: 18, lr: 1.99e-04
+2022-05-16 06:29:18,009 INFO [train.py:812] (7/8) Epoch 39, batch 3650, loss[loss=0.1734, simple_loss=0.2626, pruned_loss=0.04211, over 7078.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2408, pruned_loss=0.02818, over 1425358.77 frames.], batch size: 28, lr: 1.99e-04
+2022-05-16 06:30:16,889 INFO [train.py:812] (7/8) Epoch 39, batch 3700, loss[loss=0.154, simple_loss=0.2534, pruned_loss=0.02729, over 6442.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2414, pruned_loss=0.02823, over 1421983.15 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:31:16,275 INFO [train.py:812] (7/8) Epoch 39, batch 3750, loss[loss=0.1618, simple_loss=0.2654, pruned_loss=0.02906, over 7203.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2414, pruned_loss=0.0286, over 1415391.38 frames.], batch size: 23, lr: 1.98e-04
+2022-05-16 06:32:15,552 INFO [train.py:812] (7/8) Epoch 39, batch 3800, loss[loss=0.1329, simple_loss=0.2211, pruned_loss=0.02233, over 7371.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2408, pruned_loss=0.02815, over 1421850.05 frames.], batch size: 19, lr: 1.98e-04
+2022-05-16 06:33:12,752 INFO [train.py:812] (7/8) Epoch 39, batch 3850, loss[loss=0.1651, simple_loss=0.246, pruned_loss=0.04206, over 4696.00 frames.], tot_loss[loss=0.1489, simple_loss=0.241, pruned_loss=0.02842, over 1418170.29 frames.], batch size: 52, lr: 1.98e-04
+2022-05-16 06:34:10,699 INFO [train.py:812] (7/8) Epoch 39, batch 3900, loss[loss=0.1625, simple_loss=0.2631, pruned_loss=0.03095, over 7019.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2413, pruned_loss=0.02868, over 1419075.00 frames.], batch size: 28, lr: 1.98e-04
+2022-05-16 06:35:09,069 INFO [train.py:812] (7/8) Epoch 39, batch 3950, loss[loss=0.1638, simple_loss=0.2544, pruned_loss=0.03659, over 7321.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2413, pruned_loss=0.02859, over 1421305.78 frames.], batch size: 25, lr: 1.98e-04
+2022-05-16 06:36:07,276 INFO [train.py:812] (7/8) Epoch 39, batch 4000, loss[loss=0.1357, simple_loss=0.2288, pruned_loss=0.02124, over 6721.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2412, pruned_loss=0.02866, over 1423100.15 frames.], batch size: 31, lr: 1.98e-04
+2022-05-16 06:37:03,596 INFO [train.py:812] (7/8) Epoch 39, batch 4050, loss[loss=0.1686, simple_loss=0.2694, pruned_loss=0.03392, over 6819.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2418, pruned_loss=0.02874, over 1422262.44 frames.], batch size: 31, lr: 1.98e-04
+2022-05-16 06:38:02,809 INFO [train.py:812] (7/8) Epoch 39, batch 4100, loss[loss=0.152, simple_loss=0.2476, pruned_loss=0.02824, over 7220.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2415, pruned_loss=0.02857, over 1422103.14 frames.], batch size: 21, lr: 1.98e-04
+2022-05-16 06:39:01,698 INFO [train.py:812] (7/8) Epoch 39, batch 4150, loss[loss=0.1318, simple_loss=0.2301, pruned_loss=0.01678, over 7214.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2413, pruned_loss=0.02824, over 1420069.61 frames.], batch size: 21, lr: 1.98e-04
+2022-05-16 06:40:00,314 INFO [train.py:812] (7/8) Epoch 39, batch 4200, loss[loss=0.1648, simple_loss=0.2517, pruned_loss=0.03893, over 6709.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2418, pruned_loss=0.02848, over 1420116.03 frames.], batch size: 31, lr: 1.98e-04
+2022-05-16 06:40:58,799 INFO [train.py:812] (7/8) Epoch 39, batch 4250, loss[loss=0.1487, simple_loss=0.2268, pruned_loss=0.03524, over 7154.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2415, pruned_loss=0.02845, over 1417457.08 frames.], batch size: 17, lr: 1.98e-04
+2022-05-16 06:41:58,219 INFO [train.py:812] (7/8) Epoch 39, batch 4300, loss[loss=0.1618, simple_loss=0.2629, pruned_loss=0.0304, over 7299.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2423, pruned_loss=0.02846, over 1418859.29 frames.], batch size: 25, lr: 1.98e-04
+2022-05-16 06:42:57,011 INFO [train.py:812] (7/8) Epoch 39, batch 4350, loss[loss=0.1476, simple_loss=0.242, pruned_loss=0.02657, over 7431.00 frames.], tot_loss[loss=0.15, simple_loss=0.2427, pruned_loss=0.02868, over 1415455.08 frames.], batch size: 20, lr: 1.98e-04
+2022-05-16 06:43:56,275 INFO [train.py:812] (7/8) Epoch 39, batch 4400, loss[loss=0.1404, simple_loss=0.2422, pruned_loss=0.01931, over 7329.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2439, pruned_loss=0.02892, over 1412020.40 frames.], batch size: 22, lr: 1.98e-04
+2022-05-16 06:44:54,128 INFO [train.py:812] (7/8) Epoch 39, batch 4450, loss[loss=0.1333, simple_loss=0.2173, pruned_loss=0.0246, over 7416.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2447, pruned_loss=0.0296, over 1399005.94 frames.], batch size: 17, lr: 1.98e-04
+2022-05-16 06:45:52,386 INFO [train.py:812] (7/8) Epoch 39, batch 4500, loss[loss=0.1352, simple_loss=0.2311, pruned_loss=0.01964, over 7171.00 frames.], tot_loss[loss=0.152, simple_loss=0.2448, pruned_loss=0.02956, over 1387604.57 frames.], batch size: 18, lr: 1.98e-04
+2022-05-16 06:46:49,713 INFO [train.py:812] (7/8) Epoch 39, batch 4550, loss[loss=0.1998, simple_loss=0.2871, pruned_loss=0.05625, over 5073.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2466, pruned_loss=0.0305, over 1348534.40 frames.], batch size: 52, lr: 1.98e-04
+2022-05-16 06:47:54,912 INFO [train.py:812] (7/8) Epoch 40, batch 0, loss[loss=0.21, simple_loss=0.3032, pruned_loss=0.05837, over 7298.00 frames.], tot_loss[loss=0.21, simple_loss=0.3032, pruned_loss=0.05837, over 7298.00 frames.], batch size: 24, lr: 1.96e-04
+2022-05-16 06:48:53,206 INFO [train.py:812] (7/8) Epoch 40, batch 50, loss[loss=0.1315, simple_loss=0.2081, pruned_loss=0.0274, over 7277.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03035, over 317620.78 frames.], batch size: 17, lr: 1.95e-04
+2022-05-16 06:49:52,168 INFO [train.py:812] (7/8) Epoch 40, batch 100, loss[loss=0.1622, simple_loss=0.2579, pruned_loss=0.03323, over 7359.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2425, pruned_loss=0.02962, over 563258.61 frames.], batch size: 19, lr: 1.95e-04
+2022-05-16 06:50:51,454 INFO [train.py:812] (7/8) Epoch 40, batch 150, loss[loss=0.1609, simple_loss=0.2568, pruned_loss=0.03249, over 7239.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2398, pruned_loss=0.02879, over 755801.07 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 06:51:50,292 INFO [train.py:812] (7/8) Epoch 40, batch 200, loss[loss=0.1296, simple_loss=0.2122, pruned_loss=0.02347, over 7426.00 frames.], tot_loss[loss=0.1489, simple_loss=0.241, pruned_loss=0.02836, over 903616.72 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 06:52:48,899 INFO [train.py:812] (7/8) Epoch 40, batch 250, loss[loss=0.1441, simple_loss=0.2382, pruned_loss=0.02501, over 7442.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2407, pruned_loss=0.0283, over 1016985.49 frames.], batch size: 22, lr: 1.95e-04
+2022-05-16 06:53:47,846 INFO [train.py:812] (7/8) Epoch 40, batch 300, loss[loss=0.1566, simple_loss=0.2485, pruned_loss=0.03236, over 7294.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2409, pruned_loss=0.02825, over 1106944.13 frames.], batch size: 24, lr: 1.95e-04
+2022-05-16 06:54:46,904 INFO [train.py:812] (7/8) Epoch 40, batch 350, loss[loss=0.1506, simple_loss=0.2486, pruned_loss=0.02626, over 7149.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2404, pruned_loss=0.02814, over 1172477.33 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 06:55:45,302 INFO [train.py:812] (7/8) Epoch 40, batch 400, loss[loss=0.1493, simple_loss=0.2432, pruned_loss=0.02769, over 7207.00 frames.], tot_loss[loss=0.149, simple_loss=0.2412, pruned_loss=0.02839, over 1229437.45 frames.], batch size: 26, lr: 1.95e-04
+2022-05-16 06:56:53,575 INFO [train.py:812] (7/8) Epoch 40, batch 450, loss[loss=0.1575, simple_loss=0.2449, pruned_loss=0.03508, over 7305.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2408, pruned_loss=0.02823, over 1273387.35 frames.], batch size: 25, lr: 1.95e-04
+2022-05-16 06:57:52,484 INFO [train.py:812] (7/8) Epoch 40, batch 500, loss[loss=0.1571, simple_loss=0.2593, pruned_loss=0.02746, over 7314.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2404, pruned_loss=0.02792, over 1306206.85 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 06:58:59,654 INFO [train.py:812] (7/8) Epoch 40, batch 550, loss[loss=0.1637, simple_loss=0.2471, pruned_loss=0.04013, over 7243.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2409, pruned_loss=0.02837, over 1328180.93 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 06:59:58,473 INFO [train.py:812] (7/8) Epoch 40, batch 600, loss[loss=0.1225, simple_loss=0.2128, pruned_loss=0.01607, over 7270.00 frames.], tot_loss[loss=0.148, simple_loss=0.24, pruned_loss=0.02797, over 1349565.65 frames.], batch size: 19, lr: 1.95e-04
+2022-05-16 07:01:07,502 INFO [train.py:812] (7/8) Epoch 40, batch 650, loss[loss=0.1445, simple_loss=0.2384, pruned_loss=0.02532, over 7230.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2398, pruned_loss=0.02797, over 1368142.11 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 07:02:07,085 INFO [train.py:812] (7/8) Epoch 40, batch 700, loss[loss=0.1194, simple_loss=0.2064, pruned_loss=0.01615, over 7273.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2399, pruned_loss=0.02818, over 1381394.54 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 07:03:06,198 INFO [train.py:812] (7/8) Epoch 40, batch 750, loss[loss=0.1486, simple_loss=0.2416, pruned_loss=0.02781, over 7360.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2392, pruned_loss=0.02765, over 1387082.75 frames.], batch size: 19, lr: 1.95e-04
+2022-05-16 07:04:05,452 INFO [train.py:812] (7/8) Epoch 40, batch 800, loss[loss=0.1572, simple_loss=0.2577, pruned_loss=0.02835, over 7111.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2399, pruned_loss=0.02798, over 1396302.11 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:05:03,693 INFO [train.py:812] (7/8) Epoch 40, batch 850, loss[loss=0.1363, simple_loss=0.2213, pruned_loss=0.02564, over 7129.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2413, pruned_loss=0.02856, over 1402907.22 frames.], batch size: 17, lr: 1.95e-04
+2022-05-16 07:06:12,353 INFO [train.py:812] (7/8) Epoch 40, batch 900, loss[loss=0.1655, simple_loss=0.2607, pruned_loss=0.03518, over 7183.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2417, pruned_loss=0.02832, over 1408614.19 frames.], batch size: 23, lr: 1.95e-04
+2022-05-16 07:07:10,767 INFO [train.py:812] (7/8) Epoch 40, batch 950, loss[loss=0.1495, simple_loss=0.2388, pruned_loss=0.03011, over 5008.00 frames.], tot_loss[loss=0.1496, simple_loss=0.242, pruned_loss=0.02855, over 1411350.44 frames.], batch size: 52, lr: 1.95e-04
+2022-05-16 07:08:20,211 INFO [train.py:812] (7/8) Epoch 40, batch 1000, loss[loss=0.1454, simple_loss=0.245, pruned_loss=0.02294, over 7126.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2415, pruned_loss=0.02813, over 1409823.02 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:09:19,157 INFO [train.py:812] (7/8) Epoch 40, batch 1050, loss[loss=0.1676, simple_loss=0.2649, pruned_loss=0.03517, over 7226.00 frames.], tot_loss[loss=0.1493, simple_loss=0.242, pruned_loss=0.0283, over 1408631.64 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:10:42,487 INFO [train.py:812] (7/8) Epoch 40, batch 1100, loss[loss=0.1551, simple_loss=0.2437, pruned_loss=0.03325, over 7161.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2418, pruned_loss=0.0282, over 1408054.45 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 07:11:40,923 INFO [train.py:812] (7/8) Epoch 40, batch 1150, loss[loss=0.148, simple_loss=0.2464, pruned_loss=0.02484, over 6694.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2418, pruned_loss=0.028, over 1415246.40 frames.], batch size: 31, lr: 1.95e-04
+2022-05-16 07:12:38,519 INFO [train.py:812] (7/8) Epoch 40, batch 1200, loss[loss=0.1544, simple_loss=0.2512, pruned_loss=0.0288, over 6379.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2423, pruned_loss=0.02799, over 1417827.03 frames.], batch size: 37, lr: 1.95e-04
+2022-05-16 07:13:37,112 INFO [train.py:812] (7/8) Epoch 40, batch 1250, loss[loss=0.1988, simple_loss=0.2927, pruned_loss=0.05244, over 7295.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2417, pruned_loss=0.02809, over 1421663.70 frames.], batch size: 25, lr: 1.95e-04
+2022-05-16 07:14:35,241 INFO [train.py:812] (7/8) Epoch 40, batch 1300, loss[loss=0.1782, simple_loss=0.2825, pruned_loss=0.03693, over 7431.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2422, pruned_loss=0.02813, over 1421989.59 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 07:15:33,951 INFO [train.py:812] (7/8) Epoch 40, batch 1350, loss[loss=0.144, simple_loss=0.247, pruned_loss=0.02048, over 6451.00 frames.], tot_loss[loss=0.149, simple_loss=0.2419, pruned_loss=0.02809, over 1421372.99 frames.], batch size: 38, lr: 1.95e-04
+2022-05-16 07:16:32,360 INFO [train.py:812] (7/8) Epoch 40, batch 1400, loss[loss=0.1494, simple_loss=0.2463, pruned_loss=0.02619, over 6553.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2422, pruned_loss=0.02823, over 1423629.06 frames.], batch size: 38, lr: 1.95e-04
+2022-05-16 07:17:30,667 INFO [train.py:812] (7/8) Epoch 40, batch 1450, loss[loss=0.1718, simple_loss=0.2623, pruned_loss=0.04062, over 7227.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2417, pruned_loss=0.02828, over 1425107.32 frames.], batch size: 23, lr: 1.95e-04
+2022-05-16 07:18:29,829 INFO [train.py:812] (7/8) Epoch 40, batch 1500, loss[loss=0.1387, simple_loss=0.2256, pruned_loss=0.02586, over 7144.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2419, pruned_loss=0.02783, over 1425406.55 frames.], batch size: 17, lr: 1.95e-04
+2022-05-16 07:19:28,058 INFO [train.py:812] (7/8) Epoch 40, batch 1550, loss[loss=0.1717, simple_loss=0.2693, pruned_loss=0.03702, over 7199.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2411, pruned_loss=0.02785, over 1423682.78 frames.], batch size: 23, lr: 1.95e-04
+2022-05-16 07:20:27,062 INFO [train.py:812] (7/8) Epoch 40, batch 1600, loss[loss=0.155, simple_loss=0.2499, pruned_loss=0.03007, over 7054.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2413, pruned_loss=0.02795, over 1426627.05 frames.], batch size: 28, lr: 1.95e-04
+2022-05-16 07:21:25,493 INFO [train.py:812] (7/8) Epoch 40, batch 1650, loss[loss=0.2074, simple_loss=0.2879, pruned_loss=0.06342, over 5111.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2417, pruned_loss=0.0283, over 1420051.50 frames.], batch size: 52, lr: 1.95e-04
+2022-05-16 07:22:23,940 INFO [train.py:812] (7/8) Epoch 40, batch 1700, loss[loss=0.1384, simple_loss=0.2176, pruned_loss=0.02959, over 7022.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2416, pruned_loss=0.02848, over 1413001.59 frames.], batch size: 16, lr: 1.95e-04
+2022-05-16 07:23:23,277 INFO [train.py:812] (7/8) Epoch 40, batch 1750, loss[loss=0.1654, simple_loss=0.2516, pruned_loss=0.0396, over 7318.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2414, pruned_loss=0.02834, over 1414685.48 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:24:22,486 INFO [train.py:812] (7/8) Epoch 40, batch 1800, loss[loss=0.1496, simple_loss=0.2457, pruned_loss=0.02672, over 7321.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2419, pruned_loss=0.02862, over 1416973.73 frames.], batch size: 22, lr: 1.95e-04
+2022-05-16 07:25:21,071 INFO [train.py:812] (7/8) Epoch 40, batch 1850, loss[loss=0.1466, simple_loss=0.2311, pruned_loss=0.03104, over 7055.00 frames.], tot_loss[loss=0.1496, simple_loss=0.242, pruned_loss=0.02859, over 1420257.82 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 07:26:20,240 INFO [train.py:812] (7/8) Epoch 40, batch 1900, loss[loss=0.1281, simple_loss=0.2289, pruned_loss=0.01362, over 7158.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2421, pruned_loss=0.02843, over 1423617.34 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:27:17,897 INFO [train.py:812] (7/8) Epoch 40, batch 1950, loss[loss=0.1678, simple_loss=0.2652, pruned_loss=0.03521, over 5213.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2418, pruned_loss=0.02822, over 1418187.92 frames.], batch size: 52, lr: 1.94e-04
+2022-05-16 07:28:16,426 INFO [train.py:812] (7/8) Epoch 40, batch 2000, loss[loss=0.1459, simple_loss=0.2405, pruned_loss=0.02562, over 7458.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2417, pruned_loss=0.02829, over 1422304.92 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:29:15,115 INFO [train.py:812] (7/8) Epoch 40, batch 2050, loss[loss=0.1168, simple_loss=0.201, pruned_loss=0.01629, over 7421.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.0287, over 1426222.83 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:30:14,408 INFO [train.py:812] (7/8) Epoch 40, batch 2100, loss[loss=0.1155, simple_loss=0.2012, pruned_loss=0.01489, over 7412.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2417, pruned_loss=0.02867, over 1425837.79 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:31:12,655 INFO [train.py:812] (7/8) Epoch 40, batch 2150, loss[loss=0.1472, simple_loss=0.2495, pruned_loss=0.02241, over 7144.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2408, pruned_loss=0.02814, over 1429633.89 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:32:11,382 INFO [train.py:812] (7/8) Epoch 40, batch 2200, loss[loss=0.1565, simple_loss=0.2504, pruned_loss=0.03126, over 7237.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2412, pruned_loss=0.02806, over 1432467.54 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:33:10,332 INFO [train.py:812] (7/8) Epoch 40, batch 2250, loss[loss=0.1756, simple_loss=0.2694, pruned_loss=0.04094, over 7213.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2412, pruned_loss=0.02795, over 1430616.31 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:34:08,386 INFO [train.py:812] (7/8) Epoch 40, batch 2300, loss[loss=0.1386, simple_loss=0.2311, pruned_loss=0.02301, over 7428.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2405, pruned_loss=0.02803, over 1426439.23 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:35:07,198 INFO [train.py:812] (7/8) Epoch 40, batch 2350, loss[loss=0.1412, simple_loss=0.2248, pruned_loss=0.02875, over 7333.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2396, pruned_loss=0.02806, over 1426281.61 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:36:06,649 INFO [train.py:812] (7/8) Epoch 40, batch 2400, loss[loss=0.1705, simple_loss=0.2647, pruned_loss=0.03819, over 7204.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2404, pruned_loss=0.02844, over 1426882.07 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:37:04,726 INFO [train.py:812] (7/8) Epoch 40, batch 2450, loss[loss=0.1728, simple_loss=0.2681, pruned_loss=0.0387, over 7038.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2414, pruned_loss=0.02859, over 1422468.61 frames.], batch size: 28, lr: 1.94e-04
+2022-05-16 07:38:03,609 INFO [train.py:812] (7/8) Epoch 40, batch 2500, loss[loss=0.1456, simple_loss=0.2404, pruned_loss=0.02534, over 7409.00 frames.], tot_loss[loss=0.149, simple_loss=0.2412, pruned_loss=0.02839, over 1419150.48 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:39:02,647 INFO [train.py:812] (7/8) Epoch 40, batch 2550, loss[loss=0.1615, simple_loss=0.2609, pruned_loss=0.03107, over 6986.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2419, pruned_loss=0.0284, over 1418666.30 frames.], batch size: 28, lr: 1.94e-04
+2022-05-16 07:40:02,284 INFO [train.py:812] (7/8) Epoch 40, batch 2600, loss[loss=0.1464, simple_loss=0.2468, pruned_loss=0.02301, over 7335.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2414, pruned_loss=0.02851, over 1418504.47 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:40:59,603 INFO [train.py:812] (7/8) Epoch 40, batch 2650, loss[loss=0.1335, simple_loss=0.2211, pruned_loss=0.02296, over 7155.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2417, pruned_loss=0.02896, over 1420858.99 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:42:08,115 INFO [train.py:812] (7/8) Epoch 40, batch 2700, loss[loss=0.1604, simple_loss=0.2566, pruned_loss=0.03215, over 7197.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02887, over 1423071.38 frames.], batch size: 26, lr: 1.94e-04
+2022-05-16 07:43:06,188 INFO [train.py:812] (7/8) Epoch 40, batch 2750, loss[loss=0.174, simple_loss=0.2671, pruned_loss=0.0405, over 7297.00 frames.], tot_loss[loss=0.15, simple_loss=0.2425, pruned_loss=0.02877, over 1426293.70 frames.], batch size: 24, lr: 1.94e-04
+2022-05-16 07:44:05,723 INFO [train.py:812] (7/8) Epoch 40, batch 2800, loss[loss=0.1287, simple_loss=0.2107, pruned_loss=0.02331, over 7056.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2423, pruned_loss=0.02851, over 1423191.62 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:45:02,908 INFO [train.py:812] (7/8) Epoch 40, batch 2850, loss[loss=0.1472, simple_loss=0.2421, pruned_loss=0.02613, over 6352.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2418, pruned_loss=0.02834, over 1419505.15 frames.], batch size: 38, lr: 1.94e-04
+2022-05-16 07:46:01,114 INFO [train.py:812] (7/8) Epoch 40, batch 2900, loss[loss=0.1321, simple_loss=0.2279, pruned_loss=0.01813, over 7054.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2409, pruned_loss=0.02774, over 1419702.64 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:46:58,682 INFO [train.py:812] (7/8) Epoch 40, batch 2950, loss[loss=0.1502, simple_loss=0.2471, pruned_loss=0.02666, over 7280.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2416, pruned_loss=0.02809, over 1418473.77 frames.], batch size: 24, lr: 1.94e-04
+2022-05-16 07:47:56,509 INFO [train.py:812] (7/8) Epoch 40, batch 3000, loss[loss=0.1574, simple_loss=0.2504, pruned_loss=0.03219, over 7339.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.02831, over 1412780.82 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:47:56,511 INFO [train.py:832] (7/8) Computing validation loss
+2022-05-16 07:48:04,107 INFO [train.py:841] (7/8) Epoch 40, validation: loss=0.1534, simple_loss=0.2485, pruned_loss=0.02916, over 698248.00 frames.
+2022-05-16 07:49:02,595 INFO [train.py:812] (7/8) Epoch 40, batch 3050, loss[loss=0.1323, simple_loss=0.2304, pruned_loss=0.01711, over 7369.00 frames.], tot_loss[loss=0.149, simple_loss=0.2417, pruned_loss=0.02812, over 1414901.74 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:50:01,839 INFO [train.py:812] (7/8) Epoch 40, batch 3100, loss[loss=0.1495, simple_loss=0.2524, pruned_loss=0.02326, over 7206.00 frames.], tot_loss[loss=0.1492, simple_loss=0.242, pruned_loss=0.02821, over 1417431.55 frames.], batch size: 26, lr: 1.94e-04
+2022-05-16 07:51:00,462 INFO [train.py:812] (7/8) Epoch 40, batch 3150, loss[loss=0.1512, simple_loss=0.2518, pruned_loss=0.02537, over 7158.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2422, pruned_loss=0.02827, over 1421406.93 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:51:59,415 INFO [train.py:812] (7/8) Epoch 40, batch 3200, loss[loss=0.1497, simple_loss=0.2446, pruned_loss=0.02744, over 5274.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2419, pruned_loss=0.02798, over 1421644.45 frames.], batch size: 52, lr: 1.94e-04
+2022-05-16 07:52:57,290 INFO [train.py:812] (7/8) Epoch 40, batch 3250, loss[loss=0.1442, simple_loss=0.2369, pruned_loss=0.02578, over 7381.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2429, pruned_loss=0.02804, over 1420629.84 frames.], batch size: 23, lr: 1.94e-04
+2022-05-16 07:53:57,070 INFO [train.py:812] (7/8) Epoch 40, batch 3300, loss[loss=0.1652, simple_loss=0.2615, pruned_loss=0.03447, over 7107.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2419, pruned_loss=0.02801, over 1419784.89 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:54:55,930 INFO [train.py:812] (7/8) Epoch 40, batch 3350, loss[loss=0.1593, simple_loss=0.2601, pruned_loss=0.02922, over 7110.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2423, pruned_loss=0.02813, over 1417368.64 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:55:55,746 INFO [train.py:812] (7/8) Epoch 40, batch 3400, loss[loss=0.1628, simple_loss=0.259, pruned_loss=0.03336, over 7148.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2423, pruned_loss=0.02829, over 1418338.20 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:56:54,707 INFO [train.py:812] (7/8) Epoch 40, batch 3450, loss[loss=0.1337, simple_loss=0.2175, pruned_loss=0.02489, over 7289.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2425, pruned_loss=0.02839, over 1416995.34 frames.], batch size: 17, lr: 1.94e-04
+2022-05-16 07:57:54,446 INFO [train.py:812] (7/8) Epoch 40, batch 3500, loss[loss=0.1389, simple_loss=0.2371, pruned_loss=0.02038, over 7324.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2419, pruned_loss=0.0281, over 1418149.75 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:58:53,151 INFO [train.py:812] (7/8) Epoch 40, batch 3550, loss[loss=0.1278, simple_loss=0.2112, pruned_loss=0.02222, over 7066.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2407, pruned_loss=0.0278, over 1419323.71 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:59:51,437 INFO [train.py:812] (7/8) Epoch 40, batch 3600, loss[loss=0.1897, simple_loss=0.2688, pruned_loss=0.0553, over 5309.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2413, pruned_loss=0.02815, over 1416784.00 frames.], batch size: 52, lr: 1.94e-04
+2022-05-16 08:00:51,290 INFO [train.py:812] (7/8) Epoch 40, batch 3650, loss[loss=0.1642, simple_loss=0.2509, pruned_loss=0.03874, over 6291.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2412, pruned_loss=0.02831, over 1418522.32 frames.], batch size: 37, lr: 1.94e-04
+2022-05-16 08:01:49,927 INFO [train.py:812] (7/8) Epoch 40, batch 3700, loss[loss=0.1378, simple_loss=0.2244, pruned_loss=0.02559, over 7134.00 frames.], tot_loss[loss=0.148, simple_loss=0.2404, pruned_loss=0.02778, over 1422183.67 frames.], batch size: 17, lr: 1.94e-04
+2022-05-16 08:02:47,010 INFO [train.py:812] (7/8) Epoch 40, batch 3750, loss[loss=0.1346, simple_loss=0.2275, pruned_loss=0.02085, over 7341.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2401, pruned_loss=0.02751, over 1418778.44 frames.], batch size: 19, lr: 1.93e-04
+2022-05-16 08:03:45,485 INFO [train.py:812] (7/8) Epoch 40, batch 3800, loss[loss=0.1263, simple_loss=0.213, pruned_loss=0.01984, over 7002.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2402, pruned_loss=0.02743, over 1422622.01 frames.], batch size: 16, lr: 1.93e-04
+2022-05-16 08:04:42,356 INFO [train.py:812] (7/8) Epoch 40, batch 3850, loss[loss=0.166, simple_loss=0.2621, pruned_loss=0.03492, over 7407.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2399, pruned_loss=0.02746, over 1419238.77 frames.], batch size: 21, lr: 1.93e-04
+2022-05-16 08:05:41,383 INFO [train.py:812] (7/8) Epoch 40, batch 3900, loss[loss=0.1791, simple_loss=0.2821, pruned_loss=0.03809, over 7212.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2395, pruned_loss=0.02731, over 1419830.86 frames.], batch size: 23, lr: 1.93e-04
+2022-05-16 08:06:40,233 INFO [train.py:812] (7/8) Epoch 40, batch 3950, loss[loss=0.1343, simple_loss=0.2211, pruned_loss=0.02377, over 7057.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2393, pruned_loss=0.02761, over 1414961.54 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:07:38,741 INFO [train.py:812] (7/8) Epoch 40, batch 4000, loss[loss=0.1333, simple_loss=0.2119, pruned_loss=0.02731, over 7128.00 frames.], tot_loss[loss=0.148, simple_loss=0.2398, pruned_loss=0.02807, over 1415718.69 frames.], batch size: 17, lr: 1.93e-04
+2022-05-16 08:08:36,155 INFO [train.py:812] (7/8) Epoch 40, batch 4050, loss[loss=0.1667, simple_loss=0.2526, pruned_loss=0.04039, over 7208.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2407, pruned_loss=0.02836, over 1420327.37 frames.], batch size: 22, lr: 1.93e-04
+2022-05-16 08:09:35,671 INFO [train.py:812] (7/8) Epoch 40, batch 4100, loss[loss=0.1425, simple_loss=0.2423, pruned_loss=0.02138, over 7238.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2406, pruned_loss=0.02817, over 1420472.52 frames.], batch size: 20, lr: 1.93e-04
+2022-05-16 08:10:34,191 INFO [train.py:812] (7/8) Epoch 40, batch 4150, loss[loss=0.1657, simple_loss=0.2484, pruned_loss=0.04148, over 7288.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2406, pruned_loss=0.02813, over 1422717.47 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:11:32,971 INFO [train.py:812] (7/8) Epoch 40, batch 4200, loss[loss=0.1517, simple_loss=0.2363, pruned_loss=0.03357, over 7165.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2407, pruned_loss=0.028, over 1423890.29 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:12:31,960 INFO [train.py:812] (7/8) Epoch 40, batch 4250, loss[loss=0.1401, simple_loss=0.232, pruned_loss=0.02414, over 7330.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2409, pruned_loss=0.0282, over 1419858.99 frames.], batch size: 21, lr: 1.93e-04
+2022-05-16 08:13:30,197 INFO [train.py:812] (7/8) Epoch 40, batch 4300, loss[loss=0.1389, simple_loss=0.2242, pruned_loss=0.02682, over 7161.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2408, pruned_loss=0.02821, over 1420325.40 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:14:29,475 INFO [train.py:812] (7/8) Epoch 40, batch 4350, loss[loss=0.167, simple_loss=0.2568, pruned_loss=0.0386, over 7317.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2412, pruned_loss=0.02832, over 1421952.59 frames.], batch size: 20, lr: 1.93e-04
+2022-05-16 08:15:29,019 INFO [train.py:812] (7/8) Epoch 40, batch 4400, loss[loss=0.1611, simple_loss=0.2597, pruned_loss=0.03129, over 6702.00 frames.], tot_loss[loss=0.1494, simple_loss=0.242, pruned_loss=0.02836, over 1421643.32 frames.], batch size: 31, lr: 1.93e-04
+2022-05-16 08:16:26,688 INFO [train.py:812] (7/8) Epoch 40, batch 4450, loss[loss=0.1293, simple_loss=0.2188, pruned_loss=0.0199, over 7171.00 frames.], tot_loss[loss=0.149, simple_loss=0.2414, pruned_loss=0.0283, over 1409346.34 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:17:25,887 INFO [train.py:812] (7/8) Epoch 40, batch 4500, loss[loss=0.1648, simple_loss=0.2565, pruned_loss=0.03655, over 7223.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2418, pruned_loss=0.02841, over 1400407.67 frames.], batch size: 21, lr: 1.93e-04
+2022-05-16 08:18:25,903 INFO [train.py:812] (7/8) Epoch 40, batch 4550, loss[loss=0.1504, simple_loss=0.2347, pruned_loss=0.03302, over 7198.00 frames.], tot_loss[loss=0.1477, simple_loss=0.239, pruned_loss=0.02815, over 1393058.70 frames.], batch size: 16, lr: 1.93e-04
+2022-05-16 08:19:10,667 INFO [train.py:1030] (7/8) Done!