diff --git "a/exp/log/log-train-2022-05-13-19-15-59-1" "b/exp/log/log-train-2022-05-13-19-15-59-1"
new file mode 100644--- /dev/null
+++ "b/exp/log/log-train-2022-05-13-19-15-59-1"
@@ -0,0 +1,3784 @@
+2022-05-13 19:15:59,542 INFO [train.py:876] (1/8) Training started
+2022-05-13 19:15:59,542 INFO [train.py:886] (1/8) Device: cuda:1
+2022-05-13 19:15:59,546 INFO [train.py:895] (1/8) {'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 19:15:59,546 INFO [train.py:897] (1/8) About to create model
+2022-05-13 19:16:00,251 INFO [train.py:901] (1/8) Number of model parameters: 116553580
+2022-05-13 19:16:08,547 INFO [train.py:916] (1/8) Using DDP
+2022-05-13 19:16:09,394 INFO [asr_datamodule.py:391] (1/8) About to get train-clean-100 cuts
+2022-05-13 19:16:17,552 INFO [asr_datamodule.py:398] (1/8) About to get train-clean-360 cuts
+2022-05-13 19:16:49,798 INFO [asr_datamodule.py:405] (1/8) About to get train-other-500 cuts
+2022-05-13 19:17:42,148 INFO [asr_datamodule.py:209] (1/8) Enable MUSAN
+2022-05-13 19:17:42,148 INFO [asr_datamodule.py:210] (1/8) About to get Musan cuts
+2022-05-13 19:17:44,032 INFO [asr_datamodule.py:238] (1/8) Enable SpecAugment
+2022-05-13 19:17:44,033 INFO [asr_datamodule.py:239] (1/8) Time warp factor: 80
+2022-05-13 19:17:44,033 INFO [asr_datamodule.py:251] (1/8) Num frame mask: 10
+2022-05-13 19:17:44,034 INFO [asr_datamodule.py:264] (1/8) About to create train dataset
+2022-05-13 19:17:44,034 INFO [asr_datamodule.py:292] (1/8) Using BucketingSampler.
+2022-05-13 19:17:49,195 INFO [asr_datamodule.py:308] (1/8) About to create train dataloader
+2022-05-13 19:17:49,197 INFO [asr_datamodule.py:412] (1/8) About to get dev-clean cuts
+2022-05-13 19:17:49,542 INFO [asr_datamodule.py:417] (1/8) About to get dev-other cuts
+2022-05-13 19:17:49,741 INFO [asr_datamodule.py:339] (1/8) About to create dev dataset
+2022-05-13 19:17:49,753 INFO [asr_datamodule.py:358] (1/8) About to create dev dataloader
+2022-05-13 19:17:49,754 INFO [train.py:1078] (1/8) Sanity check -- see if any of the batches in epoch 1 would cause OOM.
+2022-05-13 19:18:18,393 INFO [distributed.py:874] (1/8) Reducer buckets have been rebuilt in this iteration.
+2022-05-13 19:18:41,989 INFO [train.py:812] (1/8) Epoch 1, batch 0, loss[loss=0.7973, simple_loss=1.595, pruned_loss=6.607, over 7292.00 frames.], tot_loss[loss=0.7973, simple_loss=1.595, pruned_loss=6.607, over 7292.00 frames.], batch size: 17, lr: 3.00e-03
+2022-05-13 19:19:41,268 INFO [train.py:812] (1/8) Epoch 1, batch 50, loss[loss=0.4941, simple_loss=0.9881, pruned_loss=7.082, over 7175.00 frames.], tot_loss[loss=0.5553, simple_loss=1.111, pruned_loss=7.115, over 324695.83 frames.], batch size: 19, lr: 3.00e-03
+2022-05-13 19:20:39,816 INFO [train.py:812] (1/8) Epoch 1, batch 100, loss[loss=0.416, simple_loss=0.832, pruned_loss=6.648, over 7014.00 frames.], tot_loss[loss=0.4941, simple_loss=0.9882, pruned_loss=6.966, over 567421.65 frames.], batch size: 16, lr: 3.00e-03
+2022-05-13 19:21:38,648 INFO [train.py:812] (1/8) Epoch 1, batch 150, loss[loss=0.3473, simple_loss=0.6946, pruned_loss=6.728, over 7002.00 frames.], tot_loss[loss=0.4621, simple_loss=0.9242, pruned_loss=6.873, over 758142.66 frames.], batch size: 16, lr: 3.00e-03
+2022-05-13 19:22:36,947 INFO [train.py:812] (1/8) Epoch 1, batch 200, loss[loss=0.4146, simple_loss=0.8291, pruned_loss=6.711, over 7339.00 frames.], tot_loss[loss=0.4418, simple_loss=0.8837, pruned_loss=6.842, over 908266.56 frames.], batch size: 25, lr: 3.00e-03
+2022-05-13 19:23:35,678 INFO [train.py:812] (1/8) Epoch 1, batch 250, loss[loss=0.4187, simple_loss=0.8373, pruned_loss=7.009, over 7323.00 frames.], tot_loss[loss=0.4293, simple_loss=0.8586, pruned_loss=6.837, over 1016829.10 frames.], batch size: 21, lr: 3.00e-03
+2022-05-13 19:24:34,028 INFO [train.py:812] (1/8) Epoch 1, batch 300, loss[loss=0.4255, simple_loss=0.8511, pruned_loss=6.871, over 7314.00 frames.], tot_loss[loss=0.4191, simple_loss=0.8383, pruned_loss=6.832, over 1109880.83 frames.], batch size: 25, lr: 3.00e-03
+2022-05-13 19:25:33,442 INFO [train.py:812] (1/8) Epoch 1, batch 350, loss[loss=0.3988, simple_loss=0.7976, pruned_loss=6.837, over 7245.00 frames.], tot_loss[loss=0.4094, simple_loss=0.8189, pruned_loss=6.818, over 1179367.54 frames.], batch size: 19, lr: 3.00e-03
+2022-05-13 19:26:31,634 INFO [train.py:812] (1/8) Epoch 1, batch 400, loss[loss=0.3705, simple_loss=0.741, pruned_loss=6.858, over 7414.00 frames.], tot_loss[loss=0.4017, simple_loss=0.8035, pruned_loss=6.802, over 1231412.73 frames.], batch size: 21, lr: 3.00e-03
+2022-05-13 19:27:30,030 INFO [train.py:812] (1/8) Epoch 1, batch 450, loss[loss=0.3493, simple_loss=0.6987, pruned_loss=6.837, over 7413.00 frames.], tot_loss[loss=0.3924, simple_loss=0.7849, pruned_loss=6.787, over 1267826.45 frames.], batch size: 21, lr: 2.99e-03
+2022-05-13 19:28:29,380 INFO [train.py:812] (1/8) Epoch 1, batch 500, loss[loss=0.3289, simple_loss=0.6578, pruned_loss=6.815, over 7197.00 frames.], tot_loss[loss=0.3776, simple_loss=0.7552, pruned_loss=6.774, over 1303984.86 frames.], batch size: 22, lr: 2.99e-03
+2022-05-13 19:29:27,221 INFO [train.py:812] (1/8) Epoch 1, batch 550, loss[loss=0.3185, simple_loss=0.637, pruned_loss=6.768, over 7322.00 frames.], tot_loss[loss=0.364, simple_loss=0.7281, pruned_loss=6.771, over 1330353.96 frames.], batch size: 22, lr: 2.99e-03
+2022-05-13 19:30:26,694 INFO [train.py:812] (1/8) Epoch 1, batch 600, loss[loss=0.3087, simple_loss=0.6173, pruned_loss=6.765, over 7117.00 frames.], tot_loss[loss=0.3469, simple_loss=0.6939, pruned_loss=6.762, over 1351033.81 frames.], batch size: 21, lr: 2.99e-03
+2022-05-13 19:31:24,367 INFO [train.py:812] (1/8) Epoch 1, batch 650, loss[loss=0.2331, simple_loss=0.4663, pruned_loss=6.563, over 6997.00 frames.], tot_loss[loss=0.3314, simple_loss=0.6628, pruned_loss=6.756, over 1369355.62 frames.], batch size: 16, lr: 2.99e-03
+2022-05-13 19:32:22,726 INFO [train.py:812] (1/8) Epoch 1, batch 700, loss[loss=0.2551, simple_loss=0.5103, pruned_loss=6.755, over 7193.00 frames.], tot_loss[loss=0.3154, simple_loss=0.6308, pruned_loss=6.742, over 1380415.06 frames.], batch size: 23, lr: 2.99e-03
+2022-05-13 19:33:21,785 INFO [train.py:812] (1/8) Epoch 1, batch 750, loss[loss=0.2229, simple_loss=0.4459, pruned_loss=6.491, over 7274.00 frames.], tot_loss[loss=0.3019, simple_loss=0.6039, pruned_loss=6.736, over 1391700.89 frames.], batch size: 17, lr: 2.98e-03
+2022-05-13 19:34:19,620 INFO [train.py:812] (1/8) Epoch 1, batch 800, loss[loss=0.2667, simple_loss=0.5334, pruned_loss=6.778, over 7126.00 frames.], tot_loss[loss=0.2912, simple_loss=0.5824, pruned_loss=6.736, over 1396997.67 frames.], batch size: 21, lr: 2.98e-03
+2022-05-13 19:35:17,941 INFO [train.py:812] (1/8) Epoch 1, batch 850, loss[loss=0.2444, simple_loss=0.4887, pruned_loss=6.775, over 7217.00 frames.], tot_loss[loss=0.281, simple_loss=0.5619, pruned_loss=6.738, over 1402272.04 frames.], batch size: 21, lr: 2.98e-03
+2022-05-13 19:36:17,406 INFO [train.py:812] (1/8) Epoch 1, batch 900, loss[loss=0.2614, simple_loss=0.5227, pruned_loss=6.885, over 7313.00 frames.], tot_loss[loss=0.2712, simple_loss=0.5423, pruned_loss=6.737, over 1407663.52 frames.], batch size: 21, lr: 2.98e-03
+2022-05-13 19:37:15,471 INFO [train.py:812] (1/8) Epoch 1, batch 950, loss[loss=0.1972, simple_loss=0.3944, pruned_loss=6.56, over 7015.00 frames.], tot_loss[loss=0.2639, simple_loss=0.5278, pruned_loss=6.74, over 1404838.42 frames.], batch size: 16, lr: 2.97e-03
+2022-05-13 19:38:15,213 INFO [train.py:812] (1/8) Epoch 1, batch 1000, loss[loss=0.1879, simple_loss=0.3758, pruned_loss=6.586, over 6983.00 frames.], tot_loss[loss=0.2569, simple_loss=0.5139, pruned_loss=6.739, over 1405651.28 frames.], batch size: 16, lr: 2.97e-03
+2022-05-13 19:39:14,095 INFO [train.py:812] (1/8) Epoch 1, batch 1050, loss[loss=0.2215, simple_loss=0.443, pruned_loss=6.651, over 6990.00 frames.], tot_loss[loss=0.2511, simple_loss=0.5022, pruned_loss=6.744, over 1407666.50 frames.], batch size: 16, lr: 2.97e-03
+2022-05-13 19:40:12,427 INFO [train.py:812] (1/8) Epoch 1, batch 1100, loss[loss=0.2486, simple_loss=0.4971, pruned_loss=6.908, over 7203.00 frames.], tot_loss[loss=0.2457, simple_loss=0.4914, pruned_loss=6.749, over 1411202.95 frames.], batch size: 22, lr: 2.96e-03
+2022-05-13 19:41:10,373 INFO [train.py:812] (1/8) Epoch 1, batch 1150, loss[loss=0.2345, simple_loss=0.4689, pruned_loss=6.832, over 6663.00 frames.], tot_loss[loss=0.241, simple_loss=0.4819, pruned_loss=6.749, over 1411754.79 frames.], batch size: 31, lr: 2.96e-03
+2022-05-13 19:42:08,517 INFO [train.py:812] (1/8) Epoch 1, batch 1200, loss[loss=0.2292, simple_loss=0.4584, pruned_loss=6.859, over 7225.00 frames.], tot_loss[loss=0.2361, simple_loss=0.4722, pruned_loss=6.753, over 1420092.04 frames.], batch size: 26, lr: 2.96e-03
+2022-05-13 19:43:07,163 INFO [train.py:812] (1/8) Epoch 1, batch 1250, loss[loss=0.2199, simple_loss=0.4397, pruned_loss=6.794, over 7382.00 frames.], tot_loss[loss=0.2321, simple_loss=0.4642, pruned_loss=6.753, over 1414141.99 frames.], batch size: 23, lr: 2.95e-03
+2022-05-13 19:44:06,116 INFO [train.py:812] (1/8) Epoch 1, batch 1300, loss[loss=0.2232, simple_loss=0.4465, pruned_loss=6.903, over 7279.00 frames.], tot_loss[loss=0.2275, simple_loss=0.4551, pruned_loss=6.756, over 1422010.97 frames.], batch size: 24, lr: 2.95e-03
+2022-05-13 19:45:04,275 INFO [train.py:812] (1/8) Epoch 1, batch 1350, loss[loss=0.2171, simple_loss=0.4341, pruned_loss=6.704, over 7141.00 frames.], tot_loss[loss=0.2238, simple_loss=0.4476, pruned_loss=6.754, over 1423059.89 frames.], batch size: 20, lr: 2.95e-03
+2022-05-13 19:46:03,471 INFO [train.py:812] (1/8) Epoch 1, batch 1400, loss[loss=0.221, simple_loss=0.442, pruned_loss=6.793, over 7291.00 frames.], tot_loss[loss=0.2216, simple_loss=0.4431, pruned_loss=6.766, over 1419866.42 frames.], batch size: 24, lr: 2.94e-03
+2022-05-13 19:47:02,119 INFO [train.py:812] (1/8) Epoch 1, batch 1450, loss[loss=0.2014, simple_loss=0.4028, pruned_loss=6.723, over 7141.00 frames.], tot_loss[loss=0.2183, simple_loss=0.4367, pruned_loss=6.765, over 1420223.07 frames.], batch size: 17, lr: 2.94e-03
+2022-05-13 19:48:00,926 INFO [train.py:812] (1/8) Epoch 1, batch 1500, loss[loss=0.2126, simple_loss=0.4252, pruned_loss=6.783, over 7302.00 frames.], tot_loss[loss=0.2159, simple_loss=0.4317, pruned_loss=6.765, over 1422738.31 frames.], batch size: 24, lr: 2.94e-03
+2022-05-13 19:48:59,489 INFO [train.py:812] (1/8) Epoch 1, batch 1550, loss[loss=0.2321, simple_loss=0.4643, pruned_loss=6.819, over 7112.00 frames.], tot_loss[loss=0.2129, simple_loss=0.4259, pruned_loss=6.762, over 1423145.74 frames.], batch size: 21, lr: 2.93e-03
+2022-05-13 19:49:59,131 INFO [train.py:812] (1/8) Epoch 1, batch 1600, loss[loss=0.1897, simple_loss=0.3794, pruned_loss=6.655, over 7331.00 frames.], tot_loss[loss=0.2106, simple_loss=0.4211, pruned_loss=6.759, over 1420311.29 frames.], batch size: 20, lr: 2.93e-03
+2022-05-13 19:50:59,005 INFO [train.py:812] (1/8) Epoch 1, batch 1650, loss[loss=0.1916, simple_loss=0.3833, pruned_loss=6.647, over 7160.00 frames.], tot_loss[loss=0.2085, simple_loss=0.417, pruned_loss=6.751, over 1421950.88 frames.], batch size: 18, lr: 2.92e-03
+2022-05-13 19:51:59,058 INFO [train.py:812] (1/8) Epoch 1, batch 1700, loss[loss=0.2008, simple_loss=0.4016, pruned_loss=6.77, over 6552.00 frames.], tot_loss[loss=0.2079, simple_loss=0.4158, pruned_loss=6.759, over 1418109.57 frames.], batch size: 38, lr: 2.92e-03
+2022-05-13 19:52:58,895 INFO [train.py:812] (1/8) Epoch 1, batch 1750, loss[loss=0.2096, simple_loss=0.4192, pruned_loss=6.716, over 6408.00 frames.], tot_loss[loss=0.2051, simple_loss=0.4101, pruned_loss=6.756, over 1418320.02 frames.], batch size: 38, lr: 2.91e-03
+2022-05-13 19:54:00,186 INFO [train.py:812] (1/8) Epoch 1, batch 1800, loss[loss=0.2058, simple_loss=0.4116, pruned_loss=6.906, over 7068.00 frames.], tot_loss[loss=0.2034, simple_loss=0.4068, pruned_loss=6.758, over 1418200.49 frames.], batch size: 28, lr: 2.91e-03
+2022-05-13 19:54:58,674 INFO [train.py:812] (1/8) Epoch 1, batch 1850, loss[loss=0.2054, simple_loss=0.4109, pruned_loss=6.75, over 5040.00 frames.], tot_loss[loss=0.2011, simple_loss=0.4023, pruned_loss=6.758, over 1419214.92 frames.], batch size: 52, lr: 2.91e-03
+2022-05-13 19:55:56,996 INFO [train.py:812] (1/8) Epoch 1, batch 1900, loss[loss=0.2108, simple_loss=0.4216, pruned_loss=6.821, over 7258.00 frames.], tot_loss[loss=0.1999, simple_loss=0.3998, pruned_loss=6.759, over 1419056.63 frames.], batch size: 19, lr: 2.90e-03
+2022-05-13 19:56:55,438 INFO [train.py:812] (1/8) Epoch 1, batch 1950, loss[loss=0.1909, simple_loss=0.3819, pruned_loss=6.663, over 7312.00 frames.], tot_loss[loss=0.1986, simple_loss=0.3972, pruned_loss=6.762, over 1422343.91 frames.], batch size: 21, lr: 2.90e-03
+2022-05-13 19:57:54,264 INFO [train.py:812] (1/8) Epoch 1, batch 2000, loss[loss=0.1634, simple_loss=0.3269, pruned_loss=6.699, over 6767.00 frames.], tot_loss[loss=0.1972, simple_loss=0.3944, pruned_loss=6.762, over 1422592.58 frames.], batch size: 15, lr: 2.89e-03
+2022-05-13 19:58:53,057 INFO [train.py:812] (1/8) Epoch 1, batch 2050, loss[loss=0.1979, simple_loss=0.3959, pruned_loss=6.791, over 7163.00 frames.], tot_loss[loss=0.1957, simple_loss=0.3914, pruned_loss=6.761, over 1421555.22 frames.], batch size: 26, lr: 2.89e-03
+2022-05-13 19:59:51,413 INFO [train.py:812] (1/8) Epoch 1, batch 2100, loss[loss=0.1994, simple_loss=0.3988, pruned_loss=6.714, over 7171.00 frames.], tot_loss[loss=0.1951, simple_loss=0.3902, pruned_loss=6.762, over 1418312.16 frames.], batch size: 18, lr: 2.88e-03
+2022-05-13 20:00:49,529 INFO [train.py:812] (1/8) Epoch 1, batch 2150, loss[loss=0.2016, simple_loss=0.4031, pruned_loss=6.763, over 7326.00 frames.], tot_loss[loss=0.1939, simple_loss=0.3878, pruned_loss=6.758, over 1422340.34 frames.], batch size: 22, lr: 2.88e-03
+2022-05-13 20:01:48,626 INFO [train.py:812] (1/8) Epoch 1, batch 2200, loss[loss=0.2023, simple_loss=0.4047, pruned_loss=6.721, over 7272.00 frames.], tot_loss[loss=0.193, simple_loss=0.386, pruned_loss=6.757, over 1422391.06 frames.], batch size: 25, lr: 2.87e-03
+2022-05-13 20:02:47,471 INFO [train.py:812] (1/8) Epoch 1, batch 2250, loss[loss=0.2089, simple_loss=0.4178, pruned_loss=6.942, over 7221.00 frames.], tot_loss[loss=0.1916, simple_loss=0.3832, pruned_loss=6.75, over 1420308.87 frames.], batch size: 21, lr: 2.86e-03
+2022-05-13 20:03:45,864 INFO [train.py:812] (1/8) Epoch 1, batch 2300, loss[loss=0.1936, simple_loss=0.3873, pruned_loss=6.776, over 7260.00 frames.], tot_loss[loss=0.1912, simple_loss=0.3823, pruned_loss=6.75, over 1415147.04 frames.], batch size: 19, lr: 2.86e-03
+2022-05-13 20:04:43,218 INFO [train.py:812] (1/8) Epoch 1, batch 2350, loss[loss=0.223, simple_loss=0.4461, pruned_loss=6.774, over 5299.00 frames.], tot_loss[loss=0.1909, simple_loss=0.3819, pruned_loss=6.756, over 1414557.55 frames.], batch size: 53, lr: 2.85e-03
+2022-05-13 20:05:42,782 INFO [train.py:812] (1/8) Epoch 1, batch 2400, loss[loss=0.1701, simple_loss=0.3402, pruned_loss=6.738, over 7435.00 frames.], tot_loss[loss=0.1899, simple_loss=0.3797, pruned_loss=6.756, over 1411427.15 frames.], batch size: 20, lr: 2.85e-03
+2022-05-13 20:06:41,411 INFO [train.py:812] (1/8) Epoch 1, batch 2450, loss[loss=0.194, simple_loss=0.388, pruned_loss=6.694, over 5110.00 frames.], tot_loss[loss=0.1885, simple_loss=0.377, pruned_loss=6.755, over 1411459.75 frames.], batch size: 53, lr: 2.84e-03
+2022-05-13 20:07:40,727 INFO [train.py:812] (1/8) Epoch 1, batch 2500, loss[loss=0.1764, simple_loss=0.3528, pruned_loss=6.785, over 7321.00 frames.], tot_loss[loss=0.1875, simple_loss=0.375, pruned_loss=6.75, over 1416750.28 frames.], batch size: 20, lr: 2.84e-03
+2022-05-13 20:08:39,344 INFO [train.py:812] (1/8) Epoch 1, batch 2550, loss[loss=0.1601, simple_loss=0.3201, pruned_loss=6.615, over 7402.00 frames.], tot_loss[loss=0.1876, simple_loss=0.3752, pruned_loss=6.747, over 1417887.16 frames.], batch size: 18, lr: 2.83e-03
+2022-05-13 20:09:37,895 INFO [train.py:812] (1/8) Epoch 1, batch 2600, loss[loss=0.1899, simple_loss=0.3798, pruned_loss=6.9, over 7231.00 frames.], tot_loss[loss=0.187, simple_loss=0.3741, pruned_loss=6.745, over 1421176.27 frames.], batch size: 20, lr: 2.83e-03
+2022-05-13 20:10:35,864 INFO [train.py:812] (1/8) Epoch 1, batch 2650, loss[loss=0.1591, simple_loss=0.3183, pruned_loss=6.707, over 7230.00 frames.], tot_loss[loss=0.1854, simple_loss=0.3708, pruned_loss=6.742, over 1422379.95 frames.], batch size: 20, lr: 2.82e-03
+2022-05-13 20:11:35,625 INFO [train.py:812] (1/8) Epoch 1, batch 2700, loss[loss=0.1761, simple_loss=0.3522, pruned_loss=6.759, over 7149.00 frames.], tot_loss[loss=0.1848, simple_loss=0.3695, pruned_loss=6.741, over 1421548.39 frames.], batch size: 20, lr: 2.81e-03
+2022-05-13 20:12:32,556 INFO [train.py:812] (1/8) Epoch 1, batch 2750, loss[loss=0.1856, simple_loss=0.3712, pruned_loss=6.769, over 7325.00 frames.], tot_loss[loss=0.1845, simple_loss=0.3689, pruned_loss=6.746, over 1422375.15 frames.], batch size: 20, lr: 2.81e-03
+2022-05-13 20:13:32,039 INFO [train.py:812] (1/8) Epoch 1, batch 2800, loss[loss=0.1944, simple_loss=0.3889, pruned_loss=6.823, over 7141.00 frames.], tot_loss[loss=0.1838, simple_loss=0.3675, pruned_loss=6.743, over 1421129.03 frames.], batch size: 20, lr: 2.80e-03
+2022-05-13 20:14:30,978 INFO [train.py:812] (1/8) Epoch 1, batch 2850, loss[loss=0.1838, simple_loss=0.3676, pruned_loss=6.65, over 7374.00 frames.], tot_loss[loss=0.1833, simple_loss=0.3665, pruned_loss=6.741, over 1423945.08 frames.], batch size: 19, lr: 2.80e-03
+2022-05-13 20:15:28,490 INFO [train.py:812] (1/8) Epoch 1, batch 2900, loss[loss=0.1793, simple_loss=0.3586, pruned_loss=6.775, over 7333.00 frames.], tot_loss[loss=0.1837, simple_loss=0.3673, pruned_loss=6.741, over 1420248.04 frames.], batch size: 20, lr: 2.79e-03
+2022-05-13 20:16:27,577 INFO [train.py:812] (1/8) Epoch 1, batch 2950, loss[loss=0.1911, simple_loss=0.3823, pruned_loss=6.755, over 7141.00 frames.], tot_loss[loss=0.1833, simple_loss=0.3665, pruned_loss=6.738, over 1415923.02 frames.], batch size: 26, lr: 2.78e-03
+2022-05-13 20:17:26,745 INFO [train.py:812] (1/8) Epoch 1, batch 3000, loss[loss=0.3354, simple_loss=0.3382, pruned_loss=1.663, over 7285.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3646, pruned_loss=6.714, over 1419537.46 frames.], batch size: 17, lr: 2.78e-03
+2022-05-13 20:17:26,746 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-13 20:17:34,929 INFO [train.py:841] (1/8) Epoch 1, validation: loss=2.094, simple_loss=0.4148, pruned_loss=1.887, over 698248.00 frames.
+2022-05-13 20:18:33,866 INFO [train.py:812] (1/8) Epoch 1, batch 3050, loss[loss=0.2991, simple_loss=0.4027, pruned_loss=0.9773, over 6255.00 frames.], tot_loss[loss=0.2407, simple_loss=0.3737, pruned_loss=5.507, over 1418605.88 frames.], batch size: 38, lr: 2.77e-03
+2022-05-13 20:19:33,921 INFO [train.py:812] (1/8) Epoch 1, batch 3100, loss[loss=0.2517, simple_loss=0.3827, pruned_loss=0.6036, over 7418.00 frames.], tot_loss[loss=0.2424, simple_loss=0.369, pruned_loss=4.428, over 1425235.07 frames.], batch size: 21, lr: 2.77e-03
+2022-05-13 20:20:32,558 INFO [train.py:812] (1/8) Epoch 1, batch 3150, loss[loss=0.2308, simple_loss=0.3858, pruned_loss=0.3784, over 7414.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3665, pruned_loss=3.54, over 1426431.36 frames.], batch size: 21, lr: 2.76e-03
+2022-05-13 20:21:30,562 INFO [train.py:812] (1/8) Epoch 1, batch 3200, loss[loss=0.217, simple_loss=0.3777, pruned_loss=0.2812, over 7291.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3656, pruned_loss=2.831, over 1422358.52 frames.], batch size: 24, lr: 2.75e-03
+2022-05-13 20:22:29,482 INFO [train.py:812] (1/8) Epoch 1, batch 3250, loss[loss=0.1815, simple_loss=0.3254, pruned_loss=0.1873, over 7151.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3636, pruned_loss=2.259, over 1422772.93 frames.], batch size: 20, lr: 2.75e-03
+2022-05-13 20:23:28,329 INFO [train.py:812] (1/8) Epoch 1, batch 3300, loss[loss=0.2143, simple_loss=0.3844, pruned_loss=0.2214, over 7382.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3632, pruned_loss=1.813, over 1419364.89 frames.], batch size: 23, lr: 2.74e-03
+2022-05-13 20:24:25,729 INFO [train.py:812] (1/8) Epoch 1, batch 3350, loss[loss=0.2101, simple_loss=0.3755, pruned_loss=0.2238, over 7271.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3619, pruned_loss=1.454, over 1423886.42 frames.], batch size: 24, lr: 2.73e-03
+2022-05-13 20:25:24,227 INFO [train.py:812] (1/8) Epoch 1, batch 3400, loss[loss=0.1958, simple_loss=0.3529, pruned_loss=0.1941, over 7252.00 frames.], tot_loss[loss=0.2128, simple_loss=0.3618, pruned_loss=1.176, over 1424121.23 frames.], batch size: 19, lr: 2.73e-03
+2022-05-13 20:26:22,129 INFO [train.py:812] (1/8) Epoch 1, batch 3450, loss[loss=0.188, simple_loss=0.3461, pruned_loss=0.1492, over 7315.00 frames.], tot_loss[loss=0.2098, simple_loss=0.3612, pruned_loss=0.9585, over 1424004.52 frames.], batch size: 25, lr: 2.72e-03
+2022-05-13 20:27:20,151 INFO [train.py:812] (1/8) Epoch 1, batch 3500, loss[loss=0.2285, simple_loss=0.4069, pruned_loss=0.2501, over 7147.00 frames.], tot_loss[loss=0.207, simple_loss=0.3605, pruned_loss=0.7874, over 1421977.00 frames.], batch size: 26, lr: 2.72e-03
+2022-05-13 20:28:19,221 INFO [train.py:812] (1/8) Epoch 1, batch 3550, loss[loss=0.1803, simple_loss=0.3317, pruned_loss=0.1442, over 7216.00 frames.], tot_loss[loss=0.2036, simple_loss=0.3579, pruned_loss=0.6509, over 1423324.34 frames.], batch size: 21, lr: 2.71e-03
+2022-05-13 20:29:18,099 INFO [train.py:812] (1/8) Epoch 1, batch 3600, loss[loss=0.1806, simple_loss=0.3294, pruned_loss=0.1592, over 6996.00 frames.], tot_loss[loss=0.2015, simple_loss=0.3569, pruned_loss=0.5454, over 1421841.41 frames.], batch size: 16, lr: 2.70e-03
+2022-05-13 20:30:25,531 INFO [train.py:812] (1/8) Epoch 1, batch 3650, loss[loss=0.2069, simple_loss=0.3777, pruned_loss=0.1807, over 7212.00 frames.], tot_loss[loss=0.199, simple_loss=0.3547, pruned_loss=0.4609, over 1422535.17 frames.], batch size: 21, lr: 2.70e-03
+2022-05-13 20:32:10,012 INFO [train.py:812] (1/8) Epoch 1, batch 3700, loss[loss=0.1999, simple_loss=0.364, pruned_loss=0.1794, over 6672.00 frames.], tot_loss[loss=0.1969, simple_loss=0.353, pruned_loss=0.3938, over 1426675.46 frames.], batch size: 31, lr: 2.69e-03
+2022-05-13 20:33:27,104 INFO [train.py:812] (1/8) Epoch 1, batch 3750, loss[loss=0.1687, simple_loss=0.3105, pruned_loss=0.134, over 7270.00 frames.], tot_loss[loss=0.1962, simple_loss=0.3532, pruned_loss=0.3446, over 1418852.79 frames.], batch size: 18, lr: 2.68e-03
+2022-05-13 20:34:26,660 INFO [train.py:812] (1/8) Epoch 1, batch 3800, loss[loss=0.182, simple_loss=0.3333, pruned_loss=0.1539, over 7127.00 frames.], tot_loss[loss=0.1941, simple_loss=0.351, pruned_loss=0.3021, over 1418881.71 frames.], batch size: 17, lr: 2.68e-03
+2022-05-13 20:35:25,750 INFO [train.py:812] (1/8) Epoch 1, batch 3850, loss[loss=0.1664, simple_loss=0.3062, pruned_loss=0.1333, over 7152.00 frames.], tot_loss[loss=0.1923, simple_loss=0.349, pruned_loss=0.2675, over 1424084.26 frames.], batch size: 17, lr: 2.67e-03
+2022-05-13 20:36:24,064 INFO [train.py:812] (1/8) Epoch 1, batch 3900, loss[loss=0.1687, simple_loss=0.3102, pruned_loss=0.1358, over 7212.00 frames.], tot_loss[loss=0.192, simple_loss=0.3493, pruned_loss=0.2434, over 1421118.06 frames.], batch size: 16, lr: 2.66e-03
+2022-05-13 20:37:21,121 INFO [train.py:812] (1/8) Epoch 1, batch 3950, loss[loss=0.1736, simple_loss=0.322, pruned_loss=0.1258, over 6842.00 frames.], tot_loss[loss=0.1911, simple_loss=0.3484, pruned_loss=0.2231, over 1418608.17 frames.], batch size: 15, lr: 2.66e-03
+2022-05-13 20:38:27,958 INFO [train.py:812] (1/8) Epoch 1, batch 4000, loss[loss=0.1968, simple_loss=0.3623, pruned_loss=0.1567, over 7312.00 frames.], tot_loss[loss=0.1903, simple_loss=0.3478, pruned_loss=0.2063, over 1420523.21 frames.], batch size: 21, lr: 2.65e-03
+2022-05-13 20:39:26,726 INFO [train.py:812] (1/8) Epoch 1, batch 4050, loss[loss=0.1794, simple_loss=0.334, pruned_loss=0.124, over 7055.00 frames.], tot_loss[loss=0.1899, simple_loss=0.3476, pruned_loss=0.1936, over 1420657.61 frames.], batch size: 28, lr: 2.64e-03
+2022-05-13 20:40:25,264 INFO [train.py:812] (1/8) Epoch 1, batch 4100, loss[loss=0.1867, simple_loss=0.3449, pruned_loss=0.142, over 7260.00 frames.], tot_loss[loss=0.1892, simple_loss=0.3468, pruned_loss=0.1839, over 1420869.85 frames.], batch size: 19, lr: 2.64e-03
+2022-05-13 20:41:23,927 INFO [train.py:812] (1/8) Epoch 1, batch 4150, loss[loss=0.1626, simple_loss=0.3022, pruned_loss=0.1151, over 7062.00 frames.], tot_loss[loss=0.1889, simple_loss=0.3468, pruned_loss=0.1753, over 1425215.52 frames.], batch size: 18, lr: 2.63e-03
+2022-05-13 20:42:22,987 INFO [train.py:812] (1/8) Epoch 1, batch 4200, loss[loss=0.1916, simple_loss=0.3528, pruned_loss=0.1523, over 7198.00 frames.], tot_loss[loss=0.1878, simple_loss=0.3454, pruned_loss=0.1668, over 1424683.25 frames.], batch size: 22, lr: 2.63e-03
+2022-05-13 20:43:21,439 INFO [train.py:812] (1/8) Epoch 1, batch 4250, loss[loss=0.1781, simple_loss=0.331, pruned_loss=0.1256, over 7434.00 frames.], tot_loss[loss=0.1884, simple_loss=0.3465, pruned_loss=0.1633, over 1423900.62 frames.], batch size: 20, lr: 2.62e-03
+2022-05-13 20:44:20,462 INFO [train.py:812] (1/8) Epoch 1, batch 4300, loss[loss=0.1921, simple_loss=0.355, pruned_loss=0.1463, over 7105.00 frames.], tot_loss[loss=0.1882, simple_loss=0.3465, pruned_loss=0.159, over 1423231.27 frames.], batch size: 28, lr: 2.61e-03
+2022-05-13 20:45:18,959 INFO [train.py:812] (1/8) Epoch 1, batch 4350, loss[loss=0.1632, simple_loss=0.307, pruned_loss=0.0967, over 7442.00 frames.], tot_loss[loss=0.1873, simple_loss=0.3451, pruned_loss=0.1542, over 1426982.85 frames.], batch size: 20, lr: 2.61e-03
+2022-05-13 20:46:18,353 INFO [train.py:812] (1/8) Epoch 1, batch 4400, loss[loss=0.1719, simple_loss=0.3201, pruned_loss=0.1182, over 7269.00 frames.], tot_loss[loss=0.1874, simple_loss=0.3457, pruned_loss=0.1517, over 1424974.29 frames.], batch size: 18, lr: 2.60e-03
+2022-05-13 20:47:17,286 INFO [train.py:812] (1/8) Epoch 1, batch 4450, loss[loss=0.1894, simple_loss=0.3489, pruned_loss=0.1491, over 7436.00 frames.], tot_loss[loss=0.1881, simple_loss=0.3469, pruned_loss=0.1506, over 1424011.21 frames.], batch size: 20, lr: 2.59e-03
+2022-05-13 20:48:16,734 INFO [train.py:812] (1/8) Epoch 1, batch 4500, loss[loss=0.2089, simple_loss=0.383, pruned_loss=0.1737, over 6438.00 frames.], tot_loss[loss=0.188, simple_loss=0.347, pruned_loss=0.1488, over 1414234.09 frames.], batch size: 38, lr: 2.59e-03
+2022-05-13 20:49:13,802 INFO [train.py:812] (1/8) Epoch 1, batch 4550, loss[loss=0.1964, simple_loss=0.3594, pruned_loss=0.167, over 4871.00 frames.], tot_loss[loss=0.1886, simple_loss=0.3482, pruned_loss=0.148, over 1395398.29 frames.], batch size: 52, lr: 2.58e-03
+2022-05-13 20:50:25,941 INFO [train.py:812] (1/8) Epoch 2, batch 0, loss[loss=0.1948, simple_loss=0.3586, pruned_loss=0.1545, over 7194.00 frames.], tot_loss[loss=0.1948, simple_loss=0.3586, pruned_loss=0.1545, over 7194.00 frames.], batch size: 26, lr: 2.56e-03
+2022-05-13 20:51:25,850 INFO [train.py:812] (1/8) Epoch 2, batch 50, loss[loss=0.1867, simple_loss=0.3462, pruned_loss=0.1361, over 7239.00 frames.], tot_loss[loss=0.1828, simple_loss=0.3382, pruned_loss=0.1367, over 312189.11 frames.], batch size: 20, lr: 2.55e-03
+2022-05-13 20:52:24,853 INFO [train.py:812] (1/8) Epoch 2, batch 100, loss[loss=0.1613, simple_loss=0.3003, pruned_loss=0.1119, over 7435.00 frames.], tot_loss[loss=0.1814, simple_loss=0.3359, pruned_loss=0.1343, over 560753.49 frames.], batch size: 20, lr: 2.54e-03
+2022-05-13 20:53:23,902 INFO [train.py:812] (1/8) Epoch 2, batch 150, loss[loss=0.1796, simple_loss=0.3326, pruned_loss=0.1328, over 7324.00 frames.], tot_loss[loss=0.1818, simple_loss=0.3368, pruned_loss=0.1337, over 751182.36 frames.], batch size: 20, lr: 2.54e-03
+2022-05-13 20:54:21,306 INFO [train.py:812] (1/8) Epoch 2, batch 200, loss[loss=0.1753, simple_loss=0.3261, pruned_loss=0.1227, over 7152.00 frames.], tot_loss[loss=0.1816, simple_loss=0.3367, pruned_loss=0.1328, over 901053.23 frames.], batch size: 19, lr: 2.53e-03
+2022-05-13 20:55:19,834 INFO [train.py:812] (1/8) Epoch 2, batch 250, loss[loss=0.1956, simple_loss=0.3626, pruned_loss=0.1428, over 7362.00 frames.], tot_loss[loss=0.1824, simple_loss=0.3381, pruned_loss=0.1335, over 1015156.54 frames.], batch size: 23, lr: 2.53e-03
+2022-05-13 20:56:18,127 INFO [train.py:812] (1/8) Epoch 2, batch 300, loss[loss=0.1823, simple_loss=0.337, pruned_loss=0.1382, over 7269.00 frames.], tot_loss[loss=0.1825, simple_loss=0.3384, pruned_loss=0.1332, over 1104838.92 frames.], batch size: 19, lr: 2.52e-03
+2022-05-13 20:57:16,221 INFO [train.py:812] (1/8) Epoch 2, batch 350, loss[loss=0.185, simple_loss=0.3436, pruned_loss=0.1318, over 7225.00 frames.], tot_loss[loss=0.183, simple_loss=0.3392, pruned_loss=0.1339, over 1173419.57 frames.], batch size: 21, lr: 2.51e-03
+2022-05-13 20:58:14,748 INFO [train.py:812] (1/8) Epoch 2, batch 400, loss[loss=0.211, simple_loss=0.3849, pruned_loss=0.1851, over 7148.00 frames.], tot_loss[loss=0.1824, simple_loss=0.3383, pruned_loss=0.1322, over 1229947.49 frames.], batch size: 20, lr: 2.51e-03
+2022-05-13 20:59:13,909 INFO [train.py:812] (1/8) Epoch 2, batch 450, loss[loss=0.1844, simple_loss=0.3406, pruned_loss=0.1408, over 7161.00 frames.], tot_loss[loss=0.182, simple_loss=0.3377, pruned_loss=0.1312, over 1274997.18 frames.], batch size: 19, lr: 2.50e-03
+2022-05-13 21:00:12,342 INFO [train.py:812] (1/8) Epoch 2, batch 500, loss[loss=0.1728, simple_loss=0.3216, pruned_loss=0.1204, over 7160.00 frames.], tot_loss[loss=0.1822, simple_loss=0.3382, pruned_loss=0.1309, over 1307022.63 frames.], batch size: 18, lr: 2.49e-03
+2022-05-13 21:01:12,107 INFO [train.py:812] (1/8) Epoch 2, batch 550, loss[loss=0.1614, simple_loss=0.3022, pruned_loss=0.1028, over 7360.00 frames.], tot_loss[loss=0.181, simple_loss=0.3361, pruned_loss=0.1293, over 1332188.30 frames.], batch size: 19, lr: 2.49e-03
+2022-05-13 21:02:09,995 INFO [train.py:812] (1/8) Epoch 2, batch 600, loss[loss=0.1685, simple_loss=0.3165, pruned_loss=0.102, over 7378.00 frames.], tot_loss[loss=0.181, simple_loss=0.3362, pruned_loss=0.1283, over 1353823.43 frames.], batch size: 23, lr: 2.48e-03
+2022-05-13 21:03:08,997 INFO [train.py:812] (1/8) Epoch 2, batch 650, loss[loss=0.152, simple_loss=0.2832, pruned_loss=0.1044, over 7270.00 frames.], tot_loss[loss=0.181, simple_loss=0.3362, pruned_loss=0.1292, over 1367650.13 frames.], batch size: 18, lr: 2.48e-03
+2022-05-13 21:04:08,340 INFO [train.py:812] (1/8) Epoch 2, batch 700, loss[loss=0.2156, simple_loss=0.3917, pruned_loss=0.198, over 4637.00 frames.], tot_loss[loss=0.1808, simple_loss=0.3358, pruned_loss=0.1286, over 1378542.29 frames.], batch size: 52, lr: 2.47e-03
+2022-05-13 21:05:07,228 INFO [train.py:812] (1/8) Epoch 2, batch 750, loss[loss=0.1634, simple_loss=0.3045, pruned_loss=0.1118, over 7257.00 frames.], tot_loss[loss=0.1794, simple_loss=0.3335, pruned_loss=0.1262, over 1389846.29 frames.], batch size: 19, lr: 2.46e-03
+2022-05-13 21:06:06,457 INFO [train.py:812] (1/8) Epoch 2, batch 800, loss[loss=0.1813, simple_loss=0.3378, pruned_loss=0.1243, over 7073.00 frames.], tot_loss[loss=0.1787, simple_loss=0.3324, pruned_loss=0.1249, over 1400212.58 frames.], batch size: 18, lr: 2.46e-03
+2022-05-13 21:07:06,090 INFO [train.py:812] (1/8) Epoch 2, batch 850, loss[loss=0.1755, simple_loss=0.3287, pruned_loss=0.1116, over 7342.00 frames.], tot_loss[loss=0.1783, simple_loss=0.3318, pruned_loss=0.1239, over 1409421.42 frames.], batch size: 20, lr: 2.45e-03
+2022-05-13 21:08:05,122 INFO [train.py:812] (1/8) Epoch 2, batch 900, loss[loss=0.1727, simple_loss=0.3233, pruned_loss=0.1109, over 7425.00 frames.], tot_loss[loss=0.178, simple_loss=0.3313, pruned_loss=0.1235, over 1414551.68 frames.], batch size: 20, lr: 2.45e-03
+2022-05-13 21:09:04,127 INFO [train.py:812] (1/8) Epoch 2, batch 950, loss[loss=0.1764, simple_loss=0.3293, pruned_loss=0.1173, over 7249.00 frames.], tot_loss[loss=0.1784, simple_loss=0.332, pruned_loss=0.124, over 1416695.03 frames.], batch size: 19, lr: 2.44e-03
+2022-05-13 21:10:02,104 INFO [train.py:812] (1/8) Epoch 2, batch 1000, loss[loss=0.1813, simple_loss=0.3376, pruned_loss=0.1253, over 6918.00 frames.], tot_loss[loss=0.1778, simple_loss=0.331, pruned_loss=0.1229, over 1419045.51 frames.], batch size: 32, lr: 2.43e-03
+2022-05-13 21:11:00,256 INFO [train.py:812] (1/8) Epoch 2, batch 1050, loss[loss=0.1869, simple_loss=0.3479, pruned_loss=0.1292, over 7424.00 frames.], tot_loss[loss=0.178, simple_loss=0.3313, pruned_loss=0.1234, over 1420971.60 frames.], batch size: 20, lr: 2.43e-03
+2022-05-13 21:11:59,250 INFO [train.py:812] (1/8) Epoch 2, batch 1100, loss[loss=0.1711, simple_loss=0.3167, pruned_loss=0.128, over 7166.00 frames.], tot_loss[loss=0.1784, simple_loss=0.3322, pruned_loss=0.1235, over 1421426.73 frames.], batch size: 18, lr: 2.42e-03
+2022-05-13 21:12:57,570 INFO [train.py:812] (1/8) Epoch 2, batch 1150, loss[loss=0.1725, simple_loss=0.3231, pruned_loss=0.1095, over 7228.00 frames.], tot_loss[loss=0.1774, simple_loss=0.3304, pruned_loss=0.1224, over 1424640.73 frames.], batch size: 20, lr: 2.41e-03
+2022-05-13 21:13:56,182 INFO [train.py:812] (1/8) Epoch 2, batch 1200, loss[loss=0.1871, simple_loss=0.3493, pruned_loss=0.1245, over 7041.00 frames.], tot_loss[loss=0.1767, simple_loss=0.3291, pruned_loss=0.1212, over 1423912.86 frames.], batch size: 28, lr: 2.41e-03
+2022-05-13 21:14:54,777 INFO [train.py:812] (1/8) Epoch 2, batch 1250, loss[loss=0.155, simple_loss=0.2926, pruned_loss=0.08658, over 7257.00 frames.], tot_loss[loss=0.1775, simple_loss=0.3307, pruned_loss=0.1218, over 1423378.18 frames.], batch size: 18, lr: 2.40e-03
+2022-05-13 21:15:53,349 INFO [train.py:812] (1/8) Epoch 2, batch 1300, loss[loss=0.1885, simple_loss=0.3509, pruned_loss=0.1303, over 7223.00 frames.], tot_loss[loss=0.1775, simple_loss=0.3306, pruned_loss=0.122, over 1417200.91 frames.], batch size: 21, lr: 2.40e-03
+2022-05-13 21:16:52,358 INFO [train.py:812] (1/8) Epoch 2, batch 1350, loss[loss=0.1509, simple_loss=0.2777, pruned_loss=0.1201, over 7272.00 frames.], tot_loss[loss=0.1772, simple_loss=0.3301, pruned_loss=0.1216, over 1419782.89 frames.], batch size: 17, lr: 2.39e-03
+2022-05-13 21:17:49,941 INFO [train.py:812] (1/8) Epoch 2, batch 1400, loss[loss=0.1813, simple_loss=0.3413, pruned_loss=0.1068, over 7232.00 frames.], tot_loss[loss=0.1776, simple_loss=0.3308, pruned_loss=0.1217, over 1418548.55 frames.], batch size: 21, lr: 2.39e-03
+2022-05-13 21:18:49,260 INFO [train.py:812] (1/8) Epoch 2, batch 1450, loss[loss=0.3231, simple_loss=0.3641, pruned_loss=0.141, over 7212.00 frames.], tot_loss[loss=0.2003, simple_loss=0.3323, pruned_loss=0.1242, over 1422157.14 frames.], batch size: 26, lr: 2.38e-03
+2022-05-13 21:19:47,677 INFO [train.py:812] (1/8) Epoch 2, batch 1500, loss[loss=0.3233, simple_loss=0.3704, pruned_loss=0.1381, over 6366.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3344, pruned_loss=0.1259, over 1422160.80 frames.], batch size: 38, lr: 2.37e-03
+2022-05-13 21:20:45,894 INFO [train.py:812] (1/8) Epoch 2, batch 1550, loss[loss=0.2543, simple_loss=0.3122, pruned_loss=0.09817, over 7436.00 frames.], tot_loss[loss=0.2391, simple_loss=0.336, pruned_loss=0.1255, over 1425018.71 frames.], batch size: 20, lr: 2.37e-03
+2022-05-13 21:21:43,113 INFO [train.py:812] (1/8) Epoch 2, batch 1600, loss[loss=0.2699, simple_loss=0.3114, pruned_loss=0.1142, over 7164.00 frames.], tot_loss[loss=0.2475, simple_loss=0.334, pruned_loss=0.1228, over 1424487.43 frames.], batch size: 18, lr: 2.36e-03
+2022-05-13 21:22:41,919 INFO [train.py:812] (1/8) Epoch 2, batch 1650, loss[loss=0.243, simple_loss=0.2979, pruned_loss=0.094, over 7449.00 frames.], tot_loss[loss=0.2546, simple_loss=0.333, pruned_loss=0.1211, over 1425196.71 frames.], batch size: 20, lr: 2.36e-03
+2022-05-13 21:23:40,001 INFO [train.py:812] (1/8) Epoch 2, batch 1700, loss[loss=0.3049, simple_loss=0.3489, pruned_loss=0.1304, over 7420.00 frames.], tot_loss[loss=0.2603, simple_loss=0.3323, pruned_loss=0.1199, over 1423756.14 frames.], batch size: 21, lr: 2.35e-03
+2022-05-13 21:24:38,979 INFO [train.py:812] (1/8) Epoch 2, batch 1750, loss[loss=0.2379, simple_loss=0.2832, pruned_loss=0.09629, over 7266.00 frames.], tot_loss[loss=0.2659, simple_loss=0.3334, pruned_loss=0.1192, over 1423540.88 frames.], batch size: 18, lr: 2.34e-03
+2022-05-13 21:25:38,304 INFO [train.py:812] (1/8) Epoch 2, batch 1800, loss[loss=0.286, simple_loss=0.3297, pruned_loss=0.1211, over 7352.00 frames.], tot_loss[loss=0.2703, simple_loss=0.334, pruned_loss=0.1189, over 1424767.34 frames.], batch size: 19, lr: 2.34e-03
+2022-05-13 21:26:37,482 INFO [train.py:812] (1/8) Epoch 2, batch 1850, loss[loss=0.2427, simple_loss=0.3102, pruned_loss=0.08761, over 7325.00 frames.], tot_loss[loss=0.2716, simple_loss=0.3329, pruned_loss=0.1173, over 1424958.42 frames.], batch size: 20, lr: 2.33e-03
+2022-05-13 21:27:35,691 INFO [train.py:812] (1/8) Epoch 2, batch 1900, loss[loss=0.2375, simple_loss=0.293, pruned_loss=0.09103, over 7000.00 frames.], tot_loss[loss=0.2721, simple_loss=0.332, pruned_loss=0.1154, over 1428668.47 frames.], batch size: 16, lr: 2.33e-03
+2022-05-13 21:28:33,670 INFO [train.py:812] (1/8) Epoch 2, batch 1950, loss[loss=0.2489, simple_loss=0.2957, pruned_loss=0.101, over 7288.00 frames.], tot_loss[loss=0.2737, simple_loss=0.3323, pruned_loss=0.1148, over 1429459.91 frames.], batch size: 18, lr: 2.32e-03
+2022-05-13 21:29:31,791 INFO [train.py:812] (1/8) Epoch 2, batch 2000, loss[loss=0.2757, simple_loss=0.345, pruned_loss=0.1032, over 7120.00 frames.], tot_loss[loss=0.2765, simple_loss=0.3336, pruned_loss=0.1154, over 1422980.82 frames.], batch size: 21, lr: 2.32e-03
+2022-05-13 21:30:31,554 INFO [train.py:812] (1/8) Epoch 2, batch 2050, loss[loss=0.3018, simple_loss=0.3503, pruned_loss=0.1267, over 7156.00 frames.], tot_loss[loss=0.277, simple_loss=0.3334, pruned_loss=0.1147, over 1423483.71 frames.], batch size: 28, lr: 2.31e-03
+2022-05-13 21:31:31,045 INFO [train.py:812] (1/8) Epoch 2, batch 2100, loss[loss=0.2724, simple_loss=0.3243, pruned_loss=0.1102, over 7409.00 frames.], tot_loss[loss=0.277, simple_loss=0.3327, pruned_loss=0.1141, over 1425363.43 frames.], batch size: 18, lr: 2.31e-03
+2022-05-13 21:32:30,575 INFO [train.py:812] (1/8) Epoch 2, batch 2150, loss[loss=0.301, simple_loss=0.3617, pruned_loss=0.1202, over 7412.00 frames.], tot_loss[loss=0.2762, simple_loss=0.3318, pruned_loss=0.113, over 1424633.33 frames.], batch size: 21, lr: 2.30e-03
+2022-05-13 21:33:29,452 INFO [train.py:812] (1/8) Epoch 2, batch 2200, loss[loss=0.3134, simple_loss=0.3678, pruned_loss=0.1295, over 7121.00 frames.], tot_loss[loss=0.2751, simple_loss=0.3301, pruned_loss=0.1121, over 1423113.91 frames.], batch size: 21, lr: 2.29e-03
+2022-05-13 21:34:29,305 INFO [train.py:812] (1/8) Epoch 2, batch 2250, loss[loss=0.2554, simple_loss=0.3278, pruned_loss=0.09148, over 7221.00 frames.], tot_loss[loss=0.2729, simple_loss=0.3283, pruned_loss=0.1104, over 1423742.06 frames.], batch size: 21, lr: 2.29e-03
+2022-05-13 21:35:27,783 INFO [train.py:812] (1/8) Epoch 2, batch 2300, loss[loss=0.3176, simple_loss=0.3732, pruned_loss=0.131, over 7212.00 frames.], tot_loss[loss=0.2743, simple_loss=0.3295, pruned_loss=0.1108, over 1425356.29 frames.], batch size: 22, lr: 2.28e-03
+2022-05-13 21:36:26,827 INFO [train.py:812] (1/8) Epoch 2, batch 2350, loss[loss=0.2815, simple_loss=0.3335, pruned_loss=0.1148, over 7232.00 frames.], tot_loss[loss=0.2769, simple_loss=0.3311, pruned_loss=0.1123, over 1423642.48 frames.], batch size: 20, lr: 2.28e-03
+2022-05-13 21:37:24,981 INFO [train.py:812] (1/8) Epoch 2, batch 2400, loss[loss=0.2603, simple_loss=0.3216, pruned_loss=0.09948, over 7326.00 frames.], tot_loss[loss=0.2759, simple_loss=0.3308, pruned_loss=0.1113, over 1423570.15 frames.], batch size: 21, lr: 2.27e-03
+2022-05-13 21:38:23,791 INFO [train.py:812] (1/8) Epoch 2, batch 2450, loss[loss=0.3115, simple_loss=0.3648, pruned_loss=0.1291, over 7319.00 frames.], tot_loss[loss=0.2766, simple_loss=0.3316, pruned_loss=0.1114, over 1426824.84 frames.], batch size: 21, lr: 2.27e-03
+2022-05-13 21:39:23,281 INFO [train.py:812] (1/8) Epoch 2, batch 2500, loss[loss=0.3017, simple_loss=0.3441, pruned_loss=0.1297, over 7176.00 frames.], tot_loss[loss=0.2764, simple_loss=0.3314, pruned_loss=0.1112, over 1426984.82 frames.], batch size: 26, lr: 2.26e-03
+2022-05-13 21:40:21,933 INFO [train.py:812] (1/8) Epoch 2, batch 2550, loss[loss=0.2298, simple_loss=0.2973, pruned_loss=0.0812, over 6999.00 frames.], tot_loss[loss=0.2752, simple_loss=0.3307, pruned_loss=0.1102, over 1427043.76 frames.], batch size: 16, lr: 2.26e-03
+2022-05-13 21:41:21,073 INFO [train.py:812] (1/8) Epoch 2, batch 2600, loss[loss=0.3014, simple_loss=0.3588, pruned_loss=0.122, over 7189.00 frames.], tot_loss[loss=0.2743, simple_loss=0.33, pruned_loss=0.1095, over 1428744.38 frames.], batch size: 26, lr: 2.25e-03
+2022-05-13 21:42:20,628 INFO [train.py:812] (1/8) Epoch 2, batch 2650, loss[loss=0.3419, simple_loss=0.3747, pruned_loss=0.1546, over 6457.00 frames.], tot_loss[loss=0.2744, simple_loss=0.3301, pruned_loss=0.1096, over 1427430.63 frames.], batch size: 38, lr: 2.25e-03
+2022-05-13 21:43:18,317 INFO [train.py:812] (1/8) Epoch 2, batch 2700, loss[loss=0.3583, simple_loss=0.3862, pruned_loss=0.1652, over 6833.00 frames.], tot_loss[loss=0.2737, simple_loss=0.3296, pruned_loss=0.1091, over 1427067.13 frames.], batch size: 31, lr: 2.24e-03
+2022-05-13 21:44:17,958 INFO [train.py:812] (1/8) Epoch 2, batch 2750, loss[loss=0.2721, simple_loss=0.3328, pruned_loss=0.1057, over 7297.00 frames.], tot_loss[loss=0.2748, simple_loss=0.3303, pruned_loss=0.1098, over 1424531.61 frames.], batch size: 24, lr: 2.24e-03
+2022-05-13 21:45:15,691 INFO [train.py:812] (1/8) Epoch 2, batch 2800, loss[loss=0.2621, simple_loss=0.326, pruned_loss=0.09906, over 7201.00 frames.], tot_loss[loss=0.272, simple_loss=0.329, pruned_loss=0.1076, over 1426695.71 frames.], batch size: 23, lr: 2.23e-03
+2022-05-13 21:46:14,848 INFO [train.py:812] (1/8) Epoch 2, batch 2850, loss[loss=0.2687, simple_loss=0.3358, pruned_loss=0.1008, over 7286.00 frames.], tot_loss[loss=0.2708, simple_loss=0.3283, pruned_loss=0.1067, over 1426690.13 frames.], batch size: 24, lr: 2.23e-03
+2022-05-13 21:47:13,479 INFO [train.py:812] (1/8) Epoch 2, batch 2900, loss[loss=0.2225, simple_loss=0.3018, pruned_loss=0.07162, over 7235.00 frames.], tot_loss[loss=0.2731, simple_loss=0.3302, pruned_loss=0.1081, over 1421381.99 frames.], batch size: 20, lr: 2.22e-03
+2022-05-13 21:48:11,752 INFO [train.py:812] (1/8) Epoch 2, batch 2950, loss[loss=0.2368, simple_loss=0.3176, pruned_loss=0.07803, over 7232.00 frames.], tot_loss[loss=0.2701, simple_loss=0.3279, pruned_loss=0.1062, over 1423142.67 frames.], batch size: 20, lr: 2.22e-03
+2022-05-13 21:49:10,836 INFO [train.py:812] (1/8) Epoch 2, batch 3000, loss[loss=0.28, simple_loss=0.3239, pruned_loss=0.118, over 7271.00 frames.], tot_loss[loss=0.268, simple_loss=0.3268, pruned_loss=0.1047, over 1425918.65 frames.], batch size: 17, lr: 2.21e-03
+2022-05-13 21:49:10,838 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-13 21:49:18,580 INFO [train.py:841] (1/8) Epoch 2, validation: loss=0.2016, simple_loss=0.2977, pruned_loss=0.0527, over 698248.00 frames.
+2022-05-13 21:50:17,416 INFO [train.py:812] (1/8) Epoch 2, batch 3050, loss[loss=0.2251, simple_loss=0.3044, pruned_loss=0.07291, over 7278.00 frames.], tot_loss[loss=0.2674, simple_loss=0.3264, pruned_loss=0.1042, over 1421866.65 frames.], batch size: 18, lr: 2.20e-03
+2022-05-13 21:51:15,121 INFO [train.py:812] (1/8) Epoch 2, batch 3100, loss[loss=0.3265, simple_loss=0.3675, pruned_loss=0.1428, over 5184.00 frames.], tot_loss[loss=0.2674, simple_loss=0.3264, pruned_loss=0.1042, over 1421201.21 frames.], batch size: 52, lr: 2.20e-03
+2022-05-13 21:52:13,944 INFO [train.py:812] (1/8) Epoch 2, batch 3150, loss[loss=0.238, simple_loss=0.2971, pruned_loss=0.08949, over 7210.00 frames.], tot_loss[loss=0.2675, simple_loss=0.3266, pruned_loss=0.1042, over 1424203.96 frames.], batch size: 16, lr: 2.19e-03
+2022-05-13 21:53:13,039 INFO [train.py:812] (1/8) Epoch 2, batch 3200, loss[loss=0.2658, simple_loss=0.3231, pruned_loss=0.1043, over 4747.00 frames.], tot_loss[loss=0.2689, simple_loss=0.3277, pruned_loss=0.1051, over 1412855.69 frames.], batch size: 52, lr: 2.19e-03
+2022-05-13 21:54:12,611 INFO [train.py:812] (1/8) Epoch 2, batch 3250, loss[loss=0.2851, simple_loss=0.35, pruned_loss=0.1101, over 7201.00 frames.], tot_loss[loss=0.2705, simple_loss=0.3292, pruned_loss=0.1059, over 1415881.09 frames.], batch size: 23, lr: 2.18e-03
+2022-05-13 21:55:12,231 INFO [train.py:812] (1/8) Epoch 2, batch 3300, loss[loss=0.2461, simple_loss=0.3199, pruned_loss=0.08615, over 7207.00 frames.], tot_loss[loss=0.2707, simple_loss=0.3292, pruned_loss=0.1061, over 1420061.66 frames.], batch size: 22, lr: 2.18e-03
+2022-05-13 21:56:11,985 INFO [train.py:812] (1/8) Epoch 2, batch 3350, loss[loss=0.2825, simple_loss=0.3396, pruned_loss=0.1127, over 7184.00 frames.], tot_loss[loss=0.2702, simple_loss=0.3297, pruned_loss=0.1054, over 1422621.76 frames.], batch size: 26, lr: 2.18e-03
+2022-05-13 21:57:11,181 INFO [train.py:812] (1/8) Epoch 2, batch 3400, loss[loss=0.2352, simple_loss=0.282, pruned_loss=0.09423, over 7120.00 frames.], tot_loss[loss=0.2683, simple_loss=0.3281, pruned_loss=0.1043, over 1424482.32 frames.], batch size: 17, lr: 2.17e-03
+2022-05-13 21:58:14,490 INFO [train.py:812] (1/8) Epoch 2, batch 3450, loss[loss=0.3055, simple_loss=0.3756, pruned_loss=0.1177, over 7276.00 frames.], tot_loss[loss=0.2684, simple_loss=0.3287, pruned_loss=0.1041, over 1427406.20 frames.], batch size: 24, lr: 2.17e-03
+2022-05-13 21:59:13,382 INFO [train.py:812] (1/8) Epoch 2, batch 3500, loss[loss=0.2918, simple_loss=0.3561, pruned_loss=0.1137, over 6148.00 frames.], tot_loss[loss=0.2695, simple_loss=0.3295, pruned_loss=0.1047, over 1424062.63 frames.], batch size: 37, lr: 2.16e-03
+2022-05-13 22:00:12,693 INFO [train.py:812] (1/8) Epoch 2, batch 3550, loss[loss=0.2874, simple_loss=0.3471, pruned_loss=0.1138, over 7296.00 frames.], tot_loss[loss=0.2688, simple_loss=0.3289, pruned_loss=0.1043, over 1423537.33 frames.], batch size: 25, lr: 2.16e-03
+2022-05-13 22:01:11,593 INFO [train.py:812] (1/8) Epoch 2, batch 3600, loss[loss=0.2707, simple_loss=0.3377, pruned_loss=0.1019, over 7236.00 frames.], tot_loss[loss=0.2681, simple_loss=0.3288, pruned_loss=0.1037, over 1425080.37 frames.], batch size: 20, lr: 2.15e-03
+2022-05-13 22:02:11,439 INFO [train.py:812] (1/8) Epoch 2, batch 3650, loss[loss=0.2394, simple_loss=0.2931, pruned_loss=0.09287, over 7230.00 frames.], tot_loss[loss=0.2675, simple_loss=0.3281, pruned_loss=0.1035, over 1427482.67 frames.], batch size: 16, lr: 2.15e-03
+2022-05-13 22:03:10,450 INFO [train.py:812] (1/8) Epoch 2, batch 3700, loss[loss=0.2492, simple_loss=0.3126, pruned_loss=0.09292, over 7165.00 frames.], tot_loss[loss=0.2681, simple_loss=0.3288, pruned_loss=0.1037, over 1429684.73 frames.], batch size: 19, lr: 2.14e-03
+2022-05-13 22:04:09,805 INFO [train.py:812] (1/8) Epoch 2, batch 3750, loss[loss=0.2821, simple_loss=0.3416, pruned_loss=0.1113, over 7267.00 frames.], tot_loss[loss=0.267, simple_loss=0.3281, pruned_loss=0.103, over 1430543.04 frames.], batch size: 24, lr: 2.14e-03
+2022-05-13 22:05:09,269 INFO [train.py:812] (1/8) Epoch 2, batch 3800, loss[loss=0.1859, simple_loss=0.2538, pruned_loss=0.05903, over 7258.00 frames.], tot_loss[loss=0.2662, simple_loss=0.3271, pruned_loss=0.1026, over 1431535.01 frames.], batch size: 16, lr: 2.13e-03
+2022-05-13 22:06:07,962 INFO [train.py:812] (1/8) Epoch 2, batch 3850, loss[loss=0.239, simple_loss=0.3222, pruned_loss=0.07793, over 7208.00 frames.], tot_loss[loss=0.2648, simple_loss=0.3266, pruned_loss=0.1015, over 1433372.68 frames.], batch size: 26, lr: 2.13e-03
+2022-05-13 22:07:06,190 INFO [train.py:812] (1/8) Epoch 2, batch 3900, loss[loss=0.2589, simple_loss=0.3287, pruned_loss=0.09456, over 7302.00 frames.], tot_loss[loss=0.2638, simple_loss=0.3262, pruned_loss=0.1008, over 1431446.67 frames.], batch size: 24, lr: 2.12e-03
+2022-05-13 22:08:05,668 INFO [train.py:812] (1/8) Epoch 2, batch 3950, loss[loss=0.2751, simple_loss=0.3424, pruned_loss=0.1038, over 7123.00 frames.], tot_loss[loss=0.2628, simple_loss=0.3251, pruned_loss=0.1003, over 1429418.37 frames.], batch size: 21, lr: 2.12e-03
+2022-05-13 22:09:04,765 INFO [train.py:812] (1/8) Epoch 2, batch 4000, loss[loss=0.2764, simple_loss=0.3345, pruned_loss=0.1091, over 7208.00 frames.], tot_loss[loss=0.2624, simple_loss=0.3246, pruned_loss=0.1001, over 1429182.68 frames.], batch size: 22, lr: 2.11e-03
+2022-05-13 22:10:02,680 INFO [train.py:812] (1/8) Epoch 2, batch 4050, loss[loss=0.2918, simple_loss=0.3409, pruned_loss=0.1213, over 6950.00 frames.], tot_loss[loss=0.2631, simple_loss=0.3254, pruned_loss=0.1005, over 1427045.69 frames.], batch size: 31, lr: 2.11e-03
+2022-05-13 22:11:01,215 INFO [train.py:812] (1/8) Epoch 2, batch 4100, loss[loss=0.2705, simple_loss=0.327, pruned_loss=0.107, over 7208.00 frames.], tot_loss[loss=0.2632, simple_loss=0.3254, pruned_loss=0.1005, over 1421079.17 frames.], batch size: 21, lr: 2.10e-03
+2022-05-13 22:11:59,874 INFO [train.py:812] (1/8) Epoch 2, batch 4150, loss[loss=0.2711, simple_loss=0.3324, pruned_loss=0.1049, over 6778.00 frames.], tot_loss[loss=0.2612, simple_loss=0.3242, pruned_loss=0.0991, over 1420443.11 frames.], batch size: 31, lr: 2.10e-03
+2022-05-13 22:12:58,523 INFO [train.py:812] (1/8) Epoch 2, batch 4200, loss[loss=0.2434, simple_loss=0.3042, pruned_loss=0.09123, over 7266.00 frames.], tot_loss[loss=0.2613, simple_loss=0.3239, pruned_loss=0.0994, over 1420250.18 frames.], batch size: 18, lr: 2.10e-03
+2022-05-13 22:13:58,086 INFO [train.py:812] (1/8) Epoch 2, batch 4250, loss[loss=0.2885, simple_loss=0.3317, pruned_loss=0.1227, over 7268.00 frames.], tot_loss[loss=0.2625, simple_loss=0.3243, pruned_loss=0.1004, over 1415350.31 frames.], batch size: 18, lr: 2.09e-03
+2022-05-13 22:14:56,715 INFO [train.py:812] (1/8) Epoch 2, batch 4300, loss[loss=0.2863, simple_loss=0.3455, pruned_loss=0.1136, over 7320.00 frames.], tot_loss[loss=0.262, simple_loss=0.3241, pruned_loss=0.09995, over 1415068.01 frames.], batch size: 25, lr: 2.09e-03
+2022-05-13 22:15:55,431 INFO [train.py:812] (1/8) Epoch 2, batch 4350, loss[loss=0.2061, simple_loss=0.2738, pruned_loss=0.06924, over 7002.00 frames.], tot_loss[loss=0.2618, simple_loss=0.3242, pruned_loss=0.09972, over 1416081.84 frames.], batch size: 16, lr: 2.08e-03
+2022-05-13 22:16:54,213 INFO [train.py:812] (1/8) Epoch 2, batch 4400, loss[loss=0.2762, simple_loss=0.3507, pruned_loss=0.1009, over 7310.00 frames.], tot_loss[loss=0.2613, simple_loss=0.3238, pruned_loss=0.09943, over 1410861.89 frames.], batch size: 21, lr: 2.08e-03
+2022-05-13 22:17:52,727 INFO [train.py:812] (1/8) Epoch 2, batch 4450, loss[loss=0.2796, simple_loss=0.3396, pruned_loss=0.1098, over 6515.00 frames.], tot_loss[loss=0.2626, simple_loss=0.3253, pruned_loss=0.09997, over 1402767.80 frames.], batch size: 38, lr: 2.07e-03
+2022-05-13 22:18:50,559 INFO [train.py:812] (1/8) Epoch 2, batch 4500, loss[loss=0.2998, simple_loss=0.3529, pruned_loss=0.1234, over 6479.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3249, pruned_loss=0.1002, over 1388150.57 frames.], batch size: 38, lr: 2.07e-03
+2022-05-13 22:19:49,224 INFO [train.py:812] (1/8) Epoch 2, batch 4550, loss[loss=0.3692, simple_loss=0.3986, pruned_loss=0.1699, over 4923.00 frames.], tot_loss[loss=0.2657, simple_loss=0.3273, pruned_loss=0.1021, over 1357874.86 frames.], batch size: 52, lr: 2.06e-03
+2022-05-13 22:20:58,925 INFO [train.py:812] (1/8) Epoch 3, batch 0, loss[loss=0.2131, simple_loss=0.2815, pruned_loss=0.07234, over 7276.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2815, pruned_loss=0.07234, over 7276.00 frames.], batch size: 17, lr: 2.02e-03
+2022-05-13 22:21:58,062 INFO [train.py:812] (1/8) Epoch 3, batch 50, loss[loss=0.2889, simple_loss=0.3512, pruned_loss=0.1133, over 7321.00 frames.], tot_loss[loss=0.2568, simple_loss=0.3202, pruned_loss=0.0967, over 321276.79 frames.], batch size: 25, lr: 2.02e-03
+2022-05-13 22:22:56,161 INFO [train.py:812] (1/8) Epoch 3, batch 100, loss[loss=0.2055, simple_loss=0.2686, pruned_loss=0.0712, over 7006.00 frames.], tot_loss[loss=0.2558, simple_loss=0.3202, pruned_loss=0.09571, over 569743.12 frames.], batch size: 16, lr: 2.01e-03
+2022-05-13 22:23:56,095 INFO [train.py:812] (1/8) Epoch 3, batch 150, loss[loss=0.2794, simple_loss=0.351, pruned_loss=0.1039, over 6762.00 frames.], tot_loss[loss=0.2538, simple_loss=0.3184, pruned_loss=0.09459, over 761594.78 frames.], batch size: 31, lr: 2.01e-03
+2022-05-13 22:24:53,588 INFO [train.py:812] (1/8) Epoch 3, batch 200, loss[loss=0.1863, simple_loss=0.252, pruned_loss=0.06031, over 6758.00 frames.], tot_loss[loss=0.2546, simple_loss=0.3191, pruned_loss=0.09499, over 900357.22 frames.], batch size: 15, lr: 2.00e-03
+2022-05-13 22:25:53,020 INFO [train.py:812] (1/8) Epoch 3, batch 250, loss[loss=0.2637, simple_loss=0.3236, pruned_loss=0.1019, over 7354.00 frames.], tot_loss[loss=0.2566, simple_loss=0.321, pruned_loss=0.09609, over 1010381.94 frames.], batch size: 19, lr: 2.00e-03
+2022-05-13 22:26:52,119 INFO [train.py:812] (1/8) Epoch 3, batch 300, loss[loss=0.2726, simple_loss=0.3328, pruned_loss=0.1062, over 6729.00 frames.], tot_loss[loss=0.2564, simple_loss=0.3214, pruned_loss=0.09569, over 1100739.96 frames.], batch size: 31, lr: 2.00e-03
+2022-05-13 22:27:51,985 INFO [train.py:812] (1/8) Epoch 3, batch 350, loss[loss=0.226, simple_loss=0.3094, pruned_loss=0.0713, over 7310.00 frames.], tot_loss[loss=0.2553, simple_loss=0.3209, pruned_loss=0.09492, over 1172070.12 frames.], batch size: 21, lr: 1.99e-03
+2022-05-13 22:29:00,806 INFO [train.py:812] (1/8) Epoch 3, batch 400, loss[loss=0.257, simple_loss=0.3283, pruned_loss=0.09283, over 7282.00 frames.], tot_loss[loss=0.2566, simple_loss=0.3217, pruned_loss=0.09581, over 1223395.18 frames.], batch size: 24, lr: 1.99e-03
+2022-05-13 22:29:59,464 INFO [train.py:812] (1/8) Epoch 3, batch 450, loss[loss=0.2908, simple_loss=0.3649, pruned_loss=0.1083, over 7199.00 frames.], tot_loss[loss=0.2576, simple_loss=0.323, pruned_loss=0.09608, over 1263606.09 frames.], batch size: 22, lr: 1.98e-03
+2022-05-13 22:31:07,388 INFO [train.py:812] (1/8) Epoch 3, batch 500, loss[loss=0.23, simple_loss=0.2978, pruned_loss=0.08107, over 7008.00 frames.], tot_loss[loss=0.2556, simple_loss=0.3214, pruned_loss=0.09489, over 1301390.45 frames.], batch size: 16, lr: 1.98e-03
+2022-05-13 22:32:54,334 INFO [train.py:812] (1/8) Epoch 3, batch 550, loss[loss=0.2207, simple_loss=0.3013, pruned_loss=0.07001, over 7216.00 frames.], tot_loss[loss=0.2533, simple_loss=0.3196, pruned_loss=0.09351, over 1331291.25 frames.], batch size: 21, lr: 1.98e-03
+2022-05-13 22:34:03,102 INFO [train.py:812] (1/8) Epoch 3, batch 600, loss[loss=0.3114, simple_loss=0.3744, pruned_loss=0.1241, over 7289.00 frames.], tot_loss[loss=0.2542, simple_loss=0.3197, pruned_loss=0.09433, over 1351901.34 frames.], batch size: 25, lr: 1.97e-03
+2022-05-13 22:35:02,658 INFO [train.py:812] (1/8) Epoch 3, batch 650, loss[loss=0.2596, simple_loss=0.3254, pruned_loss=0.09688, over 7364.00 frames.], tot_loss[loss=0.2542, simple_loss=0.3197, pruned_loss=0.0944, over 1366780.94 frames.], batch size: 19, lr: 1.97e-03
+2022-05-13 22:36:02,056 INFO [train.py:812] (1/8) Epoch 3, batch 700, loss[loss=0.2467, simple_loss=0.3151, pruned_loss=0.08911, over 7215.00 frames.], tot_loss[loss=0.2546, simple_loss=0.3202, pruned_loss=0.09452, over 1376392.40 frames.], batch size: 21, lr: 1.96e-03
+2022-05-13 22:37:01,822 INFO [train.py:812] (1/8) Epoch 3, batch 750, loss[loss=0.2194, simple_loss=0.3036, pruned_loss=0.06757, over 7170.00 frames.], tot_loss[loss=0.2536, simple_loss=0.3196, pruned_loss=0.09382, over 1390647.32 frames.], batch size: 23, lr: 1.96e-03
+2022-05-13 22:38:00,542 INFO [train.py:812] (1/8) Epoch 3, batch 800, loss[loss=0.2153, simple_loss=0.3017, pruned_loss=0.06439, over 7204.00 frames.], tot_loss[loss=0.254, simple_loss=0.3202, pruned_loss=0.09392, over 1401501.33 frames.], batch size: 23, lr: 1.96e-03
+2022-05-13 22:38:59,713 INFO [train.py:812] (1/8) Epoch 3, batch 850, loss[loss=0.232, simple_loss=0.3112, pruned_loss=0.07636, over 7308.00 frames.], tot_loss[loss=0.2527, simple_loss=0.3188, pruned_loss=0.09336, over 1410036.21 frames.], batch size: 25, lr: 1.95e-03
+2022-05-13 22:39:58,498 INFO [train.py:812] (1/8) Epoch 3, batch 900, loss[loss=0.2548, simple_loss=0.3149, pruned_loss=0.09733, over 7070.00 frames.], tot_loss[loss=0.2541, simple_loss=0.3202, pruned_loss=0.09398, over 1412850.36 frames.], batch size: 18, lr: 1.95e-03
+2022-05-13 22:40:58,633 INFO [train.py:812] (1/8) Epoch 3, batch 950, loss[loss=0.2779, simple_loss=0.3371, pruned_loss=0.1093, over 7147.00 frames.], tot_loss[loss=0.2542, simple_loss=0.3204, pruned_loss=0.09406, over 1417773.81 frames.], batch size: 20, lr: 1.94e-03
+2022-05-13 22:41:58,339 INFO [train.py:812] (1/8) Epoch 3, batch 1000, loss[loss=0.2728, simple_loss=0.3449, pruned_loss=0.1003, over 6740.00 frames.], tot_loss[loss=0.2539, simple_loss=0.3199, pruned_loss=0.09391, over 1416850.84 frames.], batch size: 31, lr: 1.94e-03
+2022-05-13 22:42:57,494 INFO [train.py:812] (1/8) Epoch 3, batch 1050, loss[loss=0.24, simple_loss=0.3099, pruned_loss=0.08506, over 7288.00 frames.], tot_loss[loss=0.2532, simple_loss=0.3198, pruned_loss=0.09332, over 1414558.15 frames.], batch size: 18, lr: 1.94e-03
+2022-05-13 22:43:56,794 INFO [train.py:812] (1/8) Epoch 3, batch 1100, loss[loss=0.2428, simple_loss=0.3202, pruned_loss=0.08268, over 7220.00 frames.], tot_loss[loss=0.2539, simple_loss=0.3212, pruned_loss=0.09333, over 1419690.76 frames.], batch size: 21, lr: 1.93e-03
+2022-05-13 22:44:56,336 INFO [train.py:812] (1/8) Epoch 3, batch 1150, loss[loss=0.264, simple_loss=0.3336, pruned_loss=0.09722, over 7234.00 frames.], tot_loss[loss=0.2531, simple_loss=0.32, pruned_loss=0.0931, over 1420955.85 frames.], batch size: 20, lr: 1.93e-03
+2022-05-13 22:45:54,822 INFO [train.py:812] (1/8) Epoch 3, batch 1200, loss[loss=0.2184, simple_loss=0.291, pruned_loss=0.07291, over 7438.00 frames.], tot_loss[loss=0.2537, simple_loss=0.3204, pruned_loss=0.09344, over 1425149.51 frames.], batch size: 20, lr: 1.93e-03
+2022-05-13 22:46:52,758 INFO [train.py:812] (1/8) Epoch 3, batch 1250, loss[loss=0.26, simple_loss=0.3292, pruned_loss=0.0954, over 7414.00 frames.], tot_loss[loss=0.2527, simple_loss=0.3194, pruned_loss=0.09301, over 1425649.48 frames.], batch size: 21, lr: 1.92e-03
+2022-05-13 22:47:52,029 INFO [train.py:812] (1/8) Epoch 3, batch 1300, loss[loss=0.2705, simple_loss=0.3396, pruned_loss=0.1006, over 7318.00 frames.], tot_loss[loss=0.2526, simple_loss=0.3191, pruned_loss=0.0931, over 1426836.84 frames.], batch size: 21, lr: 1.92e-03
+2022-05-13 22:48:50,081 INFO [train.py:812] (1/8) Epoch 3, batch 1350, loss[loss=0.2518, simple_loss=0.3283, pruned_loss=0.08766, over 7415.00 frames.], tot_loss[loss=0.253, simple_loss=0.3198, pruned_loss=0.09307, over 1426523.04 frames.], batch size: 20, lr: 1.91e-03
+2022-05-13 22:49:48,132 INFO [train.py:812] (1/8) Epoch 3, batch 1400, loss[loss=0.2506, simple_loss=0.3155, pruned_loss=0.0928, over 7156.00 frames.], tot_loss[loss=0.254, simple_loss=0.3209, pruned_loss=0.09349, over 1423540.17 frames.], batch size: 19, lr: 1.91e-03
+2022-05-13 22:50:48,082 INFO [train.py:812] (1/8) Epoch 3, batch 1450, loss[loss=0.2027, simple_loss=0.2705, pruned_loss=0.06747, over 7144.00 frames.], tot_loss[loss=0.2536, simple_loss=0.3205, pruned_loss=0.09335, over 1420044.31 frames.], batch size: 17, lr: 1.91e-03
+2022-05-13 22:51:46,938 INFO [train.py:812] (1/8) Epoch 3, batch 1500, loss[loss=0.2631, simple_loss=0.3406, pruned_loss=0.09276, over 7312.00 frames.], tot_loss[loss=0.2537, simple_loss=0.3204, pruned_loss=0.09348, over 1417647.24 frames.], batch size: 21, lr: 1.90e-03
+2022-05-13 22:52:47,275 INFO [train.py:812] (1/8) Epoch 3, batch 1550, loss[loss=0.1902, simple_loss=0.2731, pruned_loss=0.05364, over 7156.00 frames.], tot_loss[loss=0.2534, simple_loss=0.3204, pruned_loss=0.09322, over 1421675.83 frames.], batch size: 19, lr: 1.90e-03
+2022-05-13 22:53:45,773 INFO [train.py:812] (1/8) Epoch 3, batch 1600, loss[loss=0.1955, simple_loss=0.2741, pruned_loss=0.05845, over 7168.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3181, pruned_loss=0.09174, over 1424360.18 frames.], batch size: 19, lr: 1.90e-03
+2022-05-13 22:54:44,637 INFO [train.py:812] (1/8) Epoch 3, batch 1650, loss[loss=0.2353, simple_loss=0.302, pruned_loss=0.08427, over 7440.00 frames.], tot_loss[loss=0.2498, simple_loss=0.3169, pruned_loss=0.09142, over 1427057.30 frames.], batch size: 20, lr: 1.89e-03
+2022-05-13 22:55:42,300 INFO [train.py:812] (1/8) Epoch 3, batch 1700, loss[loss=0.2746, simple_loss=0.3443, pruned_loss=0.1025, over 7161.00 frames.], tot_loss[loss=0.2497, simple_loss=0.317, pruned_loss=0.09121, over 1417659.78 frames.], batch size: 20, lr: 1.89e-03
+2022-05-13 22:56:41,870 INFO [train.py:812] (1/8) Epoch 3, batch 1750, loss[loss=0.233, simple_loss=0.3098, pruned_loss=0.07809, over 7230.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3158, pruned_loss=0.08992, over 1424998.32 frames.], batch size: 20, lr: 1.88e-03
+2022-05-13 22:57:40,289 INFO [train.py:812] (1/8) Epoch 3, batch 1800, loss[loss=0.2517, simple_loss=0.3213, pruned_loss=0.0911, over 7115.00 frames.], tot_loss[loss=0.2473, simple_loss=0.3151, pruned_loss=0.08973, over 1418182.85 frames.], batch size: 21, lr: 1.88e-03
+2022-05-13 22:58:39,764 INFO [train.py:812] (1/8) Epoch 3, batch 1850, loss[loss=0.2745, simple_loss=0.3409, pruned_loss=0.104, over 7405.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3141, pruned_loss=0.08911, over 1418878.44 frames.], batch size: 21, lr: 1.88e-03
+2022-05-13 22:59:38,879 INFO [train.py:812] (1/8) Epoch 3, batch 1900, loss[loss=0.245, simple_loss=0.3132, pruned_loss=0.08843, over 7165.00 frames.], tot_loss[loss=0.2473, simple_loss=0.3149, pruned_loss=0.0899, over 1416660.05 frames.], batch size: 18, lr: 1.87e-03
+2022-05-13 23:00:38,435 INFO [train.py:812] (1/8) Epoch 3, batch 1950, loss[loss=0.2659, simple_loss=0.3416, pruned_loss=0.09512, over 6706.00 frames.], tot_loss[loss=0.2464, simple_loss=0.3142, pruned_loss=0.08928, over 1417437.67 frames.], batch size: 31, lr: 1.87e-03
+2022-05-13 23:01:37,609 INFO [train.py:812] (1/8) Epoch 3, batch 2000, loss[loss=0.218, simple_loss=0.296, pruned_loss=0.06997, over 7165.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3143, pruned_loss=0.08901, over 1421665.88 frames.], batch size: 19, lr: 1.87e-03
+2022-05-13 23:02:36,935 INFO [train.py:812] (1/8) Epoch 3, batch 2050, loss[loss=0.2796, simple_loss=0.3376, pruned_loss=0.1108, over 5208.00 frames.], tot_loss[loss=0.2482, simple_loss=0.3162, pruned_loss=0.09014, over 1421475.20 frames.], batch size: 52, lr: 1.86e-03
+2022-05-13 23:03:35,450 INFO [train.py:812] (1/8) Epoch 3, batch 2100, loss[loss=0.2208, simple_loss=0.2974, pruned_loss=0.07204, over 7322.00 frames.], tot_loss[loss=0.2491, simple_loss=0.3171, pruned_loss=0.09051, over 1423918.38 frames.], batch size: 21, lr: 1.86e-03
+2022-05-13 23:04:34,071 INFO [train.py:812] (1/8) Epoch 3, batch 2150, loss[loss=0.2693, simple_loss=0.3418, pruned_loss=0.09847, over 7250.00 frames.], tot_loss[loss=0.2487, simple_loss=0.3168, pruned_loss=0.09025, over 1425956.13 frames.], batch size: 20, lr: 1.86e-03
+2022-05-13 23:05:32,774 INFO [train.py:812] (1/8) Epoch 3, batch 2200, loss[loss=0.2494, simple_loss=0.3169, pruned_loss=0.091, over 7142.00 frames.], tot_loss[loss=0.2477, simple_loss=0.3159, pruned_loss=0.0897, over 1425157.43 frames.], batch size: 20, lr: 1.85e-03
+2022-05-13 23:06:32,201 INFO [train.py:812] (1/8) Epoch 3, batch 2250, loss[loss=0.2447, simple_loss=0.3197, pruned_loss=0.08482, over 7317.00 frames.], tot_loss[loss=0.249, simple_loss=0.3174, pruned_loss=0.09031, over 1424923.23 frames.], batch size: 20, lr: 1.85e-03
+2022-05-13 23:07:31,559 INFO [train.py:812] (1/8) Epoch 3, batch 2300, loss[loss=0.2135, simple_loss=0.294, pruned_loss=0.06654, over 7354.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3166, pruned_loss=0.08997, over 1413394.10 frames.], batch size: 19, lr: 1.85e-03
+2022-05-13 23:08:31,279 INFO [train.py:812] (1/8) Epoch 3, batch 2350, loss[loss=0.2615, simple_loss=0.3318, pruned_loss=0.09554, over 7256.00 frames.], tot_loss[loss=0.2469, simple_loss=0.3154, pruned_loss=0.0892, over 1414697.56 frames.], batch size: 19, lr: 1.84e-03
+2022-05-13 23:09:29,610 INFO [train.py:812] (1/8) Epoch 3, batch 2400, loss[loss=0.2251, simple_loss=0.2917, pruned_loss=0.07921, over 7248.00 frames.], tot_loss[loss=0.2462, simple_loss=0.3151, pruned_loss=0.08869, over 1417631.88 frames.], batch size: 19, lr: 1.84e-03
+2022-05-13 23:10:29,106 INFO [train.py:812] (1/8) Epoch 3, batch 2450, loss[loss=0.2786, simple_loss=0.3444, pruned_loss=0.1063, over 7232.00 frames.], tot_loss[loss=0.2475, simple_loss=0.3162, pruned_loss=0.08941, over 1414693.66 frames.], batch size: 20, lr: 1.84e-03
+2022-05-13 23:11:28,079 INFO [train.py:812] (1/8) Epoch 3, batch 2500, loss[loss=0.265, simple_loss=0.3235, pruned_loss=0.1032, over 7165.00 frames.], tot_loss[loss=0.2455, simple_loss=0.3144, pruned_loss=0.08832, over 1413148.72 frames.], batch size: 19, lr: 1.83e-03
+2022-05-13 23:12:27,742 INFO [train.py:812] (1/8) Epoch 3, batch 2550, loss[loss=0.2529, simple_loss=0.3277, pruned_loss=0.08907, over 7211.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3138, pruned_loss=0.08799, over 1411764.02 frames.], batch size: 21, lr: 1.83e-03
+2022-05-13 23:13:27,079 INFO [train.py:812] (1/8) Epoch 3, batch 2600, loss[loss=0.2481, simple_loss=0.3093, pruned_loss=0.09342, over 7269.00 frames.], tot_loss[loss=0.243, simple_loss=0.3123, pruned_loss=0.08688, over 1417782.34 frames.], batch size: 18, lr: 1.83e-03
+2022-05-13 23:14:26,422 INFO [train.py:812] (1/8) Epoch 3, batch 2650, loss[loss=0.2067, simple_loss=0.2852, pruned_loss=0.06409, over 7328.00 frames.], tot_loss[loss=0.2429, simple_loss=0.312, pruned_loss=0.0869, over 1417639.02 frames.], batch size: 20, lr: 1.82e-03
+2022-05-13 23:15:24,401 INFO [train.py:812] (1/8) Epoch 3, batch 2700, loss[loss=0.2088, simple_loss=0.2839, pruned_loss=0.06686, over 7071.00 frames.], tot_loss[loss=0.2422, simple_loss=0.3117, pruned_loss=0.08639, over 1418957.36 frames.], batch size: 18, lr: 1.82e-03
+2022-05-13 23:16:23,931 INFO [train.py:812] (1/8) Epoch 3, batch 2750, loss[loss=0.2869, simple_loss=0.3615, pruned_loss=0.1061, over 7173.00 frames.], tot_loss[loss=0.2434, simple_loss=0.3125, pruned_loss=0.08712, over 1417732.58 frames.], batch size: 26, lr: 1.82e-03
+2022-05-13 23:17:22,912 INFO [train.py:812] (1/8) Epoch 3, batch 2800, loss[loss=0.3006, simple_loss=0.3439, pruned_loss=0.1287, over 5237.00 frames.], tot_loss[loss=0.2433, simple_loss=0.3122, pruned_loss=0.08724, over 1418502.37 frames.], batch size: 53, lr: 1.81e-03
+2022-05-13 23:18:30,781 INFO [train.py:812] (1/8) Epoch 3, batch 2850, loss[loss=0.2483, simple_loss=0.3124, pruned_loss=0.09211, over 7214.00 frames.], tot_loss[loss=0.2435, simple_loss=0.3124, pruned_loss=0.08736, over 1421458.34 frames.], batch size: 21, lr: 1.81e-03
+2022-05-13 23:19:29,904 INFO [train.py:812] (1/8) Epoch 3, batch 2900, loss[loss=0.2946, simple_loss=0.3563, pruned_loss=0.1164, over 6283.00 frames.], tot_loss[loss=0.2444, simple_loss=0.3128, pruned_loss=0.088, over 1417733.58 frames.], batch size: 37, lr: 1.81e-03
+2022-05-13 23:20:29,314 INFO [train.py:812] (1/8) Epoch 3, batch 2950, loss[loss=0.271, simple_loss=0.3263, pruned_loss=0.1078, over 7160.00 frames.], tot_loss[loss=0.2453, simple_loss=0.314, pruned_loss=0.08835, over 1416311.98 frames.], batch size: 26, lr: 1.80e-03
+2022-05-13 23:21:28,543 INFO [train.py:812] (1/8) Epoch 3, batch 3000, loss[loss=0.2434, simple_loss=0.322, pruned_loss=0.08243, over 7331.00 frames.], tot_loss[loss=0.2454, simple_loss=0.314, pruned_loss=0.08838, over 1419412.72 frames.], batch size: 22, lr: 1.80e-03
+2022-05-13 23:21:28,544 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-13 23:21:36,068 INFO [train.py:841] (1/8) Epoch 3, validation: loss=0.1862, simple_loss=0.2867, pruned_loss=0.04278, over 698248.00 frames.
+2022-05-13 23:22:33,841 INFO [train.py:812] (1/8) Epoch 3, batch 3050, loss[loss=0.2384, simple_loss=0.3135, pruned_loss=0.08164, over 7419.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3139, pruned_loss=0.08837, over 1424900.61 frames.], batch size: 21, lr: 1.80e-03
+2022-05-13 23:23:30,789 INFO [train.py:812] (1/8) Epoch 3, batch 3100, loss[loss=0.2411, simple_loss=0.3081, pruned_loss=0.08704, over 7274.00 frames.], tot_loss[loss=0.2447, simple_loss=0.3135, pruned_loss=0.08793, over 1428330.82 frames.], batch size: 18, lr: 1.79e-03
+2022-05-13 23:24:30,033 INFO [train.py:812] (1/8) Epoch 3, batch 3150, loss[loss=0.2281, simple_loss=0.3075, pruned_loss=0.07437, over 7219.00 frames.], tot_loss[loss=0.2442, simple_loss=0.3129, pruned_loss=0.08775, over 1422901.57 frames.], batch size: 21, lr: 1.79e-03
+2022-05-13 23:25:29,456 INFO [train.py:812] (1/8) Epoch 3, batch 3200, loss[loss=0.2331, simple_loss=0.3077, pruned_loss=0.07929, over 7377.00 frames.], tot_loss[loss=0.2448, simple_loss=0.3139, pruned_loss=0.08783, over 1425597.50 frames.], batch size: 23, lr: 1.79e-03
+2022-05-13 23:26:29,122 INFO [train.py:812] (1/8) Epoch 3, batch 3250, loss[loss=0.2043, simple_loss=0.287, pruned_loss=0.06084, over 7165.00 frames.], tot_loss[loss=0.2445, simple_loss=0.3137, pruned_loss=0.08761, over 1426486.14 frames.], batch size: 19, lr: 1.79e-03
+2022-05-13 23:27:27,200 INFO [train.py:812] (1/8) Epoch 3, batch 3300, loss[loss=0.26, simple_loss=0.3303, pruned_loss=0.09483, over 7158.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3121, pruned_loss=0.0862, over 1428973.29 frames.], batch size: 26, lr: 1.78e-03
+2022-05-13 23:28:26,183 INFO [train.py:812] (1/8) Epoch 3, batch 3350, loss[loss=0.2264, simple_loss=0.297, pruned_loss=0.07795, over 7288.00 frames.], tot_loss[loss=0.2437, simple_loss=0.3134, pruned_loss=0.08702, over 1425732.24 frames.], batch size: 18, lr: 1.78e-03
+2022-05-13 23:29:23,905 INFO [train.py:812] (1/8) Epoch 3, batch 3400, loss[loss=0.221, simple_loss=0.2913, pruned_loss=0.07534, over 7413.00 frames.], tot_loss[loss=0.2446, simple_loss=0.3141, pruned_loss=0.08754, over 1423959.83 frames.], batch size: 18, lr: 1.78e-03
+2022-05-13 23:30:22,224 INFO [train.py:812] (1/8) Epoch 3, batch 3450, loss[loss=0.2354, simple_loss=0.3062, pruned_loss=0.08229, over 7248.00 frames.], tot_loss[loss=0.2441, simple_loss=0.3134, pruned_loss=0.0874, over 1420626.59 frames.], batch size: 19, lr: 1.77e-03
+2022-05-13 23:31:20,915 INFO [train.py:812] (1/8) Epoch 3, batch 3500, loss[loss=0.2513, simple_loss=0.3191, pruned_loss=0.09175, over 7303.00 frames.], tot_loss[loss=0.2421, simple_loss=0.3116, pruned_loss=0.08626, over 1422163.19 frames.], batch size: 25, lr: 1.77e-03
+2022-05-13 23:32:20,546 INFO [train.py:812] (1/8) Epoch 3, batch 3550, loss[loss=0.2496, simple_loss=0.3227, pruned_loss=0.08828, over 7218.00 frames.], tot_loss[loss=0.2417, simple_loss=0.3117, pruned_loss=0.08584, over 1421193.27 frames.], batch size: 21, lr: 1.77e-03
+2022-05-13 23:33:19,830 INFO [train.py:812] (1/8) Epoch 3, batch 3600, loss[loss=0.2809, simple_loss=0.3505, pruned_loss=0.1057, over 7310.00 frames.], tot_loss[loss=0.2398, simple_loss=0.31, pruned_loss=0.08484, over 1422413.12 frames.], batch size: 24, lr: 1.76e-03
+2022-05-13 23:34:19,468 INFO [train.py:812] (1/8) Epoch 3, batch 3650, loss[loss=0.2506, simple_loss=0.3224, pruned_loss=0.08938, over 7369.00 frames.], tot_loss[loss=0.2397, simple_loss=0.3097, pruned_loss=0.08488, over 1422114.17 frames.], batch size: 23, lr: 1.76e-03
+2022-05-13 23:35:18,549 INFO [train.py:812] (1/8) Epoch 3, batch 3700, loss[loss=0.2001, simple_loss=0.2763, pruned_loss=0.06194, over 7413.00 frames.], tot_loss[loss=0.2402, simple_loss=0.3106, pruned_loss=0.0849, over 1416994.85 frames.], batch size: 18, lr: 1.76e-03
+2022-05-13 23:36:18,208 INFO [train.py:812] (1/8) Epoch 3, batch 3750, loss[loss=0.1718, simple_loss=0.2447, pruned_loss=0.04943, over 7266.00 frames.], tot_loss[loss=0.2401, simple_loss=0.3105, pruned_loss=0.08485, over 1422569.28 frames.], batch size: 18, lr: 1.76e-03
+2022-05-13 23:37:16,801 INFO [train.py:812] (1/8) Epoch 3, batch 3800, loss[loss=0.2111, simple_loss=0.2835, pruned_loss=0.06933, over 7152.00 frames.], tot_loss[loss=0.2394, simple_loss=0.3096, pruned_loss=0.08456, over 1423825.31 frames.], batch size: 18, lr: 1.75e-03
+2022-05-13 23:38:16,203 INFO [train.py:812] (1/8) Epoch 3, batch 3850, loss[loss=0.255, simple_loss=0.3249, pruned_loss=0.09253, over 7340.00 frames.], tot_loss[loss=0.2399, simple_loss=0.3102, pruned_loss=0.08478, over 1422640.80 frames.], batch size: 22, lr: 1.75e-03
+2022-05-13 23:39:15,481 INFO [train.py:812] (1/8) Epoch 3, batch 3900, loss[loss=0.2678, simple_loss=0.332, pruned_loss=0.1018, over 7336.00 frames.], tot_loss[loss=0.2393, simple_loss=0.3098, pruned_loss=0.0844, over 1424402.79 frames.], batch size: 20, lr: 1.75e-03
+2022-05-13 23:40:14,814 INFO [train.py:812] (1/8) Epoch 3, batch 3950, loss[loss=0.2207, simple_loss=0.2975, pruned_loss=0.0719, over 7331.00 frames.], tot_loss[loss=0.2397, simple_loss=0.3098, pruned_loss=0.0848, over 1421241.52 frames.], batch size: 21, lr: 1.74e-03
+2022-05-13 23:41:13,964 INFO [train.py:812] (1/8) Epoch 3, batch 4000, loss[loss=0.2526, simple_loss=0.3281, pruned_loss=0.08853, over 7330.00 frames.], tot_loss[loss=0.2388, simple_loss=0.3096, pruned_loss=0.084, over 1425735.10 frames.], batch size: 22, lr: 1.74e-03
+2022-05-13 23:42:13,686 INFO [train.py:812] (1/8) Epoch 3, batch 4050, loss[loss=0.2593, simple_loss=0.3434, pruned_loss=0.08763, over 7422.00 frames.], tot_loss[loss=0.2388, simple_loss=0.3091, pruned_loss=0.08425, over 1426685.45 frames.], batch size: 20, lr: 1.74e-03
+2022-05-13 23:43:12,784 INFO [train.py:812] (1/8) Epoch 3, batch 4100, loss[loss=0.2399, simple_loss=0.3118, pruned_loss=0.084, over 7067.00 frames.], tot_loss[loss=0.2417, simple_loss=0.3112, pruned_loss=0.08606, over 1417112.68 frames.], batch size: 18, lr: 1.73e-03
+2022-05-13 23:44:12,464 INFO [train.py:812] (1/8) Epoch 3, batch 4150, loss[loss=0.2292, simple_loss=0.3119, pruned_loss=0.0732, over 7109.00 frames.], tot_loss[loss=0.2411, simple_loss=0.311, pruned_loss=0.08558, over 1422040.99 frames.], batch size: 21, lr: 1.73e-03
+2022-05-13 23:45:10,714 INFO [train.py:812] (1/8) Epoch 3, batch 4200, loss[loss=0.2934, simple_loss=0.3637, pruned_loss=0.1116, over 6920.00 frames.], tot_loss[loss=0.241, simple_loss=0.311, pruned_loss=0.08544, over 1420714.10 frames.], batch size: 28, lr: 1.73e-03
+2022-05-13 23:46:09,933 INFO [train.py:812] (1/8) Epoch 3, batch 4250, loss[loss=0.2579, simple_loss=0.3362, pruned_loss=0.08981, over 7214.00 frames.], tot_loss[loss=0.2402, simple_loss=0.3104, pruned_loss=0.08501, over 1421496.30 frames.], batch size: 22, lr: 1.73e-03
+2022-05-13 23:47:09,077 INFO [train.py:812] (1/8) Epoch 3, batch 4300, loss[loss=0.2066, simple_loss=0.2749, pruned_loss=0.06913, over 7063.00 frames.], tot_loss[loss=0.2411, simple_loss=0.3115, pruned_loss=0.08541, over 1423555.65 frames.], batch size: 18, lr: 1.72e-03
+2022-05-13 23:48:08,223 INFO [train.py:812] (1/8) Epoch 3, batch 4350, loss[loss=0.2397, simple_loss=0.3249, pruned_loss=0.07723, over 7133.00 frames.], tot_loss[loss=0.2397, simple_loss=0.3104, pruned_loss=0.08447, over 1425816.02 frames.], batch size: 20, lr: 1.72e-03
+2022-05-13 23:49:06,723 INFO [train.py:812] (1/8) Epoch 3, batch 4400, loss[loss=0.2454, simple_loss=0.3342, pruned_loss=0.07827, over 7297.00 frames.], tot_loss[loss=0.2396, simple_loss=0.31, pruned_loss=0.08459, over 1420024.96 frames.], batch size: 25, lr: 1.72e-03
+2022-05-13 23:50:05,671 INFO [train.py:812] (1/8) Epoch 3, batch 4450, loss[loss=0.2484, simple_loss=0.3239, pruned_loss=0.08646, over 7322.00 frames.], tot_loss[loss=0.2415, simple_loss=0.3117, pruned_loss=0.08561, over 1410911.35 frames.], batch size: 22, lr: 1.71e-03
+2022-05-13 23:51:04,260 INFO [train.py:812] (1/8) Epoch 3, batch 4500, loss[loss=0.236, simple_loss=0.3168, pruned_loss=0.07765, over 7120.00 frames.], tot_loss[loss=0.2411, simple_loss=0.3117, pruned_loss=0.08527, over 1404713.02 frames.], batch size: 21, lr: 1.71e-03
+2022-05-13 23:52:01,832 INFO [train.py:812] (1/8) Epoch 3, batch 4550, loss[loss=0.2569, simple_loss=0.3287, pruned_loss=0.09256, over 6253.00 frames.], tot_loss[loss=0.2444, simple_loss=0.3142, pruned_loss=0.08726, over 1377150.95 frames.], batch size: 37, lr: 1.71e-03
+2022-05-13 23:53:11,481 INFO [train.py:812] (1/8) Epoch 4, batch 0, loss[loss=0.2518, simple_loss=0.3228, pruned_loss=0.09036, over 7227.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3228, pruned_loss=0.09036, over 7227.00 frames.], batch size: 23, lr: 1.66e-03
+2022-05-13 23:54:10,704 INFO [train.py:812] (1/8) Epoch 4, batch 50, loss[loss=0.2344, simple_loss=0.2961, pruned_loss=0.08634, over 7267.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3108, pruned_loss=0.08497, over 318355.40 frames.], batch size: 17, lr: 1.66e-03
+2022-05-13 23:55:09,411 INFO [train.py:812] (1/8) Epoch 4, batch 100, loss[loss=0.1888, simple_loss=0.2617, pruned_loss=0.05795, over 7279.00 frames.], tot_loss[loss=0.2368, simple_loss=0.3075, pruned_loss=0.08302, over 564884.69 frames.], batch size: 17, lr: 1.65e-03
+2022-05-13 23:56:09,345 INFO [train.py:812] (1/8) Epoch 4, batch 150, loss[loss=0.2258, simple_loss=0.3015, pruned_loss=0.07501, over 7332.00 frames.], tot_loss[loss=0.2337, simple_loss=0.3053, pruned_loss=0.08107, over 755830.15 frames.], batch size: 22, lr: 1.65e-03
+2022-05-13 23:57:08,457 INFO [train.py:812] (1/8) Epoch 4, batch 200, loss[loss=0.2667, simple_loss=0.3337, pruned_loss=0.0998, over 7196.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3062, pruned_loss=0.08175, over 904456.78 frames.], batch size: 23, lr: 1.65e-03
+2022-05-13 23:58:07,157 INFO [train.py:812] (1/8) Epoch 4, batch 250, loss[loss=0.2623, simple_loss=0.3349, pruned_loss=0.09491, over 7334.00 frames.], tot_loss[loss=0.2352, simple_loss=0.3074, pruned_loss=0.0815, over 1016329.58 frames.], batch size: 22, lr: 1.64e-03
+2022-05-13 23:59:06,606 INFO [train.py:812] (1/8) Epoch 4, batch 300, loss[loss=0.2423, simple_loss=0.3228, pruned_loss=0.08086, over 7382.00 frames.], tot_loss[loss=0.2351, simple_loss=0.3067, pruned_loss=0.08175, over 1110617.66 frames.], batch size: 23, lr: 1.64e-03
+2022-05-14 00:00:06,135 INFO [train.py:812] (1/8) Epoch 4, batch 350, loss[loss=0.236, simple_loss=0.3131, pruned_loss=0.07947, over 7322.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3059, pruned_loss=0.08085, over 1182564.21 frames.], batch size: 21, lr: 1.64e-03
+2022-05-14 00:01:05,126 INFO [train.py:812] (1/8) Epoch 4, batch 400, loss[loss=0.2218, simple_loss=0.3032, pruned_loss=0.0702, over 7226.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3053, pruned_loss=0.08063, over 1232384.85 frames.], batch size: 20, lr: 1.64e-03
+2022-05-14 00:02:04,520 INFO [train.py:812] (1/8) Epoch 4, batch 450, loss[loss=0.2585, simple_loss=0.3187, pruned_loss=0.09911, over 7143.00 frames.], tot_loss[loss=0.233, simple_loss=0.305, pruned_loss=0.08049, over 1275538.94 frames.], batch size: 20, lr: 1.63e-03
+2022-05-14 00:03:03,236 INFO [train.py:812] (1/8) Epoch 4, batch 500, loss[loss=0.2158, simple_loss=0.3031, pruned_loss=0.06427, over 7150.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3064, pruned_loss=0.08066, over 1305457.94 frames.], batch size: 19, lr: 1.63e-03
+2022-05-14 00:04:02,746 INFO [train.py:812] (1/8) Epoch 4, batch 550, loss[loss=0.2016, simple_loss=0.281, pruned_loss=0.06109, over 7151.00 frames.], tot_loss[loss=0.2346, simple_loss=0.3071, pruned_loss=0.08105, over 1330704.39 frames.], batch size: 18, lr: 1.63e-03
+2022-05-14 00:05:01,388 INFO [train.py:812] (1/8) Epoch 4, batch 600, loss[loss=0.2592, simple_loss=0.3257, pruned_loss=0.09632, over 6319.00 frames.], tot_loss[loss=0.2351, simple_loss=0.3072, pruned_loss=0.08144, over 1348179.12 frames.], batch size: 37, lr: 1.63e-03
+2022-05-14 00:06:00,841 INFO [train.py:812] (1/8) Epoch 4, batch 650, loss[loss=0.2176, simple_loss=0.3016, pruned_loss=0.0668, over 7424.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3064, pruned_loss=0.08006, over 1368483.38 frames.], batch size: 20, lr: 1.62e-03
+2022-05-14 00:07:00,175 INFO [train.py:812] (1/8) Epoch 4, batch 700, loss[loss=0.2661, simple_loss=0.3329, pruned_loss=0.09971, over 7277.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3049, pruned_loss=0.07877, over 1384960.09 frames.], batch size: 24, lr: 1.62e-03
+2022-05-14 00:07:59,216 INFO [train.py:812] (1/8) Epoch 4, batch 750, loss[loss=0.2961, simple_loss=0.3519, pruned_loss=0.1201, over 7288.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3042, pruned_loss=0.07847, over 1393580.53 frames.], batch size: 24, lr: 1.62e-03
+2022-05-14 00:08:58,464 INFO [train.py:812] (1/8) Epoch 4, batch 800, loss[loss=0.2076, simple_loss=0.2825, pruned_loss=0.06639, over 7264.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3056, pruned_loss=0.07931, over 1397347.91 frames.], batch size: 19, lr: 1.62e-03
+2022-05-14 00:09:58,459 INFO [train.py:812] (1/8) Epoch 4, batch 850, loss[loss=0.2115, simple_loss=0.2855, pruned_loss=0.06874, over 7061.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3059, pruned_loss=0.07892, over 1407645.71 frames.], batch size: 18, lr: 1.61e-03
+2022-05-14 00:10:57,736 INFO [train.py:812] (1/8) Epoch 4, batch 900, loss[loss=0.2111, simple_loss=0.2943, pruned_loss=0.06397, over 7110.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3056, pruned_loss=0.07842, over 1415638.32 frames.], batch size: 21, lr: 1.61e-03
+2022-05-14 00:11:56,764 INFO [train.py:812] (1/8) Epoch 4, batch 950, loss[loss=0.2402, simple_loss=0.3138, pruned_loss=0.0833, over 7160.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3052, pruned_loss=0.07873, over 1420156.61 frames.], batch size: 26, lr: 1.61e-03
+2022-05-14 00:12:55,419 INFO [train.py:812] (1/8) Epoch 4, batch 1000, loss[loss=0.2025, simple_loss=0.28, pruned_loss=0.06246, over 7264.00 frames.], tot_loss[loss=0.2301, simple_loss=0.304, pruned_loss=0.07814, over 1420311.40 frames.], batch size: 18, lr: 1.61e-03
+2022-05-14 00:13:54,501 INFO [train.py:812] (1/8) Epoch 4, batch 1050, loss[loss=0.2574, simple_loss=0.3205, pruned_loss=0.09712, over 6721.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3045, pruned_loss=0.07858, over 1419499.01 frames.], batch size: 31, lr: 1.60e-03
+2022-05-14 00:14:53,498 INFO [train.py:812] (1/8) Epoch 4, batch 1100, loss[loss=0.231, simple_loss=0.3121, pruned_loss=0.07492, over 7417.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3038, pruned_loss=0.07847, over 1419742.14 frames.], batch size: 21, lr: 1.60e-03
+2022-05-14 00:15:52,717 INFO [train.py:812] (1/8) Epoch 4, batch 1150, loss[loss=0.2647, simple_loss=0.3265, pruned_loss=0.1015, over 7311.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3056, pruned_loss=0.07947, over 1416978.48 frames.], batch size: 21, lr: 1.60e-03
+2022-05-14 00:16:51,388 INFO [train.py:812] (1/8) Epoch 4, batch 1200, loss[loss=0.1994, simple_loss=0.2809, pruned_loss=0.05891, over 7327.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3071, pruned_loss=0.08028, over 1415558.36 frames.], batch size: 21, lr: 1.60e-03
+2022-05-14 00:17:50,417 INFO [train.py:812] (1/8) Epoch 4, batch 1250, loss[loss=0.2007, simple_loss=0.2765, pruned_loss=0.06241, over 6834.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3062, pruned_loss=0.07934, over 1413398.28 frames.], batch size: 15, lr: 1.59e-03
+2022-05-14 00:18:48,728 INFO [train.py:812] (1/8) Epoch 4, batch 1300, loss[loss=0.2468, simple_loss=0.3205, pruned_loss=0.08654, over 7203.00 frames.], tot_loss[loss=0.232, simple_loss=0.3054, pruned_loss=0.07928, over 1416489.58 frames.], batch size: 23, lr: 1.59e-03
+2022-05-14 00:19:47,565 INFO [train.py:812] (1/8) Epoch 4, batch 1350, loss[loss=0.2347, simple_loss=0.3086, pruned_loss=0.0804, over 7236.00 frames.], tot_loss[loss=0.232, simple_loss=0.3054, pruned_loss=0.0793, over 1415881.39 frames.], batch size: 20, lr: 1.59e-03
+2022-05-14 00:20:44,853 INFO [train.py:812] (1/8) Epoch 4, batch 1400, loss[loss=0.2755, simple_loss=0.3451, pruned_loss=0.103, over 7202.00 frames.], tot_loss[loss=0.231, simple_loss=0.3043, pruned_loss=0.07888, over 1419105.85 frames.], batch size: 22, lr: 1.59e-03
+2022-05-14 00:21:44,660 INFO [train.py:812] (1/8) Epoch 4, batch 1450, loss[loss=0.2671, simple_loss=0.3451, pruned_loss=0.09452, over 7283.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3052, pruned_loss=0.07921, over 1421423.27 frames.], batch size: 24, lr: 1.59e-03
+2022-05-14 00:22:43,713 INFO [train.py:812] (1/8) Epoch 4, batch 1500, loss[loss=0.238, simple_loss=0.3124, pruned_loss=0.08185, over 7283.00 frames.], tot_loss[loss=0.2302, simple_loss=0.3039, pruned_loss=0.07826, over 1418914.64 frames.], batch size: 24, lr: 1.58e-03
+2022-05-14 00:23:43,448 INFO [train.py:812] (1/8) Epoch 4, batch 1550, loss[loss=0.2925, simple_loss=0.3444, pruned_loss=0.1203, over 5179.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3045, pruned_loss=0.07932, over 1418692.22 frames.], batch size: 52, lr: 1.58e-03
+2022-05-14 00:24:41,297 INFO [train.py:812] (1/8) Epoch 4, batch 1600, loss[loss=0.2388, simple_loss=0.3182, pruned_loss=0.07969, over 7284.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3053, pruned_loss=0.07957, over 1415106.12 frames.], batch size: 25, lr: 1.58e-03
+2022-05-14 00:25:40,740 INFO [train.py:812] (1/8) Epoch 4, batch 1650, loss[loss=0.2122, simple_loss=0.2844, pruned_loss=0.07005, over 7335.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3043, pruned_loss=0.07922, over 1416585.01 frames.], batch size: 20, lr: 1.58e-03
+2022-05-14 00:26:39,529 INFO [train.py:812] (1/8) Epoch 4, batch 1700, loss[loss=0.2609, simple_loss=0.3349, pruned_loss=0.09347, over 7145.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3059, pruned_loss=0.07948, over 1420034.04 frames.], batch size: 20, lr: 1.57e-03
+2022-05-14 00:27:38,786 INFO [train.py:812] (1/8) Epoch 4, batch 1750, loss[loss=0.2422, simple_loss=0.318, pruned_loss=0.08319, over 7189.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3061, pruned_loss=0.0795, over 1419275.04 frames.], batch size: 22, lr: 1.57e-03
+2022-05-14 00:28:45,527 INFO [train.py:812] (1/8) Epoch 4, batch 1800, loss[loss=0.2221, simple_loss=0.2957, pruned_loss=0.07427, over 7214.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3062, pruned_loss=0.07932, over 1421138.98 frames.], batch size: 21, lr: 1.57e-03
+2022-05-14 00:29:45,157 INFO [train.py:812] (1/8) Epoch 4, batch 1850, loss[loss=0.2027, simple_loss=0.27, pruned_loss=0.06776, over 7132.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3059, pruned_loss=0.07858, over 1420351.94 frames.], batch size: 17, lr: 1.57e-03
+2022-05-14 00:30:44,399 INFO [train.py:812] (1/8) Epoch 4, batch 1900, loss[loss=0.2335, simple_loss=0.3009, pruned_loss=0.08304, over 7147.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3059, pruned_loss=0.07858, over 1422881.43 frames.], batch size: 19, lr: 1.56e-03
+2022-05-14 00:31:43,796 INFO [train.py:812] (1/8) Epoch 4, batch 1950, loss[loss=0.2404, simple_loss=0.3176, pruned_loss=0.08157, over 6430.00 frames.], tot_loss[loss=0.23, simple_loss=0.3048, pruned_loss=0.07764, over 1427611.72 frames.], batch size: 38, lr: 1.56e-03
+2022-05-14 00:32:40,427 INFO [train.py:812] (1/8) Epoch 4, batch 2000, loss[loss=0.2577, simple_loss=0.3342, pruned_loss=0.09062, over 7104.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3055, pruned_loss=0.07793, over 1424555.70 frames.], batch size: 21, lr: 1.56e-03
+2022-05-14 00:34:15,588 INFO [train.py:812] (1/8) Epoch 4, batch 2050, loss[loss=0.232, simple_loss=0.3018, pruned_loss=0.08111, over 6808.00 frames.], tot_loss[loss=0.2306, simple_loss=0.305, pruned_loss=0.07805, over 1421993.28 frames.], batch size: 31, lr: 1.56e-03
+2022-05-14 00:35:41,820 INFO [train.py:812] (1/8) Epoch 4, batch 2100, loss[loss=0.2469, simple_loss=0.3225, pruned_loss=0.08564, over 7328.00 frames.], tot_loss[loss=0.2286, simple_loss=0.3034, pruned_loss=0.07689, over 1419705.51 frames.], batch size: 21, lr: 1.56e-03
+2022-05-14 00:36:41,410 INFO [train.py:812] (1/8) Epoch 4, batch 2150, loss[loss=0.2458, simple_loss=0.3216, pruned_loss=0.08498, over 7329.00 frames.], tot_loss[loss=0.2281, simple_loss=0.303, pruned_loss=0.07663, over 1422664.25 frames.], batch size: 22, lr: 1.55e-03
+2022-05-14 00:37:40,368 INFO [train.py:812] (1/8) Epoch 4, batch 2200, loss[loss=0.2467, simple_loss=0.3255, pruned_loss=0.08396, over 7222.00 frames.], tot_loss[loss=0.2294, simple_loss=0.3038, pruned_loss=0.07751, over 1425168.67 frames.], batch size: 21, lr: 1.55e-03
+2022-05-14 00:38:47,609 INFO [train.py:812] (1/8) Epoch 4, batch 2250, loss[loss=0.3339, simple_loss=0.3587, pruned_loss=0.1546, over 5252.00 frames.], tot_loss[loss=0.2294, simple_loss=0.3038, pruned_loss=0.07746, over 1427180.95 frames.], batch size: 53, lr: 1.55e-03
+2022-05-14 00:39:45,549 INFO [train.py:812] (1/8) Epoch 4, batch 2300, loss[loss=0.2203, simple_loss=0.2959, pruned_loss=0.07232, over 7159.00 frames.], tot_loss[loss=0.2286, simple_loss=0.3032, pruned_loss=0.07702, over 1430136.19 frames.], batch size: 19, lr: 1.55e-03
+2022-05-14 00:40:45,375 INFO [train.py:812] (1/8) Epoch 4, batch 2350, loss[loss=0.2339, simple_loss=0.3091, pruned_loss=0.07939, over 7338.00 frames.], tot_loss[loss=0.2276, simple_loss=0.3022, pruned_loss=0.07652, over 1430965.29 frames.], batch size: 20, lr: 1.54e-03
+2022-05-14 00:41:44,134 INFO [train.py:812] (1/8) Epoch 4, batch 2400, loss[loss=0.2798, simple_loss=0.3561, pruned_loss=0.1018, over 7295.00 frames.], tot_loss[loss=0.2288, simple_loss=0.3033, pruned_loss=0.07716, over 1433742.83 frames.], batch size: 25, lr: 1.54e-03
+2022-05-14 00:42:43,275 INFO [train.py:812] (1/8) Epoch 4, batch 2450, loss[loss=0.2572, simple_loss=0.3293, pruned_loss=0.09258, over 7378.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3039, pruned_loss=0.0774, over 1436829.21 frames.], batch size: 23, lr: 1.54e-03
+2022-05-14 00:43:42,442 INFO [train.py:812] (1/8) Epoch 4, batch 2500, loss[loss=0.1926, simple_loss=0.2688, pruned_loss=0.0582, over 7160.00 frames.], tot_loss[loss=0.2296, simple_loss=0.304, pruned_loss=0.0776, over 1434337.28 frames.], batch size: 19, lr: 1.54e-03
+2022-05-14 00:44:40,437 INFO [train.py:812] (1/8) Epoch 4, batch 2550, loss[loss=0.2115, simple_loss=0.2836, pruned_loss=0.06969, over 7409.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3047, pruned_loss=0.07804, over 1426063.09 frames.], batch size: 18, lr: 1.54e-03
+2022-05-14 00:45:38,431 INFO [train.py:812] (1/8) Epoch 4, batch 2600, loss[loss=0.251, simple_loss=0.3273, pruned_loss=0.08736, over 7236.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3054, pruned_loss=0.07884, over 1426249.48 frames.], batch size: 20, lr: 1.53e-03
+2022-05-14 00:46:37,709 INFO [train.py:812] (1/8) Epoch 4, batch 2650, loss[loss=0.1967, simple_loss=0.2662, pruned_loss=0.06354, over 7016.00 frames.], tot_loss[loss=0.232, simple_loss=0.306, pruned_loss=0.07896, over 1420387.83 frames.], batch size: 16, lr: 1.53e-03
+2022-05-14 00:47:36,756 INFO [train.py:812] (1/8) Epoch 4, batch 2700, loss[loss=0.1832, simple_loss=0.2619, pruned_loss=0.05222, over 6896.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3057, pruned_loss=0.07832, over 1418436.17 frames.], batch size: 15, lr: 1.53e-03
+2022-05-14 00:48:35,490 INFO [train.py:812] (1/8) Epoch 4, batch 2750, loss[loss=0.237, simple_loss=0.2984, pruned_loss=0.08779, over 7247.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3072, pruned_loss=0.07902, over 1421581.73 frames.], batch size: 19, lr: 1.53e-03
+2022-05-14 00:49:34,107 INFO [train.py:812] (1/8) Epoch 4, batch 2800, loss[loss=0.2356, simple_loss=0.3034, pruned_loss=0.08395, over 7162.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3065, pruned_loss=0.07863, over 1423498.31 frames.], batch size: 19, lr: 1.53e-03
+2022-05-14 00:50:32,968 INFO [train.py:812] (1/8) Epoch 4, batch 2850, loss[loss=0.2555, simple_loss=0.3385, pruned_loss=0.08628, over 4907.00 frames.], tot_loss[loss=0.231, simple_loss=0.3055, pruned_loss=0.07823, over 1421559.45 frames.], batch size: 52, lr: 1.52e-03
+2022-05-14 00:51:31,209 INFO [train.py:812] (1/8) Epoch 4, batch 2900, loss[loss=0.2422, simple_loss=0.3136, pruned_loss=0.0854, over 6902.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3039, pruned_loss=0.07714, over 1422342.17 frames.], batch size: 31, lr: 1.52e-03
+2022-05-14 00:52:31,097 INFO [train.py:812] (1/8) Epoch 4, batch 2950, loss[loss=0.2165, simple_loss=0.3066, pruned_loss=0.06322, over 7088.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3043, pruned_loss=0.07719, over 1426633.37 frames.], batch size: 28, lr: 1.52e-03
+2022-05-14 00:53:30,062 INFO [train.py:812] (1/8) Epoch 4, batch 3000, loss[loss=0.2442, simple_loss=0.3126, pruned_loss=0.08788, over 7155.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3042, pruned_loss=0.07725, over 1424992.96 frames.], batch size: 20, lr: 1.52e-03
+2022-05-14 00:53:30,063 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 00:53:37,752 INFO [train.py:841] (1/8) Epoch 4, validation: loss=0.1771, simple_loss=0.279, pruned_loss=0.03761, over 698248.00 frames.
+2022-05-14 00:54:36,382 INFO [train.py:812] (1/8) Epoch 4, batch 3050, loss[loss=0.229, simple_loss=0.3219, pruned_loss=0.06807, over 7112.00 frames.], tot_loss[loss=0.2297, simple_loss=0.3046, pruned_loss=0.0774, over 1420020.45 frames.], batch size: 21, lr: 1.51e-03
+2022-05-14 00:55:35,285 INFO [train.py:812] (1/8) Epoch 4, batch 3100, loss[loss=0.2073, simple_loss=0.2832, pruned_loss=0.06574, over 7284.00 frames.], tot_loss[loss=0.2284, simple_loss=0.3032, pruned_loss=0.07681, over 1416957.91 frames.], batch size: 24, lr: 1.51e-03
+2022-05-14 00:56:35,138 INFO [train.py:812] (1/8) Epoch 4, batch 3150, loss[loss=0.2109, simple_loss=0.3001, pruned_loss=0.06079, over 7288.00 frames.], tot_loss[loss=0.2284, simple_loss=0.3028, pruned_loss=0.07702, over 1421762.09 frames.], batch size: 25, lr: 1.51e-03
+2022-05-14 00:57:33,591 INFO [train.py:812] (1/8) Epoch 4, batch 3200, loss[loss=0.1804, simple_loss=0.265, pruned_loss=0.04792, over 7062.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3011, pruned_loss=0.07576, over 1423417.24 frames.], batch size: 18, lr: 1.51e-03
+2022-05-14 00:58:32,691 INFO [train.py:812] (1/8) Epoch 4, batch 3250, loss[loss=0.2065, simple_loss=0.2784, pruned_loss=0.06732, over 7258.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3012, pruned_loss=0.07547, over 1424017.21 frames.], batch size: 19, lr: 1.51e-03
+2022-05-14 00:59:30,508 INFO [train.py:812] (1/8) Epoch 4, batch 3300, loss[loss=0.2425, simple_loss=0.3087, pruned_loss=0.08818, over 7211.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3018, pruned_loss=0.07525, over 1422983.11 frames.], batch size: 23, lr: 1.50e-03
+2022-05-14 01:00:29,645 INFO [train.py:812] (1/8) Epoch 4, batch 3350, loss[loss=0.2998, simple_loss=0.3658, pruned_loss=0.1169, over 6395.00 frames.], tot_loss[loss=0.2257, simple_loss=0.301, pruned_loss=0.07519, over 1420480.08 frames.], batch size: 38, lr: 1.50e-03
+2022-05-14 01:01:28,325 INFO [train.py:812] (1/8) Epoch 4, batch 3400, loss[loss=0.1839, simple_loss=0.2615, pruned_loss=0.0531, over 7014.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3017, pruned_loss=0.07606, over 1421350.32 frames.], batch size: 16, lr: 1.50e-03
+2022-05-14 01:02:28,057 INFO [train.py:812] (1/8) Epoch 4, batch 3450, loss[loss=0.2294, simple_loss=0.2921, pruned_loss=0.0833, over 7164.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3015, pruned_loss=0.07601, over 1426106.72 frames.], batch size: 18, lr: 1.50e-03
+2022-05-14 01:03:26,380 INFO [train.py:812] (1/8) Epoch 4, batch 3500, loss[loss=0.2283, simple_loss=0.3083, pruned_loss=0.07413, over 7390.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3005, pruned_loss=0.07584, over 1427754.15 frames.], batch size: 23, lr: 1.50e-03
+2022-05-14 01:04:26,019 INFO [train.py:812] (1/8) Epoch 4, batch 3550, loss[loss=0.2443, simple_loss=0.3105, pruned_loss=0.089, over 7302.00 frames.], tot_loss[loss=0.2257, simple_loss=0.2996, pruned_loss=0.07591, over 1428778.04 frames.], batch size: 24, lr: 1.49e-03
+2022-05-14 01:05:25,248 INFO [train.py:812] (1/8) Epoch 4, batch 3600, loss[loss=0.1711, simple_loss=0.2488, pruned_loss=0.04673, over 6991.00 frames.], tot_loss[loss=0.225, simple_loss=0.2993, pruned_loss=0.07534, over 1426968.04 frames.], batch size: 16, lr: 1.49e-03
+2022-05-14 01:06:24,745 INFO [train.py:812] (1/8) Epoch 4, batch 3650, loss[loss=0.1703, simple_loss=0.2473, pruned_loss=0.0466, over 7121.00 frames.], tot_loss[loss=0.2252, simple_loss=0.2997, pruned_loss=0.0754, over 1427523.23 frames.], batch size: 17, lr: 1.49e-03
+2022-05-14 01:07:24,233 INFO [train.py:812] (1/8) Epoch 4, batch 3700, loss[loss=0.2058, simple_loss=0.2677, pruned_loss=0.072, over 6986.00 frames.], tot_loss[loss=0.224, simple_loss=0.2986, pruned_loss=0.07467, over 1427952.54 frames.], batch size: 16, lr: 1.49e-03
+2022-05-14 01:08:24,378 INFO [train.py:812] (1/8) Epoch 4, batch 3750, loss[loss=0.1984, simple_loss=0.2826, pruned_loss=0.05716, over 7434.00 frames.], tot_loss[loss=0.223, simple_loss=0.2977, pruned_loss=0.07416, over 1425771.64 frames.], batch size: 20, lr: 1.49e-03
+2022-05-14 01:09:22,773 INFO [train.py:812] (1/8) Epoch 4, batch 3800, loss[loss=0.2272, simple_loss=0.297, pruned_loss=0.07874, over 7056.00 frames.], tot_loss[loss=0.223, simple_loss=0.2977, pruned_loss=0.07416, over 1421738.53 frames.], batch size: 18, lr: 1.48e-03
+2022-05-14 01:10:22,613 INFO [train.py:812] (1/8) Epoch 4, batch 3850, loss[loss=0.2145, simple_loss=0.2837, pruned_loss=0.0727, over 7415.00 frames.], tot_loss[loss=0.2229, simple_loss=0.2977, pruned_loss=0.07406, over 1425551.86 frames.], batch size: 18, lr: 1.48e-03
+2022-05-14 01:11:21,434 INFO [train.py:812] (1/8) Epoch 4, batch 3900, loss[loss=0.265, simple_loss=0.3207, pruned_loss=0.1047, over 5259.00 frames.], tot_loss[loss=0.2229, simple_loss=0.2982, pruned_loss=0.0738, over 1426511.91 frames.], batch size: 52, lr: 1.48e-03
+2022-05-14 01:12:20,483 INFO [train.py:812] (1/8) Epoch 4, batch 3950, loss[loss=0.2032, simple_loss=0.2762, pruned_loss=0.06508, over 6873.00 frames.], tot_loss[loss=0.222, simple_loss=0.2975, pruned_loss=0.07327, over 1425781.25 frames.], batch size: 15, lr: 1.48e-03
+2022-05-14 01:13:19,408 INFO [train.py:812] (1/8) Epoch 4, batch 4000, loss[loss=0.2614, simple_loss=0.3264, pruned_loss=0.09821, over 7218.00 frames.], tot_loss[loss=0.2235, simple_loss=0.2984, pruned_loss=0.07433, over 1418862.62 frames.], batch size: 21, lr: 1.48e-03
+2022-05-14 01:14:18,989 INFO [train.py:812] (1/8) Epoch 4, batch 4050, loss[loss=0.2054, simple_loss=0.2891, pruned_loss=0.06081, over 7401.00 frames.], tot_loss[loss=0.2243, simple_loss=0.2993, pruned_loss=0.07461, over 1420603.36 frames.], batch size: 21, lr: 1.47e-03
+2022-05-14 01:15:18,242 INFO [train.py:812] (1/8) Epoch 4, batch 4100, loss[loss=0.2465, simple_loss=0.3198, pruned_loss=0.08664, over 6342.00 frames.], tot_loss[loss=0.2249, simple_loss=0.2998, pruned_loss=0.07495, over 1422178.69 frames.], batch size: 38, lr: 1.47e-03
+2022-05-14 01:16:17,168 INFO [train.py:812] (1/8) Epoch 4, batch 4150, loss[loss=0.197, simple_loss=0.2721, pruned_loss=0.06093, over 6993.00 frames.], tot_loss[loss=0.2232, simple_loss=0.2986, pruned_loss=0.07388, over 1423879.77 frames.], batch size: 16, lr: 1.47e-03
+2022-05-14 01:17:15,919 INFO [train.py:812] (1/8) Epoch 4, batch 4200, loss[loss=0.213, simple_loss=0.2951, pruned_loss=0.06547, over 7167.00 frames.], tot_loss[loss=0.2231, simple_loss=0.2983, pruned_loss=0.07394, over 1422892.01 frames.], batch size: 19, lr: 1.47e-03
+2022-05-14 01:18:15,836 INFO [train.py:812] (1/8) Epoch 4, batch 4250, loss[loss=0.2047, simple_loss=0.28, pruned_loss=0.06469, over 7361.00 frames.], tot_loss[loss=0.2242, simple_loss=0.2989, pruned_loss=0.07477, over 1415323.13 frames.], batch size: 19, lr: 1.47e-03
+2022-05-14 01:19:14,763 INFO [train.py:812] (1/8) Epoch 4, batch 4300, loss[loss=0.2223, simple_loss=0.2949, pruned_loss=0.07484, over 7361.00 frames.], tot_loss[loss=0.2244, simple_loss=0.2983, pruned_loss=0.0753, over 1412927.55 frames.], batch size: 19, lr: 1.47e-03
+2022-05-14 01:20:14,302 INFO [train.py:812] (1/8) Epoch 4, batch 4350, loss[loss=0.24, simple_loss=0.3193, pruned_loss=0.08028, over 6353.00 frames.], tot_loss[loss=0.2236, simple_loss=0.2973, pruned_loss=0.07496, over 1411862.01 frames.], batch size: 38, lr: 1.46e-03
+2022-05-14 01:21:13,824 INFO [train.py:812] (1/8) Epoch 4, batch 4400, loss[loss=0.2238, simple_loss=0.2892, pruned_loss=0.07923, over 7070.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2962, pruned_loss=0.0746, over 1410272.60 frames.], batch size: 18, lr: 1.46e-03
+2022-05-14 01:22:13,438 INFO [train.py:812] (1/8) Epoch 4, batch 4450, loss[loss=0.2417, simple_loss=0.3076, pruned_loss=0.08789, over 7375.00 frames.], tot_loss[loss=0.2228, simple_loss=0.296, pruned_loss=0.07483, over 1401372.11 frames.], batch size: 23, lr: 1.46e-03
+2022-05-14 01:23:11,881 INFO [train.py:812] (1/8) Epoch 4, batch 4500, loss[loss=0.2404, simple_loss=0.3156, pruned_loss=0.08256, over 6361.00 frames.], tot_loss[loss=0.2228, simple_loss=0.2961, pruned_loss=0.07473, over 1396718.25 frames.], batch size: 38, lr: 1.46e-03
+2022-05-14 01:24:10,629 INFO [train.py:812] (1/8) Epoch 4, batch 4550, loss[loss=0.2611, simple_loss=0.3219, pruned_loss=0.1001, over 4813.00 frames.], tot_loss[loss=0.227, simple_loss=0.2999, pruned_loss=0.07705, over 1361284.86 frames.], batch size: 52, lr: 1.46e-03
+2022-05-14 01:25:17,915 INFO [train.py:812] (1/8) Epoch 5, batch 0, loss[loss=0.2541, simple_loss=0.3311, pruned_loss=0.08856, over 7219.00 frames.], tot_loss[loss=0.2541, simple_loss=0.3311, pruned_loss=0.08856, over 7219.00 frames.], batch size: 23, lr: 1.40e-03
+2022-05-14 01:26:16,017 INFO [train.py:812] (1/8) Epoch 5, batch 50, loss[loss=0.2611, simple_loss=0.3335, pruned_loss=0.09437, over 7332.00 frames.], tot_loss[loss=0.2199, simple_loss=0.296, pruned_loss=0.07186, over 320073.33 frames.], batch size: 22, lr: 1.40e-03
+2022-05-14 01:27:13,774 INFO [train.py:812] (1/8) Epoch 5, batch 100, loss[loss=0.2247, simple_loss=0.3057, pruned_loss=0.07188, over 7329.00 frames.], tot_loss[loss=0.222, simple_loss=0.2985, pruned_loss=0.07276, over 565739.41 frames.], batch size: 22, lr: 1.40e-03
+2022-05-14 01:28:13,019 INFO [train.py:812] (1/8) Epoch 5, batch 150, loss[loss=0.2507, simple_loss=0.3214, pruned_loss=0.09, over 5177.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3004, pruned_loss=0.07338, over 755112.75 frames.], batch size: 52, lr: 1.40e-03
+2022-05-14 01:29:12,393 INFO [train.py:812] (1/8) Epoch 5, batch 200, loss[loss=0.1971, simple_loss=0.2755, pruned_loss=0.05931, over 7160.00 frames.], tot_loss[loss=0.2244, simple_loss=0.3006, pruned_loss=0.07406, over 903790.45 frames.], batch size: 19, lr: 1.40e-03
+2022-05-14 01:30:11,969 INFO [train.py:812] (1/8) Epoch 5, batch 250, loss[loss=0.2247, simple_loss=0.3005, pruned_loss=0.07445, over 7342.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3016, pruned_loss=0.07379, over 1020946.87 frames.], batch size: 22, lr: 1.39e-03
+2022-05-14 01:31:10,334 INFO [train.py:812] (1/8) Epoch 5, batch 300, loss[loss=0.1838, simple_loss=0.2601, pruned_loss=0.05379, over 7263.00 frames.], tot_loss[loss=0.2217, simple_loss=0.2988, pruned_loss=0.07236, over 1112815.92 frames.], batch size: 17, lr: 1.39e-03
+2022-05-14 01:32:09,245 INFO [train.py:812] (1/8) Epoch 5, batch 350, loss[loss=0.1786, simple_loss=0.2588, pruned_loss=0.04915, over 7163.00 frames.], tot_loss[loss=0.2201, simple_loss=0.297, pruned_loss=0.07166, over 1180612.06 frames.], batch size: 19, lr: 1.39e-03
+2022-05-14 01:33:06,931 INFO [train.py:812] (1/8) Epoch 5, batch 400, loss[loss=0.2633, simple_loss=0.3393, pruned_loss=0.09363, over 7151.00 frames.], tot_loss[loss=0.2204, simple_loss=0.2972, pruned_loss=0.07186, over 1231527.01 frames.], batch size: 28, lr: 1.39e-03
+2022-05-14 01:34:05,731 INFO [train.py:812] (1/8) Epoch 5, batch 450, loss[loss=0.2348, simple_loss=0.3072, pruned_loss=0.08114, over 7032.00 frames.], tot_loss[loss=0.2193, simple_loss=0.2961, pruned_loss=0.07126, over 1273668.68 frames.], batch size: 28, lr: 1.39e-03
+2022-05-14 01:35:05,166 INFO [train.py:812] (1/8) Epoch 5, batch 500, loss[loss=0.2355, simple_loss=0.3133, pruned_loss=0.07885, over 7320.00 frames.], tot_loss[loss=0.2182, simple_loss=0.2951, pruned_loss=0.07067, over 1309304.18 frames.], batch size: 21, lr: 1.39e-03
+2022-05-14 01:36:04,757 INFO [train.py:812] (1/8) Epoch 5, batch 550, loss[loss=0.2451, simple_loss=0.3171, pruned_loss=0.08657, over 6867.00 frames.], tot_loss[loss=0.2183, simple_loss=0.2952, pruned_loss=0.07065, over 1334117.86 frames.], batch size: 31, lr: 1.38e-03
+2022-05-14 01:37:04,106 INFO [train.py:812] (1/8) Epoch 5, batch 600, loss[loss=0.2141, simple_loss=0.2867, pruned_loss=0.07078, over 7016.00 frames.], tot_loss[loss=0.2175, simple_loss=0.2946, pruned_loss=0.07023, over 1356421.20 frames.], batch size: 16, lr: 1.38e-03
+2022-05-14 01:38:03,180 INFO [train.py:812] (1/8) Epoch 5, batch 650, loss[loss=0.2239, simple_loss=0.3011, pruned_loss=0.07333, over 7346.00 frames.], tot_loss[loss=0.2183, simple_loss=0.2954, pruned_loss=0.07057, over 1371352.69 frames.], batch size: 20, lr: 1.38e-03
+2022-05-14 01:39:02,103 INFO [train.py:812] (1/8) Epoch 5, batch 700, loss[loss=0.2577, simple_loss=0.3395, pruned_loss=0.08794, over 7302.00 frames.], tot_loss[loss=0.218, simple_loss=0.2951, pruned_loss=0.07041, over 1380177.13 frames.], batch size: 25, lr: 1.38e-03
+2022-05-14 01:40:01,972 INFO [train.py:812] (1/8) Epoch 5, batch 750, loss[loss=0.1901, simple_loss=0.2671, pruned_loss=0.05654, over 7074.00 frames.], tot_loss[loss=0.2177, simple_loss=0.2947, pruned_loss=0.07031, over 1384890.53 frames.], batch size: 18, lr: 1.38e-03
+2022-05-14 01:40:59,762 INFO [train.py:812] (1/8) Epoch 5, batch 800, loss[loss=0.1912, simple_loss=0.2647, pruned_loss=0.05882, over 7439.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2937, pruned_loss=0.07022, over 1397339.51 frames.], batch size: 19, lr: 1.38e-03
+2022-05-14 01:41:57,356 INFO [train.py:812] (1/8) Epoch 5, batch 850, loss[loss=0.1805, simple_loss=0.259, pruned_loss=0.05098, over 7056.00 frames.], tot_loss[loss=0.2167, simple_loss=0.2934, pruned_loss=0.06996, over 1396060.26 frames.], batch size: 18, lr: 1.37e-03
+2022-05-14 01:42:55,835 INFO [train.py:812] (1/8) Epoch 5, batch 900, loss[loss=0.2197, simple_loss=0.297, pruned_loss=0.07114, over 7323.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2927, pruned_loss=0.06947, over 1403146.39 frames.], batch size: 21, lr: 1.37e-03
+2022-05-14 01:43:53,341 INFO [train.py:812] (1/8) Epoch 5, batch 950, loss[loss=0.2338, simple_loss=0.3146, pruned_loss=0.07643, over 7088.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2935, pruned_loss=0.06982, over 1407590.14 frames.], batch size: 28, lr: 1.37e-03
+2022-05-14 01:44:52,019 INFO [train.py:812] (1/8) Epoch 5, batch 1000, loss[loss=0.2101, simple_loss=0.2854, pruned_loss=0.06737, over 7063.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2928, pruned_loss=0.06985, over 1411584.36 frames.], batch size: 18, lr: 1.37e-03
+2022-05-14 01:45:49,417 INFO [train.py:812] (1/8) Epoch 5, batch 1050, loss[loss=0.2538, simple_loss=0.326, pruned_loss=0.09079, over 7297.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2933, pruned_loss=0.06979, over 1416839.94 frames.], batch size: 24, lr: 1.37e-03
+2022-05-14 01:46:47,345 INFO [train.py:812] (1/8) Epoch 5, batch 1100, loss[loss=0.1923, simple_loss=0.2809, pruned_loss=0.05183, over 6393.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2944, pruned_loss=0.07022, over 1412044.86 frames.], batch size: 38, lr: 1.37e-03
+2022-05-14 01:47:47,039 INFO [train.py:812] (1/8) Epoch 5, batch 1150, loss[loss=0.2898, simple_loss=0.3564, pruned_loss=0.1116, over 7427.00 frames.], tot_loss[loss=0.2179, simple_loss=0.2952, pruned_loss=0.07036, over 1414533.08 frames.], batch size: 20, lr: 1.36e-03
+2022-05-14 01:48:45,950 INFO [train.py:812] (1/8) Epoch 5, batch 1200, loss[loss=0.2404, simple_loss=0.3141, pruned_loss=0.08331, over 6613.00 frames.], tot_loss[loss=0.2179, simple_loss=0.295, pruned_loss=0.07047, over 1416958.57 frames.], batch size: 38, lr: 1.36e-03
+2022-05-14 01:49:45,443 INFO [train.py:812] (1/8) Epoch 5, batch 1250, loss[loss=0.1973, simple_loss=0.2628, pruned_loss=0.06587, over 7261.00 frames.], tot_loss[loss=0.2189, simple_loss=0.2955, pruned_loss=0.0712, over 1412935.82 frames.], batch size: 19, lr: 1.36e-03
+2022-05-14 01:50:43,659 INFO [train.py:812] (1/8) Epoch 5, batch 1300, loss[loss=0.2493, simple_loss=0.3091, pruned_loss=0.09482, over 7339.00 frames.], tot_loss[loss=0.2188, simple_loss=0.2955, pruned_loss=0.07102, over 1416480.10 frames.], batch size: 20, lr: 1.36e-03
+2022-05-14 01:51:42,397 INFO [train.py:812] (1/8) Epoch 5, batch 1350, loss[loss=0.1848, simple_loss=0.2624, pruned_loss=0.05362, over 7142.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2956, pruned_loss=0.07089, over 1423089.72 frames.], batch size: 17, lr: 1.36e-03
+2022-05-14 01:52:39,815 INFO [train.py:812] (1/8) Epoch 5, batch 1400, loss[loss=0.2364, simple_loss=0.3166, pruned_loss=0.07813, over 7228.00 frames.], tot_loss[loss=0.22, simple_loss=0.2972, pruned_loss=0.07137, over 1418631.55 frames.], batch size: 20, lr: 1.36e-03
+2022-05-14 01:53:37,454 INFO [train.py:812] (1/8) Epoch 5, batch 1450, loss[loss=0.1672, simple_loss=0.2485, pruned_loss=0.04295, over 7013.00 frames.], tot_loss[loss=0.2192, simple_loss=0.2964, pruned_loss=0.07101, over 1419291.81 frames.], batch size: 16, lr: 1.35e-03
+2022-05-14 01:54:35,093 INFO [train.py:812] (1/8) Epoch 5, batch 1500, loss[loss=0.2218, simple_loss=0.3001, pruned_loss=0.0717, over 7322.00 frames.], tot_loss[loss=0.2186, simple_loss=0.2957, pruned_loss=0.07072, over 1422485.58 frames.], batch size: 20, lr: 1.35e-03
+2022-05-14 01:55:34,685 INFO [train.py:812] (1/8) Epoch 5, batch 1550, loss[loss=0.2144, simple_loss=0.2924, pruned_loss=0.06817, over 7390.00 frames.], tot_loss[loss=0.218, simple_loss=0.2947, pruned_loss=0.07065, over 1424399.24 frames.], batch size: 23, lr: 1.35e-03
+2022-05-14 01:56:33,042 INFO [train.py:812] (1/8) Epoch 5, batch 1600, loss[loss=0.2505, simple_loss=0.3269, pruned_loss=0.08703, over 7328.00 frames.], tot_loss[loss=0.2185, simple_loss=0.2953, pruned_loss=0.07081, over 1423761.44 frames.], batch size: 25, lr: 1.35e-03
+2022-05-14 01:57:37,110 INFO [train.py:812] (1/8) Epoch 5, batch 1650, loss[loss=0.2344, simple_loss=0.3161, pruned_loss=0.07633, over 7119.00 frames.], tot_loss[loss=0.2183, simple_loss=0.2952, pruned_loss=0.07072, over 1421669.50 frames.], batch size: 21, lr: 1.35e-03
+2022-05-14 01:58:36,674 INFO [train.py:812] (1/8) Epoch 5, batch 1700, loss[loss=0.198, simple_loss=0.2811, pruned_loss=0.05747, over 7336.00 frames.], tot_loss[loss=0.2176, simple_loss=0.2945, pruned_loss=0.0704, over 1423547.66 frames.], batch size: 22, lr: 1.35e-03
+2022-05-14 01:59:35,629 INFO [train.py:812] (1/8) Epoch 5, batch 1750, loss[loss=0.2423, simple_loss=0.3202, pruned_loss=0.08217, over 7312.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2934, pruned_loss=0.06966, over 1423008.82 frames.], batch size: 24, lr: 1.34e-03
+2022-05-14 02:00:34,959 INFO [train.py:812] (1/8) Epoch 5, batch 1800, loss[loss=0.2387, simple_loss=0.3179, pruned_loss=0.07974, over 7330.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2935, pruned_loss=0.06937, over 1425923.29 frames.], batch size: 21, lr: 1.34e-03
+2022-05-14 02:01:33,482 INFO [train.py:812] (1/8) Epoch 5, batch 1850, loss[loss=0.254, simple_loss=0.327, pruned_loss=0.09047, over 6376.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2941, pruned_loss=0.06921, over 1425865.09 frames.], batch size: 38, lr: 1.34e-03
+2022-05-14 02:02:31,902 INFO [train.py:812] (1/8) Epoch 5, batch 1900, loss[loss=0.2046, simple_loss=0.2882, pruned_loss=0.06049, over 7124.00 frames.], tot_loss[loss=0.2169, simple_loss=0.2947, pruned_loss=0.06961, over 1427089.87 frames.], batch size: 21, lr: 1.34e-03
+2022-05-14 02:03:30,587 INFO [train.py:812] (1/8) Epoch 5, batch 1950, loss[loss=0.1977, simple_loss=0.2752, pruned_loss=0.06007, over 7159.00 frames.], tot_loss[loss=0.2162, simple_loss=0.294, pruned_loss=0.06922, over 1427423.92 frames.], batch size: 18, lr: 1.34e-03
+2022-05-14 02:04:28,244 INFO [train.py:812] (1/8) Epoch 5, batch 2000, loss[loss=0.245, simple_loss=0.3216, pruned_loss=0.08427, over 7319.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2939, pruned_loss=0.06927, over 1425019.82 frames.], batch size: 25, lr: 1.34e-03
+2022-05-14 02:05:26,862 INFO [train.py:812] (1/8) Epoch 5, batch 2050, loss[loss=0.2211, simple_loss=0.3007, pruned_loss=0.07074, over 7303.00 frames.], tot_loss[loss=0.2147, simple_loss=0.2929, pruned_loss=0.06821, over 1429780.26 frames.], batch size: 24, lr: 1.34e-03
+2022-05-14 02:06:25,383 INFO [train.py:812] (1/8) Epoch 5, batch 2100, loss[loss=0.1821, simple_loss=0.2523, pruned_loss=0.05595, over 7405.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2921, pruned_loss=0.06818, over 1433213.65 frames.], batch size: 18, lr: 1.33e-03
+2022-05-14 02:07:23,976 INFO [train.py:812] (1/8) Epoch 5, batch 2150, loss[loss=0.208, simple_loss=0.2876, pruned_loss=0.06419, over 7055.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2933, pruned_loss=0.06879, over 1432593.82 frames.], batch size: 18, lr: 1.33e-03
+2022-05-14 02:08:21,802 INFO [train.py:812] (1/8) Epoch 5, batch 2200, loss[loss=0.2268, simple_loss=0.322, pruned_loss=0.06582, over 7319.00 frames.], tot_loss[loss=0.215, simple_loss=0.2929, pruned_loss=0.0686, over 1434404.43 frames.], batch size: 22, lr: 1.33e-03
+2022-05-14 02:09:20,790 INFO [train.py:812] (1/8) Epoch 5, batch 2250, loss[loss=0.2258, simple_loss=0.3049, pruned_loss=0.07338, over 7369.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2936, pruned_loss=0.06938, over 1431264.17 frames.], batch size: 23, lr: 1.33e-03
+2022-05-14 02:10:20,193 INFO [train.py:812] (1/8) Epoch 5, batch 2300, loss[loss=0.1725, simple_loss=0.2452, pruned_loss=0.04991, over 7272.00 frames.], tot_loss[loss=0.215, simple_loss=0.2926, pruned_loss=0.06869, over 1429211.85 frames.], batch size: 17, lr: 1.33e-03
+2022-05-14 02:11:18,990 INFO [train.py:812] (1/8) Epoch 5, batch 2350, loss[loss=0.1886, simple_loss=0.2649, pruned_loss=0.05617, over 7403.00 frames.], tot_loss[loss=0.2144, simple_loss=0.2928, pruned_loss=0.06798, over 1432598.51 frames.], batch size: 18, lr: 1.33e-03
+2022-05-14 02:12:18,588 INFO [train.py:812] (1/8) Epoch 5, batch 2400, loss[loss=0.2129, simple_loss=0.2947, pruned_loss=0.06554, over 7220.00 frames.], tot_loss[loss=0.2154, simple_loss=0.293, pruned_loss=0.06889, over 1433935.80 frames.], batch size: 21, lr: 1.32e-03
+2022-05-14 02:13:16,799 INFO [train.py:812] (1/8) Epoch 5, batch 2450, loss[loss=0.1728, simple_loss=0.2529, pruned_loss=0.04639, over 7276.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2922, pruned_loss=0.06838, over 1434063.01 frames.], batch size: 18, lr: 1.32e-03
+2022-05-14 02:14:14,129 INFO [train.py:812] (1/8) Epoch 5, batch 2500, loss[loss=0.2375, simple_loss=0.313, pruned_loss=0.08096, over 7211.00 frames.], tot_loss[loss=0.215, simple_loss=0.2924, pruned_loss=0.0688, over 1432300.18 frames.], batch size: 22, lr: 1.32e-03
+2022-05-14 02:15:13,117 INFO [train.py:812] (1/8) Epoch 5, batch 2550, loss[loss=0.1846, simple_loss=0.2828, pruned_loss=0.04315, over 7141.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2934, pruned_loss=0.06947, over 1432839.10 frames.], batch size: 20, lr: 1.32e-03
+2022-05-14 02:16:11,202 INFO [train.py:812] (1/8) Epoch 5, batch 2600, loss[loss=0.2441, simple_loss=0.3012, pruned_loss=0.09353, over 7318.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2932, pruned_loss=0.0691, over 1431344.48 frames.], batch size: 21, lr: 1.32e-03
+2022-05-14 02:17:10,911 INFO [train.py:812] (1/8) Epoch 5, batch 2650, loss[loss=0.1751, simple_loss=0.2482, pruned_loss=0.05094, over 7002.00 frames.], tot_loss[loss=0.2155, simple_loss=0.293, pruned_loss=0.06897, over 1429900.07 frames.], batch size: 16, lr: 1.32e-03
+2022-05-14 02:18:10,457 INFO [train.py:812] (1/8) Epoch 5, batch 2700, loss[loss=0.1962, simple_loss=0.2732, pruned_loss=0.05958, over 7275.00 frames.], tot_loss[loss=0.2151, simple_loss=0.293, pruned_loss=0.06863, over 1432007.89 frames.], batch size: 18, lr: 1.32e-03
+2022-05-14 02:19:10,224 INFO [train.py:812] (1/8) Epoch 5, batch 2750, loss[loss=0.2568, simple_loss=0.3247, pruned_loss=0.09446, over 7362.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2929, pruned_loss=0.06866, over 1432458.70 frames.], batch size: 19, lr: 1.31e-03
+2022-05-14 02:20:09,511 INFO [train.py:812] (1/8) Epoch 5, batch 2800, loss[loss=0.1888, simple_loss=0.2496, pruned_loss=0.06403, over 7133.00 frames.], tot_loss[loss=0.2134, simple_loss=0.2914, pruned_loss=0.06765, over 1433152.61 frames.], batch size: 17, lr: 1.31e-03
+2022-05-14 02:21:07,409 INFO [train.py:812] (1/8) Epoch 5, batch 2850, loss[loss=0.2094, simple_loss=0.2898, pruned_loss=0.06457, over 6770.00 frames.], tot_loss[loss=0.2138, simple_loss=0.2919, pruned_loss=0.06786, over 1430148.58 frames.], batch size: 31, lr: 1.31e-03
+2022-05-14 02:22:06,256 INFO [train.py:812] (1/8) Epoch 5, batch 2900, loss[loss=0.2119, simple_loss=0.3039, pruned_loss=0.05999, over 7285.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2931, pruned_loss=0.06825, over 1427900.91 frames.], batch size: 24, lr: 1.31e-03
+2022-05-14 02:23:05,636 INFO [train.py:812] (1/8) Epoch 5, batch 2950, loss[loss=0.214, simple_loss=0.2985, pruned_loss=0.06479, over 7330.00 frames.], tot_loss[loss=0.2143, simple_loss=0.292, pruned_loss=0.0683, over 1428153.68 frames.], batch size: 22, lr: 1.31e-03
+2022-05-14 02:24:04,419 INFO [train.py:812] (1/8) Epoch 5, batch 3000, loss[loss=0.2519, simple_loss=0.327, pruned_loss=0.08841, over 7181.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2925, pruned_loss=0.06853, over 1423922.29 frames.], batch size: 26, lr: 1.31e-03
+2022-05-14 02:24:04,420 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 02:24:12,111 INFO [train.py:841] (1/8) Epoch 5, validation: loss=0.1705, simple_loss=0.2732, pruned_loss=0.03391, over 698248.00 frames.
+2022-05-14 02:25:11,803 INFO [train.py:812] (1/8) Epoch 5, batch 3050, loss[loss=0.1964, simple_loss=0.2762, pruned_loss=0.05828, over 7212.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2928, pruned_loss=0.0684, over 1428509.47 frames.], batch size: 22, lr: 1.31e-03
+2022-05-14 02:26:09,567 INFO [train.py:812] (1/8) Epoch 5, batch 3100, loss[loss=0.2108, simple_loss=0.3008, pruned_loss=0.06044, over 7231.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2931, pruned_loss=0.06825, over 1427172.44 frames.], batch size: 20, lr: 1.30e-03
+2022-05-14 02:27:19,079 INFO [train.py:812] (1/8) Epoch 5, batch 3150, loss[loss=0.1981, simple_loss=0.2861, pruned_loss=0.05502, over 7339.00 frames.], tot_loss[loss=0.215, simple_loss=0.2932, pruned_loss=0.06839, over 1428005.72 frames.], batch size: 25, lr: 1.30e-03
+2022-05-14 02:28:18,316 INFO [train.py:812] (1/8) Epoch 5, batch 3200, loss[loss=0.1968, simple_loss=0.2788, pruned_loss=0.05745, over 7358.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2932, pruned_loss=0.06849, over 1429029.60 frames.], batch size: 19, lr: 1.30e-03
+2022-05-14 02:29:17,244 INFO [train.py:812] (1/8) Epoch 5, batch 3250, loss[loss=0.2106, simple_loss=0.2865, pruned_loss=0.06739, over 7163.00 frames.], tot_loss[loss=0.2151, simple_loss=0.293, pruned_loss=0.06865, over 1427935.95 frames.], batch size: 18, lr: 1.30e-03
+2022-05-14 02:30:15,402 INFO [train.py:812] (1/8) Epoch 5, batch 3300, loss[loss=0.2221, simple_loss=0.3161, pruned_loss=0.06411, over 7194.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2944, pruned_loss=0.06959, over 1422730.14 frames.], batch size: 26, lr: 1.30e-03
+2022-05-14 02:31:14,128 INFO [train.py:812] (1/8) Epoch 5, batch 3350, loss[loss=0.2506, simple_loss=0.3289, pruned_loss=0.08621, over 7121.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2937, pruned_loss=0.06854, over 1425511.06 frames.], batch size: 21, lr: 1.30e-03
+2022-05-14 02:32:12,537 INFO [train.py:812] (1/8) Epoch 5, batch 3400, loss[loss=0.2105, simple_loss=0.2981, pruned_loss=0.06148, over 7240.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2937, pruned_loss=0.06824, over 1427538.80 frames.], batch size: 20, lr: 1.30e-03
+2022-05-14 02:33:11,746 INFO [train.py:812] (1/8) Epoch 5, batch 3450, loss[loss=0.1935, simple_loss=0.2789, pruned_loss=0.05404, over 7204.00 frames.], tot_loss[loss=0.2143, simple_loss=0.2926, pruned_loss=0.06805, over 1428236.41 frames.], batch size: 23, lr: 1.29e-03
+2022-05-14 02:34:10,771 INFO [train.py:812] (1/8) Epoch 5, batch 3500, loss[loss=0.1915, simple_loss=0.279, pruned_loss=0.05201, over 7320.00 frames.], tot_loss[loss=0.214, simple_loss=0.2926, pruned_loss=0.06772, over 1430101.21 frames.], batch size: 20, lr: 1.29e-03
+2022-05-14 02:35:38,307 INFO [train.py:812] (1/8) Epoch 5, batch 3550, loss[loss=0.2056, simple_loss=0.2878, pruned_loss=0.06171, over 7412.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2916, pruned_loss=0.06723, over 1424716.25 frames.], batch size: 21, lr: 1.29e-03
+2022-05-14 02:36:46,047 INFO [train.py:812] (1/8) Epoch 5, batch 3600, loss[loss=0.1778, simple_loss=0.2727, pruned_loss=0.04143, over 7256.00 frames.], tot_loss[loss=0.2127, simple_loss=0.2911, pruned_loss=0.06717, over 1421194.79 frames.], batch size: 19, lr: 1.29e-03
+2022-05-14 02:38:13,280 INFO [train.py:812] (1/8) Epoch 5, batch 3650, loss[loss=0.2198, simple_loss=0.2941, pruned_loss=0.07271, over 6766.00 frames.], tot_loss[loss=0.2147, simple_loss=0.2929, pruned_loss=0.06821, over 1415252.57 frames.], batch size: 31, lr: 1.29e-03
+2022-05-14 02:39:12,928 INFO [train.py:812] (1/8) Epoch 5, batch 3700, loss[loss=0.2164, simple_loss=0.2826, pruned_loss=0.07506, over 7166.00 frames.], tot_loss[loss=0.213, simple_loss=0.2908, pruned_loss=0.06761, over 1419305.65 frames.], batch size: 18, lr: 1.29e-03
+2022-05-14 02:40:11,639 INFO [train.py:812] (1/8) Epoch 5, batch 3750, loss[loss=0.1948, simple_loss=0.2685, pruned_loss=0.06055, over 6790.00 frames.], tot_loss[loss=0.2129, simple_loss=0.2909, pruned_loss=0.06742, over 1420322.37 frames.], batch size: 15, lr: 1.29e-03
+2022-05-14 02:41:09,951 INFO [train.py:812] (1/8) Epoch 5, batch 3800, loss[loss=0.2005, simple_loss=0.2702, pruned_loss=0.06539, over 7285.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2917, pruned_loss=0.06806, over 1421720.50 frames.], batch size: 18, lr: 1.28e-03
+2022-05-14 02:42:07,614 INFO [train.py:812] (1/8) Epoch 5, batch 3850, loss[loss=0.1981, simple_loss=0.2857, pruned_loss=0.05528, over 7413.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2923, pruned_loss=0.06848, over 1421747.15 frames.], batch size: 21, lr: 1.28e-03
+2022-05-14 02:43:06,306 INFO [train.py:812] (1/8) Epoch 5, batch 3900, loss[loss=0.2008, simple_loss=0.2754, pruned_loss=0.06315, over 7158.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2913, pruned_loss=0.06824, over 1418201.05 frames.], batch size: 18, lr: 1.28e-03
+2022-05-14 02:44:04,239 INFO [train.py:812] (1/8) Epoch 5, batch 3950, loss[loss=0.1894, simple_loss=0.2806, pruned_loss=0.04913, over 7398.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2911, pruned_loss=0.06765, over 1415204.52 frames.], batch size: 21, lr: 1.28e-03
+2022-05-14 02:45:02,163 INFO [train.py:812] (1/8) Epoch 5, batch 4000, loss[loss=0.1918, simple_loss=0.2719, pruned_loss=0.05587, over 7424.00 frames.], tot_loss[loss=0.2122, simple_loss=0.2903, pruned_loss=0.06704, over 1418014.81 frames.], batch size: 20, lr: 1.28e-03
+2022-05-14 02:46:01,626 INFO [train.py:812] (1/8) Epoch 5, batch 4050, loss[loss=0.2084, simple_loss=0.3001, pruned_loss=0.05831, over 7223.00 frames.], tot_loss[loss=0.212, simple_loss=0.29, pruned_loss=0.06702, over 1420622.02 frames.], batch size: 21, lr: 1.28e-03
+2022-05-14 02:46:59,621 INFO [train.py:812] (1/8) Epoch 5, batch 4100, loss[loss=0.1844, simple_loss=0.2606, pruned_loss=0.05412, over 7279.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2914, pruned_loss=0.06752, over 1417260.48 frames.], batch size: 18, lr: 1.28e-03
+2022-05-14 02:47:58,850 INFO [train.py:812] (1/8) Epoch 5, batch 4150, loss[loss=0.2134, simple_loss=0.2949, pruned_loss=0.06595, over 7189.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2921, pruned_loss=0.0681, over 1416301.22 frames.], batch size: 22, lr: 1.27e-03
+2022-05-14 02:48:57,882 INFO [train.py:812] (1/8) Epoch 5, batch 4200, loss[loss=0.2038, simple_loss=0.2908, pruned_loss=0.05838, over 7132.00 frames.], tot_loss[loss=0.2133, simple_loss=0.2917, pruned_loss=0.0675, over 1414695.98 frames.], batch size: 17, lr: 1.27e-03
+2022-05-14 02:49:57,150 INFO [train.py:812] (1/8) Epoch 5, batch 4250, loss[loss=0.1867, simple_loss=0.2664, pruned_loss=0.05355, over 7055.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2935, pruned_loss=0.06889, over 1415794.74 frames.], batch size: 18, lr: 1.27e-03
+2022-05-14 02:50:54,440 INFO [train.py:812] (1/8) Epoch 5, batch 4300, loss[loss=0.1715, simple_loss=0.2566, pruned_loss=0.04321, over 7142.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2939, pruned_loss=0.06878, over 1416082.49 frames.], batch size: 20, lr: 1.27e-03
+2022-05-14 02:51:52,659 INFO [train.py:812] (1/8) Epoch 5, batch 4350, loss[loss=0.2301, simple_loss=0.3026, pruned_loss=0.07883, over 7413.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2949, pruned_loss=0.06914, over 1414761.50 frames.], batch size: 21, lr: 1.27e-03
+2022-05-14 02:52:52,060 INFO [train.py:812] (1/8) Epoch 5, batch 4400, loss[loss=0.2091, simple_loss=0.2856, pruned_loss=0.06624, over 7262.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2946, pruned_loss=0.06883, over 1410936.30 frames.], batch size: 19, lr: 1.27e-03
+2022-05-14 02:53:51,752 INFO [train.py:812] (1/8) Epoch 5, batch 4450, loss[loss=0.2644, simple_loss=0.3292, pruned_loss=0.09982, over 6813.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2948, pruned_loss=0.06913, over 1404830.95 frames.], batch size: 31, lr: 1.27e-03
+2022-05-14 02:54:49,528 INFO [train.py:812] (1/8) Epoch 5, batch 4500, loss[loss=0.3044, simple_loss=0.3474, pruned_loss=0.1307, over 5060.00 frames.], tot_loss[loss=0.2202, simple_loss=0.298, pruned_loss=0.07118, over 1394805.00 frames.], batch size: 53, lr: 1.27e-03
+2022-05-14 02:55:48,812 INFO [train.py:812] (1/8) Epoch 5, batch 4550, loss[loss=0.2261, simple_loss=0.2964, pruned_loss=0.07792, over 5208.00 frames.], tot_loss[loss=0.224, simple_loss=0.3001, pruned_loss=0.07396, over 1341348.81 frames.], batch size: 53, lr: 1.26e-03
+2022-05-14 02:56:57,106 INFO [train.py:812] (1/8) Epoch 6, batch 0, loss[loss=0.18, simple_loss=0.259, pruned_loss=0.0505, over 7168.00 frames.], tot_loss[loss=0.18, simple_loss=0.259, pruned_loss=0.0505, over 7168.00 frames.], batch size: 19, lr: 1.21e-03
+2022-05-14 02:57:56,760 INFO [train.py:812] (1/8) Epoch 6, batch 50, loss[loss=0.242, simple_loss=0.3099, pruned_loss=0.08702, over 4936.00 frames.], tot_loss[loss=0.2122, simple_loss=0.2922, pruned_loss=0.06609, over 318241.22 frames.], batch size: 52, lr: 1.21e-03
+2022-05-14 02:58:56,403 INFO [train.py:812] (1/8) Epoch 6, batch 100, loss[loss=0.2462, simple_loss=0.3216, pruned_loss=0.08543, over 7143.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2941, pruned_loss=0.06862, over 561322.30 frames.], batch size: 20, lr: 1.21e-03
+2022-05-14 02:59:55,392 INFO [train.py:812] (1/8) Epoch 6, batch 150, loss[loss=0.2263, simple_loss=0.3087, pruned_loss=0.07192, over 6789.00 frames.], tot_loss[loss=0.2128, simple_loss=0.291, pruned_loss=0.06728, over 750359.04 frames.], batch size: 31, lr: 1.21e-03
+2022-05-14 03:00:54,863 INFO [train.py:812] (1/8) Epoch 6, batch 200, loss[loss=0.2084, simple_loss=0.2839, pruned_loss=0.06649, over 7412.00 frames.], tot_loss[loss=0.2111, simple_loss=0.2898, pruned_loss=0.06622, over 899433.23 frames.], batch size: 18, lr: 1.21e-03
+2022-05-14 03:01:54,418 INFO [train.py:812] (1/8) Epoch 6, batch 250, loss[loss=0.2079, simple_loss=0.2947, pruned_loss=0.06059, over 7329.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2894, pruned_loss=0.06565, over 1019726.23 frames.], batch size: 22, lr: 1.21e-03
+2022-05-14 03:02:54,510 INFO [train.py:812] (1/8) Epoch 6, batch 300, loss[loss=0.2222, simple_loss=0.2987, pruned_loss=0.07286, over 7227.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2885, pruned_loss=0.06479, over 1112417.71 frames.], batch size: 20, lr: 1.21e-03
+2022-05-14 03:03:51,876 INFO [train.py:812] (1/8) Epoch 6, batch 350, loss[loss=0.2042, simple_loss=0.2872, pruned_loss=0.06056, over 7328.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2881, pruned_loss=0.0645, over 1184658.66 frames.], batch size: 20, lr: 1.20e-03
+2022-05-14 03:04:49,929 INFO [train.py:812] (1/8) Epoch 6, batch 400, loss[loss=0.248, simple_loss=0.3212, pruned_loss=0.08736, over 7354.00 frames.], tot_loss[loss=0.2102, simple_loss=0.29, pruned_loss=0.06518, over 1236085.68 frames.], batch size: 23, lr: 1.20e-03
+2022-05-14 03:05:47,790 INFO [train.py:812] (1/8) Epoch 6, batch 450, loss[loss=0.1921, simple_loss=0.2715, pruned_loss=0.05641, over 6744.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2902, pruned_loss=0.06536, over 1278730.39 frames.], batch size: 15, lr: 1.20e-03
+2022-05-14 03:06:47,290 INFO [train.py:812] (1/8) Epoch 6, batch 500, loss[loss=0.216, simple_loss=0.294, pruned_loss=0.06906, over 4916.00 frames.], tot_loss[loss=0.211, simple_loss=0.2907, pruned_loss=0.06569, over 1307733.08 frames.], batch size: 52, lr: 1.20e-03
+2022-05-14 03:07:45,161 INFO [train.py:812] (1/8) Epoch 6, batch 550, loss[loss=0.2362, simple_loss=0.3275, pruned_loss=0.07248, over 6483.00 frames.], tot_loss[loss=0.2113, simple_loss=0.2907, pruned_loss=0.0659, over 1331747.78 frames.], batch size: 38, lr: 1.20e-03
+2022-05-14 03:08:44,000 INFO [train.py:812] (1/8) Epoch 6, batch 600, loss[loss=0.1982, simple_loss=0.2951, pruned_loss=0.05069, over 7137.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2891, pruned_loss=0.06529, over 1351113.33 frames.], batch size: 20, lr: 1.20e-03
+2022-05-14 03:09:42,700 INFO [train.py:812] (1/8) Epoch 6, batch 650, loss[loss=0.2137, simple_loss=0.2986, pruned_loss=0.06442, over 7409.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2886, pruned_loss=0.06479, over 1366221.21 frames.], batch size: 21, lr: 1.20e-03
+2022-05-14 03:10:42,145 INFO [train.py:812] (1/8) Epoch 6, batch 700, loss[loss=0.1997, simple_loss=0.2866, pruned_loss=0.05635, over 6795.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2893, pruned_loss=0.06501, over 1378070.00 frames.], batch size: 15, lr: 1.20e-03
+2022-05-14 03:11:41,180 INFO [train.py:812] (1/8) Epoch 6, batch 750, loss[loss=0.2083, simple_loss=0.29, pruned_loss=0.06334, over 7220.00 frames.], tot_loss[loss=0.21, simple_loss=0.2896, pruned_loss=0.0652, over 1387247.10 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:12:41,095 INFO [train.py:812] (1/8) Epoch 6, batch 800, loss[loss=0.2162, simple_loss=0.2972, pruned_loss=0.06757, over 7233.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2888, pruned_loss=0.065, over 1398321.44 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:13:40,485 INFO [train.py:812] (1/8) Epoch 6, batch 850, loss[loss=0.2662, simple_loss=0.3406, pruned_loss=0.09594, over 7190.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2894, pruned_loss=0.06542, over 1403897.86 frames.], batch size: 23, lr: 1.19e-03
+2022-05-14 03:14:39,812 INFO [train.py:812] (1/8) Epoch 6, batch 900, loss[loss=0.2203, simple_loss=0.3035, pruned_loss=0.06855, over 7417.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2897, pruned_loss=0.06506, over 1405299.57 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:15:38,551 INFO [train.py:812] (1/8) Epoch 6, batch 950, loss[loss=0.2106, simple_loss=0.275, pruned_loss=0.07309, over 7125.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2896, pruned_loss=0.06497, over 1406460.35 frames.], batch size: 17, lr: 1.19e-03
+2022-05-14 03:16:37,953 INFO [train.py:812] (1/8) Epoch 6, batch 1000, loss[loss=0.197, simple_loss=0.2859, pruned_loss=0.05402, over 7399.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2897, pruned_loss=0.06501, over 1408926.27 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:17:36,237 INFO [train.py:812] (1/8) Epoch 6, batch 1050, loss[loss=0.1976, simple_loss=0.2784, pruned_loss=0.05838, over 7321.00 frames.], tot_loss[loss=0.21, simple_loss=0.2897, pruned_loss=0.06517, over 1413153.83 frames.], batch size: 20, lr: 1.19e-03
+2022-05-14 03:18:39,068 INFO [train.py:812] (1/8) Epoch 6, batch 1100, loss[loss=0.2113, simple_loss=0.2952, pruned_loss=0.06368, over 7323.00 frames.], tot_loss[loss=0.2121, simple_loss=0.2913, pruned_loss=0.0664, over 1408511.63 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:19:37,382 INFO [train.py:812] (1/8) Epoch 6, batch 1150, loss[loss=0.2257, simple_loss=0.3046, pruned_loss=0.07344, over 7143.00 frames.], tot_loss[loss=0.2127, simple_loss=0.2922, pruned_loss=0.06664, over 1413837.22 frames.], batch size: 20, lr: 1.19e-03
+2022-05-14 03:20:36,646 INFO [train.py:812] (1/8) Epoch 6, batch 1200, loss[loss=0.2282, simple_loss=0.3106, pruned_loss=0.0729, over 7183.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2904, pruned_loss=0.06556, over 1415060.76 frames.], batch size: 26, lr: 1.18e-03
+2022-05-14 03:21:34,756 INFO [train.py:812] (1/8) Epoch 6, batch 1250, loss[loss=0.2263, simple_loss=0.304, pruned_loss=0.0743, over 7149.00 frames.], tot_loss[loss=0.21, simple_loss=0.2899, pruned_loss=0.06505, over 1414116.02 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:22:34,579 INFO [train.py:812] (1/8) Epoch 6, batch 1300, loss[loss=0.1949, simple_loss=0.2646, pruned_loss=0.06265, over 7356.00 frames.], tot_loss[loss=0.21, simple_loss=0.2896, pruned_loss=0.06516, over 1412013.14 frames.], batch size: 19, lr: 1.18e-03
+2022-05-14 03:23:33,464 INFO [train.py:812] (1/8) Epoch 6, batch 1350, loss[loss=0.2354, simple_loss=0.3129, pruned_loss=0.0789, over 7068.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2886, pruned_loss=0.06476, over 1414870.77 frames.], batch size: 28, lr: 1.18e-03
+2022-05-14 03:24:32,549 INFO [train.py:812] (1/8) Epoch 6, batch 1400, loss[loss=0.1736, simple_loss=0.2537, pruned_loss=0.04676, over 7329.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2878, pruned_loss=0.06422, over 1418800.31 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:25:31,685 INFO [train.py:812] (1/8) Epoch 6, batch 1450, loss[loss=0.1795, simple_loss=0.2591, pruned_loss=0.04998, over 7437.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2879, pruned_loss=0.06434, over 1419999.16 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:26:31,149 INFO [train.py:812] (1/8) Epoch 6, batch 1500, loss[loss=0.1975, simple_loss=0.2922, pruned_loss=0.05144, over 7148.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2885, pruned_loss=0.06446, over 1420241.58 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:27:30,163 INFO [train.py:812] (1/8) Epoch 6, batch 1550, loss[loss=0.1659, simple_loss=0.2483, pruned_loss=0.04172, over 7284.00 frames.], tot_loss[loss=0.2087, simple_loss=0.289, pruned_loss=0.06415, over 1422785.67 frames.], batch size: 17, lr: 1.18e-03
+2022-05-14 03:28:29,751 INFO [train.py:812] (1/8) Epoch 6, batch 1600, loss[loss=0.1979, simple_loss=0.2831, pruned_loss=0.05635, over 7423.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2888, pruned_loss=0.06413, over 1416431.73 frames.], batch size: 20, lr: 1.17e-03
+2022-05-14 03:29:29,244 INFO [train.py:812] (1/8) Epoch 6, batch 1650, loss[loss=0.213, simple_loss=0.3068, pruned_loss=0.05961, over 7286.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2886, pruned_loss=0.06398, over 1415185.59 frames.], batch size: 25, lr: 1.17e-03
+2022-05-14 03:30:27,820 INFO [train.py:812] (1/8) Epoch 6, batch 1700, loss[loss=0.2314, simple_loss=0.307, pruned_loss=0.07795, over 7213.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2887, pruned_loss=0.06489, over 1414349.96 frames.], batch size: 22, lr: 1.17e-03
+2022-05-14 03:31:26,898 INFO [train.py:812] (1/8) Epoch 6, batch 1750, loss[loss=0.1765, simple_loss=0.2522, pruned_loss=0.05043, over 7279.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2893, pruned_loss=0.06525, over 1411208.74 frames.], batch size: 18, lr: 1.17e-03
+2022-05-14 03:32:26,453 INFO [train.py:812] (1/8) Epoch 6, batch 1800, loss[loss=0.2437, simple_loss=0.3056, pruned_loss=0.09091, over 4990.00 frames.], tot_loss[loss=0.21, simple_loss=0.2895, pruned_loss=0.06528, over 1412133.44 frames.], batch size: 52, lr: 1.17e-03
+2022-05-14 03:33:25,530 INFO [train.py:812] (1/8) Epoch 6, batch 1850, loss[loss=0.1483, simple_loss=0.2448, pruned_loss=0.02587, over 7168.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2885, pruned_loss=0.06458, over 1416010.26 frames.], batch size: 18, lr: 1.17e-03
+2022-05-14 03:34:24,878 INFO [train.py:812] (1/8) Epoch 6, batch 1900, loss[loss=0.2041, simple_loss=0.2628, pruned_loss=0.07265, over 7156.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2884, pruned_loss=0.06437, over 1415226.03 frames.], batch size: 17, lr: 1.17e-03
+2022-05-14 03:35:23,962 INFO [train.py:812] (1/8) Epoch 6, batch 1950, loss[loss=0.2027, simple_loss=0.2885, pruned_loss=0.05841, over 7111.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2879, pruned_loss=0.06356, over 1420459.29 frames.], batch size: 21, lr: 1.17e-03
+2022-05-14 03:36:21,514 INFO [train.py:812] (1/8) Epoch 6, batch 2000, loss[loss=0.174, simple_loss=0.2442, pruned_loss=0.05188, over 7265.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2881, pruned_loss=0.06387, over 1423476.13 frames.], batch size: 18, lr: 1.17e-03
+2022-05-14 03:37:19,515 INFO [train.py:812] (1/8) Epoch 6, batch 2050, loss[loss=0.2428, simple_loss=0.3217, pruned_loss=0.08197, over 7089.00 frames.], tot_loss[loss=0.208, simple_loss=0.2883, pruned_loss=0.06387, over 1423594.38 frames.], batch size: 28, lr: 1.16e-03
+2022-05-14 03:38:19,351 INFO [train.py:812] (1/8) Epoch 6, batch 2100, loss[loss=0.2273, simple_loss=0.2994, pruned_loss=0.07754, over 6413.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2878, pruned_loss=0.06348, over 1425201.62 frames.], batch size: 37, lr: 1.16e-03
+2022-05-14 03:39:18,983 INFO [train.py:812] (1/8) Epoch 6, batch 2150, loss[loss=0.2299, simple_loss=0.298, pruned_loss=0.08097, over 7144.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2878, pruned_loss=0.06342, over 1430415.45 frames.], batch size: 20, lr: 1.16e-03
+2022-05-14 03:40:18,674 INFO [train.py:812] (1/8) Epoch 6, batch 2200, loss[loss=0.1872, simple_loss=0.2767, pruned_loss=0.04887, over 7151.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2879, pruned_loss=0.06331, over 1427646.75 frames.], batch size: 20, lr: 1.16e-03
+2022-05-14 03:41:17,645 INFO [train.py:812] (1/8) Epoch 6, batch 2250, loss[loss=0.1859, simple_loss=0.262, pruned_loss=0.05488, over 7359.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2878, pruned_loss=0.06331, over 1425903.07 frames.], batch size: 19, lr: 1.16e-03
+2022-05-14 03:42:16,659 INFO [train.py:812] (1/8) Epoch 6, batch 2300, loss[loss=0.2139, simple_loss=0.2923, pruned_loss=0.06773, over 7294.00 frames.], tot_loss[loss=0.2077, simple_loss=0.288, pruned_loss=0.06366, over 1423094.26 frames.], batch size: 24, lr: 1.16e-03
+2022-05-14 03:43:15,822 INFO [train.py:812] (1/8) Epoch 6, batch 2350, loss[loss=0.2023, simple_loss=0.2896, pruned_loss=0.05747, over 7214.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2865, pruned_loss=0.06311, over 1422409.18 frames.], batch size: 21, lr: 1.16e-03
+2022-05-14 03:44:15,951 INFO [train.py:812] (1/8) Epoch 6, batch 2400, loss[loss=0.1868, simple_loss=0.2689, pruned_loss=0.05231, over 7325.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2868, pruned_loss=0.06369, over 1422919.95 frames.], batch size: 20, lr: 1.16e-03
+2022-05-14 03:45:14,491 INFO [train.py:812] (1/8) Epoch 6, batch 2450, loss[loss=0.1878, simple_loss=0.2588, pruned_loss=0.0584, over 6783.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2861, pruned_loss=0.06327, over 1421607.25 frames.], batch size: 15, lr: 1.16e-03
+2022-05-14 03:46:13,713 INFO [train.py:812] (1/8) Epoch 6, batch 2500, loss[loss=0.2373, simple_loss=0.3095, pruned_loss=0.08258, over 7340.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2863, pruned_loss=0.06327, over 1420139.07 frames.], batch size: 22, lr: 1.15e-03
+2022-05-14 03:47:11,216 INFO [train.py:812] (1/8) Epoch 6, batch 2550, loss[loss=0.1715, simple_loss=0.256, pruned_loss=0.04347, over 6764.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2858, pruned_loss=0.06287, over 1421410.76 frames.], batch size: 15, lr: 1.15e-03
+2022-05-14 03:48:09,666 INFO [train.py:812] (1/8) Epoch 6, batch 2600, loss[loss=0.1964, simple_loss=0.2855, pruned_loss=0.05365, over 7308.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2861, pruned_loss=0.0623, over 1424578.13 frames.], batch size: 21, lr: 1.15e-03
+2022-05-14 03:49:08,328 INFO [train.py:812] (1/8) Epoch 6, batch 2650, loss[loss=0.2287, simple_loss=0.3218, pruned_loss=0.06775, over 7280.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2871, pruned_loss=0.06264, over 1422694.66 frames.], batch size: 25, lr: 1.15e-03
+2022-05-14 03:50:08,411 INFO [train.py:812] (1/8) Epoch 6, batch 2700, loss[loss=0.1918, simple_loss=0.27, pruned_loss=0.05681, over 7189.00 frames.], tot_loss[loss=0.206, simple_loss=0.2871, pruned_loss=0.06251, over 1424900.64 frames.], batch size: 16, lr: 1.15e-03
+2022-05-14 03:51:06,473 INFO [train.py:812] (1/8) Epoch 6, batch 2750, loss[loss=0.2181, simple_loss=0.2818, pruned_loss=0.0772, over 7228.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2868, pruned_loss=0.06221, over 1422677.63 frames.], batch size: 20, lr: 1.15e-03
+2022-05-14 03:52:05,466 INFO [train.py:812] (1/8) Epoch 6, batch 2800, loss[loss=0.2364, simple_loss=0.3087, pruned_loss=0.08204, over 7270.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2868, pruned_loss=0.06278, over 1420913.36 frames.], batch size: 18, lr: 1.15e-03
+2022-05-14 03:53:03,385 INFO [train.py:812] (1/8) Epoch 6, batch 2850, loss[loss=0.2006, simple_loss=0.265, pruned_loss=0.06806, over 7277.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2868, pruned_loss=0.06279, over 1418309.18 frames.], batch size: 17, lr: 1.15e-03
+2022-05-14 03:54:00,908 INFO [train.py:812] (1/8) Epoch 6, batch 2900, loss[loss=0.1985, simple_loss=0.282, pruned_loss=0.05752, over 6782.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2866, pruned_loss=0.0628, over 1420261.22 frames.], batch size: 31, lr: 1.15e-03
+2022-05-14 03:54:58,714 INFO [train.py:812] (1/8) Epoch 6, batch 2950, loss[loss=0.189, simple_loss=0.2857, pruned_loss=0.04613, over 7146.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2866, pruned_loss=0.063, over 1420020.19 frames.], batch size: 20, lr: 1.14e-03
+2022-05-14 03:55:55,717 INFO [train.py:812] (1/8) Epoch 6, batch 3000, loss[loss=0.1838, simple_loss=0.2762, pruned_loss=0.04573, over 7229.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2867, pruned_loss=0.06309, over 1419554.64 frames.], batch size: 20, lr: 1.14e-03
+2022-05-14 03:55:55,718 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 03:56:03,338 INFO [train.py:841] (1/8) Epoch 6, validation: loss=0.1668, simple_loss=0.2696, pruned_loss=0.03205, over 698248.00 frames.
+2022-05-14 03:57:02,162 INFO [train.py:812] (1/8) Epoch 6, batch 3050, loss[loss=0.2479, simple_loss=0.3167, pruned_loss=0.08958, over 7222.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2859, pruned_loss=0.06272, over 1425341.06 frames.], batch size: 23, lr: 1.14e-03
+2022-05-14 03:58:01,677 INFO [train.py:812] (1/8) Epoch 6, batch 3100, loss[loss=0.2262, simple_loss=0.3068, pruned_loss=0.07279, over 7336.00 frames.], tot_loss[loss=0.2049, simple_loss=0.285, pruned_loss=0.06241, over 1423689.32 frames.], batch size: 22, lr: 1.14e-03
+2022-05-14 03:58:58,841 INFO [train.py:812] (1/8) Epoch 6, batch 3150, loss[loss=0.2293, simple_loss=0.3093, pruned_loss=0.07469, over 7212.00 frames.], tot_loss[loss=0.206, simple_loss=0.2867, pruned_loss=0.06269, over 1423677.45 frames.], batch size: 23, lr: 1.14e-03
+2022-05-14 03:59:57,539 INFO [train.py:812] (1/8) Epoch 6, batch 3200, loss[loss=0.22, simple_loss=0.2946, pruned_loss=0.07269, over 7222.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2873, pruned_loss=0.06316, over 1425616.63 frames.], batch size: 21, lr: 1.14e-03
+2022-05-14 04:00:56,299 INFO [train.py:812] (1/8) Epoch 6, batch 3250, loss[loss=0.2232, simple_loss=0.2927, pruned_loss=0.07684, over 7363.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2869, pruned_loss=0.06288, over 1424694.79 frames.], batch size: 19, lr: 1.14e-03
+2022-05-14 04:01:55,496 INFO [train.py:812] (1/8) Epoch 6, batch 3300, loss[loss=0.2163, simple_loss=0.2996, pruned_loss=0.06653, over 7210.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2871, pruned_loss=0.06308, over 1420808.33 frames.], batch size: 23, lr: 1.14e-03
+2022-05-14 04:02:54,514 INFO [train.py:812] (1/8) Epoch 6, batch 3350, loss[loss=0.1849, simple_loss=0.2704, pruned_loss=0.04968, over 7256.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2867, pruned_loss=0.0628, over 1425509.54 frames.], batch size: 19, lr: 1.14e-03
+2022-05-14 04:03:53,907 INFO [train.py:812] (1/8) Epoch 6, batch 3400, loss[loss=0.1905, simple_loss=0.28, pruned_loss=0.05055, over 7272.00 frames.], tot_loss[loss=0.206, simple_loss=0.2864, pruned_loss=0.06283, over 1425032.90 frames.], batch size: 24, lr: 1.14e-03
+2022-05-14 04:04:52,394 INFO [train.py:812] (1/8) Epoch 6, batch 3450, loss[loss=0.225, simple_loss=0.3105, pruned_loss=0.06969, over 7422.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2874, pruned_loss=0.06315, over 1427127.72 frames.], batch size: 21, lr: 1.13e-03
+2022-05-14 04:05:50,788 INFO [train.py:812] (1/8) Epoch 6, batch 3500, loss[loss=0.2324, simple_loss=0.3111, pruned_loss=0.07685, over 7198.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2861, pruned_loss=0.06282, over 1424218.42 frames.], batch size: 22, lr: 1.13e-03
+2022-05-14 04:06:49,091 INFO [train.py:812] (1/8) Epoch 6, batch 3550, loss[loss=0.1948, simple_loss=0.2816, pruned_loss=0.05399, over 7321.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2856, pruned_loss=0.06216, over 1426948.26 frames.], batch size: 21, lr: 1.13e-03
+2022-05-14 04:07:47,620 INFO [train.py:812] (1/8) Epoch 6, batch 3600, loss[loss=0.1891, simple_loss=0.2717, pruned_loss=0.05324, over 7170.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2852, pruned_loss=0.06223, over 1428585.15 frames.], batch size: 18, lr: 1.13e-03
+2022-05-14 04:08:46,806 INFO [train.py:812] (1/8) Epoch 6, batch 3650, loss[loss=0.2144, simple_loss=0.2918, pruned_loss=0.06851, over 7413.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2848, pruned_loss=0.06224, over 1427372.51 frames.], batch size: 21, lr: 1.13e-03
+2022-05-14 04:09:44,222 INFO [train.py:812] (1/8) Epoch 6, batch 3700, loss[loss=0.176, simple_loss=0.2607, pruned_loss=0.04562, over 7225.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2855, pruned_loss=0.06208, over 1426417.60 frames.], batch size: 20, lr: 1.13e-03
+2022-05-14 04:10:41,359 INFO [train.py:812] (1/8) Epoch 6, batch 3750, loss[loss=0.243, simple_loss=0.3297, pruned_loss=0.0781, over 7381.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2851, pruned_loss=0.06199, over 1424128.04 frames.], batch size: 23, lr: 1.13e-03
+2022-05-14 04:11:40,663 INFO [train.py:812] (1/8) Epoch 6, batch 3800, loss[loss=0.1823, simple_loss=0.2717, pruned_loss=0.04644, over 7226.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2846, pruned_loss=0.06188, over 1420545.64 frames.], batch size: 20, lr: 1.13e-03
+2022-05-14 04:12:39,819 INFO [train.py:812] (1/8) Epoch 6, batch 3850, loss[loss=0.185, simple_loss=0.2671, pruned_loss=0.05148, over 7432.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2858, pruned_loss=0.06236, over 1420902.52 frames.], batch size: 20, lr: 1.13e-03
+2022-05-14 04:13:39,013 INFO [train.py:812] (1/8) Epoch 6, batch 3900, loss[loss=0.1424, simple_loss=0.2256, pruned_loss=0.02956, over 7416.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2858, pruned_loss=0.06289, over 1425495.94 frames.], batch size: 18, lr: 1.13e-03
+2022-05-14 04:14:38,338 INFO [train.py:812] (1/8) Epoch 6, batch 3950, loss[loss=0.2019, simple_loss=0.288, pruned_loss=0.0579, over 7301.00 frames.], tot_loss[loss=0.205, simple_loss=0.285, pruned_loss=0.06248, over 1424167.71 frames.], batch size: 24, lr: 1.12e-03
+2022-05-14 04:15:37,076 INFO [train.py:812] (1/8) Epoch 6, batch 4000, loss[loss=0.2309, simple_loss=0.3021, pruned_loss=0.07984, over 7197.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2863, pruned_loss=0.06332, over 1426374.31 frames.], batch size: 23, lr: 1.12e-03
+2022-05-14 04:16:34,884 INFO [train.py:812] (1/8) Epoch 6, batch 4050, loss[loss=0.2405, simple_loss=0.3283, pruned_loss=0.07637, over 7268.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2858, pruned_loss=0.06317, over 1426703.05 frames.], batch size: 24, lr: 1.12e-03
+2022-05-14 04:17:34,622 INFO [train.py:812] (1/8) Epoch 6, batch 4100, loss[loss=0.1642, simple_loss=0.2438, pruned_loss=0.04232, over 7403.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2852, pruned_loss=0.06331, over 1426408.26 frames.], batch size: 18, lr: 1.12e-03
+2022-05-14 04:18:33,838 INFO [train.py:812] (1/8) Epoch 6, batch 4150, loss[loss=0.2366, simple_loss=0.3225, pruned_loss=0.07537, over 6759.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2842, pruned_loss=0.06302, over 1426318.36 frames.], batch size: 31, lr: 1.12e-03
+2022-05-14 04:19:32,911 INFO [train.py:812] (1/8) Epoch 6, batch 4200, loss[loss=0.2517, simple_loss=0.3326, pruned_loss=0.08543, over 7124.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2836, pruned_loss=0.06289, over 1428189.97 frames.], batch size: 21, lr: 1.12e-03
+2022-05-14 04:20:33,096 INFO [train.py:812] (1/8) Epoch 6, batch 4250, loss[loss=0.2385, simple_loss=0.3229, pruned_loss=0.07701, over 7391.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2833, pruned_loss=0.06225, over 1430164.28 frames.], batch size: 23, lr: 1.12e-03
+2022-05-14 04:21:32,387 INFO [train.py:812] (1/8) Epoch 6, batch 4300, loss[loss=0.1882, simple_loss=0.2694, pruned_loss=0.05353, over 7069.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2838, pruned_loss=0.06298, over 1424065.65 frames.], batch size: 18, lr: 1.12e-03
+2022-05-14 04:22:31,656 INFO [train.py:812] (1/8) Epoch 6, batch 4350, loss[loss=0.2139, simple_loss=0.2992, pruned_loss=0.06437, over 7225.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2844, pruned_loss=0.06298, over 1423999.11 frames.], batch size: 21, lr: 1.12e-03
+2022-05-14 04:23:31,432 INFO [train.py:812] (1/8) Epoch 6, batch 4400, loss[loss=0.2177, simple_loss=0.2932, pruned_loss=0.07114, over 7415.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2839, pruned_loss=0.06279, over 1423058.27 frames.], batch size: 20, lr: 1.12e-03
+2022-05-14 04:24:30,568 INFO [train.py:812] (1/8) Epoch 6, batch 4450, loss[loss=0.1794, simple_loss=0.2615, pruned_loss=0.04866, over 7277.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2845, pruned_loss=0.06354, over 1409856.69 frames.], batch size: 17, lr: 1.11e-03
+2022-05-14 04:25:38,563 INFO [train.py:812] (1/8) Epoch 6, batch 4500, loss[loss=0.2019, simple_loss=0.2822, pruned_loss=0.0608, over 7229.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2825, pruned_loss=0.06306, over 1409516.14 frames.], batch size: 20, lr: 1.11e-03
+2022-05-14 04:26:36,426 INFO [train.py:812] (1/8) Epoch 6, batch 4550, loss[loss=0.3074, simple_loss=0.367, pruned_loss=0.124, over 4992.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2858, pruned_loss=0.06566, over 1361907.85 frames.], batch size: 52, lr: 1.11e-03
+2022-05-14 04:27:44,584 INFO [train.py:812] (1/8) Epoch 7, batch 0, loss[loss=0.166, simple_loss=0.2442, pruned_loss=0.04389, over 7407.00 frames.], tot_loss[loss=0.166, simple_loss=0.2442, pruned_loss=0.04389, over 7407.00 frames.], batch size: 18, lr: 1.07e-03
+2022-05-14 04:28:43,245 INFO [train.py:812] (1/8) Epoch 7, batch 50, loss[loss=0.2037, simple_loss=0.2762, pruned_loss=0.0656, over 7411.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2787, pruned_loss=0.05898, over 322456.13 frames.], batch size: 18, lr: 1.07e-03
+2022-05-14 04:29:42,457 INFO [train.py:812] (1/8) Epoch 7, batch 100, loss[loss=0.1758, simple_loss=0.2642, pruned_loss=0.04373, over 7152.00 frames.], tot_loss[loss=0.1998, simple_loss=0.28, pruned_loss=0.05977, over 567977.56 frames.], batch size: 19, lr: 1.06e-03
+2022-05-14 04:30:41,779 INFO [train.py:812] (1/8) Epoch 7, batch 150, loss[loss=0.1952, simple_loss=0.2681, pruned_loss=0.06115, over 7155.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2825, pruned_loss=0.06093, over 757475.34 frames.], batch size: 19, lr: 1.06e-03
+2022-05-14 04:31:41,618 INFO [train.py:812] (1/8) Epoch 7, batch 200, loss[loss=0.2394, simple_loss=0.3231, pruned_loss=0.0778, over 7381.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2822, pruned_loss=0.06051, over 906235.19 frames.], batch size: 23, lr: 1.06e-03
+2022-05-14 04:32:39,929 INFO [train.py:812] (1/8) Epoch 7, batch 250, loss[loss=0.1898, simple_loss=0.2661, pruned_loss=0.05679, over 7146.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2838, pruned_loss=0.06086, over 1020125.82 frames.], batch size: 20, lr: 1.06e-03
+2022-05-14 04:33:39,357 INFO [train.py:812] (1/8) Epoch 7, batch 300, loss[loss=0.1515, simple_loss=0.2271, pruned_loss=0.038, over 6816.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2833, pruned_loss=0.06078, over 1106705.98 frames.], batch size: 15, lr: 1.06e-03
+2022-05-14 04:34:57,029 INFO [train.py:812] (1/8) Epoch 7, batch 350, loss[loss=0.1823, simple_loss=0.2717, pruned_loss=0.04646, over 7120.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2826, pruned_loss=0.05962, over 1177946.98 frames.], batch size: 21, lr: 1.06e-03
+2022-05-14 04:35:53,857 INFO [train.py:812] (1/8) Epoch 7, batch 400, loss[loss=0.1822, simple_loss=0.2605, pruned_loss=0.05196, over 7172.00 frames.], tot_loss[loss=0.2012, simple_loss=0.283, pruned_loss=0.05974, over 1230091.48 frames.], batch size: 18, lr: 1.06e-03
+2022-05-14 04:37:20,597 INFO [train.py:812] (1/8) Epoch 7, batch 450, loss[loss=0.1743, simple_loss=0.2616, pruned_loss=0.04348, over 7355.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2832, pruned_loss=0.06029, over 1275682.10 frames.], batch size: 19, lr: 1.06e-03
+2022-05-14 04:38:43,154 INFO [train.py:812] (1/8) Epoch 7, batch 500, loss[loss=0.2055, simple_loss=0.2899, pruned_loss=0.06052, over 6477.00 frames.], tot_loss[loss=0.2026, simple_loss=0.284, pruned_loss=0.06056, over 1305140.83 frames.], batch size: 38, lr: 1.06e-03
+2022-05-14 04:39:42,047 INFO [train.py:812] (1/8) Epoch 7, batch 550, loss[loss=0.2229, simple_loss=0.3069, pruned_loss=0.06948, over 7116.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2834, pruned_loss=0.06063, over 1330086.64 frames.], batch size: 21, lr: 1.06e-03
+2022-05-14 04:40:39,513 INFO [train.py:812] (1/8) Epoch 7, batch 600, loss[loss=0.1884, simple_loss=0.2833, pruned_loss=0.0468, over 7030.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2843, pruned_loss=0.06108, over 1348960.30 frames.], batch size: 28, lr: 1.06e-03
+2022-05-14 04:41:38,887 INFO [train.py:812] (1/8) Epoch 7, batch 650, loss[loss=0.2699, simple_loss=0.3332, pruned_loss=0.1033, over 5084.00 frames.], tot_loss[loss=0.202, simple_loss=0.2828, pruned_loss=0.06059, over 1364326.93 frames.], batch size: 52, lr: 1.05e-03
+2022-05-14 04:42:37,556 INFO [train.py:812] (1/8) Epoch 7, batch 700, loss[loss=0.1837, simple_loss=0.2654, pruned_loss=0.05095, over 7162.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2816, pruned_loss=0.05989, over 1378323.53 frames.], batch size: 18, lr: 1.05e-03
+2022-05-14 04:43:36,169 INFO [train.py:812] (1/8) Epoch 7, batch 750, loss[loss=0.2087, simple_loss=0.2956, pruned_loss=0.06086, over 6787.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2812, pruned_loss=0.05932, over 1391190.00 frames.], batch size: 31, lr: 1.05e-03
+2022-05-14 04:44:33,663 INFO [train.py:812] (1/8) Epoch 7, batch 800, loss[loss=0.1879, simple_loss=0.2771, pruned_loss=0.04934, over 7319.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2816, pruned_loss=0.05965, over 1391438.44 frames.], batch size: 20, lr: 1.05e-03
+2022-05-14 04:45:32,932 INFO [train.py:812] (1/8) Epoch 7, batch 850, loss[loss=0.1983, simple_loss=0.2853, pruned_loss=0.05566, over 7315.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2811, pruned_loss=0.05958, over 1397590.25 frames.], batch size: 24, lr: 1.05e-03
+2022-05-14 04:46:32,283 INFO [train.py:812] (1/8) Epoch 7, batch 900, loss[loss=0.2355, simple_loss=0.3081, pruned_loss=0.08141, over 7382.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2823, pruned_loss=0.06012, over 1403428.32 frames.], batch size: 23, lr: 1.05e-03
+2022-05-14 04:47:31,112 INFO [train.py:812] (1/8) Epoch 7, batch 950, loss[loss=0.2254, simple_loss=0.2987, pruned_loss=0.07602, over 7375.00 frames.], tot_loss[loss=0.2019, simple_loss=0.283, pruned_loss=0.06037, over 1407153.86 frames.], batch size: 23, lr: 1.05e-03
+2022-05-14 04:48:29,685 INFO [train.py:812] (1/8) Epoch 7, batch 1000, loss[loss=0.212, simple_loss=0.2913, pruned_loss=0.06639, over 7378.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2826, pruned_loss=0.06064, over 1407430.19 frames.], batch size: 23, lr: 1.05e-03
+2022-05-14 04:49:29,137 INFO [train.py:812] (1/8) Epoch 7, batch 1050, loss[loss=0.1916, simple_loss=0.275, pruned_loss=0.05416, over 7160.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2823, pruned_loss=0.06038, over 1414680.66 frames.], batch size: 19, lr: 1.05e-03
+2022-05-14 04:50:29,066 INFO [train.py:812] (1/8) Epoch 7, batch 1100, loss[loss=0.2295, simple_loss=0.3136, pruned_loss=0.07269, over 7293.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2828, pruned_loss=0.06077, over 1418280.44 frames.], batch size: 25, lr: 1.05e-03
+2022-05-14 04:51:28,382 INFO [train.py:812] (1/8) Epoch 7, batch 1150, loss[loss=0.1523, simple_loss=0.2299, pruned_loss=0.03734, over 7143.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2829, pruned_loss=0.06012, over 1417300.86 frames.], batch size: 17, lr: 1.05e-03
+2022-05-14 04:52:28,291 INFO [train.py:812] (1/8) Epoch 7, batch 1200, loss[loss=0.1889, simple_loss=0.2592, pruned_loss=0.05935, over 7199.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2837, pruned_loss=0.06085, over 1412974.59 frames.], batch size: 16, lr: 1.04e-03
+2022-05-14 04:53:27,874 INFO [train.py:812] (1/8) Epoch 7, batch 1250, loss[loss=0.2083, simple_loss=0.2867, pruned_loss=0.06494, over 7230.00 frames.], tot_loss[loss=0.2024, simple_loss=0.283, pruned_loss=0.06091, over 1414551.89 frames.], batch size: 20, lr: 1.04e-03
+2022-05-14 04:54:25,603 INFO [train.py:812] (1/8) Epoch 7, batch 1300, loss[loss=0.1982, simple_loss=0.276, pruned_loss=0.06024, over 7279.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2825, pruned_loss=0.06041, over 1415677.65 frames.], batch size: 17, lr: 1.04e-03
+2022-05-14 04:55:24,136 INFO [train.py:812] (1/8) Epoch 7, batch 1350, loss[loss=0.2152, simple_loss=0.2852, pruned_loss=0.07257, over 7404.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2828, pruned_loss=0.06019, over 1421320.94 frames.], batch size: 21, lr: 1.04e-03
+2022-05-14 04:56:22,885 INFO [train.py:812] (1/8) Epoch 7, batch 1400, loss[loss=0.1871, simple_loss=0.2683, pruned_loss=0.05301, over 7142.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2834, pruned_loss=0.06025, over 1420108.88 frames.], batch size: 19, lr: 1.04e-03
+2022-05-14 04:57:22,030 INFO [train.py:812] (1/8) Epoch 7, batch 1450, loss[loss=0.1851, simple_loss=0.2638, pruned_loss=0.05323, over 6766.00 frames.], tot_loss[loss=0.201, simple_loss=0.2829, pruned_loss=0.05954, over 1420665.34 frames.], batch size: 31, lr: 1.04e-03
+2022-05-14 04:58:20,156 INFO [train.py:812] (1/8) Epoch 7, batch 1500, loss[loss=0.2495, simple_loss=0.3185, pruned_loss=0.09021, over 7409.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2833, pruned_loss=0.05999, over 1423497.73 frames.], batch size: 21, lr: 1.04e-03
+2022-05-14 04:59:18,876 INFO [train.py:812] (1/8) Epoch 7, batch 1550, loss[loss=0.2028, simple_loss=0.2868, pruned_loss=0.05938, over 7184.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2829, pruned_loss=0.05995, over 1417290.00 frames.], batch size: 26, lr: 1.04e-03
+2022-05-14 05:00:18,916 INFO [train.py:812] (1/8) Epoch 7, batch 1600, loss[loss=0.1772, simple_loss=0.2759, pruned_loss=0.03929, over 7107.00 frames.], tot_loss[loss=0.2, simple_loss=0.2822, pruned_loss=0.05895, over 1423620.31 frames.], batch size: 21, lr: 1.04e-03
+2022-05-14 05:01:18,242 INFO [train.py:812] (1/8) Epoch 7, batch 1650, loss[loss=0.1862, simple_loss=0.2658, pruned_loss=0.05336, over 7064.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2817, pruned_loss=0.05906, over 1417573.38 frames.], batch size: 18, lr: 1.04e-03
+2022-05-14 05:02:16,811 INFO [train.py:812] (1/8) Epoch 7, batch 1700, loss[loss=0.2025, simple_loss=0.2825, pruned_loss=0.06125, over 7196.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2808, pruned_loss=0.05891, over 1417170.00 frames.], batch size: 22, lr: 1.04e-03
+2022-05-14 05:03:15,989 INFO [train.py:812] (1/8) Epoch 7, batch 1750, loss[loss=0.2363, simple_loss=0.3199, pruned_loss=0.07634, over 7344.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2821, pruned_loss=0.05934, over 1412397.40 frames.], batch size: 22, lr: 1.04e-03
+2022-05-14 05:04:14,616 INFO [train.py:812] (1/8) Epoch 7, batch 1800, loss[loss=0.2013, simple_loss=0.2775, pruned_loss=0.06262, over 7266.00 frames.], tot_loss[loss=0.201, simple_loss=0.283, pruned_loss=0.05946, over 1415083.87 frames.], batch size: 25, lr: 1.03e-03
+2022-05-14 05:05:13,135 INFO [train.py:812] (1/8) Epoch 7, batch 1850, loss[loss=0.1906, simple_loss=0.2534, pruned_loss=0.06393, over 6987.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2828, pruned_loss=0.06011, over 1417492.83 frames.], batch size: 16, lr: 1.03e-03
+2022-05-14 05:06:10,527 INFO [train.py:812] (1/8) Epoch 7, batch 1900, loss[loss=0.1739, simple_loss=0.2583, pruned_loss=0.04476, over 7453.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2829, pruned_loss=0.06059, over 1414764.72 frames.], batch size: 19, lr: 1.03e-03
+2022-05-14 05:07:08,607 INFO [train.py:812] (1/8) Epoch 7, batch 1950, loss[loss=0.2209, simple_loss=0.2906, pruned_loss=0.0756, over 7277.00 frames.], tot_loss[loss=0.2012, simple_loss=0.282, pruned_loss=0.06015, over 1418130.23 frames.], batch size: 18, lr: 1.03e-03
+2022-05-14 05:08:07,325 INFO [train.py:812] (1/8) Epoch 7, batch 2000, loss[loss=0.2113, simple_loss=0.2949, pruned_loss=0.06384, over 7345.00 frames.], tot_loss[loss=0.2013, simple_loss=0.282, pruned_loss=0.06027, over 1418708.45 frames.], batch size: 25, lr: 1.03e-03
+2022-05-14 05:09:04,290 INFO [train.py:812] (1/8) Epoch 7, batch 2050, loss[loss=0.1825, simple_loss=0.2645, pruned_loss=0.05029, over 7299.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2828, pruned_loss=0.06091, over 1415947.61 frames.], batch size: 24, lr: 1.03e-03
+2022-05-14 05:10:01,688 INFO [train.py:812] (1/8) Epoch 7, batch 2100, loss[loss=0.1805, simple_loss=0.258, pruned_loss=0.05153, over 7006.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2824, pruned_loss=0.06044, over 1418568.31 frames.], batch size: 16, lr: 1.03e-03
+2022-05-14 05:11:00,086 INFO [train.py:812] (1/8) Epoch 7, batch 2150, loss[loss=0.1795, simple_loss=0.2711, pruned_loss=0.04391, over 7413.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2822, pruned_loss=0.05955, over 1423748.08 frames.], batch size: 21, lr: 1.03e-03
+2022-05-14 05:11:57,834 INFO [train.py:812] (1/8) Epoch 7, batch 2200, loss[loss=0.1819, simple_loss=0.2631, pruned_loss=0.05034, over 7128.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2818, pruned_loss=0.05942, over 1421212.30 frames.], batch size: 17, lr: 1.03e-03
+2022-05-14 05:12:56,730 INFO [train.py:812] (1/8) Epoch 7, batch 2250, loss[loss=0.1799, simple_loss=0.256, pruned_loss=0.05187, over 7282.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2823, pruned_loss=0.06001, over 1416209.06 frames.], batch size: 17, lr: 1.03e-03
+2022-05-14 05:13:54,321 INFO [train.py:812] (1/8) Epoch 7, batch 2300, loss[loss=0.2492, simple_loss=0.3318, pruned_loss=0.08326, over 7196.00 frames.], tot_loss[loss=0.2006, simple_loss=0.282, pruned_loss=0.05958, over 1419226.94 frames.], batch size: 23, lr: 1.03e-03
+2022-05-14 05:14:53,675 INFO [train.py:812] (1/8) Epoch 7, batch 2350, loss[loss=0.2077, simple_loss=0.2929, pruned_loss=0.0613, over 7409.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2812, pruned_loss=0.05864, over 1417756.20 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:15:53,756 INFO [train.py:812] (1/8) Epoch 7, batch 2400, loss[loss=0.1574, simple_loss=0.2387, pruned_loss=0.03806, over 7276.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2809, pruned_loss=0.0589, over 1421275.02 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:16:51,046 INFO [train.py:812] (1/8) Epoch 7, batch 2450, loss[loss=0.1823, simple_loss=0.2774, pruned_loss=0.04364, over 7410.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2819, pruned_loss=0.05941, over 1417168.77 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:17:49,488 INFO [train.py:812] (1/8) Epoch 7, batch 2500, loss[loss=0.2216, simple_loss=0.3013, pruned_loss=0.07091, over 7325.00 frames.], tot_loss[loss=0.2016, simple_loss=0.283, pruned_loss=0.0601, over 1416865.12 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:18:48,416 INFO [train.py:812] (1/8) Epoch 7, batch 2550, loss[loss=0.2043, simple_loss=0.2849, pruned_loss=0.06182, over 7434.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2831, pruned_loss=0.05991, over 1423427.13 frames.], batch size: 20, lr: 1.02e-03
+2022-05-14 05:19:47,247 INFO [train.py:812] (1/8) Epoch 7, batch 2600, loss[loss=0.2015, simple_loss=0.2841, pruned_loss=0.05943, over 7156.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2831, pruned_loss=0.06012, over 1417314.59 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:20:45,572 INFO [train.py:812] (1/8) Epoch 7, batch 2650, loss[loss=0.172, simple_loss=0.2557, pruned_loss=0.04414, over 7167.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2827, pruned_loss=0.06031, over 1417818.41 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:21:44,769 INFO [train.py:812] (1/8) Epoch 7, batch 2700, loss[loss=0.1667, simple_loss=0.2481, pruned_loss=0.04267, over 6828.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2816, pruned_loss=0.05963, over 1419642.74 frames.], batch size: 15, lr: 1.02e-03
+2022-05-14 05:22:44,408 INFO [train.py:812] (1/8) Epoch 7, batch 2750, loss[loss=0.1817, simple_loss=0.2552, pruned_loss=0.05403, over 7405.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2827, pruned_loss=0.05987, over 1419981.51 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:23:44,352 INFO [train.py:812] (1/8) Epoch 7, batch 2800, loss[loss=0.1749, simple_loss=0.2576, pruned_loss=0.04606, over 6992.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2818, pruned_loss=0.0597, over 1417583.25 frames.], batch size: 16, lr: 1.02e-03
+2022-05-14 05:24:43,850 INFO [train.py:812] (1/8) Epoch 7, batch 2850, loss[loss=0.1792, simple_loss=0.2677, pruned_loss=0.04531, over 7316.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2801, pruned_loss=0.05888, over 1422417.12 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:25:43,738 INFO [train.py:812] (1/8) Epoch 7, batch 2900, loss[loss=0.311, simple_loss=0.3632, pruned_loss=0.1294, over 5294.00 frames.], tot_loss[loss=0.199, simple_loss=0.2803, pruned_loss=0.05885, over 1425107.00 frames.], batch size: 52, lr: 1.02e-03
+2022-05-14 05:26:42,748 INFO [train.py:812] (1/8) Epoch 7, batch 2950, loss[loss=0.1869, simple_loss=0.2768, pruned_loss=0.04855, over 7290.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2809, pruned_loss=0.05847, over 1424974.54 frames.], batch size: 25, lr: 1.01e-03
+2022-05-14 05:27:42,372 INFO [train.py:812] (1/8) Epoch 7, batch 3000, loss[loss=0.1955, simple_loss=0.2802, pruned_loss=0.05539, over 7182.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2808, pruned_loss=0.05841, over 1426594.78 frames.], batch size: 26, lr: 1.01e-03
+2022-05-14 05:27:42,373 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 05:27:49,661 INFO [train.py:841] (1/8) Epoch 7, validation: loss=0.1637, simple_loss=0.2662, pruned_loss=0.03066, over 698248.00 frames.
+2022-05-14 05:28:48,985 INFO [train.py:812] (1/8) Epoch 7, batch 3050, loss[loss=0.2099, simple_loss=0.2971, pruned_loss=0.06135, over 7156.00 frames.], tot_loss[loss=0.2002, simple_loss=0.282, pruned_loss=0.05923, over 1426730.30 frames.], batch size: 26, lr: 1.01e-03
+2022-05-14 05:29:48,815 INFO [train.py:812] (1/8) Epoch 7, batch 3100, loss[loss=0.2188, simple_loss=0.2985, pruned_loss=0.06954, over 7193.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2826, pruned_loss=0.05951, over 1424892.52 frames.], batch size: 26, lr: 1.01e-03
+2022-05-14 05:30:48,414 INFO [train.py:812] (1/8) Epoch 7, batch 3150, loss[loss=0.2094, simple_loss=0.3026, pruned_loss=0.05808, over 7057.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2821, pruned_loss=0.05966, over 1428333.48 frames.], batch size: 28, lr: 1.01e-03
+2022-05-14 05:31:47,453 INFO [train.py:812] (1/8) Epoch 7, batch 3200, loss[loss=0.1694, simple_loss=0.2627, pruned_loss=0.03811, over 7332.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2831, pruned_loss=0.05996, over 1424327.22 frames.], batch size: 22, lr: 1.01e-03
+2022-05-14 05:32:46,882 INFO [train.py:812] (1/8) Epoch 7, batch 3250, loss[loss=0.2003, simple_loss=0.2874, pruned_loss=0.05665, over 7091.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2817, pruned_loss=0.059, over 1424268.18 frames.], batch size: 28, lr: 1.01e-03
+2022-05-14 05:33:46,250 INFO [train.py:812] (1/8) Epoch 7, batch 3300, loss[loss=0.2009, simple_loss=0.2889, pruned_loss=0.05648, over 7158.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2822, pruned_loss=0.05923, over 1418871.35 frames.], batch size: 20, lr: 1.01e-03
+2022-05-14 05:34:45,880 INFO [train.py:812] (1/8) Epoch 7, batch 3350, loss[loss=0.1747, simple_loss=0.258, pruned_loss=0.0457, over 7161.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2825, pruned_loss=0.05899, over 1419906.68 frames.], batch size: 19, lr: 1.01e-03
+2022-05-14 05:35:44,953 INFO [train.py:812] (1/8) Epoch 7, batch 3400, loss[loss=0.2044, simple_loss=0.2895, pruned_loss=0.05964, over 7113.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2825, pruned_loss=0.05912, over 1422645.44 frames.], batch size: 21, lr: 1.01e-03
+2022-05-14 05:36:43,525 INFO [train.py:812] (1/8) Epoch 7, batch 3450, loss[loss=0.2085, simple_loss=0.3067, pruned_loss=0.05513, over 7309.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2829, pruned_loss=0.05915, over 1420177.17 frames.], batch size: 24, lr: 1.01e-03
+2022-05-14 05:37:43,008 INFO [train.py:812] (1/8) Epoch 7, batch 3500, loss[loss=0.2081, simple_loss=0.2986, pruned_loss=0.05875, over 7205.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2831, pruned_loss=0.05916, over 1422708.99 frames.], batch size: 21, lr: 1.01e-03
+2022-05-14 05:38:41,454 INFO [train.py:812] (1/8) Epoch 7, batch 3550, loss[loss=0.1756, simple_loss=0.2737, pruned_loss=0.03872, over 7380.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2824, pruned_loss=0.05868, over 1423923.02 frames.], batch size: 23, lr: 1.01e-03
+2022-05-14 05:39:40,562 INFO [train.py:812] (1/8) Epoch 7, batch 3600, loss[loss=0.2085, simple_loss=0.2844, pruned_loss=0.06626, over 7227.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2822, pruned_loss=0.0583, over 1425816.22 frames.], batch size: 21, lr: 1.00e-03
+2022-05-14 05:40:39,018 INFO [train.py:812] (1/8) Epoch 7, batch 3650, loss[loss=0.1964, simple_loss=0.2794, pruned_loss=0.05674, over 7140.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2826, pruned_loss=0.05837, over 1422761.47 frames.], batch size: 28, lr: 1.00e-03
+2022-05-14 05:41:38,736 INFO [train.py:812] (1/8) Epoch 7, batch 3700, loss[loss=0.1781, simple_loss=0.2552, pruned_loss=0.05049, over 7440.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2809, pruned_loss=0.05801, over 1424083.15 frames.], batch size: 20, lr: 1.00e-03
+2022-05-14 05:42:37,957 INFO [train.py:812] (1/8) Epoch 7, batch 3750, loss[loss=0.2767, simple_loss=0.3308, pruned_loss=0.1113, over 5132.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2806, pruned_loss=0.05856, over 1424218.32 frames.], batch size: 52, lr: 1.00e-03
+2022-05-14 05:43:37,511 INFO [train.py:812] (1/8) Epoch 7, batch 3800, loss[loss=0.1632, simple_loss=0.2507, pruned_loss=0.03785, over 7372.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2809, pruned_loss=0.05839, over 1421392.57 frames.], batch size: 19, lr: 1.00e-03
+2022-05-14 05:44:35,595 INFO [train.py:812] (1/8) Epoch 7, batch 3850, loss[loss=0.1714, simple_loss=0.2633, pruned_loss=0.03979, over 7125.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2796, pruned_loss=0.05784, over 1423929.12 frames.], batch size: 17, lr: 1.00e-03
+2022-05-14 05:45:34,808 INFO [train.py:812] (1/8) Epoch 7, batch 3900, loss[loss=0.1796, simple_loss=0.2633, pruned_loss=0.04793, over 7172.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2791, pruned_loss=0.0577, over 1424602.02 frames.], batch size: 18, lr: 1.00e-03
+2022-05-14 05:46:31,678 INFO [train.py:812] (1/8) Epoch 7, batch 3950, loss[loss=0.2077, simple_loss=0.2933, pruned_loss=0.06104, over 7332.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2782, pruned_loss=0.057, over 1427070.49 frames.], batch size: 22, lr: 9.99e-04
+2022-05-14 05:47:30,572 INFO [train.py:812] (1/8) Epoch 7, batch 4000, loss[loss=0.237, simple_loss=0.3139, pruned_loss=0.08006, over 6876.00 frames.], tot_loss[loss=0.196, simple_loss=0.2782, pruned_loss=0.05688, over 1431682.74 frames.], batch size: 31, lr: 9.98e-04
+2022-05-14 05:48:29,672 INFO [train.py:812] (1/8) Epoch 7, batch 4050, loss[loss=0.1993, simple_loss=0.285, pruned_loss=0.05683, over 7163.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2786, pruned_loss=0.05696, over 1430119.91 frames.], batch size: 18, lr: 9.98e-04
+2022-05-14 05:49:28,787 INFO [train.py:812] (1/8) Epoch 7, batch 4100, loss[loss=0.1932, simple_loss=0.2806, pruned_loss=0.05286, over 7098.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2793, pruned_loss=0.05794, over 1425438.31 frames.], batch size: 21, lr: 9.97e-04
+2022-05-14 05:50:26,074 INFO [train.py:812] (1/8) Epoch 7, batch 4150, loss[loss=0.2045, simple_loss=0.2904, pruned_loss=0.05926, over 7183.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2796, pruned_loss=0.05831, over 1425651.20 frames.], batch size: 23, lr: 9.96e-04
+2022-05-14 05:51:25,283 INFO [train.py:812] (1/8) Epoch 7, batch 4200, loss[loss=0.1857, simple_loss=0.267, pruned_loss=0.05224, over 7292.00 frames.], tot_loss[loss=0.197, simple_loss=0.279, pruned_loss=0.05755, over 1427855.21 frames.], batch size: 17, lr: 9.95e-04
+2022-05-14 05:52:24,625 INFO [train.py:812] (1/8) Epoch 7, batch 4250, loss[loss=0.2084, simple_loss=0.2849, pruned_loss=0.06593, over 7435.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2792, pruned_loss=0.05779, over 1422410.67 frames.], batch size: 20, lr: 9.95e-04
+2022-05-14 05:53:23,914 INFO [train.py:812] (1/8) Epoch 7, batch 4300, loss[loss=0.2128, simple_loss=0.2998, pruned_loss=0.06289, over 7235.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2815, pruned_loss=0.05895, over 1416899.19 frames.], batch size: 20, lr: 9.94e-04
+2022-05-14 05:54:23,298 INFO [train.py:812] (1/8) Epoch 7, batch 4350, loss[loss=0.2171, simple_loss=0.2923, pruned_loss=0.07097, over 6575.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2813, pruned_loss=0.05865, over 1411083.76 frames.], batch size: 38, lr: 9.93e-04
+2022-05-14 05:55:22,292 INFO [train.py:812] (1/8) Epoch 7, batch 4400, loss[loss=0.2114, simple_loss=0.3035, pruned_loss=0.05968, over 6735.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2816, pruned_loss=0.05917, over 1412142.44 frames.], batch size: 31, lr: 9.92e-04
+2022-05-14 05:56:20,595 INFO [train.py:812] (1/8) Epoch 7, batch 4450, loss[loss=0.2189, simple_loss=0.306, pruned_loss=0.06584, over 7210.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2826, pruned_loss=0.05948, over 1406841.38 frames.], batch size: 22, lr: 9.92e-04
+2022-05-14 05:57:24,426 INFO [train.py:812] (1/8) Epoch 7, batch 4500, loss[loss=0.2106, simple_loss=0.2878, pruned_loss=0.06668, over 7192.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2835, pruned_loss=0.05959, over 1404433.93 frames.], batch size: 22, lr: 9.91e-04
+2022-05-14 05:58:22,211 INFO [train.py:812] (1/8) Epoch 7, batch 4550, loss[loss=0.259, simple_loss=0.3285, pruned_loss=0.09477, over 5245.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2851, pruned_loss=0.06027, over 1390020.26 frames.], batch size: 52, lr: 9.90e-04
+2022-05-14 05:59:32,589 INFO [train.py:812] (1/8) Epoch 8, batch 0, loss[loss=0.2111, simple_loss=0.3069, pruned_loss=0.05766, over 7326.00 frames.], tot_loss[loss=0.2111, simple_loss=0.3069, pruned_loss=0.05766, over 7326.00 frames.], batch size: 22, lr: 9.49e-04
+2022-05-14 06:00:31,165 INFO [train.py:812] (1/8) Epoch 8, batch 50, loss[loss=0.1813, simple_loss=0.2546, pruned_loss=0.054, over 7124.00 frames.], tot_loss[loss=0.2004, simple_loss=0.284, pruned_loss=0.05843, over 320829.26 frames.], batch size: 17, lr: 9.48e-04
+2022-05-14 06:01:30,400 INFO [train.py:812] (1/8) Epoch 8, batch 100, loss[loss=0.2168, simple_loss=0.2944, pruned_loss=0.06963, over 7302.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2842, pruned_loss=0.05852, over 568921.19 frames.], batch size: 25, lr: 9.48e-04
+2022-05-14 06:02:29,677 INFO [train.py:812] (1/8) Epoch 8, batch 150, loss[loss=0.1935, simple_loss=0.2815, pruned_loss=0.05281, over 7107.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2798, pruned_loss=0.05686, over 759068.65 frames.], batch size: 21, lr: 9.47e-04
+2022-05-14 06:03:26,754 INFO [train.py:812] (1/8) Epoch 8, batch 200, loss[loss=0.2293, simple_loss=0.3147, pruned_loss=0.07193, over 7221.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2788, pruned_loss=0.05597, over 907429.59 frames.], batch size: 22, lr: 9.46e-04
+2022-05-14 06:04:24,360 INFO [train.py:812] (1/8) Epoch 8, batch 250, loss[loss=0.1748, simple_loss=0.2572, pruned_loss=0.0462, over 7120.00 frames.], tot_loss[loss=0.1958, simple_loss=0.279, pruned_loss=0.05633, over 1020924.38 frames.], batch size: 21, lr: 9.46e-04
+2022-05-14 06:05:21,312 INFO [train.py:812] (1/8) Epoch 8, batch 300, loss[loss=0.1831, simple_loss=0.2626, pruned_loss=0.05179, over 7064.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2797, pruned_loss=0.05668, over 1106836.39 frames.], batch size: 18, lr: 9.45e-04
+2022-05-14 06:06:19,883 INFO [train.py:812] (1/8) Epoch 8, batch 350, loss[loss=0.2219, simple_loss=0.305, pruned_loss=0.06943, over 7109.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2789, pruned_loss=0.05615, over 1177863.14 frames.], batch size: 21, lr: 9.44e-04
+2022-05-14 06:07:19,503 INFO [train.py:812] (1/8) Epoch 8, batch 400, loss[loss=0.2338, simple_loss=0.3129, pruned_loss=0.07737, over 5114.00 frames.], tot_loss[loss=0.197, simple_loss=0.2798, pruned_loss=0.05706, over 1230676.68 frames.], batch size: 52, lr: 9.43e-04
+2022-05-14 06:08:18,800 INFO [train.py:812] (1/8) Epoch 8, batch 450, loss[loss=0.1761, simple_loss=0.2541, pruned_loss=0.04908, over 6814.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2786, pruned_loss=0.05656, over 1272187.33 frames.], batch size: 15, lr: 9.43e-04
+2022-05-14 06:09:18,363 INFO [train.py:812] (1/8) Epoch 8, batch 500, loss[loss=0.1812, simple_loss=0.2802, pruned_loss=0.04108, over 7206.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2777, pruned_loss=0.05603, over 1304938.98 frames.], batch size: 23, lr: 9.42e-04
+2022-05-14 06:10:16,963 INFO [train.py:812] (1/8) Epoch 8, batch 550, loss[loss=0.2051, simple_loss=0.2769, pruned_loss=0.06666, over 7208.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2786, pruned_loss=0.05649, over 1333070.66 frames.], batch size: 23, lr: 9.41e-04
+2022-05-14 06:11:16,906 INFO [train.py:812] (1/8) Epoch 8, batch 600, loss[loss=0.1851, simple_loss=0.2717, pruned_loss=0.04925, over 7230.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2794, pruned_loss=0.05679, over 1353053.88 frames.], batch size: 21, lr: 9.41e-04
+2022-05-14 06:12:15,261 INFO [train.py:812] (1/8) Epoch 8, batch 650, loss[loss=0.1872, simple_loss=0.2709, pruned_loss=0.05172, over 7256.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2785, pruned_loss=0.05592, over 1369188.01 frames.], batch size: 19, lr: 9.40e-04
+2022-05-14 06:13:14,183 INFO [train.py:812] (1/8) Epoch 8, batch 700, loss[loss=0.2355, simple_loss=0.3047, pruned_loss=0.08318, over 4985.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2796, pruned_loss=0.05611, over 1376446.97 frames.], batch size: 52, lr: 9.39e-04
+2022-05-14 06:14:13,340 INFO [train.py:812] (1/8) Epoch 8, batch 750, loss[loss=0.1868, simple_loss=0.26, pruned_loss=0.05682, over 7357.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2785, pruned_loss=0.05617, over 1384913.06 frames.], batch size: 19, lr: 9.39e-04
+2022-05-14 06:15:12,814 INFO [train.py:812] (1/8) Epoch 8, batch 800, loss[loss=0.1971, simple_loss=0.2855, pruned_loss=0.05433, over 6489.00 frames.], tot_loss[loss=0.1968, simple_loss=0.28, pruned_loss=0.05678, over 1389515.25 frames.], batch size: 38, lr: 9.38e-04
+2022-05-14 06:16:12,231 INFO [train.py:812] (1/8) Epoch 8, batch 850, loss[loss=0.175, simple_loss=0.2512, pruned_loss=0.04939, over 7394.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2777, pruned_loss=0.05612, over 1398408.47 frames.], batch size: 18, lr: 9.37e-04
+2022-05-14 06:17:11,301 INFO [train.py:812] (1/8) Epoch 8, batch 900, loss[loss=0.2138, simple_loss=0.2954, pruned_loss=0.06609, over 6702.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2776, pruned_loss=0.05656, over 1398441.87 frames.], batch size: 31, lr: 9.36e-04
+2022-05-14 06:18:09,038 INFO [train.py:812] (1/8) Epoch 8, batch 950, loss[loss=0.1858, simple_loss=0.2644, pruned_loss=0.05361, over 7231.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2794, pruned_loss=0.05744, over 1404830.92 frames.], batch size: 20, lr: 9.36e-04
+2022-05-14 06:19:08,068 INFO [train.py:812] (1/8) Epoch 8, batch 1000, loss[loss=0.2051, simple_loss=0.2754, pruned_loss=0.06736, over 7216.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2798, pruned_loss=0.0574, over 1409189.84 frames.], batch size: 21, lr: 9.35e-04
+2022-05-14 06:20:06,224 INFO [train.py:812] (1/8) Epoch 8, batch 1050, loss[loss=0.1652, simple_loss=0.2436, pruned_loss=0.04335, over 7130.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2797, pruned_loss=0.0569, over 1406969.76 frames.], batch size: 17, lr: 9.34e-04
+2022-05-14 06:21:04,768 INFO [train.py:812] (1/8) Epoch 8, batch 1100, loss[loss=0.1862, simple_loss=0.2839, pruned_loss=0.04426, over 7204.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2788, pruned_loss=0.05675, over 1410589.82 frames.], batch size: 22, lr: 9.34e-04
+2022-05-14 06:22:02,858 INFO [train.py:812] (1/8) Epoch 8, batch 1150, loss[loss=0.2143, simple_loss=0.2937, pruned_loss=0.06748, over 5159.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2792, pruned_loss=0.05666, over 1416480.34 frames.], batch size: 52, lr: 9.33e-04
+2022-05-14 06:23:10,860 INFO [train.py:812] (1/8) Epoch 8, batch 1200, loss[loss=0.1893, simple_loss=0.2805, pruned_loss=0.04911, over 7140.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2785, pruned_loss=0.05604, over 1421098.92 frames.], batch size: 20, lr: 9.32e-04
+2022-05-14 06:24:10,077 INFO [train.py:812] (1/8) Epoch 8, batch 1250, loss[loss=0.1619, simple_loss=0.2375, pruned_loss=0.04313, over 7296.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2764, pruned_loss=0.05523, over 1420196.46 frames.], batch size: 18, lr: 9.32e-04
+2022-05-14 06:25:09,376 INFO [train.py:812] (1/8) Epoch 8, batch 1300, loss[loss=0.195, simple_loss=0.2859, pruned_loss=0.05198, over 7146.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2772, pruned_loss=0.05519, over 1416973.18 frames.], batch size: 20, lr: 9.31e-04
+2022-05-14 06:26:08,276 INFO [train.py:812] (1/8) Epoch 8, batch 1350, loss[loss=0.1805, simple_loss=0.2637, pruned_loss=0.04862, over 7157.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2781, pruned_loss=0.05565, over 1416120.25 frames.], batch size: 19, lr: 9.30e-04
+2022-05-14 06:27:08,004 INFO [train.py:812] (1/8) Epoch 8, batch 1400, loss[loss=0.1757, simple_loss=0.2504, pruned_loss=0.05054, over 7286.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2783, pruned_loss=0.05594, over 1416782.28 frames.], batch size: 18, lr: 9.30e-04
+2022-05-14 06:28:06,826 INFO [train.py:812] (1/8) Epoch 8, batch 1450, loss[loss=0.1636, simple_loss=0.2501, pruned_loss=0.03855, over 7168.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2779, pruned_loss=0.05559, over 1416897.02 frames.], batch size: 18, lr: 9.29e-04
+2022-05-14 06:29:06,643 INFO [train.py:812] (1/8) Epoch 8, batch 1500, loss[loss=0.1807, simple_loss=0.2623, pruned_loss=0.04959, over 7421.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2773, pruned_loss=0.05558, over 1416252.68 frames.], batch size: 18, lr: 9.28e-04
+2022-05-14 06:30:05,549 INFO [train.py:812] (1/8) Epoch 8, batch 1550, loss[loss=0.2179, simple_loss=0.299, pruned_loss=0.0684, over 7212.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2782, pruned_loss=0.05573, over 1421636.68 frames.], batch size: 22, lr: 9.28e-04
+2022-05-14 06:31:05,140 INFO [train.py:812] (1/8) Epoch 8, batch 1600, loss[loss=0.2111, simple_loss=0.3023, pruned_loss=0.05991, over 6186.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2792, pruned_loss=0.05616, over 1421888.18 frames.], batch size: 37, lr: 9.27e-04
+2022-05-14 06:32:04,296 INFO [train.py:812] (1/8) Epoch 8, batch 1650, loss[loss=0.194, simple_loss=0.2862, pruned_loss=0.0509, over 7259.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2795, pruned_loss=0.05587, over 1420334.55 frames.], batch size: 24, lr: 9.26e-04
+2022-05-14 06:33:04,112 INFO [train.py:812] (1/8) Epoch 8, batch 1700, loss[loss=0.2359, simple_loss=0.325, pruned_loss=0.07339, over 7319.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2795, pruned_loss=0.05597, over 1420749.02 frames.], batch size: 21, lr: 9.26e-04
+2022-05-14 06:34:03,593 INFO [train.py:812] (1/8) Epoch 8, batch 1750, loss[loss=0.1809, simple_loss=0.2633, pruned_loss=0.04932, over 7346.00 frames.], tot_loss[loss=0.1954, simple_loss=0.279, pruned_loss=0.05594, over 1421063.62 frames.], batch size: 22, lr: 9.25e-04
+2022-05-14 06:35:12,519 INFO [train.py:812] (1/8) Epoch 8, batch 1800, loss[loss=0.1773, simple_loss=0.277, pruned_loss=0.03879, over 7335.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2771, pruned_loss=0.05525, over 1421970.88 frames.], batch size: 22, lr: 9.24e-04
+2022-05-14 06:36:21,368 INFO [train.py:812] (1/8) Epoch 8, batch 1850, loss[loss=0.1934, simple_loss=0.2688, pruned_loss=0.05898, over 7227.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2775, pruned_loss=0.05544, over 1423715.27 frames.], batch size: 20, lr: 9.24e-04
+2022-05-14 06:37:30,720 INFO [train.py:812] (1/8) Epoch 8, batch 1900, loss[loss=0.2172, simple_loss=0.2975, pruned_loss=0.0685, over 7279.00 frames.], tot_loss[loss=0.1936, simple_loss=0.277, pruned_loss=0.05512, over 1421793.16 frames.], batch size: 25, lr: 9.23e-04
+2022-05-14 06:38:48,460 INFO [train.py:812] (1/8) Epoch 8, batch 1950, loss[loss=0.1617, simple_loss=0.2423, pruned_loss=0.04049, over 7002.00 frames.], tot_loss[loss=0.193, simple_loss=0.2766, pruned_loss=0.05469, over 1426427.61 frames.], batch size: 16, lr: 9.22e-04
+2022-05-14 06:40:06,954 INFO [train.py:812] (1/8) Epoch 8, batch 2000, loss[loss=0.2123, simple_loss=0.2979, pruned_loss=0.06339, over 7122.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2762, pruned_loss=0.05431, over 1426967.89 frames.], batch size: 21, lr: 9.22e-04
+2022-05-14 06:41:06,018 INFO [train.py:812] (1/8) Epoch 8, batch 2050, loss[loss=0.2484, simple_loss=0.3142, pruned_loss=0.09124, over 5250.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2774, pruned_loss=0.05524, over 1420802.73 frames.], batch size: 52, lr: 9.21e-04
+2022-05-14 06:42:04,901 INFO [train.py:812] (1/8) Epoch 8, batch 2100, loss[loss=0.1861, simple_loss=0.274, pruned_loss=0.04908, over 7230.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2777, pruned_loss=0.05538, over 1416313.33 frames.], batch size: 20, lr: 9.20e-04
+2022-05-14 06:43:03,993 INFO [train.py:812] (1/8) Epoch 8, batch 2150, loss[loss=0.1938, simple_loss=0.2784, pruned_loss=0.05466, over 7218.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2773, pruned_loss=0.05524, over 1418372.57 frames.], batch size: 22, lr: 9.20e-04
+2022-05-14 06:44:02,972 INFO [train.py:812] (1/8) Epoch 8, batch 2200, loss[loss=0.2032, simple_loss=0.2904, pruned_loss=0.05796, over 7278.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2754, pruned_loss=0.05455, over 1415880.71 frames.], batch size: 24, lr: 9.19e-04
+2022-05-14 06:45:01,872 INFO [train.py:812] (1/8) Epoch 8, batch 2250, loss[loss=0.2037, simple_loss=0.2918, pruned_loss=0.05781, over 7206.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2752, pruned_loss=0.05487, over 1411174.74 frames.], batch size: 23, lr: 9.18e-04
+2022-05-14 06:46:00,796 INFO [train.py:812] (1/8) Epoch 8, batch 2300, loss[loss=0.1805, simple_loss=0.2581, pruned_loss=0.05147, over 7415.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2763, pruned_loss=0.05557, over 1411596.11 frames.], batch size: 18, lr: 9.18e-04
+2022-05-14 06:46:59,522 INFO [train.py:812] (1/8) Epoch 8, batch 2350, loss[loss=0.1723, simple_loss=0.2519, pruned_loss=0.04633, over 7076.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2762, pruned_loss=0.05532, over 1411243.24 frames.], batch size: 18, lr: 9.17e-04
+2022-05-14 06:47:58,464 INFO [train.py:812] (1/8) Epoch 8, batch 2400, loss[loss=0.1857, simple_loss=0.2734, pruned_loss=0.04897, over 7266.00 frames.], tot_loss[loss=0.193, simple_loss=0.2759, pruned_loss=0.05506, over 1415696.31 frames.], batch size: 19, lr: 9.16e-04
+2022-05-14 06:48:57,534 INFO [train.py:812] (1/8) Epoch 8, batch 2450, loss[loss=0.2441, simple_loss=0.3133, pruned_loss=0.08741, over 7309.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2763, pruned_loss=0.05496, over 1422346.15 frames.], batch size: 24, lr: 9.16e-04
+2022-05-14 06:49:56,997 INFO [train.py:812] (1/8) Epoch 8, batch 2500, loss[loss=0.1853, simple_loss=0.2706, pruned_loss=0.04996, over 7321.00 frames.], tot_loss[loss=0.194, simple_loss=0.2771, pruned_loss=0.05542, over 1420829.71 frames.], batch size: 21, lr: 9.15e-04
+2022-05-14 06:50:55,692 INFO [train.py:812] (1/8) Epoch 8, batch 2550, loss[loss=0.1777, simple_loss=0.2659, pruned_loss=0.04474, over 7352.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2767, pruned_loss=0.0555, over 1424740.68 frames.], batch size: 19, lr: 9.14e-04
+2022-05-14 06:51:54,445 INFO [train.py:812] (1/8) Epoch 8, batch 2600, loss[loss=0.183, simple_loss=0.2695, pruned_loss=0.04819, over 7197.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2766, pruned_loss=0.0551, over 1425496.93 frames.], batch size: 16, lr: 9.14e-04
+2022-05-14 06:52:51,846 INFO [train.py:812] (1/8) Epoch 8, batch 2650, loss[loss=0.1962, simple_loss=0.28, pruned_loss=0.05616, over 7118.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2772, pruned_loss=0.05501, over 1426305.46 frames.], batch size: 21, lr: 9.13e-04
+2022-05-14 06:53:49,753 INFO [train.py:812] (1/8) Epoch 8, batch 2700, loss[loss=0.1842, simple_loss=0.2604, pruned_loss=0.05401, over 6825.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2764, pruned_loss=0.05473, over 1428810.69 frames.], batch size: 15, lr: 9.12e-04
+2022-05-14 06:54:48,259 INFO [train.py:812] (1/8) Epoch 8, batch 2750, loss[loss=0.169, simple_loss=0.2427, pruned_loss=0.04766, over 6992.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2757, pruned_loss=0.05473, over 1427653.20 frames.], batch size: 16, lr: 9.12e-04
+2022-05-14 06:55:46,856 INFO [train.py:812] (1/8) Epoch 8, batch 2800, loss[loss=0.1888, simple_loss=0.2656, pruned_loss=0.05604, over 7143.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2767, pruned_loss=0.05499, over 1428133.90 frames.], batch size: 20, lr: 9.11e-04
+2022-05-14 06:56:44,428 INFO [train.py:812] (1/8) Epoch 8, batch 2850, loss[loss=0.1944, simple_loss=0.2693, pruned_loss=0.05974, over 7210.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2763, pruned_loss=0.05496, over 1427554.34 frames.], batch size: 22, lr: 9.11e-04
+2022-05-14 06:57:43,808 INFO [train.py:812] (1/8) Epoch 8, batch 2900, loss[loss=0.1812, simple_loss=0.2663, pruned_loss=0.04804, over 7155.00 frames.], tot_loss[loss=0.1938, simple_loss=0.277, pruned_loss=0.05527, over 1426868.90 frames.], batch size: 17, lr: 9.10e-04
+2022-05-14 06:58:42,755 INFO [train.py:812] (1/8) Epoch 8, batch 2950, loss[loss=0.1637, simple_loss=0.2515, pruned_loss=0.03795, over 7063.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2761, pruned_loss=0.05487, over 1426015.28 frames.], batch size: 18, lr: 9.09e-04
+2022-05-14 06:59:42,232 INFO [train.py:812] (1/8) Epoch 8, batch 3000, loss[loss=0.2356, simple_loss=0.309, pruned_loss=0.08104, over 4947.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2762, pruned_loss=0.05478, over 1421869.32 frames.], batch size: 52, lr: 9.09e-04
+2022-05-14 06:59:42,234 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 06:59:50,552 INFO [train.py:841] (1/8) Epoch 8, validation: loss=0.1612, simple_loss=0.2635, pruned_loss=0.0294, over 698248.00 frames.
+2022-05-14 07:00:48,452 INFO [train.py:812] (1/8) Epoch 8, batch 3050, loss[loss=0.2164, simple_loss=0.2933, pruned_loss=0.06979, over 6394.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2754, pruned_loss=0.05456, over 1415890.59 frames.], batch size: 37, lr: 9.08e-04
+2022-05-14 07:01:48,161 INFO [train.py:812] (1/8) Epoch 8, batch 3100, loss[loss=0.2035, simple_loss=0.2772, pruned_loss=0.06486, over 7256.00 frames.], tot_loss[loss=0.1919, simple_loss=0.275, pruned_loss=0.05441, over 1420634.36 frames.], batch size: 19, lr: 9.07e-04
+2022-05-14 07:02:45,300 INFO [train.py:812] (1/8) Epoch 8, batch 3150, loss[loss=0.2072, simple_loss=0.2876, pruned_loss=0.06345, over 7439.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2747, pruned_loss=0.0546, over 1422261.82 frames.], batch size: 20, lr: 9.07e-04
+2022-05-14 07:03:44,357 INFO [train.py:812] (1/8) Epoch 8, batch 3200, loss[loss=0.1645, simple_loss=0.2494, pruned_loss=0.03985, over 7426.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2741, pruned_loss=0.05423, over 1424827.24 frames.], batch size: 20, lr: 9.06e-04
+2022-05-14 07:04:43,321 INFO [train.py:812] (1/8) Epoch 8, batch 3250, loss[loss=0.1875, simple_loss=0.2719, pruned_loss=0.05151, over 7047.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2755, pruned_loss=0.05471, over 1423967.05 frames.], batch size: 28, lr: 9.05e-04
+2022-05-14 07:05:41,209 INFO [train.py:812] (1/8) Epoch 8, batch 3300, loss[loss=0.2203, simple_loss=0.3114, pruned_loss=0.06467, over 6818.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2758, pruned_loss=0.05472, over 1422436.12 frames.], batch size: 31, lr: 9.05e-04
+2022-05-14 07:06:40,372 INFO [train.py:812] (1/8) Epoch 8, batch 3350, loss[loss=0.1602, simple_loss=0.2504, pruned_loss=0.03501, over 7435.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2754, pruned_loss=0.05414, over 1421540.91 frames.], batch size: 20, lr: 9.04e-04
+2022-05-14 07:07:39,824 INFO [train.py:812] (1/8) Epoch 8, batch 3400, loss[loss=0.2003, simple_loss=0.2866, pruned_loss=0.05697, over 6749.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2758, pruned_loss=0.05442, over 1418863.37 frames.], batch size: 31, lr: 9.04e-04
+2022-05-14 07:08:38,477 INFO [train.py:812] (1/8) Epoch 8, batch 3450, loss[loss=0.177, simple_loss=0.2631, pruned_loss=0.04546, over 7431.00 frames.], tot_loss[loss=0.194, simple_loss=0.2774, pruned_loss=0.05535, over 1422709.71 frames.], batch size: 18, lr: 9.03e-04
+2022-05-14 07:09:37,924 INFO [train.py:812] (1/8) Epoch 8, batch 3500, loss[loss=0.2179, simple_loss=0.3019, pruned_loss=0.06699, over 7362.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2779, pruned_loss=0.05558, over 1422155.59 frames.], batch size: 23, lr: 9.02e-04
+2022-05-14 07:10:37,039 INFO [train.py:812] (1/8) Epoch 8, batch 3550, loss[loss=0.2043, simple_loss=0.2827, pruned_loss=0.06289, over 7261.00 frames.], tot_loss[loss=0.194, simple_loss=0.2775, pruned_loss=0.05529, over 1422995.38 frames.], batch size: 19, lr: 9.02e-04
+2022-05-14 07:11:36,658 INFO [train.py:812] (1/8) Epoch 8, batch 3600, loss[loss=0.1954, simple_loss=0.2665, pruned_loss=0.06217, over 7277.00 frames.], tot_loss[loss=0.1928, simple_loss=0.276, pruned_loss=0.05483, over 1421236.66 frames.], batch size: 17, lr: 9.01e-04
+2022-05-14 07:12:33,625 INFO [train.py:812] (1/8) Epoch 8, batch 3650, loss[loss=0.1843, simple_loss=0.2694, pruned_loss=0.04957, over 7406.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2777, pruned_loss=0.05562, over 1416228.54 frames.], batch size: 21, lr: 9.01e-04
+2022-05-14 07:13:32,605 INFO [train.py:812] (1/8) Epoch 8, batch 3700, loss[loss=0.2134, simple_loss=0.2902, pruned_loss=0.0683, over 7220.00 frames.], tot_loss[loss=0.1923, simple_loss=0.276, pruned_loss=0.05431, over 1419887.80 frames.], batch size: 21, lr: 9.00e-04
+2022-05-14 07:14:31,406 INFO [train.py:812] (1/8) Epoch 8, batch 3750, loss[loss=0.194, simple_loss=0.2815, pruned_loss=0.0532, over 7164.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2763, pruned_loss=0.05444, over 1416693.84 frames.], batch size: 19, lr: 8.99e-04
+2022-05-14 07:15:30,605 INFO [train.py:812] (1/8) Epoch 8, batch 3800, loss[loss=0.1983, simple_loss=0.2808, pruned_loss=0.05791, over 7286.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2773, pruned_loss=0.05484, over 1420304.29 frames.], batch size: 24, lr: 8.99e-04
+2022-05-14 07:16:28,746 INFO [train.py:812] (1/8) Epoch 8, batch 3850, loss[loss=0.2131, simple_loss=0.302, pruned_loss=0.06214, over 7224.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2785, pruned_loss=0.05514, over 1417450.36 frames.], batch size: 21, lr: 8.98e-04
+2022-05-14 07:17:33,253 INFO [train.py:812] (1/8) Epoch 8, batch 3900, loss[loss=0.2164, simple_loss=0.2921, pruned_loss=0.07039, over 7426.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2773, pruned_loss=0.05488, over 1421844.44 frames.], batch size: 20, lr: 8.97e-04
+2022-05-14 07:18:32,357 INFO [train.py:812] (1/8) Epoch 8, batch 3950, loss[loss=0.1739, simple_loss=0.2537, pruned_loss=0.04707, over 6992.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2763, pruned_loss=0.05417, over 1424385.59 frames.], batch size: 16, lr: 8.97e-04
+2022-05-14 07:19:31,323 INFO [train.py:812] (1/8) Epoch 8, batch 4000, loss[loss=0.2074, simple_loss=0.2909, pruned_loss=0.06197, over 7141.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2762, pruned_loss=0.05415, over 1423288.11 frames.], batch size: 20, lr: 8.96e-04
+2022-05-14 07:20:29,698 INFO [train.py:812] (1/8) Epoch 8, batch 4050, loss[loss=0.1866, simple_loss=0.2679, pruned_loss=0.0526, over 7412.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2755, pruned_loss=0.05404, over 1425965.23 frames.], batch size: 21, lr: 8.96e-04
+2022-05-14 07:21:29,473 INFO [train.py:812] (1/8) Epoch 8, batch 4100, loss[loss=0.1822, simple_loss=0.2486, pruned_loss=0.05791, over 7283.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2763, pruned_loss=0.05501, over 1419203.68 frames.], batch size: 17, lr: 8.95e-04
+2022-05-14 07:22:28,430 INFO [train.py:812] (1/8) Epoch 8, batch 4150, loss[loss=0.2101, simple_loss=0.2891, pruned_loss=0.06555, over 7346.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2777, pruned_loss=0.05547, over 1413646.16 frames.], batch size: 22, lr: 8.94e-04
+2022-05-14 07:23:28,040 INFO [train.py:812] (1/8) Epoch 8, batch 4200, loss[loss=0.1952, simple_loss=0.2838, pruned_loss=0.05328, over 7142.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2776, pruned_loss=0.05496, over 1415910.01 frames.], batch size: 20, lr: 8.94e-04
+2022-05-14 07:24:27,288 INFO [train.py:812] (1/8) Epoch 8, batch 4250, loss[loss=0.1971, simple_loss=0.2935, pruned_loss=0.05038, over 7213.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2769, pruned_loss=0.05437, over 1419757.28 frames.], batch size: 22, lr: 8.93e-04
+2022-05-14 07:25:26,245 INFO [train.py:812] (1/8) Epoch 8, batch 4300, loss[loss=0.2011, simple_loss=0.287, pruned_loss=0.05759, over 7320.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2762, pruned_loss=0.05422, over 1419234.06 frames.], batch size: 21, lr: 8.93e-04
+2022-05-14 07:26:25,344 INFO [train.py:812] (1/8) Epoch 8, batch 4350, loss[loss=0.2108, simple_loss=0.3015, pruned_loss=0.06011, over 7113.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2756, pruned_loss=0.05413, over 1414795.81 frames.], batch size: 21, lr: 8.92e-04
+2022-05-14 07:27:24,393 INFO [train.py:812] (1/8) Epoch 8, batch 4400, loss[loss=0.2179, simple_loss=0.2952, pruned_loss=0.07028, over 7102.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2749, pruned_loss=0.05382, over 1417024.62 frames.], batch size: 28, lr: 8.91e-04
+2022-05-14 07:28:23,663 INFO [train.py:812] (1/8) Epoch 8, batch 4450, loss[loss=0.1899, simple_loss=0.2741, pruned_loss=0.05283, over 7322.00 frames.], tot_loss[loss=0.191, simple_loss=0.2744, pruned_loss=0.05378, over 1417485.17 frames.], batch size: 20, lr: 8.91e-04
+2022-05-14 07:29:23,594 INFO [train.py:812] (1/8) Epoch 8, batch 4500, loss[loss=0.1874, simple_loss=0.2639, pruned_loss=0.05538, over 7157.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2735, pruned_loss=0.05362, over 1415528.37 frames.], batch size: 18, lr: 8.90e-04
+2022-05-14 07:30:22,905 INFO [train.py:812] (1/8) Epoch 8, batch 4550, loss[loss=0.1663, simple_loss=0.2462, pruned_loss=0.0432, over 7288.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2731, pruned_loss=0.05427, over 1399479.84 frames.], batch size: 17, lr: 8.90e-04
+2022-05-14 07:31:33,242 INFO [train.py:812] (1/8) Epoch 9, batch 0, loss[loss=0.2126, simple_loss=0.2918, pruned_loss=0.06667, over 7203.00 frames.], tot_loss[loss=0.2126, simple_loss=0.2918, pruned_loss=0.06667, over 7203.00 frames.], batch size: 23, lr: 8.54e-04
+2022-05-14 07:32:31,241 INFO [train.py:812] (1/8) Epoch 9, batch 50, loss[loss=0.16, simple_loss=0.2493, pruned_loss=0.0354, over 7024.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2803, pruned_loss=0.05573, over 319289.86 frames.], batch size: 28, lr: 8.53e-04
+2022-05-14 07:33:31,084 INFO [train.py:812] (1/8) Epoch 9, batch 100, loss[loss=0.2163, simple_loss=0.3002, pruned_loss=0.06619, over 7233.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2772, pruned_loss=0.0545, over 566674.81 frames.], batch size: 20, lr: 8.53e-04
+2022-05-14 07:34:29,323 INFO [train.py:812] (1/8) Epoch 9, batch 150, loss[loss=0.2109, simple_loss=0.2857, pruned_loss=0.06805, over 5153.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2761, pruned_loss=0.05318, over 753903.15 frames.], batch size: 52, lr: 8.52e-04
+2022-05-14 07:35:29,141 INFO [train.py:812] (1/8) Epoch 9, batch 200, loss[loss=0.2017, simple_loss=0.2849, pruned_loss=0.05925, over 7186.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2755, pruned_loss=0.05314, over 901870.92 frames.], batch size: 22, lr: 8.51e-04
+2022-05-14 07:36:28,011 INFO [train.py:812] (1/8) Epoch 9, batch 250, loss[loss=0.1651, simple_loss=0.2511, pruned_loss=0.03952, over 7429.00 frames.], tot_loss[loss=0.1902, simple_loss=0.275, pruned_loss=0.05275, over 1018843.73 frames.], batch size: 20, lr: 8.51e-04
+2022-05-14 07:37:25,190 INFO [train.py:812] (1/8) Epoch 9, batch 300, loss[loss=0.1822, simple_loss=0.2751, pruned_loss=0.04467, over 7346.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2773, pruned_loss=0.05407, over 1103961.83 frames.], batch size: 22, lr: 8.50e-04
+2022-05-14 07:38:24,949 INFO [train.py:812] (1/8) Epoch 9, batch 350, loss[loss=0.1819, simple_loss=0.2626, pruned_loss=0.05064, over 7160.00 frames.], tot_loss[loss=0.1912, simple_loss=0.276, pruned_loss=0.05319, over 1177613.00 frames.], batch size: 19, lr: 8.50e-04
+2022-05-14 07:39:24,187 INFO [train.py:812] (1/8) Epoch 9, batch 400, loss[loss=0.1619, simple_loss=0.2378, pruned_loss=0.04302, over 7133.00 frames.], tot_loss[loss=0.19, simple_loss=0.275, pruned_loss=0.05253, over 1236876.33 frames.], batch size: 17, lr: 8.49e-04
+2022-05-14 07:40:21,410 INFO [train.py:812] (1/8) Epoch 9, batch 450, loss[loss=0.1719, simple_loss=0.2599, pruned_loss=0.04191, over 7261.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2742, pruned_loss=0.05256, over 1278418.52 frames.], batch size: 19, lr: 8.49e-04
+2022-05-14 07:41:19,789 INFO [train.py:812] (1/8) Epoch 9, batch 500, loss[loss=0.1877, simple_loss=0.2535, pruned_loss=0.06093, over 7398.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2751, pruned_loss=0.05338, over 1311548.36 frames.], batch size: 18, lr: 8.48e-04
+2022-05-14 07:42:19,035 INFO [train.py:812] (1/8) Epoch 9, batch 550, loss[loss=0.1773, simple_loss=0.2617, pruned_loss=0.0465, over 7070.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2744, pruned_loss=0.05301, over 1339607.10 frames.], batch size: 18, lr: 8.48e-04
+2022-05-14 07:43:17,527 INFO [train.py:812] (1/8) Epoch 9, batch 600, loss[loss=0.1769, simple_loss=0.2677, pruned_loss=0.04307, over 7075.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2741, pruned_loss=0.05285, over 1360859.77 frames.], batch size: 18, lr: 8.47e-04
+2022-05-14 07:44:16,645 INFO [train.py:812] (1/8) Epoch 9, batch 650, loss[loss=0.1734, simple_loss=0.2601, pruned_loss=0.04331, over 7360.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2735, pruned_loss=0.05265, over 1374272.95 frames.], batch size: 19, lr: 8.46e-04
+2022-05-14 07:45:15,374 INFO [train.py:812] (1/8) Epoch 9, batch 700, loss[loss=0.1617, simple_loss=0.2481, pruned_loss=0.03763, over 7435.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2739, pruned_loss=0.0525, over 1386519.04 frames.], batch size: 20, lr: 8.46e-04
+2022-05-14 07:46:13,725 INFO [train.py:812] (1/8) Epoch 9, batch 750, loss[loss=0.1706, simple_loss=0.2458, pruned_loss=0.04773, over 7174.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2738, pruned_loss=0.05252, over 1390128.30 frames.], batch size: 18, lr: 8.45e-04
+2022-05-14 07:47:13,056 INFO [train.py:812] (1/8) Epoch 9, batch 800, loss[loss=0.1768, simple_loss=0.2647, pruned_loss=0.04439, over 7397.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2724, pruned_loss=0.05158, over 1396312.31 frames.], batch size: 23, lr: 8.45e-04
+2022-05-14 07:48:11,326 INFO [train.py:812] (1/8) Epoch 9, batch 850, loss[loss=0.1883, simple_loss=0.2728, pruned_loss=0.05186, over 7310.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2732, pruned_loss=0.05203, over 1402204.23 frames.], batch size: 21, lr: 8.44e-04
+2022-05-14 07:49:11,214 INFO [train.py:812] (1/8) Epoch 9, batch 900, loss[loss=0.2091, simple_loss=0.2924, pruned_loss=0.06293, over 7225.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2737, pruned_loss=0.05208, over 1411654.92 frames.], batch size: 21, lr: 8.44e-04
+2022-05-14 07:50:10,517 INFO [train.py:812] (1/8) Epoch 9, batch 950, loss[loss=0.1817, simple_loss=0.2649, pruned_loss=0.04925, over 7326.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2741, pruned_loss=0.05266, over 1409833.33 frames.], batch size: 20, lr: 8.43e-04
+2022-05-14 07:51:10,495 INFO [train.py:812] (1/8) Epoch 9, batch 1000, loss[loss=0.1831, simple_loss=0.2663, pruned_loss=0.04994, over 7431.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2739, pruned_loss=0.05263, over 1414838.12 frames.], batch size: 20, lr: 8.43e-04
+2022-05-14 07:52:08,969 INFO [train.py:812] (1/8) Epoch 9, batch 1050, loss[loss=0.1761, simple_loss=0.2573, pruned_loss=0.04743, over 7260.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2743, pruned_loss=0.05264, over 1419748.00 frames.], batch size: 19, lr: 8.42e-04
+2022-05-14 07:53:07,740 INFO [train.py:812] (1/8) Epoch 9, batch 1100, loss[loss=0.1562, simple_loss=0.2367, pruned_loss=0.03787, over 7259.00 frames.], tot_loss[loss=0.19, simple_loss=0.2749, pruned_loss=0.0525, over 1422466.03 frames.], batch size: 17, lr: 8.41e-04
+2022-05-14 07:54:04,862 INFO [train.py:812] (1/8) Epoch 9, batch 1150, loss[loss=0.2139, simple_loss=0.2961, pruned_loss=0.06586, over 7312.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2732, pruned_loss=0.05175, over 1422303.93 frames.], batch size: 25, lr: 8.41e-04
+2022-05-14 07:55:04,927 INFO [train.py:812] (1/8) Epoch 9, batch 1200, loss[loss=0.2186, simple_loss=0.2963, pruned_loss=0.07048, over 7421.00 frames.], tot_loss[loss=0.1884, simple_loss=0.273, pruned_loss=0.05187, over 1421890.61 frames.], batch size: 20, lr: 8.40e-04
+2022-05-14 07:56:02,851 INFO [train.py:812] (1/8) Epoch 9, batch 1250, loss[loss=0.1974, simple_loss=0.2702, pruned_loss=0.0623, over 7185.00 frames.], tot_loss[loss=0.1888, simple_loss=0.273, pruned_loss=0.05229, over 1417701.58 frames.], batch size: 16, lr: 8.40e-04
+2022-05-14 07:57:02,082 INFO [train.py:812] (1/8) Epoch 9, batch 1300, loss[loss=0.2247, simple_loss=0.3125, pruned_loss=0.06848, over 7148.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2733, pruned_loss=0.05272, over 1414149.39 frames.], batch size: 19, lr: 8.39e-04
+2022-05-14 07:58:01,346 INFO [train.py:812] (1/8) Epoch 9, batch 1350, loss[loss=0.2009, simple_loss=0.2891, pruned_loss=0.0564, over 7434.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2735, pruned_loss=0.0528, over 1418509.68 frames.], batch size: 20, lr: 8.39e-04
+2022-05-14 07:59:00,870 INFO [train.py:812] (1/8) Epoch 9, batch 1400, loss[loss=0.1565, simple_loss=0.2523, pruned_loss=0.03031, over 7227.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2733, pruned_loss=0.05262, over 1415576.08 frames.], batch size: 21, lr: 8.38e-04
+2022-05-14 07:59:57,891 INFO [train.py:812] (1/8) Epoch 9, batch 1450, loss[loss=0.2035, simple_loss=0.2983, pruned_loss=0.05439, over 7318.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2729, pruned_loss=0.05246, over 1420463.68 frames.], batch size: 21, lr: 8.38e-04
+2022-05-14 08:00:55,532 INFO [train.py:812] (1/8) Epoch 9, batch 1500, loss[loss=0.1777, simple_loss=0.2573, pruned_loss=0.04907, over 7231.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2734, pruned_loss=0.05304, over 1422901.52 frames.], batch size: 20, lr: 8.37e-04
+2022-05-14 08:01:53,804 INFO [train.py:812] (1/8) Epoch 9, batch 1550, loss[loss=0.214, simple_loss=0.2952, pruned_loss=0.06639, over 7198.00 frames.], tot_loss[loss=0.1883, simple_loss=0.272, pruned_loss=0.05228, over 1421819.52 frames.], batch size: 22, lr: 8.37e-04
+2022-05-14 08:02:51,999 INFO [train.py:812] (1/8) Epoch 9, batch 1600, loss[loss=0.1867, simple_loss=0.2761, pruned_loss=0.04868, over 7059.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2727, pruned_loss=0.05225, over 1420204.18 frames.], batch size: 18, lr: 8.36e-04
+2022-05-14 08:03:49,501 INFO [train.py:812] (1/8) Epoch 9, batch 1650, loss[loss=0.1784, simple_loss=0.2671, pruned_loss=0.04483, over 7102.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2737, pruned_loss=0.0527, over 1420631.45 frames.], batch size: 21, lr: 8.35e-04
+2022-05-14 08:04:47,903 INFO [train.py:812] (1/8) Epoch 9, batch 1700, loss[loss=0.1801, simple_loss=0.2686, pruned_loss=0.04583, over 7150.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2744, pruned_loss=0.05275, over 1418925.76 frames.], batch size: 20, lr: 8.35e-04
+2022-05-14 08:05:46,543 INFO [train.py:812] (1/8) Epoch 9, batch 1750, loss[loss=0.1852, simple_loss=0.2789, pruned_loss=0.04571, over 7330.00 frames.], tot_loss[loss=0.1899, simple_loss=0.274, pruned_loss=0.05292, over 1420960.61 frames.], batch size: 21, lr: 8.34e-04
+2022-05-14 08:06:45,594 INFO [train.py:812] (1/8) Epoch 9, batch 1800, loss[loss=0.157, simple_loss=0.246, pruned_loss=0.03396, over 7243.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2736, pruned_loss=0.05289, over 1418064.44 frames.], batch size: 20, lr: 8.34e-04
+2022-05-14 08:07:44,986 INFO [train.py:812] (1/8) Epoch 9, batch 1850, loss[loss=0.1749, simple_loss=0.264, pruned_loss=0.04292, over 7242.00 frames.], tot_loss[loss=0.1897, simple_loss=0.274, pruned_loss=0.05268, over 1421774.02 frames.], batch size: 20, lr: 8.33e-04
+2022-05-14 08:08:44,856 INFO [train.py:812] (1/8) Epoch 9, batch 1900, loss[loss=0.1971, simple_loss=0.2871, pruned_loss=0.05352, over 7150.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2745, pruned_loss=0.05284, over 1420345.55 frames.], batch size: 19, lr: 8.33e-04
+2022-05-14 08:09:44,223 INFO [train.py:812] (1/8) Epoch 9, batch 1950, loss[loss=0.1868, simple_loss=0.2777, pruned_loss=0.04799, over 7118.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2742, pruned_loss=0.05246, over 1421030.62 frames.], batch size: 21, lr: 8.32e-04
+2022-05-14 08:10:44,115 INFO [train.py:812] (1/8) Epoch 9, batch 2000, loss[loss=0.2072, simple_loss=0.2939, pruned_loss=0.06023, over 7269.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2734, pruned_loss=0.05222, over 1422208.57 frames.], batch size: 24, lr: 8.32e-04
+2022-05-14 08:11:43,573 INFO [train.py:812] (1/8) Epoch 9, batch 2050, loss[loss=0.1612, simple_loss=0.243, pruned_loss=0.03966, over 7270.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2738, pruned_loss=0.05283, over 1421458.75 frames.], batch size: 17, lr: 8.31e-04
+2022-05-14 08:12:43,236 INFO [train.py:812] (1/8) Epoch 9, batch 2100, loss[loss=0.1915, simple_loss=0.273, pruned_loss=0.05501, over 7259.00 frames.], tot_loss[loss=0.1897, simple_loss=0.274, pruned_loss=0.05273, over 1423517.34 frames.], batch size: 19, lr: 8.31e-04
+2022-05-14 08:13:42,061 INFO [train.py:812] (1/8) Epoch 9, batch 2150, loss[loss=0.2048, simple_loss=0.2833, pruned_loss=0.06317, over 7068.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2736, pruned_loss=0.05289, over 1425443.47 frames.], batch size: 18, lr: 8.30e-04
+2022-05-14 08:14:40,831 INFO [train.py:812] (1/8) Epoch 9, batch 2200, loss[loss=0.1743, simple_loss=0.2483, pruned_loss=0.05008, over 7272.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2734, pruned_loss=0.05313, over 1423299.23 frames.], batch size: 17, lr: 8.30e-04
+2022-05-14 08:15:40,319 INFO [train.py:812] (1/8) Epoch 9, batch 2250, loss[loss=0.1749, simple_loss=0.2576, pruned_loss=0.04607, over 7165.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2727, pruned_loss=0.05222, over 1423699.21 frames.], batch size: 18, lr: 8.29e-04
+2022-05-14 08:16:40,193 INFO [train.py:812] (1/8) Epoch 9, batch 2300, loss[loss=0.1792, simple_loss=0.2684, pruned_loss=0.04494, over 7142.00 frames.], tot_loss[loss=0.189, simple_loss=0.2732, pruned_loss=0.05234, over 1424765.85 frames.], batch size: 20, lr: 8.29e-04
+2022-05-14 08:17:37,462 INFO [train.py:812] (1/8) Epoch 9, batch 2350, loss[loss=0.2146, simple_loss=0.2983, pruned_loss=0.06544, over 6804.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2735, pruned_loss=0.05274, over 1423821.84 frames.], batch size: 31, lr: 8.28e-04
+2022-05-14 08:18:37,031 INFO [train.py:812] (1/8) Epoch 9, batch 2400, loss[loss=0.1883, simple_loss=0.2648, pruned_loss=0.05593, over 7266.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2732, pruned_loss=0.0527, over 1424850.74 frames.], batch size: 18, lr: 8.28e-04
+2022-05-14 08:19:36,152 INFO [train.py:812] (1/8) Epoch 9, batch 2450, loss[loss=0.1846, simple_loss=0.2561, pruned_loss=0.0565, over 7397.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2734, pruned_loss=0.05273, over 1425812.01 frames.], batch size: 18, lr: 8.27e-04
+2022-05-14 08:20:34,804 INFO [train.py:812] (1/8) Epoch 9, batch 2500, loss[loss=0.1836, simple_loss=0.2771, pruned_loss=0.04502, over 7200.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2724, pruned_loss=0.052, over 1425057.10 frames.], batch size: 22, lr: 8.27e-04
+2022-05-14 08:21:43,990 INFO [train.py:812] (1/8) Epoch 9, batch 2550, loss[loss=0.1902, simple_loss=0.2625, pruned_loss=0.05896, over 7129.00 frames.], tot_loss[loss=0.1878, simple_loss=0.272, pruned_loss=0.05182, over 1422055.18 frames.], batch size: 17, lr: 8.26e-04
+2022-05-14 08:22:42,419 INFO [train.py:812] (1/8) Epoch 9, batch 2600, loss[loss=0.2008, simple_loss=0.2828, pruned_loss=0.05936, over 7359.00 frames.], tot_loss[loss=0.1887, simple_loss=0.273, pruned_loss=0.05218, over 1419042.39 frames.], batch size: 23, lr: 8.25e-04
+2022-05-14 08:23:41,188 INFO [train.py:812] (1/8) Epoch 9, batch 2650, loss[loss=0.2395, simple_loss=0.3176, pruned_loss=0.08074, over 4872.00 frames.], tot_loss[loss=0.1889, simple_loss=0.273, pruned_loss=0.0524, over 1417152.69 frames.], batch size: 52, lr: 8.25e-04
+2022-05-14 08:24:39,375 INFO [train.py:812] (1/8) Epoch 9, batch 2700, loss[loss=0.1953, simple_loss=0.2855, pruned_loss=0.05257, over 7335.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2731, pruned_loss=0.05223, over 1418939.18 frames.], batch size: 22, lr: 8.24e-04
+2022-05-14 08:25:38,210 INFO [train.py:812] (1/8) Epoch 9, batch 2750, loss[loss=0.1923, simple_loss=0.2718, pruned_loss=0.05642, over 7337.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2731, pruned_loss=0.05258, over 1423437.39 frames.], batch size: 20, lr: 8.24e-04
+2022-05-14 08:26:37,730 INFO [train.py:812] (1/8) Epoch 9, batch 2800, loss[loss=0.1897, simple_loss=0.2818, pruned_loss=0.04881, over 7199.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2734, pruned_loss=0.05282, over 1426026.13 frames.], batch size: 22, lr: 8.23e-04
+2022-05-14 08:27:35,906 INFO [train.py:812] (1/8) Epoch 9, batch 2850, loss[loss=0.1807, simple_loss=0.2694, pruned_loss=0.04603, over 7149.00 frames.], tot_loss[loss=0.189, simple_loss=0.2729, pruned_loss=0.05253, over 1427971.40 frames.], batch size: 19, lr: 8.23e-04
+2022-05-14 08:28:33,947 INFO [train.py:812] (1/8) Epoch 9, batch 2900, loss[loss=0.1918, simple_loss=0.2769, pruned_loss=0.05337, over 7323.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2724, pruned_loss=0.05191, over 1427094.88 frames.], batch size: 21, lr: 8.22e-04
+2022-05-14 08:29:31,238 INFO [train.py:812] (1/8) Epoch 9, batch 2950, loss[loss=0.1727, simple_loss=0.2456, pruned_loss=0.04991, over 7277.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2726, pruned_loss=0.05192, over 1423199.20 frames.], batch size: 18, lr: 8.22e-04
+2022-05-14 08:30:30,203 INFO [train.py:812] (1/8) Epoch 9, batch 3000, loss[loss=0.207, simple_loss=0.2891, pruned_loss=0.06243, over 7288.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2724, pruned_loss=0.05219, over 1421474.93 frames.], batch size: 24, lr: 8.21e-04
+2022-05-14 08:30:30,204 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 08:30:38,337 INFO [train.py:841] (1/8) Epoch 9, validation: loss=0.1602, simple_loss=0.262, pruned_loss=0.0292, over 698248.00 frames.
+2022-05-14 08:31:37,159 INFO [train.py:812] (1/8) Epoch 9, batch 3050, loss[loss=0.1792, simple_loss=0.2621, pruned_loss=0.04817, over 7326.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2722, pruned_loss=0.05229, over 1418167.95 frames.], batch size: 20, lr: 8.21e-04
+2022-05-14 08:32:34,697 INFO [train.py:812] (1/8) Epoch 9, batch 3100, loss[loss=0.2122, simple_loss=0.2876, pruned_loss=0.0684, over 6763.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2744, pruned_loss=0.05351, over 1413429.37 frames.], batch size: 31, lr: 8.20e-04
+2022-05-14 08:33:32,679 INFO [train.py:812] (1/8) Epoch 9, batch 3150, loss[loss=0.2507, simple_loss=0.3265, pruned_loss=0.0874, over 7157.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2742, pruned_loss=0.0537, over 1416776.20 frames.], batch size: 19, lr: 8.20e-04
+2022-05-14 08:34:32,458 INFO [train.py:812] (1/8) Epoch 9, batch 3200, loss[loss=0.1714, simple_loss=0.261, pruned_loss=0.04088, over 7153.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2742, pruned_loss=0.05344, over 1420601.62 frames.], batch size: 20, lr: 8.19e-04
+2022-05-14 08:35:31,365 INFO [train.py:812] (1/8) Epoch 9, batch 3250, loss[loss=0.2547, simple_loss=0.3176, pruned_loss=0.09594, over 4872.00 frames.], tot_loss[loss=0.191, simple_loss=0.2749, pruned_loss=0.05357, over 1419057.89 frames.], batch size: 52, lr: 8.19e-04
+2022-05-14 08:36:46,152 INFO [train.py:812] (1/8) Epoch 9, batch 3300, loss[loss=0.2049, simple_loss=0.2928, pruned_loss=0.05846, over 7201.00 frames.], tot_loss[loss=0.1902, simple_loss=0.274, pruned_loss=0.05319, over 1419145.79 frames.], batch size: 22, lr: 8.18e-04
+2022-05-14 08:37:52,678 INFO [train.py:812] (1/8) Epoch 9, batch 3350, loss[loss=0.1749, simple_loss=0.2559, pruned_loss=0.04697, over 7263.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2729, pruned_loss=0.05241, over 1422538.72 frames.], batch size: 19, lr: 8.18e-04
+2022-05-14 08:38:51,548 INFO [train.py:812] (1/8) Epoch 9, batch 3400, loss[loss=0.215, simple_loss=0.3, pruned_loss=0.06503, over 6800.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2728, pruned_loss=0.05179, over 1421021.96 frames.], batch size: 31, lr: 8.17e-04
+2022-05-14 08:39:59,370 INFO [train.py:812] (1/8) Epoch 9, batch 3450, loss[loss=0.1506, simple_loss=0.2313, pruned_loss=0.03497, over 7399.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2726, pruned_loss=0.05178, over 1423639.00 frames.], batch size: 18, lr: 8.17e-04
+2022-05-14 08:41:27,453 INFO [train.py:812] (1/8) Epoch 9, batch 3500, loss[loss=0.172, simple_loss=0.2432, pruned_loss=0.05038, over 7160.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2723, pruned_loss=0.05189, over 1424303.93 frames.], batch size: 19, lr: 8.16e-04
+2022-05-14 08:42:35,743 INFO [train.py:812] (1/8) Epoch 9, batch 3550, loss[loss=0.1711, simple_loss=0.2636, pruned_loss=0.03936, over 7163.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2725, pruned_loss=0.0521, over 1426339.50 frames.], batch size: 18, lr: 8.16e-04
+2022-05-14 08:43:34,792 INFO [train.py:812] (1/8) Epoch 9, batch 3600, loss[loss=0.1692, simple_loss=0.2482, pruned_loss=0.04512, over 7279.00 frames.], tot_loss[loss=0.1899, simple_loss=0.274, pruned_loss=0.05289, over 1424189.82 frames.], batch size: 18, lr: 8.15e-04
+2022-05-14 08:44:32,175 INFO [train.py:812] (1/8) Epoch 9, batch 3650, loss[loss=0.1532, simple_loss=0.2404, pruned_loss=0.03301, over 7140.00 frames.], tot_loss[loss=0.1886, simple_loss=0.273, pruned_loss=0.05212, over 1425715.06 frames.], batch size: 17, lr: 8.15e-04
+2022-05-14 08:45:31,309 INFO [train.py:812] (1/8) Epoch 9, batch 3700, loss[loss=0.2094, simple_loss=0.2928, pruned_loss=0.06303, over 7276.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2729, pruned_loss=0.05172, over 1426486.41 frames.], batch size: 25, lr: 8.14e-04
+2022-05-14 08:46:29,961 INFO [train.py:812] (1/8) Epoch 9, batch 3750, loss[loss=0.1821, simple_loss=0.2705, pruned_loss=0.04679, over 7427.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2738, pruned_loss=0.0518, over 1426038.57 frames.], batch size: 20, lr: 8.14e-04
+2022-05-14 08:47:28,940 INFO [train.py:812] (1/8) Epoch 9, batch 3800, loss[loss=0.1731, simple_loss=0.2603, pruned_loss=0.04299, over 7412.00 frames.], tot_loss[loss=0.189, simple_loss=0.274, pruned_loss=0.05199, over 1427537.44 frames.], batch size: 18, lr: 8.13e-04
+2022-05-14 08:48:27,808 INFO [train.py:812] (1/8) Epoch 9, batch 3850, loss[loss=0.1698, simple_loss=0.2473, pruned_loss=0.0462, over 7295.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2738, pruned_loss=0.05189, over 1429712.78 frames.], batch size: 17, lr: 8.13e-04
+2022-05-14 08:49:26,810 INFO [train.py:812] (1/8) Epoch 9, batch 3900, loss[loss=0.2338, simple_loss=0.3116, pruned_loss=0.07803, over 4959.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2744, pruned_loss=0.05188, over 1427255.07 frames.], batch size: 52, lr: 8.12e-04
+2022-05-14 08:50:26,273 INFO [train.py:812] (1/8) Epoch 9, batch 3950, loss[loss=0.1884, simple_loss=0.2818, pruned_loss=0.04747, over 6771.00 frames.], tot_loss[loss=0.188, simple_loss=0.2731, pruned_loss=0.05148, over 1427784.40 frames.], batch size: 31, lr: 8.12e-04
+2022-05-14 08:51:25,796 INFO [train.py:812] (1/8) Epoch 9, batch 4000, loss[loss=0.1953, simple_loss=0.28, pruned_loss=0.0553, over 7218.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2739, pruned_loss=0.05175, over 1427030.78 frames.], batch size: 21, lr: 8.11e-04
+2022-05-14 08:52:25,213 INFO [train.py:812] (1/8) Epoch 9, batch 4050, loss[loss=0.1545, simple_loss=0.2331, pruned_loss=0.03789, over 7409.00 frames.], tot_loss[loss=0.188, simple_loss=0.2727, pruned_loss=0.05162, over 1426438.35 frames.], batch size: 18, lr: 8.11e-04
+2022-05-14 08:53:24,993 INFO [train.py:812] (1/8) Epoch 9, batch 4100, loss[loss=0.1737, simple_loss=0.2537, pruned_loss=0.04684, over 7118.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2732, pruned_loss=0.05216, over 1427157.18 frames.], batch size: 17, lr: 8.10e-04
+2022-05-14 08:54:24,678 INFO [train.py:812] (1/8) Epoch 9, batch 4150, loss[loss=0.2078, simple_loss=0.2982, pruned_loss=0.05874, over 7130.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2728, pruned_loss=0.05205, over 1422438.44 frames.], batch size: 28, lr: 8.10e-04
+2022-05-14 08:55:24,384 INFO [train.py:812] (1/8) Epoch 9, batch 4200, loss[loss=0.2143, simple_loss=0.2932, pruned_loss=0.06768, over 7328.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2718, pruned_loss=0.05175, over 1424275.45 frames.], batch size: 20, lr: 8.09e-04
+2022-05-14 08:56:23,008 INFO [train.py:812] (1/8) Epoch 9, batch 4250, loss[loss=0.1652, simple_loss=0.2383, pruned_loss=0.04604, over 7144.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2717, pruned_loss=0.05164, over 1419890.55 frames.], batch size: 17, lr: 8.09e-04
+2022-05-14 08:57:22,989 INFO [train.py:812] (1/8) Epoch 9, batch 4300, loss[loss=0.1709, simple_loss=0.2682, pruned_loss=0.0368, over 7405.00 frames.], tot_loss[loss=0.1882, simple_loss=0.272, pruned_loss=0.05223, over 1415073.25 frames.], batch size: 21, lr: 8.08e-04
+2022-05-14 08:58:21,485 INFO [train.py:812] (1/8) Epoch 9, batch 4350, loss[loss=0.1977, simple_loss=0.266, pruned_loss=0.06464, over 7279.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2702, pruned_loss=0.05098, over 1420291.26 frames.], batch size: 17, lr: 8.08e-04
+2022-05-14 08:59:21,261 INFO [train.py:812] (1/8) Epoch 9, batch 4400, loss[loss=0.2313, simple_loss=0.3101, pruned_loss=0.07624, over 7034.00 frames.], tot_loss[loss=0.1862, simple_loss=0.27, pruned_loss=0.05121, over 1416211.86 frames.], batch size: 28, lr: 8.07e-04
+2022-05-14 09:00:19,271 INFO [train.py:812] (1/8) Epoch 9, batch 4450, loss[loss=0.212, simple_loss=0.2975, pruned_loss=0.06321, over 7030.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2692, pruned_loss=0.05117, over 1410479.01 frames.], batch size: 28, lr: 8.07e-04
+2022-05-14 09:01:19,089 INFO [train.py:812] (1/8) Epoch 9, batch 4500, loss[loss=0.1814, simple_loss=0.2783, pruned_loss=0.04231, over 7067.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2706, pruned_loss=0.05244, over 1392075.56 frames.], batch size: 28, lr: 8.07e-04
+2022-05-14 09:02:17,086 INFO [train.py:812] (1/8) Epoch 9, batch 4550, loss[loss=0.1883, simple_loss=0.2713, pruned_loss=0.05267, over 6288.00 frames.], tot_loss[loss=0.192, simple_loss=0.2748, pruned_loss=0.05463, over 1351199.77 frames.], batch size: 37, lr: 8.06e-04
+2022-05-14 09:03:24,804 INFO [train.py:812] (1/8) Epoch 10, batch 0, loss[loss=0.1724, simple_loss=0.2607, pruned_loss=0.04208, over 7408.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2607, pruned_loss=0.04208, over 7408.00 frames.], batch size: 21, lr: 7.75e-04
+2022-05-14 09:04:24,012 INFO [train.py:812] (1/8) Epoch 10, batch 50, loss[loss=0.1982, simple_loss=0.2907, pruned_loss=0.05292, over 7189.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2733, pruned_loss=0.0519, over 321344.42 frames.], batch size: 23, lr: 7.74e-04
+2022-05-14 09:05:23,094 INFO [train.py:812] (1/8) Epoch 10, batch 100, loss[loss=0.2409, simple_loss=0.3057, pruned_loss=0.08803, over 5100.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2714, pruned_loss=0.05247, over 556914.33 frames.], batch size: 52, lr: 7.74e-04
+2022-05-14 09:06:22,298 INFO [train.py:812] (1/8) Epoch 10, batch 150, loss[loss=0.1635, simple_loss=0.252, pruned_loss=0.03749, over 7441.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2707, pruned_loss=0.05114, over 750262.63 frames.], batch size: 20, lr: 7.73e-04
+2022-05-14 09:07:20,643 INFO [train.py:812] (1/8) Epoch 10, batch 200, loss[loss=0.1564, simple_loss=0.2494, pruned_loss=0.03175, over 7434.00 frames.], tot_loss[loss=0.1852, simple_loss=0.27, pruned_loss=0.05021, over 898068.36 frames.], batch size: 20, lr: 7.73e-04
+2022-05-14 09:08:19,892 INFO [train.py:812] (1/8) Epoch 10, batch 250, loss[loss=0.1721, simple_loss=0.2488, pruned_loss=0.04771, over 7158.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2718, pruned_loss=0.05078, over 1010499.04 frames.], batch size: 18, lr: 7.72e-04
+2022-05-14 09:09:19,089 INFO [train.py:812] (1/8) Epoch 10, batch 300, loss[loss=0.1605, simple_loss=0.2484, pruned_loss=0.0363, over 7324.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2725, pruned_loss=0.0514, over 1104647.80 frames.], batch size: 20, lr: 7.72e-04
+2022-05-14 09:10:16,341 INFO [train.py:812] (1/8) Epoch 10, batch 350, loss[loss=0.2063, simple_loss=0.287, pruned_loss=0.06275, over 7203.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2721, pruned_loss=0.05124, over 1173819.58 frames.], batch size: 23, lr: 7.71e-04
+2022-05-14 09:11:15,058 INFO [train.py:812] (1/8) Epoch 10, batch 400, loss[loss=0.1821, simple_loss=0.2658, pruned_loss=0.04913, over 7152.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2726, pruned_loss=0.05149, over 1223362.47 frames.], batch size: 26, lr: 7.71e-04
+2022-05-14 09:12:14,064 INFO [train.py:812] (1/8) Epoch 10, batch 450, loss[loss=0.1864, simple_loss=0.2711, pruned_loss=0.05083, over 6486.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2733, pruned_loss=0.05163, over 1261843.83 frames.], batch size: 38, lr: 7.71e-04
+2022-05-14 09:13:13,641 INFO [train.py:812] (1/8) Epoch 10, batch 500, loss[loss=0.1457, simple_loss=0.248, pruned_loss=0.02164, over 7147.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2731, pruned_loss=0.05141, over 1296939.60 frames.], batch size: 19, lr: 7.70e-04
+2022-05-14 09:14:12,266 INFO [train.py:812] (1/8) Epoch 10, batch 550, loss[loss=0.1575, simple_loss=0.2321, pruned_loss=0.04148, over 7132.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2717, pruned_loss=0.05057, over 1324969.96 frames.], batch size: 17, lr: 7.70e-04
+2022-05-14 09:15:10,138 INFO [train.py:812] (1/8) Epoch 10, batch 600, loss[loss=0.1518, simple_loss=0.2414, pruned_loss=0.03114, over 7276.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2708, pruned_loss=0.05011, over 1346603.28 frames.], batch size: 18, lr: 7.69e-04
+2022-05-14 09:16:08,328 INFO [train.py:812] (1/8) Epoch 10, batch 650, loss[loss=0.1758, simple_loss=0.2649, pruned_loss=0.04337, over 7172.00 frames.], tot_loss[loss=0.1855, simple_loss=0.271, pruned_loss=0.05001, over 1363079.74 frames.], batch size: 26, lr: 7.69e-04
+2022-05-14 09:17:07,953 INFO [train.py:812] (1/8) Epoch 10, batch 700, loss[loss=0.1879, simple_loss=0.2712, pruned_loss=0.05227, over 7312.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2701, pruned_loss=0.04953, over 1376779.29 frames.], batch size: 25, lr: 7.68e-04
+2022-05-14 09:18:07,535 INFO [train.py:812] (1/8) Epoch 10, batch 750, loss[loss=0.156, simple_loss=0.252, pruned_loss=0.03002, over 7431.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2703, pruned_loss=0.04955, over 1386986.97 frames.], batch size: 20, lr: 7.68e-04
+2022-05-14 09:19:06,538 INFO [train.py:812] (1/8) Epoch 10, batch 800, loss[loss=0.1942, simple_loss=0.2891, pruned_loss=0.04964, over 7289.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2705, pruned_loss=0.05017, over 1393538.42 frames.], batch size: 24, lr: 7.67e-04
+2022-05-14 09:20:06,000 INFO [train.py:812] (1/8) Epoch 10, batch 850, loss[loss=0.2041, simple_loss=0.2872, pruned_loss=0.06048, over 6387.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2715, pruned_loss=0.05053, over 1396488.98 frames.], batch size: 37, lr: 7.67e-04
+2022-05-14 09:21:05,080 INFO [train.py:812] (1/8) Epoch 10, batch 900, loss[loss=0.1695, simple_loss=0.2642, pruned_loss=0.03735, over 7315.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2711, pruned_loss=0.05029, over 1406505.20 frames.], batch size: 21, lr: 7.66e-04
+2022-05-14 09:22:03,783 INFO [train.py:812] (1/8) Epoch 10, batch 950, loss[loss=0.1992, simple_loss=0.2748, pruned_loss=0.06178, over 7147.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2721, pruned_loss=0.05075, over 1406402.28 frames.], batch size: 26, lr: 7.66e-04
+2022-05-14 09:23:02,557 INFO [train.py:812] (1/8) Epoch 10, batch 1000, loss[loss=0.188, simple_loss=0.2868, pruned_loss=0.04457, over 7335.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2719, pruned_loss=0.0507, over 1414155.94 frames.], batch size: 20, lr: 7.66e-04
+2022-05-14 09:24:00,832 INFO [train.py:812] (1/8) Epoch 10, batch 1050, loss[loss=0.2097, simple_loss=0.291, pruned_loss=0.06416, over 7000.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2714, pruned_loss=0.05046, over 1416333.00 frames.], batch size: 28, lr: 7.65e-04
+2022-05-14 09:24:59,375 INFO [train.py:812] (1/8) Epoch 10, batch 1100, loss[loss=0.205, simple_loss=0.2916, pruned_loss=0.05922, over 7044.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2724, pruned_loss=0.05099, over 1416851.69 frames.], batch size: 28, lr: 7.65e-04
+2022-05-14 09:25:57,288 INFO [train.py:812] (1/8) Epoch 10, batch 1150, loss[loss=0.1808, simple_loss=0.2676, pruned_loss=0.04703, over 7330.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2724, pruned_loss=0.05084, over 1421310.68 frames.], batch size: 20, lr: 7.64e-04
+2022-05-14 09:26:55,705 INFO [train.py:812] (1/8) Epoch 10, batch 1200, loss[loss=0.1967, simple_loss=0.282, pruned_loss=0.05573, over 7185.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2735, pruned_loss=0.05132, over 1420442.43 frames.], batch size: 23, lr: 7.64e-04
+2022-05-14 09:27:55,417 INFO [train.py:812] (1/8) Epoch 10, batch 1250, loss[loss=0.1896, simple_loss=0.2598, pruned_loss=0.0597, over 7297.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2736, pruned_loss=0.05152, over 1419098.11 frames.], batch size: 17, lr: 7.63e-04
+2022-05-14 09:28:54,699 INFO [train.py:812] (1/8) Epoch 10, batch 1300, loss[loss=0.1927, simple_loss=0.26, pruned_loss=0.06272, over 6998.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2728, pruned_loss=0.05185, over 1416518.58 frames.], batch size: 16, lr: 7.63e-04
+2022-05-14 09:29:54,189 INFO [train.py:812] (1/8) Epoch 10, batch 1350, loss[loss=0.1998, simple_loss=0.28, pruned_loss=0.05984, over 7323.00 frames.], tot_loss[loss=0.1874, simple_loss=0.272, pruned_loss=0.05141, over 1415134.12 frames.], batch size: 21, lr: 7.62e-04
+2022-05-14 09:30:53,019 INFO [train.py:812] (1/8) Epoch 10, batch 1400, loss[loss=0.1872, simple_loss=0.2743, pruned_loss=0.04999, over 7118.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2733, pruned_loss=0.05143, over 1418110.47 frames.], batch size: 21, lr: 7.62e-04
+2022-05-14 09:31:52,536 INFO [train.py:812] (1/8) Epoch 10, batch 1450, loss[loss=0.1782, simple_loss=0.2601, pruned_loss=0.04808, over 7289.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2727, pruned_loss=0.05102, over 1418894.23 frames.], batch size: 25, lr: 7.62e-04
+2022-05-14 09:32:51,545 INFO [train.py:812] (1/8) Epoch 10, batch 1500, loss[loss=0.23, simple_loss=0.3081, pruned_loss=0.07601, over 5010.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2725, pruned_loss=0.05101, over 1415732.14 frames.], batch size: 54, lr: 7.61e-04
+2022-05-14 09:33:51,498 INFO [train.py:812] (1/8) Epoch 10, batch 1550, loss[loss=0.181, simple_loss=0.2685, pruned_loss=0.04674, over 7364.00 frames.], tot_loss[loss=0.1869, simple_loss=0.272, pruned_loss=0.05084, over 1419306.05 frames.], batch size: 19, lr: 7.61e-04
+2022-05-14 09:34:49,173 INFO [train.py:812] (1/8) Epoch 10, batch 1600, loss[loss=0.1805, simple_loss=0.2693, pruned_loss=0.04586, over 7252.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2711, pruned_loss=0.05028, over 1417782.47 frames.], batch size: 19, lr: 7.60e-04
+2022-05-14 09:35:46,384 INFO [train.py:812] (1/8) Epoch 10, batch 1650, loss[loss=0.1936, simple_loss=0.2818, pruned_loss=0.05264, over 7417.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2706, pruned_loss=0.05, over 1415822.58 frames.], batch size: 21, lr: 7.60e-04
+2022-05-14 09:36:44,419 INFO [train.py:812] (1/8) Epoch 10, batch 1700, loss[loss=0.1952, simple_loss=0.2917, pruned_loss=0.04939, over 7299.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2702, pruned_loss=0.04946, over 1413774.90 frames.], batch size: 24, lr: 7.59e-04
+2022-05-14 09:37:43,563 INFO [train.py:812] (1/8) Epoch 10, batch 1750, loss[loss=0.1752, simple_loss=0.2518, pruned_loss=0.04933, over 7183.00 frames.], tot_loss[loss=0.1854, simple_loss=0.271, pruned_loss=0.04995, over 1406329.28 frames.], batch size: 16, lr: 7.59e-04
+2022-05-14 09:38:41,648 INFO [train.py:812] (1/8) Epoch 10, batch 1800, loss[loss=0.1965, simple_loss=0.2747, pruned_loss=0.05916, over 7367.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2706, pruned_loss=0.05002, over 1410426.19 frames.], batch size: 19, lr: 7.59e-04
+2022-05-14 09:39:39,845 INFO [train.py:812] (1/8) Epoch 10, batch 1850, loss[loss=0.1962, simple_loss=0.2686, pruned_loss=0.06186, over 7350.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2716, pruned_loss=0.05059, over 1411577.84 frames.], batch size: 19, lr: 7.58e-04
+2022-05-14 09:40:38,493 INFO [train.py:812] (1/8) Epoch 10, batch 1900, loss[loss=0.1796, simple_loss=0.2524, pruned_loss=0.05339, over 7281.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2702, pruned_loss=0.05021, over 1415695.83 frames.], batch size: 18, lr: 7.58e-04
+2022-05-14 09:41:37,153 INFO [train.py:812] (1/8) Epoch 10, batch 1950, loss[loss=0.1872, simple_loss=0.2744, pruned_loss=0.04998, over 7206.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2703, pruned_loss=0.05038, over 1415753.22 frames.], batch size: 23, lr: 7.57e-04
+2022-05-14 09:42:35,061 INFO [train.py:812] (1/8) Epoch 10, batch 2000, loss[loss=0.1935, simple_loss=0.2839, pruned_loss=0.05153, over 7236.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2694, pruned_loss=0.04975, over 1418092.56 frames.], batch size: 20, lr: 7.57e-04
+2022-05-14 09:43:34,864 INFO [train.py:812] (1/8) Epoch 10, batch 2050, loss[loss=0.1888, simple_loss=0.2719, pruned_loss=0.05284, over 7191.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2696, pruned_loss=0.04963, over 1419899.18 frames.], batch size: 23, lr: 7.56e-04
+2022-05-14 09:44:34,080 INFO [train.py:812] (1/8) Epoch 10, batch 2100, loss[loss=0.1911, simple_loss=0.2686, pruned_loss=0.05683, over 7143.00 frames.], tot_loss[loss=0.183, simple_loss=0.2685, pruned_loss=0.04878, over 1424514.65 frames.], batch size: 20, lr: 7.56e-04
+2022-05-14 09:45:31,440 INFO [train.py:812] (1/8) Epoch 10, batch 2150, loss[loss=0.1499, simple_loss=0.2329, pruned_loss=0.03343, over 7403.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2673, pruned_loss=0.04823, over 1426616.25 frames.], batch size: 18, lr: 7.56e-04
+2022-05-14 09:46:28,647 INFO [train.py:812] (1/8) Epoch 10, batch 2200, loss[loss=0.1881, simple_loss=0.2714, pruned_loss=0.05234, over 6407.00 frames.], tot_loss[loss=0.1826, simple_loss=0.268, pruned_loss=0.0486, over 1425885.97 frames.], batch size: 37, lr: 7.55e-04
+2022-05-14 09:47:27,357 INFO [train.py:812] (1/8) Epoch 10, batch 2250, loss[loss=0.1696, simple_loss=0.258, pruned_loss=0.0406, over 7325.00 frames.], tot_loss[loss=0.183, simple_loss=0.2684, pruned_loss=0.04876, over 1428109.72 frames.], batch size: 21, lr: 7.55e-04
+2022-05-14 09:48:25,573 INFO [train.py:812] (1/8) Epoch 10, batch 2300, loss[loss=0.1693, simple_loss=0.2613, pruned_loss=0.03866, over 7145.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2688, pruned_loss=0.04875, over 1426417.37 frames.], batch size: 20, lr: 7.54e-04
+2022-05-14 09:49:24,921 INFO [train.py:812] (1/8) Epoch 10, batch 2350, loss[loss=0.1934, simple_loss=0.2834, pruned_loss=0.05175, over 7211.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2686, pruned_loss=0.04901, over 1426001.69 frames.], batch size: 22, lr: 7.54e-04
+2022-05-14 09:50:22,133 INFO [train.py:812] (1/8) Epoch 10, batch 2400, loss[loss=0.201, simple_loss=0.2749, pruned_loss=0.06357, over 7280.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2683, pruned_loss=0.04867, over 1427767.88 frames.], batch size: 18, lr: 7.53e-04
+2022-05-14 09:51:20,795 INFO [train.py:812] (1/8) Epoch 10, batch 2450, loss[loss=0.1673, simple_loss=0.2543, pruned_loss=0.04012, over 7069.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2682, pruned_loss=0.04843, over 1430312.95 frames.], batch size: 18, lr: 7.53e-04
+2022-05-14 09:52:18,423 INFO [train.py:812] (1/8) Epoch 10, batch 2500, loss[loss=0.192, simple_loss=0.2751, pruned_loss=0.05445, over 7317.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2673, pruned_loss=0.04792, over 1428477.32 frames.], batch size: 21, lr: 7.53e-04
+2022-05-14 09:53:18,329 INFO [train.py:812] (1/8) Epoch 10, batch 2550, loss[loss=0.1804, simple_loss=0.2707, pruned_loss=0.04511, over 7232.00 frames.], tot_loss[loss=0.1823, simple_loss=0.268, pruned_loss=0.04826, over 1425843.38 frames.], batch size: 21, lr: 7.52e-04
+2022-05-14 09:54:18,073 INFO [train.py:812] (1/8) Epoch 10, batch 2600, loss[loss=0.2017, simple_loss=0.2755, pruned_loss=0.06393, over 7181.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2686, pruned_loss=0.04909, over 1429045.57 frames.], batch size: 26, lr: 7.52e-04
+2022-05-14 09:55:17,728 INFO [train.py:812] (1/8) Epoch 10, batch 2650, loss[loss=0.1878, simple_loss=0.2725, pruned_loss=0.05152, over 7334.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2698, pruned_loss=0.04958, over 1425195.77 frames.], batch size: 22, lr: 7.51e-04
+2022-05-14 09:56:16,826 INFO [train.py:812] (1/8) Epoch 10, batch 2700, loss[loss=0.1641, simple_loss=0.2609, pruned_loss=0.03361, over 6804.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2688, pruned_loss=0.04886, over 1425250.27 frames.], batch size: 31, lr: 7.51e-04
+2022-05-14 09:57:23,629 INFO [train.py:812] (1/8) Epoch 10, batch 2750, loss[loss=0.1904, simple_loss=0.2725, pruned_loss=0.05416, over 6797.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2686, pruned_loss=0.04898, over 1423334.79 frames.], batch size: 31, lr: 7.50e-04
+2022-05-14 09:58:22,155 INFO [train.py:812] (1/8) Epoch 10, batch 2800, loss[loss=0.1888, simple_loss=0.2776, pruned_loss=0.05004, over 7369.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2681, pruned_loss=0.04889, over 1428408.38 frames.], batch size: 23, lr: 7.50e-04
+2022-05-14 09:59:21,339 INFO [train.py:812] (1/8) Epoch 10, batch 2850, loss[loss=0.1803, simple_loss=0.2737, pruned_loss=0.04347, over 7325.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2688, pruned_loss=0.0489, over 1426310.42 frames.], batch size: 22, lr: 7.50e-04
+2022-05-14 10:00:20,873 INFO [train.py:812] (1/8) Epoch 10, batch 2900, loss[loss=0.1603, simple_loss=0.2462, pruned_loss=0.03719, over 7112.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2689, pruned_loss=0.04924, over 1425372.60 frames.], batch size: 21, lr: 7.49e-04
+2022-05-14 10:01:19,226 INFO [train.py:812] (1/8) Epoch 10, batch 2950, loss[loss=0.1532, simple_loss=0.2273, pruned_loss=0.03957, over 7267.00 frames.], tot_loss[loss=0.183, simple_loss=0.2682, pruned_loss=0.04889, over 1425984.50 frames.], batch size: 18, lr: 7.49e-04
+2022-05-14 10:02:18,290 INFO [train.py:812] (1/8) Epoch 10, batch 3000, loss[loss=0.1427, simple_loss=0.226, pruned_loss=0.02966, over 7274.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2676, pruned_loss=0.0487, over 1426455.15 frames.], batch size: 17, lr: 7.48e-04
+2022-05-14 10:02:18,291 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 10:02:25,810 INFO [train.py:841] (1/8) Epoch 10, validation: loss=0.1584, simple_loss=0.26, pruned_loss=0.0284, over 698248.00 frames.
+2022-05-14 10:03:25,413 INFO [train.py:812] (1/8) Epoch 10, batch 3050, loss[loss=0.1883, simple_loss=0.29, pruned_loss=0.0433, over 7152.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2675, pruned_loss=0.04861, over 1426357.61 frames.], batch size: 19, lr: 7.48e-04
+2022-05-14 10:04:24,554 INFO [train.py:812] (1/8) Epoch 10, batch 3100, loss[loss=0.1657, simple_loss=0.2535, pruned_loss=0.03894, over 7126.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2677, pruned_loss=0.04823, over 1429038.53 frames.], batch size: 21, lr: 7.47e-04
+2022-05-14 10:05:24,312 INFO [train.py:812] (1/8) Epoch 10, batch 3150, loss[loss=0.1836, simple_loss=0.276, pruned_loss=0.04561, over 7330.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2688, pruned_loss=0.04875, over 1424870.73 frames.], batch size: 21, lr: 7.47e-04
+2022-05-14 10:06:23,644 INFO [train.py:812] (1/8) Epoch 10, batch 3200, loss[loss=0.172, simple_loss=0.2695, pruned_loss=0.03726, over 7233.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2676, pruned_loss=0.04787, over 1425589.65 frames.], batch size: 20, lr: 7.47e-04
+2022-05-14 10:07:23,030 INFO [train.py:812] (1/8) Epoch 10, batch 3250, loss[loss=0.177, simple_loss=0.278, pruned_loss=0.03806, over 7420.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2691, pruned_loss=0.04857, over 1427533.82 frames.], batch size: 21, lr: 7.46e-04
+2022-05-14 10:08:22,151 INFO [train.py:812] (1/8) Epoch 10, batch 3300, loss[loss=0.185, simple_loss=0.2711, pruned_loss=0.04942, over 7204.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2693, pruned_loss=0.04892, over 1428445.46 frames.], batch size: 22, lr: 7.46e-04
+2022-05-14 10:09:21,719 INFO [train.py:812] (1/8) Epoch 10, batch 3350, loss[loss=0.1823, simple_loss=0.2688, pruned_loss=0.04791, over 7194.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2703, pruned_loss=0.04912, over 1430264.48 frames.], batch size: 23, lr: 7.45e-04
+2022-05-14 10:10:20,624 INFO [train.py:812] (1/8) Epoch 10, batch 3400, loss[loss=0.1356, simple_loss=0.2143, pruned_loss=0.0285, over 7269.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2702, pruned_loss=0.04919, over 1425899.61 frames.], batch size: 17, lr: 7.45e-04
+2022-05-14 10:11:20,099 INFO [train.py:812] (1/8) Epoch 10, batch 3450, loss[loss=0.1594, simple_loss=0.2535, pruned_loss=0.03265, over 7280.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2703, pruned_loss=0.0494, over 1424932.04 frames.], batch size: 24, lr: 7.45e-04
+2022-05-14 10:12:19,083 INFO [train.py:812] (1/8) Epoch 10, batch 3500, loss[loss=0.1858, simple_loss=0.2836, pruned_loss=0.04402, over 7422.00 frames.], tot_loss[loss=0.184, simple_loss=0.2702, pruned_loss=0.04888, over 1424706.66 frames.], batch size: 21, lr: 7.44e-04
+2022-05-14 10:13:18,714 INFO [train.py:812] (1/8) Epoch 10, batch 3550, loss[loss=0.1841, simple_loss=0.2704, pruned_loss=0.0489, over 7011.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2689, pruned_loss=0.04831, over 1427424.61 frames.], batch size: 28, lr: 7.44e-04
+2022-05-14 10:14:16,914 INFO [train.py:812] (1/8) Epoch 10, batch 3600, loss[loss=0.228, simple_loss=0.3076, pruned_loss=0.07417, over 7024.00 frames.], tot_loss[loss=0.1827, simple_loss=0.269, pruned_loss=0.04823, over 1427248.21 frames.], batch size: 28, lr: 7.43e-04
+2022-05-14 10:15:16,464 INFO [train.py:812] (1/8) Epoch 10, batch 3650, loss[loss=0.1521, simple_loss=0.2454, pruned_loss=0.02942, over 7071.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2688, pruned_loss=0.04839, over 1423389.92 frames.], batch size: 18, lr: 7.43e-04
+2022-05-14 10:16:15,505 INFO [train.py:812] (1/8) Epoch 10, batch 3700, loss[loss=0.1913, simple_loss=0.2678, pruned_loss=0.05741, over 7277.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2694, pruned_loss=0.04854, over 1425411.95 frames.], batch size: 17, lr: 7.43e-04
+2022-05-14 10:17:15,201 INFO [train.py:812] (1/8) Epoch 10, batch 3750, loss[loss=0.1688, simple_loss=0.2579, pruned_loss=0.03981, over 7162.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2701, pruned_loss=0.04861, over 1428188.17 frames.], batch size: 19, lr: 7.42e-04
+2022-05-14 10:18:14,390 INFO [train.py:812] (1/8) Epoch 10, batch 3800, loss[loss=0.1754, simple_loss=0.2601, pruned_loss=0.04537, over 7416.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2704, pruned_loss=0.04891, over 1426305.49 frames.], batch size: 20, lr: 7.42e-04
+2022-05-14 10:19:12,955 INFO [train.py:812] (1/8) Epoch 10, batch 3850, loss[loss=0.1807, simple_loss=0.271, pruned_loss=0.04517, over 7071.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2712, pruned_loss=0.04905, over 1425384.11 frames.], batch size: 18, lr: 7.41e-04
+2022-05-14 10:20:21,775 INFO [train.py:812] (1/8) Epoch 10, batch 3900, loss[loss=0.1918, simple_loss=0.2852, pruned_loss=0.04913, over 7162.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2702, pruned_loss=0.04859, over 1427363.19 frames.], batch size: 19, lr: 7.41e-04
+2022-05-14 10:21:21,331 INFO [train.py:812] (1/8) Epoch 10, batch 3950, loss[loss=0.2441, simple_loss=0.3237, pruned_loss=0.08227, over 5113.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2694, pruned_loss=0.04842, over 1422327.60 frames.], batch size: 52, lr: 7.41e-04
+2022-05-14 10:22:19,904 INFO [train.py:812] (1/8) Epoch 10, batch 4000, loss[loss=0.1713, simple_loss=0.2578, pruned_loss=0.04241, over 7263.00 frames.], tot_loss[loss=0.1839, simple_loss=0.27, pruned_loss=0.0489, over 1423824.39 frames.], batch size: 19, lr: 7.40e-04
+2022-05-14 10:23:18,816 INFO [train.py:812] (1/8) Epoch 10, batch 4050, loss[loss=0.187, simple_loss=0.2666, pruned_loss=0.0537, over 7132.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2705, pruned_loss=0.04944, over 1424478.83 frames.], batch size: 17, lr: 7.40e-04
+2022-05-14 10:24:16,991 INFO [train.py:812] (1/8) Epoch 10, batch 4100, loss[loss=0.1799, simple_loss=0.274, pruned_loss=0.04292, over 7329.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2697, pruned_loss=0.04876, over 1425992.70 frames.], batch size: 21, lr: 7.39e-04
+2022-05-14 10:25:16,586 INFO [train.py:812] (1/8) Epoch 10, batch 4150, loss[loss=0.1634, simple_loss=0.2449, pruned_loss=0.04097, over 7402.00 frames.], tot_loss[loss=0.184, simple_loss=0.27, pruned_loss=0.04896, over 1425711.49 frames.], batch size: 18, lr: 7.39e-04
+2022-05-14 10:26:14,792 INFO [train.py:812] (1/8) Epoch 10, batch 4200, loss[loss=0.206, simple_loss=0.291, pruned_loss=0.06056, over 7283.00 frames.], tot_loss[loss=0.1841, simple_loss=0.27, pruned_loss=0.04907, over 1427359.92 frames.], batch size: 24, lr: 7.39e-04
+2022-05-14 10:27:13,948 INFO [train.py:812] (1/8) Epoch 10, batch 4250, loss[loss=0.1747, simple_loss=0.2499, pruned_loss=0.04976, over 7279.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2702, pruned_loss=0.04911, over 1423973.58 frames.], batch size: 17, lr: 7.38e-04
+2022-05-14 10:28:13,108 INFO [train.py:812] (1/8) Epoch 10, batch 4300, loss[loss=0.2189, simple_loss=0.3161, pruned_loss=0.06087, over 7295.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2705, pruned_loss=0.04936, over 1418534.02 frames.], batch size: 24, lr: 7.38e-04
+2022-05-14 10:29:10,975 INFO [train.py:812] (1/8) Epoch 10, batch 4350, loss[loss=0.2111, simple_loss=0.2808, pruned_loss=0.07066, over 4985.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2718, pruned_loss=0.0499, over 1408603.35 frames.], batch size: 52, lr: 7.37e-04
+2022-05-14 10:30:10,253 INFO [train.py:812] (1/8) Epoch 10, batch 4400, loss[loss=0.1877, simple_loss=0.2698, pruned_loss=0.05282, over 7196.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2724, pruned_loss=0.05036, over 1412189.21 frames.], batch size: 22, lr: 7.37e-04
+2022-05-14 10:31:10,031 INFO [train.py:812] (1/8) Epoch 10, batch 4450, loss[loss=0.221, simple_loss=0.2915, pruned_loss=0.07528, over 5216.00 frames.], tot_loss[loss=0.188, simple_loss=0.2734, pruned_loss=0.05126, over 1396309.25 frames.], batch size: 53, lr: 7.37e-04
+2022-05-14 10:32:09,140 INFO [train.py:812] (1/8) Epoch 10, batch 4500, loss[loss=0.1793, simple_loss=0.268, pruned_loss=0.04528, over 7143.00 frames.], tot_loss[loss=0.187, simple_loss=0.272, pruned_loss=0.05094, over 1393236.96 frames.], batch size: 20, lr: 7.36e-04
+2022-05-14 10:33:08,611 INFO [train.py:812] (1/8) Epoch 10, batch 4550, loss[loss=0.2131, simple_loss=0.2976, pruned_loss=0.06433, over 7159.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2718, pruned_loss=0.05154, over 1374702.96 frames.], batch size: 26, lr: 7.36e-04
+2022-05-14 10:34:22,339 INFO [train.py:812] (1/8) Epoch 11, batch 0, loss[loss=0.2034, simple_loss=0.2863, pruned_loss=0.06022, over 7437.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2863, pruned_loss=0.06022, over 7437.00 frames.], batch size: 20, lr: 7.08e-04
+2022-05-14 10:35:21,218 INFO [train.py:812] (1/8) Epoch 11, batch 50, loss[loss=0.1822, simple_loss=0.2795, pruned_loss=0.04239, over 7430.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2751, pruned_loss=0.05035, over 322684.91 frames.], batch size: 20, lr: 7.08e-04
+2022-05-14 10:36:19,854 INFO [train.py:812] (1/8) Epoch 11, batch 100, loss[loss=0.1597, simple_loss=0.2418, pruned_loss=0.03884, over 7284.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2725, pruned_loss=0.05037, over 567291.56 frames.], batch size: 18, lr: 7.08e-04
+2022-05-14 10:37:28,462 INFO [train.py:812] (1/8) Epoch 11, batch 150, loss[loss=0.1554, simple_loss=0.2374, pruned_loss=0.0367, over 7224.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2741, pruned_loss=0.05047, over 760372.89 frames.], batch size: 16, lr: 7.07e-04
+2022-05-14 10:38:36,332 INFO [train.py:812] (1/8) Epoch 11, batch 200, loss[loss=0.1623, simple_loss=0.2392, pruned_loss=0.04275, over 7415.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2713, pruned_loss=0.04878, over 908053.91 frames.], batch size: 18, lr: 7.07e-04
+2022-05-14 10:39:34,529 INFO [train.py:812] (1/8) Epoch 11, batch 250, loss[loss=0.2062, simple_loss=0.2962, pruned_loss=0.05808, over 6350.00 frames.], tot_loss[loss=0.183, simple_loss=0.2698, pruned_loss=0.04808, over 1023558.26 frames.], batch size: 38, lr: 7.06e-04
+2022-05-14 10:40:50,471 INFO [train.py:812] (1/8) Epoch 11, batch 300, loss[loss=0.2241, simple_loss=0.2973, pruned_loss=0.07543, over 5099.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2684, pruned_loss=0.04759, over 1114980.67 frames.], batch size: 52, lr: 7.06e-04
+2022-05-14 10:41:47,787 INFO [train.py:812] (1/8) Epoch 11, batch 350, loss[loss=0.209, simple_loss=0.2982, pruned_loss=0.05993, over 6785.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2674, pruned_loss=0.04686, over 1187528.34 frames.], batch size: 31, lr: 7.06e-04
+2022-05-14 10:43:03,921 INFO [train.py:812] (1/8) Epoch 11, batch 400, loss[loss=0.1752, simple_loss=0.2683, pruned_loss=0.04107, over 7427.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2673, pruned_loss=0.04698, over 1241895.73 frames.], batch size: 20, lr: 7.05e-04
+2022-05-14 10:44:13,169 INFO [train.py:812] (1/8) Epoch 11, batch 450, loss[loss=0.1841, simple_loss=0.2731, pruned_loss=0.04761, over 7234.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2657, pruned_loss=0.04685, over 1282231.65 frames.], batch size: 20, lr: 7.05e-04
+2022-05-14 10:45:12,582 INFO [train.py:812] (1/8) Epoch 11, batch 500, loss[loss=0.1653, simple_loss=0.2456, pruned_loss=0.04248, over 7330.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2652, pruned_loss=0.04684, over 1317313.90 frames.], batch size: 20, lr: 7.04e-04
+2022-05-14 10:46:12,007 INFO [train.py:812] (1/8) Epoch 11, batch 550, loss[loss=0.1611, simple_loss=0.2445, pruned_loss=0.03882, over 7060.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2655, pruned_loss=0.047, over 1342120.81 frames.], batch size: 18, lr: 7.04e-04
+2022-05-14 10:47:11,313 INFO [train.py:812] (1/8) Epoch 11, batch 600, loss[loss=0.149, simple_loss=0.2342, pruned_loss=0.03189, over 6989.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2665, pruned_loss=0.04783, over 1360944.84 frames.], batch size: 16, lr: 7.04e-04
+2022-05-14 10:48:09,764 INFO [train.py:812] (1/8) Epoch 11, batch 650, loss[loss=0.1742, simple_loss=0.248, pruned_loss=0.05023, over 7124.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2669, pruned_loss=0.04837, over 1366548.67 frames.], batch size: 17, lr: 7.03e-04
+2022-05-14 10:49:08,406 INFO [train.py:812] (1/8) Epoch 11, batch 700, loss[loss=0.1602, simple_loss=0.2485, pruned_loss=0.0359, over 7253.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2679, pruned_loss=0.04871, over 1377060.44 frames.], batch size: 16, lr: 7.03e-04
+2022-05-14 10:50:07,691 INFO [train.py:812] (1/8) Epoch 11, batch 750, loss[loss=0.1918, simple_loss=0.2924, pruned_loss=0.04561, over 7148.00 frames.], tot_loss[loss=0.1827, simple_loss=0.268, pruned_loss=0.04869, over 1384164.64 frames.], batch size: 20, lr: 7.03e-04
+2022-05-14 10:51:05,917 INFO [train.py:812] (1/8) Epoch 11, batch 800, loss[loss=0.1962, simple_loss=0.2838, pruned_loss=0.05434, over 7164.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2679, pruned_loss=0.04842, over 1396176.86 frames.], batch size: 26, lr: 7.02e-04
+2022-05-14 10:52:03,629 INFO [train.py:812] (1/8) Epoch 11, batch 850, loss[loss=0.175, simple_loss=0.2668, pruned_loss=0.04156, over 7334.00 frames.], tot_loss[loss=0.1826, simple_loss=0.268, pruned_loss=0.04854, over 1400631.09 frames.], batch size: 20, lr: 7.02e-04
+2022-05-14 10:53:01,756 INFO [train.py:812] (1/8) Epoch 11, batch 900, loss[loss=0.1637, simple_loss=0.2503, pruned_loss=0.03853, over 7429.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2685, pruned_loss=0.04882, over 1408880.40 frames.], batch size: 20, lr: 7.02e-04
+2022-05-14 10:54:00,387 INFO [train.py:812] (1/8) Epoch 11, batch 950, loss[loss=0.1679, simple_loss=0.2461, pruned_loss=0.04484, over 6998.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2675, pruned_loss=0.04788, over 1410634.63 frames.], batch size: 16, lr: 7.01e-04
+2022-05-14 10:54:58,954 INFO [train.py:812] (1/8) Epoch 11, batch 1000, loss[loss=0.2082, simple_loss=0.2997, pruned_loss=0.05835, over 7276.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2667, pruned_loss=0.04775, over 1414453.04 frames.], batch size: 25, lr: 7.01e-04
+2022-05-14 10:55:58,050 INFO [train.py:812] (1/8) Epoch 11, batch 1050, loss[loss=0.1666, simple_loss=0.247, pruned_loss=0.04311, over 7250.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2679, pruned_loss=0.04826, over 1409143.02 frames.], batch size: 19, lr: 7.00e-04
+2022-05-14 10:56:57,227 INFO [train.py:812] (1/8) Epoch 11, batch 1100, loss[loss=0.1622, simple_loss=0.2417, pruned_loss=0.04134, over 7170.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2677, pruned_loss=0.0479, over 1413797.95 frames.], batch size: 18, lr: 7.00e-04
+2022-05-14 10:57:56,859 INFO [train.py:812] (1/8) Epoch 11, batch 1150, loss[loss=0.1797, simple_loss=0.2607, pruned_loss=0.0494, over 7061.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2669, pruned_loss=0.04774, over 1417907.19 frames.], batch size: 18, lr: 7.00e-04
+2022-05-14 10:58:55,459 INFO [train.py:812] (1/8) Epoch 11, batch 1200, loss[loss=0.1536, simple_loss=0.2277, pruned_loss=0.03972, over 6797.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2661, pruned_loss=0.04753, over 1420574.35 frames.], batch size: 15, lr: 6.99e-04
+2022-05-14 10:59:53,781 INFO [train.py:812] (1/8) Epoch 11, batch 1250, loss[loss=0.1552, simple_loss=0.228, pruned_loss=0.04118, over 7128.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2654, pruned_loss=0.04714, over 1423642.81 frames.], batch size: 17, lr: 6.99e-04
+2022-05-14 11:00:50,429 INFO [train.py:812] (1/8) Epoch 11, batch 1300, loss[loss=0.1483, simple_loss=0.2485, pruned_loss=0.02403, over 7317.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2656, pruned_loss=0.04735, over 1419646.25 frames.], batch size: 21, lr: 6.99e-04
+2022-05-14 11:01:49,331 INFO [train.py:812] (1/8) Epoch 11, batch 1350, loss[loss=0.1822, simple_loss=0.2704, pruned_loss=0.04697, over 7325.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2658, pruned_loss=0.04734, over 1423790.70 frames.], batch size: 21, lr: 6.98e-04
+2022-05-14 11:02:46,393 INFO [train.py:812] (1/8) Epoch 11, batch 1400, loss[loss=0.1714, simple_loss=0.2565, pruned_loss=0.04312, over 7170.00 frames.], tot_loss[loss=0.18, simple_loss=0.2652, pruned_loss=0.04735, over 1426961.12 frames.], batch size: 19, lr: 6.98e-04
+2022-05-14 11:03:44,650 INFO [train.py:812] (1/8) Epoch 11, batch 1450, loss[loss=0.1735, simple_loss=0.2596, pruned_loss=0.04377, over 7254.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2659, pruned_loss=0.04731, over 1427345.51 frames.], batch size: 17, lr: 6.97e-04
+2022-05-14 11:04:41,552 INFO [train.py:812] (1/8) Epoch 11, batch 1500, loss[loss=0.1659, simple_loss=0.2719, pruned_loss=0.02991, over 7030.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2662, pruned_loss=0.04718, over 1425466.06 frames.], batch size: 28, lr: 6.97e-04
+2022-05-14 11:05:41,357 INFO [train.py:812] (1/8) Epoch 11, batch 1550, loss[loss=0.1503, simple_loss=0.2417, pruned_loss=0.02941, over 7429.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2666, pruned_loss=0.04709, over 1423829.01 frames.], batch size: 20, lr: 6.97e-04
+2022-05-14 11:06:38,922 INFO [train.py:812] (1/8) Epoch 11, batch 1600, loss[loss=0.2018, simple_loss=0.2938, pruned_loss=0.0549, over 6729.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2662, pruned_loss=0.04714, over 1418488.50 frames.], batch size: 31, lr: 6.96e-04
+2022-05-14 11:07:38,264 INFO [train.py:812] (1/8) Epoch 11, batch 1650, loss[loss=0.1654, simple_loss=0.2411, pruned_loss=0.04487, over 6813.00 frames.], tot_loss[loss=0.18, simple_loss=0.2659, pruned_loss=0.04709, over 1417282.59 frames.], batch size: 15, lr: 6.96e-04
+2022-05-14 11:08:37,013 INFO [train.py:812] (1/8) Epoch 11, batch 1700, loss[loss=0.1565, simple_loss=0.2347, pruned_loss=0.03912, over 6801.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2668, pruned_loss=0.04729, over 1416574.51 frames.], batch size: 15, lr: 6.96e-04
+2022-05-14 11:09:36,824 INFO [train.py:812] (1/8) Epoch 11, batch 1750, loss[loss=0.1683, simple_loss=0.2642, pruned_loss=0.03616, over 7118.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2666, pruned_loss=0.04784, over 1413098.49 frames.], batch size: 21, lr: 6.95e-04
+2022-05-14 11:10:35,677 INFO [train.py:812] (1/8) Epoch 11, batch 1800, loss[loss=0.184, simple_loss=0.269, pruned_loss=0.04951, over 5471.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2665, pruned_loss=0.04721, over 1413198.22 frames.], batch size: 53, lr: 6.95e-04
+2022-05-14 11:11:35,358 INFO [train.py:812] (1/8) Epoch 11, batch 1850, loss[loss=0.1841, simple_loss=0.2777, pruned_loss=0.04528, over 6494.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2667, pruned_loss=0.04719, over 1417813.48 frames.], batch size: 38, lr: 6.95e-04
+2022-05-14 11:12:33,309 INFO [train.py:812] (1/8) Epoch 11, batch 1900, loss[loss=0.1963, simple_loss=0.2976, pruned_loss=0.04756, over 7319.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2669, pruned_loss=0.04744, over 1422037.04 frames.], batch size: 21, lr: 6.94e-04
+2022-05-14 11:13:32,942 INFO [train.py:812] (1/8) Epoch 11, batch 1950, loss[loss=0.1992, simple_loss=0.291, pruned_loss=0.05364, over 7356.00 frames.], tot_loss[loss=0.1811, simple_loss=0.267, pruned_loss=0.04759, over 1421641.29 frames.], batch size: 19, lr: 6.94e-04
+2022-05-14 11:14:32,019 INFO [train.py:812] (1/8) Epoch 11, batch 2000, loss[loss=0.1671, simple_loss=0.2477, pruned_loss=0.04322, over 7169.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2673, pruned_loss=0.04758, over 1423255.98 frames.], batch size: 18, lr: 6.93e-04
+2022-05-14 11:15:30,885 INFO [train.py:812] (1/8) Epoch 11, batch 2050, loss[loss=0.1751, simple_loss=0.2503, pruned_loss=0.04996, over 7279.00 frames.], tot_loss[loss=0.181, simple_loss=0.2672, pruned_loss=0.04745, over 1424387.86 frames.], batch size: 17, lr: 6.93e-04
+2022-05-14 11:16:30,465 INFO [train.py:812] (1/8) Epoch 11, batch 2100, loss[loss=0.1821, simple_loss=0.2698, pruned_loss=0.04721, over 7380.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2674, pruned_loss=0.04738, over 1424761.62 frames.], batch size: 23, lr: 6.93e-04
+2022-05-14 11:17:37,595 INFO [train.py:812] (1/8) Epoch 11, batch 2150, loss[loss=0.1613, simple_loss=0.2536, pruned_loss=0.0345, over 7155.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2669, pruned_loss=0.04744, over 1425211.13 frames.], batch size: 18, lr: 6.92e-04
+2022-05-14 11:18:36,035 INFO [train.py:812] (1/8) Epoch 11, batch 2200, loss[loss=0.1665, simple_loss=0.2562, pruned_loss=0.03846, over 7238.00 frames.], tot_loss[loss=0.181, simple_loss=0.2669, pruned_loss=0.0475, over 1423822.84 frames.], batch size: 20, lr: 6.92e-04
+2022-05-14 11:19:35,022 INFO [train.py:812] (1/8) Epoch 11, batch 2250, loss[loss=0.1879, simple_loss=0.2766, pruned_loss=0.04954, over 7336.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2676, pruned_loss=0.04785, over 1427064.93 frames.], batch size: 22, lr: 6.92e-04
+2022-05-14 11:20:34,376 INFO [train.py:812] (1/8) Epoch 11, batch 2300, loss[loss=0.2021, simple_loss=0.2925, pruned_loss=0.05588, over 7173.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2676, pruned_loss=0.04804, over 1427489.33 frames.], batch size: 26, lr: 6.91e-04
+2022-05-14 11:21:33,302 INFO [train.py:812] (1/8) Epoch 11, batch 2350, loss[loss=0.1825, simple_loss=0.2691, pruned_loss=0.04796, over 6957.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2668, pruned_loss=0.04734, over 1429921.52 frames.], batch size: 32, lr: 6.91e-04
+2022-05-14 11:22:32,010 INFO [train.py:812] (1/8) Epoch 11, batch 2400, loss[loss=0.2084, simple_loss=0.2965, pruned_loss=0.06014, over 7311.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2663, pruned_loss=0.04726, over 1423088.84 frames.], batch size: 21, lr: 6.91e-04
+2022-05-14 11:23:31,119 INFO [train.py:812] (1/8) Epoch 11, batch 2450, loss[loss=0.2137, simple_loss=0.2859, pruned_loss=0.07072, over 7006.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2652, pruned_loss=0.04691, over 1423717.82 frames.], batch size: 16, lr: 6.90e-04
+2022-05-14 11:24:30,207 INFO [train.py:812] (1/8) Epoch 11, batch 2500, loss[loss=0.1612, simple_loss=0.2552, pruned_loss=0.03359, over 7165.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2662, pruned_loss=0.04708, over 1422258.69 frames.], batch size: 19, lr: 6.90e-04
+2022-05-14 11:25:29,318 INFO [train.py:812] (1/8) Epoch 11, batch 2550, loss[loss=0.1478, simple_loss=0.2331, pruned_loss=0.03128, over 7177.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2658, pruned_loss=0.04647, over 1426299.16 frames.], batch size: 16, lr: 6.90e-04
+2022-05-14 11:26:27,797 INFO [train.py:812] (1/8) Epoch 11, batch 2600, loss[loss=0.1814, simple_loss=0.2655, pruned_loss=0.0486, over 7371.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2659, pruned_loss=0.04676, over 1427336.29 frames.], batch size: 23, lr: 6.89e-04
+2022-05-14 11:27:26,093 INFO [train.py:812] (1/8) Epoch 11, batch 2650, loss[loss=0.1504, simple_loss=0.2259, pruned_loss=0.0375, over 7014.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2667, pruned_loss=0.04715, over 1422570.04 frames.], batch size: 16, lr: 6.89e-04
+2022-05-14 11:28:23,549 INFO [train.py:812] (1/8) Epoch 11, batch 2700, loss[loss=0.1905, simple_loss=0.2853, pruned_loss=0.04787, over 7414.00 frames.], tot_loss[loss=0.1805, simple_loss=0.267, pruned_loss=0.04696, over 1425789.13 frames.], batch size: 21, lr: 6.89e-04
+2022-05-14 11:29:20,996 INFO [train.py:812] (1/8) Epoch 11, batch 2750, loss[loss=0.1655, simple_loss=0.2486, pruned_loss=0.04117, over 7296.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2657, pruned_loss=0.04676, over 1424143.65 frames.], batch size: 18, lr: 6.88e-04
+2022-05-14 11:30:17,967 INFO [train.py:812] (1/8) Epoch 11, batch 2800, loss[loss=0.1852, simple_loss=0.2845, pruned_loss=0.04289, over 7153.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2663, pruned_loss=0.04676, over 1423543.99 frames.], batch size: 19, lr: 6.88e-04
+2022-05-14 11:31:17,637 INFO [train.py:812] (1/8) Epoch 11, batch 2850, loss[loss=0.1949, simple_loss=0.2871, pruned_loss=0.05133, over 7324.00 frames.], tot_loss[loss=0.1796, simple_loss=0.266, pruned_loss=0.04659, over 1424660.25 frames.], batch size: 21, lr: 6.87e-04
+2022-05-14 11:32:14,489 INFO [train.py:812] (1/8) Epoch 11, batch 2900, loss[loss=0.2183, simple_loss=0.3014, pruned_loss=0.06761, over 7206.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2662, pruned_loss=0.04647, over 1427341.16 frames.], batch size: 23, lr: 6.87e-04
+2022-05-14 11:33:13,353 INFO [train.py:812] (1/8) Epoch 11, batch 2950, loss[loss=0.1914, simple_loss=0.2755, pruned_loss=0.0536, over 7194.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2671, pruned_loss=0.04662, over 1425187.14 frames.], batch size: 22, lr: 6.87e-04
+2022-05-14 11:34:12,262 INFO [train.py:812] (1/8) Epoch 11, batch 3000, loss[loss=0.1552, simple_loss=0.2457, pruned_loss=0.03236, over 7159.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2671, pruned_loss=0.04657, over 1423825.66 frames.], batch size: 18, lr: 6.86e-04
+2022-05-14 11:34:12,263 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 11:34:19,822 INFO [train.py:841] (1/8) Epoch 11, validation: loss=0.1564, simple_loss=0.2581, pruned_loss=0.02737, over 698248.00 frames.
+2022-05-14 11:35:18,260 INFO [train.py:812] (1/8) Epoch 11, batch 3050, loss[loss=0.1868, simple_loss=0.2723, pruned_loss=0.05069, over 7182.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2665, pruned_loss=0.04689, over 1427611.79 frames.], batch size: 26, lr: 6.86e-04
+2022-05-14 11:36:16,725 INFO [train.py:812] (1/8) Epoch 11, batch 3100, loss[loss=0.1702, simple_loss=0.2468, pruned_loss=0.04682, over 7411.00 frames.], tot_loss[loss=0.1814, simple_loss=0.267, pruned_loss=0.04787, over 1425596.91 frames.], batch size: 18, lr: 6.86e-04
+2022-05-14 11:37:16,184 INFO [train.py:812] (1/8) Epoch 11, batch 3150, loss[loss=0.1397, simple_loss=0.2273, pruned_loss=0.02609, over 7280.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2663, pruned_loss=0.04742, over 1427891.67 frames.], batch size: 18, lr: 6.85e-04
+2022-05-14 11:38:15,164 INFO [train.py:812] (1/8) Epoch 11, batch 3200, loss[loss=0.1348, simple_loss=0.2234, pruned_loss=0.02311, over 7153.00 frames.], tot_loss[loss=0.18, simple_loss=0.2655, pruned_loss=0.04725, over 1429767.30 frames.], batch size: 18, lr: 6.85e-04
+2022-05-14 11:39:14,885 INFO [train.py:812] (1/8) Epoch 11, batch 3250, loss[loss=0.1647, simple_loss=0.2514, pruned_loss=0.03901, over 7069.00 frames.], tot_loss[loss=0.18, simple_loss=0.2656, pruned_loss=0.04717, over 1431401.73 frames.], batch size: 18, lr: 6.85e-04
+2022-05-14 11:40:14,266 INFO [train.py:812] (1/8) Epoch 11, batch 3300, loss[loss=0.1888, simple_loss=0.2724, pruned_loss=0.05263, over 6583.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2658, pruned_loss=0.04727, over 1431225.66 frames.], batch size: 38, lr: 6.84e-04
+2022-05-14 11:41:13,840 INFO [train.py:812] (1/8) Epoch 11, batch 3350, loss[loss=0.1857, simple_loss=0.2772, pruned_loss=0.04709, over 7120.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2667, pruned_loss=0.04782, over 1425322.94 frames.], batch size: 21, lr: 6.84e-04
+2022-05-14 11:42:12,400 INFO [train.py:812] (1/8) Epoch 11, batch 3400, loss[loss=0.1441, simple_loss=0.2274, pruned_loss=0.03044, over 6993.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2669, pruned_loss=0.04773, over 1421641.32 frames.], batch size: 16, lr: 6.84e-04
+2022-05-14 11:43:11,480 INFO [train.py:812] (1/8) Epoch 11, batch 3450, loss[loss=0.1785, simple_loss=0.2682, pruned_loss=0.04442, over 7108.00 frames.], tot_loss[loss=0.181, simple_loss=0.267, pruned_loss=0.04752, over 1424539.11 frames.], batch size: 21, lr: 6.83e-04
+2022-05-14 11:44:10,163 INFO [train.py:812] (1/8) Epoch 11, batch 3500, loss[loss=0.1651, simple_loss=0.2434, pruned_loss=0.04342, over 7398.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2666, pruned_loss=0.0475, over 1424988.20 frames.], batch size: 18, lr: 6.83e-04
+2022-05-14 11:45:10,019 INFO [train.py:812] (1/8) Epoch 11, batch 3550, loss[loss=0.1716, simple_loss=0.257, pruned_loss=0.04307, over 6414.00 frames.], tot_loss[loss=0.1802, simple_loss=0.266, pruned_loss=0.04716, over 1423934.81 frames.], batch size: 38, lr: 6.83e-04
+2022-05-14 11:46:08,746 INFO [train.py:812] (1/8) Epoch 11, batch 3600, loss[loss=0.1636, simple_loss=0.2505, pruned_loss=0.03832, over 6329.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2657, pruned_loss=0.04699, over 1419917.77 frames.], batch size: 37, lr: 6.82e-04
+2022-05-14 11:47:07,755 INFO [train.py:812] (1/8) Epoch 11, batch 3650, loss[loss=0.171, simple_loss=0.258, pruned_loss=0.04205, over 7117.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2657, pruned_loss=0.04664, over 1422234.29 frames.], batch size: 21, lr: 6.82e-04
+2022-05-14 11:48:06,837 INFO [train.py:812] (1/8) Epoch 11, batch 3700, loss[loss=0.1924, simple_loss=0.2869, pruned_loss=0.04889, over 7118.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2664, pruned_loss=0.04686, over 1418591.54 frames.], batch size: 21, lr: 6.82e-04
+2022-05-14 11:49:06,473 INFO [train.py:812] (1/8) Epoch 11, batch 3750, loss[loss=0.175, simple_loss=0.2612, pruned_loss=0.04447, over 7433.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2661, pruned_loss=0.04656, over 1424379.87 frames.], batch size: 20, lr: 6.81e-04
+2022-05-14 11:50:05,389 INFO [train.py:812] (1/8) Epoch 11, batch 3800, loss[loss=0.1802, simple_loss=0.2788, pruned_loss=0.04075, over 7325.00 frames.], tot_loss[loss=0.1796, simple_loss=0.266, pruned_loss=0.04654, over 1422873.71 frames.], batch size: 24, lr: 6.81e-04
+2022-05-14 11:51:04,551 INFO [train.py:812] (1/8) Epoch 11, batch 3850, loss[loss=0.1916, simple_loss=0.2824, pruned_loss=0.05043, over 7218.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2654, pruned_loss=0.04618, over 1426743.01 frames.], batch size: 22, lr: 6.81e-04
+2022-05-14 11:52:01,422 INFO [train.py:812] (1/8) Epoch 11, batch 3900, loss[loss=0.1774, simple_loss=0.2698, pruned_loss=0.04253, over 7383.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2651, pruned_loss=0.04624, over 1427045.62 frames.], batch size: 23, lr: 6.80e-04
+2022-05-14 11:53:00,851 INFO [train.py:812] (1/8) Epoch 11, batch 3950, loss[loss=0.2109, simple_loss=0.2926, pruned_loss=0.0646, over 7432.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2643, pruned_loss=0.04599, over 1426143.39 frames.], batch size: 20, lr: 6.80e-04
+2022-05-14 11:53:59,461 INFO [train.py:812] (1/8) Epoch 11, batch 4000, loss[loss=0.174, simple_loss=0.2762, pruned_loss=0.03592, over 7218.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2644, pruned_loss=0.04623, over 1418161.15 frames.], batch size: 21, lr: 6.80e-04
+2022-05-14 11:54:58,915 INFO [train.py:812] (1/8) Epoch 11, batch 4050, loss[loss=0.2126, simple_loss=0.2991, pruned_loss=0.06312, over 7200.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2657, pruned_loss=0.04697, over 1418449.91 frames.], batch size: 22, lr: 6.79e-04
+2022-05-14 11:55:57,981 INFO [train.py:812] (1/8) Epoch 11, batch 4100, loss[loss=0.1899, simple_loss=0.2738, pruned_loss=0.05304, over 7205.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2658, pruned_loss=0.04701, over 1417936.90 frames.], batch size: 22, lr: 6.79e-04
+2022-05-14 11:56:56,027 INFO [train.py:812] (1/8) Epoch 11, batch 4150, loss[loss=0.2017, simple_loss=0.2773, pruned_loss=0.06302, over 6798.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2666, pruned_loss=0.04724, over 1415457.31 frames.], batch size: 31, lr: 6.79e-04
+2022-05-14 11:57:54,855 INFO [train.py:812] (1/8) Epoch 11, batch 4200, loss[loss=0.1706, simple_loss=0.2549, pruned_loss=0.04315, over 7071.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2681, pruned_loss=0.04762, over 1416393.44 frames.], batch size: 28, lr: 6.78e-04
+2022-05-14 11:58:54,365 INFO [train.py:812] (1/8) Epoch 11, batch 4250, loss[loss=0.2173, simple_loss=0.3047, pruned_loss=0.06492, over 5147.00 frames.], tot_loss[loss=0.181, simple_loss=0.267, pruned_loss=0.04754, over 1415391.13 frames.], batch size: 52, lr: 6.78e-04
+2022-05-14 11:59:53,053 INFO [train.py:812] (1/8) Epoch 11, batch 4300, loss[loss=0.2592, simple_loss=0.3299, pruned_loss=0.09429, over 5278.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2679, pruned_loss=0.04815, over 1412067.97 frames.], batch size: 53, lr: 6.78e-04
+2022-05-14 12:00:52,212 INFO [train.py:812] (1/8) Epoch 11, batch 4350, loss[loss=0.1615, simple_loss=0.2558, pruned_loss=0.03363, over 7238.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2681, pruned_loss=0.04818, over 1410396.78 frames.], batch size: 20, lr: 6.77e-04
+2022-05-14 12:01:50,108 INFO [train.py:812] (1/8) Epoch 11, batch 4400, loss[loss=0.1968, simple_loss=0.2784, pruned_loss=0.05763, over 7205.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2695, pruned_loss=0.0487, over 1415651.23 frames.], batch size: 22, lr: 6.77e-04
+2022-05-14 12:02:49,051 INFO [train.py:812] (1/8) Epoch 11, batch 4450, loss[loss=0.1656, simple_loss=0.2597, pruned_loss=0.03577, over 7231.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2707, pruned_loss=0.04929, over 1418307.29 frames.], batch size: 20, lr: 6.77e-04
+2022-05-14 12:03:48,061 INFO [train.py:812] (1/8) Epoch 11, batch 4500, loss[loss=0.2529, simple_loss=0.315, pruned_loss=0.09539, over 4762.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2718, pruned_loss=0.0496, over 1410557.20 frames.], batch size: 52, lr: 6.76e-04
+2022-05-14 12:04:46,790 INFO [train.py:812] (1/8) Epoch 11, batch 4550, loss[loss=0.2317, simple_loss=0.3022, pruned_loss=0.0806, over 4787.00 frames.], tot_loss[loss=0.1888, simple_loss=0.274, pruned_loss=0.05182, over 1345863.85 frames.], batch size: 52, lr: 6.76e-04
+2022-05-14 12:05:54,958 INFO [train.py:812] (1/8) Epoch 12, batch 0, loss[loss=0.1842, simple_loss=0.2763, pruned_loss=0.04607, over 7408.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2763, pruned_loss=0.04607, over 7408.00 frames.], batch size: 21, lr: 6.52e-04
+2022-05-14 12:06:54,751 INFO [train.py:812] (1/8) Epoch 12, batch 50, loss[loss=0.1896, simple_loss=0.2663, pruned_loss=0.05646, over 5226.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2651, pruned_loss=0.04635, over 319294.08 frames.], batch size: 52, lr: 6.52e-04
+2022-05-14 12:07:53,906 INFO [train.py:812] (1/8) Epoch 12, batch 100, loss[loss=0.1541, simple_loss=0.2397, pruned_loss=0.03429, over 6341.00 frames.], tot_loss[loss=0.18, simple_loss=0.2668, pruned_loss=0.04656, over 558865.59 frames.], batch size: 38, lr: 6.51e-04
+2022-05-14 12:08:53,452 INFO [train.py:812] (1/8) Epoch 12, batch 150, loss[loss=0.1471, simple_loss=0.226, pruned_loss=0.03412, over 7262.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2696, pruned_loss=0.04781, over 749210.37 frames.], batch size: 17, lr: 6.51e-04
+2022-05-14 12:09:52,490 INFO [train.py:812] (1/8) Epoch 12, batch 200, loss[loss=0.2226, simple_loss=0.3112, pruned_loss=0.06697, over 7216.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2691, pruned_loss=0.04794, over 896436.66 frames.], batch size: 22, lr: 6.51e-04
+2022-05-14 12:10:51,861 INFO [train.py:812] (1/8) Epoch 12, batch 250, loss[loss=0.175, simple_loss=0.2593, pruned_loss=0.04532, over 6785.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2668, pruned_loss=0.04654, over 1014483.50 frames.], batch size: 31, lr: 6.50e-04
+2022-05-14 12:11:51,038 INFO [train.py:812] (1/8) Epoch 12, batch 300, loss[loss=0.1865, simple_loss=0.2758, pruned_loss=0.04856, over 7206.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2666, pruned_loss=0.04655, over 1099541.77 frames.], batch size: 22, lr: 6.50e-04
+2022-05-14 12:12:50,782 INFO [train.py:812] (1/8) Epoch 12, batch 350, loss[loss=0.1554, simple_loss=0.2556, pruned_loss=0.02762, over 7345.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2656, pruned_loss=0.04572, over 1166346.37 frames.], batch size: 22, lr: 6.50e-04
+2022-05-14 12:13:50,258 INFO [train.py:812] (1/8) Epoch 12, batch 400, loss[loss=0.1785, simple_loss=0.28, pruned_loss=0.03848, over 7336.00 frames.], tot_loss[loss=0.1791, simple_loss=0.266, pruned_loss=0.04604, over 1221441.25 frames.], batch size: 22, lr: 6.49e-04
+2022-05-14 12:14:48,357 INFO [train.py:812] (1/8) Epoch 12, batch 450, loss[loss=0.1671, simple_loss=0.2515, pruned_loss=0.04138, over 7168.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2655, pruned_loss=0.04552, over 1269752.76 frames.], batch size: 19, lr: 6.49e-04
+2022-05-14 12:15:47,352 INFO [train.py:812] (1/8) Epoch 12, batch 500, loss[loss=0.2203, simple_loss=0.3082, pruned_loss=0.06621, over 7376.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2657, pruned_loss=0.04571, over 1303597.95 frames.], batch size: 23, lr: 6.49e-04
+2022-05-14 12:16:45,617 INFO [train.py:812] (1/8) Epoch 12, batch 550, loss[loss=0.1909, simple_loss=0.28, pruned_loss=0.0509, over 7416.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2646, pruned_loss=0.04547, over 1329679.71 frames.], batch size: 21, lr: 6.48e-04
+2022-05-14 12:17:43,503 INFO [train.py:812] (1/8) Epoch 12, batch 600, loss[loss=0.1923, simple_loss=0.2823, pruned_loss=0.05115, over 7327.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2648, pruned_loss=0.04541, over 1348984.79 frames.], batch size: 22, lr: 6.48e-04
+2022-05-14 12:18:41,732 INFO [train.py:812] (1/8) Epoch 12, batch 650, loss[loss=0.2028, simple_loss=0.2896, pruned_loss=0.05802, over 7382.00 frames.], tot_loss[loss=0.177, simple_loss=0.2639, pruned_loss=0.04499, over 1370019.50 frames.], batch size: 23, lr: 6.48e-04
+2022-05-14 12:19:49,855 INFO [train.py:812] (1/8) Epoch 12, batch 700, loss[loss=0.2239, simple_loss=0.3084, pruned_loss=0.06968, over 7313.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2641, pruned_loss=0.04519, over 1380327.31 frames.], batch size: 24, lr: 6.47e-04
+2022-05-14 12:20:48,652 INFO [train.py:812] (1/8) Epoch 12, batch 750, loss[loss=0.144, simple_loss=0.2381, pruned_loss=0.02492, over 7313.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2654, pruned_loss=0.04555, over 1386504.65 frames.], batch size: 20, lr: 6.47e-04
+2022-05-14 12:21:47,951 INFO [train.py:812] (1/8) Epoch 12, batch 800, loss[loss=0.1675, simple_loss=0.2507, pruned_loss=0.04218, over 7409.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2652, pruned_loss=0.04519, over 1400097.47 frames.], batch size: 18, lr: 6.47e-04
+2022-05-14 12:22:46,127 INFO [train.py:812] (1/8) Epoch 12, batch 850, loss[loss=0.1755, simple_loss=0.2719, pruned_loss=0.03961, over 6747.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2665, pruned_loss=0.04565, over 1403652.01 frames.], batch size: 31, lr: 6.46e-04
+2022-05-14 12:23:43,975 INFO [train.py:812] (1/8) Epoch 12, batch 900, loss[loss=0.1788, simple_loss=0.2717, pruned_loss=0.04294, over 7342.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2668, pruned_loss=0.04576, over 1408264.18 frames.], batch size: 22, lr: 6.46e-04
+2022-05-14 12:24:43,682 INFO [train.py:812] (1/8) Epoch 12, batch 950, loss[loss=0.1695, simple_loss=0.2552, pruned_loss=0.04191, over 7432.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2665, pruned_loss=0.04588, over 1413151.05 frames.], batch size: 20, lr: 6.46e-04
+2022-05-14 12:25:42,167 INFO [train.py:812] (1/8) Epoch 12, batch 1000, loss[loss=0.1823, simple_loss=0.2755, pruned_loss=0.04451, over 7152.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2675, pruned_loss=0.04639, over 1415585.84 frames.], batch size: 19, lr: 6.46e-04
+2022-05-14 12:26:41,698 INFO [train.py:812] (1/8) Epoch 12, batch 1050, loss[loss=0.1628, simple_loss=0.244, pruned_loss=0.04074, over 6990.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2674, pruned_loss=0.04618, over 1415011.66 frames.], batch size: 16, lr: 6.45e-04
+2022-05-14 12:27:40,719 INFO [train.py:812] (1/8) Epoch 12, batch 1100, loss[loss=0.196, simple_loss=0.2773, pruned_loss=0.0573, over 7153.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2667, pruned_loss=0.04554, over 1418130.13 frames.], batch size: 19, lr: 6.45e-04
+2022-05-14 12:28:40,253 INFO [train.py:812] (1/8) Epoch 12, batch 1150, loss[loss=0.2157, simple_loss=0.2887, pruned_loss=0.07133, over 5159.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2656, pruned_loss=0.04547, over 1420774.51 frames.], batch size: 52, lr: 6.45e-04
+2022-05-14 12:29:38,127 INFO [train.py:812] (1/8) Epoch 12, batch 1200, loss[loss=0.1714, simple_loss=0.2643, pruned_loss=0.03929, over 7115.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2656, pruned_loss=0.04539, over 1423036.38 frames.], batch size: 21, lr: 6.44e-04
+2022-05-14 12:30:37,011 INFO [train.py:812] (1/8) Epoch 12, batch 1250, loss[loss=0.1451, simple_loss=0.2118, pruned_loss=0.03918, over 6984.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2648, pruned_loss=0.04504, over 1424200.10 frames.], batch size: 16, lr: 6.44e-04
+2022-05-14 12:31:36,637 INFO [train.py:812] (1/8) Epoch 12, batch 1300, loss[loss=0.1878, simple_loss=0.2691, pruned_loss=0.05324, over 7330.00 frames.], tot_loss[loss=0.178, simple_loss=0.2654, pruned_loss=0.04532, over 1425867.39 frames.], batch size: 20, lr: 6.44e-04
+2022-05-14 12:32:34,810 INFO [train.py:812] (1/8) Epoch 12, batch 1350, loss[loss=0.18, simple_loss=0.2636, pruned_loss=0.04822, over 7320.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2658, pruned_loss=0.04592, over 1422602.06 frames.], batch size: 21, lr: 6.43e-04
+2022-05-14 12:33:34,084 INFO [train.py:812] (1/8) Epoch 12, batch 1400, loss[loss=0.1636, simple_loss=0.2598, pruned_loss=0.03366, over 7315.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2644, pruned_loss=0.0454, over 1420545.55 frames.], batch size: 21, lr: 6.43e-04
+2022-05-14 12:34:33,346 INFO [train.py:812] (1/8) Epoch 12, batch 1450, loss[loss=0.1402, simple_loss=0.2253, pruned_loss=0.02758, over 7063.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2643, pruned_loss=0.04541, over 1420688.29 frames.], batch size: 18, lr: 6.43e-04
+2022-05-14 12:35:32,027 INFO [train.py:812] (1/8) Epoch 12, batch 1500, loss[loss=0.2047, simple_loss=0.2926, pruned_loss=0.0584, over 7205.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2649, pruned_loss=0.04596, over 1425208.57 frames.], batch size: 23, lr: 6.42e-04
+2022-05-14 12:36:36,803 INFO [train.py:812] (1/8) Epoch 12, batch 1550, loss[loss=0.193, simple_loss=0.2839, pruned_loss=0.05104, over 7229.00 frames.], tot_loss[loss=0.178, simple_loss=0.2642, pruned_loss=0.04587, over 1425288.04 frames.], batch size: 20, lr: 6.42e-04
+2022-05-14 12:37:35,857 INFO [train.py:812] (1/8) Epoch 12, batch 1600, loss[loss=0.1594, simple_loss=0.2438, pruned_loss=0.03755, over 7363.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2652, pruned_loss=0.04604, over 1426077.95 frames.], batch size: 19, lr: 6.42e-04
+2022-05-14 12:38:44,920 INFO [train.py:812] (1/8) Epoch 12, batch 1650, loss[loss=0.1856, simple_loss=0.2776, pruned_loss=0.0468, over 7386.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2656, pruned_loss=0.04644, over 1426130.25 frames.], batch size: 23, lr: 6.42e-04
+2022-05-14 12:39:52,047 INFO [train.py:812] (1/8) Epoch 12, batch 1700, loss[loss=0.1753, simple_loss=0.2666, pruned_loss=0.04198, over 7215.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2663, pruned_loss=0.04658, over 1427575.55 frames.], batch size: 21, lr: 6.41e-04
+2022-05-14 12:40:51,342 INFO [train.py:812] (1/8) Epoch 12, batch 1750, loss[loss=0.1848, simple_loss=0.2634, pruned_loss=0.05315, over 7147.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2662, pruned_loss=0.04619, over 1427606.08 frames.], batch size: 26, lr: 6.41e-04
+2022-05-14 12:41:58,748 INFO [train.py:812] (1/8) Epoch 12, batch 1800, loss[loss=0.1746, simple_loss=0.2467, pruned_loss=0.05123, over 6989.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2658, pruned_loss=0.04638, over 1428640.98 frames.], batch size: 16, lr: 6.41e-04
+2022-05-14 12:43:07,990 INFO [train.py:812] (1/8) Epoch 12, batch 1850, loss[loss=0.1691, simple_loss=0.2608, pruned_loss=0.03864, over 7159.00 frames.], tot_loss[loss=0.1787, simple_loss=0.265, pruned_loss=0.04616, over 1426949.78 frames.], batch size: 26, lr: 6.40e-04
+2022-05-14 12:44:16,800 INFO [train.py:812] (1/8) Epoch 12, batch 1900, loss[loss=0.1634, simple_loss=0.2561, pruned_loss=0.03537, over 7440.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2652, pruned_loss=0.0462, over 1429313.02 frames.], batch size: 20, lr: 6.40e-04
+2022-05-14 12:45:34,899 INFO [train.py:812] (1/8) Epoch 12, batch 1950, loss[loss=0.1483, simple_loss=0.2316, pruned_loss=0.03253, over 7022.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2648, pruned_loss=0.04648, over 1427602.35 frames.], batch size: 16, lr: 6.40e-04
+2022-05-14 12:46:34,655 INFO [train.py:812] (1/8) Epoch 12, batch 2000, loss[loss=0.1646, simple_loss=0.2588, pruned_loss=0.03518, over 6515.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2653, pruned_loss=0.04677, over 1425079.07 frames.], batch size: 37, lr: 6.39e-04
+2022-05-14 12:47:34,771 INFO [train.py:812] (1/8) Epoch 12, batch 2050, loss[loss=0.1959, simple_loss=0.2857, pruned_loss=0.05309, over 7374.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2652, pruned_loss=0.04647, over 1423338.03 frames.], batch size: 23, lr: 6.39e-04
+2022-05-14 12:48:34,242 INFO [train.py:812] (1/8) Epoch 12, batch 2100, loss[loss=0.1948, simple_loss=0.2808, pruned_loss=0.05443, over 6783.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2652, pruned_loss=0.04623, over 1427034.64 frames.], batch size: 31, lr: 6.39e-04
+2022-05-14 12:49:34,270 INFO [train.py:812] (1/8) Epoch 12, batch 2150, loss[loss=0.2151, simple_loss=0.2869, pruned_loss=0.07162, over 7199.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2654, pruned_loss=0.04658, over 1423499.05 frames.], batch size: 16, lr: 6.38e-04
+2022-05-14 12:50:33,516 INFO [train.py:812] (1/8) Epoch 12, batch 2200, loss[loss=0.173, simple_loss=0.2714, pruned_loss=0.0373, over 7413.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2648, pruned_loss=0.04588, over 1427356.78 frames.], batch size: 20, lr: 6.38e-04
+2022-05-14 12:51:31,636 INFO [train.py:812] (1/8) Epoch 12, batch 2250, loss[loss=0.1907, simple_loss=0.2717, pruned_loss=0.05484, over 7150.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2647, pruned_loss=0.04608, over 1426628.88 frames.], batch size: 17, lr: 6.38e-04
+2022-05-14 12:52:29,470 INFO [train.py:812] (1/8) Epoch 12, batch 2300, loss[loss=0.1733, simple_loss=0.2614, pruned_loss=0.04259, over 7369.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2655, pruned_loss=0.0462, over 1424650.35 frames.], batch size: 19, lr: 6.38e-04
+2022-05-14 12:53:28,555 INFO [train.py:812] (1/8) Epoch 12, batch 2350, loss[loss=0.1886, simple_loss=0.2797, pruned_loss=0.04874, over 7311.00 frames.], tot_loss[loss=0.1773, simple_loss=0.264, pruned_loss=0.04533, over 1425682.03 frames.], batch size: 24, lr: 6.37e-04
+2022-05-14 12:54:27,659 INFO [train.py:812] (1/8) Epoch 12, batch 2400, loss[loss=0.1689, simple_loss=0.2633, pruned_loss=0.03731, over 7110.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2647, pruned_loss=0.04549, over 1428005.57 frames.], batch size: 21, lr: 6.37e-04
+2022-05-14 12:55:26,374 INFO [train.py:812] (1/8) Epoch 12, batch 2450, loss[loss=0.2152, simple_loss=0.2977, pruned_loss=0.06631, over 7241.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2643, pruned_loss=0.04525, over 1425589.99 frames.], batch size: 20, lr: 6.37e-04
+2022-05-14 12:56:25,359 INFO [train.py:812] (1/8) Epoch 12, batch 2500, loss[loss=0.1646, simple_loss=0.2456, pruned_loss=0.0418, over 7077.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2636, pruned_loss=0.0451, over 1424637.72 frames.], batch size: 18, lr: 6.36e-04
+2022-05-14 12:57:24,975 INFO [train.py:812] (1/8) Epoch 12, batch 2550, loss[loss=0.1591, simple_loss=0.2432, pruned_loss=0.03748, over 7277.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2647, pruned_loss=0.04519, over 1428116.92 frames.], batch size: 17, lr: 6.36e-04
+2022-05-14 12:58:23,571 INFO [train.py:812] (1/8) Epoch 12, batch 2600, loss[loss=0.1858, simple_loss=0.2777, pruned_loss=0.04697, over 7277.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2641, pruned_loss=0.04485, over 1422581.25 frames.], batch size: 24, lr: 6.36e-04
+2022-05-14 12:59:22,469 INFO [train.py:812] (1/8) Epoch 12, batch 2650, loss[loss=0.1605, simple_loss=0.2564, pruned_loss=0.03223, over 7260.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2642, pruned_loss=0.04502, over 1419497.50 frames.], batch size: 19, lr: 6.36e-04
+2022-05-14 13:00:21,650 INFO [train.py:812] (1/8) Epoch 12, batch 2700, loss[loss=0.2279, simple_loss=0.3203, pruned_loss=0.06779, over 7302.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2642, pruned_loss=0.04498, over 1423227.15 frames.], batch size: 25, lr: 6.35e-04
+2022-05-14 13:01:21,318 INFO [train.py:812] (1/8) Epoch 12, batch 2750, loss[loss=0.1683, simple_loss=0.2546, pruned_loss=0.04105, over 7430.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2641, pruned_loss=0.04512, over 1426173.84 frames.], batch size: 20, lr: 6.35e-04
+2022-05-14 13:02:20,424 INFO [train.py:812] (1/8) Epoch 12, batch 2800, loss[loss=0.2117, simple_loss=0.2959, pruned_loss=0.06376, over 7115.00 frames.], tot_loss[loss=0.1771, simple_loss=0.264, pruned_loss=0.0451, over 1427193.57 frames.], batch size: 21, lr: 6.35e-04
+2022-05-14 13:03:19,809 INFO [train.py:812] (1/8) Epoch 12, batch 2850, loss[loss=0.1749, simple_loss=0.2713, pruned_loss=0.03922, over 7330.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2638, pruned_loss=0.0452, over 1429684.19 frames.], batch size: 21, lr: 6.34e-04
+2022-05-14 13:04:18,948 INFO [train.py:812] (1/8) Epoch 12, batch 2900, loss[loss=0.1935, simple_loss=0.2914, pruned_loss=0.04782, over 7281.00 frames.], tot_loss[loss=0.1784, simple_loss=0.265, pruned_loss=0.04588, over 1425400.80 frames.], batch size: 24, lr: 6.34e-04
+2022-05-14 13:05:18,612 INFO [train.py:812] (1/8) Epoch 12, batch 2950, loss[loss=0.176, simple_loss=0.2673, pruned_loss=0.04239, over 7233.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2644, pruned_loss=0.04565, over 1421257.13 frames.], batch size: 21, lr: 6.34e-04
+2022-05-14 13:06:17,602 INFO [train.py:812] (1/8) Epoch 12, batch 3000, loss[loss=0.2026, simple_loss=0.2925, pruned_loss=0.05638, over 7306.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2641, pruned_loss=0.04548, over 1422455.73 frames.], batch size: 25, lr: 6.33e-04
+2022-05-14 13:06:17,603 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 13:06:26,032 INFO [train.py:841] (1/8) Epoch 12, validation: loss=0.1553, simple_loss=0.2571, pruned_loss=0.02678, over 698248.00 frames.
+2022-05-14 13:07:25,170 INFO [train.py:812] (1/8) Epoch 12, batch 3050, loss[loss=0.1858, simple_loss=0.2872, pruned_loss=0.04215, over 7388.00 frames.], tot_loss[loss=0.178, simple_loss=0.2651, pruned_loss=0.04546, over 1420503.82 frames.], batch size: 23, lr: 6.33e-04
+2022-05-14 13:08:24,601 INFO [train.py:812] (1/8) Epoch 12, batch 3100, loss[loss=0.1618, simple_loss=0.2505, pruned_loss=0.03658, over 7325.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2635, pruned_loss=0.04475, over 1421853.48 frames.], batch size: 20, lr: 6.33e-04
+2022-05-14 13:09:23,905 INFO [train.py:812] (1/8) Epoch 12, batch 3150, loss[loss=0.1769, simple_loss=0.2634, pruned_loss=0.04518, over 7365.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2639, pruned_loss=0.04512, over 1424261.34 frames.], batch size: 23, lr: 6.33e-04
+2022-05-14 13:10:22,791 INFO [train.py:812] (1/8) Epoch 12, batch 3200, loss[loss=0.1852, simple_loss=0.2631, pruned_loss=0.05367, over 7126.00 frames.], tot_loss[loss=0.1771, simple_loss=0.264, pruned_loss=0.0451, over 1423498.16 frames.], batch size: 21, lr: 6.32e-04
+2022-05-14 13:11:22,008 INFO [train.py:812] (1/8) Epoch 12, batch 3250, loss[loss=0.1774, simple_loss=0.2677, pruned_loss=0.04358, over 7425.00 frames.], tot_loss[loss=0.1772, simple_loss=0.264, pruned_loss=0.04518, over 1424981.01 frames.], batch size: 21, lr: 6.32e-04
+2022-05-14 13:12:21,138 INFO [train.py:812] (1/8) Epoch 12, batch 3300, loss[loss=0.1505, simple_loss=0.2378, pruned_loss=0.03162, over 7427.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2653, pruned_loss=0.04564, over 1425640.59 frames.], batch size: 17, lr: 6.32e-04
+2022-05-14 13:13:18,550 INFO [train.py:812] (1/8) Epoch 12, batch 3350, loss[loss=0.1746, simple_loss=0.2567, pruned_loss=0.04621, over 7269.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2658, pruned_loss=0.04564, over 1426459.41 frames.], batch size: 18, lr: 6.31e-04
+2022-05-14 13:14:17,030 INFO [train.py:812] (1/8) Epoch 12, batch 3400, loss[loss=0.1919, simple_loss=0.2846, pruned_loss=0.04965, over 6116.00 frames.], tot_loss[loss=0.1796, simple_loss=0.267, pruned_loss=0.04612, over 1420636.65 frames.], batch size: 37, lr: 6.31e-04
+2022-05-14 13:15:16,592 INFO [train.py:812] (1/8) Epoch 12, batch 3450, loss[loss=0.1718, simple_loss=0.2619, pruned_loss=0.04082, over 7115.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2657, pruned_loss=0.04571, over 1417630.30 frames.], batch size: 21, lr: 6.31e-04
+2022-05-14 13:16:15,022 INFO [train.py:812] (1/8) Epoch 12, batch 3500, loss[loss=0.1736, simple_loss=0.2662, pruned_loss=0.04052, over 7324.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2659, pruned_loss=0.04547, over 1423515.40 frames.], batch size: 21, lr: 6.31e-04
+2022-05-14 13:17:13,774 INFO [train.py:812] (1/8) Epoch 12, batch 3550, loss[loss=0.1539, simple_loss=0.2344, pruned_loss=0.03669, over 6995.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2656, pruned_loss=0.04569, over 1421981.27 frames.], batch size: 16, lr: 6.30e-04
+2022-05-14 13:18:12,625 INFO [train.py:812] (1/8) Epoch 12, batch 3600, loss[loss=0.1681, simple_loss=0.2649, pruned_loss=0.03565, over 7232.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2659, pruned_loss=0.04528, over 1424102.40 frames.], batch size: 20, lr: 6.30e-04
+2022-05-14 13:19:11,476 INFO [train.py:812] (1/8) Epoch 12, batch 3650, loss[loss=0.1748, simple_loss=0.2638, pruned_loss=0.04285, over 7440.00 frames.], tot_loss[loss=0.1774, simple_loss=0.265, pruned_loss=0.04487, over 1423821.55 frames.], batch size: 20, lr: 6.30e-04
+2022-05-14 13:20:08,354 INFO [train.py:812] (1/8) Epoch 12, batch 3700, loss[loss=0.1863, simple_loss=0.2734, pruned_loss=0.04961, over 6751.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2649, pruned_loss=0.04499, over 1420371.23 frames.], batch size: 31, lr: 6.29e-04
+2022-05-14 13:21:06,286 INFO [train.py:812] (1/8) Epoch 12, batch 3750, loss[loss=0.1736, simple_loss=0.2705, pruned_loss=0.03839, over 7377.00 frames.], tot_loss[loss=0.1753, simple_loss=0.263, pruned_loss=0.04378, over 1425100.97 frames.], batch size: 23, lr: 6.29e-04
+2022-05-14 13:22:05,720 INFO [train.py:812] (1/8) Epoch 12, batch 3800, loss[loss=0.1763, simple_loss=0.2631, pruned_loss=0.04476, over 7176.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2623, pruned_loss=0.04335, over 1427730.23 frames.], batch size: 26, lr: 6.29e-04
+2022-05-14 13:23:04,542 INFO [train.py:812] (1/8) Epoch 12, batch 3850, loss[loss=0.1569, simple_loss=0.2566, pruned_loss=0.02858, over 7122.00 frames.], tot_loss[loss=0.175, simple_loss=0.2626, pruned_loss=0.04373, over 1428400.61 frames.], batch size: 21, lr: 6.29e-04
+2022-05-14 13:24:03,542 INFO [train.py:812] (1/8) Epoch 12, batch 3900, loss[loss=0.1975, simple_loss=0.2838, pruned_loss=0.05562, over 7432.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2638, pruned_loss=0.04462, over 1428919.50 frames.], batch size: 20, lr: 6.28e-04
+2022-05-14 13:25:02,796 INFO [train.py:812] (1/8) Epoch 12, batch 3950, loss[loss=0.1927, simple_loss=0.2801, pruned_loss=0.05265, over 7236.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2639, pruned_loss=0.04512, over 1430476.94 frames.], batch size: 20, lr: 6.28e-04
+2022-05-14 13:26:01,746 INFO [train.py:812] (1/8) Epoch 12, batch 4000, loss[loss=0.1846, simple_loss=0.2688, pruned_loss=0.05023, over 7410.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2642, pruned_loss=0.0453, over 1425631.43 frames.], batch size: 21, lr: 6.28e-04
+2022-05-14 13:27:01,235 INFO [train.py:812] (1/8) Epoch 12, batch 4050, loss[loss=0.1942, simple_loss=0.2833, pruned_loss=0.05257, over 7432.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2641, pruned_loss=0.04535, over 1424863.62 frames.], batch size: 20, lr: 6.27e-04
+2022-05-14 13:28:00,391 INFO [train.py:812] (1/8) Epoch 12, batch 4100, loss[loss=0.1615, simple_loss=0.2615, pruned_loss=0.0307, over 7316.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2641, pruned_loss=0.04528, over 1421057.44 frames.], batch size: 20, lr: 6.27e-04
+2022-05-14 13:28:59,925 INFO [train.py:812] (1/8) Epoch 12, batch 4150, loss[loss=0.1563, simple_loss=0.2483, pruned_loss=0.03213, over 7239.00 frames.], tot_loss[loss=0.178, simple_loss=0.2649, pruned_loss=0.04555, over 1421272.56 frames.], batch size: 20, lr: 6.27e-04
+2022-05-14 13:29:59,286 INFO [train.py:812] (1/8) Epoch 12, batch 4200, loss[loss=0.1779, simple_loss=0.2729, pruned_loss=0.04149, over 7348.00 frames.], tot_loss[loss=0.1781, simple_loss=0.265, pruned_loss=0.04563, over 1421530.39 frames.], batch size: 22, lr: 6.27e-04
+2022-05-14 13:30:59,178 INFO [train.py:812] (1/8) Epoch 12, batch 4250, loss[loss=0.1665, simple_loss=0.2455, pruned_loss=0.04377, over 7406.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2636, pruned_loss=0.04505, over 1424320.96 frames.], batch size: 18, lr: 6.26e-04
+2022-05-14 13:31:58,490 INFO [train.py:812] (1/8) Epoch 12, batch 4300, loss[loss=0.1521, simple_loss=0.249, pruned_loss=0.02763, over 7229.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2634, pruned_loss=0.04485, over 1417706.05 frames.], batch size: 20, lr: 6.26e-04
+2022-05-14 13:32:57,465 INFO [train.py:812] (1/8) Epoch 12, batch 4350, loss[loss=0.1932, simple_loss=0.2834, pruned_loss=0.05157, over 7200.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2622, pruned_loss=0.04457, over 1419421.89 frames.], batch size: 22, lr: 6.26e-04
+2022-05-14 13:33:56,595 INFO [train.py:812] (1/8) Epoch 12, batch 4400, loss[loss=0.1765, simple_loss=0.2793, pruned_loss=0.03688, over 7318.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2619, pruned_loss=0.04425, over 1418015.13 frames.], batch size: 21, lr: 6.25e-04
+2022-05-14 13:34:56,717 INFO [train.py:812] (1/8) Epoch 12, batch 4450, loss[loss=0.2022, simple_loss=0.2901, pruned_loss=0.05713, over 6289.00 frames.], tot_loss[loss=0.175, simple_loss=0.2611, pruned_loss=0.04451, over 1406398.49 frames.], batch size: 38, lr: 6.25e-04
+2022-05-14 13:35:55,753 INFO [train.py:812] (1/8) Epoch 12, batch 4500, loss[loss=0.181, simple_loss=0.2669, pruned_loss=0.04762, over 6607.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2608, pruned_loss=0.0449, over 1391609.31 frames.], batch size: 40, lr: 6.25e-04
+2022-05-14 13:36:54,585 INFO [train.py:812] (1/8) Epoch 12, batch 4550, loss[loss=0.208, simple_loss=0.2811, pruned_loss=0.06751, over 5151.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2631, pruned_loss=0.04673, over 1352570.04 frames.], batch size: 52, lr: 6.25e-04
+2022-05-14 13:38:08,552 INFO [train.py:812] (1/8) Epoch 13, batch 0, loss[loss=0.1668, simple_loss=0.255, pruned_loss=0.03936, over 7150.00 frames.], tot_loss[loss=0.1668, simple_loss=0.255, pruned_loss=0.03936, over 7150.00 frames.], batch size: 20, lr: 6.03e-04
+2022-05-14 13:39:08,083 INFO [train.py:812] (1/8) Epoch 13, batch 50, loss[loss=0.1668, simple_loss=0.264, pruned_loss=0.03478, over 7239.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2666, pruned_loss=0.04598, over 318314.23 frames.], batch size: 20, lr: 6.03e-04
+2022-05-14 13:40:06,196 INFO [train.py:812] (1/8) Epoch 13, batch 100, loss[loss=0.2115, simple_loss=0.2973, pruned_loss=0.06284, over 7199.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2668, pruned_loss=0.04598, over 564411.77 frames.], batch size: 23, lr: 6.03e-04
+2022-05-14 13:41:05,024 INFO [train.py:812] (1/8) Epoch 13, batch 150, loss[loss=0.1729, simple_loss=0.2583, pruned_loss=0.0438, over 7152.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2673, pruned_loss=0.04599, over 753711.34 frames.], batch size: 20, lr: 6.03e-04
+2022-05-14 13:42:04,237 INFO [train.py:812] (1/8) Epoch 13, batch 200, loss[loss=0.19, simple_loss=0.2777, pruned_loss=0.05116, over 7148.00 frames.], tot_loss[loss=0.179, simple_loss=0.2666, pruned_loss=0.04572, over 899927.84 frames.], batch size: 20, lr: 6.02e-04
+2022-05-14 13:43:03,745 INFO [train.py:812] (1/8) Epoch 13, batch 250, loss[loss=0.1827, simple_loss=0.261, pruned_loss=0.05223, over 6795.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2667, pruned_loss=0.04592, over 1013477.28 frames.], batch size: 15, lr: 6.02e-04
+2022-05-14 13:44:02,525 INFO [train.py:812] (1/8) Epoch 13, batch 300, loss[loss=0.1757, simple_loss=0.2629, pruned_loss=0.04422, over 7145.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2647, pruned_loss=0.04503, over 1104949.59 frames.], batch size: 20, lr: 6.02e-04
+2022-05-14 13:45:01,889 INFO [train.py:812] (1/8) Epoch 13, batch 350, loss[loss=0.1661, simple_loss=0.2703, pruned_loss=0.03095, over 7073.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2649, pruned_loss=0.04446, over 1177382.83 frames.], batch size: 28, lr: 6.01e-04
+2022-05-14 13:46:00,670 INFO [train.py:812] (1/8) Epoch 13, batch 400, loss[loss=0.1641, simple_loss=0.2466, pruned_loss=0.0408, over 7356.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2641, pruned_loss=0.04428, over 1234809.52 frames.], batch size: 19, lr: 6.01e-04
+2022-05-14 13:46:57,910 INFO [train.py:812] (1/8) Epoch 13, batch 450, loss[loss=0.1718, simple_loss=0.2682, pruned_loss=0.03771, over 7317.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2633, pruned_loss=0.04394, over 1278368.55 frames.], batch size: 21, lr: 6.01e-04
+2022-05-14 13:47:55,562 INFO [train.py:812] (1/8) Epoch 13, batch 500, loss[loss=0.1633, simple_loss=0.2531, pruned_loss=0.0367, over 6306.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2611, pruned_loss=0.04331, over 1312039.92 frames.], batch size: 37, lr: 6.01e-04
+2022-05-14 13:48:55,158 INFO [train.py:812] (1/8) Epoch 13, batch 550, loss[loss=0.1925, simple_loss=0.2797, pruned_loss=0.05259, over 7399.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2611, pruned_loss=0.04356, over 1334061.64 frames.], batch size: 23, lr: 6.00e-04
+2022-05-14 13:49:53,967 INFO [train.py:812] (1/8) Epoch 13, batch 600, loss[loss=0.151, simple_loss=0.2286, pruned_loss=0.03673, over 6794.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2602, pruned_loss=0.04349, over 1347339.95 frames.], batch size: 15, lr: 6.00e-04
+2022-05-14 13:50:53,009 INFO [train.py:812] (1/8) Epoch 13, batch 650, loss[loss=0.1701, simple_loss=0.2676, pruned_loss=0.03627, over 7300.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2613, pruned_loss=0.04376, over 1366539.52 frames.], batch size: 18, lr: 6.00e-04
+2022-05-14 13:51:52,323 INFO [train.py:812] (1/8) Epoch 13, batch 700, loss[loss=0.1461, simple_loss=0.2109, pruned_loss=0.04063, over 6804.00 frames.], tot_loss[loss=0.175, simple_loss=0.2623, pruned_loss=0.04384, over 1383926.89 frames.], batch size: 15, lr: 6.00e-04
+2022-05-14 13:52:51,779 INFO [train.py:812] (1/8) Epoch 13, batch 750, loss[loss=0.1957, simple_loss=0.2855, pruned_loss=0.05294, over 7215.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2629, pruned_loss=0.04363, over 1395823.68 frames.], batch size: 23, lr: 5.99e-04
+2022-05-14 13:53:50,408 INFO [train.py:812] (1/8) Epoch 13, batch 800, loss[loss=0.2003, simple_loss=0.2862, pruned_loss=0.05717, over 7215.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2627, pruned_loss=0.04348, over 1405709.60 frames.], batch size: 22, lr: 5.99e-04
+2022-05-14 13:54:49,216 INFO [train.py:812] (1/8) Epoch 13, batch 850, loss[loss=0.1542, simple_loss=0.2338, pruned_loss=0.03727, over 7141.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2638, pruned_loss=0.04388, over 1411306.60 frames.], batch size: 17, lr: 5.99e-04
+2022-05-14 13:55:48,209 INFO [train.py:812] (1/8) Epoch 13, batch 900, loss[loss=0.175, simple_loss=0.263, pruned_loss=0.0435, over 7313.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2626, pruned_loss=0.04319, over 1413766.04 frames.], batch size: 20, lr: 5.99e-04
+2022-05-14 13:56:53,003 INFO [train.py:812] (1/8) Epoch 13, batch 950, loss[loss=0.2, simple_loss=0.289, pruned_loss=0.05549, over 7180.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2634, pruned_loss=0.04358, over 1414789.78 frames.], batch size: 26, lr: 5.98e-04
+2022-05-14 13:57:52,236 INFO [train.py:812] (1/8) Epoch 13, batch 1000, loss[loss=0.1587, simple_loss=0.2443, pruned_loss=0.03653, over 6428.00 frames.], tot_loss[loss=0.1761, simple_loss=0.264, pruned_loss=0.04412, over 1415985.88 frames.], batch size: 38, lr: 5.98e-04
+2022-05-14 13:58:51,876 INFO [train.py:812] (1/8) Epoch 13, batch 1050, loss[loss=0.1656, simple_loss=0.2566, pruned_loss=0.03734, over 7249.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2641, pruned_loss=0.04442, over 1417473.06 frames.], batch size: 19, lr: 5.98e-04
+2022-05-14 13:59:49,633 INFO [train.py:812] (1/8) Epoch 13, batch 1100, loss[loss=0.1756, simple_loss=0.2636, pruned_loss=0.04375, over 7384.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2635, pruned_loss=0.04408, over 1423427.81 frames.], batch size: 23, lr: 5.97e-04
+2022-05-14 14:00:49,265 INFO [train.py:812] (1/8) Epoch 13, batch 1150, loss[loss=0.163, simple_loss=0.251, pruned_loss=0.03752, over 7331.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2627, pruned_loss=0.04372, over 1425650.12 frames.], batch size: 20, lr: 5.97e-04
+2022-05-14 14:01:48,650 INFO [train.py:812] (1/8) Epoch 13, batch 1200, loss[loss=0.219, simple_loss=0.3013, pruned_loss=0.0683, over 4832.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2631, pruned_loss=0.04382, over 1421742.91 frames.], batch size: 53, lr: 5.97e-04
+2022-05-14 14:02:48,264 INFO [train.py:812] (1/8) Epoch 13, batch 1250, loss[loss=0.1835, simple_loss=0.2681, pruned_loss=0.0494, over 7155.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2636, pruned_loss=0.04436, over 1419041.65 frames.], batch size: 19, lr: 5.97e-04
+2022-05-14 14:03:47,347 INFO [train.py:812] (1/8) Epoch 13, batch 1300, loss[loss=0.1621, simple_loss=0.2464, pruned_loss=0.03889, over 7056.00 frames.], tot_loss[loss=0.175, simple_loss=0.2621, pruned_loss=0.04393, over 1419974.71 frames.], batch size: 18, lr: 5.96e-04
+2022-05-14 14:04:46,582 INFO [train.py:812] (1/8) Epoch 13, batch 1350, loss[loss=0.2188, simple_loss=0.2941, pruned_loss=0.07177, over 5423.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2638, pruned_loss=0.0446, over 1418112.97 frames.], batch size: 53, lr: 5.96e-04
+2022-05-14 14:05:45,498 INFO [train.py:812] (1/8) Epoch 13, batch 1400, loss[loss=0.1875, simple_loss=0.2781, pruned_loss=0.04844, over 7286.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2642, pruned_loss=0.04475, over 1417997.67 frames.], batch size: 25, lr: 5.96e-04
+2022-05-14 14:06:43,979 INFO [train.py:812] (1/8) Epoch 13, batch 1450, loss[loss=0.1924, simple_loss=0.2844, pruned_loss=0.05026, over 7322.00 frames.], tot_loss[loss=0.1763, simple_loss=0.264, pruned_loss=0.04433, over 1415650.33 frames.], batch size: 21, lr: 5.96e-04
+2022-05-14 14:07:42,551 INFO [train.py:812] (1/8) Epoch 13, batch 1500, loss[loss=0.1836, simple_loss=0.2741, pruned_loss=0.04653, over 7191.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2639, pruned_loss=0.04432, over 1418706.41 frames.], batch size: 23, lr: 5.95e-04
+2022-05-14 14:08:42,625 INFO [train.py:812] (1/8) Epoch 13, batch 1550, loss[loss=0.214, simple_loss=0.3143, pruned_loss=0.05687, over 7039.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2635, pruned_loss=0.04389, over 1420175.96 frames.], batch size: 28, lr: 5.95e-04
+2022-05-14 14:09:41,283 INFO [train.py:812] (1/8) Epoch 13, batch 1600, loss[loss=0.1805, simple_loss=0.2683, pruned_loss=0.04632, over 7307.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2638, pruned_loss=0.04439, over 1419227.20 frames.], batch size: 25, lr: 5.95e-04
+2022-05-14 14:10:39,363 INFO [train.py:812] (1/8) Epoch 13, batch 1650, loss[loss=0.1882, simple_loss=0.2725, pruned_loss=0.05188, over 7300.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2636, pruned_loss=0.04448, over 1422288.16 frames.], batch size: 24, lr: 5.95e-04
+2022-05-14 14:11:36,469 INFO [train.py:812] (1/8) Epoch 13, batch 1700, loss[loss=0.1706, simple_loss=0.2603, pruned_loss=0.04044, over 7127.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2626, pruned_loss=0.04386, over 1417808.08 frames.], batch size: 17, lr: 5.94e-04
+2022-05-14 14:12:34,781 INFO [train.py:812] (1/8) Epoch 13, batch 1750, loss[loss=0.1922, simple_loss=0.2932, pruned_loss=0.04563, over 7188.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2621, pruned_loss=0.04378, over 1421706.41 frames.], batch size: 26, lr: 5.94e-04
+2022-05-14 14:13:34,202 INFO [train.py:812] (1/8) Epoch 13, batch 1800, loss[loss=0.1621, simple_loss=0.2392, pruned_loss=0.04252, over 7003.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2625, pruned_loss=0.04405, over 1427017.44 frames.], batch size: 16, lr: 5.94e-04
+2022-05-14 14:14:33,817 INFO [train.py:812] (1/8) Epoch 13, batch 1850, loss[loss=0.199, simple_loss=0.2864, pruned_loss=0.05584, over 7324.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2617, pruned_loss=0.04358, over 1427586.10 frames.], batch size: 22, lr: 5.94e-04
+2022-05-14 14:15:33,210 INFO [train.py:812] (1/8) Epoch 13, batch 1900, loss[loss=0.1707, simple_loss=0.2528, pruned_loss=0.04428, over 7229.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2617, pruned_loss=0.04327, over 1428447.98 frames.], batch size: 20, lr: 5.93e-04
+2022-05-14 14:16:32,244 INFO [train.py:812] (1/8) Epoch 13, batch 1950, loss[loss=0.1448, simple_loss=0.2263, pruned_loss=0.0317, over 7281.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2614, pruned_loss=0.04311, over 1428493.09 frames.], batch size: 17, lr: 5.93e-04
+2022-05-14 14:17:31,539 INFO [train.py:812] (1/8) Epoch 13, batch 2000, loss[loss=0.1538, simple_loss=0.2327, pruned_loss=0.03747, over 7009.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2604, pruned_loss=0.0429, over 1428740.54 frames.], batch size: 16, lr: 5.93e-04
+2022-05-14 14:18:40,078 INFO [train.py:812] (1/8) Epoch 13, batch 2050, loss[loss=0.1671, simple_loss=0.2537, pruned_loss=0.04025, over 7158.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2597, pruned_loss=0.04296, over 1422597.54 frames.], batch size: 19, lr: 5.93e-04
+2022-05-14 14:19:39,662 INFO [train.py:812] (1/8) Epoch 13, batch 2100, loss[loss=0.1502, simple_loss=0.2438, pruned_loss=0.02832, over 7154.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2607, pruned_loss=0.04354, over 1423116.05 frames.], batch size: 19, lr: 5.92e-04
+2022-05-14 14:20:39,440 INFO [train.py:812] (1/8) Epoch 13, batch 2150, loss[loss=0.1498, simple_loss=0.2286, pruned_loss=0.0355, over 7269.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2613, pruned_loss=0.04327, over 1422501.53 frames.], batch size: 18, lr: 5.92e-04
+2022-05-14 14:21:36,889 INFO [train.py:812] (1/8) Epoch 13, batch 2200, loss[loss=0.1518, simple_loss=0.2487, pruned_loss=0.02744, over 7327.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2605, pruned_loss=0.04283, over 1422917.39 frames.], batch size: 20, lr: 5.92e-04
+2022-05-14 14:22:35,531 INFO [train.py:812] (1/8) Epoch 13, batch 2250, loss[loss=0.1559, simple_loss=0.2463, pruned_loss=0.03274, over 7079.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2608, pruned_loss=0.04276, over 1421676.31 frames.], batch size: 28, lr: 5.91e-04
+2022-05-14 14:23:34,267 INFO [train.py:812] (1/8) Epoch 13, batch 2300, loss[loss=0.176, simple_loss=0.2672, pruned_loss=0.04245, over 7114.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2608, pruned_loss=0.04282, over 1425552.91 frames.], batch size: 21, lr: 5.91e-04
+2022-05-14 14:24:34,069 INFO [train.py:812] (1/8) Epoch 13, batch 2350, loss[loss=0.1827, simple_loss=0.2746, pruned_loss=0.04541, over 7157.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2615, pruned_loss=0.04315, over 1427038.68 frames.], batch size: 19, lr: 5.91e-04
+2022-05-14 14:25:33,549 INFO [train.py:812] (1/8) Epoch 13, batch 2400, loss[loss=0.1586, simple_loss=0.231, pruned_loss=0.0431, over 7142.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2621, pruned_loss=0.04321, over 1426929.48 frames.], batch size: 17, lr: 5.91e-04
+2022-05-14 14:26:31,978 INFO [train.py:812] (1/8) Epoch 13, batch 2450, loss[loss=0.1789, simple_loss=0.2672, pruned_loss=0.04525, over 7217.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2623, pruned_loss=0.0432, over 1426207.28 frames.], batch size: 21, lr: 5.90e-04
+2022-05-14 14:27:30,758 INFO [train.py:812] (1/8) Epoch 13, batch 2500, loss[loss=0.1786, simple_loss=0.2587, pruned_loss=0.0492, over 7282.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2628, pruned_loss=0.04321, over 1427394.55 frames.], batch size: 18, lr: 5.90e-04
+2022-05-14 14:28:30,429 INFO [train.py:812] (1/8) Epoch 13, batch 2550, loss[loss=0.1943, simple_loss=0.2641, pruned_loss=0.0623, over 7244.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2635, pruned_loss=0.04385, over 1428810.70 frames.], batch size: 16, lr: 5.90e-04
+2022-05-14 14:29:29,637 INFO [train.py:812] (1/8) Epoch 13, batch 2600, loss[loss=0.1598, simple_loss=0.246, pruned_loss=0.03684, over 7226.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2629, pruned_loss=0.04388, over 1424650.28 frames.], batch size: 16, lr: 5.90e-04
+2022-05-14 14:30:29,024 INFO [train.py:812] (1/8) Epoch 13, batch 2650, loss[loss=0.1731, simple_loss=0.2443, pruned_loss=0.05097, over 7010.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2638, pruned_loss=0.0442, over 1422755.25 frames.], batch size: 16, lr: 5.89e-04
+2022-05-14 14:31:27,711 INFO [train.py:812] (1/8) Epoch 13, batch 2700, loss[loss=0.164, simple_loss=0.2451, pruned_loss=0.04149, over 7012.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2627, pruned_loss=0.04388, over 1423747.21 frames.], batch size: 16, lr: 5.89e-04
+2022-05-14 14:32:27,069 INFO [train.py:812] (1/8) Epoch 13, batch 2750, loss[loss=0.1896, simple_loss=0.2812, pruned_loss=0.04903, over 7110.00 frames.], tot_loss[loss=0.175, simple_loss=0.2625, pruned_loss=0.04372, over 1420906.27 frames.], batch size: 21, lr: 5.89e-04
+2022-05-14 14:33:24,884 INFO [train.py:812] (1/8) Epoch 13, batch 2800, loss[loss=0.1632, simple_loss=0.2428, pruned_loss=0.04186, over 7134.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2629, pruned_loss=0.04378, over 1420431.87 frames.], batch size: 17, lr: 5.89e-04
+2022-05-14 14:34:24,905 INFO [train.py:812] (1/8) Epoch 13, batch 2850, loss[loss=0.1652, simple_loss=0.2514, pruned_loss=0.03956, over 7374.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2627, pruned_loss=0.04371, over 1426711.71 frames.], batch size: 23, lr: 5.88e-04
+2022-05-14 14:35:22,592 INFO [train.py:812] (1/8) Epoch 13, batch 2900, loss[loss=0.1566, simple_loss=0.2503, pruned_loss=0.03146, over 7347.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2636, pruned_loss=0.0438, over 1424695.34 frames.], batch size: 19, lr: 5.88e-04
+2022-05-14 14:36:21,968 INFO [train.py:812] (1/8) Epoch 13, batch 2950, loss[loss=0.1483, simple_loss=0.2391, pruned_loss=0.02877, over 7114.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2626, pruned_loss=0.0436, over 1427165.17 frames.], batch size: 21, lr: 5.88e-04
+2022-05-14 14:37:20,741 INFO [train.py:812] (1/8) Epoch 13, batch 3000, loss[loss=0.1434, simple_loss=0.2171, pruned_loss=0.03483, over 7298.00 frames.], tot_loss[loss=0.1747, simple_loss=0.263, pruned_loss=0.04324, over 1428188.10 frames.], batch size: 17, lr: 5.88e-04
+2022-05-14 14:37:20,742 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 14:37:28,227 INFO [train.py:841] (1/8) Epoch 13, validation: loss=0.1549, simple_loss=0.2559, pruned_loss=0.02694, over 698248.00 frames.
+2022-05-14 14:38:28,323 INFO [train.py:812] (1/8) Epoch 13, batch 3050, loss[loss=0.1444, simple_loss=0.2278, pruned_loss=0.03048, over 7120.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2625, pruned_loss=0.04327, over 1429330.83 frames.], batch size: 17, lr: 5.87e-04
+2022-05-14 14:39:27,853 INFO [train.py:812] (1/8) Epoch 13, batch 3100, loss[loss=0.1632, simple_loss=0.2602, pruned_loss=0.03308, over 7123.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2616, pruned_loss=0.04289, over 1427924.96 frames.], batch size: 21, lr: 5.87e-04
+2022-05-14 14:40:36,457 INFO [train.py:812] (1/8) Epoch 13, batch 3150, loss[loss=0.1825, simple_loss=0.2703, pruned_loss=0.04737, over 7326.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2632, pruned_loss=0.04373, over 1424719.48 frames.], batch size: 25, lr: 5.87e-04
+2022-05-14 14:41:35,460 INFO [train.py:812] (1/8) Epoch 13, batch 3200, loss[loss=0.2222, simple_loss=0.2946, pruned_loss=0.07493, over 5120.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2635, pruned_loss=0.04387, over 1425879.45 frames.], batch size: 52, lr: 5.87e-04
+2022-05-14 14:42:44,504 INFO [train.py:812] (1/8) Epoch 13, batch 3250, loss[loss=0.1497, simple_loss=0.2338, pruned_loss=0.03281, over 7312.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2635, pruned_loss=0.04378, over 1428254.42 frames.], batch size: 17, lr: 5.86e-04
+2022-05-14 14:43:53,098 INFO [train.py:812] (1/8) Epoch 13, batch 3300, loss[loss=0.1694, simple_loss=0.2558, pruned_loss=0.04144, over 7323.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2628, pruned_loss=0.04347, over 1428753.65 frames.], batch size: 20, lr: 5.86e-04
+2022-05-14 14:44:51,605 INFO [train.py:812] (1/8) Epoch 13, batch 3350, loss[loss=0.1717, simple_loss=0.2594, pruned_loss=0.04198, over 6989.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2628, pruned_loss=0.04333, over 1421896.29 frames.], batch size: 16, lr: 5.86e-04
+2022-05-14 14:46:18,928 INFO [train.py:812] (1/8) Epoch 13, batch 3400, loss[loss=0.1788, simple_loss=0.2751, pruned_loss=0.04123, over 7376.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2631, pruned_loss=0.04349, over 1425005.25 frames.], batch size: 23, lr: 5.86e-04
+2022-05-14 14:47:27,728 INFO [train.py:812] (1/8) Epoch 13, batch 3450, loss[loss=0.1465, simple_loss=0.2255, pruned_loss=0.03369, over 7418.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2633, pruned_loss=0.04413, over 1414560.11 frames.], batch size: 18, lr: 5.85e-04
+2022-05-14 14:48:26,507 INFO [train.py:812] (1/8) Epoch 13, batch 3500, loss[loss=0.1963, simple_loss=0.2893, pruned_loss=0.05167, over 6782.00 frames.], tot_loss[loss=0.176, simple_loss=0.2638, pruned_loss=0.04416, over 1416418.77 frames.], batch size: 31, lr: 5.85e-04
+2022-05-14 14:49:26,043 INFO [train.py:812] (1/8) Epoch 13, batch 3550, loss[loss=0.1426, simple_loss=0.2276, pruned_loss=0.02881, over 7018.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2636, pruned_loss=0.04378, over 1421406.90 frames.], batch size: 16, lr: 5.85e-04
+2022-05-14 14:50:24,018 INFO [train.py:812] (1/8) Epoch 13, batch 3600, loss[loss=0.1793, simple_loss=0.2589, pruned_loss=0.04991, over 7279.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2633, pruned_loss=0.04361, over 1421846.05 frames.], batch size: 18, lr: 5.85e-04
+2022-05-14 14:51:22,132 INFO [train.py:812] (1/8) Epoch 13, batch 3650, loss[loss=0.1934, simple_loss=0.2925, pruned_loss=0.0471, over 7422.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2625, pruned_loss=0.04319, over 1425114.96 frames.], batch size: 21, lr: 5.84e-04
+2022-05-14 14:52:20,925 INFO [train.py:812] (1/8) Epoch 13, batch 3700, loss[loss=0.1414, simple_loss=0.2308, pruned_loss=0.026, over 7271.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2612, pruned_loss=0.04291, over 1425494.05 frames.], batch size: 19, lr: 5.84e-04
+2022-05-14 14:53:20,284 INFO [train.py:812] (1/8) Epoch 13, batch 3750, loss[loss=0.1946, simple_loss=0.2895, pruned_loss=0.04982, over 7419.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2608, pruned_loss=0.04269, over 1425509.32 frames.], batch size: 21, lr: 5.84e-04
+2022-05-14 14:54:19,194 INFO [train.py:812] (1/8) Epoch 13, batch 3800, loss[loss=0.1715, simple_loss=0.2591, pruned_loss=0.04189, over 7040.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2619, pruned_loss=0.04336, over 1429541.94 frames.], batch size: 28, lr: 5.84e-04
+2022-05-14 14:55:18,386 INFO [train.py:812] (1/8) Epoch 13, batch 3850, loss[loss=0.1885, simple_loss=0.2738, pruned_loss=0.0516, over 7208.00 frames.], tot_loss[loss=0.1754, simple_loss=0.263, pruned_loss=0.04392, over 1426687.02 frames.], batch size: 22, lr: 5.83e-04
+2022-05-14 14:56:17,000 INFO [train.py:812] (1/8) Epoch 13, batch 3900, loss[loss=0.1792, simple_loss=0.2676, pruned_loss=0.04539, over 7323.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2618, pruned_loss=0.04353, over 1424941.92 frames.], batch size: 24, lr: 5.83e-04
+2022-05-14 14:57:16,821 INFO [train.py:812] (1/8) Epoch 13, batch 3950, loss[loss=0.1785, simple_loss=0.2633, pruned_loss=0.0469, over 7208.00 frames.], tot_loss[loss=0.174, simple_loss=0.2613, pruned_loss=0.04332, over 1424163.47 frames.], batch size: 23, lr: 5.83e-04
+2022-05-14 14:58:15,075 INFO [train.py:812] (1/8) Epoch 13, batch 4000, loss[loss=0.1537, simple_loss=0.2357, pruned_loss=0.03583, over 7134.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2612, pruned_loss=0.04348, over 1423656.84 frames.], batch size: 17, lr: 5.83e-04
+2022-05-14 14:59:14,573 INFO [train.py:812] (1/8) Epoch 13, batch 4050, loss[loss=0.1661, simple_loss=0.2671, pruned_loss=0.03258, over 7231.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2609, pruned_loss=0.0432, over 1425589.19 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:00:14,089 INFO [train.py:812] (1/8) Epoch 13, batch 4100, loss[loss=0.2093, simple_loss=0.3081, pruned_loss=0.0552, over 7140.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2608, pruned_loss=0.04321, over 1424839.39 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:01:13,268 INFO [train.py:812] (1/8) Epoch 13, batch 4150, loss[loss=0.153, simple_loss=0.2475, pruned_loss=0.02927, over 7435.00 frames.], tot_loss[loss=0.1748, simple_loss=0.262, pruned_loss=0.04384, over 1419479.16 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:02:11,348 INFO [train.py:812] (1/8) Epoch 13, batch 4200, loss[loss=0.1683, simple_loss=0.2635, pruned_loss=0.03661, over 7150.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2614, pruned_loss=0.04372, over 1421339.57 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:03:10,126 INFO [train.py:812] (1/8) Epoch 13, batch 4250, loss[loss=0.1657, simple_loss=0.2589, pruned_loss=0.03629, over 7163.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2614, pruned_loss=0.04391, over 1419477.30 frames.], batch size: 26, lr: 5.81e-04
+2022-05-14 15:04:08,189 INFO [train.py:812] (1/8) Epoch 13, batch 4300, loss[loss=0.1835, simple_loss=0.2715, pruned_loss=0.04774, over 7430.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2627, pruned_loss=0.04457, over 1417124.27 frames.], batch size: 20, lr: 5.81e-04
+2022-05-14 15:05:06,771 INFO [train.py:812] (1/8) Epoch 13, batch 4350, loss[loss=0.1596, simple_loss=0.2426, pruned_loss=0.03832, over 6991.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2622, pruned_loss=0.04436, over 1411971.80 frames.], batch size: 16, lr: 5.81e-04
+2022-05-14 15:06:06,047 INFO [train.py:812] (1/8) Epoch 13, batch 4400, loss[loss=0.2337, simple_loss=0.302, pruned_loss=0.08271, over 4862.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2609, pruned_loss=0.04367, over 1409680.90 frames.], batch size: 52, lr: 5.81e-04
+2022-05-14 15:07:04,939 INFO [train.py:812] (1/8) Epoch 13, batch 4450, loss[loss=0.2224, simple_loss=0.3046, pruned_loss=0.07012, over 7276.00 frames.], tot_loss[loss=0.174, simple_loss=0.2608, pruned_loss=0.04355, over 1407202.62 frames.], batch size: 24, lr: 5.81e-04
+2022-05-14 15:08:03,275 INFO [train.py:812] (1/8) Epoch 13, batch 4500, loss[loss=0.1868, simple_loss=0.2807, pruned_loss=0.04643, over 7413.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2622, pruned_loss=0.04396, over 1388774.16 frames.], batch size: 21, lr: 5.80e-04
+2022-05-14 15:09:01,458 INFO [train.py:812] (1/8) Epoch 13, batch 4550, loss[loss=0.1979, simple_loss=0.2769, pruned_loss=0.05947, over 5171.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2643, pruned_loss=0.04469, over 1352901.23 frames.], batch size: 52, lr: 5.80e-04
+2022-05-14 15:10:14,173 INFO [train.py:812] (1/8) Epoch 14, batch 0, loss[loss=0.1546, simple_loss=0.2472, pruned_loss=0.03096, over 7391.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2472, pruned_loss=0.03096, over 7391.00 frames.], batch size: 23, lr: 5.61e-04
+2022-05-14 15:11:14,039 INFO [train.py:812] (1/8) Epoch 14, batch 50, loss[loss=0.197, simple_loss=0.2873, pruned_loss=0.05329, over 7118.00 frames.], tot_loss[loss=0.1724, simple_loss=0.258, pruned_loss=0.04339, over 322836.70 frames.], batch size: 21, lr: 5.61e-04
+2022-05-14 15:12:13,749 INFO [train.py:812] (1/8) Epoch 14, batch 100, loss[loss=0.2187, simple_loss=0.3149, pruned_loss=0.06125, over 7134.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2593, pruned_loss=0.04205, over 572522.20 frames.], batch size: 20, lr: 5.61e-04
+2022-05-14 15:13:13,202 INFO [train.py:812] (1/8) Epoch 14, batch 150, loss[loss=0.1363, simple_loss=0.2221, pruned_loss=0.02528, over 6993.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2574, pruned_loss=0.04175, over 762979.68 frames.], batch size: 16, lr: 5.61e-04
+2022-05-14 15:14:11,611 INFO [train.py:812] (1/8) Epoch 14, batch 200, loss[loss=0.1809, simple_loss=0.2644, pruned_loss=0.04875, over 7211.00 frames.], tot_loss[loss=0.1707, simple_loss=0.258, pruned_loss=0.04172, over 909455.67 frames.], batch size: 22, lr: 5.60e-04
+2022-05-14 15:15:09,285 INFO [train.py:812] (1/8) Epoch 14, batch 250, loss[loss=0.2085, simple_loss=0.2922, pruned_loss=0.06247, over 7198.00 frames.], tot_loss[loss=0.171, simple_loss=0.2586, pruned_loss=0.0417, over 1025427.57 frames.], batch size: 22, lr: 5.60e-04
+2022-05-14 15:16:07,600 INFO [train.py:812] (1/8) Epoch 14, batch 300, loss[loss=0.1696, simple_loss=0.2563, pruned_loss=0.04144, over 7408.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2604, pruned_loss=0.04218, over 1111565.78 frames.], batch size: 21, lr: 5.60e-04
+2022-05-14 15:17:06,822 INFO [train.py:812] (1/8) Epoch 14, batch 350, loss[loss=0.1563, simple_loss=0.2416, pruned_loss=0.03548, over 7428.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2604, pruned_loss=0.04293, over 1179991.25 frames.], batch size: 20, lr: 5.60e-04
+2022-05-14 15:18:11,716 INFO [train.py:812] (1/8) Epoch 14, batch 400, loss[loss=0.174, simple_loss=0.2663, pruned_loss=0.04092, over 7071.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2602, pruned_loss=0.04282, over 1231156.35 frames.], batch size: 28, lr: 5.59e-04
+2022-05-14 15:19:10,167 INFO [train.py:812] (1/8) Epoch 14, batch 450, loss[loss=0.2094, simple_loss=0.2915, pruned_loss=0.06365, over 6292.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2612, pruned_loss=0.04292, over 1273125.36 frames.], batch size: 37, lr: 5.59e-04
+2022-05-14 15:20:09,611 INFO [train.py:812] (1/8) Epoch 14, batch 500, loss[loss=0.172, simple_loss=0.261, pruned_loss=0.04147, over 7073.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2596, pruned_loss=0.04245, over 1299784.81 frames.], batch size: 28, lr: 5.59e-04
+2022-05-14 15:21:08,781 INFO [train.py:812] (1/8) Epoch 14, batch 550, loss[loss=0.1708, simple_loss=0.2606, pruned_loss=0.04052, over 6481.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2603, pruned_loss=0.04289, over 1325942.86 frames.], batch size: 38, lr: 5.59e-04
+2022-05-14 15:22:08,320 INFO [train.py:812] (1/8) Epoch 14, batch 600, loss[loss=0.1705, simple_loss=0.2636, pruned_loss=0.03873, over 7312.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2596, pruned_loss=0.04274, over 1348796.40 frames.], batch size: 21, lr: 5.59e-04
+2022-05-14 15:23:07,038 INFO [train.py:812] (1/8) Epoch 14, batch 650, loss[loss=0.186, simple_loss=0.2736, pruned_loss=0.04919, over 7064.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2604, pruned_loss=0.04333, over 1361078.33 frames.], batch size: 18, lr: 5.58e-04
+2022-05-14 15:24:06,552 INFO [train.py:812] (1/8) Epoch 14, batch 700, loss[loss=0.1445, simple_loss=0.2306, pruned_loss=0.02919, over 7255.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2608, pruned_loss=0.04352, over 1376609.54 frames.], batch size: 18, lr: 5.58e-04
+2022-05-14 15:25:05,441 INFO [train.py:812] (1/8) Epoch 14, batch 750, loss[loss=0.2057, simple_loss=0.3017, pruned_loss=0.05484, over 7179.00 frames.], tot_loss[loss=0.174, simple_loss=0.261, pruned_loss=0.04347, over 1382986.29 frames.], batch size: 23, lr: 5.58e-04
+2022-05-14 15:26:04,464 INFO [train.py:812] (1/8) Epoch 14, batch 800, loss[loss=0.1848, simple_loss=0.2807, pruned_loss=0.0444, over 7309.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2614, pruned_loss=0.0434, over 1392235.93 frames.], batch size: 25, lr: 5.58e-04
+2022-05-14 15:27:03,665 INFO [train.py:812] (1/8) Epoch 14, batch 850, loss[loss=0.1599, simple_loss=0.2594, pruned_loss=0.03025, over 7215.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2601, pruned_loss=0.0426, over 1399803.73 frames.], batch size: 21, lr: 5.57e-04
+2022-05-14 15:28:02,924 INFO [train.py:812] (1/8) Epoch 14, batch 900, loss[loss=0.165, simple_loss=0.2472, pruned_loss=0.04135, over 7171.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2602, pruned_loss=0.04234, over 1402846.99 frames.], batch size: 18, lr: 5.57e-04
+2022-05-14 15:29:01,731 INFO [train.py:812] (1/8) Epoch 14, batch 950, loss[loss=0.1816, simple_loss=0.2712, pruned_loss=0.04605, over 7232.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2609, pruned_loss=0.0427, over 1403868.52 frames.], batch size: 21, lr: 5.57e-04
+2022-05-14 15:30:01,410 INFO [train.py:812] (1/8) Epoch 14, batch 1000, loss[loss=0.1709, simple_loss=0.2483, pruned_loss=0.04674, over 7206.00 frames.], tot_loss[loss=0.172, simple_loss=0.2598, pruned_loss=0.04208, over 1410691.07 frames.], batch size: 22, lr: 5.57e-04
+2022-05-14 15:31:00,122 INFO [train.py:812] (1/8) Epoch 14, batch 1050, loss[loss=0.1839, simple_loss=0.2756, pruned_loss=0.04611, over 7414.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2603, pruned_loss=0.04233, over 1411397.24 frames.], batch size: 21, lr: 5.56e-04
+2022-05-14 15:31:57,360 INFO [train.py:812] (1/8) Epoch 14, batch 1100, loss[loss=0.181, simple_loss=0.2649, pruned_loss=0.04854, over 6746.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2601, pruned_loss=0.04229, over 1410871.48 frames.], batch size: 31, lr: 5.56e-04
+2022-05-14 15:32:55,042 INFO [train.py:812] (1/8) Epoch 14, batch 1150, loss[loss=0.1934, simple_loss=0.279, pruned_loss=0.05393, over 7342.00 frames.], tot_loss[loss=0.173, simple_loss=0.261, pruned_loss=0.04253, over 1410821.65 frames.], batch size: 22, lr: 5.56e-04
+2022-05-14 15:33:54,464 INFO [train.py:812] (1/8) Epoch 14, batch 1200, loss[loss=0.2006, simple_loss=0.2766, pruned_loss=0.06229, over 5341.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2609, pruned_loss=0.04243, over 1410374.03 frames.], batch size: 52, lr: 5.56e-04
+2022-05-14 15:34:52,768 INFO [train.py:812] (1/8) Epoch 14, batch 1250, loss[loss=0.1359, simple_loss=0.2208, pruned_loss=0.02553, over 7427.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2616, pruned_loss=0.04285, over 1414761.60 frames.], batch size: 20, lr: 5.56e-04
+2022-05-14 15:35:51,072 INFO [train.py:812] (1/8) Epoch 14, batch 1300, loss[loss=0.176, simple_loss=0.2605, pruned_loss=0.04578, over 7264.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2616, pruned_loss=0.04261, over 1417751.30 frames.], batch size: 19, lr: 5.55e-04
+2022-05-14 15:36:49,465 INFO [train.py:812] (1/8) Epoch 14, batch 1350, loss[loss=0.1494, simple_loss=0.23, pruned_loss=0.03441, over 7277.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2606, pruned_loss=0.04239, over 1421531.76 frames.], batch size: 18, lr: 5.55e-04
+2022-05-14 15:37:48,223 INFO [train.py:812] (1/8) Epoch 14, batch 1400, loss[loss=0.1749, simple_loss=0.2532, pruned_loss=0.04834, over 7157.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2619, pruned_loss=0.04325, over 1417791.22 frames.], batch size: 18, lr: 5.55e-04
+2022-05-14 15:38:45,035 INFO [train.py:812] (1/8) Epoch 14, batch 1450, loss[loss=0.1353, simple_loss=0.2158, pruned_loss=0.02741, over 7290.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2618, pruned_loss=0.04315, over 1421534.23 frames.], batch size: 17, lr: 5.55e-04
+2022-05-14 15:39:43,868 INFO [train.py:812] (1/8) Epoch 14, batch 1500, loss[loss=0.1442, simple_loss=0.2275, pruned_loss=0.03049, over 7263.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2611, pruned_loss=0.04299, over 1423232.41 frames.], batch size: 17, lr: 5.54e-04
+2022-05-14 15:40:41,995 INFO [train.py:812] (1/8) Epoch 14, batch 1550, loss[loss=0.1993, simple_loss=0.2822, pruned_loss=0.05819, over 6427.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2621, pruned_loss=0.04343, over 1419117.35 frames.], batch size: 38, lr: 5.54e-04
+2022-05-14 15:41:40,133 INFO [train.py:812] (1/8) Epoch 14, batch 1600, loss[loss=0.1624, simple_loss=0.2602, pruned_loss=0.03229, over 7424.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2626, pruned_loss=0.04344, over 1418005.43 frames.], batch size: 21, lr: 5.54e-04
+2022-05-14 15:42:38,928 INFO [train.py:812] (1/8) Epoch 14, batch 1650, loss[loss=0.2091, simple_loss=0.301, pruned_loss=0.0586, over 7238.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2625, pruned_loss=0.04345, over 1419731.35 frames.], batch size: 20, lr: 5.54e-04
+2022-05-14 15:43:38,137 INFO [train.py:812] (1/8) Epoch 14, batch 1700, loss[loss=0.1905, simple_loss=0.2897, pruned_loss=0.04568, over 6298.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2626, pruned_loss=0.04312, over 1418929.25 frames.], batch size: 37, lr: 5.54e-04
+2022-05-14 15:44:37,145 INFO [train.py:812] (1/8) Epoch 14, batch 1750, loss[loss=0.1436, simple_loss=0.2311, pruned_loss=0.0281, over 7275.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2611, pruned_loss=0.04253, over 1420916.61 frames.], batch size: 17, lr: 5.53e-04
+2022-05-14 15:45:37,328 INFO [train.py:812] (1/8) Epoch 14, batch 1800, loss[loss=0.1714, simple_loss=0.2562, pruned_loss=0.04332, over 7146.00 frames.], tot_loss[loss=0.173, simple_loss=0.2613, pruned_loss=0.0423, over 1426358.89 frames.], batch size: 20, lr: 5.53e-04
+2022-05-14 15:46:35,084 INFO [train.py:812] (1/8) Epoch 14, batch 1850, loss[loss=0.2065, simple_loss=0.2963, pruned_loss=0.05836, over 7311.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2618, pruned_loss=0.04261, over 1426167.73 frames.], batch size: 25, lr: 5.53e-04
+2022-05-14 15:47:33,723 INFO [train.py:812] (1/8) Epoch 14, batch 1900, loss[loss=0.1879, simple_loss=0.2826, pruned_loss=0.04663, over 6356.00 frames.], tot_loss[loss=0.1739, simple_loss=0.262, pruned_loss=0.04292, over 1422390.19 frames.], batch size: 37, lr: 5.53e-04
+2022-05-14 15:48:32,630 INFO [train.py:812] (1/8) Epoch 14, batch 1950, loss[loss=0.1805, simple_loss=0.2677, pruned_loss=0.04666, over 7257.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2621, pruned_loss=0.04257, over 1423711.82 frames.], batch size: 19, lr: 5.52e-04
+2022-05-14 15:49:32,353 INFO [train.py:812] (1/8) Epoch 14, batch 2000, loss[loss=0.1896, simple_loss=0.2895, pruned_loss=0.04481, over 7325.00 frames.], tot_loss[loss=0.1732, simple_loss=0.262, pruned_loss=0.04221, over 1425262.98 frames.], batch size: 22, lr: 5.52e-04
+2022-05-14 15:50:31,354 INFO [train.py:812] (1/8) Epoch 14, batch 2050, loss[loss=0.1728, simple_loss=0.265, pruned_loss=0.04024, over 7375.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2614, pruned_loss=0.04187, over 1426771.06 frames.], batch size: 23, lr: 5.52e-04
+2022-05-14 15:51:31,086 INFO [train.py:812] (1/8) Epoch 14, batch 2100, loss[loss=0.1404, simple_loss=0.2342, pruned_loss=0.02331, over 7217.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2617, pruned_loss=0.04172, over 1426720.48 frames.], batch size: 20, lr: 5.52e-04
+2022-05-14 15:52:30,494 INFO [train.py:812] (1/8) Epoch 14, batch 2150, loss[loss=0.1806, simple_loss=0.2735, pruned_loss=0.04387, over 7206.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2614, pruned_loss=0.04144, over 1428882.94 frames.], batch size: 26, lr: 5.52e-04
+2022-05-14 15:53:29,899 INFO [train.py:812] (1/8) Epoch 14, batch 2200, loss[loss=0.173, simple_loss=0.2534, pruned_loss=0.04629, over 7429.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2615, pruned_loss=0.04156, over 1427560.08 frames.], batch size: 20, lr: 5.51e-04
+2022-05-14 15:54:28,284 INFO [train.py:812] (1/8) Epoch 14, batch 2250, loss[loss=0.184, simple_loss=0.2769, pruned_loss=0.04556, over 7227.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2612, pruned_loss=0.04134, over 1427707.22 frames.], batch size: 20, lr: 5.51e-04
+2022-05-14 15:55:26,895 INFO [train.py:812] (1/8) Epoch 14, batch 2300, loss[loss=0.1796, simple_loss=0.2675, pruned_loss=0.04588, over 7035.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2602, pruned_loss=0.04132, over 1428293.44 frames.], batch size: 28, lr: 5.51e-04
+2022-05-14 15:56:25,011 INFO [train.py:812] (1/8) Epoch 14, batch 2350, loss[loss=0.2036, simple_loss=0.2798, pruned_loss=0.06368, over 5229.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2604, pruned_loss=0.04159, over 1427345.33 frames.], batch size: 54, lr: 5.51e-04
+2022-05-14 15:57:24,244 INFO [train.py:812] (1/8) Epoch 14, batch 2400, loss[loss=0.1645, simple_loss=0.2399, pruned_loss=0.04451, over 7284.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2601, pruned_loss=0.04125, over 1427904.95 frames.], batch size: 17, lr: 5.50e-04
+2022-05-14 15:58:23,285 INFO [train.py:812] (1/8) Epoch 14, batch 2450, loss[loss=0.2043, simple_loss=0.2906, pruned_loss=0.05905, over 7000.00 frames.], tot_loss[loss=0.172, simple_loss=0.2608, pruned_loss=0.04156, over 1430687.73 frames.], batch size: 32, lr: 5.50e-04
+2022-05-14 15:59:21,598 INFO [train.py:812] (1/8) Epoch 14, batch 2500, loss[loss=0.1334, simple_loss=0.221, pruned_loss=0.02289, over 7287.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2615, pruned_loss=0.04197, over 1427193.46 frames.], batch size: 17, lr: 5.50e-04
+2022-05-14 16:00:19,961 INFO [train.py:812] (1/8) Epoch 14, batch 2550, loss[loss=0.1657, simple_loss=0.2572, pruned_loss=0.03713, over 7289.00 frames.], tot_loss[loss=0.173, simple_loss=0.2614, pruned_loss=0.0423, over 1422974.29 frames.], batch size: 25, lr: 5.50e-04
+2022-05-14 16:01:19,223 INFO [train.py:812] (1/8) Epoch 14, batch 2600, loss[loss=0.174, simple_loss=0.27, pruned_loss=0.03898, over 7407.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2607, pruned_loss=0.042, over 1419219.26 frames.], batch size: 21, lr: 5.50e-04
+2022-05-14 16:02:16,352 INFO [train.py:812] (1/8) Epoch 14, batch 2650, loss[loss=0.1835, simple_loss=0.27, pruned_loss=0.04853, over 7112.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2611, pruned_loss=0.04215, over 1417343.66 frames.], batch size: 21, lr: 5.49e-04
+2022-05-14 16:03:15,387 INFO [train.py:812] (1/8) Epoch 14, batch 2700, loss[loss=0.1497, simple_loss=0.2367, pruned_loss=0.03137, over 6999.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2607, pruned_loss=0.04184, over 1422514.96 frames.], batch size: 16, lr: 5.49e-04
+2022-05-14 16:04:13,416 INFO [train.py:812] (1/8) Epoch 14, batch 2750, loss[loss=0.1779, simple_loss=0.278, pruned_loss=0.03894, over 7289.00 frames.], tot_loss[loss=0.1724, simple_loss=0.261, pruned_loss=0.04192, over 1427859.16 frames.], batch size: 24, lr: 5.49e-04
+2022-05-14 16:05:11,589 INFO [train.py:812] (1/8) Epoch 14, batch 2800, loss[loss=0.1725, simple_loss=0.2513, pruned_loss=0.04686, over 7149.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2602, pruned_loss=0.04178, over 1425947.74 frames.], batch size: 17, lr: 5.49e-04
+2022-05-14 16:06:10,653 INFO [train.py:812] (1/8) Epoch 14, batch 2850, loss[loss=0.1668, simple_loss=0.2657, pruned_loss=0.03396, over 7410.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2597, pruned_loss=0.04147, over 1427344.46 frames.], batch size: 21, lr: 5.48e-04
+2022-05-14 16:07:10,187 INFO [train.py:812] (1/8) Epoch 14, batch 2900, loss[loss=0.166, simple_loss=0.2589, pruned_loss=0.03657, over 7116.00 frames.], tot_loss[loss=0.172, simple_loss=0.2605, pruned_loss=0.04179, over 1428012.06 frames.], batch size: 21, lr: 5.48e-04
+2022-05-14 16:08:08,878 INFO [train.py:812] (1/8) Epoch 14, batch 2950, loss[loss=0.1972, simple_loss=0.2927, pruned_loss=0.05084, over 7196.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2605, pruned_loss=0.0416, over 1428443.61 frames.], batch size: 23, lr: 5.48e-04
+2022-05-14 16:09:07,581 INFO [train.py:812] (1/8) Epoch 14, batch 3000, loss[loss=0.1935, simple_loss=0.2961, pruned_loss=0.04543, over 7296.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2596, pruned_loss=0.04128, over 1429994.85 frames.], batch size: 24, lr: 5.48e-04
+2022-05-14 16:09:07,582 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 16:09:15,054 INFO [train.py:841] (1/8) Epoch 14, validation: loss=0.1549, simple_loss=0.2556, pruned_loss=0.02713, over 698248.00 frames.
+2022-05-14 16:10:14,207 INFO [train.py:812] (1/8) Epoch 14, batch 3050, loss[loss=0.1668, simple_loss=0.2497, pruned_loss=0.04193, over 7276.00 frames.], tot_loss[loss=0.171, simple_loss=0.2594, pruned_loss=0.04133, over 1430478.16 frames.], batch size: 17, lr: 5.48e-04
+2022-05-14 16:11:13,756 INFO [train.py:812] (1/8) Epoch 14, batch 3100, loss[loss=0.1698, simple_loss=0.2597, pruned_loss=0.03996, over 7210.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2603, pruned_loss=0.04179, over 1430993.68 frames.], batch size: 23, lr: 5.47e-04
+2022-05-14 16:12:13,363 INFO [train.py:812] (1/8) Epoch 14, batch 3150, loss[loss=0.1945, simple_loss=0.2843, pruned_loss=0.05229, over 4731.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2598, pruned_loss=0.04201, over 1429366.99 frames.], batch size: 52, lr: 5.47e-04
+2022-05-14 16:13:13,721 INFO [train.py:812] (1/8) Epoch 14, batch 3200, loss[loss=0.1631, simple_loss=0.2641, pruned_loss=0.03099, over 7319.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2597, pruned_loss=0.04172, over 1429018.93 frames.], batch size: 22, lr: 5.47e-04
+2022-05-14 16:14:11,593 INFO [train.py:812] (1/8) Epoch 14, batch 3250, loss[loss=0.1849, simple_loss=0.2804, pruned_loss=0.04474, over 7188.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2602, pruned_loss=0.04176, over 1426817.06 frames.], batch size: 26, lr: 5.47e-04
+2022-05-14 16:15:10,524 INFO [train.py:812] (1/8) Epoch 14, batch 3300, loss[loss=0.1478, simple_loss=0.2324, pruned_loss=0.03159, over 7160.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2603, pruned_loss=0.04206, over 1423547.87 frames.], batch size: 18, lr: 5.46e-04
+2022-05-14 16:16:09,530 INFO [train.py:812] (1/8) Epoch 14, batch 3350, loss[loss=0.1539, simple_loss=0.2377, pruned_loss=0.03512, over 7411.00 frames.], tot_loss[loss=0.1718, simple_loss=0.26, pruned_loss=0.04183, over 1425528.74 frames.], batch size: 18, lr: 5.46e-04
+2022-05-14 16:17:08,389 INFO [train.py:812] (1/8) Epoch 14, batch 3400, loss[loss=0.1753, simple_loss=0.2676, pruned_loss=0.04148, over 7164.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2602, pruned_loss=0.04159, over 1426826.52 frames.], batch size: 18, lr: 5.46e-04
+2022-05-14 16:18:17,665 INFO [train.py:812] (1/8) Epoch 14, batch 3450, loss[loss=0.1631, simple_loss=0.2608, pruned_loss=0.0327, over 7111.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2606, pruned_loss=0.04178, over 1426219.24 frames.], batch size: 21, lr: 5.46e-04
+2022-05-14 16:19:16,720 INFO [train.py:812] (1/8) Epoch 14, batch 3500, loss[loss=0.1714, simple_loss=0.2738, pruned_loss=0.03451, over 7334.00 frames.], tot_loss[loss=0.172, simple_loss=0.2604, pruned_loss=0.04181, over 1427969.39 frames.], batch size: 22, lr: 5.46e-04
+2022-05-14 16:20:15,509 INFO [train.py:812] (1/8) Epoch 14, batch 3550, loss[loss=0.1763, simple_loss=0.2794, pruned_loss=0.03654, over 7331.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2606, pruned_loss=0.04183, over 1428196.82 frames.], batch size: 21, lr: 5.45e-04
+2022-05-14 16:21:14,194 INFO [train.py:812] (1/8) Epoch 14, batch 3600, loss[loss=0.1777, simple_loss=0.2551, pruned_loss=0.05013, over 7355.00 frames.], tot_loss[loss=0.1707, simple_loss=0.259, pruned_loss=0.04124, over 1431304.35 frames.], batch size: 19, lr: 5.45e-04
+2022-05-14 16:22:13,048 INFO [train.py:812] (1/8) Epoch 14, batch 3650, loss[loss=0.1691, simple_loss=0.2674, pruned_loss=0.03546, over 7240.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2595, pruned_loss=0.04131, over 1430110.09 frames.], batch size: 20, lr: 5.45e-04
+2022-05-14 16:23:12,480 INFO [train.py:812] (1/8) Epoch 14, batch 3700, loss[loss=0.1946, simple_loss=0.2781, pruned_loss=0.05556, over 7302.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2602, pruned_loss=0.04208, over 1421581.23 frames.], batch size: 24, lr: 5.45e-04
+2022-05-14 16:24:11,505 INFO [train.py:812] (1/8) Epoch 14, batch 3750, loss[loss=0.2195, simple_loss=0.291, pruned_loss=0.07395, over 4889.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2604, pruned_loss=0.04197, over 1420687.82 frames.], batch size: 52, lr: 5.45e-04
+2022-05-14 16:25:11,057 INFO [train.py:812] (1/8) Epoch 14, batch 3800, loss[loss=0.1519, simple_loss=0.2242, pruned_loss=0.03985, over 7000.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2603, pruned_loss=0.0423, over 1419844.66 frames.], batch size: 16, lr: 5.44e-04
+2022-05-14 16:26:09,755 INFO [train.py:812] (1/8) Epoch 14, batch 3850, loss[loss=0.2275, simple_loss=0.2994, pruned_loss=0.07783, over 7206.00 frames.], tot_loss[loss=0.173, simple_loss=0.2609, pruned_loss=0.04255, over 1420117.74 frames.], batch size: 22, lr: 5.44e-04
+2022-05-14 16:27:08,436 INFO [train.py:812] (1/8) Epoch 14, batch 3900, loss[loss=0.1924, simple_loss=0.2793, pruned_loss=0.05274, over 7318.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2613, pruned_loss=0.04258, over 1422044.44 frames.], batch size: 21, lr: 5.44e-04
+2022-05-14 16:28:07,611 INFO [train.py:812] (1/8) Epoch 14, batch 3950, loss[loss=0.2407, simple_loss=0.3027, pruned_loss=0.08938, over 5034.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2607, pruned_loss=0.0428, over 1420744.68 frames.], batch size: 53, lr: 5.44e-04
+2022-05-14 16:29:06,379 INFO [train.py:812] (1/8) Epoch 14, batch 4000, loss[loss=0.1909, simple_loss=0.2853, pruned_loss=0.04823, over 7339.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2615, pruned_loss=0.04259, over 1422063.59 frames.], batch size: 22, lr: 5.43e-04
+2022-05-14 16:30:03,963 INFO [train.py:812] (1/8) Epoch 14, batch 4050, loss[loss=0.1461, simple_loss=0.2298, pruned_loss=0.03116, over 6856.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2605, pruned_loss=0.04239, over 1423503.98 frames.], batch size: 15, lr: 5.43e-04
+2022-05-14 16:31:03,490 INFO [train.py:812] (1/8) Epoch 14, batch 4100, loss[loss=0.2035, simple_loss=0.2898, pruned_loss=0.05864, over 6684.00 frames.], tot_loss[loss=0.173, simple_loss=0.2605, pruned_loss=0.04271, over 1420199.81 frames.], batch size: 31, lr: 5.43e-04
+2022-05-14 16:32:02,258 INFO [train.py:812] (1/8) Epoch 14, batch 4150, loss[loss=0.1503, simple_loss=0.2534, pruned_loss=0.02365, over 7231.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2609, pruned_loss=0.04262, over 1420964.98 frames.], batch size: 21, lr: 5.43e-04
+2022-05-14 16:33:01,717 INFO [train.py:812] (1/8) Epoch 14, batch 4200, loss[loss=0.1408, simple_loss=0.2232, pruned_loss=0.02918, over 7285.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2595, pruned_loss=0.04216, over 1421970.83 frames.], batch size: 17, lr: 5.43e-04
+2022-05-14 16:34:00,227 INFO [train.py:812] (1/8) Epoch 14, batch 4250, loss[loss=0.1762, simple_loss=0.2677, pruned_loss=0.04239, over 6482.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2593, pruned_loss=0.04198, over 1417138.86 frames.], batch size: 38, lr: 5.42e-04
+2022-05-14 16:34:59,086 INFO [train.py:812] (1/8) Epoch 14, batch 4300, loss[loss=0.1685, simple_loss=0.2608, pruned_loss=0.03811, over 7222.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2596, pruned_loss=0.04236, over 1412304.67 frames.], batch size: 21, lr: 5.42e-04
+2022-05-14 16:35:56,842 INFO [train.py:812] (1/8) Epoch 14, batch 4350, loss[loss=0.1472, simple_loss=0.2329, pruned_loss=0.03074, over 6815.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2596, pruned_loss=0.04195, over 1408535.57 frames.], batch size: 15, lr: 5.42e-04
+2022-05-14 16:37:01,589 INFO [train.py:812] (1/8) Epoch 14, batch 4400, loss[loss=0.163, simple_loss=0.2613, pruned_loss=0.03231, over 7146.00 frames.], tot_loss[loss=0.172, simple_loss=0.2595, pruned_loss=0.04225, over 1402708.01 frames.], batch size: 20, lr: 5.42e-04
+2022-05-14 16:38:00,476 INFO [train.py:812] (1/8) Epoch 14, batch 4450, loss[loss=0.2272, simple_loss=0.2874, pruned_loss=0.08349, over 4783.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2601, pruned_loss=0.04241, over 1393289.77 frames.], batch size: 55, lr: 5.42e-04
+2022-05-14 16:38:59,691 INFO [train.py:812] (1/8) Epoch 14, batch 4500, loss[loss=0.1858, simple_loss=0.2744, pruned_loss=0.04861, over 4979.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2608, pruned_loss=0.0428, over 1378659.15 frames.], batch size: 52, lr: 5.41e-04
+2022-05-14 16:40:07,822 INFO [train.py:812] (1/8) Epoch 14, batch 4550, loss[loss=0.1851, simple_loss=0.2725, pruned_loss=0.04882, over 6729.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2614, pruned_loss=0.04337, over 1368500.97 frames.], batch size: 31, lr: 5.41e-04
+2022-05-14 16:41:16,663 INFO [train.py:812] (1/8) Epoch 15, batch 0, loss[loss=0.1737, simple_loss=0.2629, pruned_loss=0.04227, over 7098.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2629, pruned_loss=0.04227, over 7098.00 frames.], batch size: 28, lr: 5.25e-04
+2022-05-14 16:42:15,479 INFO [train.py:812] (1/8) Epoch 15, batch 50, loss[loss=0.1852, simple_loss=0.269, pruned_loss=0.05074, over 5503.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2579, pruned_loss=0.04113, over 321912.59 frames.], batch size: 52, lr: 5.24e-04
+2022-05-14 16:43:15,408 INFO [train.py:812] (1/8) Epoch 15, batch 100, loss[loss=0.1461, simple_loss=0.234, pruned_loss=0.02914, over 7156.00 frames.], tot_loss[loss=0.1677, simple_loss=0.257, pruned_loss=0.03921, over 568562.36 frames.], batch size: 18, lr: 5.24e-04
+2022-05-14 16:44:31,101 INFO [train.py:812] (1/8) Epoch 15, batch 150, loss[loss=0.2173, simple_loss=0.3019, pruned_loss=0.06634, over 7108.00 frames.], tot_loss[loss=0.171, simple_loss=0.2603, pruned_loss=0.04086, over 758942.14 frames.], batch size: 21, lr: 5.24e-04
+2022-05-14 16:45:30,981 INFO [train.py:812] (1/8) Epoch 15, batch 200, loss[loss=0.1722, simple_loss=0.2607, pruned_loss=0.04184, over 7335.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2605, pruned_loss=0.04143, over 902792.74 frames.], batch size: 20, lr: 5.24e-04
+2022-05-14 16:46:49,162 INFO [train.py:812] (1/8) Epoch 15, batch 250, loss[loss=0.1672, simple_loss=0.2706, pruned_loss=0.03195, over 6167.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2598, pruned_loss=0.04026, over 1019157.05 frames.], batch size: 37, lr: 5.24e-04
+2022-05-14 16:48:07,494 INFO [train.py:812] (1/8) Epoch 15, batch 300, loss[loss=0.1583, simple_loss=0.2393, pruned_loss=0.03864, over 7137.00 frames.], tot_loss[loss=0.1701, simple_loss=0.259, pruned_loss=0.04055, over 1108875.73 frames.], batch size: 17, lr: 5.23e-04
+2022-05-14 16:49:06,735 INFO [train.py:812] (1/8) Epoch 15, batch 350, loss[loss=0.1774, simple_loss=0.2586, pruned_loss=0.04812, over 6855.00 frames.], tot_loss[loss=0.17, simple_loss=0.2586, pruned_loss=0.04071, over 1170456.32 frames.], batch size: 15, lr: 5.23e-04
+2022-05-14 16:50:06,782 INFO [train.py:812] (1/8) Epoch 15, batch 400, loss[loss=0.168, simple_loss=0.2655, pruned_loss=0.03523, over 7146.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2582, pruned_loss=0.04061, over 1226600.21 frames.], batch size: 20, lr: 5.23e-04
+2022-05-14 16:51:05,889 INFO [train.py:812] (1/8) Epoch 15, batch 450, loss[loss=0.167, simple_loss=0.2638, pruned_loss=0.03508, over 7164.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2583, pruned_loss=0.04063, over 1271826.21 frames.], batch size: 19, lr: 5.23e-04
+2022-05-14 16:52:05,391 INFO [train.py:812] (1/8) Epoch 15, batch 500, loss[loss=0.1846, simple_loss=0.2728, pruned_loss=0.04822, over 7433.00 frames.], tot_loss[loss=0.1705, simple_loss=0.259, pruned_loss=0.04101, over 1303076.31 frames.], batch size: 20, lr: 5.23e-04
+2022-05-14 16:53:04,822 INFO [train.py:812] (1/8) Epoch 15, batch 550, loss[loss=0.154, simple_loss=0.2434, pruned_loss=0.03227, over 7280.00 frames.], tot_loss[loss=0.17, simple_loss=0.2586, pruned_loss=0.04072, over 1332104.24 frames.], batch size: 18, lr: 5.22e-04
+2022-05-14 16:54:04,514 INFO [train.py:812] (1/8) Epoch 15, batch 600, loss[loss=0.1428, simple_loss=0.2402, pruned_loss=0.02274, over 7237.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2578, pruned_loss=0.04023, over 1355378.45 frames.], batch size: 20, lr: 5.22e-04
+2022-05-14 16:55:03,721 INFO [train.py:812] (1/8) Epoch 15, batch 650, loss[loss=0.1733, simple_loss=0.2683, pruned_loss=0.03912, over 7348.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2589, pruned_loss=0.04034, over 1370012.30 frames.], batch size: 22, lr: 5.22e-04
+2022-05-14 16:56:03,044 INFO [train.py:812] (1/8) Epoch 15, batch 700, loss[loss=0.1782, simple_loss=0.2706, pruned_loss=0.04289, over 7323.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2593, pruned_loss=0.04078, over 1383132.85 frames.], batch size: 20, lr: 5.22e-04
+2022-05-14 16:57:02,255 INFO [train.py:812] (1/8) Epoch 15, batch 750, loss[loss=0.1714, simple_loss=0.263, pruned_loss=0.03988, over 7337.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2594, pruned_loss=0.04097, over 1390966.17 frames.], batch size: 22, lr: 5.22e-04
+2022-05-14 16:58:01,665 INFO [train.py:812] (1/8) Epoch 15, batch 800, loss[loss=0.1514, simple_loss=0.2478, pruned_loss=0.02749, over 7328.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2586, pruned_loss=0.04039, over 1399822.97 frames.], batch size: 22, lr: 5.21e-04
+2022-05-14 16:59:00,999 INFO [train.py:812] (1/8) Epoch 15, batch 850, loss[loss=0.166, simple_loss=0.2452, pruned_loss=0.04346, over 7121.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2586, pruned_loss=0.0404, over 1402809.36 frames.], batch size: 17, lr: 5.21e-04
+2022-05-14 17:00:00,530 INFO [train.py:812] (1/8) Epoch 15, batch 900, loss[loss=0.1652, simple_loss=0.2525, pruned_loss=0.03895, over 7264.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2585, pruned_loss=0.04067, over 1396714.15 frames.], batch size: 19, lr: 5.21e-04
+2022-05-14 17:00:59,823 INFO [train.py:812] (1/8) Epoch 15, batch 950, loss[loss=0.1747, simple_loss=0.2726, pruned_loss=0.03842, over 7334.00 frames.], tot_loss[loss=0.17, simple_loss=0.2587, pruned_loss=0.04059, over 1405444.25 frames.], batch size: 22, lr: 5.21e-04
+2022-05-14 17:01:59,710 INFO [train.py:812] (1/8) Epoch 15, batch 1000, loss[loss=0.1555, simple_loss=0.252, pruned_loss=0.02948, over 7018.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2592, pruned_loss=0.04065, over 1405691.08 frames.], batch size: 28, lr: 5.21e-04
+2022-05-14 17:02:57,914 INFO [train.py:812] (1/8) Epoch 15, batch 1050, loss[loss=0.147, simple_loss=0.2372, pruned_loss=0.02844, over 7287.00 frames.], tot_loss[loss=0.1704, simple_loss=0.259, pruned_loss=0.04096, over 1411377.89 frames.], batch size: 18, lr: 5.20e-04
+2022-05-14 17:03:56,824 INFO [train.py:812] (1/8) Epoch 15, batch 1100, loss[loss=0.1646, simple_loss=0.2472, pruned_loss=0.04099, over 7263.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2591, pruned_loss=0.0412, over 1415314.77 frames.], batch size: 17, lr: 5.20e-04
+2022-05-14 17:04:54,403 INFO [train.py:812] (1/8) Epoch 15, batch 1150, loss[loss=0.1378, simple_loss=0.2282, pruned_loss=0.02368, over 7408.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2585, pruned_loss=0.04103, over 1421022.82 frames.], batch size: 21, lr: 5.20e-04
+2022-05-14 17:05:54,078 INFO [train.py:812] (1/8) Epoch 15, batch 1200, loss[loss=0.1535, simple_loss=0.2512, pruned_loss=0.02792, over 7434.00 frames.], tot_loss[loss=0.17, simple_loss=0.2584, pruned_loss=0.04087, over 1422346.87 frames.], batch size: 20, lr: 5.20e-04
+2022-05-14 17:06:52,037 INFO [train.py:812] (1/8) Epoch 15, batch 1250, loss[loss=0.1482, simple_loss=0.2379, pruned_loss=0.02927, over 7347.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2588, pruned_loss=0.04118, over 1425221.84 frames.], batch size: 19, lr: 5.20e-04
+2022-05-14 17:07:51,283 INFO [train.py:812] (1/8) Epoch 15, batch 1300, loss[loss=0.2001, simple_loss=0.2804, pruned_loss=0.05988, over 6445.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2593, pruned_loss=0.04175, over 1419325.65 frames.], batch size: 37, lr: 5.19e-04
+2022-05-14 17:08:51,296 INFO [train.py:812] (1/8) Epoch 15, batch 1350, loss[loss=0.1752, simple_loss=0.2485, pruned_loss=0.05097, over 6988.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2597, pruned_loss=0.042, over 1420615.10 frames.], batch size: 16, lr: 5.19e-04
+2022-05-14 17:09:50,449 INFO [train.py:812] (1/8) Epoch 15, batch 1400, loss[loss=0.1634, simple_loss=0.2502, pruned_loss=0.03826, over 7300.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2587, pruned_loss=0.04154, over 1420275.48 frames.], batch size: 24, lr: 5.19e-04
+2022-05-14 17:10:49,133 INFO [train.py:812] (1/8) Epoch 15, batch 1450, loss[loss=0.1672, simple_loss=0.2582, pruned_loss=0.03809, over 7385.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2594, pruned_loss=0.04148, over 1417361.81 frames.], batch size: 23, lr: 5.19e-04
+2022-05-14 17:11:46,395 INFO [train.py:812] (1/8) Epoch 15, batch 1500, loss[loss=0.1509, simple_loss=0.2421, pruned_loss=0.02989, over 7153.00 frames.], tot_loss[loss=0.1716, simple_loss=0.26, pruned_loss=0.04164, over 1411980.92 frames.], batch size: 20, lr: 5.19e-04
+2022-05-14 17:12:45,408 INFO [train.py:812] (1/8) Epoch 15, batch 1550, loss[loss=0.1706, simple_loss=0.2649, pruned_loss=0.03819, over 7115.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2594, pruned_loss=0.04147, over 1416840.81 frames.], batch size: 21, lr: 5.18e-04
+2022-05-14 17:13:44,520 INFO [train.py:812] (1/8) Epoch 15, batch 1600, loss[loss=0.1838, simple_loss=0.2664, pruned_loss=0.05062, over 7417.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2587, pruned_loss=0.041, over 1419509.26 frames.], batch size: 21, lr: 5.18e-04
+2022-05-14 17:14:43,361 INFO [train.py:812] (1/8) Epoch 15, batch 1650, loss[loss=0.1919, simple_loss=0.2799, pruned_loss=0.05201, over 7189.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2586, pruned_loss=0.04059, over 1425252.55 frames.], batch size: 23, lr: 5.18e-04
+2022-05-14 17:15:42,313 INFO [train.py:812] (1/8) Epoch 15, batch 1700, loss[loss=0.1735, simple_loss=0.2661, pruned_loss=0.04047, over 7301.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2576, pruned_loss=0.04054, over 1428820.99 frames.], batch size: 25, lr: 5.18e-04
+2022-05-14 17:16:41,864 INFO [train.py:812] (1/8) Epoch 15, batch 1750, loss[loss=0.2092, simple_loss=0.3072, pruned_loss=0.0556, over 7069.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2585, pruned_loss=0.04067, over 1431634.11 frames.], batch size: 28, lr: 5.18e-04
+2022-05-14 17:17:41,420 INFO [train.py:812] (1/8) Epoch 15, batch 1800, loss[loss=0.1293, simple_loss=0.2165, pruned_loss=0.02108, over 7281.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2584, pruned_loss=0.04073, over 1428196.70 frames.], batch size: 17, lr: 5.17e-04
+2022-05-14 17:18:41,021 INFO [train.py:812] (1/8) Epoch 15, batch 1850, loss[loss=0.1544, simple_loss=0.2451, pruned_loss=0.03188, over 7165.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2583, pruned_loss=0.04061, over 1432089.11 frames.], batch size: 18, lr: 5.17e-04
+2022-05-14 17:19:40,983 INFO [train.py:812] (1/8) Epoch 15, batch 1900, loss[loss=0.1698, simple_loss=0.2536, pruned_loss=0.04302, over 7447.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2578, pruned_loss=0.04035, over 1431518.33 frames.], batch size: 22, lr: 5.17e-04
+2022-05-14 17:20:40,326 INFO [train.py:812] (1/8) Epoch 15, batch 1950, loss[loss=0.1905, simple_loss=0.2811, pruned_loss=0.04996, over 7265.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2579, pruned_loss=0.04044, over 1431751.31 frames.], batch size: 18, lr: 5.17e-04
+2022-05-14 17:21:39,015 INFO [train.py:812] (1/8) Epoch 15, batch 2000, loss[loss=0.1818, simple_loss=0.2765, pruned_loss=0.04359, over 6450.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2588, pruned_loss=0.04133, over 1427556.89 frames.], batch size: 38, lr: 5.17e-04
+2022-05-14 17:22:38,287 INFO [train.py:812] (1/8) Epoch 15, batch 2050, loss[loss=0.1781, simple_loss=0.27, pruned_loss=0.04308, over 7292.00 frames.], tot_loss[loss=0.171, simple_loss=0.2595, pruned_loss=0.04125, over 1429023.90 frames.], batch size: 25, lr: 5.16e-04
+2022-05-14 17:23:37,400 INFO [train.py:812] (1/8) Epoch 15, batch 2100, loss[loss=0.1489, simple_loss=0.2352, pruned_loss=0.03131, over 7415.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2593, pruned_loss=0.04147, over 1422246.93 frames.], batch size: 18, lr: 5.16e-04
+2022-05-14 17:24:36,099 INFO [train.py:812] (1/8) Epoch 15, batch 2150, loss[loss=0.193, simple_loss=0.284, pruned_loss=0.05103, over 7213.00 frames.], tot_loss[loss=0.1708, simple_loss=0.259, pruned_loss=0.04123, over 1420427.63 frames.], batch size: 22, lr: 5.16e-04
+2022-05-14 17:25:35,468 INFO [train.py:812] (1/8) Epoch 15, batch 2200, loss[loss=0.1956, simple_loss=0.2863, pruned_loss=0.05238, over 7434.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2589, pruned_loss=0.04109, over 1420406.00 frames.], batch size: 20, lr: 5.16e-04
+2022-05-14 17:26:33,945 INFO [train.py:812] (1/8) Epoch 15, batch 2250, loss[loss=0.1972, simple_loss=0.2806, pruned_loss=0.05695, over 7185.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2587, pruned_loss=0.04074, over 1422253.52 frames.], batch size: 28, lr: 5.16e-04
+2022-05-14 17:27:32,330 INFO [train.py:812] (1/8) Epoch 15, batch 2300, loss[loss=0.1641, simple_loss=0.2431, pruned_loss=0.04261, over 6840.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2588, pruned_loss=0.04112, over 1420913.45 frames.], batch size: 15, lr: 5.15e-04
+2022-05-14 17:28:30,793 INFO [train.py:812] (1/8) Epoch 15, batch 2350, loss[loss=0.1365, simple_loss=0.221, pruned_loss=0.02603, over 7389.00 frames.], tot_loss[loss=0.17, simple_loss=0.2583, pruned_loss=0.04088, over 1423833.63 frames.], batch size: 18, lr: 5.15e-04
+2022-05-14 17:29:30,880 INFO [train.py:812] (1/8) Epoch 15, batch 2400, loss[loss=0.1379, simple_loss=0.2189, pruned_loss=0.02849, over 7419.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2594, pruned_loss=0.04124, over 1421911.54 frames.], batch size: 18, lr: 5.15e-04
+2022-05-14 17:30:30,108 INFO [train.py:812] (1/8) Epoch 15, batch 2450, loss[loss=0.1904, simple_loss=0.2723, pruned_loss=0.05427, over 7406.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2605, pruned_loss=0.04157, over 1423095.37 frames.], batch size: 21, lr: 5.15e-04
+2022-05-14 17:31:29,562 INFO [train.py:812] (1/8) Epoch 15, batch 2500, loss[loss=0.181, simple_loss=0.2759, pruned_loss=0.04304, over 7316.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2611, pruned_loss=0.04168, over 1425170.05 frames.], batch size: 21, lr: 5.15e-04
+2022-05-14 17:32:27,886 INFO [train.py:812] (1/8) Epoch 15, batch 2550, loss[loss=0.1533, simple_loss=0.2437, pruned_loss=0.03144, over 7153.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2605, pruned_loss=0.04162, over 1427840.31 frames.], batch size: 18, lr: 5.14e-04
+2022-05-14 17:33:27,552 INFO [train.py:812] (1/8) Epoch 15, batch 2600, loss[loss=0.1923, simple_loss=0.2754, pruned_loss=0.05457, over 7210.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2609, pruned_loss=0.04219, over 1421039.96 frames.], batch size: 23, lr: 5.14e-04
+2022-05-14 17:34:25,780 INFO [train.py:812] (1/8) Epoch 15, batch 2650, loss[loss=0.1788, simple_loss=0.2643, pruned_loss=0.04663, over 7307.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2606, pruned_loss=0.04181, over 1421504.84 frames.], batch size: 25, lr: 5.14e-04
+2022-05-14 17:35:25,133 INFO [train.py:812] (1/8) Epoch 15, batch 2700, loss[loss=0.1876, simple_loss=0.2833, pruned_loss=0.04598, over 7324.00 frames.], tot_loss[loss=0.1713, simple_loss=0.26, pruned_loss=0.04132, over 1423983.31 frames.], batch size: 21, lr: 5.14e-04
+2022-05-14 17:36:24,200 INFO [train.py:812] (1/8) Epoch 15, batch 2750, loss[loss=0.1591, simple_loss=0.257, pruned_loss=0.03055, over 7274.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2602, pruned_loss=0.0414, over 1425122.45 frames.], batch size: 24, lr: 5.14e-04
+2022-05-14 17:37:23,467 INFO [train.py:812] (1/8) Epoch 15, batch 2800, loss[loss=0.1631, simple_loss=0.2581, pruned_loss=0.0341, over 7146.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2593, pruned_loss=0.04085, over 1427986.23 frames.], batch size: 20, lr: 5.14e-04
+2022-05-14 17:38:20,798 INFO [train.py:812] (1/8) Epoch 15, batch 2850, loss[loss=0.2041, simple_loss=0.2843, pruned_loss=0.06193, over 6780.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2594, pruned_loss=0.04082, over 1427729.68 frames.], batch size: 15, lr: 5.13e-04
+2022-05-14 17:39:21,011 INFO [train.py:812] (1/8) Epoch 15, batch 2900, loss[loss=0.1515, simple_loss=0.2521, pruned_loss=0.02543, over 7363.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2594, pruned_loss=0.04136, over 1423693.68 frames.], batch size: 23, lr: 5.13e-04
+2022-05-14 17:40:19,998 INFO [train.py:812] (1/8) Epoch 15, batch 2950, loss[loss=0.1643, simple_loss=0.2522, pruned_loss=0.0382, over 7430.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2593, pruned_loss=0.04141, over 1424953.23 frames.], batch size: 20, lr: 5.13e-04
+2022-05-14 17:41:19,154 INFO [train.py:812] (1/8) Epoch 15, batch 3000, loss[loss=0.153, simple_loss=0.2518, pruned_loss=0.02713, over 7168.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2589, pruned_loss=0.0413, over 1423529.75 frames.], batch size: 19, lr: 5.13e-04
+2022-05-14 17:41:19,155 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 17:41:26,768 INFO [train.py:841] (1/8) Epoch 15, validation: loss=0.1543, simple_loss=0.2544, pruned_loss=0.02713, over 698248.00 frames.
+2022-05-14 17:42:25,629 INFO [train.py:812] (1/8) Epoch 15, batch 3050, loss[loss=0.1499, simple_loss=0.2274, pruned_loss=0.03615, over 6823.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2595, pruned_loss=0.04156, over 1425956.36 frames.], batch size: 15, lr: 5.13e-04
+2022-05-14 17:43:23,114 INFO [train.py:812] (1/8) Epoch 15, batch 3100, loss[loss=0.1519, simple_loss=0.2413, pruned_loss=0.03124, over 7336.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2602, pruned_loss=0.0418, over 1422405.50 frames.], batch size: 20, lr: 5.12e-04
+2022-05-14 17:44:21,947 INFO [train.py:812] (1/8) Epoch 15, batch 3150, loss[loss=0.1611, simple_loss=0.2331, pruned_loss=0.04456, over 7278.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2593, pruned_loss=0.04179, over 1427361.50 frames.], batch size: 17, lr: 5.12e-04
+2022-05-14 17:45:20,568 INFO [train.py:812] (1/8) Epoch 15, batch 3200, loss[loss=0.1791, simple_loss=0.2624, pruned_loss=0.04784, over 7074.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2591, pruned_loss=0.04183, over 1427753.81 frames.], batch size: 28, lr: 5.12e-04
+2022-05-14 17:46:20,203 INFO [train.py:812] (1/8) Epoch 15, batch 3250, loss[loss=0.1585, simple_loss=0.2454, pruned_loss=0.03581, over 7057.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2589, pruned_loss=0.04188, over 1428263.42 frames.], batch size: 18, lr: 5.12e-04
+2022-05-14 17:47:18,749 INFO [train.py:812] (1/8) Epoch 15, batch 3300, loss[loss=0.1626, simple_loss=0.2436, pruned_loss=0.04086, over 7263.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2573, pruned_loss=0.04105, over 1427529.27 frames.], batch size: 17, lr: 5.12e-04
+2022-05-14 17:48:17,420 INFO [train.py:812] (1/8) Epoch 15, batch 3350, loss[loss=0.1845, simple_loss=0.2855, pruned_loss=0.04178, over 7206.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2587, pruned_loss=0.04132, over 1427139.02 frames.], batch size: 23, lr: 5.11e-04
+2022-05-14 17:49:14,695 INFO [train.py:812] (1/8) Epoch 15, batch 3400, loss[loss=0.1797, simple_loss=0.2728, pruned_loss=0.04325, over 7225.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2591, pruned_loss=0.04103, over 1424233.24 frames.], batch size: 21, lr: 5.11e-04
+2022-05-14 17:50:13,359 INFO [train.py:812] (1/8) Epoch 15, batch 3450, loss[loss=0.1648, simple_loss=0.2594, pruned_loss=0.0351, over 7013.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2601, pruned_loss=0.0415, over 1420781.88 frames.], batch size: 28, lr: 5.11e-04
+2022-05-14 17:51:13,186 INFO [train.py:812] (1/8) Epoch 15, batch 3500, loss[loss=0.1698, simple_loss=0.2591, pruned_loss=0.0403, over 7181.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2592, pruned_loss=0.04134, over 1425950.83 frames.], batch size: 26, lr: 5.11e-04
+2022-05-14 17:52:12,823 INFO [train.py:812] (1/8) Epoch 15, batch 3550, loss[loss=0.181, simple_loss=0.2828, pruned_loss=0.03958, over 7227.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2596, pruned_loss=0.04132, over 1427768.25 frames.], batch size: 20, lr: 5.11e-04
+2022-05-14 17:53:11,371 INFO [train.py:812] (1/8) Epoch 15, batch 3600, loss[loss=0.1933, simple_loss=0.2757, pruned_loss=0.05551, over 7325.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2598, pruned_loss=0.04156, over 1424762.44 frames.], batch size: 21, lr: 5.11e-04
+2022-05-14 17:54:10,554 INFO [train.py:812] (1/8) Epoch 15, batch 3650, loss[loss=0.164, simple_loss=0.2571, pruned_loss=0.03542, over 7265.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2597, pruned_loss=0.04122, over 1424718.61 frames.], batch size: 19, lr: 5.10e-04
+2022-05-14 17:55:10,190 INFO [train.py:812] (1/8) Epoch 15, batch 3700, loss[loss=0.1511, simple_loss=0.2418, pruned_loss=0.03019, over 7433.00 frames.], tot_loss[loss=0.172, simple_loss=0.2604, pruned_loss=0.04182, over 1421561.66 frames.], batch size: 20, lr: 5.10e-04
+2022-05-14 17:56:09,471 INFO [train.py:812] (1/8) Epoch 15, batch 3750, loss[loss=0.1766, simple_loss=0.2651, pruned_loss=0.0441, over 5442.00 frames.], tot_loss[loss=0.1716, simple_loss=0.26, pruned_loss=0.04161, over 1423360.25 frames.], batch size: 52, lr: 5.10e-04
+2022-05-14 17:57:14,314 INFO [train.py:812] (1/8) Epoch 15, batch 3800, loss[loss=0.1633, simple_loss=0.2511, pruned_loss=0.03773, over 7064.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2594, pruned_loss=0.04105, over 1425050.17 frames.], batch size: 18, lr: 5.10e-04
+2022-05-14 17:58:12,041 INFO [train.py:812] (1/8) Epoch 15, batch 3850, loss[loss=0.1802, simple_loss=0.2768, pruned_loss=0.04178, over 7224.00 frames.], tot_loss[loss=0.1712, simple_loss=0.26, pruned_loss=0.04124, over 1427416.43 frames.], batch size: 20, lr: 5.10e-04
+2022-05-14 17:59:11,794 INFO [train.py:812] (1/8) Epoch 15, batch 3900, loss[loss=0.1773, simple_loss=0.2665, pruned_loss=0.04401, over 7253.00 frames.], tot_loss[loss=0.17, simple_loss=0.2584, pruned_loss=0.0408, over 1424684.69 frames.], batch size: 19, lr: 5.09e-04
+2022-05-14 18:00:10,973 INFO [train.py:812] (1/8) Epoch 15, batch 3950, loss[loss=0.1881, simple_loss=0.2802, pruned_loss=0.04805, over 7360.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2584, pruned_loss=0.04104, over 1421916.18 frames.], batch size: 19, lr: 5.09e-04
+2022-05-14 18:01:10,514 INFO [train.py:812] (1/8) Epoch 15, batch 4000, loss[loss=0.1666, simple_loss=0.2618, pruned_loss=0.03565, over 7226.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2583, pruned_loss=0.04069, over 1422672.67 frames.], batch size: 21, lr: 5.09e-04
+2022-05-14 18:02:09,515 INFO [train.py:812] (1/8) Epoch 15, batch 4050, loss[loss=0.1767, simple_loss=0.2742, pruned_loss=0.03962, over 7209.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2585, pruned_loss=0.04015, over 1426885.05 frames.], batch size: 21, lr: 5.09e-04
+2022-05-14 18:03:08,722 INFO [train.py:812] (1/8) Epoch 15, batch 4100, loss[loss=0.176, simple_loss=0.2675, pruned_loss=0.04225, over 7195.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2582, pruned_loss=0.04034, over 1417965.53 frames.], batch size: 23, lr: 5.09e-04
+2022-05-14 18:04:07,535 INFO [train.py:812] (1/8) Epoch 15, batch 4150, loss[loss=0.2377, simple_loss=0.3033, pruned_loss=0.08602, over 5088.00 frames.], tot_loss[loss=0.17, simple_loss=0.2585, pruned_loss=0.0408, over 1411929.38 frames.], batch size: 54, lr: 5.08e-04
+2022-05-14 18:05:07,010 INFO [train.py:812] (1/8) Epoch 15, batch 4200, loss[loss=0.1498, simple_loss=0.2463, pruned_loss=0.02667, over 7238.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2576, pruned_loss=0.04079, over 1410289.85 frames.], batch size: 20, lr: 5.08e-04
+2022-05-14 18:06:05,952 INFO [train.py:812] (1/8) Epoch 15, batch 4250, loss[loss=0.1713, simple_loss=0.2599, pruned_loss=0.04136, over 7069.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2577, pruned_loss=0.04072, over 1408331.77 frames.], batch size: 18, lr: 5.08e-04
+2022-05-14 18:07:05,138 INFO [train.py:812] (1/8) Epoch 15, batch 4300, loss[loss=0.1455, simple_loss=0.2344, pruned_loss=0.02832, over 7172.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2585, pruned_loss=0.04091, over 1404735.85 frames.], batch size: 16, lr: 5.08e-04
+2022-05-14 18:08:04,067 INFO [train.py:812] (1/8) Epoch 15, batch 4350, loss[loss=0.161, simple_loss=0.2566, pruned_loss=0.03271, over 7322.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2592, pruned_loss=0.04086, over 1409304.48 frames.], batch size: 21, lr: 5.08e-04
+2022-05-14 18:09:03,501 INFO [train.py:812] (1/8) Epoch 15, batch 4400, loss[loss=0.1532, simple_loss=0.2395, pruned_loss=0.03348, over 7165.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2573, pruned_loss=0.04, over 1411653.97 frames.], batch size: 19, lr: 5.08e-04
+2022-05-14 18:10:02,433 INFO [train.py:812] (1/8) Epoch 15, batch 4450, loss[loss=0.1636, simple_loss=0.259, pruned_loss=0.03408, over 7174.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2568, pruned_loss=0.04024, over 1405361.00 frames.], batch size: 18, lr: 5.07e-04
+2022-05-14 18:11:01,294 INFO [train.py:812] (1/8) Epoch 15, batch 4500, loss[loss=0.1553, simple_loss=0.2465, pruned_loss=0.03201, over 7068.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2574, pruned_loss=0.04062, over 1395766.17 frames.], batch size: 18, lr: 5.07e-04
+2022-05-14 18:11:59,586 INFO [train.py:812] (1/8) Epoch 15, batch 4550, loss[loss=0.2132, simple_loss=0.2993, pruned_loss=0.06357, over 5022.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2584, pruned_loss=0.0414, over 1369225.82 frames.], batch size: 52, lr: 5.07e-04
+2022-05-14 18:13:08,761 INFO [train.py:812] (1/8) Epoch 16, batch 0, loss[loss=0.1833, simple_loss=0.2736, pruned_loss=0.04649, over 7291.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2736, pruned_loss=0.04649, over 7291.00 frames.], batch size: 24, lr: 4.92e-04
+2022-05-14 18:14:07,987 INFO [train.py:812] (1/8) Epoch 16, batch 50, loss[loss=0.1422, simple_loss=0.2299, pruned_loss=0.02718, over 7395.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2574, pruned_loss=0.03937, over 321492.26 frames.], batch size: 18, lr: 4.92e-04
+2022-05-14 18:15:07,120 INFO [train.py:812] (1/8) Epoch 16, batch 100, loss[loss=0.1468, simple_loss=0.2309, pruned_loss=0.03135, over 7330.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2541, pruned_loss=0.03814, over 564939.64 frames.], batch size: 20, lr: 4.92e-04
+2022-05-14 18:16:06,275 INFO [train.py:812] (1/8) Epoch 16, batch 150, loss[loss=0.1829, simple_loss=0.2766, pruned_loss=0.04462, over 7154.00 frames.], tot_loss[loss=0.1662, simple_loss=0.255, pruned_loss=0.03876, over 755208.44 frames.], batch size: 20, lr: 4.92e-04
+2022-05-14 18:17:15,043 INFO [train.py:812] (1/8) Epoch 16, batch 200, loss[loss=0.1821, simple_loss=0.2645, pruned_loss=0.04988, over 7115.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2551, pruned_loss=0.03895, over 898430.60 frames.], batch size: 21, lr: 4.91e-04
+2022-05-14 18:18:13,073 INFO [train.py:812] (1/8) Epoch 16, batch 250, loss[loss=0.1543, simple_loss=0.2418, pruned_loss=0.03341, over 7157.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2549, pruned_loss=0.0388, over 1015060.17 frames.], batch size: 19, lr: 4.91e-04
+2022-05-14 18:19:12,331 INFO [train.py:812] (1/8) Epoch 16, batch 300, loss[loss=0.1443, simple_loss=0.2428, pruned_loss=0.02288, over 7154.00 frames.], tot_loss[loss=0.1664, simple_loss=0.255, pruned_loss=0.03887, over 1109470.28 frames.], batch size: 19, lr: 4.91e-04
+2022-05-14 18:20:11,383 INFO [train.py:812] (1/8) Epoch 16, batch 350, loss[loss=0.1495, simple_loss=0.2346, pruned_loss=0.03218, over 7280.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2552, pruned_loss=0.03911, over 1180213.56 frames.], batch size: 18, lr: 4.91e-04
+2022-05-14 18:21:11,295 INFO [train.py:812] (1/8) Epoch 16, batch 400, loss[loss=0.1627, simple_loss=0.2403, pruned_loss=0.04253, over 7248.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2562, pruned_loss=0.03924, over 1233856.79 frames.], batch size: 19, lr: 4.91e-04
+2022-05-14 18:22:10,133 INFO [train.py:812] (1/8) Epoch 16, batch 450, loss[loss=0.1476, simple_loss=0.2386, pruned_loss=0.02827, over 7427.00 frames.], tot_loss[loss=0.167, simple_loss=0.2561, pruned_loss=0.0389, over 1280950.76 frames.], batch size: 20, lr: 4.91e-04
+2022-05-14 18:23:09,256 INFO [train.py:812] (1/8) Epoch 16, batch 500, loss[loss=0.199, simple_loss=0.2885, pruned_loss=0.05479, over 7185.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2579, pruned_loss=0.03969, over 1317903.05 frames.], batch size: 23, lr: 4.90e-04
+2022-05-14 18:24:07,727 INFO [train.py:812] (1/8) Epoch 16, batch 550, loss[loss=0.1397, simple_loss=0.2319, pruned_loss=0.02372, over 7282.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2565, pruned_loss=0.0394, over 1345109.78 frames.], batch size: 18, lr: 4.90e-04
+2022-05-14 18:25:07,649 INFO [train.py:812] (1/8) Epoch 16, batch 600, loss[loss=0.17, simple_loss=0.2544, pruned_loss=0.04282, over 7160.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2568, pruned_loss=0.0397, over 1361788.08 frames.], batch size: 19, lr: 4.90e-04
+2022-05-14 18:26:06,741 INFO [train.py:812] (1/8) Epoch 16, batch 650, loss[loss=0.1613, simple_loss=0.2537, pruned_loss=0.03444, over 6524.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2567, pruned_loss=0.03984, over 1374109.65 frames.], batch size: 38, lr: 4.90e-04
+2022-05-14 18:27:05,469 INFO [train.py:812] (1/8) Epoch 16, batch 700, loss[loss=0.1874, simple_loss=0.2806, pruned_loss=0.04712, over 7087.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2575, pruned_loss=0.03998, over 1386363.53 frames.], batch size: 28, lr: 4.90e-04
+2022-05-14 18:28:04,357 INFO [train.py:812] (1/8) Epoch 16, batch 750, loss[loss=0.1781, simple_loss=0.2547, pruned_loss=0.05074, over 7162.00 frames.], tot_loss[loss=0.1681, simple_loss=0.257, pruned_loss=0.03957, over 1395122.44 frames.], batch size: 19, lr: 4.89e-04
+2022-05-14 18:29:03,807 INFO [train.py:812] (1/8) Epoch 16, batch 800, loss[loss=0.1857, simple_loss=0.2698, pruned_loss=0.05081, over 7260.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2566, pruned_loss=0.0393, over 1402578.05 frames.], batch size: 19, lr: 4.89e-04
+2022-05-14 18:30:02,509 INFO [train.py:812] (1/8) Epoch 16, batch 850, loss[loss=0.1626, simple_loss=0.2555, pruned_loss=0.03486, over 7141.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2573, pruned_loss=0.03965, over 1404922.81 frames.], batch size: 20, lr: 4.89e-04
+2022-05-14 18:31:02,371 INFO [train.py:812] (1/8) Epoch 16, batch 900, loss[loss=0.1562, simple_loss=0.24, pruned_loss=0.0362, over 7360.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2576, pruned_loss=0.03999, over 1404419.34 frames.], batch size: 19, lr: 4.89e-04
+2022-05-14 18:32:01,912 INFO [train.py:812] (1/8) Epoch 16, batch 950, loss[loss=0.1643, simple_loss=0.2565, pruned_loss=0.03604, over 7435.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2571, pruned_loss=0.0402, over 1407134.89 frames.], batch size: 20, lr: 4.89e-04
+2022-05-14 18:33:00,788 INFO [train.py:812] (1/8) Epoch 16, batch 1000, loss[loss=0.1561, simple_loss=0.2527, pruned_loss=0.02976, over 7286.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2568, pruned_loss=0.03999, over 1413265.69 frames.], batch size: 25, lr: 4.89e-04
+2022-05-14 18:33:59,608 INFO [train.py:812] (1/8) Epoch 16, batch 1050, loss[loss=0.183, simple_loss=0.2701, pruned_loss=0.04798, over 7320.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2582, pruned_loss=0.0405, over 1418283.64 frames.], batch size: 20, lr: 4.88e-04
+2022-05-14 18:34:59,560 INFO [train.py:812] (1/8) Epoch 16, batch 1100, loss[loss=0.1471, simple_loss=0.2337, pruned_loss=0.03023, over 7362.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2575, pruned_loss=0.04012, over 1422098.99 frames.], batch size: 19, lr: 4.88e-04
+2022-05-14 18:35:59,308 INFO [train.py:812] (1/8) Epoch 16, batch 1150, loss[loss=0.1738, simple_loss=0.2685, pruned_loss=0.03951, over 5130.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2568, pruned_loss=0.04004, over 1422277.00 frames.], batch size: 52, lr: 4.88e-04
+2022-05-14 18:36:59,227 INFO [train.py:812] (1/8) Epoch 16, batch 1200, loss[loss=0.1732, simple_loss=0.269, pruned_loss=0.03873, over 7117.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2569, pruned_loss=0.03996, over 1418413.96 frames.], batch size: 21, lr: 4.88e-04
+2022-05-14 18:37:58,855 INFO [train.py:812] (1/8) Epoch 16, batch 1250, loss[loss=0.1371, simple_loss=0.22, pruned_loss=0.02711, over 7182.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2566, pruned_loss=0.0401, over 1419471.74 frames.], batch size: 16, lr: 4.88e-04
+2022-05-14 18:38:58,783 INFO [train.py:812] (1/8) Epoch 16, batch 1300, loss[loss=0.1575, simple_loss=0.249, pruned_loss=0.033, over 7206.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2574, pruned_loss=0.04014, over 1425546.22 frames.], batch size: 22, lr: 4.88e-04
+2022-05-14 18:39:58,305 INFO [train.py:812] (1/8) Epoch 16, batch 1350, loss[loss=0.1609, simple_loss=0.2467, pruned_loss=0.03762, over 7160.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2578, pruned_loss=0.04091, over 1418394.69 frames.], batch size: 19, lr: 4.87e-04
+2022-05-14 18:40:58,011 INFO [train.py:812] (1/8) Epoch 16, batch 1400, loss[loss=0.1716, simple_loss=0.2678, pruned_loss=0.03773, over 7348.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2583, pruned_loss=0.0407, over 1416493.00 frames.], batch size: 22, lr: 4.87e-04
+2022-05-14 18:41:57,517 INFO [train.py:812] (1/8) Epoch 16, batch 1450, loss[loss=0.188, simple_loss=0.2807, pruned_loss=0.0477, over 7423.00 frames.], tot_loss[loss=0.17, simple_loss=0.2587, pruned_loss=0.04069, over 1422491.76 frames.], batch size: 21, lr: 4.87e-04
+2022-05-14 18:43:06,578 INFO [train.py:812] (1/8) Epoch 16, batch 1500, loss[loss=0.1951, simple_loss=0.2807, pruned_loss=0.05479, over 7199.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2583, pruned_loss=0.04066, over 1422774.40 frames.], batch size: 23, lr: 4.87e-04
+2022-05-14 18:44:06,052 INFO [train.py:812] (1/8) Epoch 16, batch 1550, loss[loss=0.1359, simple_loss=0.2158, pruned_loss=0.02799, over 7227.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2576, pruned_loss=0.04057, over 1421475.31 frames.], batch size: 16, lr: 4.87e-04
+2022-05-14 18:45:05,964 INFO [train.py:812] (1/8) Epoch 16, batch 1600, loss[loss=0.1911, simple_loss=0.2542, pruned_loss=0.06402, over 7240.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2579, pruned_loss=0.0407, over 1424002.40 frames.], batch size: 16, lr: 4.87e-04
+2022-05-14 18:46:05,460 INFO [train.py:812] (1/8) Epoch 16, batch 1650, loss[loss=0.1511, simple_loss=0.2455, pruned_loss=0.02836, over 7128.00 frames.], tot_loss[loss=0.169, simple_loss=0.2576, pruned_loss=0.04017, over 1425597.58 frames.], batch size: 20, lr: 4.86e-04
+2022-05-14 18:47:14,902 INFO [train.py:812] (1/8) Epoch 16, batch 1700, loss[loss=0.1487, simple_loss=0.2315, pruned_loss=0.0329, over 7400.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2562, pruned_loss=0.03962, over 1425641.91 frames.], batch size: 18, lr: 4.86e-04
+2022-05-14 18:48:31,547 INFO [train.py:812] (1/8) Epoch 16, batch 1750, loss[loss=0.1835, simple_loss=0.2778, pruned_loss=0.04461, over 7378.00 frames.], tot_loss[loss=0.1684, simple_loss=0.257, pruned_loss=0.03991, over 1425258.60 frames.], batch size: 23, lr: 4.86e-04
+2022-05-14 18:49:49,348 INFO [train.py:812] (1/8) Epoch 16, batch 1800, loss[loss=0.1585, simple_loss=0.2464, pruned_loss=0.03531, over 7362.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2577, pruned_loss=0.04006, over 1423330.16 frames.], batch size: 19, lr: 4.86e-04
+2022-05-14 18:50:57,668 INFO [train.py:812] (1/8) Epoch 16, batch 1850, loss[loss=0.1692, simple_loss=0.2708, pruned_loss=0.03377, over 7150.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2567, pruned_loss=0.04009, over 1425942.27 frames.], batch size: 20, lr: 4.86e-04
+2022-05-14 18:51:57,517 INFO [train.py:812] (1/8) Epoch 16, batch 1900, loss[loss=0.1833, simple_loss=0.2774, pruned_loss=0.04461, over 7303.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2566, pruned_loss=0.03978, over 1429832.49 frames.], batch size: 25, lr: 4.86e-04
+2022-05-14 18:52:55,105 INFO [train.py:812] (1/8) Epoch 16, batch 1950, loss[loss=0.1779, simple_loss=0.2722, pruned_loss=0.04183, over 7215.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2576, pruned_loss=0.04023, over 1430544.02 frames.], batch size: 23, lr: 4.85e-04
+2022-05-14 18:53:54,407 INFO [train.py:812] (1/8) Epoch 16, batch 2000, loss[loss=0.2433, simple_loss=0.3128, pruned_loss=0.08686, over 4812.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2577, pruned_loss=0.04023, over 1423605.35 frames.], batch size: 53, lr: 4.85e-04
+2022-05-14 18:54:53,356 INFO [train.py:812] (1/8) Epoch 16, batch 2050, loss[loss=0.1733, simple_loss=0.2577, pruned_loss=0.04447, over 6398.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2583, pruned_loss=0.04027, over 1422598.48 frames.], batch size: 37, lr: 4.85e-04
+2022-05-14 18:55:52,719 INFO [train.py:812] (1/8) Epoch 16, batch 2100, loss[loss=0.1632, simple_loss=0.2617, pruned_loss=0.03231, over 7117.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2583, pruned_loss=0.04032, over 1424003.50 frames.], batch size: 21, lr: 4.85e-04
+2022-05-14 18:56:51,660 INFO [train.py:812] (1/8) Epoch 16, batch 2150, loss[loss=0.1597, simple_loss=0.2438, pruned_loss=0.0378, over 7263.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2582, pruned_loss=0.03997, over 1419485.54 frames.], batch size: 19, lr: 4.85e-04
+2022-05-14 18:57:50,994 INFO [train.py:812] (1/8) Epoch 16, batch 2200, loss[loss=0.1717, simple_loss=0.2573, pruned_loss=0.04301, over 7206.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2582, pruned_loss=0.04042, over 1416687.99 frames.], batch size: 22, lr: 4.84e-04
+2022-05-14 18:58:50,184 INFO [train.py:812] (1/8) Epoch 16, batch 2250, loss[loss=0.183, simple_loss=0.2703, pruned_loss=0.04783, over 7424.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2581, pruned_loss=0.04016, over 1418672.83 frames.], batch size: 21, lr: 4.84e-04
+2022-05-14 18:59:49,559 INFO [train.py:812] (1/8) Epoch 16, batch 2300, loss[loss=0.187, simple_loss=0.2708, pruned_loss=0.05166, over 7195.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2584, pruned_loss=0.04028, over 1419817.68 frames.], batch size: 23, lr: 4.84e-04
+2022-05-14 19:00:48,687 INFO [train.py:812] (1/8) Epoch 16, batch 2350, loss[loss=0.1986, simple_loss=0.2901, pruned_loss=0.05354, over 7292.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2575, pruned_loss=0.03965, over 1422993.50 frames.], batch size: 25, lr: 4.84e-04
+2022-05-14 19:01:48,353 INFO [train.py:812] (1/8) Epoch 16, batch 2400, loss[loss=0.1956, simple_loss=0.2814, pruned_loss=0.05491, over 7294.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2565, pruned_loss=0.03935, over 1426493.91 frames.], batch size: 25, lr: 4.84e-04
+2022-05-14 19:02:47,253 INFO [train.py:812] (1/8) Epoch 16, batch 2450, loss[loss=0.1923, simple_loss=0.2833, pruned_loss=0.05064, over 6750.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2564, pruned_loss=0.03932, over 1424956.06 frames.], batch size: 31, lr: 4.84e-04
+2022-05-14 19:03:46,834 INFO [train.py:812] (1/8) Epoch 16, batch 2500, loss[loss=0.1532, simple_loss=0.2489, pruned_loss=0.02878, over 7233.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2563, pruned_loss=0.03925, over 1427216.79 frames.], batch size: 21, lr: 4.83e-04
+2022-05-14 19:04:46,112 INFO [train.py:812] (1/8) Epoch 16, batch 2550, loss[loss=0.149, simple_loss=0.2512, pruned_loss=0.0234, over 7147.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2558, pruned_loss=0.03897, over 1423990.23 frames.], batch size: 20, lr: 4.83e-04
+2022-05-14 19:05:45,579 INFO [train.py:812] (1/8) Epoch 16, batch 2600, loss[loss=0.1662, simple_loss=0.2595, pruned_loss=0.0365, over 7366.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2567, pruned_loss=0.03978, over 1422564.89 frames.], batch size: 19, lr: 4.83e-04
+2022-05-14 19:06:45,270 INFO [train.py:812] (1/8) Epoch 16, batch 2650, loss[loss=0.1791, simple_loss=0.2752, pruned_loss=0.04155, over 7387.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2572, pruned_loss=0.04004, over 1422644.81 frames.], batch size: 23, lr: 4.83e-04
+2022-05-14 19:07:45,171 INFO [train.py:812] (1/8) Epoch 16, batch 2700, loss[loss=0.1899, simple_loss=0.2864, pruned_loss=0.04664, over 7201.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2571, pruned_loss=0.04015, over 1419501.49 frames.], batch size: 26, lr: 4.83e-04
+2022-05-14 19:08:44,238 INFO [train.py:812] (1/8) Epoch 16, batch 2750, loss[loss=0.1524, simple_loss=0.2438, pruned_loss=0.03054, over 7274.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2583, pruned_loss=0.0403, over 1423255.18 frames.], batch size: 18, lr: 4.83e-04
+2022-05-14 19:09:44,119 INFO [train.py:812] (1/8) Epoch 16, batch 2800, loss[loss=0.1625, simple_loss=0.2533, pruned_loss=0.03591, over 7222.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2586, pruned_loss=0.04011, over 1425809.76 frames.], batch size: 21, lr: 4.82e-04
+2022-05-14 19:10:43,377 INFO [train.py:812] (1/8) Epoch 16, batch 2850, loss[loss=0.1599, simple_loss=0.2366, pruned_loss=0.04154, over 7150.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2583, pruned_loss=0.04031, over 1424937.84 frames.], batch size: 18, lr: 4.82e-04
+2022-05-14 19:11:42,827 INFO [train.py:812] (1/8) Epoch 16, batch 2900, loss[loss=0.1519, simple_loss=0.2395, pruned_loss=0.03216, over 7157.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2586, pruned_loss=0.04019, over 1427989.36 frames.], batch size: 18, lr: 4.82e-04
+2022-05-14 19:12:41,625 INFO [train.py:812] (1/8) Epoch 16, batch 2950, loss[loss=0.169, simple_loss=0.2669, pruned_loss=0.03553, over 7330.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2588, pruned_loss=0.04073, over 1423975.49 frames.], batch size: 22, lr: 4.82e-04
+2022-05-14 19:13:40,837 INFO [train.py:812] (1/8) Epoch 16, batch 3000, loss[loss=0.1712, simple_loss=0.2684, pruned_loss=0.03704, over 7411.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2593, pruned_loss=0.04071, over 1428255.26 frames.], batch size: 21, lr: 4.82e-04
+2022-05-14 19:13:40,838 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 19:13:48,992 INFO [train.py:841] (1/8) Epoch 16, validation: loss=0.1537, simple_loss=0.2535, pruned_loss=0.02695, over 698248.00 frames.
+2022-05-14 19:14:47,140 INFO [train.py:812] (1/8) Epoch 16, batch 3050, loss[loss=0.157, simple_loss=0.2369, pruned_loss=0.03859, over 7421.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2596, pruned_loss=0.04132, over 1426031.69 frames.], batch size: 18, lr: 4.82e-04
+2022-05-14 19:15:46,673 INFO [train.py:812] (1/8) Epoch 16, batch 3100, loss[loss=0.1942, simple_loss=0.2694, pruned_loss=0.05953, over 7206.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2589, pruned_loss=0.04091, over 1426128.97 frames.], batch size: 23, lr: 4.81e-04
+2022-05-14 19:16:44,971 INFO [train.py:812] (1/8) Epoch 16, batch 3150, loss[loss=0.1626, simple_loss=0.247, pruned_loss=0.03913, over 7158.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2585, pruned_loss=0.04055, over 1424376.69 frames.], batch size: 18, lr: 4.81e-04
+2022-05-14 19:17:47,859 INFO [train.py:812] (1/8) Epoch 16, batch 3200, loss[loss=0.2014, simple_loss=0.2901, pruned_loss=0.05639, over 7289.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2599, pruned_loss=0.04092, over 1424426.03 frames.], batch size: 24, lr: 4.81e-04
+2022-05-14 19:18:47,168 INFO [train.py:812] (1/8) Epoch 16, batch 3250, loss[loss=0.1607, simple_loss=0.2561, pruned_loss=0.03271, over 7327.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2577, pruned_loss=0.03973, over 1425477.66 frames.], batch size: 21, lr: 4.81e-04
+2022-05-14 19:19:45,417 INFO [train.py:812] (1/8) Epoch 16, batch 3300, loss[loss=0.1918, simple_loss=0.2893, pruned_loss=0.04717, over 7343.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2578, pruned_loss=0.0392, over 1429472.49 frames.], batch size: 25, lr: 4.81e-04
+2022-05-14 19:20:42,558 INFO [train.py:812] (1/8) Epoch 16, batch 3350, loss[loss=0.1578, simple_loss=0.2506, pruned_loss=0.03257, over 7235.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2576, pruned_loss=0.03893, over 1431939.98 frames.], batch size: 20, lr: 4.81e-04
+2022-05-14 19:21:41,189 INFO [train.py:812] (1/8) Epoch 16, batch 3400, loss[loss=0.1591, simple_loss=0.2518, pruned_loss=0.0332, over 7082.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2581, pruned_loss=0.03924, over 1429127.42 frames.], batch size: 28, lr: 4.80e-04
+2022-05-14 19:22:40,327 INFO [train.py:812] (1/8) Epoch 16, batch 3450, loss[loss=0.1606, simple_loss=0.2585, pruned_loss=0.03133, over 7360.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2578, pruned_loss=0.03944, over 1430522.94 frames.], batch size: 19, lr: 4.80e-04
+2022-05-14 19:23:40,274 INFO [train.py:812] (1/8) Epoch 16, batch 3500, loss[loss=0.1593, simple_loss=0.2576, pruned_loss=0.03057, over 7317.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2581, pruned_loss=0.0397, over 1428416.81 frames.], batch size: 21, lr: 4.80e-04
+2022-05-14 19:24:39,221 INFO [train.py:812] (1/8) Epoch 16, batch 3550, loss[loss=0.1839, simple_loss=0.2736, pruned_loss=0.04704, over 7162.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2583, pruned_loss=0.0397, over 1424723.50 frames.], batch size: 26, lr: 4.80e-04
+2022-05-14 19:25:38,816 INFO [train.py:812] (1/8) Epoch 16, batch 3600, loss[loss=0.1714, simple_loss=0.2765, pruned_loss=0.03317, over 7332.00 frames.], tot_loss[loss=0.168, simple_loss=0.2577, pruned_loss=0.03914, over 1426488.31 frames.], batch size: 21, lr: 4.80e-04
+2022-05-14 19:26:37,926 INFO [train.py:812] (1/8) Epoch 16, batch 3650, loss[loss=0.1541, simple_loss=0.2376, pruned_loss=0.03525, over 7289.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2581, pruned_loss=0.0393, over 1426101.76 frames.], batch size: 18, lr: 4.80e-04
+2022-05-14 19:27:36,132 INFO [train.py:812] (1/8) Epoch 16, batch 3700, loss[loss=0.1335, simple_loss=0.2159, pruned_loss=0.02553, over 6810.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2575, pruned_loss=0.03917, over 1424107.12 frames.], batch size: 15, lr: 4.79e-04
+2022-05-14 19:28:35,316 INFO [train.py:812] (1/8) Epoch 16, batch 3750, loss[loss=0.1795, simple_loss=0.2831, pruned_loss=0.03792, over 7290.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2571, pruned_loss=0.03932, over 1422096.56 frames.], batch size: 25, lr: 4.79e-04
+2022-05-14 19:29:33,342 INFO [train.py:812] (1/8) Epoch 16, batch 3800, loss[loss=0.1643, simple_loss=0.2413, pruned_loss=0.0436, over 7134.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2572, pruned_loss=0.03933, over 1425981.91 frames.], batch size: 17, lr: 4.79e-04
+2022-05-14 19:30:31,488 INFO [train.py:812] (1/8) Epoch 16, batch 3850, loss[loss=0.143, simple_loss=0.2311, pruned_loss=0.0274, over 7295.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2573, pruned_loss=0.03943, over 1421594.74 frames.], batch size: 18, lr: 4.79e-04
+2022-05-14 19:31:29,703 INFO [train.py:812] (1/8) Epoch 16, batch 3900, loss[loss=0.1604, simple_loss=0.2564, pruned_loss=0.03222, over 7226.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2574, pruned_loss=0.03961, over 1423326.22 frames.], batch size: 21, lr: 4.79e-04
+2022-05-14 19:32:28,909 INFO [train.py:812] (1/8) Epoch 16, batch 3950, loss[loss=0.1654, simple_loss=0.2524, pruned_loss=0.03919, over 7234.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2575, pruned_loss=0.03983, over 1422758.79 frames.], batch size: 20, lr: 4.79e-04
+2022-05-14 19:33:27,634 INFO [train.py:812] (1/8) Epoch 16, batch 4000, loss[loss=0.155, simple_loss=0.257, pruned_loss=0.02649, over 7311.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2574, pruned_loss=0.03937, over 1420190.61 frames.], batch size: 21, lr: 4.79e-04
+2022-05-14 19:34:27,167 INFO [train.py:812] (1/8) Epoch 16, batch 4050, loss[loss=0.1579, simple_loss=0.2514, pruned_loss=0.03226, over 7161.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2574, pruned_loss=0.03959, over 1418649.65 frames.], batch size: 18, lr: 4.78e-04
+2022-05-14 19:35:27,342 INFO [train.py:812] (1/8) Epoch 16, batch 4100, loss[loss=0.1512, simple_loss=0.238, pruned_loss=0.03223, over 7168.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2561, pruned_loss=0.0388, over 1424429.06 frames.], batch size: 18, lr: 4.78e-04
+2022-05-14 19:36:26,213 INFO [train.py:812] (1/8) Epoch 16, batch 4150, loss[loss=0.1602, simple_loss=0.2523, pruned_loss=0.03403, over 7018.00 frames.], tot_loss[loss=0.1667, simple_loss=0.256, pruned_loss=0.03868, over 1418709.28 frames.], batch size: 28, lr: 4.78e-04
+2022-05-14 19:37:25,122 INFO [train.py:812] (1/8) Epoch 16, batch 4200, loss[loss=0.1569, simple_loss=0.2408, pruned_loss=0.03648, over 7024.00 frames.], tot_loss[loss=0.1667, simple_loss=0.256, pruned_loss=0.03866, over 1418259.77 frames.], batch size: 16, lr: 4.78e-04
+2022-05-14 19:38:24,443 INFO [train.py:812] (1/8) Epoch 16, batch 4250, loss[loss=0.1906, simple_loss=0.2603, pruned_loss=0.06042, over 7172.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2556, pruned_loss=0.03904, over 1416318.94 frames.], batch size: 18, lr: 4.78e-04
+2022-05-14 19:39:23,838 INFO [train.py:812] (1/8) Epoch 16, batch 4300, loss[loss=0.1748, simple_loss=0.266, pruned_loss=0.04178, over 6740.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2557, pruned_loss=0.039, over 1411701.10 frames.], batch size: 31, lr: 4.78e-04
+2022-05-14 19:40:22,730 INFO [train.py:812] (1/8) Epoch 16, batch 4350, loss[loss=0.1653, simple_loss=0.2536, pruned_loss=0.03846, over 7169.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2557, pruned_loss=0.03885, over 1415311.64 frames.], batch size: 18, lr: 4.77e-04
+2022-05-14 19:41:21,973 INFO [train.py:812] (1/8) Epoch 16, batch 4400, loss[loss=0.1626, simple_loss=0.2566, pruned_loss=0.03429, over 7110.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2559, pruned_loss=0.03878, over 1415926.50 frames.], batch size: 21, lr: 4.77e-04
+2022-05-14 19:42:18,617 INFO [train.py:812] (1/8) Epoch 16, batch 4450, loss[loss=0.1502, simple_loss=0.242, pruned_loss=0.02917, over 7205.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2564, pruned_loss=0.03925, over 1410520.92 frames.], batch size: 22, lr: 4.77e-04
+2022-05-14 19:43:16,031 INFO [train.py:812] (1/8) Epoch 16, batch 4500, loss[loss=0.1391, simple_loss=0.2227, pruned_loss=0.02772, over 7135.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2568, pruned_loss=0.03938, over 1400457.30 frames.], batch size: 17, lr: 4.77e-04
+2022-05-14 19:44:12,836 INFO [train.py:812] (1/8) Epoch 16, batch 4550, loss[loss=0.1822, simple_loss=0.2659, pruned_loss=0.0493, over 5214.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2595, pruned_loss=0.04113, over 1350652.22 frames.], batch size: 52, lr: 4.77e-04
+2022-05-14 19:45:27,026 INFO [train.py:812] (1/8) Epoch 17, batch 0, loss[loss=0.1782, simple_loss=0.2703, pruned_loss=0.04306, over 7118.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2703, pruned_loss=0.04306, over 7118.00 frames.], batch size: 21, lr: 4.63e-04
+2022-05-14 19:46:26,100 INFO [train.py:812] (1/8) Epoch 17, batch 50, loss[loss=0.1777, simple_loss=0.2659, pruned_loss=0.04471, over 7341.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2643, pruned_loss=0.04266, over 316901.34 frames.], batch size: 21, lr: 4.63e-04
+2022-05-14 19:47:25,014 INFO [train.py:812] (1/8) Epoch 17, batch 100, loss[loss=0.1786, simple_loss=0.2712, pruned_loss=0.04301, over 7143.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2594, pruned_loss=0.04093, over 559004.34 frames.], batch size: 20, lr: 4.63e-04
+2022-05-14 19:48:23,528 INFO [train.py:812] (1/8) Epoch 17, batch 150, loss[loss=0.1505, simple_loss=0.2303, pruned_loss=0.03536, over 6985.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2572, pruned_loss=0.03933, over 746989.87 frames.], batch size: 16, lr: 4.63e-04
+2022-05-14 19:49:23,002 INFO [train.py:812] (1/8) Epoch 17, batch 200, loss[loss=0.1308, simple_loss=0.2179, pruned_loss=0.02182, over 7143.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2579, pruned_loss=0.03927, over 896413.40 frames.], batch size: 17, lr: 4.63e-04
+2022-05-14 19:50:21,369 INFO [train.py:812] (1/8) Epoch 17, batch 250, loss[loss=0.1569, simple_loss=0.2447, pruned_loss=0.03459, over 7255.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2579, pruned_loss=0.03938, over 1016267.56 frames.], batch size: 19, lr: 4.63e-04
+2022-05-14 19:51:20,293 INFO [train.py:812] (1/8) Epoch 17, batch 300, loss[loss=0.1493, simple_loss=0.2381, pruned_loss=0.03021, over 7055.00 frames.], tot_loss[loss=0.169, simple_loss=0.2587, pruned_loss=0.03966, over 1101978.76 frames.], batch size: 18, lr: 4.62e-04
+2022-05-14 19:52:19,506 INFO [train.py:812] (1/8) Epoch 17, batch 350, loss[loss=0.1561, simple_loss=0.2469, pruned_loss=0.03267, over 6774.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2572, pruned_loss=0.0391, over 1172050.70 frames.], batch size: 15, lr: 4.62e-04
+2022-05-14 19:53:18,627 INFO [train.py:812] (1/8) Epoch 17, batch 400, loss[loss=0.2, simple_loss=0.28, pruned_loss=0.06003, over 4976.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2575, pruned_loss=0.03947, over 1227642.14 frames.], batch size: 53, lr: 4.62e-04
+2022-05-14 19:54:16,195 INFO [train.py:812] (1/8) Epoch 17, batch 450, loss[loss=0.1879, simple_loss=0.2682, pruned_loss=0.05383, over 7348.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2579, pruned_loss=0.03988, over 1268868.94 frames.], batch size: 19, lr: 4.62e-04
+2022-05-14 19:55:14,836 INFO [train.py:812] (1/8) Epoch 17, batch 500, loss[loss=0.1596, simple_loss=0.2478, pruned_loss=0.03567, over 7165.00 frames.], tot_loss[loss=0.1679, simple_loss=0.257, pruned_loss=0.03944, over 1301581.48 frames.], batch size: 18, lr: 4.62e-04
+2022-05-14 19:56:13,697 INFO [train.py:812] (1/8) Epoch 17, batch 550, loss[loss=0.1498, simple_loss=0.2366, pruned_loss=0.03147, over 7120.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2565, pruned_loss=0.03943, over 1327295.52 frames.], batch size: 17, lr: 4.62e-04
+2022-05-14 19:57:12,587 INFO [train.py:812] (1/8) Epoch 17, batch 600, loss[loss=0.1564, simple_loss=0.2497, pruned_loss=0.03157, over 7013.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2574, pruned_loss=0.04037, over 1342678.03 frames.], batch size: 28, lr: 4.62e-04
+2022-05-14 19:58:11,561 INFO [train.py:812] (1/8) Epoch 17, batch 650, loss[loss=0.172, simple_loss=0.2543, pruned_loss=0.04485, over 7337.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2575, pruned_loss=0.04046, over 1360942.30 frames.], batch size: 20, lr: 4.61e-04
+2022-05-14 19:59:10,285 INFO [train.py:812] (1/8) Epoch 17, batch 700, loss[loss=0.1489, simple_loss=0.2328, pruned_loss=0.03246, over 7253.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2578, pruned_loss=0.0403, over 1367671.35 frames.], batch size: 19, lr: 4.61e-04
+2022-05-14 20:00:09,348 INFO [train.py:812] (1/8) Epoch 17, batch 750, loss[loss=0.1416, simple_loss=0.241, pruned_loss=0.02106, over 7151.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2575, pruned_loss=0.03985, over 1376609.14 frames.], batch size: 20, lr: 4.61e-04
+2022-05-14 20:01:08,203 INFO [train.py:812] (1/8) Epoch 17, batch 800, loss[loss=0.1632, simple_loss=0.2578, pruned_loss=0.03427, over 7158.00 frames.], tot_loss[loss=0.1688, simple_loss=0.258, pruned_loss=0.03979, over 1387567.42 frames.], batch size: 19, lr: 4.61e-04
+2022-05-14 20:02:07,162 INFO [train.py:812] (1/8) Epoch 17, batch 850, loss[loss=0.1786, simple_loss=0.2731, pruned_loss=0.04201, over 6215.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2572, pruned_loss=0.03994, over 1395734.13 frames.], batch size: 37, lr: 4.61e-04
+2022-05-14 20:03:05,137 INFO [train.py:812] (1/8) Epoch 17, batch 900, loss[loss=0.1575, simple_loss=0.2502, pruned_loss=0.03244, over 7329.00 frames.], tot_loss[loss=0.168, simple_loss=0.257, pruned_loss=0.03953, over 1407696.05 frames.], batch size: 20, lr: 4.61e-04
+2022-05-14 20:04:03,147 INFO [train.py:812] (1/8) Epoch 17, batch 950, loss[loss=0.1575, simple_loss=0.239, pruned_loss=0.03793, over 7139.00 frames.], tot_loss[loss=0.167, simple_loss=0.256, pruned_loss=0.03897, over 1412509.87 frames.], batch size: 17, lr: 4.60e-04
+2022-05-14 20:05:01,747 INFO [train.py:812] (1/8) Epoch 17, batch 1000, loss[loss=0.1548, simple_loss=0.2464, pruned_loss=0.03166, over 7123.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2557, pruned_loss=0.03857, over 1417467.70 frames.], batch size: 21, lr: 4.60e-04
+2022-05-14 20:06:00,351 INFO [train.py:812] (1/8) Epoch 17, batch 1050, loss[loss=0.1768, simple_loss=0.2851, pruned_loss=0.03426, over 7341.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2548, pruned_loss=0.03839, over 1421709.39 frames.], batch size: 22, lr: 4.60e-04
+2022-05-14 20:06:59,568 INFO [train.py:812] (1/8) Epoch 17, batch 1100, loss[loss=0.1685, simple_loss=0.2569, pruned_loss=0.04009, over 7290.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2554, pruned_loss=0.03874, over 1422543.44 frames.], batch size: 24, lr: 4.60e-04
+2022-05-14 20:07:58,276 INFO [train.py:812] (1/8) Epoch 17, batch 1150, loss[loss=0.1587, simple_loss=0.2491, pruned_loss=0.03418, over 7254.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2556, pruned_loss=0.03833, over 1423308.78 frames.], batch size: 24, lr: 4.60e-04
+2022-05-14 20:08:57,631 INFO [train.py:812] (1/8) Epoch 17, batch 1200, loss[loss=0.2042, simple_loss=0.2999, pruned_loss=0.05424, over 7286.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2559, pruned_loss=0.03884, over 1419822.01 frames.], batch size: 25, lr: 4.60e-04
+2022-05-14 20:09:55,621 INFO [train.py:812] (1/8) Epoch 17, batch 1250, loss[loss=0.1868, simple_loss=0.2513, pruned_loss=0.06117, over 7301.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2568, pruned_loss=0.03934, over 1415320.36 frames.], batch size: 18, lr: 4.60e-04
+2022-05-14 20:10:53,527 INFO [train.py:812] (1/8) Epoch 17, batch 1300, loss[loss=0.167, simple_loss=0.2635, pruned_loss=0.03522, over 7348.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2564, pruned_loss=0.03919, over 1413231.42 frames.], batch size: 22, lr: 4.59e-04
+2022-05-14 20:11:51,653 INFO [train.py:812] (1/8) Epoch 17, batch 1350, loss[loss=0.1561, simple_loss=0.2446, pruned_loss=0.03382, over 6999.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2567, pruned_loss=0.03918, over 1418485.04 frames.], batch size: 16, lr: 4.59e-04
+2022-05-14 20:12:51,097 INFO [train.py:812] (1/8) Epoch 17, batch 1400, loss[loss=0.1798, simple_loss=0.2742, pruned_loss=0.04271, over 7138.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2558, pruned_loss=0.03903, over 1419200.63 frames.], batch size: 20, lr: 4.59e-04
+2022-05-14 20:13:49,593 INFO [train.py:812] (1/8) Epoch 17, batch 1450, loss[loss=0.174, simple_loss=0.27, pruned_loss=0.03903, over 7346.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2566, pruned_loss=0.0393, over 1418615.23 frames.], batch size: 22, lr: 4.59e-04
+2022-05-14 20:14:48,946 INFO [train.py:812] (1/8) Epoch 17, batch 1500, loss[loss=0.1573, simple_loss=0.2456, pruned_loss=0.0345, over 7264.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2558, pruned_loss=0.03906, over 1424382.71 frames.], batch size: 19, lr: 4.59e-04
+2022-05-14 20:15:57,355 INFO [train.py:812] (1/8) Epoch 17, batch 1550, loss[loss=0.1642, simple_loss=0.2565, pruned_loss=0.03593, over 7212.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2557, pruned_loss=0.03926, over 1422589.15 frames.], batch size: 21, lr: 4.59e-04
+2022-05-14 20:16:56,750 INFO [train.py:812] (1/8) Epoch 17, batch 1600, loss[loss=0.1767, simple_loss=0.2583, pruned_loss=0.04759, over 7416.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2552, pruned_loss=0.03877, over 1427165.77 frames.], batch size: 20, lr: 4.58e-04
+2022-05-14 20:17:55,348 INFO [train.py:812] (1/8) Epoch 17, batch 1650, loss[loss=0.1955, simple_loss=0.2832, pruned_loss=0.05393, over 7413.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2558, pruned_loss=0.03896, over 1429091.99 frames.], batch size: 21, lr: 4.58e-04
+2022-05-14 20:18:53,695 INFO [train.py:812] (1/8) Epoch 17, batch 1700, loss[loss=0.2216, simple_loss=0.2903, pruned_loss=0.07648, over 4596.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2569, pruned_loss=0.03937, over 1422805.68 frames.], batch size: 52, lr: 4.58e-04
+2022-05-14 20:19:52,407 INFO [train.py:812] (1/8) Epoch 17, batch 1750, loss[loss=0.1841, simple_loss=0.2732, pruned_loss=0.04753, over 7376.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2573, pruned_loss=0.0392, over 1414455.69 frames.], batch size: 23, lr: 4.58e-04
+2022-05-14 20:20:51,548 INFO [train.py:812] (1/8) Epoch 17, batch 1800, loss[loss=0.1791, simple_loss=0.265, pruned_loss=0.04663, over 7203.00 frames.], tot_loss[loss=0.1674, simple_loss=0.257, pruned_loss=0.03886, over 1415924.41 frames.], batch size: 23, lr: 4.58e-04
+2022-05-14 20:21:48,759 INFO [train.py:812] (1/8) Epoch 17, batch 1850, loss[loss=0.18, simple_loss=0.2773, pruned_loss=0.04133, over 6261.00 frames.], tot_loss[loss=0.1674, simple_loss=0.257, pruned_loss=0.03893, over 1416621.91 frames.], batch size: 37, lr: 4.58e-04
+2022-05-14 20:22:47,370 INFO [train.py:812] (1/8) Epoch 17, batch 1900, loss[loss=0.1608, simple_loss=0.2463, pruned_loss=0.03765, over 7421.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2572, pruned_loss=0.03921, over 1420865.75 frames.], batch size: 20, lr: 4.58e-04
+2022-05-14 20:23:46,069 INFO [train.py:812] (1/8) Epoch 17, batch 1950, loss[loss=0.1789, simple_loss=0.2683, pruned_loss=0.04471, over 7325.00 frames.], tot_loss[loss=0.168, simple_loss=0.2571, pruned_loss=0.03941, over 1423210.65 frames.], batch size: 21, lr: 4.57e-04
+2022-05-14 20:24:44,619 INFO [train.py:812] (1/8) Epoch 17, batch 2000, loss[loss=0.1456, simple_loss=0.2395, pruned_loss=0.02588, over 7259.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2569, pruned_loss=0.03892, over 1424703.87 frames.], batch size: 19, lr: 4.57e-04
+2022-05-14 20:25:43,657 INFO [train.py:812] (1/8) Epoch 17, batch 2050, loss[loss=0.1733, simple_loss=0.2509, pruned_loss=0.04784, over 7410.00 frames.], tot_loss[loss=0.167, simple_loss=0.2559, pruned_loss=0.03906, over 1428247.83 frames.], batch size: 18, lr: 4.57e-04
+2022-05-14 20:26:43,363 INFO [train.py:812] (1/8) Epoch 17, batch 2100, loss[loss=0.1862, simple_loss=0.2795, pruned_loss=0.04648, over 7413.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2558, pruned_loss=0.03836, over 1428318.26 frames.], batch size: 21, lr: 4.57e-04
+2022-05-14 20:27:42,662 INFO [train.py:812] (1/8) Epoch 17, batch 2150, loss[loss=0.1704, simple_loss=0.2517, pruned_loss=0.04454, over 7340.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2565, pruned_loss=0.03892, over 1424549.72 frames.], batch size: 19, lr: 4.57e-04
+2022-05-14 20:28:40,068 INFO [train.py:812] (1/8) Epoch 17, batch 2200, loss[loss=0.1463, simple_loss=0.2445, pruned_loss=0.024, over 7325.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2561, pruned_loss=0.03832, over 1421916.41 frames.], batch size: 22, lr: 4.57e-04
+2022-05-14 20:29:39,214 INFO [train.py:812] (1/8) Epoch 17, batch 2250, loss[loss=0.1563, simple_loss=0.2434, pruned_loss=0.03465, over 7406.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2565, pruned_loss=0.03846, over 1424502.08 frames.], batch size: 21, lr: 4.56e-04
+2022-05-14 20:30:37,973 INFO [train.py:812] (1/8) Epoch 17, batch 2300, loss[loss=0.189, simple_loss=0.2848, pruned_loss=0.04662, over 7298.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2564, pruned_loss=0.03855, over 1423244.20 frames.], batch size: 24, lr: 4.56e-04
+2022-05-14 20:31:36,710 INFO [train.py:812] (1/8) Epoch 17, batch 2350, loss[loss=0.1656, simple_loss=0.2588, pruned_loss=0.03617, over 7387.00 frames.], tot_loss[loss=0.166, simple_loss=0.2554, pruned_loss=0.03832, over 1426969.99 frames.], batch size: 23, lr: 4.56e-04
+2022-05-14 20:32:36,100 INFO [train.py:812] (1/8) Epoch 17, batch 2400, loss[loss=0.1459, simple_loss=0.2318, pruned_loss=0.03003, over 7011.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2556, pruned_loss=0.03865, over 1424525.85 frames.], batch size: 16, lr: 4.56e-04
+2022-05-14 20:33:34,530 INFO [train.py:812] (1/8) Epoch 17, batch 2450, loss[loss=0.1537, simple_loss=0.2484, pruned_loss=0.02949, over 7335.00 frames.], tot_loss[loss=0.166, simple_loss=0.255, pruned_loss=0.03846, over 1424094.02 frames.], batch size: 22, lr: 4.56e-04
+2022-05-14 20:34:34,264 INFO [train.py:812] (1/8) Epoch 17, batch 2500, loss[loss=0.1604, simple_loss=0.2551, pruned_loss=0.03283, over 7221.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2547, pruned_loss=0.0385, over 1424146.12 frames.], batch size: 21, lr: 4.56e-04
+2022-05-14 20:35:31,564 INFO [train.py:812] (1/8) Epoch 17, batch 2550, loss[loss=0.1765, simple_loss=0.2716, pruned_loss=0.04065, over 7212.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2542, pruned_loss=0.03827, over 1419320.98 frames.], batch size: 21, lr: 4.56e-04
+2022-05-14 20:36:37,553 INFO [train.py:812] (1/8) Epoch 17, batch 2600, loss[loss=0.1575, simple_loss=0.2555, pruned_loss=0.02979, over 7074.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2562, pruned_loss=0.03902, over 1421577.70 frames.], batch size: 28, lr: 4.55e-04
+2022-05-14 20:37:36,702 INFO [train.py:812] (1/8) Epoch 17, batch 2650, loss[loss=0.1932, simple_loss=0.2753, pruned_loss=0.05551, over 7348.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2564, pruned_loss=0.03904, over 1419883.64 frames.], batch size: 19, lr: 4.55e-04
+2022-05-14 20:38:34,782 INFO [train.py:812] (1/8) Epoch 17, batch 2700, loss[loss=0.1666, simple_loss=0.269, pruned_loss=0.03213, over 7331.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2558, pruned_loss=0.03862, over 1423533.99 frames.], batch size: 22, lr: 4.55e-04
+2022-05-14 20:39:32,811 INFO [train.py:812] (1/8) Epoch 17, batch 2750, loss[loss=0.1652, simple_loss=0.2658, pruned_loss=0.0323, over 7163.00 frames.], tot_loss[loss=0.1668, simple_loss=0.256, pruned_loss=0.03877, over 1422953.49 frames.], batch size: 19, lr: 4.55e-04
+2022-05-14 20:40:31,886 INFO [train.py:812] (1/8) Epoch 17, batch 2800, loss[loss=0.1773, simple_loss=0.2697, pruned_loss=0.04247, over 5220.00 frames.], tot_loss[loss=0.166, simple_loss=0.2553, pruned_loss=0.03837, over 1421881.08 frames.], batch size: 52, lr: 4.55e-04
+2022-05-14 20:41:30,551 INFO [train.py:812] (1/8) Epoch 17, batch 2850, loss[loss=0.1668, simple_loss=0.2562, pruned_loss=0.03873, over 7317.00 frames.], tot_loss[loss=0.166, simple_loss=0.2556, pruned_loss=0.03823, over 1422256.11 frames.], batch size: 21, lr: 4.55e-04
+2022-05-14 20:42:28,894 INFO [train.py:812] (1/8) Epoch 17, batch 2900, loss[loss=0.1655, simple_loss=0.2632, pruned_loss=0.03386, over 7232.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2555, pruned_loss=0.03855, over 1419103.70 frames.], batch size: 20, lr: 4.55e-04
+2022-05-14 20:43:27,758 INFO [train.py:812] (1/8) Epoch 17, batch 2950, loss[loss=0.1463, simple_loss=0.2348, pruned_loss=0.02895, over 7285.00 frames.], tot_loss[loss=0.167, simple_loss=0.2564, pruned_loss=0.0388, over 1419279.82 frames.], batch size: 18, lr: 4.54e-04
+2022-05-14 20:44:36,162 INFO [train.py:812] (1/8) Epoch 17, batch 3000, loss[loss=0.1561, simple_loss=0.246, pruned_loss=0.03313, over 7143.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2567, pruned_loss=0.03856, over 1424058.39 frames.], batch size: 20, lr: 4.54e-04
+2022-05-14 20:44:36,163 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 20:44:43,901 INFO [train.py:841] (1/8) Epoch 17, validation: loss=0.1538, simple_loss=0.2534, pruned_loss=0.02708, over 698248.00 frames.
+2022-05-14 20:45:42,777 INFO [train.py:812] (1/8) Epoch 17, batch 3050, loss[loss=0.1662, simple_loss=0.2665, pruned_loss=0.03294, over 6463.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2563, pruned_loss=0.03841, over 1423403.13 frames.], batch size: 38, lr: 4.54e-04
+2022-05-14 20:46:41,072 INFO [train.py:812] (1/8) Epoch 17, batch 3100, loss[loss=0.1645, simple_loss=0.2585, pruned_loss=0.03528, over 7319.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2574, pruned_loss=0.039, over 1419821.53 frames.], batch size: 25, lr: 4.54e-04
+2022-05-14 20:47:58,627 INFO [train.py:812] (1/8) Epoch 17, batch 3150, loss[loss=0.1457, simple_loss=0.2382, pruned_loss=0.0266, over 7339.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2574, pruned_loss=0.03943, over 1418266.02 frames.], batch size: 20, lr: 4.54e-04
+2022-05-14 20:49:07,272 INFO [train.py:812] (1/8) Epoch 17, batch 3200, loss[loss=0.175, simple_loss=0.2542, pruned_loss=0.04795, over 7366.00 frames.], tot_loss[loss=0.1687, simple_loss=0.258, pruned_loss=0.03976, over 1418264.89 frames.], batch size: 19, lr: 4.54e-04
+2022-05-14 20:50:25,524 INFO [train.py:812] (1/8) Epoch 17, batch 3250, loss[loss=0.1557, simple_loss=0.2467, pruned_loss=0.03232, over 7062.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2567, pruned_loss=0.0391, over 1423563.70 frames.], batch size: 18, lr: 4.54e-04
+2022-05-14 20:51:34,395 INFO [train.py:812] (1/8) Epoch 17, batch 3300, loss[loss=0.1984, simple_loss=0.2982, pruned_loss=0.04934, over 7171.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2571, pruned_loss=0.03921, over 1424473.20 frames.], batch size: 19, lr: 4.53e-04
+2022-05-14 20:52:33,319 INFO [train.py:812] (1/8) Epoch 17, batch 3350, loss[loss=0.1573, simple_loss=0.2566, pruned_loss=0.02906, over 7350.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2573, pruned_loss=0.03906, over 1425582.86 frames.], batch size: 22, lr: 4.53e-04
+2022-05-14 20:53:32,421 INFO [train.py:812] (1/8) Epoch 17, batch 3400, loss[loss=0.1692, simple_loss=0.2676, pruned_loss=0.03539, over 7151.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2569, pruned_loss=0.0391, over 1423549.16 frames.], batch size: 20, lr: 4.53e-04
+2022-05-14 20:54:31,686 INFO [train.py:812] (1/8) Epoch 17, batch 3450, loss[loss=0.1917, simple_loss=0.2677, pruned_loss=0.0579, over 7322.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2557, pruned_loss=0.03906, over 1424674.27 frames.], batch size: 20, lr: 4.53e-04
+2022-05-14 20:55:30,345 INFO [train.py:812] (1/8) Epoch 17, batch 3500, loss[loss=0.1643, simple_loss=0.2551, pruned_loss=0.03678, over 7200.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2552, pruned_loss=0.03851, over 1423993.51 frames.], batch size: 22, lr: 4.53e-04
+2022-05-14 20:56:29,297 INFO [train.py:812] (1/8) Epoch 17, batch 3550, loss[loss=0.1573, simple_loss=0.2545, pruned_loss=0.0301, over 7112.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2558, pruned_loss=0.03848, over 1426286.64 frames.], batch size: 21, lr: 4.53e-04
+2022-05-14 20:57:28,817 INFO [train.py:812] (1/8) Epoch 17, batch 3600, loss[loss=0.1538, simple_loss=0.2384, pruned_loss=0.03456, over 7286.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2564, pruned_loss=0.03842, over 1427499.73 frames.], batch size: 18, lr: 4.52e-04
+2022-05-14 20:58:27,777 INFO [train.py:812] (1/8) Epoch 17, batch 3650, loss[loss=0.154, simple_loss=0.2494, pruned_loss=0.0293, over 7314.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2552, pruned_loss=0.03798, over 1431100.40 frames.], batch size: 21, lr: 4.52e-04
+2022-05-14 20:59:27,701 INFO [train.py:812] (1/8) Epoch 17, batch 3700, loss[loss=0.171, simple_loss=0.2684, pruned_loss=0.03682, over 7141.00 frames.], tot_loss[loss=0.1658, simple_loss=0.255, pruned_loss=0.03826, over 1431033.83 frames.], batch size: 20, lr: 4.52e-04
+2022-05-14 21:00:26,360 INFO [train.py:812] (1/8) Epoch 17, batch 3750, loss[loss=0.1737, simple_loss=0.2683, pruned_loss=0.0396, over 6334.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2553, pruned_loss=0.03868, over 1427574.41 frames.], batch size: 37, lr: 4.52e-04
+2022-05-14 21:01:24,374 INFO [train.py:812] (1/8) Epoch 17, batch 3800, loss[loss=0.1637, simple_loss=0.2662, pruned_loss=0.03065, over 6464.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2555, pruned_loss=0.03853, over 1426157.36 frames.], batch size: 37, lr: 4.52e-04
+2022-05-14 21:02:23,090 INFO [train.py:812] (1/8) Epoch 17, batch 3850, loss[loss=0.1457, simple_loss=0.2251, pruned_loss=0.03313, over 6996.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2556, pruned_loss=0.03854, over 1425951.50 frames.], batch size: 16, lr: 4.52e-04
+2022-05-14 21:03:22,488 INFO [train.py:812] (1/8) Epoch 17, batch 3900, loss[loss=0.1667, simple_loss=0.2533, pruned_loss=0.04002, over 7202.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2544, pruned_loss=0.03826, over 1428116.17 frames.], batch size: 22, lr: 4.52e-04
+2022-05-14 21:04:21,492 INFO [train.py:812] (1/8) Epoch 17, batch 3950, loss[loss=0.1742, simple_loss=0.2652, pruned_loss=0.04156, over 7206.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2559, pruned_loss=0.03847, over 1428664.48 frames.], batch size: 23, lr: 4.51e-04
+2022-05-14 21:05:20,844 INFO [train.py:812] (1/8) Epoch 17, batch 4000, loss[loss=0.1603, simple_loss=0.2536, pruned_loss=0.03353, over 7273.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2556, pruned_loss=0.03868, over 1429119.08 frames.], batch size: 18, lr: 4.51e-04
+2022-05-14 21:06:19,931 INFO [train.py:812] (1/8) Epoch 17, batch 4050, loss[loss=0.1506, simple_loss=0.246, pruned_loss=0.02766, over 6713.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2551, pruned_loss=0.0383, over 1424989.82 frames.], batch size: 31, lr: 4.51e-04
+2022-05-14 21:07:19,005 INFO [train.py:812] (1/8) Epoch 17, batch 4100, loss[loss=0.1688, simple_loss=0.2609, pruned_loss=0.0383, over 6505.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2563, pruned_loss=0.0385, over 1423779.30 frames.], batch size: 38, lr: 4.51e-04
+2022-05-14 21:08:18,270 INFO [train.py:812] (1/8) Epoch 17, batch 4150, loss[loss=0.1339, simple_loss=0.2202, pruned_loss=0.02383, over 7131.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2552, pruned_loss=0.03811, over 1422609.26 frames.], batch size: 17, lr: 4.51e-04
+2022-05-14 21:09:17,054 INFO [train.py:812] (1/8) Epoch 17, batch 4200, loss[loss=0.1563, simple_loss=0.2482, pruned_loss=0.03222, over 7164.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2556, pruned_loss=0.03842, over 1422188.42 frames.], batch size: 26, lr: 4.51e-04
+2022-05-14 21:10:16,220 INFO [train.py:812] (1/8) Epoch 17, batch 4250, loss[loss=0.1522, simple_loss=0.2435, pruned_loss=0.03048, over 7301.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2563, pruned_loss=0.03857, over 1423057.75 frames.], batch size: 18, lr: 4.51e-04
+2022-05-14 21:11:15,270 INFO [train.py:812] (1/8) Epoch 17, batch 4300, loss[loss=0.16, simple_loss=0.255, pruned_loss=0.03251, over 7069.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2555, pruned_loss=0.03852, over 1422026.20 frames.], batch size: 18, lr: 4.50e-04
+2022-05-14 21:12:14,025 INFO [train.py:812] (1/8) Epoch 17, batch 4350, loss[loss=0.1781, simple_loss=0.2499, pruned_loss=0.05311, over 7171.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2549, pruned_loss=0.03829, over 1421352.43 frames.], batch size: 18, lr: 4.50e-04
+2022-05-14 21:13:12,854 INFO [train.py:812] (1/8) Epoch 17, batch 4400, loss[loss=0.1876, simple_loss=0.2804, pruned_loss=0.04741, over 7226.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2548, pruned_loss=0.0379, over 1419607.18 frames.], batch size: 21, lr: 4.50e-04
+2022-05-14 21:14:12,279 INFO [train.py:812] (1/8) Epoch 17, batch 4450, loss[loss=0.1444, simple_loss=0.2223, pruned_loss=0.03319, over 7122.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2557, pruned_loss=0.0383, over 1415504.49 frames.], batch size: 17, lr: 4.50e-04
+2022-05-14 21:15:12,245 INFO [train.py:812] (1/8) Epoch 17, batch 4500, loss[loss=0.1539, simple_loss=0.2425, pruned_loss=0.03264, over 7246.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2548, pruned_loss=0.03808, over 1414684.19 frames.], batch size: 20, lr: 4.50e-04
+2022-05-14 21:16:11,536 INFO [train.py:812] (1/8) Epoch 17, batch 4550, loss[loss=0.1986, simple_loss=0.2777, pruned_loss=0.05972, over 5281.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2548, pruned_loss=0.03907, over 1380933.42 frames.], batch size: 52, lr: 4.50e-04
+2022-05-14 21:17:18,365 INFO [train.py:812] (1/8) Epoch 18, batch 0, loss[loss=0.1756, simple_loss=0.2604, pruned_loss=0.04541, over 7234.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2604, pruned_loss=0.04541, over 7234.00 frames.], batch size: 20, lr: 4.38e-04
+2022-05-14 21:18:18,233 INFO [train.py:812] (1/8) Epoch 18, batch 50, loss[loss=0.138, simple_loss=0.2121, pruned_loss=0.03199, over 7000.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2515, pruned_loss=0.03618, over 323385.31 frames.], batch size: 16, lr: 4.38e-04
+2022-05-14 21:19:17,371 INFO [train.py:812] (1/8) Epoch 18, batch 100, loss[loss=0.1692, simple_loss=0.2473, pruned_loss=0.04555, over 7158.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2546, pruned_loss=0.03782, over 564556.24 frames.], batch size: 18, lr: 4.37e-04
+2022-05-14 21:20:15,722 INFO [train.py:812] (1/8) Epoch 18, batch 150, loss[loss=0.1688, simple_loss=0.266, pruned_loss=0.03578, over 7139.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2551, pruned_loss=0.03838, over 751383.08 frames.], batch size: 20, lr: 4.37e-04
+2022-05-14 21:21:13,512 INFO [train.py:812] (1/8) Epoch 18, batch 200, loss[loss=0.162, simple_loss=0.2408, pruned_loss=0.04161, over 7168.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2554, pruned_loss=0.03821, over 901901.79 frames.], batch size: 18, lr: 4.37e-04
+2022-05-14 21:22:12,911 INFO [train.py:812] (1/8) Epoch 18, batch 250, loss[loss=0.1779, simple_loss=0.2651, pruned_loss=0.04535, over 6713.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2558, pruned_loss=0.03831, over 1019663.81 frames.], batch size: 31, lr: 4.37e-04
+2022-05-14 21:23:11,921 INFO [train.py:812] (1/8) Epoch 18, batch 300, loss[loss=0.1748, simple_loss=0.2651, pruned_loss=0.04229, over 7067.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2559, pruned_loss=0.03834, over 1104159.15 frames.], batch size: 28, lr: 4.37e-04
+2022-05-14 21:24:11,086 INFO [train.py:812] (1/8) Epoch 18, batch 350, loss[loss=0.1951, simple_loss=0.2805, pruned_loss=0.05488, over 7333.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2548, pruned_loss=0.03834, over 1172274.74 frames.], batch size: 22, lr: 4.37e-04
+2022-05-14 21:25:08,903 INFO [train.py:812] (1/8) Epoch 18, batch 400, loss[loss=0.1436, simple_loss=0.2338, pruned_loss=0.02673, over 6806.00 frames.], tot_loss[loss=0.1653, simple_loss=0.255, pruned_loss=0.03786, over 1232185.54 frames.], batch size: 15, lr: 4.37e-04
+2022-05-14 21:26:06,611 INFO [train.py:812] (1/8) Epoch 18, batch 450, loss[loss=0.1753, simple_loss=0.264, pruned_loss=0.04326, over 7206.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2553, pruned_loss=0.03757, over 1275597.08 frames.], batch size: 22, lr: 4.36e-04
+2022-05-14 21:27:06,224 INFO [train.py:812] (1/8) Epoch 18, batch 500, loss[loss=0.1642, simple_loss=0.258, pruned_loss=0.03521, over 7342.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2552, pruned_loss=0.03769, over 1313326.49 frames.], batch size: 22, lr: 4.36e-04
+2022-05-14 21:28:04,629 INFO [train.py:812] (1/8) Epoch 18, batch 550, loss[loss=0.1419, simple_loss=0.2311, pruned_loss=0.02631, over 7144.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2542, pruned_loss=0.03738, over 1339996.35 frames.], batch size: 17, lr: 4.36e-04
+2022-05-14 21:29:02,264 INFO [train.py:812] (1/8) Epoch 18, batch 600, loss[loss=0.1655, simple_loss=0.2585, pruned_loss=0.0363, over 6336.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2557, pruned_loss=0.03824, over 1357230.50 frames.], batch size: 37, lr: 4.36e-04
+2022-05-14 21:30:01,245 INFO [train.py:812] (1/8) Epoch 18, batch 650, loss[loss=0.1781, simple_loss=0.262, pruned_loss=0.04712, over 5030.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2557, pruned_loss=0.03822, over 1369509.23 frames.], batch size: 53, lr: 4.36e-04
+2022-05-14 21:30:59,627 INFO [train.py:812] (1/8) Epoch 18, batch 700, loss[loss=0.1695, simple_loss=0.2589, pruned_loss=0.0401, over 7307.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2545, pruned_loss=0.03784, over 1380617.53 frames.], batch size: 21, lr: 4.36e-04
+2022-05-14 21:31:59,630 INFO [train.py:812] (1/8) Epoch 18, batch 750, loss[loss=0.149, simple_loss=0.241, pruned_loss=0.02849, over 7412.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2534, pruned_loss=0.03722, over 1391342.81 frames.], batch size: 18, lr: 4.36e-04
+2022-05-14 21:32:57,576 INFO [train.py:812] (1/8) Epoch 18, batch 800, loss[loss=0.1663, simple_loss=0.2666, pruned_loss=0.03301, over 7319.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2539, pruned_loss=0.03737, over 1403114.71 frames.], batch size: 21, lr: 4.36e-04
+2022-05-14 21:33:57,265 INFO [train.py:812] (1/8) Epoch 18, batch 850, loss[loss=0.1586, simple_loss=0.2627, pruned_loss=0.02725, over 7409.00 frames.], tot_loss[loss=0.1645, simple_loss=0.254, pruned_loss=0.03748, over 1407031.37 frames.], batch size: 21, lr: 4.35e-04
+2022-05-14 21:34:56,175 INFO [train.py:812] (1/8) Epoch 18, batch 900, loss[loss=0.1568, simple_loss=0.2479, pruned_loss=0.03281, over 7178.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2558, pruned_loss=0.0384, over 1406859.99 frames.], batch size: 22, lr: 4.35e-04
+2022-05-14 21:35:54,606 INFO [train.py:812] (1/8) Epoch 18, batch 950, loss[loss=0.1657, simple_loss=0.2653, pruned_loss=0.03306, over 7269.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2558, pruned_loss=0.03854, over 1409682.51 frames.], batch size: 19, lr: 4.35e-04
+2022-05-14 21:36:52,263 INFO [train.py:812] (1/8) Epoch 18, batch 1000, loss[loss=0.1861, simple_loss=0.2805, pruned_loss=0.0458, over 7264.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2551, pruned_loss=0.03802, over 1414488.56 frames.], batch size: 24, lr: 4.35e-04
+2022-05-14 21:37:51,918 INFO [train.py:812] (1/8) Epoch 18, batch 1050, loss[loss=0.1637, simple_loss=0.2427, pruned_loss=0.04238, over 7294.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2549, pruned_loss=0.03814, over 1416545.51 frames.], batch size: 17, lr: 4.35e-04
+2022-05-14 21:38:50,485 INFO [train.py:812] (1/8) Epoch 18, batch 1100, loss[loss=0.1821, simple_loss=0.2724, pruned_loss=0.04592, over 7282.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2554, pruned_loss=0.03847, over 1420562.50 frames.], batch size: 25, lr: 4.35e-04
+2022-05-14 21:39:48,092 INFO [train.py:812] (1/8) Epoch 18, batch 1150, loss[loss=0.1685, simple_loss=0.2649, pruned_loss=0.03607, over 7378.00 frames.], tot_loss[loss=0.1664, simple_loss=0.256, pruned_loss=0.03842, over 1419140.41 frames.], batch size: 23, lr: 4.35e-04
+2022-05-14 21:40:45,340 INFO [train.py:812] (1/8) Epoch 18, batch 1200, loss[loss=0.1692, simple_loss=0.2502, pruned_loss=0.04411, over 7278.00 frames.], tot_loss[loss=0.1666, simple_loss=0.256, pruned_loss=0.03858, over 1417322.10 frames.], batch size: 18, lr: 4.34e-04
+2022-05-14 21:41:44,605 INFO [train.py:812] (1/8) Epoch 18, batch 1250, loss[loss=0.1634, simple_loss=0.2438, pruned_loss=0.04147, over 7415.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2555, pruned_loss=0.03807, over 1419748.04 frames.], batch size: 21, lr: 4.34e-04
+2022-05-14 21:42:42,166 INFO [train.py:812] (1/8) Epoch 18, batch 1300, loss[loss=0.1563, simple_loss=0.2412, pruned_loss=0.03574, over 7168.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2554, pruned_loss=0.0386, over 1420269.42 frames.], batch size: 26, lr: 4.34e-04
+2022-05-14 21:43:41,336 INFO [train.py:812] (1/8) Epoch 18, batch 1350, loss[loss=0.1539, simple_loss=0.2343, pruned_loss=0.03675, over 6998.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2553, pruned_loss=0.03829, over 1422833.22 frames.], batch size: 16, lr: 4.34e-04
+2022-05-14 21:44:39,588 INFO [train.py:812] (1/8) Epoch 18, batch 1400, loss[loss=0.1577, simple_loss=0.2596, pruned_loss=0.02793, over 7117.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2558, pruned_loss=0.03801, over 1423962.92 frames.], batch size: 21, lr: 4.34e-04
+2022-05-14 21:45:38,207 INFO [train.py:812] (1/8) Epoch 18, batch 1450, loss[loss=0.1756, simple_loss=0.2671, pruned_loss=0.04209, over 7151.00 frames.], tot_loss[loss=0.1658, simple_loss=0.256, pruned_loss=0.03776, over 1422194.71 frames.], batch size: 20, lr: 4.34e-04
+2022-05-14 21:46:36,911 INFO [train.py:812] (1/8) Epoch 18, batch 1500, loss[loss=0.1544, simple_loss=0.2509, pruned_loss=0.02901, over 7321.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2562, pruned_loss=0.03806, over 1415876.66 frames.], batch size: 25, lr: 4.34e-04
+2022-05-14 21:47:35,826 INFO [train.py:812] (1/8) Epoch 18, batch 1550, loss[loss=0.1474, simple_loss=0.2345, pruned_loss=0.03009, over 7140.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2559, pruned_loss=0.03794, over 1422810.98 frames.], batch size: 19, lr: 4.33e-04
+2022-05-14 21:48:33,676 INFO [train.py:812] (1/8) Epoch 18, batch 1600, loss[loss=0.1634, simple_loss=0.2546, pruned_loss=0.03609, over 7420.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2565, pruned_loss=0.03861, over 1423141.44 frames.], batch size: 20, lr: 4.33e-04
+2022-05-14 21:49:33,280 INFO [train.py:812] (1/8) Epoch 18, batch 1650, loss[loss=0.1424, simple_loss=0.2189, pruned_loss=0.03294, over 7290.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2568, pruned_loss=0.0387, over 1422635.38 frames.], batch size: 17, lr: 4.33e-04
+2022-05-14 21:50:30,808 INFO [train.py:812] (1/8) Epoch 18, batch 1700, loss[loss=0.1701, simple_loss=0.2627, pruned_loss=0.03874, over 7360.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2566, pruned_loss=0.03839, over 1425260.69 frames.], batch size: 19, lr: 4.33e-04
+2022-05-14 21:51:29,630 INFO [train.py:812] (1/8) Epoch 18, batch 1750, loss[loss=0.151, simple_loss=0.2483, pruned_loss=0.0268, over 7320.00 frames.], tot_loss[loss=0.166, simple_loss=0.2559, pruned_loss=0.0381, over 1426456.68 frames.], batch size: 21, lr: 4.33e-04
+2022-05-14 21:52:27,482 INFO [train.py:812] (1/8) Epoch 18, batch 1800, loss[loss=0.1693, simple_loss=0.247, pruned_loss=0.0458, over 7235.00 frames.], tot_loss[loss=0.166, simple_loss=0.2555, pruned_loss=0.03828, over 1430592.42 frames.], batch size: 20, lr: 4.33e-04
+2022-05-14 21:53:27,320 INFO [train.py:812] (1/8) Epoch 18, batch 1850, loss[loss=0.1679, simple_loss=0.2539, pruned_loss=0.04091, over 5107.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2538, pruned_loss=0.03787, over 1428122.36 frames.], batch size: 53, lr: 4.33e-04
+2022-05-14 21:54:25,902 INFO [train.py:812] (1/8) Epoch 18, batch 1900, loss[loss=0.1784, simple_loss=0.2684, pruned_loss=0.04422, over 7328.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2554, pruned_loss=0.03801, over 1427965.22 frames.], batch size: 21, lr: 4.33e-04
+2022-05-14 21:55:25,267 INFO [train.py:812] (1/8) Epoch 18, batch 1950, loss[loss=0.1723, simple_loss=0.2653, pruned_loss=0.03961, over 7317.00 frames.], tot_loss[loss=0.1663, simple_loss=0.256, pruned_loss=0.03832, over 1424439.01 frames.], batch size: 21, lr: 4.32e-04
+2022-05-14 21:56:23,562 INFO [train.py:812] (1/8) Epoch 18, batch 2000, loss[loss=0.1726, simple_loss=0.2537, pruned_loss=0.04576, over 5308.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2551, pruned_loss=0.03823, over 1425527.95 frames.], batch size: 52, lr: 4.32e-04
+2022-05-14 21:57:27,186 INFO [train.py:812] (1/8) Epoch 18, batch 2050, loss[loss=0.181, simple_loss=0.2718, pruned_loss=0.04514, over 7109.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2548, pruned_loss=0.03805, over 1420490.13 frames.], batch size: 21, lr: 4.32e-04
+2022-05-14 21:58:25,559 INFO [train.py:812] (1/8) Epoch 18, batch 2100, loss[loss=0.1944, simple_loss=0.3019, pruned_loss=0.04347, over 6680.00 frames.], tot_loss[loss=0.165, simple_loss=0.2544, pruned_loss=0.03783, over 1416050.04 frames.], batch size: 31, lr: 4.32e-04
+2022-05-14 21:59:24,610 INFO [train.py:812] (1/8) Epoch 18, batch 2150, loss[loss=0.178, simple_loss=0.277, pruned_loss=0.03957, over 7220.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2543, pruned_loss=0.03745, over 1418158.31 frames.], batch size: 21, lr: 4.32e-04
+2022-05-14 22:00:22,626 INFO [train.py:812] (1/8) Epoch 18, batch 2200, loss[loss=0.1696, simple_loss=0.2422, pruned_loss=0.04845, over 6786.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2544, pruned_loss=0.03733, over 1421729.19 frames.], batch size: 15, lr: 4.32e-04
+2022-05-14 22:01:22,001 INFO [train.py:812] (1/8) Epoch 18, batch 2250, loss[loss=0.1338, simple_loss=0.2159, pruned_loss=0.0258, over 7020.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2542, pruned_loss=0.03725, over 1424666.81 frames.], batch size: 16, lr: 4.32e-04
+2022-05-14 22:02:21,442 INFO [train.py:812] (1/8) Epoch 18, batch 2300, loss[loss=0.1606, simple_loss=0.2544, pruned_loss=0.03344, over 7140.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2547, pruned_loss=0.03752, over 1427166.20 frames.], batch size: 20, lr: 4.31e-04
+2022-05-14 22:03:21,214 INFO [train.py:812] (1/8) Epoch 18, batch 2350, loss[loss=0.2145, simple_loss=0.3076, pruned_loss=0.06075, over 7165.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2546, pruned_loss=0.03777, over 1426473.13 frames.], batch size: 26, lr: 4.31e-04
+2022-05-14 22:04:20,402 INFO [train.py:812] (1/8) Epoch 18, batch 2400, loss[loss=0.2053, simple_loss=0.2888, pruned_loss=0.06092, over 6487.00 frames.], tot_loss[loss=0.1655, simple_loss=0.255, pruned_loss=0.03804, over 1425261.59 frames.], batch size: 38, lr: 4.31e-04
+2022-05-14 22:05:18,787 INFO [train.py:812] (1/8) Epoch 18, batch 2450, loss[loss=0.1583, simple_loss=0.251, pruned_loss=0.03282, over 7151.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2539, pruned_loss=0.03787, over 1426410.85 frames.], batch size: 19, lr: 4.31e-04
+2022-05-14 22:06:16,644 INFO [train.py:812] (1/8) Epoch 18, batch 2500, loss[loss=0.1845, simple_loss=0.2832, pruned_loss=0.04288, over 7115.00 frames.], tot_loss[loss=0.1658, simple_loss=0.255, pruned_loss=0.03833, over 1419399.49 frames.], batch size: 21, lr: 4.31e-04
+2022-05-14 22:07:15,274 INFO [train.py:812] (1/8) Epoch 18, batch 2550, loss[loss=0.177, simple_loss=0.2756, pruned_loss=0.03923, over 7316.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2548, pruned_loss=0.03817, over 1419738.89 frames.], batch size: 21, lr: 4.31e-04
+2022-05-14 22:08:14,571 INFO [train.py:812] (1/8) Epoch 18, batch 2600, loss[loss=0.1563, simple_loss=0.2448, pruned_loss=0.03389, over 6778.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2548, pruned_loss=0.03796, over 1419073.47 frames.], batch size: 15, lr: 4.31e-04
+2022-05-14 22:09:14,553 INFO [train.py:812] (1/8) Epoch 18, batch 2650, loss[loss=0.1831, simple_loss=0.2679, pruned_loss=0.04918, over 7359.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2548, pruned_loss=0.03827, over 1420021.93 frames.], batch size: 19, lr: 4.31e-04
+2022-05-14 22:10:13,351 INFO [train.py:812] (1/8) Epoch 18, batch 2700, loss[loss=0.1449, simple_loss=0.2404, pruned_loss=0.0247, over 7291.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2542, pruned_loss=0.03781, over 1419817.13 frames.], batch size: 18, lr: 4.30e-04
+2022-05-14 22:11:12,901 INFO [train.py:812] (1/8) Epoch 18, batch 2750, loss[loss=0.1783, simple_loss=0.2668, pruned_loss=0.04495, over 7137.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2544, pruned_loss=0.03816, over 1417884.74 frames.], batch size: 20, lr: 4.30e-04
+2022-05-14 22:12:10,427 INFO [train.py:812] (1/8) Epoch 18, batch 2800, loss[loss=0.1851, simple_loss=0.2769, pruned_loss=0.04661, over 7321.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2534, pruned_loss=0.03763, over 1417372.48 frames.], batch size: 21, lr: 4.30e-04
+2022-05-14 22:13:09,209 INFO [train.py:812] (1/8) Epoch 18, batch 2850, loss[loss=0.1707, simple_loss=0.2555, pruned_loss=0.04297, over 7294.00 frames.], tot_loss[loss=0.1647, simple_loss=0.254, pruned_loss=0.0377, over 1420325.42 frames.], batch size: 25, lr: 4.30e-04
+2022-05-14 22:14:17,878 INFO [train.py:812] (1/8) Epoch 18, batch 2900, loss[loss=0.1994, simple_loss=0.2963, pruned_loss=0.05124, over 7199.00 frames.], tot_loss[loss=0.1654, simple_loss=0.255, pruned_loss=0.03791, over 1422488.50 frames.], batch size: 22, lr: 4.30e-04
+2022-05-14 22:15:17,299 INFO [train.py:812] (1/8) Epoch 18, batch 2950, loss[loss=0.1992, simple_loss=0.2842, pruned_loss=0.0571, over 6223.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2554, pruned_loss=0.03817, over 1418793.37 frames.], batch size: 37, lr: 4.30e-04
+2022-05-14 22:16:16,204 INFO [train.py:812] (1/8) Epoch 18, batch 3000, loss[loss=0.1845, simple_loss=0.2819, pruned_loss=0.04353, over 7293.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2559, pruned_loss=0.03812, over 1417397.11 frames.], batch size: 25, lr: 4.30e-04
+2022-05-14 22:16:16,205 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 22:16:23,833 INFO [train.py:841] (1/8) Epoch 18, validation: loss=0.153, simple_loss=0.2523, pruned_loss=0.02686, over 698248.00 frames.
+2022-05-14 22:17:22,910 INFO [train.py:812] (1/8) Epoch 18, batch 3050, loss[loss=0.1723, simple_loss=0.2588, pruned_loss=0.04287, over 7128.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2564, pruned_loss=0.03841, over 1417131.83 frames.], batch size: 21, lr: 4.29e-04
+2022-05-14 22:18:21,081 INFO [train.py:812] (1/8) Epoch 18, batch 3100, loss[loss=0.1761, simple_loss=0.2701, pruned_loss=0.04107, over 7230.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2569, pruned_loss=0.03852, over 1418393.96 frames.], batch size: 20, lr: 4.29e-04
+2022-05-14 22:19:19,571 INFO [train.py:812] (1/8) Epoch 18, batch 3150, loss[loss=0.1339, simple_loss=0.228, pruned_loss=0.01993, over 7247.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2563, pruned_loss=0.03846, over 1421493.35 frames.], batch size: 19, lr: 4.29e-04
+2022-05-14 22:20:18,603 INFO [train.py:812] (1/8) Epoch 18, batch 3200, loss[loss=0.1764, simple_loss=0.2676, pruned_loss=0.04256, over 6765.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2566, pruned_loss=0.03897, over 1419207.81 frames.], batch size: 31, lr: 4.29e-04
+2022-05-14 22:21:17,368 INFO [train.py:812] (1/8) Epoch 18, batch 3250, loss[loss=0.1652, simple_loss=0.2533, pruned_loss=0.03852, over 7381.00 frames.], tot_loss[loss=0.1657, simple_loss=0.255, pruned_loss=0.03819, over 1422612.83 frames.], batch size: 23, lr: 4.29e-04
+2022-05-14 22:22:16,095 INFO [train.py:812] (1/8) Epoch 18, batch 3300, loss[loss=0.1575, simple_loss=0.239, pruned_loss=0.03796, over 7167.00 frames.], tot_loss[loss=0.165, simple_loss=0.2544, pruned_loss=0.03778, over 1427417.30 frames.], batch size: 18, lr: 4.29e-04
+2022-05-14 22:23:15,276 INFO [train.py:812] (1/8) Epoch 18, batch 3350, loss[loss=0.1343, simple_loss=0.2201, pruned_loss=0.02425, over 7422.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2547, pruned_loss=0.03775, over 1427246.58 frames.], batch size: 18, lr: 4.29e-04
+2022-05-14 22:24:13,570 INFO [train.py:812] (1/8) Epoch 18, batch 3400, loss[loss=0.1811, simple_loss=0.2743, pruned_loss=0.0439, over 7375.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2546, pruned_loss=0.03754, over 1430438.64 frames.], batch size: 23, lr: 4.29e-04
+2022-05-14 22:25:13,422 INFO [train.py:812] (1/8) Epoch 18, batch 3450, loss[loss=0.1266, simple_loss=0.2128, pruned_loss=0.02019, over 7413.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2546, pruned_loss=0.03735, over 1430573.47 frames.], batch size: 18, lr: 4.28e-04
+2022-05-14 22:26:12,111 INFO [train.py:812] (1/8) Epoch 18, batch 3500, loss[loss=0.1811, simple_loss=0.2686, pruned_loss=0.04685, over 6205.00 frames.], tot_loss[loss=0.164, simple_loss=0.2538, pruned_loss=0.03705, over 1432851.08 frames.], batch size: 37, lr: 4.28e-04
+2022-05-14 22:27:09,548 INFO [train.py:812] (1/8) Epoch 18, batch 3550, loss[loss=0.1674, simple_loss=0.2581, pruned_loss=0.03832, over 7199.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2538, pruned_loss=0.03728, over 1431562.05 frames.], batch size: 23, lr: 4.28e-04
+2022-05-14 22:28:09,172 INFO [train.py:812] (1/8) Epoch 18, batch 3600, loss[loss=0.1891, simple_loss=0.2801, pruned_loss=0.04905, over 7219.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2537, pruned_loss=0.03709, over 1432380.63 frames.], batch size: 21, lr: 4.28e-04
+2022-05-14 22:29:08,003 INFO [train.py:812] (1/8) Epoch 18, batch 3650, loss[loss=0.1641, simple_loss=0.2537, pruned_loss=0.03726, over 7341.00 frames.], tot_loss[loss=0.1645, simple_loss=0.254, pruned_loss=0.03752, over 1423567.32 frames.], batch size: 22, lr: 4.28e-04
+2022-05-14 22:30:06,374 INFO [train.py:812] (1/8) Epoch 18, batch 3700, loss[loss=0.1542, simple_loss=0.2315, pruned_loss=0.03846, over 6982.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2545, pruned_loss=0.03734, over 1424812.42 frames.], batch size: 16, lr: 4.28e-04
+2022-05-14 22:31:03,709 INFO [train.py:812] (1/8) Epoch 18, batch 3750, loss[loss=0.1667, simple_loss=0.2578, pruned_loss=0.03782, over 7293.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2546, pruned_loss=0.03711, over 1426574.56 frames.], batch size: 25, lr: 4.28e-04
+2022-05-14 22:32:02,177 INFO [train.py:812] (1/8) Epoch 18, batch 3800, loss[loss=0.1735, simple_loss=0.272, pruned_loss=0.03751, over 7360.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2545, pruned_loss=0.0369, over 1425620.79 frames.], batch size: 19, lr: 4.28e-04
+2022-05-14 22:33:01,943 INFO [train.py:812] (1/8) Epoch 18, batch 3850, loss[loss=0.1583, simple_loss=0.2541, pruned_loss=0.03123, over 7415.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2545, pruned_loss=0.03747, over 1424492.88 frames.], batch size: 18, lr: 4.27e-04
+2022-05-14 22:34:00,985 INFO [train.py:812] (1/8) Epoch 18, batch 3900, loss[loss=0.1957, simple_loss=0.2854, pruned_loss=0.05299, over 7122.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2551, pruned_loss=0.03756, over 1420753.23 frames.], batch size: 21, lr: 4.27e-04
+2022-05-14 22:35:00,684 INFO [train.py:812] (1/8) Epoch 18, batch 3950, loss[loss=0.1579, simple_loss=0.2493, pruned_loss=0.03324, over 7107.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2547, pruned_loss=0.03797, over 1422343.88 frames.], batch size: 28, lr: 4.27e-04
+2022-05-14 22:35:58,138 INFO [train.py:812] (1/8) Epoch 18, batch 4000, loss[loss=0.1594, simple_loss=0.2416, pruned_loss=0.03865, over 6828.00 frames.], tot_loss[loss=0.1654, simple_loss=0.255, pruned_loss=0.03795, over 1423791.54 frames.], batch size: 15, lr: 4.27e-04
+2022-05-14 22:36:56,542 INFO [train.py:812] (1/8) Epoch 18, batch 4050, loss[loss=0.1588, simple_loss=0.2491, pruned_loss=0.03424, over 7119.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2555, pruned_loss=0.0384, over 1426939.08 frames.], batch size: 28, lr: 4.27e-04
+2022-05-14 22:37:55,336 INFO [train.py:812] (1/8) Epoch 18, batch 4100, loss[loss=0.1679, simple_loss=0.2623, pruned_loss=0.03681, over 7145.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2554, pruned_loss=0.03864, over 1423596.41 frames.], batch size: 20, lr: 4.27e-04
+2022-05-14 22:38:54,564 INFO [train.py:812] (1/8) Epoch 18, batch 4150, loss[loss=0.1665, simple_loss=0.2605, pruned_loss=0.03623, over 7330.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2554, pruned_loss=0.03862, over 1422801.94 frames.], batch size: 20, lr: 4.27e-04
+2022-05-14 22:39:53,792 INFO [train.py:812] (1/8) Epoch 18, batch 4200, loss[loss=0.1675, simple_loss=0.2614, pruned_loss=0.03685, over 6997.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2538, pruned_loss=0.03784, over 1422552.15 frames.], batch size: 16, lr: 4.26e-04
+2022-05-14 22:40:53,082 INFO [train.py:812] (1/8) Epoch 18, batch 4250, loss[loss=0.1606, simple_loss=0.2529, pruned_loss=0.03415, over 6872.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2537, pruned_loss=0.03792, over 1418291.80 frames.], batch size: 32, lr: 4.26e-04
+2022-05-14 22:41:52,058 INFO [train.py:812] (1/8) Epoch 18, batch 4300, loss[loss=0.1388, simple_loss=0.2166, pruned_loss=0.03048, over 6990.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2521, pruned_loss=0.03759, over 1419062.33 frames.], batch size: 16, lr: 4.26e-04
+2022-05-14 22:42:51,533 INFO [train.py:812] (1/8) Epoch 18, batch 4350, loss[loss=0.1711, simple_loss=0.2661, pruned_loss=0.0381, over 7217.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2534, pruned_loss=0.03844, over 1406790.70 frames.], batch size: 21, lr: 4.26e-04
+2022-05-14 22:43:50,337 INFO [train.py:812] (1/8) Epoch 18, batch 4400, loss[loss=0.1562, simple_loss=0.2473, pruned_loss=0.0325, over 7074.00 frames.], tot_loss[loss=0.166, simple_loss=0.2545, pruned_loss=0.03873, over 1401906.62 frames.], batch size: 18, lr: 4.26e-04
+2022-05-14 22:44:47,957 INFO [train.py:812] (1/8) Epoch 18, batch 4450, loss[loss=0.1679, simple_loss=0.2622, pruned_loss=0.03681, over 6377.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2555, pruned_loss=0.03858, over 1392519.43 frames.], batch size: 37, lr: 4.26e-04
+2022-05-14 22:45:55,868 INFO [train.py:812] (1/8) Epoch 18, batch 4500, loss[loss=0.1381, simple_loss=0.2193, pruned_loss=0.02842, over 6988.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2559, pruned_loss=0.03867, over 1380260.34 frames.], batch size: 16, lr: 4.26e-04
+2022-05-14 22:46:55,057 INFO [train.py:812] (1/8) Epoch 18, batch 4550, loss[loss=0.1508, simple_loss=0.2399, pruned_loss=0.03088, over 7161.00 frames.], tot_loss[loss=0.166, simple_loss=0.2552, pruned_loss=0.03847, over 1368521.77 frames.], batch size: 19, lr: 4.26e-04
+2022-05-14 22:48:10,084 INFO [train.py:812] (1/8) Epoch 19, batch 0, loss[loss=0.1758, simple_loss=0.2696, pruned_loss=0.04103, over 7299.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2696, pruned_loss=0.04103, over 7299.00 frames.], batch size: 25, lr: 4.15e-04
+2022-05-14 22:49:27,400 INFO [train.py:812] (1/8) Epoch 19, batch 50, loss[loss=0.1624, simple_loss=0.2549, pruned_loss=0.03495, over 7335.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2539, pruned_loss=0.0376, over 324759.81 frames.], batch size: 22, lr: 4.15e-04
+2022-05-14 22:50:35,550 INFO [train.py:812] (1/8) Epoch 19, batch 100, loss[loss=0.1803, simple_loss=0.2784, pruned_loss=0.04105, over 7348.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2542, pruned_loss=0.03674, over 574616.80 frames.], batch size: 22, lr: 4.14e-04
+2022-05-14 22:51:34,799 INFO [train.py:812] (1/8) Epoch 19, batch 150, loss[loss=0.1804, simple_loss=0.2794, pruned_loss=0.04071, over 7222.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2529, pruned_loss=0.03699, over 764496.83 frames.], batch size: 21, lr: 4.14e-04
+2022-05-14 22:53:02,396 INFO [train.py:812] (1/8) Epoch 19, batch 200, loss[loss=0.1446, simple_loss=0.2345, pruned_loss=0.02735, over 7275.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2525, pruned_loss=0.03655, over 909764.88 frames.], batch size: 17, lr: 4.14e-04
+2022-05-14 22:54:01,877 INFO [train.py:812] (1/8) Epoch 19, batch 250, loss[loss=0.1602, simple_loss=0.256, pruned_loss=0.03223, over 6759.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2529, pruned_loss=0.03641, over 1025821.28 frames.], batch size: 31, lr: 4.14e-04
+2022-05-14 22:55:01,087 INFO [train.py:812] (1/8) Epoch 19, batch 300, loss[loss=0.18, simple_loss=0.2721, pruned_loss=0.04397, over 7239.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2534, pruned_loss=0.03659, over 1116027.73 frames.], batch size: 20, lr: 4.14e-04
+2022-05-14 22:56:00,984 INFO [train.py:812] (1/8) Epoch 19, batch 350, loss[loss=0.1671, simple_loss=0.2558, pruned_loss=0.03919, over 6859.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2525, pruned_loss=0.03616, over 1182633.94 frames.], batch size: 31, lr: 4.14e-04
+2022-05-14 22:56:59,182 INFO [train.py:812] (1/8) Epoch 19, batch 400, loss[loss=0.1569, simple_loss=0.2395, pruned_loss=0.0372, over 7061.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2534, pruned_loss=0.03686, over 1233661.17 frames.], batch size: 18, lr: 4.14e-04
+2022-05-14 22:57:58,720 INFO [train.py:812] (1/8) Epoch 19, batch 450, loss[loss=0.1484, simple_loss=0.2538, pruned_loss=0.02153, over 7335.00 frames.], tot_loss[loss=0.164, simple_loss=0.2543, pruned_loss=0.03687, over 1275330.84 frames.], batch size: 22, lr: 4.14e-04
+2022-05-14 22:58:57,680 INFO [train.py:812] (1/8) Epoch 19, batch 500, loss[loss=0.1466, simple_loss=0.2248, pruned_loss=0.03421, over 7128.00 frames.], tot_loss[loss=0.1649, simple_loss=0.255, pruned_loss=0.03735, over 1306418.05 frames.], batch size: 17, lr: 4.13e-04
+2022-05-14 22:59:57,488 INFO [train.py:812] (1/8) Epoch 19, batch 550, loss[loss=0.1529, simple_loss=0.2371, pruned_loss=0.03438, over 7272.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2549, pruned_loss=0.03709, over 1336343.71 frames.], batch size: 17, lr: 4.13e-04
+2022-05-14 23:00:56,147 INFO [train.py:812] (1/8) Epoch 19, batch 600, loss[loss=0.1481, simple_loss=0.2321, pruned_loss=0.032, over 7280.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2547, pruned_loss=0.0372, over 1356614.31 frames.], batch size: 18, lr: 4.13e-04
+2022-05-14 23:01:55,594 INFO [train.py:812] (1/8) Epoch 19, batch 650, loss[loss=0.1799, simple_loss=0.2703, pruned_loss=0.04471, over 7118.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2539, pruned_loss=0.03672, over 1374937.81 frames.], batch size: 21, lr: 4.13e-04
+2022-05-14 23:02:54,273 INFO [train.py:812] (1/8) Epoch 19, batch 700, loss[loss=0.1447, simple_loss=0.2406, pruned_loss=0.02444, over 5049.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2536, pruned_loss=0.03641, over 1385325.13 frames.], batch size: 52, lr: 4.13e-04
+2022-05-14 23:03:53,343 INFO [train.py:812] (1/8) Epoch 19, batch 750, loss[loss=0.1539, simple_loss=0.2524, pruned_loss=0.02768, over 7171.00 frames.], tot_loss[loss=0.163, simple_loss=0.2531, pruned_loss=0.03645, over 1394071.49 frames.], batch size: 19, lr: 4.13e-04
+2022-05-14 23:04:52,299 INFO [train.py:812] (1/8) Epoch 19, batch 800, loss[loss=0.1586, simple_loss=0.2595, pruned_loss=0.02887, over 6666.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2543, pruned_loss=0.03657, over 1397666.80 frames.], batch size: 31, lr: 4.13e-04
+2022-05-14 23:05:50,873 INFO [train.py:812] (1/8) Epoch 19, batch 850, loss[loss=0.1534, simple_loss=0.2413, pruned_loss=0.03279, over 7074.00 frames.], tot_loss[loss=0.1645, simple_loss=0.255, pruned_loss=0.03695, over 1405035.64 frames.], batch size: 18, lr: 4.13e-04
+2022-05-14 23:06:49,944 INFO [train.py:812] (1/8) Epoch 19, batch 900, loss[loss=0.1819, simple_loss=0.2549, pruned_loss=0.0545, over 7199.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2555, pruned_loss=0.03738, over 1410653.39 frames.], batch size: 16, lr: 4.12e-04
+2022-05-14 23:07:49,370 INFO [train.py:812] (1/8) Epoch 19, batch 950, loss[loss=0.2311, simple_loss=0.3009, pruned_loss=0.08064, over 7368.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2546, pruned_loss=0.03744, over 1413448.08 frames.], batch size: 23, lr: 4.12e-04
+2022-05-14 23:08:48,635 INFO [train.py:812] (1/8) Epoch 19, batch 1000, loss[loss=0.1546, simple_loss=0.2517, pruned_loss=0.02874, over 7159.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2542, pruned_loss=0.03717, over 1420006.17 frames.], batch size: 20, lr: 4.12e-04
+2022-05-14 23:09:47,747 INFO [train.py:812] (1/8) Epoch 19, batch 1050, loss[loss=0.1728, simple_loss=0.2627, pruned_loss=0.0415, over 7283.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2542, pruned_loss=0.03769, over 1417644.03 frames.], batch size: 25, lr: 4.12e-04
+2022-05-14 23:10:45,899 INFO [train.py:812] (1/8) Epoch 19, batch 1100, loss[loss=0.1537, simple_loss=0.2559, pruned_loss=0.02572, over 7327.00 frames.], tot_loss[loss=0.164, simple_loss=0.2532, pruned_loss=0.03735, over 1418486.78 frames.], batch size: 20, lr: 4.12e-04
+2022-05-14 23:11:43,620 INFO [train.py:812] (1/8) Epoch 19, batch 1150, loss[loss=0.1635, simple_loss=0.2544, pruned_loss=0.03626, over 7284.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2527, pruned_loss=0.03702, over 1418794.89 frames.], batch size: 24, lr: 4.12e-04
+2022-05-14 23:12:42,327 INFO [train.py:812] (1/8) Epoch 19, batch 1200, loss[loss=0.1757, simple_loss=0.2567, pruned_loss=0.0473, over 4682.00 frames.], tot_loss[loss=0.1639, simple_loss=0.253, pruned_loss=0.03738, over 1413455.48 frames.], batch size: 52, lr: 4.12e-04
+2022-05-14 23:13:40,376 INFO [train.py:812] (1/8) Epoch 19, batch 1250, loss[loss=0.1687, simple_loss=0.259, pruned_loss=0.03921, over 7134.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2535, pruned_loss=0.03762, over 1413848.58 frames.], batch size: 21, lr: 4.12e-04
+2022-05-14 23:14:39,569 INFO [train.py:812] (1/8) Epoch 19, batch 1300, loss[loss=0.1441, simple_loss=0.2407, pruned_loss=0.02374, over 7154.00 frames.], tot_loss[loss=0.1645, simple_loss=0.254, pruned_loss=0.03752, over 1413515.99 frames.], batch size: 19, lr: 4.12e-04
+2022-05-14 23:15:38,787 INFO [train.py:812] (1/8) Epoch 19, batch 1350, loss[loss=0.1962, simple_loss=0.2781, pruned_loss=0.05714, over 7011.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2543, pruned_loss=0.03776, over 1412454.49 frames.], batch size: 28, lr: 4.11e-04
+2022-05-14 23:16:38,077 INFO [train.py:812] (1/8) Epoch 19, batch 1400, loss[loss=0.1628, simple_loss=0.2398, pruned_loss=0.04284, over 7071.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2537, pruned_loss=0.03751, over 1411110.45 frames.], batch size: 18, lr: 4.11e-04
+2022-05-14 23:17:42,361 INFO [train.py:812] (1/8) Epoch 19, batch 1450, loss[loss=0.1686, simple_loss=0.2571, pruned_loss=0.04002, over 7315.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2535, pruned_loss=0.03729, over 1418613.58 frames.], batch size: 21, lr: 4.11e-04
+2022-05-14 23:18:41,293 INFO [train.py:812] (1/8) Epoch 19, batch 1500, loss[loss=0.1424, simple_loss=0.2232, pruned_loss=0.03079, over 7256.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2541, pruned_loss=0.03757, over 1422027.95 frames.], batch size: 19, lr: 4.11e-04
+2022-05-14 23:19:40,446 INFO [train.py:812] (1/8) Epoch 19, batch 1550, loss[loss=0.1668, simple_loss=0.2594, pruned_loss=0.03712, over 7408.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2539, pruned_loss=0.03759, over 1425309.85 frames.], batch size: 21, lr: 4.11e-04
+2022-05-14 23:20:39,981 INFO [train.py:812] (1/8) Epoch 19, batch 1600, loss[loss=0.1782, simple_loss=0.2612, pruned_loss=0.04757, over 7199.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2526, pruned_loss=0.03731, over 1424212.25 frames.], batch size: 22, lr: 4.11e-04
+2022-05-14 23:21:39,522 INFO [train.py:812] (1/8) Epoch 19, batch 1650, loss[loss=0.1397, simple_loss=0.2315, pruned_loss=0.02391, over 7174.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2528, pruned_loss=0.03717, over 1422798.85 frames.], batch size: 18, lr: 4.11e-04
+2022-05-14 23:22:38,867 INFO [train.py:812] (1/8) Epoch 19, batch 1700, loss[loss=0.1641, simple_loss=0.2482, pruned_loss=0.04007, over 7167.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2534, pruned_loss=0.03714, over 1423608.15 frames.], batch size: 18, lr: 4.11e-04
+2022-05-14 23:23:37,793 INFO [train.py:812] (1/8) Epoch 19, batch 1750, loss[loss=0.1452, simple_loss=0.2419, pruned_loss=0.02421, over 7141.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2546, pruned_loss=0.03756, over 1416191.73 frames.], batch size: 20, lr: 4.10e-04
+2022-05-14 23:24:36,352 INFO [train.py:812] (1/8) Epoch 19, batch 1800, loss[loss=0.1661, simple_loss=0.2519, pruned_loss=0.04014, over 7265.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2558, pruned_loss=0.03745, over 1416050.23 frames.], batch size: 19, lr: 4.10e-04
+2022-05-14 23:25:35,719 INFO [train.py:812] (1/8) Epoch 19, batch 1850, loss[loss=0.1762, simple_loss=0.2605, pruned_loss=0.04598, over 7304.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2552, pruned_loss=0.03709, over 1421880.60 frames.], batch size: 24, lr: 4.10e-04
+2022-05-14 23:26:34,574 INFO [train.py:812] (1/8) Epoch 19, batch 1900, loss[loss=0.1758, simple_loss=0.2666, pruned_loss=0.04246, over 7089.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2561, pruned_loss=0.03771, over 1419515.80 frames.], batch size: 28, lr: 4.10e-04
+2022-05-14 23:27:34,101 INFO [train.py:812] (1/8) Epoch 19, batch 1950, loss[loss=0.1602, simple_loss=0.2331, pruned_loss=0.04367, over 6988.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2555, pruned_loss=0.03738, over 1420266.99 frames.], batch size: 16, lr: 4.10e-04
+2022-05-14 23:28:32,903 INFO [train.py:812] (1/8) Epoch 19, batch 2000, loss[loss=0.17, simple_loss=0.2622, pruned_loss=0.03893, over 7144.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2548, pruned_loss=0.03709, over 1423613.97 frames.], batch size: 20, lr: 4.10e-04
+2022-05-14 23:29:32,680 INFO [train.py:812] (1/8) Epoch 19, batch 2050, loss[loss=0.1936, simple_loss=0.2883, pruned_loss=0.04946, over 7281.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2544, pruned_loss=0.0372, over 1423999.98 frames.], batch size: 25, lr: 4.10e-04
+2022-05-14 23:30:30,657 INFO [train.py:812] (1/8) Epoch 19, batch 2100, loss[loss=0.159, simple_loss=0.2441, pruned_loss=0.0369, over 7162.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2538, pruned_loss=0.03656, over 1424237.72 frames.], batch size: 19, lr: 4.10e-04
+2022-05-14 23:31:30,580 INFO [train.py:812] (1/8) Epoch 19, batch 2150, loss[loss=0.1649, simple_loss=0.2709, pruned_loss=0.02946, over 7223.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2536, pruned_loss=0.0366, over 1420493.36 frames.], batch size: 21, lr: 4.09e-04
+2022-05-14 23:32:29,959 INFO [train.py:812] (1/8) Epoch 19, batch 2200, loss[loss=0.1755, simple_loss=0.2694, pruned_loss=0.04081, over 7116.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2533, pruned_loss=0.03651, over 1424646.74 frames.], batch size: 21, lr: 4.09e-04
+2022-05-14 23:33:29,281 INFO [train.py:812] (1/8) Epoch 19, batch 2250, loss[loss=0.17, simple_loss=0.2599, pruned_loss=0.04003, over 6545.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2531, pruned_loss=0.03653, over 1423998.56 frames.], batch size: 38, lr: 4.09e-04
+2022-05-14 23:34:27,801 INFO [train.py:812] (1/8) Epoch 19, batch 2300, loss[loss=0.1622, simple_loss=0.2599, pruned_loss=0.03222, over 7365.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2524, pruned_loss=0.03635, over 1425576.48 frames.], batch size: 23, lr: 4.09e-04
+2022-05-14 23:35:25,966 INFO [train.py:812] (1/8) Epoch 19, batch 2350, loss[loss=0.1596, simple_loss=0.2275, pruned_loss=0.04589, over 7272.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2527, pruned_loss=0.03661, over 1423285.39 frames.], batch size: 17, lr: 4.09e-04
+2022-05-14 23:36:25,348 INFO [train.py:812] (1/8) Epoch 19, batch 2400, loss[loss=0.1522, simple_loss=0.2529, pruned_loss=0.02575, over 7146.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2535, pruned_loss=0.03703, over 1420170.38 frames.], batch size: 20, lr: 4.09e-04
+2022-05-14 23:37:24,211 INFO [train.py:812] (1/8) Epoch 19, batch 2450, loss[loss=0.182, simple_loss=0.2677, pruned_loss=0.04818, over 7145.00 frames.], tot_loss[loss=0.164, simple_loss=0.2536, pruned_loss=0.03721, over 1423034.34 frames.], batch size: 20, lr: 4.09e-04
+2022-05-14 23:38:23,517 INFO [train.py:812] (1/8) Epoch 19, batch 2500, loss[loss=0.1494, simple_loss=0.2474, pruned_loss=0.0257, over 7187.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2531, pruned_loss=0.03699, over 1421759.40 frames.], batch size: 26, lr: 4.09e-04
+2022-05-14 23:39:22,980 INFO [train.py:812] (1/8) Epoch 19, batch 2550, loss[loss=0.1869, simple_loss=0.28, pruned_loss=0.04696, over 7285.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2531, pruned_loss=0.03705, over 1421384.27 frames.], batch size: 24, lr: 4.08e-04
+2022-05-14 23:40:21,745 INFO [train.py:812] (1/8) Epoch 19, batch 2600, loss[loss=0.1625, simple_loss=0.2252, pruned_loss=0.0499, over 7013.00 frames.], tot_loss[loss=0.1642, simple_loss=0.254, pruned_loss=0.03717, over 1425003.78 frames.], batch size: 16, lr: 4.08e-04
+2022-05-14 23:41:20,970 INFO [train.py:812] (1/8) Epoch 19, batch 2650, loss[loss=0.1894, simple_loss=0.2791, pruned_loss=0.04988, over 7273.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2549, pruned_loss=0.03779, over 1426906.19 frames.], batch size: 24, lr: 4.08e-04
+2022-05-14 23:42:20,840 INFO [train.py:812] (1/8) Epoch 19, batch 2700, loss[loss=0.1648, simple_loss=0.2642, pruned_loss=0.03273, over 7284.00 frames.], tot_loss[loss=0.164, simple_loss=0.2538, pruned_loss=0.03707, over 1431081.54 frames.], batch size: 25, lr: 4.08e-04
+2022-05-14 23:43:20,354 INFO [train.py:812] (1/8) Epoch 19, batch 2750, loss[loss=0.1763, simple_loss=0.2619, pruned_loss=0.04537, over 7409.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2538, pruned_loss=0.03685, over 1430665.32 frames.], batch size: 21, lr: 4.08e-04
+2022-05-14 23:44:19,826 INFO [train.py:812] (1/8) Epoch 19, batch 2800, loss[loss=0.1732, simple_loss=0.2699, pruned_loss=0.03825, over 7064.00 frames.], tot_loss[loss=0.163, simple_loss=0.2527, pruned_loss=0.03665, over 1431046.47 frames.], batch size: 18, lr: 4.08e-04
+2022-05-14 23:45:18,631 INFO [train.py:812] (1/8) Epoch 19, batch 2850, loss[loss=0.1588, simple_loss=0.2519, pruned_loss=0.03284, over 7154.00 frames.], tot_loss[loss=0.163, simple_loss=0.2529, pruned_loss=0.03654, over 1427621.97 frames.], batch size: 19, lr: 4.08e-04
+2022-05-14 23:46:17,155 INFO [train.py:812] (1/8) Epoch 19, batch 2900, loss[loss=0.1852, simple_loss=0.2766, pruned_loss=0.04695, over 7206.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2522, pruned_loss=0.03619, over 1424245.74 frames.], batch size: 26, lr: 4.08e-04
+2022-05-14 23:47:15,880 INFO [train.py:812] (1/8) Epoch 19, batch 2950, loss[loss=0.1615, simple_loss=0.2361, pruned_loss=0.04346, over 7273.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2527, pruned_loss=0.0363, over 1429951.98 frames.], batch size: 17, lr: 4.08e-04
+2022-05-14 23:48:15,114 INFO [train.py:812] (1/8) Epoch 19, batch 3000, loss[loss=0.1833, simple_loss=0.2696, pruned_loss=0.04851, over 5116.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2526, pruned_loss=0.03657, over 1429695.56 frames.], batch size: 53, lr: 4.07e-04
+2022-05-14 23:48:15,115 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-14 23:48:22,685 INFO [train.py:841] (1/8) Epoch 19, validation: loss=0.1531, simple_loss=0.2523, pruned_loss=0.02694, over 698248.00 frames.
+2022-05-14 23:49:22,397 INFO [train.py:812] (1/8) Epoch 19, batch 3050, loss[loss=0.1922, simple_loss=0.2795, pruned_loss=0.05249, over 7205.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2538, pruned_loss=0.03688, over 1430683.33 frames.], batch size: 23, lr: 4.07e-04
+2022-05-14 23:50:21,361 INFO [train.py:812] (1/8) Epoch 19, batch 3100, loss[loss=0.1727, simple_loss=0.2656, pruned_loss=0.03993, over 6654.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2539, pruned_loss=0.03683, over 1431697.43 frames.], batch size: 38, lr: 4.07e-04
+2022-05-14 23:51:20,046 INFO [train.py:812] (1/8) Epoch 19, batch 3150, loss[loss=0.1435, simple_loss=0.2182, pruned_loss=0.03438, over 7266.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2547, pruned_loss=0.03753, over 1429132.18 frames.], batch size: 18, lr: 4.07e-04
+2022-05-14 23:52:18,560 INFO [train.py:812] (1/8) Epoch 19, batch 3200, loss[loss=0.1605, simple_loss=0.2578, pruned_loss=0.03157, over 7160.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2546, pruned_loss=0.03754, over 1427409.94 frames.], batch size: 19, lr: 4.07e-04
+2022-05-14 23:53:18,019 INFO [train.py:812] (1/8) Epoch 19, batch 3250, loss[loss=0.1517, simple_loss=0.2401, pruned_loss=0.0317, over 7362.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2561, pruned_loss=0.03806, over 1424481.53 frames.], batch size: 19, lr: 4.07e-04
+2022-05-14 23:54:16,314 INFO [train.py:812] (1/8) Epoch 19, batch 3300, loss[loss=0.166, simple_loss=0.2622, pruned_loss=0.03493, over 6338.00 frames.], tot_loss[loss=0.166, simple_loss=0.256, pruned_loss=0.03807, over 1424461.05 frames.], batch size: 37, lr: 4.07e-04
+2022-05-14 23:55:15,319 INFO [train.py:812] (1/8) Epoch 19, batch 3350, loss[loss=0.163, simple_loss=0.2612, pruned_loss=0.03238, over 7132.00 frames.], tot_loss[loss=0.1649, simple_loss=0.255, pruned_loss=0.03736, over 1423472.02 frames.], batch size: 21, lr: 4.07e-04
+2022-05-14 23:56:14,418 INFO [train.py:812] (1/8) Epoch 19, batch 3400, loss[loss=0.1629, simple_loss=0.24, pruned_loss=0.04291, over 7257.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2547, pruned_loss=0.03724, over 1424092.42 frames.], batch size: 18, lr: 4.06e-04
+2022-05-14 23:57:14,011 INFO [train.py:812] (1/8) Epoch 19, batch 3450, loss[loss=0.1455, simple_loss=0.2415, pruned_loss=0.0247, over 7361.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2521, pruned_loss=0.03628, over 1420364.19 frames.], batch size: 19, lr: 4.06e-04
+2022-05-14 23:58:13,016 INFO [train.py:812] (1/8) Epoch 19, batch 3500, loss[loss=0.1359, simple_loss=0.2275, pruned_loss=0.02208, over 7279.00 frames.], tot_loss[loss=0.1619, simple_loss=0.252, pruned_loss=0.0359, over 1423087.55 frames.], batch size: 18, lr: 4.06e-04
+2022-05-14 23:59:12,605 INFO [train.py:812] (1/8) Epoch 19, batch 3550, loss[loss=0.1328, simple_loss=0.2041, pruned_loss=0.03077, over 7134.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2516, pruned_loss=0.03613, over 1423122.36 frames.], batch size: 17, lr: 4.06e-04
+2022-05-15 00:00:11,602 INFO [train.py:812] (1/8) Epoch 19, batch 3600, loss[loss=0.1734, simple_loss=0.262, pruned_loss=0.04243, over 7195.00 frames.], tot_loss[loss=0.1624, simple_loss=0.252, pruned_loss=0.03644, over 1420246.03 frames.], batch size: 23, lr: 4.06e-04
+2022-05-15 00:01:10,995 INFO [train.py:812] (1/8) Epoch 19, batch 3650, loss[loss=0.1764, simple_loss=0.2583, pruned_loss=0.04725, over 7329.00 frames.], tot_loss[loss=0.163, simple_loss=0.2526, pruned_loss=0.03674, over 1413459.34 frames.], batch size: 20, lr: 4.06e-04
+2022-05-15 00:02:10,009 INFO [train.py:812] (1/8) Epoch 19, batch 3700, loss[loss=0.1604, simple_loss=0.2602, pruned_loss=0.03031, over 7414.00 frames.], tot_loss[loss=0.164, simple_loss=0.2538, pruned_loss=0.03705, over 1415383.95 frames.], batch size: 21, lr: 4.06e-04
+2022-05-15 00:03:09,349 INFO [train.py:812] (1/8) Epoch 19, batch 3750, loss[loss=0.195, simple_loss=0.2814, pruned_loss=0.0543, over 7363.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2541, pruned_loss=0.03762, over 1411610.99 frames.], batch size: 23, lr: 4.06e-04
+2022-05-15 00:04:08,153 INFO [train.py:812] (1/8) Epoch 19, batch 3800, loss[loss=0.1596, simple_loss=0.2468, pruned_loss=0.03626, over 7371.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2545, pruned_loss=0.03739, over 1417178.77 frames.], batch size: 19, lr: 4.06e-04
+2022-05-15 00:05:06,746 INFO [train.py:812] (1/8) Epoch 19, batch 3850, loss[loss=0.1404, simple_loss=0.2264, pruned_loss=0.02726, over 7158.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2545, pruned_loss=0.03754, over 1415425.28 frames.], batch size: 18, lr: 4.05e-04
+2022-05-15 00:06:04,370 INFO [train.py:812] (1/8) Epoch 19, batch 3900, loss[loss=0.1724, simple_loss=0.2728, pruned_loss=0.03599, over 7115.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2555, pruned_loss=0.03785, over 1413430.05 frames.], batch size: 21, lr: 4.05e-04
+2022-05-15 00:07:04,144 INFO [train.py:812] (1/8) Epoch 19, batch 3950, loss[loss=0.1766, simple_loss=0.2675, pruned_loss=0.04289, over 7172.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2559, pruned_loss=0.0377, over 1416324.00 frames.], batch size: 18, lr: 4.05e-04
+2022-05-15 00:08:03,272 INFO [train.py:812] (1/8) Epoch 19, batch 4000, loss[loss=0.1799, simple_loss=0.271, pruned_loss=0.04442, over 5150.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2554, pruned_loss=0.03749, over 1417336.44 frames.], batch size: 52, lr: 4.05e-04
+2022-05-15 00:09:00,795 INFO [train.py:812] (1/8) Epoch 19, batch 4050, loss[loss=0.177, simple_loss=0.2521, pruned_loss=0.051, over 7282.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2544, pruned_loss=0.03743, over 1415792.25 frames.], batch size: 16, lr: 4.05e-04
+2022-05-15 00:09:59,475 INFO [train.py:812] (1/8) Epoch 19, batch 4100, loss[loss=0.1969, simple_loss=0.2799, pruned_loss=0.05695, over 5038.00 frames.], tot_loss[loss=0.1653, simple_loss=0.255, pruned_loss=0.0378, over 1415521.39 frames.], batch size: 52, lr: 4.05e-04
+2022-05-15 00:10:57,151 INFO [train.py:812] (1/8) Epoch 19, batch 4150, loss[loss=0.1517, simple_loss=0.2446, pruned_loss=0.02936, over 7373.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2536, pruned_loss=0.03747, over 1420801.67 frames.], batch size: 23, lr: 4.05e-04
+2022-05-15 00:11:56,835 INFO [train.py:812] (1/8) Epoch 19, batch 4200, loss[loss=0.164, simple_loss=0.2592, pruned_loss=0.03439, over 7184.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2533, pruned_loss=0.03689, over 1419118.40 frames.], batch size: 23, lr: 4.05e-04
+2022-05-15 00:12:56,144 INFO [train.py:812] (1/8) Epoch 19, batch 4250, loss[loss=0.1331, simple_loss=0.2163, pruned_loss=0.02493, over 6832.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2531, pruned_loss=0.03669, over 1419153.65 frames.], batch size: 15, lr: 4.04e-04
+2022-05-15 00:14:05,102 INFO [train.py:812] (1/8) Epoch 19, batch 4300, loss[loss=0.1792, simple_loss=0.2622, pruned_loss=0.04808, over 7131.00 frames.], tot_loss[loss=0.163, simple_loss=0.2531, pruned_loss=0.03646, over 1419059.43 frames.], batch size: 26, lr: 4.04e-04
+2022-05-15 00:15:04,945 INFO [train.py:812] (1/8) Epoch 19, batch 4350, loss[loss=0.1531, simple_loss=0.2376, pruned_loss=0.03428, over 7160.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2524, pruned_loss=0.03643, over 1416260.38 frames.], batch size: 18, lr: 4.04e-04
+2022-05-15 00:16:03,312 INFO [train.py:812] (1/8) Epoch 19, batch 4400, loss[loss=0.1852, simple_loss=0.2805, pruned_loss=0.04494, over 6329.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2525, pruned_loss=0.03692, over 1412576.70 frames.], batch size: 37, lr: 4.04e-04
+2022-05-15 00:17:02,482 INFO [train.py:812] (1/8) Epoch 19, batch 4450, loss[loss=0.1544, simple_loss=0.2389, pruned_loss=0.03495, over 6768.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2521, pruned_loss=0.03678, over 1407909.52 frames.], batch size: 15, lr: 4.04e-04
+2022-05-15 00:18:02,037 INFO [train.py:812] (1/8) Epoch 19, batch 4500, loss[loss=0.1626, simple_loss=0.2497, pruned_loss=0.03776, over 7152.00 frames.], tot_loss[loss=0.1637, simple_loss=0.253, pruned_loss=0.03723, over 1395235.22 frames.], batch size: 20, lr: 4.04e-04
+2022-05-15 00:19:01,077 INFO [train.py:812] (1/8) Epoch 19, batch 4550, loss[loss=0.1737, simple_loss=0.263, pruned_loss=0.04217, over 6401.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2527, pruned_loss=0.03816, over 1365601.21 frames.], batch size: 37, lr: 4.04e-04
+2022-05-15 00:20:09,405 INFO [train.py:812] (1/8) Epoch 20, batch 0, loss[loss=0.1477, simple_loss=0.2416, pruned_loss=0.02688, over 7359.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2416, pruned_loss=0.02688, over 7359.00 frames.], batch size: 19, lr: 3.94e-04
+2022-05-15 00:21:09,534 INFO [train.py:812] (1/8) Epoch 20, batch 50, loss[loss=0.148, simple_loss=0.2344, pruned_loss=0.03081, over 7296.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2534, pruned_loss=0.03557, over 321592.73 frames.], batch size: 18, lr: 3.94e-04
+2022-05-15 00:22:08,825 INFO [train.py:812] (1/8) Epoch 20, batch 100, loss[loss=0.1678, simple_loss=0.2586, pruned_loss=0.03848, over 5270.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2527, pruned_loss=0.03535, over 566239.59 frames.], batch size: 52, lr: 3.94e-04
+2022-05-15 00:23:08,480 INFO [train.py:812] (1/8) Epoch 20, batch 150, loss[loss=0.1772, simple_loss=0.2759, pruned_loss=0.03924, over 7310.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2544, pruned_loss=0.03588, over 756800.20 frames.], batch size: 21, lr: 3.94e-04
+2022-05-15 00:24:07,749 INFO [train.py:812] (1/8) Epoch 20, batch 200, loss[loss=0.1662, simple_loss=0.2667, pruned_loss=0.03283, over 7342.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2535, pruned_loss=0.03603, over 904543.61 frames.], batch size: 22, lr: 3.93e-04
+2022-05-15 00:25:08,006 INFO [train.py:812] (1/8) Epoch 20, batch 250, loss[loss=0.1749, simple_loss=0.2636, pruned_loss=0.0431, over 7339.00 frames.], tot_loss[loss=0.162, simple_loss=0.2517, pruned_loss=0.03611, over 1023641.10 frames.], batch size: 22, lr: 3.93e-04
+2022-05-15 00:26:07,267 INFO [train.py:812] (1/8) Epoch 20, batch 300, loss[loss=0.1801, simple_loss=0.2683, pruned_loss=0.04594, over 7207.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2523, pruned_loss=0.03568, over 1113428.54 frames.], batch size: 23, lr: 3.93e-04
+2022-05-15 00:27:07,173 INFO [train.py:812] (1/8) Epoch 20, batch 350, loss[loss=0.1583, simple_loss=0.2497, pruned_loss=0.03339, over 7150.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2539, pruned_loss=0.03682, over 1185903.45 frames.], batch size: 20, lr: 3.93e-04
+2022-05-15 00:28:05,116 INFO [train.py:812] (1/8) Epoch 20, batch 400, loss[loss=0.1551, simple_loss=0.2403, pruned_loss=0.0349, over 7139.00 frames.], tot_loss[loss=0.1645, simple_loss=0.255, pruned_loss=0.03699, over 1238795.19 frames.], batch size: 20, lr: 3.93e-04
+2022-05-15 00:29:03,591 INFO [train.py:812] (1/8) Epoch 20, batch 450, loss[loss=0.1994, simple_loss=0.2927, pruned_loss=0.05307, over 7370.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2555, pruned_loss=0.03704, over 1276509.52 frames.], batch size: 23, lr: 3.93e-04
+2022-05-15 00:30:01,850 INFO [train.py:812] (1/8) Epoch 20, batch 500, loss[loss=0.1668, simple_loss=0.2636, pruned_loss=0.03502, over 7226.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2554, pruned_loss=0.03699, over 1309065.18 frames.], batch size: 21, lr: 3.93e-04
+2022-05-15 00:31:00,459 INFO [train.py:812] (1/8) Epoch 20, batch 550, loss[loss=0.1651, simple_loss=0.2591, pruned_loss=0.03553, over 6694.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2539, pruned_loss=0.0364, over 1334730.04 frames.], batch size: 31, lr: 3.93e-04
+2022-05-15 00:32:00,097 INFO [train.py:812] (1/8) Epoch 20, batch 600, loss[loss=0.1395, simple_loss=0.2318, pruned_loss=0.02357, over 7163.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2523, pruned_loss=0.0359, over 1356021.80 frames.], batch size: 18, lr: 3.93e-04
+2022-05-15 00:32:59,170 INFO [train.py:812] (1/8) Epoch 20, batch 650, loss[loss=0.152, simple_loss=0.2289, pruned_loss=0.03754, over 7164.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2529, pruned_loss=0.03598, over 1369742.40 frames.], batch size: 18, lr: 3.92e-04
+2022-05-15 00:33:55,661 INFO [train.py:812] (1/8) Epoch 20, batch 700, loss[loss=0.1732, simple_loss=0.2587, pruned_loss=0.04386, over 7229.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2533, pruned_loss=0.03582, over 1383659.40 frames.], batch size: 20, lr: 3.92e-04
+2022-05-15 00:34:54,549 INFO [train.py:812] (1/8) Epoch 20, batch 750, loss[loss=0.1879, simple_loss=0.2727, pruned_loss=0.05149, over 7310.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2527, pruned_loss=0.03599, over 1393882.12 frames.], batch size: 25, lr: 3.92e-04
+2022-05-15 00:35:51,670 INFO [train.py:812] (1/8) Epoch 20, batch 800, loss[loss=0.1436, simple_loss=0.2223, pruned_loss=0.03249, over 7411.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2524, pruned_loss=0.03605, over 1403558.10 frames.], batch size: 18, lr: 3.92e-04
+2022-05-15 00:36:56,560 INFO [train.py:812] (1/8) Epoch 20, batch 850, loss[loss=0.1639, simple_loss=0.2438, pruned_loss=0.04199, over 7070.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2525, pruned_loss=0.03638, over 1410827.95 frames.], batch size: 28, lr: 3.92e-04
+2022-05-15 00:37:55,359 INFO [train.py:812] (1/8) Epoch 20, batch 900, loss[loss=0.1388, simple_loss=0.2377, pruned_loss=0.01995, over 7360.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2512, pruned_loss=0.03552, over 1416570.96 frames.], batch size: 19, lr: 3.92e-04
+2022-05-15 00:38:53,703 INFO [train.py:812] (1/8) Epoch 20, batch 950, loss[loss=0.1584, simple_loss=0.2495, pruned_loss=0.03371, over 7233.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2516, pruned_loss=0.03564, over 1419805.35 frames.], batch size: 20, lr: 3.92e-04
+2022-05-15 00:39:52,439 INFO [train.py:812] (1/8) Epoch 20, batch 1000, loss[loss=0.1714, simple_loss=0.2578, pruned_loss=0.04247, over 7314.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2519, pruned_loss=0.0359, over 1420928.65 frames.], batch size: 24, lr: 3.92e-04
+2022-05-15 00:40:51,835 INFO [train.py:812] (1/8) Epoch 20, batch 1050, loss[loss=0.1671, simple_loss=0.2538, pruned_loss=0.04017, over 7199.00 frames.], tot_loss[loss=0.1619, simple_loss=0.252, pruned_loss=0.0359, over 1420046.95 frames.], batch size: 22, lr: 3.92e-04
+2022-05-15 00:41:50,556 INFO [train.py:812] (1/8) Epoch 20, batch 1100, loss[loss=0.174, simple_loss=0.2652, pruned_loss=0.04137, over 7203.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2522, pruned_loss=0.0361, over 1416043.51 frames.], batch size: 22, lr: 3.91e-04
+2022-05-15 00:42:49,018 INFO [train.py:812] (1/8) Epoch 20, batch 1150, loss[loss=0.1951, simple_loss=0.3035, pruned_loss=0.04335, over 7294.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2528, pruned_loss=0.0359, over 1420420.37 frames.], batch size: 24, lr: 3.91e-04
+2022-05-15 00:43:48,217 INFO [train.py:812] (1/8) Epoch 20, batch 1200, loss[loss=0.1758, simple_loss=0.2693, pruned_loss=0.04116, over 7324.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2517, pruned_loss=0.03549, over 1424862.42 frames.], batch size: 22, lr: 3.91e-04
+2022-05-15 00:44:47,689 INFO [train.py:812] (1/8) Epoch 20, batch 1250, loss[loss=0.1722, simple_loss=0.2493, pruned_loss=0.0475, over 7136.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2514, pruned_loss=0.03576, over 1425644.63 frames.], batch size: 17, lr: 3.91e-04
+2022-05-15 00:45:46,806 INFO [train.py:812] (1/8) Epoch 20, batch 1300, loss[loss=0.1607, simple_loss=0.2602, pruned_loss=0.03056, over 7126.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2512, pruned_loss=0.03583, over 1427123.04 frames.], batch size: 21, lr: 3.91e-04
+2022-05-15 00:46:46,849 INFO [train.py:812] (1/8) Epoch 20, batch 1350, loss[loss=0.1676, simple_loss=0.2684, pruned_loss=0.03338, over 7211.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2523, pruned_loss=0.03607, over 1429313.87 frames.], batch size: 22, lr: 3.91e-04
+2022-05-15 00:47:55,899 INFO [train.py:812] (1/8) Epoch 20, batch 1400, loss[loss=0.1527, simple_loss=0.2491, pruned_loss=0.02816, over 7151.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2524, pruned_loss=0.036, over 1431127.20 frames.], batch size: 26, lr: 3.91e-04
+2022-05-15 00:48:55,550 INFO [train.py:812] (1/8) Epoch 20, batch 1450, loss[loss=0.194, simple_loss=0.2768, pruned_loss=0.05566, over 7149.00 frames.], tot_loss[loss=0.163, simple_loss=0.253, pruned_loss=0.03649, over 1429153.82 frames.], batch size: 26, lr: 3.91e-04
+2022-05-15 00:49:54,738 INFO [train.py:812] (1/8) Epoch 20, batch 1500, loss[loss=0.1844, simple_loss=0.2727, pruned_loss=0.04805, over 7383.00 frames.], tot_loss[loss=0.1639, simple_loss=0.254, pruned_loss=0.0369, over 1428135.90 frames.], batch size: 23, lr: 3.91e-04
+2022-05-15 00:51:04,078 INFO [train.py:812] (1/8) Epoch 20, batch 1550, loss[loss=0.1525, simple_loss=0.2417, pruned_loss=0.03171, over 7426.00 frames.], tot_loss[loss=0.1631, simple_loss=0.253, pruned_loss=0.03657, over 1429646.28 frames.], batch size: 20, lr: 3.91e-04
+2022-05-15 00:52:22,074 INFO [train.py:812] (1/8) Epoch 20, batch 1600, loss[loss=0.1448, simple_loss=0.2446, pruned_loss=0.02246, over 7327.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2538, pruned_loss=0.03692, over 1424000.20 frames.], batch size: 22, lr: 3.90e-04
+2022-05-15 00:53:19,532 INFO [train.py:812] (1/8) Epoch 20, batch 1650, loss[loss=0.1778, simple_loss=0.2696, pruned_loss=0.04296, over 7223.00 frames.], tot_loss[loss=0.1646, simple_loss=0.255, pruned_loss=0.03714, over 1421985.46 frames.], batch size: 23, lr: 3.90e-04
+2022-05-15 00:54:36,068 INFO [train.py:812] (1/8) Epoch 20, batch 1700, loss[loss=0.1226, simple_loss=0.2129, pruned_loss=0.0162, over 7159.00 frames.], tot_loss[loss=0.1638, simple_loss=0.254, pruned_loss=0.03682, over 1421283.84 frames.], batch size: 19, lr: 3.90e-04
+2022-05-15 00:55:43,688 INFO [train.py:812] (1/8) Epoch 20, batch 1750, loss[loss=0.1798, simple_loss=0.269, pruned_loss=0.04527, over 7339.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2545, pruned_loss=0.03721, over 1427140.95 frames.], batch size: 22, lr: 3.90e-04
+2022-05-15 00:56:42,593 INFO [train.py:812] (1/8) Epoch 20, batch 1800, loss[loss=0.1564, simple_loss=0.2444, pruned_loss=0.03421, over 7260.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2546, pruned_loss=0.03717, over 1425696.75 frames.], batch size: 25, lr: 3.90e-04
+2022-05-15 00:57:42,330 INFO [train.py:812] (1/8) Epoch 20, batch 1850, loss[loss=0.129, simple_loss=0.2192, pruned_loss=0.01944, over 7065.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2536, pruned_loss=0.03672, over 1428411.63 frames.], batch size: 18, lr: 3.90e-04
+2022-05-15 00:58:41,677 INFO [train.py:812] (1/8) Epoch 20, batch 1900, loss[loss=0.1433, simple_loss=0.2382, pruned_loss=0.02422, over 7235.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2543, pruned_loss=0.03693, over 1429037.48 frames.], batch size: 20, lr: 3.90e-04
+2022-05-15 00:59:40,059 INFO [train.py:812] (1/8) Epoch 20, batch 1950, loss[loss=0.1481, simple_loss=0.2418, pruned_loss=0.0272, over 6560.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2532, pruned_loss=0.03681, over 1429871.47 frames.], batch size: 38, lr: 3.90e-04
+2022-05-15 01:00:37,502 INFO [train.py:812] (1/8) Epoch 20, batch 2000, loss[loss=0.1533, simple_loss=0.2464, pruned_loss=0.03006, over 7238.00 frames.], tot_loss[loss=0.1621, simple_loss=0.252, pruned_loss=0.03614, over 1430898.06 frames.], batch size: 20, lr: 3.90e-04
+2022-05-15 01:01:35,458 INFO [train.py:812] (1/8) Epoch 20, batch 2050, loss[loss=0.1499, simple_loss=0.2454, pruned_loss=0.02724, over 7215.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2515, pruned_loss=0.03644, over 1430329.39 frames.], batch size: 21, lr: 3.89e-04
+2022-05-15 01:02:33,046 INFO [train.py:812] (1/8) Epoch 20, batch 2100, loss[loss=0.1644, simple_loss=0.2519, pruned_loss=0.03846, over 7424.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2517, pruned_loss=0.03685, over 1432989.64 frames.], batch size: 20, lr: 3.89e-04
+2022-05-15 01:03:30,906 INFO [train.py:812] (1/8) Epoch 20, batch 2150, loss[loss=0.1516, simple_loss=0.2309, pruned_loss=0.03615, over 7208.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2511, pruned_loss=0.0366, over 1426210.94 frames.], batch size: 22, lr: 3.89e-04
+2022-05-15 01:04:30,272 INFO [train.py:812] (1/8) Epoch 20, batch 2200, loss[loss=0.1376, simple_loss=0.225, pruned_loss=0.02507, over 6836.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2511, pruned_loss=0.03634, over 1421597.27 frames.], batch size: 15, lr: 3.89e-04
+2022-05-15 01:05:28,862 INFO [train.py:812] (1/8) Epoch 20, batch 2250, loss[loss=0.1488, simple_loss=0.2388, pruned_loss=0.02944, over 7144.00 frames.], tot_loss[loss=0.1618, simple_loss=0.251, pruned_loss=0.03628, over 1424449.12 frames.], batch size: 20, lr: 3.89e-04
+2022-05-15 01:06:27,811 INFO [train.py:812] (1/8) Epoch 20, batch 2300, loss[loss=0.1898, simple_loss=0.2829, pruned_loss=0.04835, over 7371.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2504, pruned_loss=0.03587, over 1424483.37 frames.], batch size: 23, lr: 3.89e-04
+2022-05-15 01:07:25,469 INFO [train.py:812] (1/8) Epoch 20, batch 2350, loss[loss=0.1913, simple_loss=0.2808, pruned_loss=0.05087, over 7316.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2515, pruned_loss=0.03589, over 1423434.20 frames.], batch size: 21, lr: 3.89e-04
+2022-05-15 01:08:24,202 INFO [train.py:812] (1/8) Epoch 20, batch 2400, loss[loss=0.1321, simple_loss=0.2268, pruned_loss=0.0187, over 7431.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2514, pruned_loss=0.0359, over 1424825.51 frames.], batch size: 20, lr: 3.89e-04
+2022-05-15 01:09:23,900 INFO [train.py:812] (1/8) Epoch 20, batch 2450, loss[loss=0.1631, simple_loss=0.256, pruned_loss=0.03505, over 7040.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2515, pruned_loss=0.03614, over 1427813.79 frames.], batch size: 28, lr: 3.89e-04
+2022-05-15 01:10:23,010 INFO [train.py:812] (1/8) Epoch 20, batch 2500, loss[loss=0.1623, simple_loss=0.2588, pruned_loss=0.03287, over 7122.00 frames.], tot_loss[loss=0.1612, simple_loss=0.251, pruned_loss=0.03567, over 1426314.33 frames.], batch size: 26, lr: 3.88e-04
+2022-05-15 01:11:22,815 INFO [train.py:812] (1/8) Epoch 20, batch 2550, loss[loss=0.1839, simple_loss=0.2699, pruned_loss=0.04894, over 7335.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2517, pruned_loss=0.03588, over 1425518.24 frames.], batch size: 20, lr: 3.88e-04
+2022-05-15 01:12:22,062 INFO [train.py:812] (1/8) Epoch 20, batch 2600, loss[loss=0.1817, simple_loss=0.2744, pruned_loss=0.04444, over 6782.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2519, pruned_loss=0.03599, over 1426361.38 frames.], batch size: 31, lr: 3.88e-04
+2022-05-15 01:13:22,175 INFO [train.py:812] (1/8) Epoch 20, batch 2650, loss[loss=0.1614, simple_loss=0.2405, pruned_loss=0.04114, over 7002.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2517, pruned_loss=0.03586, over 1427192.71 frames.], batch size: 16, lr: 3.88e-04
+2022-05-15 01:14:21,647 INFO [train.py:812] (1/8) Epoch 20, batch 2700, loss[loss=0.1845, simple_loss=0.2679, pruned_loss=0.0506, over 7381.00 frames.], tot_loss[loss=0.161, simple_loss=0.2507, pruned_loss=0.03561, over 1428086.19 frames.], batch size: 23, lr: 3.88e-04
+2022-05-15 01:15:21,495 INFO [train.py:812] (1/8) Epoch 20, batch 2750, loss[loss=0.1603, simple_loss=0.2543, pruned_loss=0.03319, over 7210.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2514, pruned_loss=0.03577, over 1427146.64 frames.], batch size: 23, lr: 3.88e-04
+2022-05-15 01:16:20,986 INFO [train.py:812] (1/8) Epoch 20, batch 2800, loss[loss=0.1484, simple_loss=0.2315, pruned_loss=0.03262, over 7159.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2508, pruned_loss=0.03527, over 1431286.46 frames.], batch size: 18, lr: 3.88e-04
+2022-05-15 01:17:20,823 INFO [train.py:812] (1/8) Epoch 20, batch 2850, loss[loss=0.1841, simple_loss=0.2733, pruned_loss=0.04744, over 7408.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2509, pruned_loss=0.03516, over 1433213.58 frames.], batch size: 21, lr: 3.88e-04
+2022-05-15 01:18:20,012 INFO [train.py:812] (1/8) Epoch 20, batch 2900, loss[loss=0.1388, simple_loss=0.2323, pruned_loss=0.02264, over 7205.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2506, pruned_loss=0.03487, over 1428479.73 frames.], batch size: 26, lr: 3.88e-04
+2022-05-15 01:19:19,543 INFO [train.py:812] (1/8) Epoch 20, batch 2950, loss[loss=0.1531, simple_loss=0.242, pruned_loss=0.03216, over 7225.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2514, pruned_loss=0.0352, over 1432238.00 frames.], batch size: 20, lr: 3.87e-04
+2022-05-15 01:20:18,528 INFO [train.py:812] (1/8) Epoch 20, batch 3000, loss[loss=0.1816, simple_loss=0.2812, pruned_loss=0.041, over 7391.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2523, pruned_loss=0.03544, over 1431493.53 frames.], batch size: 23, lr: 3.87e-04
+2022-05-15 01:20:18,529 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 01:20:27,134 INFO [train.py:841] (1/8) Epoch 20, validation: loss=0.1532, simple_loss=0.2519, pruned_loss=0.02723, over 698248.00 frames.
+2022-05-15 01:21:26,362 INFO [train.py:812] (1/8) Epoch 20, batch 3050, loss[loss=0.1484, simple_loss=0.2333, pruned_loss=0.03178, over 7155.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2526, pruned_loss=0.03564, over 1433153.47 frames.], batch size: 19, lr: 3.87e-04
+2022-05-15 01:22:25,323 INFO [train.py:812] (1/8) Epoch 20, batch 3100, loss[loss=0.1831, simple_loss=0.2756, pruned_loss=0.04531, over 7113.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2528, pruned_loss=0.03588, over 1431923.36 frames.], batch size: 21, lr: 3.87e-04
+2022-05-15 01:23:24,545 INFO [train.py:812] (1/8) Epoch 20, batch 3150, loss[loss=0.1665, simple_loss=0.2568, pruned_loss=0.03812, over 7285.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2527, pruned_loss=0.03599, over 1432754.29 frames.], batch size: 18, lr: 3.87e-04
+2022-05-15 01:24:21,343 INFO [train.py:812] (1/8) Epoch 20, batch 3200, loss[loss=0.1735, simple_loss=0.2755, pruned_loss=0.0358, over 6939.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2522, pruned_loss=0.0362, over 1432813.36 frames.], batch size: 32, lr: 3.87e-04
+2022-05-15 01:25:18,746 INFO [train.py:812] (1/8) Epoch 20, batch 3250, loss[loss=0.1655, simple_loss=0.2579, pruned_loss=0.03656, over 7068.00 frames.], tot_loss[loss=0.1631, simple_loss=0.253, pruned_loss=0.03658, over 1428873.77 frames.], batch size: 18, lr: 3.87e-04
+2022-05-15 01:26:16,473 INFO [train.py:812] (1/8) Epoch 20, batch 3300, loss[loss=0.1437, simple_loss=0.2346, pruned_loss=0.0264, over 7142.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2533, pruned_loss=0.03673, over 1427060.73 frames.], batch size: 17, lr: 3.87e-04
+2022-05-15 01:27:14,065 INFO [train.py:812] (1/8) Epoch 20, batch 3350, loss[loss=0.1585, simple_loss=0.2583, pruned_loss=0.02941, over 7147.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2526, pruned_loss=0.03638, over 1427273.57 frames.], batch size: 20, lr: 3.87e-04
+2022-05-15 01:28:13,195 INFO [train.py:812] (1/8) Epoch 20, batch 3400, loss[loss=0.1744, simple_loss=0.245, pruned_loss=0.05192, over 7274.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2522, pruned_loss=0.03617, over 1426667.77 frames.], batch size: 17, lr: 3.87e-04
+2022-05-15 01:29:12,297 INFO [train.py:812] (1/8) Epoch 20, batch 3450, loss[loss=0.159, simple_loss=0.2433, pruned_loss=0.03734, over 7241.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2527, pruned_loss=0.03633, over 1425941.01 frames.], batch size: 20, lr: 3.86e-04
+2022-05-15 01:30:11,788 INFO [train.py:812] (1/8) Epoch 20, batch 3500, loss[loss=0.1564, simple_loss=0.2395, pruned_loss=0.03665, over 7263.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2523, pruned_loss=0.03651, over 1424825.97 frames.], batch size: 19, lr: 3.86e-04
+2022-05-15 01:31:11,502 INFO [train.py:812] (1/8) Epoch 20, batch 3550, loss[loss=0.1436, simple_loss=0.2415, pruned_loss=0.02287, over 7111.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2528, pruned_loss=0.03622, over 1426899.20 frames.], batch size: 21, lr: 3.86e-04
+2022-05-15 01:32:11,001 INFO [train.py:812] (1/8) Epoch 20, batch 3600, loss[loss=0.185, simple_loss=0.2743, pruned_loss=0.04784, over 7192.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2528, pruned_loss=0.03654, over 1430059.02 frames.], batch size: 23, lr: 3.86e-04
+2022-05-15 01:33:10,980 INFO [train.py:812] (1/8) Epoch 20, batch 3650, loss[loss=0.1727, simple_loss=0.265, pruned_loss=0.04023, over 7325.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2523, pruned_loss=0.0363, over 1430471.57 frames.], batch size: 21, lr: 3.86e-04
+2022-05-15 01:34:09,098 INFO [train.py:812] (1/8) Epoch 20, batch 3700, loss[loss=0.1419, simple_loss=0.2319, pruned_loss=0.02593, over 7169.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2527, pruned_loss=0.0363, over 1432173.88 frames.], batch size: 18, lr: 3.86e-04
+2022-05-15 01:35:08,008 INFO [train.py:812] (1/8) Epoch 20, batch 3750, loss[loss=0.1708, simple_loss=0.2644, pruned_loss=0.03857, over 7043.00 frames.], tot_loss[loss=0.1622, simple_loss=0.252, pruned_loss=0.03619, over 1426161.83 frames.], batch size: 28, lr: 3.86e-04
+2022-05-15 01:36:06,433 INFO [train.py:812] (1/8) Epoch 20, batch 3800, loss[loss=0.1292, simple_loss=0.2247, pruned_loss=0.01683, over 7322.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2512, pruned_loss=0.03595, over 1422420.60 frames.], batch size: 20, lr: 3.86e-04
+2022-05-15 01:37:04,403 INFO [train.py:812] (1/8) Epoch 20, batch 3850, loss[loss=0.1384, simple_loss=0.222, pruned_loss=0.02744, over 7284.00 frames.], tot_loss[loss=0.1612, simple_loss=0.251, pruned_loss=0.03576, over 1420031.98 frames.], batch size: 17, lr: 3.86e-04
+2022-05-15 01:38:02,162 INFO [train.py:812] (1/8) Epoch 20, batch 3900, loss[loss=0.1397, simple_loss=0.2311, pruned_loss=0.02414, over 7119.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2521, pruned_loss=0.03621, over 1417580.90 frames.], batch size: 21, lr: 3.85e-04
+2022-05-15 01:39:01,289 INFO [train.py:812] (1/8) Epoch 20, batch 3950, loss[loss=0.1703, simple_loss=0.2678, pruned_loss=0.03636, over 7333.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2525, pruned_loss=0.03634, over 1411700.39 frames.], batch size: 20, lr: 3.85e-04
+2022-05-15 01:39:59,109 INFO [train.py:812] (1/8) Epoch 20, batch 4000, loss[loss=0.1529, simple_loss=0.2332, pruned_loss=0.03626, over 7166.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2525, pruned_loss=0.03669, over 1409755.05 frames.], batch size: 18, lr: 3.85e-04
+2022-05-15 01:40:58,263 INFO [train.py:812] (1/8) Epoch 20, batch 4050, loss[loss=0.1486, simple_loss=0.2486, pruned_loss=0.02431, over 7339.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2521, pruned_loss=0.03646, over 1406270.99 frames.], batch size: 20, lr: 3.85e-04
+2022-05-15 01:41:57,210 INFO [train.py:812] (1/8) Epoch 20, batch 4100, loss[loss=0.1545, simple_loss=0.2455, pruned_loss=0.03177, over 7282.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2507, pruned_loss=0.03604, over 1406522.45 frames.], batch size: 18, lr: 3.85e-04
+2022-05-15 01:42:56,561 INFO [train.py:812] (1/8) Epoch 20, batch 4150, loss[loss=0.1377, simple_loss=0.2254, pruned_loss=0.02497, over 7062.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2496, pruned_loss=0.0356, over 1410622.87 frames.], batch size: 18, lr: 3.85e-04
+2022-05-15 01:43:53,660 INFO [train.py:812] (1/8) Epoch 20, batch 4200, loss[loss=0.1578, simple_loss=0.2406, pruned_loss=0.03755, over 6782.00 frames.], tot_loss[loss=0.1605, simple_loss=0.25, pruned_loss=0.03554, over 1405775.92 frames.], batch size: 15, lr: 3.85e-04
+2022-05-15 01:44:52,597 INFO [train.py:812] (1/8) Epoch 20, batch 4250, loss[loss=0.16, simple_loss=0.2639, pruned_loss=0.02806, over 7199.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2497, pruned_loss=0.03553, over 1403384.71 frames.], batch size: 23, lr: 3.85e-04
+2022-05-15 01:45:49,895 INFO [train.py:812] (1/8) Epoch 20, batch 4300, loss[loss=0.2044, simple_loss=0.301, pruned_loss=0.05386, over 7228.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2505, pruned_loss=0.03563, over 1400214.76 frames.], batch size: 21, lr: 3.85e-04
+2022-05-15 01:46:48,981 INFO [train.py:812] (1/8) Epoch 20, batch 4350, loss[loss=0.2008, simple_loss=0.2846, pruned_loss=0.05856, over 5114.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2502, pruned_loss=0.03567, over 1403148.28 frames.], batch size: 53, lr: 3.84e-04
+2022-05-15 01:47:48,034 INFO [train.py:812] (1/8) Epoch 20, batch 4400, loss[loss=0.1458, simple_loss=0.2344, pruned_loss=0.02862, over 7168.00 frames.], tot_loss[loss=0.1606, simple_loss=0.25, pruned_loss=0.03564, over 1399388.30 frames.], batch size: 19, lr: 3.84e-04
+2022-05-15 01:48:47,113 INFO [train.py:812] (1/8) Epoch 20, batch 4450, loss[loss=0.1384, simple_loss=0.2164, pruned_loss=0.03018, over 7245.00 frames.], tot_loss[loss=0.1611, simple_loss=0.25, pruned_loss=0.03609, over 1392323.83 frames.], batch size: 16, lr: 3.84e-04
+2022-05-15 01:49:45,785 INFO [train.py:812] (1/8) Epoch 20, batch 4500, loss[loss=0.1719, simple_loss=0.2607, pruned_loss=0.04159, over 7185.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2511, pruned_loss=0.03627, over 1385517.24 frames.], batch size: 23, lr: 3.84e-04
+2022-05-15 01:50:44,400 INFO [train.py:812] (1/8) Epoch 20, batch 4550, loss[loss=0.1567, simple_loss=0.2484, pruned_loss=0.03253, over 6078.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2535, pruned_loss=0.03773, over 1338857.27 frames.], batch size: 37, lr: 3.84e-04
+2022-05-15 01:51:55,158 INFO [train.py:812] (1/8) Epoch 21, batch 0, loss[loss=0.1643, simple_loss=0.2552, pruned_loss=0.03672, over 7006.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2552, pruned_loss=0.03672, over 7006.00 frames.], batch size: 16, lr: 3.75e-04
+2022-05-15 01:52:54,953 INFO [train.py:812] (1/8) Epoch 21, batch 50, loss[loss=0.1546, simple_loss=0.2439, pruned_loss=0.03264, over 6394.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2492, pruned_loss=0.03505, over 323507.03 frames.], batch size: 38, lr: 3.75e-04
+2022-05-15 01:53:53,831 INFO [train.py:812] (1/8) Epoch 21, batch 100, loss[loss=0.1604, simple_loss=0.2544, pruned_loss=0.03321, over 6824.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2496, pruned_loss=0.03511, over 566887.58 frames.], batch size: 15, lr: 3.75e-04
+2022-05-15 01:54:52,689 INFO [train.py:812] (1/8) Epoch 21, batch 150, loss[loss=0.1474, simple_loss=0.2363, pruned_loss=0.0293, over 7156.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2507, pruned_loss=0.03522, over 756243.63 frames.], batch size: 18, lr: 3.75e-04
+2022-05-15 01:55:51,315 INFO [train.py:812] (1/8) Epoch 21, batch 200, loss[loss=0.1839, simple_loss=0.2894, pruned_loss=0.03922, over 6829.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2527, pruned_loss=0.03597, over 901710.04 frames.], batch size: 31, lr: 3.75e-04
+2022-05-15 01:56:53,953 INFO [train.py:812] (1/8) Epoch 21, batch 250, loss[loss=0.1575, simple_loss=0.2487, pruned_loss=0.03312, over 7152.00 frames.], tot_loss[loss=0.162, simple_loss=0.2523, pruned_loss=0.03587, over 1013659.43 frames.], batch size: 19, lr: 3.75e-04
+2022-05-15 01:57:52,812 INFO [train.py:812] (1/8) Epoch 21, batch 300, loss[loss=0.1669, simple_loss=0.259, pruned_loss=0.0374, over 7280.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2523, pruned_loss=0.03577, over 1102693.16 frames.], batch size: 18, lr: 3.75e-04
+2022-05-15 01:58:49,817 INFO [train.py:812] (1/8) Epoch 21, batch 350, loss[loss=0.1435, simple_loss=0.2249, pruned_loss=0.03105, over 7257.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2524, pruned_loss=0.03596, over 1170693.80 frames.], batch size: 19, lr: 3.74e-04
+2022-05-15 01:59:47,325 INFO [train.py:812] (1/8) Epoch 21, batch 400, loss[loss=0.1409, simple_loss=0.2204, pruned_loss=0.03069, over 7072.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2517, pruned_loss=0.03587, over 1229380.35 frames.], batch size: 18, lr: 3.74e-04
+2022-05-15 02:00:46,710 INFO [train.py:812] (1/8) Epoch 21, batch 450, loss[loss=0.1371, simple_loss=0.2265, pruned_loss=0.02382, over 7072.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2516, pruned_loss=0.03565, over 1271731.99 frames.], batch size: 18, lr: 3.74e-04
+2022-05-15 02:01:45,877 INFO [train.py:812] (1/8) Epoch 21, batch 500, loss[loss=0.1428, simple_loss=0.2324, pruned_loss=0.02659, over 7043.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2519, pruned_loss=0.03579, over 1310411.81 frames.], batch size: 28, lr: 3.74e-04
+2022-05-15 02:02:44,634 INFO [train.py:812] (1/8) Epoch 21, batch 550, loss[loss=0.15, simple_loss=0.234, pruned_loss=0.03297, over 6833.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2516, pruned_loss=0.03571, over 1336436.36 frames.], batch size: 15, lr: 3.74e-04
+2022-05-15 02:03:42,717 INFO [train.py:812] (1/8) Epoch 21, batch 600, loss[loss=0.157, simple_loss=0.2554, pruned_loss=0.02932, over 7210.00 frames.], tot_loss[loss=0.1615, simple_loss=0.252, pruned_loss=0.03547, over 1355452.33 frames.], batch size: 22, lr: 3.74e-04
+2022-05-15 02:04:42,154 INFO [train.py:812] (1/8) Epoch 21, batch 650, loss[loss=0.1462, simple_loss=0.2308, pruned_loss=0.03081, over 7145.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2499, pruned_loss=0.03497, over 1369900.26 frames.], batch size: 17, lr: 3.74e-04
+2022-05-15 02:05:41,116 INFO [train.py:812] (1/8) Epoch 21, batch 700, loss[loss=0.1552, simple_loss=0.2466, pruned_loss=0.03189, over 7234.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2507, pruned_loss=0.03479, over 1380005.24 frames.], batch size: 20, lr: 3.74e-04
+2022-05-15 02:06:40,199 INFO [train.py:812] (1/8) Epoch 21, batch 750, loss[loss=0.1266, simple_loss=0.2113, pruned_loss=0.02097, over 7414.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2515, pruned_loss=0.03541, over 1385244.50 frames.], batch size: 18, lr: 3.74e-04
+2022-05-15 02:07:37,515 INFO [train.py:812] (1/8) Epoch 21, batch 800, loss[loss=0.1517, simple_loss=0.2516, pruned_loss=0.0259, over 7228.00 frames.], tot_loss[loss=0.1606, simple_loss=0.251, pruned_loss=0.03513, over 1384758.86 frames.], batch size: 20, lr: 3.73e-04
+2022-05-15 02:08:37,253 INFO [train.py:812] (1/8) Epoch 21, batch 850, loss[loss=0.1682, simple_loss=0.2664, pruned_loss=0.03502, over 7314.00 frames.], tot_loss[loss=0.16, simple_loss=0.25, pruned_loss=0.03496, over 1391183.06 frames.], batch size: 25, lr: 3.73e-04
+2022-05-15 02:09:36,858 INFO [train.py:812] (1/8) Epoch 21, batch 900, loss[loss=0.1595, simple_loss=0.2493, pruned_loss=0.03487, over 7229.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2487, pruned_loss=0.0344, over 1399628.47 frames.], batch size: 20, lr: 3.73e-04
+2022-05-15 02:10:36,709 INFO [train.py:812] (1/8) Epoch 21, batch 950, loss[loss=0.16, simple_loss=0.2592, pruned_loss=0.03042, over 7328.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2492, pruned_loss=0.03455, over 1406192.52 frames.], batch size: 22, lr: 3.73e-04
+2022-05-15 02:11:34,900 INFO [train.py:812] (1/8) Epoch 21, batch 1000, loss[loss=0.2044, simple_loss=0.2863, pruned_loss=0.06122, over 7204.00 frames.], tot_loss[loss=0.1596, simple_loss=0.25, pruned_loss=0.03456, over 1405226.88 frames.], batch size: 23, lr: 3.73e-04
+2022-05-15 02:12:42,503 INFO [train.py:812] (1/8) Epoch 21, batch 1050, loss[loss=0.1421, simple_loss=0.2339, pruned_loss=0.02517, over 7398.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2501, pruned_loss=0.03423, over 1406381.55 frames.], batch size: 21, lr: 3.73e-04
+2022-05-15 02:13:41,818 INFO [train.py:812] (1/8) Epoch 21, batch 1100, loss[loss=0.1571, simple_loss=0.2381, pruned_loss=0.03801, over 7219.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2495, pruned_loss=0.03383, over 1408211.80 frames.], batch size: 16, lr: 3.73e-04
+2022-05-15 02:14:40,537 INFO [train.py:812] (1/8) Epoch 21, batch 1150, loss[loss=0.166, simple_loss=0.2639, pruned_loss=0.03402, over 7293.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2499, pruned_loss=0.0338, over 1413302.81 frames.], batch size: 24, lr: 3.73e-04
+2022-05-15 02:15:37,789 INFO [train.py:812] (1/8) Epoch 21, batch 1200, loss[loss=0.1541, simple_loss=0.2426, pruned_loss=0.03279, over 7290.00 frames.], tot_loss[loss=0.16, simple_loss=0.2513, pruned_loss=0.03432, over 1416540.27 frames.], batch size: 18, lr: 3.73e-04
+2022-05-15 02:16:37,260 INFO [train.py:812] (1/8) Epoch 21, batch 1250, loss[loss=0.1854, simple_loss=0.2844, pruned_loss=0.04321, over 7287.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2505, pruned_loss=0.03459, over 1418188.87 frames.], batch size: 24, lr: 3.73e-04
+2022-05-15 02:17:36,462 INFO [train.py:812] (1/8) Epoch 21, batch 1300, loss[loss=0.1442, simple_loss=0.2315, pruned_loss=0.02844, over 7054.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2493, pruned_loss=0.03412, over 1417007.57 frames.], batch size: 18, lr: 3.72e-04
+2022-05-15 02:18:34,032 INFO [train.py:812] (1/8) Epoch 21, batch 1350, loss[loss=0.1656, simple_loss=0.2646, pruned_loss=0.0333, over 7340.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2494, pruned_loss=0.03411, over 1424155.17 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:19:32,905 INFO [train.py:812] (1/8) Epoch 21, batch 1400, loss[loss=0.1736, simple_loss=0.2588, pruned_loss=0.04418, over 7370.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2497, pruned_loss=0.03454, over 1426418.47 frames.], batch size: 23, lr: 3.72e-04
+2022-05-15 02:20:31,799 INFO [train.py:812] (1/8) Epoch 21, batch 1450, loss[loss=0.2087, simple_loss=0.295, pruned_loss=0.06117, over 5290.00 frames.], tot_loss[loss=0.1601, simple_loss=0.25, pruned_loss=0.03513, over 1420838.22 frames.], batch size: 52, lr: 3.72e-04
+2022-05-15 02:21:30,166 INFO [train.py:812] (1/8) Epoch 21, batch 1500, loss[loss=0.1729, simple_loss=0.2715, pruned_loss=0.03717, over 7320.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2512, pruned_loss=0.03527, over 1418874.24 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:22:29,837 INFO [train.py:812] (1/8) Epoch 21, batch 1550, loss[loss=0.1974, simple_loss=0.288, pruned_loss=0.0534, over 6843.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2519, pruned_loss=0.0357, over 1420269.71 frames.], batch size: 31, lr: 3.72e-04
+2022-05-15 02:23:26,744 INFO [train.py:812] (1/8) Epoch 21, batch 1600, loss[loss=0.167, simple_loss=0.264, pruned_loss=0.03495, over 7335.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2523, pruned_loss=0.03538, over 1422311.35 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:24:25,701 INFO [train.py:812] (1/8) Epoch 21, batch 1650, loss[loss=0.1424, simple_loss=0.2422, pruned_loss=0.02128, over 7328.00 frames.], tot_loss[loss=0.162, simple_loss=0.2526, pruned_loss=0.03576, over 1424224.19 frames.], batch size: 20, lr: 3.72e-04
+2022-05-15 02:25:24,257 INFO [train.py:812] (1/8) Epoch 21, batch 1700, loss[loss=0.1579, simple_loss=0.2524, pruned_loss=0.03172, over 7333.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2524, pruned_loss=0.0356, over 1423459.67 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:26:22,314 INFO [train.py:812] (1/8) Epoch 21, batch 1750, loss[loss=0.1565, simple_loss=0.2361, pruned_loss=0.03851, over 7396.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2518, pruned_loss=0.03504, over 1423581.62 frames.], batch size: 18, lr: 3.72e-04
+2022-05-15 02:27:21,188 INFO [train.py:812] (1/8) Epoch 21, batch 1800, loss[loss=0.1815, simple_loss=0.2792, pruned_loss=0.04188, over 7180.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2511, pruned_loss=0.0347, over 1424932.69 frames.], batch size: 23, lr: 3.71e-04
+2022-05-15 02:28:20,360 INFO [train.py:812] (1/8) Epoch 21, batch 1850, loss[loss=0.1541, simple_loss=0.2406, pruned_loss=0.0338, over 7408.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2506, pruned_loss=0.0348, over 1423516.67 frames.], batch size: 18, lr: 3.71e-04
+2022-05-15 02:29:19,100 INFO [train.py:812] (1/8) Epoch 21, batch 1900, loss[loss=0.1419, simple_loss=0.2355, pruned_loss=0.02416, over 7158.00 frames.], tot_loss[loss=0.1606, simple_loss=0.251, pruned_loss=0.03516, over 1424659.17 frames.], batch size: 19, lr: 3.71e-04
+2022-05-15 02:30:18,943 INFO [train.py:812] (1/8) Epoch 21, batch 1950, loss[loss=0.1416, simple_loss=0.2294, pruned_loss=0.02689, over 7260.00 frames.], tot_loss[loss=0.1607, simple_loss=0.251, pruned_loss=0.03517, over 1428007.70 frames.], batch size: 19, lr: 3.71e-04
+2022-05-15 02:31:18,444 INFO [train.py:812] (1/8) Epoch 21, batch 2000, loss[loss=0.1645, simple_loss=0.2554, pruned_loss=0.03681, over 6723.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2507, pruned_loss=0.03521, over 1424108.79 frames.], batch size: 31, lr: 3.71e-04
+2022-05-15 02:32:18,148 INFO [train.py:812] (1/8) Epoch 21, batch 2050, loss[loss=0.1833, simple_loss=0.2808, pruned_loss=0.04292, over 7223.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2512, pruned_loss=0.0352, over 1423793.92 frames.], batch size: 21, lr: 3.71e-04
+2022-05-15 02:33:17,364 INFO [train.py:812] (1/8) Epoch 21, batch 2100, loss[loss=0.1694, simple_loss=0.2515, pruned_loss=0.04368, over 7064.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2512, pruned_loss=0.03524, over 1422849.21 frames.], batch size: 18, lr: 3.71e-04
+2022-05-15 02:34:16,891 INFO [train.py:812] (1/8) Epoch 21, batch 2150, loss[loss=0.1425, simple_loss=0.2244, pruned_loss=0.03027, over 7261.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2507, pruned_loss=0.035, over 1422732.10 frames.], batch size: 16, lr: 3.71e-04
+2022-05-15 02:35:14,481 INFO [train.py:812] (1/8) Epoch 21, batch 2200, loss[loss=0.1921, simple_loss=0.2859, pruned_loss=0.04911, over 7203.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2498, pruned_loss=0.03466, over 1425688.04 frames.], batch size: 22, lr: 3.71e-04
+2022-05-15 02:36:12,370 INFO [train.py:812] (1/8) Epoch 21, batch 2250, loss[loss=0.1379, simple_loss=0.2295, pruned_loss=0.02315, over 7204.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2511, pruned_loss=0.03518, over 1426767.23 frames.], batch size: 22, lr: 3.71e-04
+2022-05-15 02:37:12,524 INFO [train.py:812] (1/8) Epoch 21, batch 2300, loss[loss=0.1854, simple_loss=0.2695, pruned_loss=0.05059, over 4813.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2507, pruned_loss=0.03548, over 1423340.23 frames.], batch size: 53, lr: 3.71e-04
+2022-05-15 02:38:11,393 INFO [train.py:812] (1/8) Epoch 21, batch 2350, loss[loss=0.1659, simple_loss=0.261, pruned_loss=0.03542, over 7286.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2523, pruned_loss=0.03623, over 1418694.31 frames.], batch size: 24, lr: 3.70e-04
+2022-05-15 02:39:10,735 INFO [train.py:812] (1/8) Epoch 21, batch 2400, loss[loss=0.1521, simple_loss=0.2502, pruned_loss=0.02701, over 7203.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2514, pruned_loss=0.03605, over 1421434.06 frames.], batch size: 23, lr: 3.70e-04
+2022-05-15 02:40:10,443 INFO [train.py:812] (1/8) Epoch 21, batch 2450, loss[loss=0.1569, simple_loss=0.2475, pruned_loss=0.03313, over 7152.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2512, pruned_loss=0.03575, over 1422779.76 frames.], batch size: 19, lr: 3.70e-04
+2022-05-15 02:41:09,422 INFO [train.py:812] (1/8) Epoch 21, batch 2500, loss[loss=0.1481, simple_loss=0.2458, pruned_loss=0.02522, over 7416.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2509, pruned_loss=0.03584, over 1423398.05 frames.], batch size: 21, lr: 3.70e-04
+2022-05-15 02:42:07,848 INFO [train.py:812] (1/8) Epoch 21, batch 2550, loss[loss=0.1801, simple_loss=0.2659, pruned_loss=0.04717, over 5029.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2523, pruned_loss=0.03616, over 1421211.34 frames.], batch size: 52, lr: 3.70e-04
+2022-05-15 02:43:06,156 INFO [train.py:812] (1/8) Epoch 21, batch 2600, loss[loss=0.158, simple_loss=0.2398, pruned_loss=0.03812, over 7067.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2527, pruned_loss=0.03611, over 1421899.57 frames.], batch size: 18, lr: 3.70e-04
+2022-05-15 02:44:05,920 INFO [train.py:812] (1/8) Epoch 21, batch 2650, loss[loss=0.1574, simple_loss=0.2363, pruned_loss=0.03918, over 7320.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2525, pruned_loss=0.03617, over 1417073.18 frames.], batch size: 20, lr: 3.70e-04
+2022-05-15 02:45:04,655 INFO [train.py:812] (1/8) Epoch 21, batch 2700, loss[loss=0.1329, simple_loss=0.2112, pruned_loss=0.02725, over 7406.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2514, pruned_loss=0.03552, over 1420747.23 frames.], batch size: 18, lr: 3.70e-04
+2022-05-15 02:46:03,780 INFO [train.py:812] (1/8) Epoch 21, batch 2750, loss[loss=0.1427, simple_loss=0.2309, pruned_loss=0.02719, over 7159.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2517, pruned_loss=0.03554, over 1422194.42 frames.], batch size: 18, lr: 3.70e-04
+2022-05-15 02:47:03,046 INFO [train.py:812] (1/8) Epoch 21, batch 2800, loss[loss=0.1763, simple_loss=0.2661, pruned_loss=0.04328, over 7386.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2507, pruned_loss=0.03487, over 1425370.47 frames.], batch size: 23, lr: 3.70e-04
+2022-05-15 02:48:12,154 INFO [train.py:812] (1/8) Epoch 21, batch 2850, loss[loss=0.1516, simple_loss=0.2481, pruned_loss=0.02751, over 7217.00 frames.], tot_loss[loss=0.1605, simple_loss=0.251, pruned_loss=0.03501, over 1420483.92 frames.], batch size: 23, lr: 3.69e-04
+2022-05-15 02:49:11,140 INFO [train.py:812] (1/8) Epoch 21, batch 2900, loss[loss=0.1487, simple_loss=0.2401, pruned_loss=0.0286, over 7062.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2505, pruned_loss=0.0349, over 1415837.90 frames.], batch size: 28, lr: 3.69e-04
+2022-05-15 02:50:09,818 INFO [train.py:812] (1/8) Epoch 21, batch 2950, loss[loss=0.1596, simple_loss=0.2455, pruned_loss=0.03689, over 7356.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2511, pruned_loss=0.03494, over 1415047.45 frames.], batch size: 19, lr: 3.69e-04
+2022-05-15 02:51:09,039 INFO [train.py:812] (1/8) Epoch 21, batch 3000, loss[loss=0.169, simple_loss=0.2627, pruned_loss=0.03761, over 6785.00 frames.], tot_loss[loss=0.1606, simple_loss=0.251, pruned_loss=0.0351, over 1414926.03 frames.], batch size: 31, lr: 3.69e-04
+2022-05-15 02:51:09,040 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 02:51:16,350 INFO [train.py:841] (1/8) Epoch 21, validation: loss=0.153, simple_loss=0.2519, pruned_loss=0.02704, over 698248.00 frames.
+2022-05-15 02:52:35,379 INFO [train.py:812] (1/8) Epoch 21, batch 3050, loss[loss=0.1376, simple_loss=0.2312, pruned_loss=0.02199, over 7272.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2501, pruned_loss=0.03469, over 1415654.28 frames.], batch size: 18, lr: 3.69e-04
+2022-05-15 02:53:32,968 INFO [train.py:812] (1/8) Epoch 21, batch 3100, loss[loss=0.1714, simple_loss=0.259, pruned_loss=0.0419, over 7384.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2514, pruned_loss=0.03556, over 1413675.49 frames.], batch size: 23, lr: 3.69e-04
+2022-05-15 02:55:01,535 INFO [train.py:812] (1/8) Epoch 21, batch 3150, loss[loss=0.1814, simple_loss=0.2675, pruned_loss=0.04762, over 7290.00 frames.], tot_loss[loss=0.1624, simple_loss=0.252, pruned_loss=0.03638, over 1419024.80 frames.], batch size: 24, lr: 3.69e-04
+2022-05-15 02:56:00,662 INFO [train.py:812] (1/8) Epoch 21, batch 3200, loss[loss=0.1662, simple_loss=0.2657, pruned_loss=0.03337, over 7314.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2531, pruned_loss=0.0367, over 1423224.25 frames.], batch size: 21, lr: 3.69e-04
+2022-05-15 02:57:00,396 INFO [train.py:812] (1/8) Epoch 21, batch 3250, loss[loss=0.1571, simple_loss=0.2557, pruned_loss=0.0293, over 7064.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2522, pruned_loss=0.03605, over 1421642.76 frames.], batch size: 18, lr: 3.69e-04
+2022-05-15 02:58:08,761 INFO [train.py:812] (1/8) Epoch 21, batch 3300, loss[loss=0.1595, simple_loss=0.2388, pruned_loss=0.04005, over 7134.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2516, pruned_loss=0.0357, over 1423012.38 frames.], batch size: 17, lr: 3.69e-04
+2022-05-15 02:59:08,377 INFO [train.py:812] (1/8) Epoch 21, batch 3350, loss[loss=0.1831, simple_loss=0.2858, pruned_loss=0.04019, over 7234.00 frames.], tot_loss[loss=0.162, simple_loss=0.2519, pruned_loss=0.03603, over 1419750.17 frames.], batch size: 20, lr: 3.68e-04
+2022-05-15 03:00:06,799 INFO [train.py:812] (1/8) Epoch 21, batch 3400, loss[loss=0.1711, simple_loss=0.2579, pruned_loss=0.04213, over 6624.00 frames.], tot_loss[loss=0.162, simple_loss=0.2521, pruned_loss=0.03592, over 1416672.46 frames.], batch size: 38, lr: 3.68e-04
+2022-05-15 03:01:06,180 INFO [train.py:812] (1/8) Epoch 21, batch 3450, loss[loss=0.1816, simple_loss=0.286, pruned_loss=0.03862, over 7319.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2526, pruned_loss=0.03595, over 1414887.11 frames.], batch size: 21, lr: 3.68e-04
+2022-05-15 03:02:05,069 INFO [train.py:812] (1/8) Epoch 21, batch 3500, loss[loss=0.1702, simple_loss=0.2706, pruned_loss=0.03492, over 7015.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2527, pruned_loss=0.03595, over 1409934.45 frames.], batch size: 28, lr: 3.68e-04
+2022-05-15 03:03:04,129 INFO [train.py:812] (1/8) Epoch 21, batch 3550, loss[loss=0.1585, simple_loss=0.2338, pruned_loss=0.04164, over 7280.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2513, pruned_loss=0.03515, over 1413427.80 frames.], batch size: 17, lr: 3.68e-04
+2022-05-15 03:04:02,912 INFO [train.py:812] (1/8) Epoch 21, batch 3600, loss[loss=0.1787, simple_loss=0.2704, pruned_loss=0.04348, over 7383.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2519, pruned_loss=0.03558, over 1411106.99 frames.], batch size: 23, lr: 3.68e-04
+2022-05-15 03:05:02,885 INFO [train.py:812] (1/8) Epoch 21, batch 3650, loss[loss=0.1733, simple_loss=0.2723, pruned_loss=0.03711, over 7136.00 frames.], tot_loss[loss=0.1618, simple_loss=0.252, pruned_loss=0.03581, over 1412775.07 frames.], batch size: 26, lr: 3.68e-04
+2022-05-15 03:06:01,339 INFO [train.py:812] (1/8) Epoch 21, batch 3700, loss[loss=0.1575, simple_loss=0.251, pruned_loss=0.03206, over 7323.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2518, pruned_loss=0.03571, over 1413414.42 frames.], batch size: 21, lr: 3.68e-04
+2022-05-15 03:07:01,119 INFO [train.py:812] (1/8) Epoch 21, batch 3750, loss[loss=0.1658, simple_loss=0.2518, pruned_loss=0.03987, over 7317.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2515, pruned_loss=0.03598, over 1416742.19 frames.], batch size: 25, lr: 3.68e-04
+2022-05-15 03:07:59,609 INFO [train.py:812] (1/8) Epoch 21, batch 3800, loss[loss=0.1773, simple_loss=0.2624, pruned_loss=0.04615, over 7104.00 frames.], tot_loss[loss=0.1611, simple_loss=0.251, pruned_loss=0.03562, over 1417117.99 frames.], batch size: 26, lr: 3.68e-04
+2022-05-15 03:08:58,689 INFO [train.py:812] (1/8) Epoch 21, batch 3850, loss[loss=0.1753, simple_loss=0.2745, pruned_loss=0.03803, over 7329.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2511, pruned_loss=0.03533, over 1418459.82 frames.], batch size: 20, lr: 3.68e-04
+2022-05-15 03:09:55,531 INFO [train.py:812] (1/8) Epoch 21, batch 3900, loss[loss=0.1947, simple_loss=0.2844, pruned_loss=0.05252, over 7255.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2518, pruned_loss=0.03571, over 1421800.09 frames.], batch size: 19, lr: 3.67e-04
+2022-05-15 03:10:53,476 INFO [train.py:812] (1/8) Epoch 21, batch 3950, loss[loss=0.1413, simple_loss=0.2292, pruned_loss=0.02667, over 7392.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2525, pruned_loss=0.0359, over 1416797.10 frames.], batch size: 18, lr: 3.67e-04
+2022-05-15 03:11:51,917 INFO [train.py:812] (1/8) Epoch 21, batch 4000, loss[loss=0.1529, simple_loss=0.2453, pruned_loss=0.03024, over 7360.00 frames.], tot_loss[loss=0.1614, simple_loss=0.252, pruned_loss=0.03542, over 1420929.12 frames.], batch size: 19, lr: 3.67e-04
+2022-05-15 03:12:50,955 INFO [train.py:812] (1/8) Epoch 21, batch 4050, loss[loss=0.1989, simple_loss=0.2805, pruned_loss=0.05861, over 4902.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2509, pruned_loss=0.0353, over 1418097.94 frames.], batch size: 52, lr: 3.67e-04
+2022-05-15 03:13:49,288 INFO [train.py:812] (1/8) Epoch 21, batch 4100, loss[loss=0.1516, simple_loss=0.2603, pruned_loss=0.02146, over 7218.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2516, pruned_loss=0.03557, over 1409672.87 frames.], batch size: 21, lr: 3.67e-04
+2022-05-15 03:14:46,151 INFO [train.py:812] (1/8) Epoch 21, batch 4150, loss[loss=0.1563, simple_loss=0.24, pruned_loss=0.03634, over 7073.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2524, pruned_loss=0.03573, over 1411442.58 frames.], batch size: 18, lr: 3.67e-04
+2022-05-15 03:15:43,927 INFO [train.py:812] (1/8) Epoch 21, batch 4200, loss[loss=0.1823, simple_loss=0.2755, pruned_loss=0.04451, over 6803.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2528, pruned_loss=0.03581, over 1410560.99 frames.], batch size: 31, lr: 3.67e-04
+2022-05-15 03:16:47,806 INFO [train.py:812] (1/8) Epoch 21, batch 4250, loss[loss=0.1806, simple_loss=0.2793, pruned_loss=0.04097, over 7218.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2522, pruned_loss=0.03544, over 1415261.11 frames.], batch size: 21, lr: 3.67e-04
+2022-05-15 03:17:46,888 INFO [train.py:812] (1/8) Epoch 21, batch 4300, loss[loss=0.1693, simple_loss=0.2629, pruned_loss=0.03783, over 7317.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2518, pruned_loss=0.03498, over 1416298.44 frames.], batch size: 24, lr: 3.67e-04
+2022-05-15 03:18:45,852 INFO [train.py:812] (1/8) Epoch 21, batch 4350, loss[loss=0.1568, simple_loss=0.2648, pruned_loss=0.02435, over 7227.00 frames.], tot_loss[loss=0.1609, simple_loss=0.252, pruned_loss=0.03492, over 1416007.65 frames.], batch size: 21, lr: 3.67e-04
+2022-05-15 03:19:43,038 INFO [train.py:812] (1/8) Epoch 21, batch 4400, loss[loss=0.157, simple_loss=0.239, pruned_loss=0.03752, over 7158.00 frames.], tot_loss[loss=0.161, simple_loss=0.252, pruned_loss=0.03494, over 1415240.79 frames.], batch size: 18, lr: 3.66e-04
+2022-05-15 03:20:42,007 INFO [train.py:812] (1/8) Epoch 21, batch 4450, loss[loss=0.1573, simple_loss=0.2444, pruned_loss=0.03512, over 6986.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2523, pruned_loss=0.03521, over 1407703.35 frames.], batch size: 16, lr: 3.66e-04
+2022-05-15 03:21:40,277 INFO [train.py:812] (1/8) Epoch 21, batch 4500, loss[loss=0.1272, simple_loss=0.2176, pruned_loss=0.01838, over 6997.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2523, pruned_loss=0.03511, over 1410740.51 frames.], batch size: 16, lr: 3.66e-04
+2022-05-15 03:22:39,942 INFO [train.py:812] (1/8) Epoch 21, batch 4550, loss[loss=0.1905, simple_loss=0.2761, pruned_loss=0.05245, over 5166.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2515, pruned_loss=0.03563, over 1394593.58 frames.], batch size: 52, lr: 3.66e-04
+2022-05-15 03:23:52,241 INFO [train.py:812] (1/8) Epoch 22, batch 0, loss[loss=0.1677, simple_loss=0.2653, pruned_loss=0.03502, over 7299.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2653, pruned_loss=0.03502, over 7299.00 frames.], batch size: 25, lr: 3.58e-04
+2022-05-15 03:24:50,141 INFO [train.py:812] (1/8) Epoch 22, batch 50, loss[loss=0.1327, simple_loss=0.2171, pruned_loss=0.02418, over 7167.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2527, pruned_loss=0.03475, over 318506.41 frames.], batch size: 18, lr: 3.58e-04
+2022-05-15 03:25:49,149 INFO [train.py:812] (1/8) Epoch 22, batch 100, loss[loss=0.1811, simple_loss=0.2743, pruned_loss=0.04394, over 7113.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2506, pruned_loss=0.03511, over 564768.09 frames.], batch size: 21, lr: 3.58e-04
+2022-05-15 03:26:47,182 INFO [train.py:812] (1/8) Epoch 22, batch 150, loss[loss=0.1752, simple_loss=0.2767, pruned_loss=0.0368, over 7321.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2512, pruned_loss=0.03531, over 754903.10 frames.], batch size: 21, lr: 3.58e-04
+2022-05-15 03:27:46,007 INFO [train.py:812] (1/8) Epoch 22, batch 200, loss[loss=0.1457, simple_loss=0.2422, pruned_loss=0.02462, over 7342.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2516, pruned_loss=0.03533, over 902374.97 frames.], batch size: 22, lr: 3.58e-04
+2022-05-15 03:28:43,581 INFO [train.py:812] (1/8) Epoch 22, batch 250, loss[loss=0.1526, simple_loss=0.2424, pruned_loss=0.03145, over 7256.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2514, pruned_loss=0.03538, over 1016536.07 frames.], batch size: 19, lr: 3.57e-04
+2022-05-15 03:29:41,567 INFO [train.py:812] (1/8) Epoch 22, batch 300, loss[loss=0.1709, simple_loss=0.2568, pruned_loss=0.04245, over 7239.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2517, pruned_loss=0.03602, over 1108537.73 frames.], batch size: 20, lr: 3.57e-04
+2022-05-15 03:30:39,468 INFO [train.py:812] (1/8) Epoch 22, batch 350, loss[loss=0.1496, simple_loss=0.2418, pruned_loss=0.02873, over 7147.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2502, pruned_loss=0.03507, over 1178912.45 frames.], batch size: 19, lr: 3.57e-04
+2022-05-15 03:31:38,295 INFO [train.py:812] (1/8) Epoch 22, batch 400, loss[loss=0.1523, simple_loss=0.2542, pruned_loss=0.02522, over 7233.00 frames.], tot_loss[loss=0.16, simple_loss=0.2504, pruned_loss=0.03484, over 1231576.63 frames.], batch size: 21, lr: 3.57e-04
+2022-05-15 03:32:37,213 INFO [train.py:812] (1/8) Epoch 22, batch 450, loss[loss=0.2049, simple_loss=0.2939, pruned_loss=0.05793, over 5066.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2496, pruned_loss=0.03442, over 1275180.22 frames.], batch size: 55, lr: 3.57e-04
+2022-05-15 03:33:36,430 INFO [train.py:812] (1/8) Epoch 22, batch 500, loss[loss=0.187, simple_loss=0.2829, pruned_loss=0.04554, over 7317.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2513, pruned_loss=0.03483, over 1310502.70 frames.], batch size: 25, lr: 3.57e-04
+2022-05-15 03:34:33,237 INFO [train.py:812] (1/8) Epoch 22, batch 550, loss[loss=0.1391, simple_loss=0.2243, pruned_loss=0.02691, over 7439.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2516, pruned_loss=0.0351, over 1332872.05 frames.], batch size: 20, lr: 3.57e-04
+2022-05-15 03:35:32,154 INFO [train.py:812] (1/8) Epoch 22, batch 600, loss[loss=0.1685, simple_loss=0.2617, pruned_loss=0.03771, over 7338.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2507, pruned_loss=0.03486, over 1354260.77 frames.], batch size: 22, lr: 3.57e-04
+2022-05-15 03:36:31,009 INFO [train.py:812] (1/8) Epoch 22, batch 650, loss[loss=0.1604, simple_loss=0.2589, pruned_loss=0.03095, over 7330.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2512, pruned_loss=0.03468, over 1370884.75 frames.], batch size: 22, lr: 3.57e-04
+2022-05-15 03:37:30,482 INFO [train.py:812] (1/8) Epoch 22, batch 700, loss[loss=0.1962, simple_loss=0.281, pruned_loss=0.0557, over 7310.00 frames.], tot_loss[loss=0.1603, simple_loss=0.251, pruned_loss=0.03485, over 1378484.89 frames.], batch size: 25, lr: 3.57e-04
+2022-05-15 03:38:28,389 INFO [train.py:812] (1/8) Epoch 22, batch 750, loss[loss=0.1652, simple_loss=0.2479, pruned_loss=0.04129, over 7161.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2503, pruned_loss=0.03477, over 1387255.12 frames.], batch size: 18, lr: 3.57e-04
+2022-05-15 03:39:28,259 INFO [train.py:812] (1/8) Epoch 22, batch 800, loss[loss=0.1708, simple_loss=0.2789, pruned_loss=0.03136, over 7286.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2509, pruned_loss=0.03484, over 1399959.21 frames.], batch size: 25, lr: 3.56e-04
+2022-05-15 03:40:27,691 INFO [train.py:812] (1/8) Epoch 22, batch 850, loss[loss=0.1614, simple_loss=0.2496, pruned_loss=0.03659, over 7403.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2515, pruned_loss=0.03529, over 1405405.62 frames.], batch size: 18, lr: 3.56e-04
+2022-05-15 03:41:26,075 INFO [train.py:812] (1/8) Epoch 22, batch 900, loss[loss=0.1873, simple_loss=0.2733, pruned_loss=0.05067, over 6361.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2517, pruned_loss=0.0356, over 1409537.36 frames.], batch size: 37, lr: 3.56e-04
+2022-05-15 03:42:25,444 INFO [train.py:812] (1/8) Epoch 22, batch 950, loss[loss=0.1226, simple_loss=0.2069, pruned_loss=0.01912, over 7277.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2511, pruned_loss=0.03533, over 1411833.58 frames.], batch size: 18, lr: 3.56e-04
+2022-05-15 03:43:24,203 INFO [train.py:812] (1/8) Epoch 22, batch 1000, loss[loss=0.1644, simple_loss=0.2617, pruned_loss=0.03353, over 7157.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2523, pruned_loss=0.03596, over 1412082.70 frames.], batch size: 19, lr: 3.56e-04
+2022-05-15 03:44:23,451 INFO [train.py:812] (1/8) Epoch 22, batch 1050, loss[loss=0.1402, simple_loss=0.245, pruned_loss=0.01774, over 7324.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2512, pruned_loss=0.0356, over 1415246.40 frames.], batch size: 22, lr: 3.56e-04
+2022-05-15 03:45:23,001 INFO [train.py:812] (1/8) Epoch 22, batch 1100, loss[loss=0.1778, simple_loss=0.2714, pruned_loss=0.04213, over 6326.00 frames.], tot_loss[loss=0.161, simple_loss=0.2511, pruned_loss=0.03543, over 1418970.81 frames.], batch size: 37, lr: 3.56e-04
+2022-05-15 03:46:20,331 INFO [train.py:812] (1/8) Epoch 22, batch 1150, loss[loss=0.1534, simple_loss=0.2485, pruned_loss=0.02912, over 7262.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2501, pruned_loss=0.03482, over 1419811.58 frames.], batch size: 19, lr: 3.56e-04
+2022-05-15 03:47:19,437 INFO [train.py:812] (1/8) Epoch 22, batch 1200, loss[loss=0.1876, simple_loss=0.2818, pruned_loss=0.04672, over 7302.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2505, pruned_loss=0.03519, over 1420748.56 frames.], batch size: 25, lr: 3.56e-04
+2022-05-15 03:48:18,942 INFO [train.py:812] (1/8) Epoch 22, batch 1250, loss[loss=0.1371, simple_loss=0.2163, pruned_loss=0.02893, over 7001.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2506, pruned_loss=0.03489, over 1419810.76 frames.], batch size: 16, lr: 3.56e-04
+2022-05-15 03:49:19,106 INFO [train.py:812] (1/8) Epoch 22, batch 1300, loss[loss=0.1914, simple_loss=0.2764, pruned_loss=0.05315, over 7159.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2507, pruned_loss=0.03505, over 1418639.54 frames.], batch size: 19, lr: 3.56e-04
+2022-05-15 03:50:16,170 INFO [train.py:812] (1/8) Epoch 22, batch 1350, loss[loss=0.1595, simple_loss=0.2586, pruned_loss=0.03024, over 7418.00 frames.], tot_loss[loss=0.1599, simple_loss=0.25, pruned_loss=0.03488, over 1422878.79 frames.], batch size: 21, lr: 3.55e-04
+2022-05-15 03:51:15,331 INFO [train.py:812] (1/8) Epoch 22, batch 1400, loss[loss=0.1758, simple_loss=0.2663, pruned_loss=0.04267, over 7196.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2499, pruned_loss=0.03484, over 1419404.57 frames.], batch size: 22, lr: 3.55e-04
+2022-05-15 03:52:14,140 INFO [train.py:812] (1/8) Epoch 22, batch 1450, loss[loss=0.1596, simple_loss=0.2491, pruned_loss=0.03508, over 7436.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2505, pruned_loss=0.03509, over 1424739.75 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:53:13,826 INFO [train.py:812] (1/8) Epoch 22, batch 1500, loss[loss=0.1552, simple_loss=0.2561, pruned_loss=0.02722, over 7232.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2496, pruned_loss=0.03475, over 1426868.77 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:54:13,330 INFO [train.py:812] (1/8) Epoch 22, batch 1550, loss[loss=0.1536, simple_loss=0.2511, pruned_loss=0.02809, over 7236.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2497, pruned_loss=0.03466, over 1429725.39 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:55:12,247 INFO [train.py:812] (1/8) Epoch 22, batch 1600, loss[loss=0.1272, simple_loss=0.2066, pruned_loss=0.02387, over 6862.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2501, pruned_loss=0.03464, over 1430481.13 frames.], batch size: 15, lr: 3.55e-04
+2022-05-15 03:56:08,984 INFO [train.py:812] (1/8) Epoch 22, batch 1650, loss[loss=0.1653, simple_loss=0.2586, pruned_loss=0.03601, over 6800.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2505, pruned_loss=0.03468, over 1431862.68 frames.], batch size: 31, lr: 3.55e-04
+2022-05-15 03:57:06,975 INFO [train.py:812] (1/8) Epoch 22, batch 1700, loss[loss=0.1422, simple_loss=0.24, pruned_loss=0.02218, over 7330.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2494, pruned_loss=0.03413, over 1434030.16 frames.], batch size: 22, lr: 3.55e-04
+2022-05-15 03:58:03,878 INFO [train.py:812] (1/8) Epoch 22, batch 1750, loss[loss=0.1649, simple_loss=0.2529, pruned_loss=0.03838, over 7227.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2497, pruned_loss=0.03404, over 1432749.00 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:59:03,631 INFO [train.py:812] (1/8) Epoch 22, batch 1800, loss[loss=0.1315, simple_loss=0.2168, pruned_loss=0.02308, over 7259.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2494, pruned_loss=0.03395, over 1431145.86 frames.], batch size: 17, lr: 3.55e-04
+2022-05-15 04:00:02,112 INFO [train.py:812] (1/8) Epoch 22, batch 1850, loss[loss=0.1586, simple_loss=0.2571, pruned_loss=0.03002, over 6252.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2494, pruned_loss=0.03379, over 1426937.61 frames.], batch size: 37, lr: 3.55e-04
+2022-05-15 04:01:00,868 INFO [train.py:812] (1/8) Epoch 22, batch 1900, loss[loss=0.2078, simple_loss=0.2921, pruned_loss=0.06174, over 5438.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2499, pruned_loss=0.03465, over 1424880.80 frames.], batch size: 52, lr: 3.54e-04
+2022-05-15 04:02:00,144 INFO [train.py:812] (1/8) Epoch 22, batch 1950, loss[loss=0.147, simple_loss=0.2297, pruned_loss=0.03209, over 7284.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2496, pruned_loss=0.03448, over 1425542.00 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:02:59,571 INFO [train.py:812] (1/8) Epoch 22, batch 2000, loss[loss=0.1856, simple_loss=0.2809, pruned_loss=0.04514, over 7324.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2505, pruned_loss=0.03468, over 1427529.97 frames.], batch size: 20, lr: 3.54e-04
+2022-05-15 04:03:58,500 INFO [train.py:812] (1/8) Epoch 22, batch 2050, loss[loss=0.1326, simple_loss=0.2174, pruned_loss=0.02393, over 7273.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2505, pruned_loss=0.03442, over 1428550.98 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:04:58,103 INFO [train.py:812] (1/8) Epoch 22, batch 2100, loss[loss=0.1347, simple_loss=0.2169, pruned_loss=0.02625, over 7402.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2499, pruned_loss=0.0339, over 1426908.97 frames.], batch size: 18, lr: 3.54e-04
+2022-05-15 04:05:56,574 INFO [train.py:812] (1/8) Epoch 22, batch 2150, loss[loss=0.1477, simple_loss=0.2358, pruned_loss=0.02983, over 7153.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2489, pruned_loss=0.03379, over 1423000.84 frames.], batch size: 18, lr: 3.54e-04
+2022-05-15 04:06:54,942 INFO [train.py:812] (1/8) Epoch 22, batch 2200, loss[loss=0.1701, simple_loss=0.2626, pruned_loss=0.03882, over 7113.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2499, pruned_loss=0.03439, over 1425468.21 frames.], batch size: 21, lr: 3.54e-04
+2022-05-15 04:07:52,612 INFO [train.py:812] (1/8) Epoch 22, batch 2250, loss[loss=0.1277, simple_loss=0.2116, pruned_loss=0.02196, over 6783.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2507, pruned_loss=0.03512, over 1423174.27 frames.], batch size: 15, lr: 3.54e-04
+2022-05-15 04:08:49,583 INFO [train.py:812] (1/8) Epoch 22, batch 2300, loss[loss=0.1747, simple_loss=0.2573, pruned_loss=0.04609, over 5249.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2509, pruned_loss=0.03516, over 1424341.61 frames.], batch size: 52, lr: 3.54e-04
+2022-05-15 04:09:47,971 INFO [train.py:812] (1/8) Epoch 22, batch 2350, loss[loss=0.1683, simple_loss=0.2668, pruned_loss=0.03495, over 6523.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2502, pruned_loss=0.03508, over 1426965.59 frames.], batch size: 38, lr: 3.54e-04
+2022-05-15 04:10:57,214 INFO [train.py:812] (1/8) Epoch 22, batch 2400, loss[loss=0.1463, simple_loss=0.2232, pruned_loss=0.03471, over 7135.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2503, pruned_loss=0.03513, over 1426875.23 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:11:56,421 INFO [train.py:812] (1/8) Epoch 22, batch 2450, loss[loss=0.139, simple_loss=0.2285, pruned_loss=0.02476, over 7280.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2503, pruned_loss=0.03466, over 1425798.94 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:12:56,106 INFO [train.py:812] (1/8) Epoch 22, batch 2500, loss[loss=0.178, simple_loss=0.2717, pruned_loss=0.04221, over 7414.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2501, pruned_loss=0.03453, over 1422506.91 frames.], batch size: 21, lr: 3.53e-04
+2022-05-15 04:13:55,275 INFO [train.py:812] (1/8) Epoch 22, batch 2550, loss[loss=0.1898, simple_loss=0.2745, pruned_loss=0.05256, over 7078.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2503, pruned_loss=0.03459, over 1421505.16 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:14:54,427 INFO [train.py:812] (1/8) Epoch 22, batch 2600, loss[loss=0.1463, simple_loss=0.2411, pruned_loss=0.02575, over 7157.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2511, pruned_loss=0.03487, over 1418010.49 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:15:53,314 INFO [train.py:812] (1/8) Epoch 22, batch 2650, loss[loss=0.1484, simple_loss=0.2455, pruned_loss=0.02568, over 7258.00 frames.], tot_loss[loss=0.1596, simple_loss=0.25, pruned_loss=0.03457, over 1422108.52 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:16:52,244 INFO [train.py:812] (1/8) Epoch 22, batch 2700, loss[loss=0.1459, simple_loss=0.2298, pruned_loss=0.03102, over 7173.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2492, pruned_loss=0.03407, over 1421115.21 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:17:51,011 INFO [train.py:812] (1/8) Epoch 22, batch 2750, loss[loss=0.1612, simple_loss=0.2404, pruned_loss=0.04095, over 7066.00 frames.], tot_loss[loss=0.159, simple_loss=0.2494, pruned_loss=0.03427, over 1420628.87 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:18:49,824 INFO [train.py:812] (1/8) Epoch 22, batch 2800, loss[loss=0.133, simple_loss=0.2228, pruned_loss=0.02165, over 7279.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2502, pruned_loss=0.03456, over 1421002.55 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:19:48,484 INFO [train.py:812] (1/8) Epoch 22, batch 2850, loss[loss=0.1585, simple_loss=0.2491, pruned_loss=0.03391, over 7159.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2498, pruned_loss=0.03455, over 1419206.86 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:20:47,852 INFO [train.py:812] (1/8) Epoch 22, batch 2900, loss[loss=0.16, simple_loss=0.2478, pruned_loss=0.03614, over 7163.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2502, pruned_loss=0.03464, over 1421407.23 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:21:47,224 INFO [train.py:812] (1/8) Epoch 22, batch 2950, loss[loss=0.1498, simple_loss=0.2471, pruned_loss=0.02628, over 7416.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2502, pruned_loss=0.0348, over 1421169.06 frames.], batch size: 21, lr: 3.53e-04
+2022-05-15 04:22:47,052 INFO [train.py:812] (1/8) Epoch 22, batch 3000, loss[loss=0.1714, simple_loss=0.2565, pruned_loss=0.04312, over 7161.00 frames.], tot_loss[loss=0.1598, simple_loss=0.25, pruned_loss=0.03477, over 1424870.95 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:22:47,053 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 04:22:54,482 INFO [train.py:841] (1/8) Epoch 22, validation: loss=0.1529, simple_loss=0.2512, pruned_loss=0.02731, over 698248.00 frames.
+2022-05-15 04:23:53,738 INFO [train.py:812] (1/8) Epoch 22, batch 3050, loss[loss=0.1751, simple_loss=0.2614, pruned_loss=0.04439, over 7090.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2499, pruned_loss=0.03466, over 1426626.03 frames.], batch size: 28, lr: 3.52e-04
+2022-05-15 04:24:53,801 INFO [train.py:812] (1/8) Epoch 22, batch 3100, loss[loss=0.1926, simple_loss=0.2811, pruned_loss=0.05201, over 4918.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2491, pruned_loss=0.03452, over 1426963.22 frames.], batch size: 52, lr: 3.52e-04
+2022-05-15 04:25:52,328 INFO [train.py:812] (1/8) Epoch 22, batch 3150, loss[loss=0.1638, simple_loss=0.264, pruned_loss=0.03183, over 7412.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2487, pruned_loss=0.03442, over 1424225.37 frames.], batch size: 21, lr: 3.52e-04
+2022-05-15 04:26:51,015 INFO [train.py:812] (1/8) Epoch 22, batch 3200, loss[loss=0.1499, simple_loss=0.2385, pruned_loss=0.03069, over 7059.00 frames.], tot_loss[loss=0.159, simple_loss=0.2491, pruned_loss=0.03447, over 1425984.81 frames.], batch size: 18, lr: 3.52e-04
+2022-05-15 04:27:50,211 INFO [train.py:812] (1/8) Epoch 22, batch 3250, loss[loss=0.1358, simple_loss=0.2191, pruned_loss=0.02629, over 6994.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2505, pruned_loss=0.03529, over 1427230.32 frames.], batch size: 16, lr: 3.52e-04
+2022-05-15 04:28:47,779 INFO [train.py:812] (1/8) Epoch 22, batch 3300, loss[loss=0.1858, simple_loss=0.2725, pruned_loss=0.04951, over 7428.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2515, pruned_loss=0.03549, over 1430788.95 frames.], batch size: 20, lr: 3.52e-04
+2022-05-15 04:29:46,919 INFO [train.py:812] (1/8) Epoch 22, batch 3350, loss[loss=0.1463, simple_loss=0.2295, pruned_loss=0.03161, over 7368.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2512, pruned_loss=0.03519, over 1429371.73 frames.], batch size: 19, lr: 3.52e-04
+2022-05-15 04:30:46,408 INFO [train.py:812] (1/8) Epoch 22, batch 3400, loss[loss=0.1486, simple_loss=0.2412, pruned_loss=0.02803, over 7125.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2507, pruned_loss=0.03472, over 1425790.29 frames.], batch size: 17, lr: 3.52e-04
+2022-05-15 04:31:45,547 INFO [train.py:812] (1/8) Epoch 22, batch 3450, loss[loss=0.1682, simple_loss=0.2659, pruned_loss=0.03524, over 7341.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2511, pruned_loss=0.0346, over 1427383.55 frames.], batch size: 22, lr: 3.52e-04
+2022-05-15 04:32:45,116 INFO [train.py:812] (1/8) Epoch 22, batch 3500, loss[loss=0.1717, simple_loss=0.2692, pruned_loss=0.03709, over 7326.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2504, pruned_loss=0.03437, over 1429696.04 frames.], batch size: 22, lr: 3.52e-04
+2022-05-15 04:33:44,162 INFO [train.py:812] (1/8) Epoch 22, batch 3550, loss[loss=0.1646, simple_loss=0.2528, pruned_loss=0.03821, over 6791.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2516, pruned_loss=0.03482, over 1427373.12 frames.], batch size: 31, lr: 3.52e-04
+2022-05-15 04:34:43,565 INFO [train.py:812] (1/8) Epoch 22, batch 3600, loss[loss=0.1401, simple_loss=0.2219, pruned_loss=0.02914, over 7289.00 frames.], tot_loss[loss=0.16, simple_loss=0.2506, pruned_loss=0.03473, over 1422957.95 frames.], batch size: 17, lr: 3.51e-04
+2022-05-15 04:35:42,257 INFO [train.py:812] (1/8) Epoch 22, batch 3650, loss[loss=0.1697, simple_loss=0.2634, pruned_loss=0.03804, over 7376.00 frames.], tot_loss[loss=0.1601, simple_loss=0.251, pruned_loss=0.03463, over 1425322.29 frames.], batch size: 23, lr: 3.51e-04
+2022-05-15 04:36:47,190 INFO [train.py:812] (1/8) Epoch 22, batch 3700, loss[loss=0.1703, simple_loss=0.2644, pruned_loss=0.03811, over 7225.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2504, pruned_loss=0.03428, over 1427617.54 frames.], batch size: 21, lr: 3.51e-04
+2022-05-15 04:37:46,499 INFO [train.py:812] (1/8) Epoch 22, batch 3750, loss[loss=0.1615, simple_loss=0.2424, pruned_loss=0.04028, over 7003.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2504, pruned_loss=0.03474, over 1431153.45 frames.], batch size: 16, lr: 3.51e-04
+2022-05-15 04:38:46,121 INFO [train.py:812] (1/8) Epoch 22, batch 3800, loss[loss=0.1903, simple_loss=0.2662, pruned_loss=0.05716, over 5163.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2494, pruned_loss=0.03443, over 1425380.90 frames.], batch size: 52, lr: 3.51e-04
+2022-05-15 04:39:43,949 INFO [train.py:812] (1/8) Epoch 22, batch 3850, loss[loss=0.1958, simple_loss=0.2923, pruned_loss=0.04964, over 7236.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2498, pruned_loss=0.03432, over 1428049.01 frames.], batch size: 20, lr: 3.51e-04
+2022-05-15 04:40:43,466 INFO [train.py:812] (1/8) Epoch 22, batch 3900, loss[loss=0.1698, simple_loss=0.2631, pruned_loss=0.03823, over 6330.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2487, pruned_loss=0.03383, over 1427551.69 frames.], batch size: 38, lr: 3.51e-04
+2022-05-15 04:41:41,331 INFO [train.py:812] (1/8) Epoch 22, batch 3950, loss[loss=0.1593, simple_loss=0.2461, pruned_loss=0.03625, over 7285.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2484, pruned_loss=0.03363, over 1425861.64 frames.], batch size: 17, lr: 3.51e-04
+2022-05-15 04:42:39,862 INFO [train.py:812] (1/8) Epoch 22, batch 4000, loss[loss=0.1683, simple_loss=0.2752, pruned_loss=0.03072, over 7312.00 frames.], tot_loss[loss=0.1595, simple_loss=0.25, pruned_loss=0.03447, over 1424905.71 frames.], batch size: 21, lr: 3.51e-04
+2022-05-15 04:43:37,309 INFO [train.py:812] (1/8) Epoch 22, batch 4050, loss[loss=0.1629, simple_loss=0.2416, pruned_loss=0.04209, over 7374.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2493, pruned_loss=0.03444, over 1423862.64 frames.], batch size: 19, lr: 3.51e-04
+2022-05-15 04:44:35,620 INFO [train.py:812] (1/8) Epoch 22, batch 4100, loss[loss=0.1732, simple_loss=0.2631, pruned_loss=0.04168, over 7328.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2488, pruned_loss=0.03389, over 1425147.32 frames.], batch size: 20, lr: 3.51e-04
+2022-05-15 04:45:34,804 INFO [train.py:812] (1/8) Epoch 22, batch 4150, loss[loss=0.1421, simple_loss=0.2211, pruned_loss=0.03149, over 7065.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2487, pruned_loss=0.03406, over 1420259.14 frames.], batch size: 18, lr: 3.51e-04
+2022-05-15 04:46:33,514 INFO [train.py:812] (1/8) Epoch 22, batch 4200, loss[loss=0.1542, simple_loss=0.244, pruned_loss=0.03217, over 7155.00 frames.], tot_loss[loss=0.1588, simple_loss=0.249, pruned_loss=0.03435, over 1415646.33 frames.], batch size: 20, lr: 3.50e-04
+2022-05-15 04:47:30,295 INFO [train.py:812] (1/8) Epoch 22, batch 4250, loss[loss=0.1592, simple_loss=0.2588, pruned_loss=0.02984, over 6599.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2497, pruned_loss=0.0348, over 1409221.04 frames.], batch size: 31, lr: 3.50e-04
+2022-05-15 04:48:27,298 INFO [train.py:812] (1/8) Epoch 22, batch 4300, loss[loss=0.1721, simple_loss=0.2792, pruned_loss=0.03248, over 7286.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2507, pruned_loss=0.03479, over 1411199.11 frames.], batch size: 24, lr: 3.50e-04
+2022-05-15 04:49:26,474 INFO [train.py:812] (1/8) Epoch 22, batch 4350, loss[loss=0.1797, simple_loss=0.2705, pruned_loss=0.04444, over 7331.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2508, pruned_loss=0.03473, over 1408243.75 frames.], batch size: 22, lr: 3.50e-04
+2022-05-15 04:50:35,271 INFO [train.py:812] (1/8) Epoch 22, batch 4400, loss[loss=0.1546, simple_loss=0.2499, pruned_loss=0.02962, over 7118.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2511, pruned_loss=0.03503, over 1403120.77 frames.], batch size: 21, lr: 3.50e-04
+2022-05-15 04:51:33,775 INFO [train.py:812] (1/8) Epoch 22, batch 4450, loss[loss=0.1613, simple_loss=0.2584, pruned_loss=0.03212, over 7340.00 frames.], tot_loss[loss=0.1612, simple_loss=0.252, pruned_loss=0.03521, over 1399120.08 frames.], batch size: 22, lr: 3.50e-04
+2022-05-15 04:52:33,292 INFO [train.py:812] (1/8) Epoch 22, batch 4500, loss[loss=0.1813, simple_loss=0.2659, pruned_loss=0.04836, over 7114.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2537, pruned_loss=0.03623, over 1389502.03 frames.], batch size: 28, lr: 3.50e-04
+2022-05-15 04:53:50,563 INFO [train.py:812] (1/8) Epoch 22, batch 4550, loss[loss=0.1821, simple_loss=0.266, pruned_loss=0.04911, over 5223.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2557, pruned_loss=0.03765, over 1347270.38 frames.], batch size: 52, lr: 3.50e-04
+2022-05-15 04:55:29,963 INFO [train.py:812] (1/8) Epoch 23, batch 0, loss[loss=0.136, simple_loss=0.2213, pruned_loss=0.02536, over 7189.00 frames.], tot_loss[loss=0.136, simple_loss=0.2213, pruned_loss=0.02536, over 7189.00 frames.], batch size: 16, lr: 3.42e-04
+2022-05-15 04:56:28,538 INFO [train.py:812] (1/8) Epoch 23, batch 50, loss[loss=0.1427, simple_loss=0.2346, pruned_loss=0.02545, over 7164.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2492, pruned_loss=0.03323, over 319350.67 frames.], batch size: 19, lr: 3.42e-04
+2022-05-15 04:57:26,786 INFO [train.py:812] (1/8) Epoch 23, batch 100, loss[loss=0.1582, simple_loss=0.2522, pruned_loss=0.03209, over 7299.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2508, pruned_loss=0.03354, over 565713.29 frames.], batch size: 18, lr: 3.42e-04
+2022-05-15 04:58:25,164 INFO [train.py:812] (1/8) Epoch 23, batch 150, loss[loss=0.1574, simple_loss=0.2538, pruned_loss=0.03049, over 7266.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2527, pruned_loss=0.03472, over 753273.56 frames.], batch size: 24, lr: 3.42e-04
+2022-05-15 04:59:34,122 INFO [train.py:812] (1/8) Epoch 23, batch 200, loss[loss=0.1502, simple_loss=0.2389, pruned_loss=0.03079, over 6192.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2521, pruned_loss=0.03426, over 901423.96 frames.], batch size: 37, lr: 3.42e-04
+2022-05-15 05:00:33,210 INFO [train.py:812] (1/8) Epoch 23, batch 250, loss[loss=0.1746, simple_loss=0.2646, pruned_loss=0.0423, over 7193.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2517, pruned_loss=0.03441, over 1016424.01 frames.], batch size: 23, lr: 3.42e-04
+2022-05-15 05:01:30,509 INFO [train.py:812] (1/8) Epoch 23, batch 300, loss[loss=0.1644, simple_loss=0.2497, pruned_loss=0.03952, over 7144.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2507, pruned_loss=0.03428, over 1101952.59 frames.], batch size: 19, lr: 3.42e-04
+2022-05-15 05:02:29,196 INFO [train.py:812] (1/8) Epoch 23, batch 350, loss[loss=0.1644, simple_loss=0.276, pruned_loss=0.02635, over 7339.00 frames.], tot_loss[loss=0.159, simple_loss=0.2501, pruned_loss=0.0339, over 1176431.04 frames.], batch size: 22, lr: 3.42e-04
+2022-05-15 05:03:27,248 INFO [train.py:812] (1/8) Epoch 23, batch 400, loss[loss=0.1713, simple_loss=0.2679, pruned_loss=0.03738, over 7191.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2501, pruned_loss=0.03388, over 1230155.67 frames.], batch size: 23, lr: 3.42e-04
+2022-05-15 05:04:26,526 INFO [train.py:812] (1/8) Epoch 23, batch 450, loss[loss=0.1837, simple_loss=0.2827, pruned_loss=0.04233, over 7265.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2511, pruned_loss=0.03405, over 1271404.66 frames.], batch size: 24, lr: 3.42e-04
+2022-05-15 05:05:24,824 INFO [train.py:812] (1/8) Epoch 23, batch 500, loss[loss=0.1404, simple_loss=0.228, pruned_loss=0.02638, over 6777.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2511, pruned_loss=0.03408, over 1307057.47 frames.], batch size: 15, lr: 3.41e-04
+2022-05-15 05:06:21,985 INFO [train.py:812] (1/8) Epoch 23, batch 550, loss[loss=0.1612, simple_loss=0.2568, pruned_loss=0.03281, over 7286.00 frames.], tot_loss[loss=0.159, simple_loss=0.2504, pruned_loss=0.03382, over 1337254.81 frames.], batch size: 24, lr: 3.41e-04
+2022-05-15 05:07:20,811 INFO [train.py:812] (1/8) Epoch 23, batch 600, loss[loss=0.1441, simple_loss=0.2416, pruned_loss=0.02331, over 7110.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2504, pruned_loss=0.03361, over 1359816.82 frames.], batch size: 21, lr: 3.41e-04
+2022-05-15 05:08:19,858 INFO [train.py:812] (1/8) Epoch 23, batch 650, loss[loss=0.1679, simple_loss=0.2582, pruned_loss=0.03876, over 6896.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2513, pruned_loss=0.03405, over 1374146.88 frames.], batch size: 31, lr: 3.41e-04
+2022-05-15 05:09:19,431 INFO [train.py:812] (1/8) Epoch 23, batch 700, loss[loss=0.1933, simple_loss=0.2739, pruned_loss=0.0563, over 5172.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2509, pruned_loss=0.03437, over 1380725.47 frames.], batch size: 53, lr: 3.41e-04
+2022-05-15 05:10:18,456 INFO [train.py:812] (1/8) Epoch 23, batch 750, loss[loss=0.1469, simple_loss=0.2479, pruned_loss=0.02296, over 7215.00 frames.], tot_loss[loss=0.16, simple_loss=0.2515, pruned_loss=0.03429, over 1392638.03 frames.], batch size: 23, lr: 3.41e-04
+2022-05-15 05:11:17,824 INFO [train.py:812] (1/8) Epoch 23, batch 800, loss[loss=0.1579, simple_loss=0.253, pruned_loss=0.03141, over 7355.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2512, pruned_loss=0.0345, over 1396522.40 frames.], batch size: 19, lr: 3.41e-04
+2022-05-15 05:12:15,509 INFO [train.py:812] (1/8) Epoch 23, batch 850, loss[loss=0.1424, simple_loss=0.2454, pruned_loss=0.01964, over 7424.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2508, pruned_loss=0.03427, over 1404331.66 frames.], batch size: 20, lr: 3.41e-04
+2022-05-15 05:13:14,534 INFO [train.py:812] (1/8) Epoch 23, batch 900, loss[loss=0.1598, simple_loss=0.2539, pruned_loss=0.03284, over 7166.00 frames.], tot_loss[loss=0.1598, simple_loss=0.251, pruned_loss=0.03434, over 1408758.44 frames.], batch size: 19, lr: 3.41e-04
+2022-05-15 05:14:13,174 INFO [train.py:812] (1/8) Epoch 23, batch 950, loss[loss=0.1714, simple_loss=0.268, pruned_loss=0.03734, over 7022.00 frames.], tot_loss[loss=0.16, simple_loss=0.2512, pruned_loss=0.03442, over 1410179.99 frames.], batch size: 28, lr: 3.41e-04
+2022-05-15 05:15:13,114 INFO [train.py:812] (1/8) Epoch 23, batch 1000, loss[loss=0.1554, simple_loss=0.2476, pruned_loss=0.03156, over 7359.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2512, pruned_loss=0.03447, over 1417193.06 frames.], batch size: 19, lr: 3.41e-04
+2022-05-15 05:16:12,071 INFO [train.py:812] (1/8) Epoch 23, batch 1050, loss[loss=0.181, simple_loss=0.2734, pruned_loss=0.04429, over 4862.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2504, pruned_loss=0.03429, over 1417755.04 frames.], batch size: 53, lr: 3.41e-04
+2022-05-15 05:17:10,936 INFO [train.py:812] (1/8) Epoch 23, batch 1100, loss[loss=0.1384, simple_loss=0.2139, pruned_loss=0.03148, over 7278.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2513, pruned_loss=0.03417, over 1417239.22 frames.], batch size: 17, lr: 3.40e-04
+2022-05-15 05:18:09,881 INFO [train.py:812] (1/8) Epoch 23, batch 1150, loss[loss=0.1539, simple_loss=0.2442, pruned_loss=0.03179, over 7422.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2513, pruned_loss=0.03408, over 1421451.97 frames.], batch size: 20, lr: 3.40e-04
+2022-05-15 05:19:09,546 INFO [train.py:812] (1/8) Epoch 23, batch 1200, loss[loss=0.1512, simple_loss=0.2367, pruned_loss=0.03283, over 7288.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2506, pruned_loss=0.03406, over 1421628.61 frames.], batch size: 18, lr: 3.40e-04
+2022-05-15 05:20:07,300 INFO [train.py:812] (1/8) Epoch 23, batch 1250, loss[loss=0.1485, simple_loss=0.2303, pruned_loss=0.03341, over 6841.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2497, pruned_loss=0.0338, over 1425297.84 frames.], batch size: 15, lr: 3.40e-04
+2022-05-15 05:21:05,552 INFO [train.py:812] (1/8) Epoch 23, batch 1300, loss[loss=0.1626, simple_loss=0.2525, pruned_loss=0.03636, over 7204.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2497, pruned_loss=0.03368, over 1427724.92 frames.], batch size: 23, lr: 3.40e-04
+2022-05-15 05:22:03,015 INFO [train.py:812] (1/8) Epoch 23, batch 1350, loss[loss=0.1366, simple_loss=0.2214, pruned_loss=0.02584, over 7276.00 frames.], tot_loss[loss=0.158, simple_loss=0.2487, pruned_loss=0.03359, over 1428161.30 frames.], batch size: 18, lr: 3.40e-04
+2022-05-15 05:23:02,498 INFO [train.py:812] (1/8) Epoch 23, batch 1400, loss[loss=0.1863, simple_loss=0.2804, pruned_loss=0.04611, over 7104.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2492, pruned_loss=0.03362, over 1428393.25 frames.], batch size: 21, lr: 3.40e-04
+2022-05-15 05:24:01,075 INFO [train.py:812] (1/8) Epoch 23, batch 1450, loss[loss=0.1361, simple_loss=0.221, pruned_loss=0.02557, over 7419.00 frames.], tot_loss[loss=0.1583, simple_loss=0.249, pruned_loss=0.03383, over 1421889.92 frames.], batch size: 18, lr: 3.40e-04
+2022-05-15 05:24:59,731 INFO [train.py:812] (1/8) Epoch 23, batch 1500, loss[loss=0.1806, simple_loss=0.2787, pruned_loss=0.0412, over 7038.00 frames.], tot_loss[loss=0.158, simple_loss=0.2483, pruned_loss=0.03381, over 1422950.80 frames.], batch size: 28, lr: 3.40e-04
+2022-05-15 05:25:58,346 INFO [train.py:812] (1/8) Epoch 23, batch 1550, loss[loss=0.1559, simple_loss=0.2341, pruned_loss=0.03883, over 7357.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2488, pruned_loss=0.03416, over 1414460.23 frames.], batch size: 19, lr: 3.40e-04
+2022-05-15 05:26:57,172 INFO [train.py:812] (1/8) Epoch 23, batch 1600, loss[loss=0.1811, simple_loss=0.2776, pruned_loss=0.04229, over 7221.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2492, pruned_loss=0.03417, over 1411794.72 frames.], batch size: 21, lr: 3.40e-04
+2022-05-15 05:27:55,180 INFO [train.py:812] (1/8) Epoch 23, batch 1650, loss[loss=0.1669, simple_loss=0.2513, pruned_loss=0.04123, over 7371.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2497, pruned_loss=0.03439, over 1414373.26 frames.], batch size: 23, lr: 3.40e-04
+2022-05-15 05:28:54,101 INFO [train.py:812] (1/8) Epoch 23, batch 1700, loss[loss=0.1377, simple_loss=0.2248, pruned_loss=0.02532, over 7422.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2499, pruned_loss=0.0343, over 1415538.02 frames.], batch size: 18, lr: 3.39e-04
+2022-05-15 05:29:50,561 INFO [train.py:812] (1/8) Epoch 23, batch 1750, loss[loss=0.1651, simple_loss=0.2538, pruned_loss=0.03819, over 7188.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2502, pruned_loss=0.0343, over 1414477.23 frames.], batch size: 26, lr: 3.39e-04
+2022-05-15 05:30:48,705 INFO [train.py:812] (1/8) Epoch 23, batch 1800, loss[loss=0.238, simple_loss=0.3229, pruned_loss=0.07658, over 5153.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2507, pruned_loss=0.03481, over 1410886.59 frames.], batch size: 52, lr: 3.39e-04
+2022-05-15 05:31:46,091 INFO [train.py:812] (1/8) Epoch 23, batch 1850, loss[loss=0.158, simple_loss=0.2545, pruned_loss=0.03073, over 7421.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2501, pruned_loss=0.03447, over 1416428.94 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:32:44,001 INFO [train.py:812] (1/8) Epoch 23, batch 1900, loss[loss=0.1615, simple_loss=0.2547, pruned_loss=0.03412, over 7154.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2499, pruned_loss=0.03477, over 1420282.86 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:33:42,347 INFO [train.py:812] (1/8) Epoch 23, batch 1950, loss[loss=0.149, simple_loss=0.2455, pruned_loss=0.02623, over 7154.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2499, pruned_loss=0.0351, over 1417340.13 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:34:41,195 INFO [train.py:812] (1/8) Epoch 23, batch 2000, loss[loss=0.1459, simple_loss=0.2359, pruned_loss=0.0279, over 7256.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2516, pruned_loss=0.03543, over 1421216.79 frames.], batch size: 19, lr: 3.39e-04
+2022-05-15 05:35:40,293 INFO [train.py:812] (1/8) Epoch 23, batch 2050, loss[loss=0.1788, simple_loss=0.2607, pruned_loss=0.04848, over 7230.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2509, pruned_loss=0.03524, over 1425272.76 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:36:39,468 INFO [train.py:812] (1/8) Epoch 23, batch 2100, loss[loss=0.1936, simple_loss=0.2769, pruned_loss=0.05508, over 7208.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2508, pruned_loss=0.03509, over 1419463.21 frames.], batch size: 23, lr: 3.39e-04
+2022-05-15 05:37:37,947 INFO [train.py:812] (1/8) Epoch 23, batch 2150, loss[loss=0.1483, simple_loss=0.2362, pruned_loss=0.03025, over 7156.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2504, pruned_loss=0.03499, over 1419469.47 frames.], batch size: 19, lr: 3.39e-04
+2022-05-15 05:38:37,637 INFO [train.py:812] (1/8) Epoch 23, batch 2200, loss[loss=0.1427, simple_loss=0.2414, pruned_loss=0.022, over 7143.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2498, pruned_loss=0.03459, over 1414662.94 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:39:36,699 INFO [train.py:812] (1/8) Epoch 23, batch 2250, loss[loss=0.1328, simple_loss=0.2344, pruned_loss=0.01563, over 7154.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2505, pruned_loss=0.03486, over 1410939.33 frames.], batch size: 19, lr: 3.39e-04
+2022-05-15 05:40:35,582 INFO [train.py:812] (1/8) Epoch 23, batch 2300, loss[loss=0.1573, simple_loss=0.2562, pruned_loss=0.02927, over 7320.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2503, pruned_loss=0.03476, over 1412666.72 frames.], batch size: 21, lr: 3.38e-04
+2022-05-15 05:41:34,382 INFO [train.py:812] (1/8) Epoch 23, batch 2350, loss[loss=0.1723, simple_loss=0.2724, pruned_loss=0.03607, over 7337.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2504, pruned_loss=0.03467, over 1414580.62 frames.], batch size: 22, lr: 3.38e-04
+2022-05-15 05:42:33,215 INFO [train.py:812] (1/8) Epoch 23, batch 2400, loss[loss=0.1818, simple_loss=0.2778, pruned_loss=0.04294, over 7301.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2513, pruned_loss=0.03486, over 1417245.48 frames.], batch size: 24, lr: 3.38e-04
+2022-05-15 05:43:31,228 INFO [train.py:812] (1/8) Epoch 23, batch 2450, loss[loss=0.1711, simple_loss=0.2593, pruned_loss=0.04149, over 7210.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2521, pruned_loss=0.03464, over 1421516.79 frames.], batch size: 22, lr: 3.38e-04
+2022-05-15 05:44:30,335 INFO [train.py:812] (1/8) Epoch 23, batch 2500, loss[loss=0.1618, simple_loss=0.2529, pruned_loss=0.0354, over 6515.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2503, pruned_loss=0.03471, over 1419745.01 frames.], batch size: 38, lr: 3.38e-04
+2022-05-15 05:45:29,333 INFO [train.py:812] (1/8) Epoch 23, batch 2550, loss[loss=0.1613, simple_loss=0.2451, pruned_loss=0.03881, over 7380.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2501, pruned_loss=0.03452, over 1420808.39 frames.], batch size: 23, lr: 3.38e-04
+2022-05-15 05:46:26,774 INFO [train.py:812] (1/8) Epoch 23, batch 2600, loss[loss=0.1485, simple_loss=0.2353, pruned_loss=0.0309, over 7343.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2496, pruned_loss=0.03425, over 1425102.38 frames.], batch size: 22, lr: 3.38e-04
+2022-05-15 05:47:25,310 INFO [train.py:812] (1/8) Epoch 23, batch 2650, loss[loss=0.1635, simple_loss=0.2566, pruned_loss=0.03524, over 7288.00 frames.], tot_loss[loss=0.1578, simple_loss=0.248, pruned_loss=0.03381, over 1422175.86 frames.], batch size: 25, lr: 3.38e-04
+2022-05-15 05:48:25,317 INFO [train.py:812] (1/8) Epoch 23, batch 2700, loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.02882, over 7154.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2483, pruned_loss=0.03379, over 1421961.74 frames.], batch size: 19, lr: 3.38e-04
+2022-05-15 05:49:24,351 INFO [train.py:812] (1/8) Epoch 23, batch 2750, loss[loss=0.132, simple_loss=0.2179, pruned_loss=0.02307, over 7156.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2485, pruned_loss=0.03414, over 1419438.19 frames.], batch size: 18, lr: 3.38e-04
+2022-05-15 05:50:23,652 INFO [train.py:812] (1/8) Epoch 23, batch 2800, loss[loss=0.139, simple_loss=0.2201, pruned_loss=0.02898, over 7161.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2487, pruned_loss=0.03457, over 1418767.32 frames.], batch size: 18, lr: 3.38e-04
+2022-05-15 05:51:22,627 INFO [train.py:812] (1/8) Epoch 23, batch 2850, loss[loss=0.1836, simple_loss=0.2816, pruned_loss=0.04283, over 7069.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2491, pruned_loss=0.03461, over 1420537.60 frames.], batch size: 28, lr: 3.38e-04
+2022-05-15 05:52:22,316 INFO [train.py:812] (1/8) Epoch 23, batch 2900, loss[loss=0.1682, simple_loss=0.2647, pruned_loss=0.03586, over 7284.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2494, pruned_loss=0.03439, over 1422621.98 frames.], batch size: 25, lr: 3.37e-04
+2022-05-15 05:53:20,353 INFO [train.py:812] (1/8) Epoch 23, batch 2950, loss[loss=0.1784, simple_loss=0.2649, pruned_loss=0.04591, over 7222.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2498, pruned_loss=0.03428, over 1423211.49 frames.], batch size: 22, lr: 3.37e-04
+2022-05-15 05:54:18,722 INFO [train.py:812] (1/8) Epoch 23, batch 3000, loss[loss=0.1333, simple_loss=0.2164, pruned_loss=0.02513, over 7004.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2499, pruned_loss=0.03426, over 1423461.56 frames.], batch size: 16, lr: 3.37e-04
+2022-05-15 05:54:18,723 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 05:54:28,115 INFO [train.py:841] (1/8) Epoch 23, validation: loss=0.153, simple_loss=0.251, pruned_loss=0.02752, over 698248.00 frames.
+2022-05-15 05:55:26,690 INFO [train.py:812] (1/8) Epoch 23, batch 3050, loss[loss=0.126, simple_loss=0.2089, pruned_loss=0.02159, over 7155.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2494, pruned_loss=0.03411, over 1425879.64 frames.], batch size: 19, lr: 3.37e-04
+2022-05-15 05:56:31,539 INFO [train.py:812] (1/8) Epoch 23, batch 3100, loss[loss=0.1507, simple_loss=0.2527, pruned_loss=0.0243, over 7236.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2493, pruned_loss=0.03401, over 1424957.06 frames.], batch size: 20, lr: 3.37e-04
+2022-05-15 05:57:30,937 INFO [train.py:812] (1/8) Epoch 23, batch 3150, loss[loss=0.1622, simple_loss=0.251, pruned_loss=0.03667, over 7322.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2498, pruned_loss=0.03441, over 1426952.83 frames.], batch size: 20, lr: 3.37e-04
+2022-05-15 05:58:30,535 INFO [train.py:812] (1/8) Epoch 23, batch 3200, loss[loss=0.1671, simple_loss=0.262, pruned_loss=0.03611, over 7110.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2497, pruned_loss=0.03426, over 1427798.98 frames.], batch size: 21, lr: 3.37e-04
+2022-05-15 05:59:29,506 INFO [train.py:812] (1/8) Epoch 23, batch 3250, loss[loss=0.1433, simple_loss=0.2475, pruned_loss=0.01954, over 6337.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2504, pruned_loss=0.03445, over 1422438.03 frames.], batch size: 38, lr: 3.37e-04
+2022-05-15 06:00:29,702 INFO [train.py:812] (1/8) Epoch 23, batch 3300, loss[loss=0.1986, simple_loss=0.2918, pruned_loss=0.05274, over 7289.00 frames.], tot_loss[loss=0.16, simple_loss=0.251, pruned_loss=0.0345, over 1422992.72 frames.], batch size: 24, lr: 3.37e-04
+2022-05-15 06:01:29,026 INFO [train.py:812] (1/8) Epoch 23, batch 3350, loss[loss=0.1558, simple_loss=0.2482, pruned_loss=0.03172, over 7158.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2489, pruned_loss=0.0338, over 1427247.82 frames.], batch size: 26, lr: 3.37e-04
+2022-05-15 06:02:28,576 INFO [train.py:812] (1/8) Epoch 23, batch 3400, loss[loss=0.1351, simple_loss=0.2246, pruned_loss=0.02283, over 7160.00 frames.], tot_loss[loss=0.158, simple_loss=0.2488, pruned_loss=0.03358, over 1428156.55 frames.], batch size: 19, lr: 3.37e-04
+2022-05-15 06:03:27,791 INFO [train.py:812] (1/8) Epoch 23, batch 3450, loss[loss=0.1391, simple_loss=0.2268, pruned_loss=0.02566, over 6805.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2488, pruned_loss=0.03388, over 1430070.41 frames.], batch size: 15, lr: 3.37e-04
+2022-05-15 06:04:27,367 INFO [train.py:812] (1/8) Epoch 23, batch 3500, loss[loss=0.1409, simple_loss=0.2203, pruned_loss=0.03076, over 6759.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2484, pruned_loss=0.03351, over 1430667.08 frames.], batch size: 15, lr: 3.37e-04
+2022-05-15 06:05:25,895 INFO [train.py:812] (1/8) Epoch 23, batch 3550, loss[loss=0.1263, simple_loss=0.2147, pruned_loss=0.01898, over 7410.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2488, pruned_loss=0.03378, over 1431485.52 frames.], batch size: 18, lr: 3.36e-04
+2022-05-15 06:06:25,042 INFO [train.py:812] (1/8) Epoch 23, batch 3600, loss[loss=0.13, simple_loss=0.214, pruned_loss=0.02295, over 7282.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2493, pruned_loss=0.03388, over 1432012.27 frames.], batch size: 17, lr: 3.36e-04
+2022-05-15 06:07:24,126 INFO [train.py:812] (1/8) Epoch 23, batch 3650, loss[loss=0.163, simple_loss=0.2501, pruned_loss=0.03789, over 6407.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2494, pruned_loss=0.03395, over 1431626.35 frames.], batch size: 37, lr: 3.36e-04
+2022-05-15 06:08:33,462 INFO [train.py:812] (1/8) Epoch 23, batch 3700, loss[loss=0.1818, simple_loss=0.27, pruned_loss=0.04682, over 7162.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2495, pruned_loss=0.03406, over 1430446.29 frames.], batch size: 19, lr: 3.36e-04
+2022-05-15 06:09:32,125 INFO [train.py:812] (1/8) Epoch 23, batch 3750, loss[loss=0.1484, simple_loss=0.2317, pruned_loss=0.03253, over 7283.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2495, pruned_loss=0.03375, over 1427818.27 frames.], batch size: 17, lr: 3.36e-04
+2022-05-15 06:10:31,408 INFO [train.py:812] (1/8) Epoch 23, batch 3800, loss[loss=0.1664, simple_loss=0.2645, pruned_loss=0.03418, over 7370.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2495, pruned_loss=0.03362, over 1429314.04 frames.], batch size: 23, lr: 3.36e-04
+2022-05-15 06:11:30,121 INFO [train.py:812] (1/8) Epoch 23, batch 3850, loss[loss=0.1457, simple_loss=0.2352, pruned_loss=0.02803, over 7057.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2484, pruned_loss=0.03336, over 1430176.18 frames.], batch size: 28, lr: 3.36e-04
+2022-05-15 06:12:28,296 INFO [train.py:812] (1/8) Epoch 23, batch 3900, loss[loss=0.163, simple_loss=0.2591, pruned_loss=0.03342, over 7129.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2485, pruned_loss=0.0337, over 1430596.53 frames.], batch size: 21, lr: 3.36e-04
+2022-05-15 06:13:25,765 INFO [train.py:812] (1/8) Epoch 23, batch 3950, loss[loss=0.1469, simple_loss=0.2395, pruned_loss=0.02708, over 7158.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2485, pruned_loss=0.03351, over 1430322.70 frames.], batch size: 19, lr: 3.36e-04
+2022-05-15 06:14:22,990 INFO [train.py:812] (1/8) Epoch 23, batch 4000, loss[loss=0.1487, simple_loss=0.2329, pruned_loss=0.03225, over 7259.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2484, pruned_loss=0.03366, over 1427010.96 frames.], batch size: 17, lr: 3.36e-04
+2022-05-15 06:15:21,470 INFO [train.py:812] (1/8) Epoch 23, batch 4050, loss[loss=0.1324, simple_loss=0.217, pruned_loss=0.0239, over 6824.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2496, pruned_loss=0.03407, over 1422017.97 frames.], batch size: 15, lr: 3.36e-04
+2022-05-15 06:16:21,793 INFO [train.py:812] (1/8) Epoch 23, batch 4100, loss[loss=0.1407, simple_loss=0.2231, pruned_loss=0.02909, over 7203.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2485, pruned_loss=0.03396, over 1418818.17 frames.], batch size: 16, lr: 3.36e-04
+2022-05-15 06:17:19,467 INFO [train.py:812] (1/8) Epoch 23, batch 4150, loss[loss=0.1709, simple_loss=0.2579, pruned_loss=0.04199, over 7324.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2498, pruned_loss=0.03446, over 1418043.32 frames.], batch size: 21, lr: 3.35e-04
+2022-05-15 06:18:18,885 INFO [train.py:812] (1/8) Epoch 23, batch 4200, loss[loss=0.1362, simple_loss=0.2226, pruned_loss=0.02489, over 6989.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2504, pruned_loss=0.03471, over 1422562.88 frames.], batch size: 16, lr: 3.35e-04
+2022-05-15 06:19:17,842 INFO [train.py:812] (1/8) Epoch 23, batch 4250, loss[loss=0.1446, simple_loss=0.2416, pruned_loss=0.02374, over 7236.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2505, pruned_loss=0.0346, over 1423929.21 frames.], batch size: 20, lr: 3.35e-04
+2022-05-15 06:20:16,266 INFO [train.py:812] (1/8) Epoch 23, batch 4300, loss[loss=0.1424, simple_loss=0.2385, pruned_loss=0.02312, over 7157.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2492, pruned_loss=0.03413, over 1420847.41 frames.], batch size: 18, lr: 3.35e-04
+2022-05-15 06:21:15,783 INFO [train.py:812] (1/8) Epoch 23, batch 4350, loss[loss=0.1349, simple_loss=0.2228, pruned_loss=0.02352, over 7196.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2482, pruned_loss=0.03383, over 1422174.46 frames.], batch size: 16, lr: 3.35e-04
+2022-05-15 06:22:15,636 INFO [train.py:812] (1/8) Epoch 23, batch 4400, loss[loss=0.1488, simple_loss=0.2398, pruned_loss=0.0289, over 7060.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2482, pruned_loss=0.03359, over 1419066.63 frames.], batch size: 18, lr: 3.35e-04
+2022-05-15 06:23:14,862 INFO [train.py:812] (1/8) Epoch 23, batch 4450, loss[loss=0.1973, simple_loss=0.2768, pruned_loss=0.05888, over 4642.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2491, pruned_loss=0.0342, over 1412700.51 frames.], batch size: 53, lr: 3.35e-04
+2022-05-15 06:24:12,958 INFO [train.py:812] (1/8) Epoch 23, batch 4500, loss[loss=0.1599, simple_loss=0.2509, pruned_loss=0.03444, over 7064.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2497, pruned_loss=0.03421, over 1411814.65 frames.], batch size: 18, lr: 3.35e-04
+2022-05-15 06:25:11,003 INFO [train.py:812] (1/8) Epoch 23, batch 4550, loss[loss=0.2206, simple_loss=0.2976, pruned_loss=0.07182, over 4865.00 frames.], tot_loss[loss=0.1619, simple_loss=0.252, pruned_loss=0.03594, over 1354126.35 frames.], batch size: 52, lr: 3.35e-04
+2022-05-15 06:26:16,424 INFO [train.py:812] (1/8) Epoch 24, batch 0, loss[loss=0.1419, simple_loss=0.2235, pruned_loss=0.03017, over 6836.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2235, pruned_loss=0.03017, over 6836.00 frames.], batch size: 15, lr: 3.28e-04
+2022-05-15 06:27:14,048 INFO [train.py:812] (1/8) Epoch 24, batch 50, loss[loss=0.1221, simple_loss=0.2103, pruned_loss=0.01701, over 7274.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2487, pruned_loss=0.03302, over 315399.80 frames.], batch size: 17, lr: 3.28e-04
+2022-05-15 06:28:13,400 INFO [train.py:812] (1/8) Epoch 24, batch 100, loss[loss=0.1689, simple_loss=0.2663, pruned_loss=0.03581, over 7325.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2492, pruned_loss=0.03294, over 566634.42 frames.], batch size: 20, lr: 3.28e-04
+2022-05-15 06:29:11,067 INFO [train.py:812] (1/8) Epoch 24, batch 150, loss[loss=0.1825, simple_loss=0.2629, pruned_loss=0.05098, over 7371.00 frames.], tot_loss[loss=0.1575, simple_loss=0.249, pruned_loss=0.033, over 752483.40 frames.], batch size: 23, lr: 3.28e-04
+2022-05-15 06:30:10,079 INFO [train.py:812] (1/8) Epoch 24, batch 200, loss[loss=0.1694, simple_loss=0.2592, pruned_loss=0.03985, over 7205.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2491, pruned_loss=0.03322, over 903241.33 frames.], batch size: 22, lr: 3.28e-04
+2022-05-15 06:31:07,640 INFO [train.py:812] (1/8) Epoch 24, batch 250, loss[loss=0.1661, simple_loss=0.2646, pruned_loss=0.03382, over 7410.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2485, pruned_loss=0.03309, over 1016079.37 frames.], batch size: 21, lr: 3.28e-04
+2022-05-15 06:32:07,186 INFO [train.py:812] (1/8) Epoch 24, batch 300, loss[loss=0.1678, simple_loss=0.2564, pruned_loss=0.03958, over 7141.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2477, pruned_loss=0.03309, over 1107481.88 frames.], batch size: 20, lr: 3.27e-04
+2022-05-15 06:33:03,996 INFO [train.py:812] (1/8) Epoch 24, batch 350, loss[loss=0.1756, simple_loss=0.2702, pruned_loss=0.0405, over 7292.00 frames.], tot_loss[loss=0.1572, simple_loss=0.248, pruned_loss=0.03313, over 1179328.40 frames.], batch size: 25, lr: 3.27e-04
+2022-05-15 06:34:01,084 INFO [train.py:812] (1/8) Epoch 24, batch 400, loss[loss=0.155, simple_loss=0.2419, pruned_loss=0.03401, over 7300.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2482, pruned_loss=0.03305, over 1231209.69 frames.], batch size: 24, lr: 3.27e-04
+2022-05-15 06:34:58,896 INFO [train.py:812] (1/8) Epoch 24, batch 450, loss[loss=0.1581, simple_loss=0.2511, pruned_loss=0.03253, over 7147.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2477, pruned_loss=0.03274, over 1276253.32 frames.], batch size: 20, lr: 3.27e-04
+2022-05-15 06:35:57,370 INFO [train.py:812] (1/8) Epoch 24, batch 500, loss[loss=0.1526, simple_loss=0.2372, pruned_loss=0.03403, over 7362.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2486, pruned_loss=0.03324, over 1307828.72 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:36:55,889 INFO [train.py:812] (1/8) Epoch 24, batch 550, loss[loss=0.173, simple_loss=0.2686, pruned_loss=0.03868, over 7205.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2489, pruned_loss=0.03332, over 1336918.51 frames.], batch size: 22, lr: 3.27e-04
+2022-05-15 06:37:55,360 INFO [train.py:812] (1/8) Epoch 24, batch 600, loss[loss=0.1648, simple_loss=0.2553, pruned_loss=0.03712, over 7354.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2484, pruned_loss=0.03358, over 1354235.86 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:38:54,595 INFO [train.py:812] (1/8) Epoch 24, batch 650, loss[loss=0.1513, simple_loss=0.2401, pruned_loss=0.03129, over 7353.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2479, pruned_loss=0.03341, over 1364330.27 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:39:54,718 INFO [train.py:812] (1/8) Epoch 24, batch 700, loss[loss=0.1641, simple_loss=0.2559, pruned_loss=0.03618, over 7171.00 frames.], tot_loss[loss=0.1568, simple_loss=0.247, pruned_loss=0.03335, over 1381222.85 frames.], batch size: 26, lr: 3.27e-04
+2022-05-15 06:40:53,832 INFO [train.py:812] (1/8) Epoch 24, batch 750, loss[loss=0.1486, simple_loss=0.2391, pruned_loss=0.02907, over 7028.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2475, pruned_loss=0.03302, over 1392119.56 frames.], batch size: 16, lr: 3.27e-04
+2022-05-15 06:41:53,029 INFO [train.py:812] (1/8) Epoch 24, batch 800, loss[loss=0.1427, simple_loss=0.2338, pruned_loss=0.02581, over 7252.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2472, pruned_loss=0.03296, over 1399681.60 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:42:52,212 INFO [train.py:812] (1/8) Epoch 24, batch 850, loss[loss=0.1669, simple_loss=0.2624, pruned_loss=0.03567, over 6751.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2469, pruned_loss=0.03271, over 1405407.06 frames.], batch size: 31, lr: 3.27e-04
+2022-05-15 06:43:51,467 INFO [train.py:812] (1/8) Epoch 24, batch 900, loss[loss=0.1441, simple_loss=0.2403, pruned_loss=0.02401, over 7428.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2465, pruned_loss=0.03215, over 1411201.99 frames.], batch size: 20, lr: 3.27e-04
+2022-05-15 06:44:50,514 INFO [train.py:812] (1/8) Epoch 24, batch 950, loss[loss=0.1614, simple_loss=0.2466, pruned_loss=0.03812, over 6272.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2461, pruned_loss=0.03225, over 1415918.53 frames.], batch size: 38, lr: 3.26e-04
+2022-05-15 06:45:49,543 INFO [train.py:812] (1/8) Epoch 24, batch 1000, loss[loss=0.169, simple_loss=0.2729, pruned_loss=0.03251, over 7325.00 frames.], tot_loss[loss=0.156, simple_loss=0.2469, pruned_loss=0.03253, over 1418073.77 frames.], batch size: 21, lr: 3.26e-04
+2022-05-15 06:46:47,307 INFO [train.py:812] (1/8) Epoch 24, batch 1050, loss[loss=0.1368, simple_loss=0.2331, pruned_loss=0.02027, over 7238.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2479, pruned_loss=0.03316, over 1411847.39 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:47:46,419 INFO [train.py:812] (1/8) Epoch 24, batch 1100, loss[loss=0.1748, simple_loss=0.2605, pruned_loss=0.04459, over 7137.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2482, pruned_loss=0.0335, over 1411238.98 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:48:44,900 INFO [train.py:812] (1/8) Epoch 24, batch 1150, loss[loss=0.1517, simple_loss=0.2531, pruned_loss=0.02512, over 6394.00 frames.], tot_loss[loss=0.1565, simple_loss=0.247, pruned_loss=0.03303, over 1415218.56 frames.], batch size: 38, lr: 3.26e-04
+2022-05-15 06:49:42,953 INFO [train.py:812] (1/8) Epoch 24, batch 1200, loss[loss=0.159, simple_loss=0.24, pruned_loss=0.03902, over 7159.00 frames.], tot_loss[loss=0.157, simple_loss=0.2477, pruned_loss=0.03314, over 1417235.11 frames.], batch size: 18, lr: 3.26e-04
+2022-05-15 06:50:50,710 INFO [train.py:812] (1/8) Epoch 24, batch 1250, loss[loss=0.1503, simple_loss=0.2378, pruned_loss=0.03135, over 7331.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2476, pruned_loss=0.03343, over 1418288.90 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:51:49,897 INFO [train.py:812] (1/8) Epoch 24, batch 1300, loss[loss=0.158, simple_loss=0.253, pruned_loss=0.03144, over 6601.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2475, pruned_loss=0.03318, over 1419577.05 frames.], batch size: 31, lr: 3.26e-04
+2022-05-15 06:52:48,831 INFO [train.py:812] (1/8) Epoch 24, batch 1350, loss[loss=0.1317, simple_loss=0.2144, pruned_loss=0.02449, over 7405.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2484, pruned_loss=0.03343, over 1425078.35 frames.], batch size: 18, lr: 3.26e-04
+2022-05-15 06:53:46,294 INFO [train.py:812] (1/8) Epoch 24, batch 1400, loss[loss=0.1781, simple_loss=0.2791, pruned_loss=0.03854, over 7174.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2483, pruned_loss=0.03318, over 1423503.11 frames.], batch size: 26, lr: 3.26e-04
+2022-05-15 06:55:13,450 INFO [train.py:812] (1/8) Epoch 24, batch 1450, loss[loss=0.1431, simple_loss=0.231, pruned_loss=0.02762, over 7147.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2494, pruned_loss=0.03376, over 1421986.57 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:56:21,942 INFO [train.py:812] (1/8) Epoch 24, batch 1500, loss[loss=0.1563, simple_loss=0.2631, pruned_loss=0.0248, over 7150.00 frames.], tot_loss[loss=0.158, simple_loss=0.2489, pruned_loss=0.03358, over 1420026.47 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:57:21,237 INFO [train.py:812] (1/8) Epoch 24, batch 1550, loss[loss=0.168, simple_loss=0.2713, pruned_loss=0.03235, over 6739.00 frames.], tot_loss[loss=0.1575, simple_loss=0.248, pruned_loss=0.03347, over 1419877.30 frames.], batch size: 31, lr: 3.26e-04
+2022-05-15 06:58:39,395 INFO [train.py:812] (1/8) Epoch 24, batch 1600, loss[loss=0.1522, simple_loss=0.2379, pruned_loss=0.03325, over 7324.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2482, pruned_loss=0.03323, over 1421709.19 frames.], batch size: 20, lr: 3.25e-04
+2022-05-15 06:59:37,740 INFO [train.py:812] (1/8) Epoch 24, batch 1650, loss[loss=0.1306, simple_loss=0.2172, pruned_loss=0.02198, over 6790.00 frames.], tot_loss[loss=0.158, simple_loss=0.2489, pruned_loss=0.03351, over 1414670.70 frames.], batch size: 15, lr: 3.25e-04
+2022-05-15 07:00:36,790 INFO [train.py:812] (1/8) Epoch 24, batch 1700, loss[loss=0.1809, simple_loss=0.2789, pruned_loss=0.04141, over 7325.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2492, pruned_loss=0.03362, over 1418751.55 frames.], batch size: 21, lr: 3.25e-04
+2022-05-15 07:01:34,453 INFO [train.py:812] (1/8) Epoch 24, batch 1750, loss[loss=0.1562, simple_loss=0.2407, pruned_loss=0.03592, over 7071.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2496, pruned_loss=0.03388, over 1420227.01 frames.], batch size: 18, lr: 3.25e-04
+2022-05-15 07:02:33,279 INFO [train.py:812] (1/8) Epoch 24, batch 1800, loss[loss=0.1319, simple_loss=0.2335, pruned_loss=0.01512, over 7327.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2493, pruned_loss=0.0338, over 1420674.34 frames.], batch size: 22, lr: 3.25e-04
+2022-05-15 07:03:31,327 INFO [train.py:812] (1/8) Epoch 24, batch 1850, loss[loss=0.1745, simple_loss=0.2734, pruned_loss=0.03777, over 7330.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2491, pruned_loss=0.03373, over 1424673.26 frames.], batch size: 24, lr: 3.25e-04
+2022-05-15 07:04:30,215 INFO [train.py:812] (1/8) Epoch 24, batch 1900, loss[loss=0.1558, simple_loss=0.2616, pruned_loss=0.02496, over 7039.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2492, pruned_loss=0.03386, over 1423119.77 frames.], batch size: 28, lr: 3.25e-04
+2022-05-15 07:05:29,098 INFO [train.py:812] (1/8) Epoch 24, batch 1950, loss[loss=0.1567, simple_loss=0.2587, pruned_loss=0.0274, over 7110.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2492, pruned_loss=0.03361, over 1423743.73 frames.], batch size: 21, lr: 3.25e-04
+2022-05-15 07:06:27,361 INFO [train.py:812] (1/8) Epoch 24, batch 2000, loss[loss=0.1577, simple_loss=0.2517, pruned_loss=0.03184, over 5226.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2506, pruned_loss=0.0343, over 1422880.27 frames.], batch size: 52, lr: 3.25e-04
+2022-05-15 07:07:25,815 INFO [train.py:812] (1/8) Epoch 24, batch 2050, loss[loss=0.168, simple_loss=0.2585, pruned_loss=0.03878, over 7424.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2506, pruned_loss=0.03412, over 1422719.64 frames.], batch size: 20, lr: 3.25e-04
+2022-05-15 07:08:23,655 INFO [train.py:812] (1/8) Epoch 24, batch 2100, loss[loss=0.157, simple_loss=0.2424, pruned_loss=0.03582, over 7009.00 frames.], tot_loss[loss=0.1585, simple_loss=0.25, pruned_loss=0.03356, over 1424266.11 frames.], batch size: 16, lr: 3.25e-04
+2022-05-15 07:09:22,551 INFO [train.py:812] (1/8) Epoch 24, batch 2150, loss[loss=0.1898, simple_loss=0.2759, pruned_loss=0.0519, over 5341.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2495, pruned_loss=0.03366, over 1421495.91 frames.], batch size: 52, lr: 3.25e-04
+2022-05-15 07:10:21,855 INFO [train.py:812] (1/8) Epoch 24, batch 2200, loss[loss=0.1408, simple_loss=0.2223, pruned_loss=0.02967, over 7149.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2494, pruned_loss=0.03361, over 1420178.33 frames.], batch size: 17, lr: 3.25e-04
+2022-05-15 07:11:20,853 INFO [train.py:812] (1/8) Epoch 24, batch 2250, loss[loss=0.1544, simple_loss=0.2406, pruned_loss=0.03417, over 7319.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2503, pruned_loss=0.03403, over 1409760.91 frames.], batch size: 25, lr: 3.24e-04
+2022-05-15 07:12:19,959 INFO [train.py:812] (1/8) Epoch 24, batch 2300, loss[loss=0.1264, simple_loss=0.2077, pruned_loss=0.02257, over 7282.00 frames.], tot_loss[loss=0.1579, simple_loss=0.249, pruned_loss=0.03342, over 1416859.38 frames.], batch size: 17, lr: 3.24e-04
+2022-05-15 07:13:18,775 INFO [train.py:812] (1/8) Epoch 24, batch 2350, loss[loss=0.1568, simple_loss=0.2474, pruned_loss=0.03315, over 7329.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2496, pruned_loss=0.03363, over 1418955.54 frames.], batch size: 22, lr: 3.24e-04
+2022-05-15 07:14:18,397 INFO [train.py:812] (1/8) Epoch 24, batch 2400, loss[loss=0.1506, simple_loss=0.2234, pruned_loss=0.03889, over 6801.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2502, pruned_loss=0.03346, over 1421644.99 frames.], batch size: 15, lr: 3.24e-04
+2022-05-15 07:15:15,760 INFO [train.py:812] (1/8) Epoch 24, batch 2450, loss[loss=0.1813, simple_loss=0.2827, pruned_loss=0.03993, over 7227.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2503, pruned_loss=0.03366, over 1419011.29 frames.], batch size: 20, lr: 3.24e-04
+2022-05-15 07:16:21,375 INFO [train.py:812] (1/8) Epoch 24, batch 2500, loss[loss=0.149, simple_loss=0.2477, pruned_loss=0.02521, over 7320.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2494, pruned_loss=0.03347, over 1418659.82 frames.], batch size: 21, lr: 3.24e-04
+2022-05-15 07:17:19,928 INFO [train.py:812] (1/8) Epoch 24, batch 2550, loss[loss=0.1744, simple_loss=0.2674, pruned_loss=0.0407, over 4930.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2485, pruned_loss=0.03359, over 1413636.17 frames.], batch size: 52, lr: 3.24e-04
+2022-05-15 07:18:18,698 INFO [train.py:812] (1/8) Epoch 24, batch 2600, loss[loss=0.1506, simple_loss=0.2508, pruned_loss=0.02518, over 7288.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2497, pruned_loss=0.03343, over 1417577.01 frames.], batch size: 18, lr: 3.24e-04
+2022-05-15 07:19:17,310 INFO [train.py:812] (1/8) Epoch 24, batch 2650, loss[loss=0.1545, simple_loss=0.2492, pruned_loss=0.02991, over 7321.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2496, pruned_loss=0.03355, over 1417003.31 frames.], batch size: 21, lr: 3.24e-04
+2022-05-15 07:20:16,530 INFO [train.py:812] (1/8) Epoch 24, batch 2700, loss[loss=0.1636, simple_loss=0.2684, pruned_loss=0.02938, over 7342.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2495, pruned_loss=0.03366, over 1421584.44 frames.], batch size: 22, lr: 3.24e-04
+2022-05-15 07:21:15,971 INFO [train.py:812] (1/8) Epoch 24, batch 2750, loss[loss=0.1424, simple_loss=0.2383, pruned_loss=0.02326, over 7415.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2487, pruned_loss=0.03289, over 1425141.05 frames.], batch size: 21, lr: 3.24e-04
+2022-05-15 07:22:15,047 INFO [train.py:812] (1/8) Epoch 24, batch 2800, loss[loss=0.1548, simple_loss=0.244, pruned_loss=0.03277, over 7245.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2498, pruned_loss=0.03376, over 1421109.71 frames.], batch size: 20, lr: 3.24e-04
+2022-05-15 07:23:13,161 INFO [train.py:812] (1/8) Epoch 24, batch 2850, loss[loss=0.1617, simple_loss=0.2553, pruned_loss=0.03403, over 7357.00 frames.], tot_loss[loss=0.159, simple_loss=0.2507, pruned_loss=0.03361, over 1422238.48 frames.], batch size: 19, lr: 3.24e-04
+2022-05-15 07:24:12,090 INFO [train.py:812] (1/8) Epoch 24, batch 2900, loss[loss=0.1762, simple_loss=0.2748, pruned_loss=0.03883, over 7304.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2513, pruned_loss=0.03395, over 1421621.14 frames.], batch size: 25, lr: 3.24e-04
+2022-05-15 07:25:09,864 INFO [train.py:812] (1/8) Epoch 24, batch 2950, loss[loss=0.1737, simple_loss=0.2578, pruned_loss=0.04475, over 7284.00 frames.], tot_loss[loss=0.1594, simple_loss=0.251, pruned_loss=0.0339, over 1425667.30 frames.], batch size: 17, lr: 3.23e-04
+2022-05-15 07:26:08,036 INFO [train.py:812] (1/8) Epoch 24, batch 3000, loss[loss=0.1549, simple_loss=0.2527, pruned_loss=0.02851, over 7120.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2506, pruned_loss=0.03397, over 1421313.76 frames.], batch size: 21, lr: 3.23e-04
+2022-05-15 07:26:08,037 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 07:26:15,602 INFO [train.py:841] (1/8) Epoch 24, validation: loss=0.1537, simple_loss=0.2513, pruned_loss=0.02802, over 698248.00 frames.
+2022-05-15 07:27:15,000 INFO [train.py:812] (1/8) Epoch 24, batch 3050, loss[loss=0.1517, simple_loss=0.2407, pruned_loss=0.03134, over 7271.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2503, pruned_loss=0.03408, over 1416923.58 frames.], batch size: 18, lr: 3.23e-04
+2022-05-15 07:28:13,635 INFO [train.py:812] (1/8) Epoch 24, batch 3100, loss[loss=0.1298, simple_loss=0.22, pruned_loss=0.01985, over 6766.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2497, pruned_loss=0.03423, over 1420336.71 frames.], batch size: 31, lr: 3.23e-04
+2022-05-15 07:29:12,197 INFO [train.py:812] (1/8) Epoch 24, batch 3150, loss[loss=0.1457, simple_loss=0.2165, pruned_loss=0.03748, over 7418.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2494, pruned_loss=0.0341, over 1422083.99 frames.], batch size: 17, lr: 3.23e-04
+2022-05-15 07:30:11,685 INFO [train.py:812] (1/8) Epoch 24, batch 3200, loss[loss=0.1599, simple_loss=0.2572, pruned_loss=0.03125, over 7311.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2493, pruned_loss=0.03355, over 1426286.43 frames.], batch size: 21, lr: 3.23e-04
+2022-05-15 07:31:10,168 INFO [train.py:812] (1/8) Epoch 24, batch 3250, loss[loss=0.1487, simple_loss=0.2331, pruned_loss=0.0322, over 7172.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2484, pruned_loss=0.0334, over 1428584.72 frames.], batch size: 18, lr: 3.23e-04
+2022-05-15 07:32:09,038 INFO [train.py:812] (1/8) Epoch 24, batch 3300, loss[loss=0.1586, simple_loss=0.261, pruned_loss=0.02811, over 7298.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2487, pruned_loss=0.03313, over 1428308.20 frames.], batch size: 24, lr: 3.23e-04
+2022-05-15 07:33:06,614 INFO [train.py:812] (1/8) Epoch 24, batch 3350, loss[loss=0.169, simple_loss=0.2604, pruned_loss=0.03884, over 7291.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2496, pruned_loss=0.0337, over 1423798.02 frames.], batch size: 24, lr: 3.23e-04
+2022-05-15 07:34:04,973 INFO [train.py:812] (1/8) Epoch 24, batch 3400, loss[loss=0.1552, simple_loss=0.2457, pruned_loss=0.03234, over 7372.00 frames.], tot_loss[loss=0.1589, simple_loss=0.25, pruned_loss=0.03392, over 1427994.14 frames.], batch size: 19, lr: 3.23e-04
+2022-05-15 07:35:03,123 INFO [train.py:812] (1/8) Epoch 24, batch 3450, loss[loss=0.1486, simple_loss=0.2446, pruned_loss=0.02633, over 7345.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2501, pruned_loss=0.034, over 1423000.57 frames.], batch size: 22, lr: 3.23e-04
+2022-05-15 07:36:01,796 INFO [train.py:812] (1/8) Epoch 24, batch 3500, loss[loss=0.1235, simple_loss=0.2053, pruned_loss=0.02081, over 6795.00 frames.], tot_loss[loss=0.158, simple_loss=0.2487, pruned_loss=0.03358, over 1422245.36 frames.], batch size: 15, lr: 3.23e-04
+2022-05-15 07:37:00,359 INFO [train.py:812] (1/8) Epoch 24, batch 3550, loss[loss=0.1546, simple_loss=0.2528, pruned_loss=0.02816, over 7119.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2484, pruned_loss=0.03323, over 1423312.91 frames.], batch size: 21, lr: 3.23e-04
+2022-05-15 07:38:00,108 INFO [train.py:812] (1/8) Epoch 24, batch 3600, loss[loss=0.1576, simple_loss=0.2495, pruned_loss=0.03287, over 7068.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2494, pruned_loss=0.03339, over 1423481.50 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:38:57,462 INFO [train.py:812] (1/8) Epoch 24, batch 3650, loss[loss=0.1426, simple_loss=0.2318, pruned_loss=0.02669, over 7350.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2509, pruned_loss=0.03386, over 1424045.08 frames.], batch size: 19, lr: 3.22e-04
+2022-05-15 07:39:55,857 INFO [train.py:812] (1/8) Epoch 24, batch 3700, loss[loss=0.1579, simple_loss=0.2591, pruned_loss=0.02838, over 6416.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2508, pruned_loss=0.03336, over 1420755.93 frames.], batch size: 37, lr: 3.22e-04
+2022-05-15 07:40:52,816 INFO [train.py:812] (1/8) Epoch 24, batch 3750, loss[loss=0.1484, simple_loss=0.2408, pruned_loss=0.02798, over 7278.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2502, pruned_loss=0.03333, over 1422117.36 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:41:51,839 INFO [train.py:812] (1/8) Epoch 24, batch 3800, loss[loss=0.1408, simple_loss=0.2311, pruned_loss=0.02527, over 7425.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2489, pruned_loss=0.03293, over 1424296.63 frames.], batch size: 20, lr: 3.22e-04
+2022-05-15 07:42:51,146 INFO [train.py:812] (1/8) Epoch 24, batch 3850, loss[loss=0.1861, simple_loss=0.2755, pruned_loss=0.04838, over 5110.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2489, pruned_loss=0.03315, over 1420945.89 frames.], batch size: 53, lr: 3.22e-04
+2022-05-15 07:43:50,677 INFO [train.py:812] (1/8) Epoch 24, batch 3900, loss[loss=0.1666, simple_loss=0.2572, pruned_loss=0.03801, over 6755.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2495, pruned_loss=0.03366, over 1417304.28 frames.], batch size: 31, lr: 3.22e-04
+2022-05-15 07:44:49,672 INFO [train.py:812] (1/8) Epoch 24, batch 3950, loss[loss=0.1269, simple_loss=0.2116, pruned_loss=0.02117, over 7148.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2493, pruned_loss=0.03331, over 1417407.64 frames.], batch size: 17, lr: 3.22e-04
+2022-05-15 07:45:48,714 INFO [train.py:812] (1/8) Epoch 24, batch 4000, loss[loss=0.1644, simple_loss=0.2594, pruned_loss=0.03468, over 7213.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2498, pruned_loss=0.03361, over 1415475.13 frames.], batch size: 22, lr: 3.22e-04
+2022-05-15 07:46:47,066 INFO [train.py:812] (1/8) Epoch 24, batch 4050, loss[loss=0.1604, simple_loss=0.2532, pruned_loss=0.0338, over 4831.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2497, pruned_loss=0.03371, over 1416833.01 frames.], batch size: 52, lr: 3.22e-04
+2022-05-15 07:47:46,730 INFO [train.py:812] (1/8) Epoch 24, batch 4100, loss[loss=0.144, simple_loss=0.2276, pruned_loss=0.03015, over 7284.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2498, pruned_loss=0.0338, over 1416929.37 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:48:45,767 INFO [train.py:812] (1/8) Epoch 24, batch 4150, loss[loss=0.1432, simple_loss=0.2223, pruned_loss=0.03203, over 6999.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2498, pruned_loss=0.03397, over 1418375.65 frames.], batch size: 16, lr: 3.22e-04
+2022-05-15 07:49:44,869 INFO [train.py:812] (1/8) Epoch 24, batch 4200, loss[loss=0.1234, simple_loss=0.2083, pruned_loss=0.01923, over 7272.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2499, pruned_loss=0.0339, over 1418943.17 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:50:44,108 INFO [train.py:812] (1/8) Epoch 24, batch 4250, loss[loss=0.1898, simple_loss=0.2782, pruned_loss=0.05064, over 7373.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2491, pruned_loss=0.03388, over 1417064.61 frames.], batch size: 23, lr: 3.22e-04
+2022-05-15 07:51:43,363 INFO [train.py:812] (1/8) Epoch 24, batch 4300, loss[loss=0.1548, simple_loss=0.2342, pruned_loss=0.03774, over 6809.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2483, pruned_loss=0.03351, over 1415922.72 frames.], batch size: 15, lr: 3.21e-04
+2022-05-15 07:52:41,809 INFO [train.py:812] (1/8) Epoch 24, batch 4350, loss[loss=0.1691, simple_loss=0.2644, pruned_loss=0.03691, over 6697.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2487, pruned_loss=0.03348, over 1413166.01 frames.], batch size: 31, lr: 3.21e-04
+2022-05-15 07:53:40,606 INFO [train.py:812] (1/8) Epoch 24, batch 4400, loss[loss=0.1524, simple_loss=0.2485, pruned_loss=0.0282, over 6388.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2494, pruned_loss=0.03398, over 1406371.52 frames.], batch size: 37, lr: 3.21e-04
+2022-05-15 07:54:38,518 INFO [train.py:812] (1/8) Epoch 24, batch 4450, loss[loss=0.1754, simple_loss=0.2699, pruned_loss=0.04039, over 6354.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2486, pruned_loss=0.03384, over 1408754.30 frames.], batch size: 37, lr: 3.21e-04
+2022-05-15 07:55:37,556 INFO [train.py:812] (1/8) Epoch 24, batch 4500, loss[loss=0.1425, simple_loss=0.2379, pruned_loss=0.02357, over 6346.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2493, pruned_loss=0.03408, over 1396168.12 frames.], batch size: 37, lr: 3.21e-04
+2022-05-15 07:56:36,608 INFO [train.py:812] (1/8) Epoch 24, batch 4550, loss[loss=0.1752, simple_loss=0.2689, pruned_loss=0.04075, over 7297.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2496, pruned_loss=0.03425, over 1386042.80 frames.], batch size: 24, lr: 3.21e-04
+2022-05-15 07:57:47,756 INFO [train.py:812] (1/8) Epoch 25, batch 0, loss[loss=0.1787, simple_loss=0.2755, pruned_loss=0.04092, over 7069.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2755, pruned_loss=0.04092, over 7069.00 frames.], batch size: 18, lr: 3.15e-04
+2022-05-15 07:58:47,072 INFO [train.py:812] (1/8) Epoch 25, batch 50, loss[loss=0.1335, simple_loss=0.2235, pruned_loss=0.02178, over 7256.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2511, pruned_loss=0.03474, over 322134.90 frames.], batch size: 19, lr: 3.15e-04
+2022-05-15 07:59:46,724 INFO [train.py:812] (1/8) Epoch 25, batch 100, loss[loss=0.1424, simple_loss=0.236, pruned_loss=0.02434, over 7329.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2499, pruned_loss=0.03495, over 570468.22 frames.], batch size: 20, lr: 3.15e-04
+2022-05-15 08:00:45,689 INFO [train.py:812] (1/8) Epoch 25, batch 150, loss[loss=0.1484, simple_loss=0.2422, pruned_loss=0.02731, over 7308.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2493, pruned_loss=0.03374, over 761445.38 frames.], batch size: 21, lr: 3.14e-04
+2022-05-15 08:01:45,470 INFO [train.py:812] (1/8) Epoch 25, batch 200, loss[loss=0.1416, simple_loss=0.2269, pruned_loss=0.02811, over 6799.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2483, pruned_loss=0.03352, over 906360.31 frames.], batch size: 15, lr: 3.14e-04
+2022-05-15 08:02:44,403 INFO [train.py:812] (1/8) Epoch 25, batch 250, loss[loss=0.1689, simple_loss=0.2665, pruned_loss=0.0356, over 7232.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2487, pruned_loss=0.03326, over 1018404.30 frames.], batch size: 20, lr: 3.14e-04
+2022-05-15 08:03:43,892 INFO [train.py:812] (1/8) Epoch 25, batch 300, loss[loss=0.1509, simple_loss=0.2362, pruned_loss=0.03279, over 7158.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2496, pruned_loss=0.03331, over 1112360.20 frames.], batch size: 19, lr: 3.14e-04
+2022-05-15 08:04:42,718 INFO [train.py:812] (1/8) Epoch 25, batch 350, loss[loss=0.1729, simple_loss=0.2708, pruned_loss=0.03748, over 7197.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2488, pruned_loss=0.03348, over 1181335.92 frames.], batch size: 23, lr: 3.14e-04
+2022-05-15 08:05:50,916 INFO [train.py:812] (1/8) Epoch 25, batch 400, loss[loss=0.1644, simple_loss=0.2617, pruned_loss=0.03359, over 7231.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2474, pruned_loss=0.0327, over 1236505.60 frames.], batch size: 20, lr: 3.14e-04
+2022-05-15 08:06:49,134 INFO [train.py:812] (1/8) Epoch 25, batch 450, loss[loss=0.152, simple_loss=0.2551, pruned_loss=0.02447, over 7027.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2476, pruned_loss=0.03308, over 1277141.88 frames.], batch size: 28, lr: 3.14e-04
+2022-05-15 08:07:48,541 INFO [train.py:812] (1/8) Epoch 25, batch 500, loss[loss=0.1514, simple_loss=0.2433, pruned_loss=0.02978, over 7168.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2481, pruned_loss=0.03313, over 1312730.95 frames.], batch size: 18, lr: 3.14e-04
+2022-05-15 08:08:47,660 INFO [train.py:812] (1/8) Epoch 25, batch 550, loss[loss=0.1501, simple_loss=0.2408, pruned_loss=0.02973, over 7166.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2485, pruned_loss=0.03315, over 1340185.60 frames.], batch size: 18, lr: 3.14e-04
+2022-05-15 08:09:45,620 INFO [train.py:812] (1/8) Epoch 25, batch 600, loss[loss=0.176, simple_loss=0.2714, pruned_loss=0.04031, over 7203.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2486, pruned_loss=0.03297, over 1358904.13 frames.], batch size: 23, lr: 3.14e-04
+2022-05-15 08:10:45,004 INFO [train.py:812] (1/8) Epoch 25, batch 650, loss[loss=0.1768, simple_loss=0.2472, pruned_loss=0.0532, over 7285.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2478, pruned_loss=0.03336, over 1370556.06 frames.], batch size: 17, lr: 3.14e-04
+2022-05-15 08:11:43,791 INFO [train.py:812] (1/8) Epoch 25, batch 700, loss[loss=0.1298, simple_loss=0.2118, pruned_loss=0.0239, over 6815.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2481, pruned_loss=0.03315, over 1386665.10 frames.], batch size: 15, lr: 3.14e-04
+2022-05-15 08:12:42,949 INFO [train.py:812] (1/8) Epoch 25, batch 750, loss[loss=0.1615, simple_loss=0.2599, pruned_loss=0.03155, over 7228.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2482, pruned_loss=0.03326, over 1397603.69 frames.], batch size: 20, lr: 3.14e-04
+2022-05-15 08:13:42,684 INFO [train.py:812] (1/8) Epoch 25, batch 800, loss[loss=0.1738, simple_loss=0.2639, pruned_loss=0.04187, over 7411.00 frames.], tot_loss[loss=0.1571, simple_loss=0.248, pruned_loss=0.03312, over 1405396.14 frames.], batch size: 21, lr: 3.14e-04
+2022-05-15 08:14:42,175 INFO [train.py:812] (1/8) Epoch 25, batch 850, loss[loss=0.1807, simple_loss=0.2756, pruned_loss=0.04293, over 7317.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2485, pruned_loss=0.03312, over 1407527.92 frames.], batch size: 21, lr: 3.13e-04
+2022-05-15 08:15:39,802 INFO [train.py:812] (1/8) Epoch 25, batch 900, loss[loss=0.1864, simple_loss=0.2904, pruned_loss=0.04119, over 7289.00 frames.], tot_loss[loss=0.158, simple_loss=0.2494, pruned_loss=0.0333, over 1410450.46 frames.], batch size: 25, lr: 3.13e-04
+2022-05-15 08:16:38,341 INFO [train.py:812] (1/8) Epoch 25, batch 950, loss[loss=0.1532, simple_loss=0.2469, pruned_loss=0.02978, over 4790.00 frames.], tot_loss[loss=0.158, simple_loss=0.2493, pruned_loss=0.03332, over 1405597.29 frames.], batch size: 52, lr: 3.13e-04
+2022-05-15 08:17:38,346 INFO [train.py:812] (1/8) Epoch 25, batch 1000, loss[loss=0.1666, simple_loss=0.2591, pruned_loss=0.03703, over 7417.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2494, pruned_loss=0.03309, over 1412661.11 frames.], batch size: 21, lr: 3.13e-04
+2022-05-15 08:18:37,744 INFO [train.py:812] (1/8) Epoch 25, batch 1050, loss[loss=0.1507, simple_loss=0.2403, pruned_loss=0.03051, over 7332.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2495, pruned_loss=0.03335, over 1419564.00 frames.], batch size: 20, lr: 3.13e-04
+2022-05-15 08:19:35,299 INFO [train.py:812] (1/8) Epoch 25, batch 1100, loss[loss=0.1522, simple_loss=0.2549, pruned_loss=0.02474, over 7339.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2482, pruned_loss=0.03266, over 1421781.91 frames.], batch size: 22, lr: 3.13e-04
+2022-05-15 08:20:32,131 INFO [train.py:812] (1/8) Epoch 25, batch 1150, loss[loss=0.1828, simple_loss=0.2857, pruned_loss=0.03995, over 7209.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2483, pruned_loss=0.03261, over 1424668.95 frames.], batch size: 23, lr: 3.13e-04
+2022-05-15 08:21:31,794 INFO [train.py:812] (1/8) Epoch 25, batch 1200, loss[loss=0.1701, simple_loss=0.2571, pruned_loss=0.04152, over 7380.00 frames.], tot_loss[loss=0.157, simple_loss=0.2484, pruned_loss=0.03282, over 1424654.20 frames.], batch size: 23, lr: 3.13e-04
+2022-05-15 08:22:29,887 INFO [train.py:812] (1/8) Epoch 25, batch 1250, loss[loss=0.1358, simple_loss=0.2349, pruned_loss=0.0183, over 7141.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2484, pruned_loss=0.03312, over 1423122.34 frames.], batch size: 20, lr: 3.13e-04
+2022-05-15 08:23:28,187 INFO [train.py:812] (1/8) Epoch 25, batch 1300, loss[loss=0.1727, simple_loss=0.2454, pruned_loss=0.05002, over 6821.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2479, pruned_loss=0.03298, over 1422320.04 frames.], batch size: 15, lr: 3.13e-04
+2022-05-15 08:24:27,531 INFO [train.py:812] (1/8) Epoch 25, batch 1350, loss[loss=0.1556, simple_loss=0.2488, pruned_loss=0.03125, over 6567.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2479, pruned_loss=0.03311, over 1421658.61 frames.], batch size: 38, lr: 3.13e-04
+2022-05-15 08:25:26,989 INFO [train.py:812] (1/8) Epoch 25, batch 1400, loss[loss=0.1224, simple_loss=0.2051, pruned_loss=0.01987, over 7278.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2484, pruned_loss=0.03323, over 1426431.44 frames.], batch size: 17, lr: 3.13e-04
+2022-05-15 08:26:26,002 INFO [train.py:812] (1/8) Epoch 25, batch 1450, loss[loss=0.1621, simple_loss=0.2682, pruned_loss=0.02804, over 7148.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2479, pruned_loss=0.03281, over 1422726.94 frames.], batch size: 20, lr: 3.13e-04
+2022-05-15 08:27:24,407 INFO [train.py:812] (1/8) Epoch 25, batch 1500, loss[loss=0.1654, simple_loss=0.259, pruned_loss=0.03586, over 6965.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2475, pruned_loss=0.03275, over 1422111.16 frames.], batch size: 32, lr: 3.13e-04
+2022-05-15 08:28:23,097 INFO [train.py:812] (1/8) Epoch 25, batch 1550, loss[loss=0.1515, simple_loss=0.2317, pruned_loss=0.0357, over 7268.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2489, pruned_loss=0.03292, over 1423191.26 frames.], batch size: 18, lr: 3.12e-04
+2022-05-15 08:29:22,773 INFO [train.py:812] (1/8) Epoch 25, batch 1600, loss[loss=0.1441, simple_loss=0.2331, pruned_loss=0.02753, over 7257.00 frames.], tot_loss[loss=0.1578, simple_loss=0.249, pruned_loss=0.03334, over 1421232.25 frames.], batch size: 16, lr: 3.12e-04
+2022-05-15 08:30:21,913 INFO [train.py:812] (1/8) Epoch 25, batch 1650, loss[loss=0.1511, simple_loss=0.2456, pruned_loss=0.0283, over 7215.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2482, pruned_loss=0.03326, over 1422286.17 frames.], batch size: 21, lr: 3.12e-04
+2022-05-15 08:31:21,075 INFO [train.py:812] (1/8) Epoch 25, batch 1700, loss[loss=0.1626, simple_loss=0.255, pruned_loss=0.03506, over 7388.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2482, pruned_loss=0.03327, over 1419933.11 frames.], batch size: 23, lr: 3.12e-04
+2022-05-15 08:32:19,158 INFO [train.py:812] (1/8) Epoch 25, batch 1750, loss[loss=0.1477, simple_loss=0.2275, pruned_loss=0.03393, over 7146.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2484, pruned_loss=0.0332, over 1422461.23 frames.], batch size: 17, lr: 3.12e-04
+2022-05-15 08:33:18,560 INFO [train.py:812] (1/8) Epoch 25, batch 1800, loss[loss=0.1338, simple_loss=0.2195, pruned_loss=0.02403, over 7009.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2485, pruned_loss=0.03282, over 1422827.25 frames.], batch size: 16, lr: 3.12e-04
+2022-05-15 08:34:17,248 INFO [train.py:812] (1/8) Epoch 25, batch 1850, loss[loss=0.1419, simple_loss=0.2221, pruned_loss=0.0308, over 7207.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2488, pruned_loss=0.03325, over 1419920.59 frames.], batch size: 16, lr: 3.12e-04
+2022-05-15 08:35:20,957 INFO [train.py:812] (1/8) Epoch 25, batch 1900, loss[loss=0.1684, simple_loss=0.2546, pruned_loss=0.04115, over 7329.00 frames.], tot_loss[loss=0.1581, simple_loss=0.249, pruned_loss=0.03354, over 1421718.00 frames.], batch size: 25, lr: 3.12e-04
+2022-05-15 08:36:19,538 INFO [train.py:812] (1/8) Epoch 25, batch 1950, loss[loss=0.1346, simple_loss=0.2245, pruned_loss=0.02228, over 7255.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2479, pruned_loss=0.03328, over 1423424.41 frames.], batch size: 19, lr: 3.12e-04
+2022-05-15 08:37:18,260 INFO [train.py:812] (1/8) Epoch 25, batch 2000, loss[loss=0.1408, simple_loss=0.234, pruned_loss=0.02379, over 7159.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2471, pruned_loss=0.03291, over 1423921.81 frames.], batch size: 18, lr: 3.12e-04
+2022-05-15 08:38:16,610 INFO [train.py:812] (1/8) Epoch 25, batch 2050, loss[loss=0.1725, simple_loss=0.2693, pruned_loss=0.03784, over 7312.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2466, pruned_loss=0.03306, over 1426947.32 frames.], batch size: 21, lr: 3.12e-04
+2022-05-15 08:39:15,901 INFO [train.py:812] (1/8) Epoch 25, batch 2100, loss[loss=0.1458, simple_loss=0.2351, pruned_loss=0.02827, over 7258.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2468, pruned_loss=0.03313, over 1423149.89 frames.], batch size: 19, lr: 3.12e-04
+2022-05-15 08:40:13,572 INFO [train.py:812] (1/8) Epoch 25, batch 2150, loss[loss=0.1651, simple_loss=0.2666, pruned_loss=0.03181, over 7438.00 frames.], tot_loss[loss=0.157, simple_loss=0.2479, pruned_loss=0.03308, over 1421595.82 frames.], batch size: 20, lr: 3.12e-04
+2022-05-15 08:41:13,381 INFO [train.py:812] (1/8) Epoch 25, batch 2200, loss[loss=0.1337, simple_loss=0.2109, pruned_loss=0.02823, over 6779.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2474, pruned_loss=0.03288, over 1421117.75 frames.], batch size: 15, lr: 3.12e-04
+2022-05-15 08:42:11,776 INFO [train.py:812] (1/8) Epoch 25, batch 2250, loss[loss=0.1508, simple_loss=0.2424, pruned_loss=0.02963, over 7073.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2471, pruned_loss=0.03275, over 1417533.80 frames.], batch size: 18, lr: 3.12e-04
+2022-05-15 08:43:09,217 INFO [train.py:812] (1/8) Epoch 25, batch 2300, loss[loss=0.1474, simple_loss=0.2281, pruned_loss=0.03332, over 6805.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2468, pruned_loss=0.03242, over 1418151.57 frames.], batch size: 15, lr: 3.11e-04
+2022-05-15 08:44:06,009 INFO [train.py:812] (1/8) Epoch 25, batch 2350, loss[loss=0.1632, simple_loss=0.2578, pruned_loss=0.0343, over 7314.00 frames.], tot_loss[loss=0.156, simple_loss=0.2466, pruned_loss=0.03265, over 1418738.74 frames.], batch size: 21, lr: 3.11e-04
+2022-05-15 08:45:05,379 INFO [train.py:812] (1/8) Epoch 25, batch 2400, loss[loss=0.1849, simple_loss=0.2693, pruned_loss=0.05025, over 7351.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2487, pruned_loss=0.0335, over 1423873.47 frames.], batch size: 19, lr: 3.11e-04
+2022-05-15 08:46:04,721 INFO [train.py:812] (1/8) Epoch 25, batch 2450, loss[loss=0.1451, simple_loss=0.2303, pruned_loss=0.02997, over 7139.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2486, pruned_loss=0.03347, over 1423126.53 frames.], batch size: 17, lr: 3.11e-04
+2022-05-15 08:47:04,378 INFO [train.py:812] (1/8) Epoch 25, batch 2500, loss[loss=0.1644, simple_loss=0.2613, pruned_loss=0.03379, over 7410.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2483, pruned_loss=0.03343, over 1423436.68 frames.], batch size: 21, lr: 3.11e-04
+2022-05-15 08:48:03,391 INFO [train.py:812] (1/8) Epoch 25, batch 2550, loss[loss=0.1615, simple_loss=0.2593, pruned_loss=0.03187, over 7427.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2485, pruned_loss=0.03303, over 1424635.05 frames.], batch size: 20, lr: 3.11e-04
+2022-05-15 08:49:03,056 INFO [train.py:812] (1/8) Epoch 25, batch 2600, loss[loss=0.1578, simple_loss=0.2376, pruned_loss=0.03896, over 7146.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2482, pruned_loss=0.03312, over 1420550.24 frames.], batch size: 17, lr: 3.11e-04
+2022-05-15 08:50:01,834 INFO [train.py:812] (1/8) Epoch 25, batch 2650, loss[loss=0.1684, simple_loss=0.2594, pruned_loss=0.03873, over 7202.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2489, pruned_loss=0.03337, over 1423133.64 frames.], batch size: 22, lr: 3.11e-04
+2022-05-15 08:51:09,483 INFO [train.py:812] (1/8) Epoch 25, batch 2700, loss[loss=0.1535, simple_loss=0.2396, pruned_loss=0.03373, over 7059.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2482, pruned_loss=0.03317, over 1425299.92 frames.], batch size: 18, lr: 3.11e-04
+2022-05-15 08:52:06,905 INFO [train.py:812] (1/8) Epoch 25, batch 2750, loss[loss=0.1642, simple_loss=0.2577, pruned_loss=0.03533, over 7137.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2472, pruned_loss=0.03297, over 1420813.33 frames.], batch size: 20, lr: 3.11e-04
+2022-05-15 08:53:06,500 INFO [train.py:812] (1/8) Epoch 25, batch 2800, loss[loss=0.1524, simple_loss=0.244, pruned_loss=0.03037, over 7260.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2466, pruned_loss=0.03249, over 1420832.62 frames.], batch size: 19, lr: 3.11e-04
+2022-05-15 08:54:05,449 INFO [train.py:812] (1/8) Epoch 25, batch 2850, loss[loss=0.1485, simple_loss=0.2338, pruned_loss=0.03159, over 7431.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2466, pruned_loss=0.03204, over 1420219.59 frames.], batch size: 20, lr: 3.11e-04
+2022-05-15 08:55:04,573 INFO [train.py:812] (1/8) Epoch 25, batch 2900, loss[loss=0.1507, simple_loss=0.2472, pruned_loss=0.02711, over 7204.00 frames.], tot_loss[loss=0.1562, simple_loss=0.248, pruned_loss=0.03217, over 1420482.07 frames.], batch size: 23, lr: 3.11e-04
+2022-05-15 08:56:02,078 INFO [train.py:812] (1/8) Epoch 25, batch 2950, loss[loss=0.1421, simple_loss=0.2478, pruned_loss=0.01822, over 7114.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2482, pruned_loss=0.03246, over 1425661.75 frames.], batch size: 21, lr: 3.11e-04
+2022-05-15 08:57:29,007 INFO [train.py:812] (1/8) Epoch 25, batch 3000, loss[loss=0.1584, simple_loss=0.2605, pruned_loss=0.02817, over 6704.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2468, pruned_loss=0.03199, over 1428250.75 frames.], batch size: 31, lr: 3.10e-04
+2022-05-15 08:57:29,008 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 08:57:46,644 INFO [train.py:841] (1/8) Epoch 25, validation: loss=0.1532, simple_loss=0.2507, pruned_loss=0.02787, over 698248.00 frames.
+2022-05-15 08:58:45,931 INFO [train.py:812] (1/8) Epoch 25, batch 3050, loss[loss=0.1594, simple_loss=0.265, pruned_loss=0.02689, over 7115.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2468, pruned_loss=0.03193, over 1429129.39 frames.], batch size: 21, lr: 3.10e-04
+2022-05-15 08:59:53,862 INFO [train.py:812] (1/8) Epoch 25, batch 3100, loss[loss=0.1326, simple_loss=0.2189, pruned_loss=0.02316, over 6834.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2459, pruned_loss=0.03187, over 1429142.37 frames.], batch size: 15, lr: 3.10e-04
+2022-05-15 09:01:01,451 INFO [train.py:812] (1/8) Epoch 25, batch 3150, loss[loss=0.1425, simple_loss=0.2354, pruned_loss=0.02484, over 7252.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2469, pruned_loss=0.03249, over 1430292.60 frames.], batch size: 19, lr: 3.10e-04
+2022-05-15 09:02:01,440 INFO [train.py:812] (1/8) Epoch 25, batch 3200, loss[loss=0.2029, simple_loss=0.2755, pruned_loss=0.06513, over 4839.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2463, pruned_loss=0.03241, over 1429282.00 frames.], batch size: 53, lr: 3.10e-04
+2022-05-15 09:03:00,349 INFO [train.py:812] (1/8) Epoch 25, batch 3250, loss[loss=0.1573, simple_loss=0.2386, pruned_loss=0.03798, over 7226.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2473, pruned_loss=0.03307, over 1426564.32 frames.], batch size: 20, lr: 3.10e-04
+2022-05-15 09:03:59,274 INFO [train.py:812] (1/8) Epoch 25, batch 3300, loss[loss=0.151, simple_loss=0.2438, pruned_loss=0.02913, over 7162.00 frames.], tot_loss[loss=0.1574, simple_loss=0.248, pruned_loss=0.03343, over 1425691.09 frames.], batch size: 19, lr: 3.10e-04
+2022-05-15 09:04:58,418 INFO [train.py:812] (1/8) Epoch 25, batch 3350, loss[loss=0.1616, simple_loss=0.2481, pruned_loss=0.03759, over 7258.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2488, pruned_loss=0.03391, over 1423272.52 frames.], batch size: 19, lr: 3.10e-04
+2022-05-15 09:05:57,546 INFO [train.py:812] (1/8) Epoch 25, batch 3400, loss[loss=0.1397, simple_loss=0.2247, pruned_loss=0.02739, over 7268.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2479, pruned_loss=0.03346, over 1425167.64 frames.], batch size: 17, lr: 3.10e-04
+2022-05-15 09:06:55,961 INFO [train.py:812] (1/8) Epoch 25, batch 3450, loss[loss=0.1451, simple_loss=0.24, pruned_loss=0.02513, over 7218.00 frames.], tot_loss[loss=0.1575, simple_loss=0.248, pruned_loss=0.03348, over 1421859.87 frames.], batch size: 21, lr: 3.10e-04
+2022-05-15 09:07:54,089 INFO [train.py:812] (1/8) Epoch 25, batch 3500, loss[loss=0.1336, simple_loss=0.2177, pruned_loss=0.02472, over 7139.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2478, pruned_loss=0.03356, over 1422797.62 frames.], batch size: 17, lr: 3.10e-04
+2022-05-15 09:08:53,537 INFO [train.py:812] (1/8) Epoch 25, batch 3550, loss[loss=0.1484, simple_loss=0.2404, pruned_loss=0.0282, over 7325.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2484, pruned_loss=0.03364, over 1424917.49 frames.], batch size: 20, lr: 3.10e-04
+2022-05-15 09:09:52,738 INFO [train.py:812] (1/8) Epoch 25, batch 3600, loss[loss=0.1622, simple_loss=0.2465, pruned_loss=0.03898, over 7209.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2482, pruned_loss=0.03342, over 1423989.72 frames.], batch size: 23, lr: 3.10e-04
+2022-05-15 09:10:51,687 INFO [train.py:812] (1/8) Epoch 25, batch 3650, loss[loss=0.1553, simple_loss=0.2458, pruned_loss=0.03235, over 6457.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2475, pruned_loss=0.03299, over 1419925.55 frames.], batch size: 38, lr: 3.10e-04
+2022-05-15 09:11:51,258 INFO [train.py:812] (1/8) Epoch 25, batch 3700, loss[loss=0.1598, simple_loss=0.2513, pruned_loss=0.03413, over 7433.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2469, pruned_loss=0.03282, over 1422418.79 frames.], batch size: 20, lr: 3.10e-04
+2022-05-15 09:12:50,494 INFO [train.py:812] (1/8) Epoch 25, batch 3750, loss[loss=0.1713, simple_loss=0.2576, pruned_loss=0.04252, over 7385.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2474, pruned_loss=0.033, over 1424226.17 frames.], batch size: 23, lr: 3.09e-04
+2022-05-15 09:13:50,115 INFO [train.py:812] (1/8) Epoch 25, batch 3800, loss[loss=0.1855, simple_loss=0.2774, pruned_loss=0.04684, over 4985.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2481, pruned_loss=0.03374, over 1421954.15 frames.], batch size: 52, lr: 3.09e-04
+2022-05-15 09:14:48,003 INFO [train.py:812] (1/8) Epoch 25, batch 3850, loss[loss=0.1382, simple_loss=0.2293, pruned_loss=0.02354, over 7278.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2485, pruned_loss=0.03381, over 1421390.56 frames.], batch size: 18, lr: 3.09e-04
+2022-05-15 09:15:47,048 INFO [train.py:812] (1/8) Epoch 25, batch 3900, loss[loss=0.1492, simple_loss=0.2414, pruned_loss=0.02849, over 7257.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2484, pruned_loss=0.03364, over 1420834.34 frames.], batch size: 19, lr: 3.09e-04
+2022-05-15 09:16:44,712 INFO [train.py:812] (1/8) Epoch 25, batch 3950, loss[loss=0.1493, simple_loss=0.2385, pruned_loss=0.03007, over 7425.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2485, pruned_loss=0.03339, over 1422916.42 frames.], batch size: 18, lr: 3.09e-04
+2022-05-15 09:17:43,596 INFO [train.py:812] (1/8) Epoch 25, batch 4000, loss[loss=0.1523, simple_loss=0.2513, pruned_loss=0.02666, over 7320.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2487, pruned_loss=0.03333, over 1422352.43 frames.], batch size: 21, lr: 3.09e-04
+2022-05-15 09:18:42,644 INFO [train.py:812] (1/8) Epoch 25, batch 4050, loss[loss=0.1516, simple_loss=0.2374, pruned_loss=0.03291, over 7447.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2479, pruned_loss=0.03299, over 1421378.10 frames.], batch size: 20, lr: 3.09e-04
+2022-05-15 09:19:41,941 INFO [train.py:812] (1/8) Epoch 25, batch 4100, loss[loss=0.1726, simple_loss=0.2578, pruned_loss=0.04372, over 6442.00 frames.], tot_loss[loss=0.158, simple_loss=0.2487, pruned_loss=0.03363, over 1421863.61 frames.], batch size: 38, lr: 3.09e-04
+2022-05-15 09:20:41,041 INFO [train.py:812] (1/8) Epoch 25, batch 4150, loss[loss=0.1616, simple_loss=0.2547, pruned_loss=0.0343, over 7230.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2481, pruned_loss=0.03338, over 1419006.27 frames.], batch size: 21, lr: 3.09e-04
+2022-05-15 09:21:39,848 INFO [train.py:812] (1/8) Epoch 25, batch 4200, loss[loss=0.1604, simple_loss=0.255, pruned_loss=0.03291, over 7224.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2497, pruned_loss=0.03371, over 1420319.27 frames.], batch size: 23, lr: 3.09e-04
+2022-05-15 09:22:38,426 INFO [train.py:812] (1/8) Epoch 25, batch 4250, loss[loss=0.1638, simple_loss=0.264, pruned_loss=0.0318, over 6532.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2498, pruned_loss=0.0339, over 1414806.58 frames.], batch size: 38, lr: 3.09e-04
+2022-05-15 09:23:37,031 INFO [train.py:812] (1/8) Epoch 25, batch 4300, loss[loss=0.1455, simple_loss=0.2314, pruned_loss=0.02982, over 7161.00 frames.], tot_loss[loss=0.1582, simple_loss=0.249, pruned_loss=0.03366, over 1414940.74 frames.], batch size: 19, lr: 3.09e-04
+2022-05-15 09:24:36,167 INFO [train.py:812] (1/8) Epoch 25, batch 4350, loss[loss=0.1735, simple_loss=0.2682, pruned_loss=0.03938, over 7307.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2482, pruned_loss=0.03367, over 1415185.25 frames.], batch size: 25, lr: 3.09e-04
+2022-05-15 09:25:35,368 INFO [train.py:812] (1/8) Epoch 25, batch 4400, loss[loss=0.1778, simple_loss=0.2671, pruned_loss=0.04429, over 7268.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2491, pruned_loss=0.03383, over 1414421.29 frames.], batch size: 24, lr: 3.09e-04
+2022-05-15 09:26:34,026 INFO [train.py:812] (1/8) Epoch 25, batch 4450, loss[loss=0.1409, simple_loss=0.2424, pruned_loss=0.01966, over 7296.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2497, pruned_loss=0.03373, over 1406069.71 frames.], batch size: 25, lr: 3.09e-04
+2022-05-15 09:27:33,014 INFO [train.py:812] (1/8) Epoch 25, batch 4500, loss[loss=0.1818, simple_loss=0.2613, pruned_loss=0.05112, over 5231.00 frames.], tot_loss[loss=0.1595, simple_loss=0.251, pruned_loss=0.03405, over 1389738.71 frames.], batch size: 55, lr: 3.08e-04
+2022-05-15 09:28:30,316 INFO [train.py:812] (1/8) Epoch 25, batch 4550, loss[loss=0.1739, simple_loss=0.2566, pruned_loss=0.04554, over 5403.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2529, pruned_loss=0.03497, over 1352160.02 frames.], batch size: 52, lr: 3.08e-04
+2022-05-15 09:29:36,551 INFO [train.py:812] (1/8) Epoch 26, batch 0, loss[loss=0.1781, simple_loss=0.2705, pruned_loss=0.04279, over 7216.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2705, pruned_loss=0.04279, over 7216.00 frames.], batch size: 21, lr: 3.02e-04
+2022-05-15 09:30:35,851 INFO [train.py:812] (1/8) Epoch 26, batch 50, loss[loss=0.141, simple_loss=0.2379, pruned_loss=0.02207, over 7324.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2442, pruned_loss=0.02982, over 323111.38 frames.], batch size: 21, lr: 3.02e-04
+2022-05-15 09:31:35,511 INFO [train.py:812] (1/8) Epoch 26, batch 100, loss[loss=0.1895, simple_loss=0.2739, pruned_loss=0.05253, over 5249.00 frames.], tot_loss[loss=0.1545, simple_loss=0.247, pruned_loss=0.03094, over 567251.14 frames.], batch size: 52, lr: 3.02e-04
+2022-05-15 09:32:35,333 INFO [train.py:812] (1/8) Epoch 26, batch 150, loss[loss=0.1464, simple_loss=0.235, pruned_loss=0.02889, over 7267.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2493, pruned_loss=0.03252, over 760524.19 frames.], batch size: 17, lr: 3.02e-04
+2022-05-15 09:33:34,903 INFO [train.py:812] (1/8) Epoch 26, batch 200, loss[loss=0.1758, simple_loss=0.2659, pruned_loss=0.04281, over 7381.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2477, pruned_loss=0.03204, over 907557.41 frames.], batch size: 23, lr: 3.02e-04
+2022-05-15 09:34:32,546 INFO [train.py:812] (1/8) Epoch 26, batch 250, loss[loss=0.1555, simple_loss=0.2503, pruned_loss=0.03034, over 7217.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2474, pruned_loss=0.03238, over 1019661.15 frames.], batch size: 22, lr: 3.02e-04
+2022-05-15 09:35:31,865 INFO [train.py:812] (1/8) Epoch 26, batch 300, loss[loss=0.142, simple_loss=0.2339, pruned_loss=0.02508, over 7328.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2477, pruned_loss=0.03243, over 1106450.50 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:36:29,843 INFO [train.py:812] (1/8) Epoch 26, batch 350, loss[loss=0.136, simple_loss=0.2236, pruned_loss=0.02421, over 7168.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2464, pruned_loss=0.03196, over 1175601.98 frames.], batch size: 18, lr: 3.02e-04
+2022-05-15 09:37:29,643 INFO [train.py:812] (1/8) Epoch 26, batch 400, loss[loss=0.1494, simple_loss=0.2353, pruned_loss=0.0318, over 7411.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2467, pruned_loss=0.03192, over 1233388.02 frames.], batch size: 18, lr: 3.02e-04
+2022-05-15 09:38:28,204 INFO [train.py:812] (1/8) Epoch 26, batch 450, loss[loss=0.1516, simple_loss=0.255, pruned_loss=0.02415, over 7415.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2467, pruned_loss=0.03196, over 1274188.55 frames.], batch size: 21, lr: 3.02e-04
+2022-05-15 09:39:25,636 INFO [train.py:812] (1/8) Epoch 26, batch 500, loss[loss=0.1544, simple_loss=0.2534, pruned_loss=0.02765, over 7371.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2473, pruned_loss=0.03212, over 1302793.53 frames.], batch size: 23, lr: 3.02e-04
+2022-05-15 09:40:22,335 INFO [train.py:812] (1/8) Epoch 26, batch 550, loss[loss=0.1508, simple_loss=0.2508, pruned_loss=0.02544, over 7235.00 frames.], tot_loss[loss=0.155, simple_loss=0.2467, pruned_loss=0.03168, over 1329180.18 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:41:20,606 INFO [train.py:812] (1/8) Epoch 26, batch 600, loss[loss=0.1571, simple_loss=0.2544, pruned_loss=0.02991, over 6999.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2474, pruned_loss=0.03248, over 1347268.08 frames.], batch size: 28, lr: 3.02e-04
+2022-05-15 09:42:19,345 INFO [train.py:812] (1/8) Epoch 26, batch 650, loss[loss=0.1514, simple_loss=0.2459, pruned_loss=0.0285, over 7339.00 frames.], tot_loss[loss=0.156, simple_loss=0.2469, pruned_loss=0.03257, over 1361847.98 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:43:17,901 INFO [train.py:812] (1/8) Epoch 26, batch 700, loss[loss=0.1532, simple_loss=0.2517, pruned_loss=0.02737, over 7146.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2468, pruned_loss=0.03241, over 1375115.51 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:44:17,494 INFO [train.py:812] (1/8) Epoch 26, batch 750, loss[loss=0.1451, simple_loss=0.2378, pruned_loss=0.0262, over 7425.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2471, pruned_loss=0.03212, over 1390804.27 frames.], batch size: 20, lr: 3.01e-04
+2022-05-15 09:45:17,287 INFO [train.py:812] (1/8) Epoch 26, batch 800, loss[loss=0.1578, simple_loss=0.256, pruned_loss=0.02984, over 6888.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2473, pruned_loss=0.0325, over 1396385.51 frames.], batch size: 31, lr: 3.01e-04
+2022-05-15 09:46:14,826 INFO [train.py:812] (1/8) Epoch 26, batch 850, loss[loss=0.1761, simple_loss=0.2767, pruned_loss=0.03773, over 7110.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2479, pruned_loss=0.03231, over 1406732.50 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:47:13,163 INFO [train.py:812] (1/8) Epoch 26, batch 900, loss[loss=0.1421, simple_loss=0.2126, pruned_loss=0.0358, over 6787.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2479, pruned_loss=0.03262, over 1406325.27 frames.], batch size: 15, lr: 3.01e-04
+2022-05-15 09:48:12,077 INFO [train.py:812] (1/8) Epoch 26, batch 950, loss[loss=0.131, simple_loss=0.213, pruned_loss=0.02447, over 7261.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2471, pruned_loss=0.03232, over 1412661.65 frames.], batch size: 17, lr: 3.01e-04
+2022-05-15 09:49:11,021 INFO [train.py:812] (1/8) Epoch 26, batch 1000, loss[loss=0.173, simple_loss=0.2648, pruned_loss=0.04058, over 7123.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2482, pruned_loss=0.03271, over 1411930.30 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:50:10,504 INFO [train.py:812] (1/8) Epoch 26, batch 1050, loss[loss=0.1685, simple_loss=0.2564, pruned_loss=0.0403, over 5405.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2485, pruned_loss=0.03241, over 1412583.71 frames.], batch size: 53, lr: 3.01e-04
+2022-05-15 09:51:08,583 INFO [train.py:812] (1/8) Epoch 26, batch 1100, loss[loss=0.1691, simple_loss=0.2604, pruned_loss=0.03895, over 7115.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2485, pruned_loss=0.03229, over 1413568.81 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:52:08,140 INFO [train.py:812] (1/8) Epoch 26, batch 1150, loss[loss=0.1675, simple_loss=0.2569, pruned_loss=0.03906, over 7376.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2483, pruned_loss=0.03274, over 1417179.44 frames.], batch size: 23, lr: 3.01e-04
+2022-05-15 09:53:08,260 INFO [train.py:812] (1/8) Epoch 26, batch 1200, loss[loss=0.1612, simple_loss=0.2377, pruned_loss=0.04231, over 7129.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2485, pruned_loss=0.0331, over 1420792.83 frames.], batch size: 17, lr: 3.01e-04
+2022-05-15 09:54:07,361 INFO [train.py:812] (1/8) Epoch 26, batch 1250, loss[loss=0.1433, simple_loss=0.2327, pruned_loss=0.02694, over 7315.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2483, pruned_loss=0.03324, over 1422911.75 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:55:11,132 INFO [train.py:812] (1/8) Epoch 26, batch 1300, loss[loss=0.1531, simple_loss=0.2501, pruned_loss=0.02807, over 7421.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2483, pruned_loss=0.03324, over 1426051.01 frames.], batch size: 20, lr: 3.01e-04
+2022-05-15 09:56:09,538 INFO [train.py:812] (1/8) Epoch 26, batch 1350, loss[loss=0.1612, simple_loss=0.2565, pruned_loss=0.03292, over 7326.00 frames.], tot_loss[loss=0.158, simple_loss=0.2489, pruned_loss=0.03348, over 1426647.52 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:57:07,825 INFO [train.py:812] (1/8) Epoch 26, batch 1400, loss[loss=0.1787, simple_loss=0.2686, pruned_loss=0.04437, over 7328.00 frames.], tot_loss[loss=0.1594, simple_loss=0.25, pruned_loss=0.03438, over 1426678.56 frames.], batch size: 22, lr: 3.01e-04
+2022-05-15 09:58:05,641 INFO [train.py:812] (1/8) Epoch 26, batch 1450, loss[loss=0.1356, simple_loss=0.2243, pruned_loss=0.02339, over 7018.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2493, pruned_loss=0.03399, over 1428908.82 frames.], batch size: 16, lr: 3.01e-04
+2022-05-15 09:59:03,790 INFO [train.py:812] (1/8) Epoch 26, batch 1500, loss[loss=0.1524, simple_loss=0.2537, pruned_loss=0.0256, over 7213.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2487, pruned_loss=0.03343, over 1428013.67 frames.], batch size: 21, lr: 3.00e-04
+2022-05-15 10:00:02,488 INFO [train.py:812] (1/8) Epoch 26, batch 1550, loss[loss=0.1402, simple_loss=0.2309, pruned_loss=0.02479, over 7150.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2481, pruned_loss=0.03304, over 1427195.02 frames.], batch size: 17, lr: 3.00e-04
+2022-05-15 10:01:01,516 INFO [train.py:812] (1/8) Epoch 26, batch 1600, loss[loss=0.168, simple_loss=0.2662, pruned_loss=0.03495, over 7145.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2496, pruned_loss=0.03353, over 1424043.19 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:02:00,514 INFO [train.py:812] (1/8) Epoch 26, batch 1650, loss[loss=0.1789, simple_loss=0.2658, pruned_loss=0.04604, over 7167.00 frames.], tot_loss[loss=0.157, simple_loss=0.2481, pruned_loss=0.03294, over 1425177.87 frames.], batch size: 28, lr: 3.00e-04
+2022-05-15 10:02:59,717 INFO [train.py:812] (1/8) Epoch 26, batch 1700, loss[loss=0.1698, simple_loss=0.2649, pruned_loss=0.03732, over 7308.00 frames.], tot_loss[loss=0.1568, simple_loss=0.248, pruned_loss=0.0328, over 1425354.16 frames.], batch size: 21, lr: 3.00e-04
+2022-05-15 10:04:07,540 INFO [train.py:812] (1/8) Epoch 26, batch 1750, loss[loss=0.1304, simple_loss=0.217, pruned_loss=0.02189, over 7142.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2473, pruned_loss=0.0326, over 1424333.15 frames.], batch size: 17, lr: 3.00e-04
+2022-05-15 10:05:06,525 INFO [train.py:812] (1/8) Epoch 26, batch 1800, loss[loss=0.1663, simple_loss=0.259, pruned_loss=0.03683, over 7143.00 frames.], tot_loss[loss=0.156, simple_loss=0.2469, pruned_loss=0.03257, over 1420891.64 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:06:05,260 INFO [train.py:812] (1/8) Epoch 26, batch 1850, loss[loss=0.1628, simple_loss=0.2584, pruned_loss=0.03358, over 7442.00 frames.], tot_loss[loss=0.1558, simple_loss=0.247, pruned_loss=0.03232, over 1422117.23 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:07:04,815 INFO [train.py:812] (1/8) Epoch 26, batch 1900, loss[loss=0.1541, simple_loss=0.228, pruned_loss=0.04007, over 7137.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2471, pruned_loss=0.03233, over 1422939.92 frames.], batch size: 17, lr: 3.00e-04
+2022-05-15 10:08:02,584 INFO [train.py:812] (1/8) Epoch 26, batch 1950, loss[loss=0.1695, simple_loss=0.256, pruned_loss=0.04148, over 5017.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2469, pruned_loss=0.03232, over 1421205.18 frames.], batch size: 52, lr: 3.00e-04
+2022-05-15 10:09:00,906 INFO [train.py:812] (1/8) Epoch 26, batch 2000, loss[loss=0.1546, simple_loss=0.2495, pruned_loss=0.02987, over 7148.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2467, pruned_loss=0.03216, over 1417902.64 frames.], batch size: 19, lr: 3.00e-04
+2022-05-15 10:10:00,117 INFO [train.py:812] (1/8) Epoch 26, batch 2050, loss[loss=0.1538, simple_loss=0.2477, pruned_loss=0.02996, over 7332.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2463, pruned_loss=0.03222, over 1419025.84 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:10:59,277 INFO [train.py:812] (1/8) Epoch 26, batch 2100, loss[loss=0.1534, simple_loss=0.2453, pruned_loss=0.03076, over 7210.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2469, pruned_loss=0.03227, over 1418048.57 frames.], batch size: 22, lr: 3.00e-04
+2022-05-15 10:11:58,143 INFO [train.py:812] (1/8) Epoch 26, batch 2150, loss[loss=0.1434, simple_loss=0.2321, pruned_loss=0.02734, over 7177.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2481, pruned_loss=0.03203, over 1419496.28 frames.], batch size: 18, lr: 3.00e-04
+2022-05-15 10:12:57,684 INFO [train.py:812] (1/8) Epoch 26, batch 2200, loss[loss=0.1669, simple_loss=0.2602, pruned_loss=0.03684, over 7143.00 frames.], tot_loss[loss=0.157, simple_loss=0.2489, pruned_loss=0.03255, over 1421420.12 frames.], batch size: 28, lr: 3.00e-04
+2022-05-15 10:13:56,430 INFO [train.py:812] (1/8) Epoch 26, batch 2250, loss[loss=0.1661, simple_loss=0.2602, pruned_loss=0.03601, over 7377.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2479, pruned_loss=0.03228, over 1423978.91 frames.], batch size: 23, lr: 3.00e-04
+2022-05-15 10:14:54,802 INFO [train.py:812] (1/8) Epoch 26, batch 2300, loss[loss=0.1343, simple_loss=0.2283, pruned_loss=0.02017, over 7060.00 frames.], tot_loss[loss=0.156, simple_loss=0.2478, pruned_loss=0.03211, over 1424210.84 frames.], batch size: 18, lr: 2.99e-04
+2022-05-15 10:15:54,088 INFO [train.py:812] (1/8) Epoch 26, batch 2350, loss[loss=0.1395, simple_loss=0.2355, pruned_loss=0.02174, over 7266.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2474, pruned_loss=0.03224, over 1424455.44 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:16:53,708 INFO [train.py:812] (1/8) Epoch 26, batch 2400, loss[loss=0.173, simple_loss=0.2671, pruned_loss=0.03949, over 7388.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03229, over 1422752.48 frames.], batch size: 23, lr: 2.99e-04
+2022-05-15 10:17:52,704 INFO [train.py:812] (1/8) Epoch 26, batch 2450, loss[loss=0.1725, simple_loss=0.2711, pruned_loss=0.03697, over 6799.00 frames.], tot_loss[loss=0.1569, simple_loss=0.248, pruned_loss=0.03287, over 1422278.10 frames.], batch size: 31, lr: 2.99e-04
+2022-05-15 10:18:50,827 INFO [train.py:812] (1/8) Epoch 26, batch 2500, loss[loss=0.1383, simple_loss=0.2283, pruned_loss=0.02413, over 7356.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2464, pruned_loss=0.03211, over 1422721.47 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:19:48,014 INFO [train.py:812] (1/8) Epoch 26, batch 2550, loss[loss=0.1448, simple_loss=0.2282, pruned_loss=0.03073, over 7408.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2457, pruned_loss=0.03188, over 1425396.57 frames.], batch size: 18, lr: 2.99e-04
+2022-05-15 10:20:46,850 INFO [train.py:812] (1/8) Epoch 26, batch 2600, loss[loss=0.1479, simple_loss=0.2394, pruned_loss=0.02821, over 7147.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2463, pruned_loss=0.03226, over 1423947.39 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:21:44,643 INFO [train.py:812] (1/8) Epoch 26, batch 2650, loss[loss=0.1668, simple_loss=0.2508, pruned_loss=0.04134, over 7132.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2463, pruned_loss=0.03219, over 1419477.32 frames.], batch size: 28, lr: 2.99e-04
+2022-05-15 10:22:43,729 INFO [train.py:812] (1/8) Epoch 26, batch 2700, loss[loss=0.1483, simple_loss=0.2297, pruned_loss=0.03344, over 7260.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2466, pruned_loss=0.03208, over 1420238.60 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:23:42,367 INFO [train.py:812] (1/8) Epoch 26, batch 2750, loss[loss=0.1737, simple_loss=0.2682, pruned_loss=0.03957, over 7279.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2464, pruned_loss=0.03202, over 1413459.98 frames.], batch size: 25, lr: 2.99e-04
+2022-05-15 10:24:40,491 INFO [train.py:812] (1/8) Epoch 26, batch 2800, loss[loss=0.1413, simple_loss=0.2305, pruned_loss=0.02601, over 7284.00 frames.], tot_loss[loss=0.155, simple_loss=0.2461, pruned_loss=0.03194, over 1416207.76 frames.], batch size: 18, lr: 2.99e-04
+2022-05-15 10:25:38,076 INFO [train.py:812] (1/8) Epoch 26, batch 2850, loss[loss=0.1627, simple_loss=0.2608, pruned_loss=0.03231, over 7412.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2456, pruned_loss=0.03182, over 1411800.72 frames.], batch size: 21, lr: 2.99e-04
+2022-05-15 10:26:37,764 INFO [train.py:812] (1/8) Epoch 26, batch 2900, loss[loss=0.1403, simple_loss=0.2315, pruned_loss=0.0246, over 7137.00 frames.], tot_loss[loss=0.1549, simple_loss=0.246, pruned_loss=0.03192, over 1418228.17 frames.], batch size: 20, lr: 2.99e-04
+2022-05-15 10:27:35,281 INFO [train.py:812] (1/8) Epoch 26, batch 2950, loss[loss=0.1449, simple_loss=0.2321, pruned_loss=0.02889, over 7327.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2465, pruned_loss=0.03199, over 1418580.04 frames.], batch size: 20, lr: 2.99e-04
+2022-05-15 10:28:33,134 INFO [train.py:812] (1/8) Epoch 26, batch 3000, loss[loss=0.1474, simple_loss=0.2451, pruned_loss=0.02491, over 6549.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2465, pruned_loss=0.03224, over 1423451.43 frames.], batch size: 38, lr: 2.99e-04
+2022-05-15 10:28:33,135 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 10:28:40,784 INFO [train.py:841] (1/8) Epoch 26, validation: loss=0.1534, simple_loss=0.2507, pruned_loss=0.02805, over 698248.00 frames.
+2022-05-15 10:29:38,762 INFO [train.py:812] (1/8) Epoch 26, batch 3050, loss[loss=0.1574, simple_loss=0.2551, pruned_loss=0.02981, over 7330.00 frames.], tot_loss[loss=0.1556, simple_loss=0.247, pruned_loss=0.03208, over 1422667.64 frames.], batch size: 22, lr: 2.99e-04
+2022-05-15 10:30:38,713 INFO [train.py:812] (1/8) Epoch 26, batch 3100, loss[loss=0.1475, simple_loss=0.2369, pruned_loss=0.029, over 7258.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2472, pruned_loss=0.03219, over 1419598.99 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:31:36,294 INFO [train.py:812] (1/8) Epoch 26, batch 3150, loss[loss=0.1318, simple_loss=0.2145, pruned_loss=0.02455, over 7127.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2472, pruned_loss=0.03254, over 1418947.01 frames.], batch size: 17, lr: 2.98e-04
+2022-05-15 10:32:35,709 INFO [train.py:812] (1/8) Epoch 26, batch 3200, loss[loss=0.1438, simple_loss=0.2377, pruned_loss=0.02498, over 7162.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2476, pruned_loss=0.03229, over 1421236.24 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:33:35,058 INFO [train.py:812] (1/8) Epoch 26, batch 3250, loss[loss=0.1294, simple_loss=0.2186, pruned_loss=0.02008, over 7277.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2462, pruned_loss=0.032, over 1424489.97 frames.], batch size: 18, lr: 2.98e-04
+2022-05-15 10:34:33,020 INFO [train.py:812] (1/8) Epoch 26, batch 3300, loss[loss=0.1592, simple_loss=0.2486, pruned_loss=0.03496, over 7179.00 frames.], tot_loss[loss=0.156, simple_loss=0.2472, pruned_loss=0.0324, over 1417802.74 frames.], batch size: 26, lr: 2.98e-04
+2022-05-15 10:35:31,816 INFO [train.py:812] (1/8) Epoch 26, batch 3350, loss[loss=0.1845, simple_loss=0.2733, pruned_loss=0.04782, over 7308.00 frames.], tot_loss[loss=0.156, simple_loss=0.2473, pruned_loss=0.03234, over 1414757.96 frames.], batch size: 21, lr: 2.98e-04
+2022-05-15 10:36:31,839 INFO [train.py:812] (1/8) Epoch 26, batch 3400, loss[loss=0.1518, simple_loss=0.2533, pruned_loss=0.02513, over 6567.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2467, pruned_loss=0.03221, over 1419434.75 frames.], batch size: 38, lr: 2.98e-04
+2022-05-15 10:37:30,428 INFO [train.py:812] (1/8) Epoch 26, batch 3450, loss[loss=0.1514, simple_loss=0.2371, pruned_loss=0.03286, over 7158.00 frames.], tot_loss[loss=0.155, simple_loss=0.2461, pruned_loss=0.03198, over 1419474.17 frames.], batch size: 18, lr: 2.98e-04
+2022-05-15 10:38:29,754 INFO [train.py:812] (1/8) Epoch 26, batch 3500, loss[loss=0.1655, simple_loss=0.2578, pruned_loss=0.03661, over 7391.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2467, pruned_loss=0.0319, over 1418652.22 frames.], batch size: 23, lr: 2.98e-04
+2022-05-15 10:39:28,317 INFO [train.py:812] (1/8) Epoch 26, batch 3550, loss[loss=0.1459, simple_loss=0.2427, pruned_loss=0.0245, over 7408.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2467, pruned_loss=0.03195, over 1420752.20 frames.], batch size: 21, lr: 2.98e-04
+2022-05-15 10:40:26,266 INFO [train.py:812] (1/8) Epoch 26, batch 3600, loss[loss=0.1546, simple_loss=0.2396, pruned_loss=0.03473, over 7221.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2466, pruned_loss=0.03192, over 1425481.88 frames.], batch size: 23, lr: 2.98e-04
+2022-05-15 10:41:25,808 INFO [train.py:812] (1/8) Epoch 26, batch 3650, loss[loss=0.1366, simple_loss=0.2228, pruned_loss=0.02516, over 7249.00 frames.], tot_loss[loss=0.1556, simple_loss=0.247, pruned_loss=0.03209, over 1426868.81 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:42:23,891 INFO [train.py:812] (1/8) Epoch 26, batch 3700, loss[loss=0.1583, simple_loss=0.2513, pruned_loss=0.03269, over 7077.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2465, pruned_loss=0.03222, over 1423958.01 frames.], batch size: 18, lr: 2.98e-04
+2022-05-15 10:43:22,965 INFO [train.py:812] (1/8) Epoch 26, batch 3750, loss[loss=0.1491, simple_loss=0.244, pruned_loss=0.02712, over 7147.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2473, pruned_loss=0.03275, over 1422343.11 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:44:21,247 INFO [train.py:812] (1/8) Epoch 26, batch 3800, loss[loss=0.1562, simple_loss=0.2454, pruned_loss=0.03353, over 6408.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2465, pruned_loss=0.03246, over 1419754.79 frames.], batch size: 37, lr: 2.98e-04
+2022-05-15 10:45:20,411 INFO [train.py:812] (1/8) Epoch 26, batch 3850, loss[loss=0.1577, simple_loss=0.2512, pruned_loss=0.03205, over 7142.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2466, pruned_loss=0.03253, over 1418225.79 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:46:19,972 INFO [train.py:812] (1/8) Epoch 26, batch 3900, loss[loss=0.1443, simple_loss=0.2239, pruned_loss=0.03232, over 7416.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2475, pruned_loss=0.03283, over 1420259.75 frames.], batch size: 18, lr: 2.97e-04
+2022-05-15 10:47:17,428 INFO [train.py:812] (1/8) Epoch 26, batch 3950, loss[loss=0.1501, simple_loss=0.2411, pruned_loss=0.02958, over 7236.00 frames.], tot_loss[loss=0.156, simple_loss=0.247, pruned_loss=0.0325, over 1424747.78 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:48:16,825 INFO [train.py:812] (1/8) Epoch 26, batch 4000, loss[loss=0.1591, simple_loss=0.2496, pruned_loss=0.03431, over 7438.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2471, pruned_loss=0.03258, over 1417994.49 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:49:15,509 INFO [train.py:812] (1/8) Epoch 26, batch 4050, loss[loss=0.1556, simple_loss=0.25, pruned_loss=0.03058, over 7419.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2467, pruned_loss=0.03215, over 1419583.82 frames.], batch size: 21, lr: 2.97e-04
+2022-05-15 10:50:14,945 INFO [train.py:812] (1/8) Epoch 26, batch 4100, loss[loss=0.146, simple_loss=0.2403, pruned_loss=0.02589, over 7413.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2472, pruned_loss=0.03254, over 1418216.46 frames.], batch size: 21, lr: 2.97e-04
+2022-05-15 10:51:14,792 INFO [train.py:812] (1/8) Epoch 26, batch 4150, loss[loss=0.1359, simple_loss=0.2352, pruned_loss=0.01833, over 7263.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2472, pruned_loss=0.03215, over 1423415.07 frames.], batch size: 19, lr: 2.97e-04
+2022-05-15 10:52:13,190 INFO [train.py:812] (1/8) Epoch 26, batch 4200, loss[loss=0.1521, simple_loss=0.2446, pruned_loss=0.02975, over 7105.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2475, pruned_loss=0.03251, over 1419708.90 frames.], batch size: 28, lr: 2.97e-04
+2022-05-15 10:53:19,324 INFO [train.py:812] (1/8) Epoch 26, batch 4250, loss[loss=0.1332, simple_loss=0.2191, pruned_loss=0.02368, over 7158.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2472, pruned_loss=0.03289, over 1419319.50 frames.], batch size: 18, lr: 2.97e-04
+2022-05-15 10:54:17,959 INFO [train.py:812] (1/8) Epoch 26, batch 4300, loss[loss=0.1763, simple_loss=0.2644, pruned_loss=0.04409, over 7195.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2477, pruned_loss=0.03298, over 1422788.10 frames.], batch size: 26, lr: 2.97e-04
+2022-05-15 10:55:15,842 INFO [train.py:812] (1/8) Epoch 26, batch 4350, loss[loss=0.1431, simple_loss=0.2396, pruned_loss=0.02335, over 7227.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2472, pruned_loss=0.03277, over 1415726.22 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:56:15,085 INFO [train.py:812] (1/8) Epoch 26, batch 4400, loss[loss=0.155, simple_loss=0.2345, pruned_loss=0.0377, over 7449.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2478, pruned_loss=0.03258, over 1415470.10 frames.], batch size: 19, lr: 2.97e-04
+2022-05-15 10:57:23,161 INFO [train.py:812] (1/8) Epoch 26, batch 4450, loss[loss=0.1587, simple_loss=0.2531, pruned_loss=0.03216, over 7299.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2479, pruned_loss=0.03266, over 1414628.36 frames.], batch size: 24, lr: 2.97e-04
+2022-05-15 10:58:40,624 INFO [train.py:812] (1/8) Epoch 26, batch 4500, loss[loss=0.1783, simple_loss=0.2637, pruned_loss=0.04643, over 7315.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2485, pruned_loss=0.03307, over 1399255.69 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:59:48,362 INFO [train.py:812] (1/8) Epoch 26, batch 4550, loss[loss=0.1771, simple_loss=0.262, pruned_loss=0.04613, over 5179.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2488, pruned_loss=0.0334, over 1388643.97 frames.], batch size: 52, lr: 2.97e-04
+2022-05-15 11:01:05,805 INFO [train.py:812] (1/8) Epoch 27, batch 0, loss[loss=0.1352, simple_loss=0.2228, pruned_loss=0.02385, over 7176.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2228, pruned_loss=0.02385, over 7176.00 frames.], batch size: 18, lr: 2.91e-04
+2022-05-15 11:02:14,194 INFO [train.py:812] (1/8) Epoch 27, batch 50, loss[loss=0.1457, simple_loss=0.2246, pruned_loss=0.03343, over 7280.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2463, pruned_loss=0.03318, over 318774.87 frames.], batch size: 17, lr: 2.91e-04
+2022-05-15 11:03:12,397 INFO [train.py:812] (1/8) Epoch 27, batch 100, loss[loss=0.1444, simple_loss=0.2337, pruned_loss=0.0275, over 7282.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2455, pruned_loss=0.03239, over 562113.49 frames.], batch size: 17, lr: 2.91e-04
+2022-05-15 11:04:11,550 INFO [train.py:812] (1/8) Epoch 27, batch 150, loss[loss=0.1644, simple_loss=0.2637, pruned_loss=0.03253, over 6447.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2459, pruned_loss=0.03262, over 750619.27 frames.], batch size: 38, lr: 2.91e-04
+2022-05-15 11:05:08,305 INFO [train.py:812] (1/8) Epoch 27, batch 200, loss[loss=0.1781, simple_loss=0.2702, pruned_loss=0.04297, over 7190.00 frames.], tot_loss[loss=0.1566, simple_loss=0.247, pruned_loss=0.03307, over 892994.01 frames.], batch size: 26, lr: 2.91e-04
+2022-05-15 11:06:06,622 INFO [train.py:812] (1/8) Epoch 27, batch 250, loss[loss=0.14, simple_loss=0.2362, pruned_loss=0.02191, over 6397.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2476, pruned_loss=0.0331, over 1005394.99 frames.], batch size: 38, lr: 2.91e-04
+2022-05-15 11:07:05,730 INFO [train.py:812] (1/8) Epoch 27, batch 300, loss[loss=0.163, simple_loss=0.2632, pruned_loss=0.03137, over 6518.00 frames.], tot_loss[loss=0.157, simple_loss=0.2481, pruned_loss=0.033, over 1100274.91 frames.], batch size: 38, lr: 2.91e-04
+2022-05-15 11:08:04,237 INFO [train.py:812] (1/8) Epoch 27, batch 350, loss[loss=0.1662, simple_loss=0.2521, pruned_loss=0.04018, over 6824.00 frames.], tot_loss[loss=0.156, simple_loss=0.2469, pruned_loss=0.03259, over 1168141.55 frames.], batch size: 32, lr: 2.91e-04
+2022-05-15 11:09:03,270 INFO [train.py:812] (1/8) Epoch 27, batch 400, loss[loss=0.151, simple_loss=0.2423, pruned_loss=0.02986, over 7151.00 frames.], tot_loss[loss=0.1559, simple_loss=0.247, pruned_loss=0.03239, over 1228608.85 frames.], batch size: 20, lr: 2.91e-04
+2022-05-15 11:10:01,857 INFO [train.py:812] (1/8) Epoch 27, batch 450, loss[loss=0.1449, simple_loss=0.2389, pruned_loss=0.02547, over 7243.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2476, pruned_loss=0.03239, over 1276172.99 frames.], batch size: 20, lr: 2.91e-04
+2022-05-15 11:10:59,680 INFO [train.py:812] (1/8) Epoch 27, batch 500, loss[loss=0.1663, simple_loss=0.2432, pruned_loss=0.04464, over 5026.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2466, pruned_loss=0.032, over 1308098.79 frames.], batch size: 52, lr: 2.91e-04
+2022-05-15 11:11:59,501 INFO [train.py:812] (1/8) Epoch 27, batch 550, loss[loss=0.1619, simple_loss=0.2544, pruned_loss=0.03471, over 7195.00 frames.], tot_loss[loss=0.1556, simple_loss=0.247, pruned_loss=0.03211, over 1332395.19 frames.], batch size: 22, lr: 2.90e-04
+2022-05-15 11:12:58,967 INFO [train.py:812] (1/8) Epoch 27, batch 600, loss[loss=0.1356, simple_loss=0.2258, pruned_loss=0.0227, over 7261.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2471, pruned_loss=0.03207, over 1355222.79 frames.], batch size: 19, lr: 2.90e-04
+2022-05-15 11:13:58,659 INFO [train.py:812] (1/8) Epoch 27, batch 650, loss[loss=0.1205, simple_loss=0.2067, pruned_loss=0.01712, over 7280.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2468, pruned_loss=0.0318, over 1371590.34 frames.], batch size: 18, lr: 2.90e-04
+2022-05-15 11:14:57,643 INFO [train.py:812] (1/8) Epoch 27, batch 700, loss[loss=0.1485, simple_loss=0.2467, pruned_loss=0.02518, over 7102.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2474, pruned_loss=0.03213, over 1380996.59 frames.], batch size: 21, lr: 2.90e-04
+2022-05-15 11:16:01,097 INFO [train.py:812] (1/8) Epoch 27, batch 750, loss[loss=0.1479, simple_loss=0.2453, pruned_loss=0.02527, over 7150.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2473, pruned_loss=0.032, over 1389738.03 frames.], batch size: 20, lr: 2.90e-04
+2022-05-15 11:17:00,041 INFO [train.py:812] (1/8) Epoch 27, batch 800, loss[loss=0.155, simple_loss=0.2482, pruned_loss=0.0309, over 7232.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2472, pruned_loss=0.03225, over 1395614.83 frames.], batch size: 20, lr: 2.90e-04
+2022-05-15 11:17:59,355 INFO [train.py:812] (1/8) Epoch 27, batch 850, loss[loss=0.1548, simple_loss=0.243, pruned_loss=0.03332, over 4863.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2478, pruned_loss=0.03201, over 1398540.05 frames.], batch size: 53, lr: 2.90e-04
+2022-05-15 11:18:57,706 INFO [train.py:812] (1/8) Epoch 27, batch 900, loss[loss=0.131, simple_loss=0.2096, pruned_loss=0.02625, over 7413.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2469, pruned_loss=0.03194, over 1408636.67 frames.], batch size: 18, lr: 2.90e-04
+2022-05-15 11:19:56,356 INFO [train.py:812] (1/8) Epoch 27, batch 950, loss[loss=0.1314, simple_loss=0.2192, pruned_loss=0.0218, over 6820.00 frames.], tot_loss[loss=0.156, simple_loss=0.2476, pruned_loss=0.03219, over 1409021.67 frames.], batch size: 15, lr: 2.90e-04
+2022-05-15 11:20:55,297 INFO [train.py:812] (1/8) Epoch 27, batch 1000, loss[loss=0.1706, simple_loss=0.267, pruned_loss=0.03705, over 7278.00 frames.], tot_loss[loss=0.1563, simple_loss=0.248, pruned_loss=0.03226, over 1412351.04 frames.], batch size: 24, lr: 2.90e-04
+2022-05-15 11:21:53,181 INFO [train.py:812] (1/8) Epoch 27, batch 1050, loss[loss=0.1708, simple_loss=0.2662, pruned_loss=0.03771, over 7200.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2483, pruned_loss=0.03227, over 1417331.33 frames.], batch size: 23, lr: 2.90e-04
+2022-05-15 11:22:52,376 INFO [train.py:812] (1/8) Epoch 27, batch 1100, loss[loss=0.1676, simple_loss=0.2639, pruned_loss=0.0357, over 7210.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2472, pruned_loss=0.0319, over 1421595.57 frames.], batch size: 22, lr: 2.90e-04
+2022-05-15 11:23:52,073 INFO [train.py:812] (1/8) Epoch 27, batch 1150, loss[loss=0.1384, simple_loss=0.2309, pruned_loss=0.02293, over 7167.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2473, pruned_loss=0.03164, over 1422888.30 frames.], batch size: 19, lr: 2.90e-04
+2022-05-15 11:24:50,276 INFO [train.py:812] (1/8) Epoch 27, batch 1200, loss[loss=0.1631, simple_loss=0.2588, pruned_loss=0.03368, over 7308.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2476, pruned_loss=0.03186, over 1426626.70 frames.], batch size: 24, lr: 2.90e-04
+2022-05-15 11:25:49,798 INFO [train.py:812] (1/8) Epoch 27, batch 1250, loss[loss=0.1664, simple_loss=0.2577, pruned_loss=0.03752, over 6344.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2476, pruned_loss=0.03176, over 1426246.51 frames.], batch size: 37, lr: 2.90e-04
+2022-05-15 11:26:48,358 INFO [train.py:812] (1/8) Epoch 27, batch 1300, loss[loss=0.1291, simple_loss=0.2152, pruned_loss=0.02147, over 7276.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2476, pruned_loss=0.03171, over 1423383.36 frames.], batch size: 18, lr: 2.90e-04
+2022-05-15 11:27:46,498 INFO [train.py:812] (1/8) Epoch 27, batch 1350, loss[loss=0.1398, simple_loss=0.2307, pruned_loss=0.02447, over 7423.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2463, pruned_loss=0.03154, over 1426595.50 frames.], batch size: 18, lr: 2.89e-04
+2022-05-15 11:28:44,272 INFO [train.py:812] (1/8) Epoch 27, batch 1400, loss[loss=0.1853, simple_loss=0.2657, pruned_loss=0.0525, over 7213.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2454, pruned_loss=0.03137, over 1419291.91 frames.], batch size: 23, lr: 2.89e-04
+2022-05-15 11:29:43,170 INFO [train.py:812] (1/8) Epoch 27, batch 1450, loss[loss=0.1255, simple_loss=0.2084, pruned_loss=0.02134, over 7284.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2461, pruned_loss=0.03208, over 1422014.44 frames.], batch size: 18, lr: 2.89e-04
+2022-05-15 11:30:41,590 INFO [train.py:812] (1/8) Epoch 27, batch 1500, loss[loss=0.1739, simple_loss=0.2585, pruned_loss=0.0446, over 4798.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2456, pruned_loss=0.03132, over 1418047.12 frames.], batch size: 52, lr: 2.89e-04
+2022-05-15 11:31:41,139 INFO [train.py:812] (1/8) Epoch 27, batch 1550, loss[loss=0.1514, simple_loss=0.249, pruned_loss=0.02691, over 7110.00 frames.], tot_loss[loss=0.1543, simple_loss=0.246, pruned_loss=0.03129, over 1420962.70 frames.], batch size: 21, lr: 2.89e-04
+2022-05-15 11:32:40,459 INFO [train.py:812] (1/8) Epoch 27, batch 1600, loss[loss=0.1426, simple_loss=0.2311, pruned_loss=0.02698, over 7261.00 frames.], tot_loss[loss=0.1537, simple_loss=0.245, pruned_loss=0.03118, over 1425319.16 frames.], batch size: 19, lr: 2.89e-04
+2022-05-15 11:33:39,626 INFO [train.py:812] (1/8) Epoch 27, batch 1650, loss[loss=0.1858, simple_loss=0.2855, pruned_loss=0.04304, over 7131.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2455, pruned_loss=0.03139, over 1429052.36 frames.], batch size: 26, lr: 2.89e-04
+2022-05-15 11:34:37,988 INFO [train.py:812] (1/8) Epoch 27, batch 1700, loss[loss=0.1728, simple_loss=0.2713, pruned_loss=0.03717, over 7337.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2457, pruned_loss=0.03141, over 1430478.45 frames.], batch size: 22, lr: 2.89e-04
+2022-05-15 11:35:35,784 INFO [train.py:812] (1/8) Epoch 27, batch 1750, loss[loss=0.2049, simple_loss=0.2887, pruned_loss=0.06057, over 7167.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2466, pruned_loss=0.03201, over 1430725.25 frames.], batch size: 26, lr: 2.89e-04
+2022-05-15 11:36:34,358 INFO [train.py:812] (1/8) Epoch 27, batch 1800, loss[loss=0.1553, simple_loss=0.2516, pruned_loss=0.02954, over 7132.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2469, pruned_loss=0.03218, over 1428056.42 frames.], batch size: 21, lr: 2.89e-04
+2022-05-15 11:37:32,436 INFO [train.py:812] (1/8) Epoch 27, batch 1850, loss[loss=0.1921, simple_loss=0.2762, pruned_loss=0.05398, over 4998.00 frames.], tot_loss[loss=0.1556, simple_loss=0.247, pruned_loss=0.03209, over 1429026.91 frames.], batch size: 53, lr: 2.89e-04
+2022-05-15 11:38:30,737 INFO [train.py:812] (1/8) Epoch 27, batch 1900, loss[loss=0.153, simple_loss=0.2441, pruned_loss=0.03093, over 7357.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2458, pruned_loss=0.03187, over 1427831.82 frames.], batch size: 19, lr: 2.89e-04
+2022-05-15 11:39:30,045 INFO [train.py:812] (1/8) Epoch 27, batch 1950, loss[loss=0.1582, simple_loss=0.2475, pruned_loss=0.03439, over 6397.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2463, pruned_loss=0.0324, over 1424789.28 frames.], batch size: 38, lr: 2.89e-04
+2022-05-15 11:40:29,355 INFO [train.py:812] (1/8) Epoch 27, batch 2000, loss[loss=0.1468, simple_loss=0.2351, pruned_loss=0.02927, over 6732.00 frames.], tot_loss[loss=0.1544, simple_loss=0.245, pruned_loss=0.03195, over 1423380.10 frames.], batch size: 31, lr: 2.89e-04
+2022-05-15 11:41:28,624 INFO [train.py:812] (1/8) Epoch 27, batch 2050, loss[loss=0.1849, simple_loss=0.2887, pruned_loss=0.04053, over 7120.00 frames.], tot_loss[loss=0.156, simple_loss=0.2468, pruned_loss=0.03259, over 1426343.38 frames.], batch size: 26, lr: 2.89e-04
+2022-05-15 11:42:27,677 INFO [train.py:812] (1/8) Epoch 27, batch 2100, loss[loss=0.1762, simple_loss=0.2595, pruned_loss=0.04649, over 7212.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2469, pruned_loss=0.03278, over 1424328.00 frames.], batch size: 22, lr: 2.89e-04
+2022-05-15 11:43:25,344 INFO [train.py:812] (1/8) Epoch 27, batch 2150, loss[loss=0.1637, simple_loss=0.2604, pruned_loss=0.03344, over 7297.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2481, pruned_loss=0.03314, over 1427815.74 frames.], batch size: 25, lr: 2.89e-04
+2022-05-15 11:44:23,707 INFO [train.py:812] (1/8) Epoch 27, batch 2200, loss[loss=0.1462, simple_loss=0.24, pruned_loss=0.02618, over 7227.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2478, pruned_loss=0.03255, over 1426954.68 frames.], batch size: 20, lr: 2.88e-04
+2022-05-15 11:45:23,010 INFO [train.py:812] (1/8) Epoch 27, batch 2250, loss[loss=0.1238, simple_loss=0.2096, pruned_loss=0.01899, over 6997.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2477, pruned_loss=0.03238, over 1431978.07 frames.], batch size: 16, lr: 2.88e-04
+2022-05-15 11:46:21,526 INFO [train.py:812] (1/8) Epoch 27, batch 2300, loss[loss=0.1258, simple_loss=0.2031, pruned_loss=0.02424, over 7136.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2479, pruned_loss=0.03264, over 1433363.00 frames.], batch size: 17, lr: 2.88e-04
+2022-05-15 11:47:19,554 INFO [train.py:812] (1/8) Epoch 27, batch 2350, loss[loss=0.1767, simple_loss=0.2686, pruned_loss=0.04242, over 7155.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2488, pruned_loss=0.03284, over 1431759.42 frames.], batch size: 20, lr: 2.88e-04
+2022-05-15 11:48:16,535 INFO [train.py:812] (1/8) Epoch 27, batch 2400, loss[loss=0.1864, simple_loss=0.2771, pruned_loss=0.04788, over 7313.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2482, pruned_loss=0.03246, over 1432739.08 frames.], batch size: 24, lr: 2.88e-04
+2022-05-15 11:49:16,164 INFO [train.py:812] (1/8) Epoch 27, batch 2450, loss[loss=0.1414, simple_loss=0.2288, pruned_loss=0.02695, over 7230.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2471, pruned_loss=0.03195, over 1435446.56 frames.], batch size: 20, lr: 2.88e-04
+2022-05-15 11:50:15,234 INFO [train.py:812] (1/8) Epoch 27, batch 2500, loss[loss=0.1591, simple_loss=0.2486, pruned_loss=0.03476, over 7219.00 frames.], tot_loss[loss=0.1554, simple_loss=0.247, pruned_loss=0.03187, over 1437330.77 frames.], batch size: 21, lr: 2.88e-04
+2022-05-15 11:51:13,617 INFO [train.py:812] (1/8) Epoch 27, batch 2550, loss[loss=0.144, simple_loss=0.2331, pruned_loss=0.02747, over 6823.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2462, pruned_loss=0.03116, over 1434986.91 frames.], batch size: 31, lr: 2.88e-04
+2022-05-15 11:52:12,747 INFO [train.py:812] (1/8) Epoch 27, batch 2600, loss[loss=0.166, simple_loss=0.2482, pruned_loss=0.04197, over 6794.00 frames.], tot_loss[loss=0.154, simple_loss=0.2456, pruned_loss=0.03123, over 1435471.68 frames.], batch size: 15, lr: 2.88e-04
+2022-05-15 11:53:12,234 INFO [train.py:812] (1/8) Epoch 27, batch 2650, loss[loss=0.1807, simple_loss=0.2661, pruned_loss=0.04765, over 7314.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2464, pruned_loss=0.03186, over 1431056.08 frames.], batch size: 24, lr: 2.88e-04
+2022-05-15 11:54:11,604 INFO [train.py:812] (1/8) Epoch 27, batch 2700, loss[loss=0.1554, simple_loss=0.2549, pruned_loss=0.02793, over 7339.00 frames.], tot_loss[loss=0.1547, simple_loss=0.246, pruned_loss=0.03164, over 1428937.78 frames.], batch size: 22, lr: 2.88e-04
+2022-05-15 11:55:10,411 INFO [train.py:812] (1/8) Epoch 27, batch 2750, loss[loss=0.1579, simple_loss=0.2402, pruned_loss=0.03779, over 7145.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2456, pruned_loss=0.03151, over 1427624.68 frames.], batch size: 19, lr: 2.88e-04
+2022-05-15 11:56:08,585 INFO [train.py:812] (1/8) Epoch 27, batch 2800, loss[loss=0.1543, simple_loss=0.246, pruned_loss=0.03127, over 7300.00 frames.], tot_loss[loss=0.155, simple_loss=0.2466, pruned_loss=0.03165, over 1427153.07 frames.], batch size: 25, lr: 2.88e-04
+2022-05-15 11:57:08,022 INFO [train.py:812] (1/8) Epoch 27, batch 2850, loss[loss=0.1351, simple_loss=0.2261, pruned_loss=0.02202, over 7263.00 frames.], tot_loss[loss=0.1553, simple_loss=0.247, pruned_loss=0.03179, over 1426537.69 frames.], batch size: 19, lr: 2.88e-04
+2022-05-15 11:58:06,922 INFO [train.py:812] (1/8) Epoch 27, batch 2900, loss[loss=0.1488, simple_loss=0.2408, pruned_loss=0.02846, over 7167.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2463, pruned_loss=0.03126, over 1425557.37 frames.], batch size: 19, lr: 2.88e-04
+2022-05-15 11:59:06,486 INFO [train.py:812] (1/8) Epoch 27, batch 2950, loss[loss=0.1518, simple_loss=0.2514, pruned_loss=0.02613, over 7117.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2465, pruned_loss=0.03113, over 1419873.30 frames.], batch size: 21, lr: 2.88e-04
+2022-05-15 12:00:05,427 INFO [train.py:812] (1/8) Epoch 27, batch 3000, loss[loss=0.1705, simple_loss=0.2596, pruned_loss=0.04073, over 7409.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2467, pruned_loss=0.03112, over 1418962.51 frames.], batch size: 21, lr: 2.88e-04
+2022-05-15 12:00:05,428 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 12:00:12,945 INFO [train.py:841] (1/8) Epoch 27, validation: loss=0.1528, simple_loss=0.25, pruned_loss=0.02785, over 698248.00 frames.
+2022-05-15 12:01:11,831 INFO [train.py:812] (1/8) Epoch 27, batch 3050, loss[loss=0.1655, simple_loss=0.2696, pruned_loss=0.03068, over 7107.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2459, pruned_loss=0.03125, over 1410713.94 frames.], batch size: 21, lr: 2.87e-04
+2022-05-15 12:02:10,770 INFO [train.py:812] (1/8) Epoch 27, batch 3100, loss[loss=0.1547, simple_loss=0.2502, pruned_loss=0.02958, over 7317.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2464, pruned_loss=0.03123, over 1416897.33 frames.], batch size: 21, lr: 2.87e-04
+2022-05-15 12:03:20,245 INFO [train.py:812] (1/8) Epoch 27, batch 3150, loss[loss=0.1678, simple_loss=0.2538, pruned_loss=0.04089, over 7216.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2476, pruned_loss=0.03238, over 1417471.07 frames.], batch size: 22, lr: 2.87e-04
+2022-05-15 12:04:19,265 INFO [train.py:812] (1/8) Epoch 27, batch 3200, loss[loss=0.1756, simple_loss=0.2677, pruned_loss=0.04168, over 7212.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2485, pruned_loss=0.03282, over 1419480.42 frames.], batch size: 23, lr: 2.87e-04
+2022-05-15 12:05:18,853 INFO [train.py:812] (1/8) Epoch 27, batch 3250, loss[loss=0.1551, simple_loss=0.249, pruned_loss=0.03066, over 6640.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2484, pruned_loss=0.03249, over 1420083.44 frames.], batch size: 39, lr: 2.87e-04
+2022-05-15 12:06:17,718 INFO [train.py:812] (1/8) Epoch 27, batch 3300, loss[loss=0.1581, simple_loss=0.2523, pruned_loss=0.03201, over 6757.00 frames.], tot_loss[loss=0.156, simple_loss=0.2475, pruned_loss=0.03224, over 1419933.25 frames.], batch size: 31, lr: 2.87e-04
+2022-05-15 12:07:17,054 INFO [train.py:812] (1/8) Epoch 27, batch 3350, loss[loss=0.1828, simple_loss=0.2709, pruned_loss=0.04735, over 7330.00 frames.], tot_loss[loss=0.1563, simple_loss=0.248, pruned_loss=0.03233, over 1420290.24 frames.], batch size: 22, lr: 2.87e-04
+2022-05-15 12:08:16,169 INFO [train.py:812] (1/8) Epoch 27, batch 3400, loss[loss=0.155, simple_loss=0.2526, pruned_loss=0.02868, over 7151.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2475, pruned_loss=0.03214, over 1417430.07 frames.], batch size: 20, lr: 2.87e-04
+2022-05-15 12:09:14,979 INFO [train.py:812] (1/8) Epoch 27, batch 3450, loss[loss=0.1706, simple_loss=0.2572, pruned_loss=0.04198, over 7341.00 frames.], tot_loss[loss=0.1561, simple_loss=0.248, pruned_loss=0.03207, over 1420900.02 frames.], batch size: 22, lr: 2.87e-04
+2022-05-15 12:10:13,334 INFO [train.py:812] (1/8) Epoch 27, batch 3500, loss[loss=0.1325, simple_loss=0.2232, pruned_loss=0.02086, over 7245.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03226, over 1423657.23 frames.], batch size: 16, lr: 2.87e-04
+2022-05-15 12:11:13,078 INFO [train.py:812] (1/8) Epoch 27, batch 3550, loss[loss=0.1701, simple_loss=0.2591, pruned_loss=0.04056, over 5528.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2462, pruned_loss=0.03177, over 1418529.70 frames.], batch size: 52, lr: 2.87e-04
+2022-05-15 12:12:10,923 INFO [train.py:812] (1/8) Epoch 27, batch 3600, loss[loss=0.1538, simple_loss=0.2475, pruned_loss=0.03004, over 7158.00 frames.], tot_loss[loss=0.155, simple_loss=0.2464, pruned_loss=0.03184, over 1416003.82 frames.], batch size: 19, lr: 2.87e-04
+2022-05-15 12:13:10,315 INFO [train.py:812] (1/8) Epoch 27, batch 3650, loss[loss=0.1353, simple_loss=0.2278, pruned_loss=0.02137, over 7075.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2464, pruned_loss=0.03208, over 1414946.81 frames.], batch size: 18, lr: 2.87e-04
+2022-05-15 12:14:09,323 INFO [train.py:812] (1/8) Epoch 27, batch 3700, loss[loss=0.1429, simple_loss=0.2267, pruned_loss=0.0296, over 7286.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2463, pruned_loss=0.03215, over 1413511.90 frames.], batch size: 18, lr: 2.87e-04
+2022-05-15 12:15:08,326 INFO [train.py:812] (1/8) Epoch 27, batch 3750, loss[loss=0.1404, simple_loss=0.2357, pruned_loss=0.0226, over 7226.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2454, pruned_loss=0.03211, over 1417628.32 frames.], batch size: 21, lr: 2.87e-04
+2022-05-15 12:16:08,059 INFO [train.py:812] (1/8) Epoch 27, batch 3800, loss[loss=0.1585, simple_loss=0.2562, pruned_loss=0.0304, over 7329.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2452, pruned_loss=0.03195, over 1421594.57 frames.], batch size: 20, lr: 2.87e-04
+2022-05-15 12:17:07,779 INFO [train.py:812] (1/8) Epoch 27, batch 3850, loss[loss=0.1263, simple_loss=0.2099, pruned_loss=0.02133, over 7398.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2467, pruned_loss=0.03241, over 1414754.67 frames.], batch size: 18, lr: 2.87e-04
+2022-05-15 12:18:06,250 INFO [train.py:812] (1/8) Epoch 27, batch 3900, loss[loss=0.1705, simple_loss=0.2635, pruned_loss=0.03871, over 7070.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2476, pruned_loss=0.03262, over 1415393.74 frames.], batch size: 28, lr: 2.86e-04
+2022-05-15 12:19:04,967 INFO [train.py:812] (1/8) Epoch 27, batch 3950, loss[loss=0.1513, simple_loss=0.2334, pruned_loss=0.03457, over 7360.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2478, pruned_loss=0.03256, over 1419160.07 frames.], batch size: 19, lr: 2.86e-04
+2022-05-15 12:20:04,220 INFO [train.py:812] (1/8) Epoch 27, batch 4000, loss[loss=0.165, simple_loss=0.2664, pruned_loss=0.03179, over 7135.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2466, pruned_loss=0.03196, over 1424719.07 frames.], batch size: 28, lr: 2.86e-04
+2022-05-15 12:21:04,113 INFO [train.py:812] (1/8) Epoch 27, batch 4050, loss[loss=0.1466, simple_loss=0.2373, pruned_loss=0.02793, over 7345.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.0318, over 1426320.03 frames.], batch size: 20, lr: 2.86e-04
+2022-05-15 12:22:03,544 INFO [train.py:812] (1/8) Epoch 27, batch 4100, loss[loss=0.1548, simple_loss=0.2507, pruned_loss=0.02947, over 7323.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2451, pruned_loss=0.03127, over 1424617.48 frames.], batch size: 20, lr: 2.86e-04
+2022-05-15 12:23:02,357 INFO [train.py:812] (1/8) Epoch 27, batch 4150, loss[loss=0.1548, simple_loss=0.2439, pruned_loss=0.03289, over 7104.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2456, pruned_loss=0.03142, over 1421363.50 frames.], batch size: 21, lr: 2.86e-04
+2022-05-15 12:23:59,498 INFO [train.py:812] (1/8) Epoch 27, batch 4200, loss[loss=0.1432, simple_loss=0.2337, pruned_loss=0.02632, over 7332.00 frames.], tot_loss[loss=0.154, simple_loss=0.2454, pruned_loss=0.03136, over 1422820.46 frames.], batch size: 22, lr: 2.86e-04
+2022-05-15 12:24:57,507 INFO [train.py:812] (1/8) Epoch 27, batch 4250, loss[loss=0.1853, simple_loss=0.2821, pruned_loss=0.04422, over 7413.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2469, pruned_loss=0.03184, over 1415649.06 frames.], batch size: 21, lr: 2.86e-04
+2022-05-15 12:25:55,495 INFO [train.py:812] (1/8) Epoch 27, batch 4300, loss[loss=0.1867, simple_loss=0.2763, pruned_loss=0.04852, over 6693.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2476, pruned_loss=0.03229, over 1414067.74 frames.], batch size: 31, lr: 2.86e-04
+2022-05-15 12:26:54,778 INFO [train.py:812] (1/8) Epoch 27, batch 4350, loss[loss=0.1318, simple_loss=0.2121, pruned_loss=0.02578, over 7017.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2474, pruned_loss=0.0324, over 1413153.45 frames.], batch size: 16, lr: 2.86e-04
+2022-05-15 12:27:53,343 INFO [train.py:812] (1/8) Epoch 27, batch 4400, loss[loss=0.1509, simple_loss=0.2492, pruned_loss=0.02624, over 6353.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2486, pruned_loss=0.03327, over 1400215.14 frames.], batch size: 37, lr: 2.86e-04
+2022-05-15 12:28:51,267 INFO [train.py:812] (1/8) Epoch 27, batch 4450, loss[loss=0.1481, simple_loss=0.2507, pruned_loss=0.02278, over 7345.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2478, pruned_loss=0.03276, over 1396018.21 frames.], batch size: 22, lr: 2.86e-04
+2022-05-15 12:29:50,410 INFO [train.py:812] (1/8) Epoch 27, batch 4500, loss[loss=0.1743, simple_loss=0.267, pruned_loss=0.04081, over 7162.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2477, pruned_loss=0.03285, over 1385452.88 frames.], batch size: 18, lr: 2.86e-04
+2022-05-15 12:30:49,292 INFO [train.py:812] (1/8) Epoch 27, batch 4550, loss[loss=0.1926, simple_loss=0.284, pruned_loss=0.05059, over 5045.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2466, pruned_loss=0.03297, over 1369407.12 frames.], batch size: 52, lr: 2.86e-04
+2022-05-15 12:32:00,089 INFO [train.py:812] (1/8) Epoch 28, batch 0, loss[loss=0.1417, simple_loss=0.2278, pruned_loss=0.02783, over 7264.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2278, pruned_loss=0.02783, over 7264.00 frames.], batch size: 19, lr: 2.81e-04
+2022-05-15 12:32:59,359 INFO [train.py:812] (1/8) Epoch 28, batch 50, loss[loss=0.1535, simple_loss=0.2428, pruned_loss=0.03211, over 7264.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2464, pruned_loss=0.032, over 321502.71 frames.], batch size: 19, lr: 2.81e-04
+2022-05-15 12:33:58,539 INFO [train.py:812] (1/8) Epoch 28, batch 100, loss[loss=0.1575, simple_loss=0.2474, pruned_loss=0.03381, over 7143.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2471, pruned_loss=0.0317, over 565018.47 frames.], batch size: 20, lr: 2.80e-04
+2022-05-15 12:35:03,230 INFO [train.py:812] (1/8) Epoch 28, batch 150, loss[loss=0.1353, simple_loss=0.2344, pruned_loss=0.01807, over 6464.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2458, pruned_loss=0.0308, over 753288.05 frames.], batch size: 37, lr: 2.80e-04
+2022-05-15 12:36:01,532 INFO [train.py:812] (1/8) Epoch 28, batch 200, loss[loss=0.1749, simple_loss=0.2685, pruned_loss=0.0406, over 7221.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2455, pruned_loss=0.03063, over 898976.19 frames.], batch size: 23, lr: 2.80e-04
+2022-05-15 12:36:59,616 INFO [train.py:812] (1/8) Epoch 28, batch 250, loss[loss=0.1481, simple_loss=0.2461, pruned_loss=0.02505, over 7277.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2465, pruned_loss=0.03126, over 1014863.98 frames.], batch size: 24, lr: 2.80e-04
+2022-05-15 12:37:58,314 INFO [train.py:812] (1/8) Epoch 28, batch 300, loss[loss=0.1478, simple_loss=0.2502, pruned_loss=0.0227, over 6820.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2472, pruned_loss=0.03129, over 1104317.84 frames.], batch size: 31, lr: 2.80e-04
+2022-05-15 12:38:57,249 INFO [train.py:812] (1/8) Epoch 28, batch 350, loss[loss=0.1478, simple_loss=0.2435, pruned_loss=0.02604, over 7156.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2474, pruned_loss=0.03149, over 1176511.64 frames.], batch size: 19, lr: 2.80e-04
+2022-05-15 12:39:55,230 INFO [train.py:812] (1/8) Epoch 28, batch 400, loss[loss=0.1473, simple_loss=0.2397, pruned_loss=0.0274, over 7144.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2475, pruned_loss=0.03183, over 1232961.19 frames.], batch size: 17, lr: 2.80e-04
+2022-05-15 12:40:54,508 INFO [train.py:812] (1/8) Epoch 28, batch 450, loss[loss=0.1657, simple_loss=0.2606, pruned_loss=0.03545, over 7344.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2471, pruned_loss=0.03174, over 1269819.89 frames.], batch size: 25, lr: 2.80e-04
+2022-05-15 12:41:53,062 INFO [train.py:812] (1/8) Epoch 28, batch 500, loss[loss=0.1558, simple_loss=0.2614, pruned_loss=0.02512, over 7309.00 frames.], tot_loss[loss=0.155, simple_loss=0.2472, pruned_loss=0.03145, over 1307153.07 frames.], batch size: 21, lr: 2.80e-04
+2022-05-15 12:42:52,288 INFO [train.py:812] (1/8) Epoch 28, batch 550, loss[loss=0.1487, simple_loss=0.2427, pruned_loss=0.02729, over 7048.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2466, pruned_loss=0.03158, over 1329250.32 frames.], batch size: 18, lr: 2.80e-04
+2022-05-15 12:43:51,386 INFO [train.py:812] (1/8) Epoch 28, batch 600, loss[loss=0.1387, simple_loss=0.2319, pruned_loss=0.02274, over 7324.00 frames.], tot_loss[loss=0.1544, simple_loss=0.246, pruned_loss=0.03142, over 1347781.31 frames.], batch size: 20, lr: 2.80e-04
+2022-05-15 12:44:49,177 INFO [train.py:812] (1/8) Epoch 28, batch 650, loss[loss=0.1529, simple_loss=0.2513, pruned_loss=0.02727, over 7055.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2464, pruned_loss=0.0315, over 1365747.47 frames.], batch size: 28, lr: 2.80e-04
+2022-05-15 12:45:47,942 INFO [train.py:812] (1/8) Epoch 28, batch 700, loss[loss=0.1446, simple_loss=0.23, pruned_loss=0.02962, over 7064.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2463, pruned_loss=0.03163, over 1379740.49 frames.], batch size: 18, lr: 2.80e-04
+2022-05-15 12:46:48,082 INFO [train.py:812] (1/8) Epoch 28, batch 750, loss[loss=0.1522, simple_loss=0.2513, pruned_loss=0.02652, over 7228.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2452, pruned_loss=0.03131, over 1391120.87 frames.], batch size: 21, lr: 2.80e-04
+2022-05-15 12:47:47,178 INFO [train.py:812] (1/8) Epoch 28, batch 800, loss[loss=0.1618, simple_loss=0.2598, pruned_loss=0.03193, over 7051.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2453, pruned_loss=0.03116, over 1397635.01 frames.], batch size: 28, lr: 2.80e-04
+2022-05-15 12:48:46,798 INFO [train.py:812] (1/8) Epoch 28, batch 850, loss[loss=0.1615, simple_loss=0.2584, pruned_loss=0.03228, over 7292.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2459, pruned_loss=0.03126, over 1405074.81 frames.], batch size: 25, lr: 2.80e-04
+2022-05-15 12:49:45,708 INFO [train.py:812] (1/8) Epoch 28, batch 900, loss[loss=0.1407, simple_loss=0.2299, pruned_loss=0.02576, over 7002.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2472, pruned_loss=0.03193, over 1407220.55 frames.], batch size: 16, lr: 2.80e-04
+2022-05-15 12:50:45,002 INFO [train.py:812] (1/8) Epoch 28, batch 950, loss[loss=0.1506, simple_loss=0.2416, pruned_loss=0.02984, over 7152.00 frames.], tot_loss[loss=0.155, simple_loss=0.2467, pruned_loss=0.03162, over 1409313.11 frames.], batch size: 18, lr: 2.80e-04
+2022-05-15 12:51:43,939 INFO [train.py:812] (1/8) Epoch 28, batch 1000, loss[loss=0.159, simple_loss=0.2511, pruned_loss=0.03342, over 7425.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2465, pruned_loss=0.03163, over 1415026.33 frames.], batch size: 20, lr: 2.79e-04
+2022-05-15 12:52:42,469 INFO [train.py:812] (1/8) Epoch 28, batch 1050, loss[loss=0.1811, simple_loss=0.2698, pruned_loss=0.04616, over 7414.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2471, pruned_loss=0.03214, over 1414916.28 frames.], batch size: 21, lr: 2.79e-04
+2022-05-15 12:53:50,426 INFO [train.py:812] (1/8) Epoch 28, batch 1100, loss[loss=0.1634, simple_loss=0.2479, pruned_loss=0.03943, over 7056.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2481, pruned_loss=0.03241, over 1414445.39 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 12:54:49,772 INFO [train.py:812] (1/8) Epoch 28, batch 1150, loss[loss=0.1531, simple_loss=0.2481, pruned_loss=0.029, over 7200.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2473, pruned_loss=0.03217, over 1419834.89 frames.], batch size: 23, lr: 2.79e-04
+2022-05-15 12:55:48,175 INFO [train.py:812] (1/8) Epoch 28, batch 1200, loss[loss=0.1512, simple_loss=0.2324, pruned_loss=0.035, over 7147.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2467, pruned_loss=0.03194, over 1424559.79 frames.], batch size: 17, lr: 2.79e-04
+2022-05-15 12:56:47,566 INFO [train.py:812] (1/8) Epoch 28, batch 1250, loss[loss=0.1231, simple_loss=0.2094, pruned_loss=0.0184, over 7146.00 frames.], tot_loss[loss=0.1557, simple_loss=0.247, pruned_loss=0.03217, over 1422556.44 frames.], batch size: 17, lr: 2.79e-04
+2022-05-15 12:57:56,211 INFO [train.py:812] (1/8) Epoch 28, batch 1300, loss[loss=0.1274, simple_loss=0.2159, pruned_loss=0.01942, over 7269.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2469, pruned_loss=0.03221, over 1418757.58 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 12:58:55,619 INFO [train.py:812] (1/8) Epoch 28, batch 1350, loss[loss=0.1461, simple_loss=0.2356, pruned_loss=0.02833, over 7356.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2462, pruned_loss=0.03209, over 1419082.93 frames.], batch size: 19, lr: 2.79e-04
+2022-05-15 13:00:02,704 INFO [train.py:812] (1/8) Epoch 28, batch 1400, loss[loss=0.1484, simple_loss=0.2414, pruned_loss=0.02775, over 7050.00 frames.], tot_loss[loss=0.155, simple_loss=0.246, pruned_loss=0.03196, over 1418657.96 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 13:01:30,480 INFO [train.py:812] (1/8) Epoch 28, batch 1450, loss[loss=0.135, simple_loss=0.2221, pruned_loss=0.024, over 7330.00 frames.], tot_loss[loss=0.1541, simple_loss=0.245, pruned_loss=0.03156, over 1421592.82 frames.], batch size: 20, lr: 2.79e-04
+2022-05-15 13:02:27,760 INFO [train.py:812] (1/8) Epoch 28, batch 1500, loss[loss=0.1806, simple_loss=0.2775, pruned_loss=0.04182, over 7120.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2458, pruned_loss=0.03156, over 1423485.89 frames.], batch size: 21, lr: 2.79e-04
+2022-05-15 13:03:25,150 INFO [train.py:812] (1/8) Epoch 28, batch 1550, loss[loss=0.1429, simple_loss=0.225, pruned_loss=0.03041, over 6776.00 frames.], tot_loss[loss=0.155, simple_loss=0.2463, pruned_loss=0.03186, over 1420757.79 frames.], batch size: 15, lr: 2.79e-04
+2022-05-15 13:04:33,675 INFO [train.py:812] (1/8) Epoch 28, batch 1600, loss[loss=0.1426, simple_loss=0.2373, pruned_loss=0.02395, over 7415.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2462, pruned_loss=0.03198, over 1425385.39 frames.], batch size: 21, lr: 2.79e-04
+2022-05-15 13:05:32,118 INFO [train.py:812] (1/8) Epoch 28, batch 1650, loss[loss=0.1523, simple_loss=0.2455, pruned_loss=0.02958, over 7067.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2464, pruned_loss=0.03217, over 1426542.02 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 13:06:30,574 INFO [train.py:812] (1/8) Epoch 28, batch 1700, loss[loss=0.1628, simple_loss=0.2486, pruned_loss=0.03855, over 7346.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2471, pruned_loss=0.03237, over 1428012.47 frames.], batch size: 19, lr: 2.79e-04
+2022-05-15 13:07:29,476 INFO [train.py:812] (1/8) Epoch 28, batch 1750, loss[loss=0.1709, simple_loss=0.2651, pruned_loss=0.03836, over 6779.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2463, pruned_loss=0.03209, over 1429878.64 frames.], batch size: 31, lr: 2.79e-04
+2022-05-15 13:08:28,867 INFO [train.py:812] (1/8) Epoch 28, batch 1800, loss[loss=0.1784, simple_loss=0.2773, pruned_loss=0.03973, over 7234.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2468, pruned_loss=0.03218, over 1429606.51 frames.], batch size: 20, lr: 2.79e-04
+2022-05-15 13:09:27,168 INFO [train.py:812] (1/8) Epoch 28, batch 1850, loss[loss=0.1395, simple_loss=0.2316, pruned_loss=0.02372, over 7158.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2467, pruned_loss=0.03195, over 1431931.18 frames.], batch size: 19, lr: 2.79e-04
+2022-05-15 13:10:26,312 INFO [train.py:812] (1/8) Epoch 28, batch 1900, loss[loss=0.1461, simple_loss=0.237, pruned_loss=0.02759, over 7279.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2474, pruned_loss=0.03209, over 1431556.96 frames.], batch size: 17, lr: 2.78e-04
+2022-05-15 13:11:24,501 INFO [train.py:812] (1/8) Epoch 28, batch 1950, loss[loss=0.1551, simple_loss=0.2528, pruned_loss=0.02872, over 6503.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2468, pruned_loss=0.03187, over 1426186.09 frames.], batch size: 38, lr: 2.78e-04
+2022-05-15 13:12:23,341 INFO [train.py:812] (1/8) Epoch 28, batch 2000, loss[loss=0.1655, simple_loss=0.2709, pruned_loss=0.03001, over 7224.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2469, pruned_loss=0.03193, over 1425623.12 frames.], batch size: 21, lr: 2.78e-04
+2022-05-15 13:13:21,535 INFO [train.py:812] (1/8) Epoch 28, batch 2050, loss[loss=0.1698, simple_loss=0.2502, pruned_loss=0.04472, over 7195.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2479, pruned_loss=0.03241, over 1424242.87 frames.], batch size: 23, lr: 2.78e-04
+2022-05-15 13:14:21,000 INFO [train.py:812] (1/8) Epoch 28, batch 2100, loss[loss=0.1864, simple_loss=0.275, pruned_loss=0.04886, over 7297.00 frames.], tot_loss[loss=0.156, simple_loss=0.2477, pruned_loss=0.03219, over 1423998.51 frames.], batch size: 25, lr: 2.78e-04
+2022-05-15 13:15:20,657 INFO [train.py:812] (1/8) Epoch 28, batch 2150, loss[loss=0.1388, simple_loss=0.2241, pruned_loss=0.02677, over 7138.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2477, pruned_loss=0.03219, over 1422697.74 frames.], batch size: 17, lr: 2.78e-04
+2022-05-15 13:16:19,069 INFO [train.py:812] (1/8) Epoch 28, batch 2200, loss[loss=0.1646, simple_loss=0.2533, pruned_loss=0.03794, over 7284.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2476, pruned_loss=0.03243, over 1422118.48 frames.], batch size: 24, lr: 2.78e-04
+2022-05-15 13:17:18,173 INFO [train.py:812] (1/8) Epoch 28, batch 2250, loss[loss=0.1613, simple_loss=0.2573, pruned_loss=0.03262, over 7322.00 frames.], tot_loss[loss=0.156, simple_loss=0.2473, pruned_loss=0.0323, over 1424414.82 frames.], batch size: 22, lr: 2.78e-04
+2022-05-15 13:18:16,754 INFO [train.py:812] (1/8) Epoch 28, batch 2300, loss[loss=0.1696, simple_loss=0.269, pruned_loss=0.03509, over 7136.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03219, over 1422033.53 frames.], batch size: 20, lr: 2.78e-04
+2022-05-15 13:19:16,293 INFO [train.py:812] (1/8) Epoch 28, batch 2350, loss[loss=0.1306, simple_loss=0.2185, pruned_loss=0.02138, over 7163.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2476, pruned_loss=0.03252, over 1419417.14 frames.], batch size: 19, lr: 2.78e-04
+2022-05-15 13:20:14,237 INFO [train.py:812] (1/8) Epoch 28, batch 2400, loss[loss=0.1813, simple_loss=0.2721, pruned_loss=0.04522, over 7189.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2477, pruned_loss=0.03247, over 1421947.48 frames.], batch size: 23, lr: 2.78e-04
+2022-05-15 13:21:14,079 INFO [train.py:812] (1/8) Epoch 28, batch 2450, loss[loss=0.1501, simple_loss=0.2504, pruned_loss=0.02491, over 6446.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2467, pruned_loss=0.03183, over 1423405.69 frames.], batch size: 37, lr: 2.78e-04
+2022-05-15 13:22:13,016 INFO [train.py:812] (1/8) Epoch 28, batch 2500, loss[loss=0.1403, simple_loss=0.2172, pruned_loss=0.03165, over 6763.00 frames.], tot_loss[loss=0.1546, simple_loss=0.246, pruned_loss=0.03156, over 1419781.74 frames.], batch size: 15, lr: 2.78e-04
+2022-05-15 13:23:12,409 INFO [train.py:812] (1/8) Epoch 28, batch 2550, loss[loss=0.1301, simple_loss=0.2268, pruned_loss=0.01672, over 7255.00 frames.], tot_loss[loss=0.1546, simple_loss=0.246, pruned_loss=0.03164, over 1420591.44 frames.], batch size: 19, lr: 2.78e-04
+2022-05-15 13:24:10,655 INFO [train.py:812] (1/8) Epoch 28, batch 2600, loss[loss=0.1505, simple_loss=0.242, pruned_loss=0.02953, over 7225.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2461, pruned_loss=0.03143, over 1420859.38 frames.], batch size: 20, lr: 2.78e-04
+2022-05-15 13:25:09,880 INFO [train.py:812] (1/8) Epoch 28, batch 2650, loss[loss=0.128, simple_loss=0.2214, pruned_loss=0.01729, over 6999.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2471, pruned_loss=0.03215, over 1419836.52 frames.], batch size: 16, lr: 2.78e-04
+2022-05-15 13:26:08,938 INFO [train.py:812] (1/8) Epoch 28, batch 2700, loss[loss=0.1537, simple_loss=0.2457, pruned_loss=0.03085, over 7307.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2475, pruned_loss=0.03207, over 1421873.26 frames.], batch size: 21, lr: 2.78e-04
+2022-05-15 13:27:07,533 INFO [train.py:812] (1/8) Epoch 28, batch 2750, loss[loss=0.1421, simple_loss=0.2349, pruned_loss=0.02463, over 7260.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2473, pruned_loss=0.03184, over 1419672.33 frames.], batch size: 19, lr: 2.78e-04
+2022-05-15 13:28:05,906 INFO [train.py:812] (1/8) Epoch 28, batch 2800, loss[loss=0.1488, simple_loss=0.2379, pruned_loss=0.02981, over 7226.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2471, pruned_loss=0.03198, over 1416310.52 frames.], batch size: 20, lr: 2.77e-04
+2022-05-15 13:29:05,090 INFO [train.py:812] (1/8) Epoch 28, batch 2850, loss[loss=0.1565, simple_loss=0.2446, pruned_loss=0.03422, over 7126.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2466, pruned_loss=0.0318, over 1420716.85 frames.], batch size: 17, lr: 2.77e-04
+2022-05-15 13:30:03,006 INFO [train.py:812] (1/8) Epoch 28, batch 2900, loss[loss=0.1774, simple_loss=0.2822, pruned_loss=0.03628, over 7332.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2474, pruned_loss=0.03174, over 1420356.09 frames.], batch size: 25, lr: 2.77e-04
+2022-05-15 13:31:01,403 INFO [train.py:812] (1/8) Epoch 28, batch 2950, loss[loss=0.1519, simple_loss=0.2457, pruned_loss=0.02904, over 7228.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2472, pruned_loss=0.03186, over 1423521.08 frames.], batch size: 23, lr: 2.77e-04
+2022-05-15 13:32:00,612 INFO [train.py:812] (1/8) Epoch 28, batch 3000, loss[loss=0.1773, simple_loss=0.2736, pruned_loss=0.04049, over 7031.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2469, pruned_loss=0.03167, over 1425342.97 frames.], batch size: 28, lr: 2.77e-04
+2022-05-15 13:32:00,613 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 13:32:08,091 INFO [train.py:841] (1/8) Epoch 28, validation: loss=0.1523, simple_loss=0.2496, pruned_loss=0.02748, over 698248.00 frames.
+2022-05-15 13:33:05,908 INFO [train.py:812] (1/8) Epoch 28, batch 3050, loss[loss=0.1411, simple_loss=0.2141, pruned_loss=0.034, over 7138.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2471, pruned_loss=0.03177, over 1427154.42 frames.], batch size: 17, lr: 2.77e-04
+2022-05-15 13:34:04,039 INFO [train.py:812] (1/8) Epoch 28, batch 3100, loss[loss=0.1494, simple_loss=0.2405, pruned_loss=0.02912, over 7389.00 frames.], tot_loss[loss=0.155, simple_loss=0.2462, pruned_loss=0.03186, over 1425820.89 frames.], batch size: 23, lr: 2.77e-04
+2022-05-15 13:35:03,620 INFO [train.py:812] (1/8) Epoch 28, batch 3150, loss[loss=0.129, simple_loss=0.2225, pruned_loss=0.01777, over 7407.00 frames.], tot_loss[loss=0.155, simple_loss=0.2463, pruned_loss=0.03184, over 1424063.94 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:36:02,623 INFO [train.py:812] (1/8) Epoch 28, batch 3200, loss[loss=0.1443, simple_loss=0.2448, pruned_loss=0.02193, over 7311.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2464, pruned_loss=0.03165, over 1424516.71 frames.], batch size: 21, lr: 2.77e-04
+2022-05-15 13:37:02,640 INFO [train.py:812] (1/8) Epoch 28, batch 3250, loss[loss=0.1587, simple_loss=0.2479, pruned_loss=0.0347, over 7162.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2458, pruned_loss=0.03179, over 1424374.34 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:37:59,651 INFO [train.py:812] (1/8) Epoch 28, batch 3300, loss[loss=0.1321, simple_loss=0.2141, pruned_loss=0.02499, over 6991.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.03174, over 1423330.98 frames.], batch size: 16, lr: 2.77e-04
+2022-05-15 13:38:57,854 INFO [train.py:812] (1/8) Epoch 28, batch 3350, loss[loss=0.1676, simple_loss=0.2576, pruned_loss=0.03878, over 7377.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2462, pruned_loss=0.03201, over 1420812.53 frames.], batch size: 23, lr: 2.77e-04
+2022-05-15 13:39:56,928 INFO [train.py:812] (1/8) Epoch 28, batch 3400, loss[loss=0.1653, simple_loss=0.253, pruned_loss=0.03879, over 7316.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2466, pruned_loss=0.0321, over 1422646.59 frames.], batch size: 20, lr: 2.77e-04
+2022-05-15 13:40:56,429 INFO [train.py:812] (1/8) Epoch 28, batch 3450, loss[loss=0.1862, simple_loss=0.2767, pruned_loss=0.04781, over 7206.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2465, pruned_loss=0.03201, over 1423622.14 frames.], batch size: 22, lr: 2.77e-04
+2022-05-15 13:41:55,467 INFO [train.py:812] (1/8) Epoch 28, batch 3500, loss[loss=0.1645, simple_loss=0.2548, pruned_loss=0.03714, over 7068.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2462, pruned_loss=0.03203, over 1422676.21 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:42:54,597 INFO [train.py:812] (1/8) Epoch 28, batch 3550, loss[loss=0.1735, simple_loss=0.2719, pruned_loss=0.0375, over 7339.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2467, pruned_loss=0.03184, over 1423643.05 frames.], batch size: 22, lr: 2.77e-04
+2022-05-15 13:43:53,656 INFO [train.py:812] (1/8) Epoch 28, batch 3600, loss[loss=0.1663, simple_loss=0.246, pruned_loss=0.04326, over 7066.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2472, pruned_loss=0.03191, over 1422576.55 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:44:53,069 INFO [train.py:812] (1/8) Epoch 28, batch 3650, loss[loss=0.1689, simple_loss=0.259, pruned_loss=0.03945, over 7416.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2463, pruned_loss=0.032, over 1423523.70 frames.], batch size: 21, lr: 2.77e-04
+2022-05-15 13:45:51,488 INFO [train.py:812] (1/8) Epoch 28, batch 3700, loss[loss=0.1405, simple_loss=0.2303, pruned_loss=0.02533, over 7433.00 frames.], tot_loss[loss=0.1549, simple_loss=0.246, pruned_loss=0.03185, over 1422915.72 frames.], batch size: 20, lr: 2.77e-04
+2022-05-15 13:46:50,220 INFO [train.py:812] (1/8) Epoch 28, batch 3750, loss[loss=0.1746, simple_loss=0.2543, pruned_loss=0.04744, over 5037.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2461, pruned_loss=0.0318, over 1419498.47 frames.], batch size: 52, lr: 2.76e-04
+2022-05-15 13:47:49,318 INFO [train.py:812] (1/8) Epoch 28, batch 3800, loss[loss=0.1456, simple_loss=0.23, pruned_loss=0.03064, over 7269.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2461, pruned_loss=0.03156, over 1421448.65 frames.], batch size: 17, lr: 2.76e-04
+2022-05-15 13:48:48,422 INFO [train.py:812] (1/8) Epoch 28, batch 3850, loss[loss=0.1697, simple_loss=0.269, pruned_loss=0.03521, over 7169.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2458, pruned_loss=0.03132, over 1425589.44 frames.], batch size: 19, lr: 2.76e-04
+2022-05-15 13:49:47,452 INFO [train.py:812] (1/8) Epoch 28, batch 3900, loss[loss=0.1712, simple_loss=0.2591, pruned_loss=0.04166, over 7202.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2461, pruned_loss=0.03155, over 1424076.79 frames.], batch size: 22, lr: 2.76e-04
+2022-05-15 13:50:47,231 INFO [train.py:812] (1/8) Epoch 28, batch 3950, loss[loss=0.1769, simple_loss=0.2573, pruned_loss=0.04828, over 7207.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2454, pruned_loss=0.03121, over 1425091.17 frames.], batch size: 22, lr: 2.76e-04
+2022-05-15 13:51:46,168 INFO [train.py:812] (1/8) Epoch 28, batch 4000, loss[loss=0.1561, simple_loss=0.2476, pruned_loss=0.03225, over 6739.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2444, pruned_loss=0.03125, over 1421542.72 frames.], batch size: 31, lr: 2.76e-04
+2022-05-15 13:52:45,717 INFO [train.py:812] (1/8) Epoch 28, batch 4050, loss[loss=0.1721, simple_loss=0.2609, pruned_loss=0.04166, over 5284.00 frames.], tot_loss[loss=0.154, simple_loss=0.2453, pruned_loss=0.03131, over 1415650.76 frames.], batch size: 52, lr: 2.76e-04
+2022-05-15 13:53:44,801 INFO [train.py:812] (1/8) Epoch 28, batch 4100, loss[loss=0.1545, simple_loss=0.2308, pruned_loss=0.03914, over 7144.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2453, pruned_loss=0.03145, over 1417669.02 frames.], batch size: 17, lr: 2.76e-04
+2022-05-15 13:54:49,272 INFO [train.py:812] (1/8) Epoch 28, batch 4150, loss[loss=0.1376, simple_loss=0.2358, pruned_loss=0.01969, over 7156.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2463, pruned_loss=0.03159, over 1422434.87 frames.], batch size: 19, lr: 2.76e-04
+2022-05-15 13:55:47,970 INFO [train.py:812] (1/8) Epoch 28, batch 4200, loss[loss=0.1957, simple_loss=0.2854, pruned_loss=0.05302, over 4923.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2475, pruned_loss=0.03236, over 1416290.93 frames.], batch size: 53, lr: 2.76e-04
+2022-05-15 13:56:46,295 INFO [train.py:812] (1/8) Epoch 28, batch 4250, loss[loss=0.1369, simple_loss=0.2222, pruned_loss=0.02576, over 7063.00 frames.], tot_loss[loss=0.156, simple_loss=0.2474, pruned_loss=0.03233, over 1414510.51 frames.], batch size: 18, lr: 2.76e-04
+2022-05-15 13:57:45,183 INFO [train.py:812] (1/8) Epoch 28, batch 4300, loss[loss=0.1171, simple_loss=0.1939, pruned_loss=0.02013, over 7135.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2468, pruned_loss=0.03249, over 1417018.61 frames.], batch size: 17, lr: 2.76e-04
+2022-05-15 13:58:44,139 INFO [train.py:812] (1/8) Epoch 28, batch 4350, loss[loss=0.1654, simple_loss=0.2629, pruned_loss=0.03392, over 7216.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2465, pruned_loss=0.03226, over 1417143.96 frames.], batch size: 21, lr: 2.76e-04
+2022-05-15 13:59:42,363 INFO [train.py:812] (1/8) Epoch 28, batch 4400, loss[loss=0.1611, simple_loss=0.2585, pruned_loss=0.03182, over 6415.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2468, pruned_loss=0.03239, over 1408112.89 frames.], batch size: 38, lr: 2.76e-04
+2022-05-15 14:00:51,458 INFO [train.py:812] (1/8) Epoch 28, batch 4450, loss[loss=0.1315, simple_loss=0.2144, pruned_loss=0.02428, over 6803.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2468, pruned_loss=0.03276, over 1402588.47 frames.], batch size: 15, lr: 2.76e-04
+2022-05-15 14:01:50,438 INFO [train.py:812] (1/8) Epoch 28, batch 4500, loss[loss=0.1434, simple_loss=0.2284, pruned_loss=0.0292, over 7212.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2466, pruned_loss=0.03263, over 1389111.29 frames.], batch size: 21, lr: 2.76e-04
+2022-05-15 14:02:49,659 INFO [train.py:812] (1/8) Epoch 28, batch 4550, loss[loss=0.1496, simple_loss=0.2484, pruned_loss=0.02538, over 6429.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2469, pruned_loss=0.03327, over 1359130.36 frames.], batch size: 38, lr: 2.76e-04
+2022-05-15 14:04:01,559 INFO [train.py:812] (1/8) Epoch 29, batch 0, loss[loss=0.1509, simple_loss=0.2379, pruned_loss=0.03194, over 7097.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2379, pruned_loss=0.03194, over 7097.00 frames.], batch size: 28, lr: 2.71e-04
+2022-05-15 14:05:00,858 INFO [train.py:812] (1/8) Epoch 29, batch 50, loss[loss=0.1376, simple_loss=0.2361, pruned_loss=0.01957, over 7305.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2458, pruned_loss=0.03199, over 323128.36 frames.], batch size: 24, lr: 2.71e-04
+2022-05-15 14:05:59,918 INFO [train.py:812] (1/8) Epoch 29, batch 100, loss[loss=0.1502, simple_loss=0.2444, pruned_loss=0.02796, over 7326.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2452, pruned_loss=0.03128, over 569103.39 frames.], batch size: 21, lr: 2.71e-04
+2022-05-15 14:06:58,562 INFO [train.py:812] (1/8) Epoch 29, batch 150, loss[loss=0.153, simple_loss=0.2611, pruned_loss=0.02246, over 7237.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2455, pruned_loss=0.03089, over 759090.60 frames.], batch size: 20, lr: 2.71e-04
+2022-05-15 14:07:56,838 INFO [train.py:812] (1/8) Epoch 29, batch 200, loss[loss=0.1407, simple_loss=0.2339, pruned_loss=0.0238, over 7053.00 frames.], tot_loss[loss=0.1537, simple_loss=0.245, pruned_loss=0.03114, over 908153.02 frames.], batch size: 18, lr: 2.71e-04
+2022-05-15 14:08:56,093 INFO [train.py:812] (1/8) Epoch 29, batch 250, loss[loss=0.1898, simple_loss=0.2732, pruned_loss=0.05323, over 5161.00 frames.], tot_loss[loss=0.153, simple_loss=0.2439, pruned_loss=0.03104, over 1019571.76 frames.], batch size: 52, lr: 2.71e-04
+2022-05-15 14:09:54,911 INFO [train.py:812] (1/8) Epoch 29, batch 300, loss[loss=0.1518, simple_loss=0.2414, pruned_loss=0.03107, over 7166.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2444, pruned_loss=0.03085, over 1109089.55 frames.], batch size: 18, lr: 2.70e-04
+2022-05-15 14:10:53,111 INFO [train.py:812] (1/8) Epoch 29, batch 350, loss[loss=0.1486, simple_loss=0.2365, pruned_loss=0.03037, over 7067.00 frames.], tot_loss[loss=0.1535, simple_loss=0.245, pruned_loss=0.03098, over 1180323.79 frames.], batch size: 18, lr: 2.70e-04
+2022-05-15 14:11:51,411 INFO [train.py:812] (1/8) Epoch 29, batch 400, loss[loss=0.1366, simple_loss=0.2206, pruned_loss=0.02626, over 7147.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2455, pruned_loss=0.03117, over 1236206.06 frames.], batch size: 20, lr: 2.70e-04
+2022-05-15 14:12:49,828 INFO [train.py:812] (1/8) Epoch 29, batch 450, loss[loss=0.1439, simple_loss=0.2436, pruned_loss=0.02212, over 7112.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2455, pruned_loss=0.03115, over 1282007.63 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:13:47,250 INFO [train.py:812] (1/8) Epoch 29, batch 500, loss[loss=0.1872, simple_loss=0.2782, pruned_loss=0.04809, over 5173.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2464, pruned_loss=0.03199, over 1309749.52 frames.], batch size: 52, lr: 2.70e-04
+2022-05-15 14:14:46,080 INFO [train.py:812] (1/8) Epoch 29, batch 550, loss[loss=0.1561, simple_loss=0.2512, pruned_loss=0.03051, over 7212.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2466, pruned_loss=0.03182, over 1331953.60 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:15:44,268 INFO [train.py:812] (1/8) Epoch 29, batch 600, loss[loss=0.1517, simple_loss=0.2428, pruned_loss=0.03031, over 7257.00 frames.], tot_loss[loss=0.155, simple_loss=0.2464, pruned_loss=0.03184, over 1349962.75 frames.], batch size: 19, lr: 2.70e-04
+2022-05-15 14:16:43,605 INFO [train.py:812] (1/8) Epoch 29, batch 650, loss[loss=0.158, simple_loss=0.2502, pruned_loss=0.03284, over 7074.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2465, pruned_loss=0.0321, over 1368301.04 frames.], batch size: 18, lr: 2.70e-04
+2022-05-15 14:17:43,345 INFO [train.py:812] (1/8) Epoch 29, batch 700, loss[loss=0.1814, simple_loss=0.2707, pruned_loss=0.04603, over 5062.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2474, pruned_loss=0.03222, over 1376500.07 frames.], batch size: 54, lr: 2.70e-04
+2022-05-15 14:18:41,555 INFO [train.py:812] (1/8) Epoch 29, batch 750, loss[loss=0.1471, simple_loss=0.2436, pruned_loss=0.02528, over 7430.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2475, pruned_loss=0.03211, over 1382819.44 frames.], batch size: 20, lr: 2.70e-04
+2022-05-15 14:19:40,279 INFO [train.py:812] (1/8) Epoch 29, batch 800, loss[loss=0.1477, simple_loss=0.2509, pruned_loss=0.02228, over 7109.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2484, pruned_loss=0.03246, over 1389344.16 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:20:39,290 INFO [train.py:812] (1/8) Epoch 29, batch 850, loss[loss=0.1609, simple_loss=0.2541, pruned_loss=0.03381, over 6229.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2479, pruned_loss=0.03236, over 1393759.88 frames.], batch size: 37, lr: 2.70e-04
+2022-05-15 14:21:38,039 INFO [train.py:812] (1/8) Epoch 29, batch 900, loss[loss=0.1626, simple_loss=0.2541, pruned_loss=0.0356, over 6820.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2466, pruned_loss=0.03202, over 1400148.96 frames.], batch size: 31, lr: 2.70e-04
+2022-05-15 14:22:37,047 INFO [train.py:812] (1/8) Epoch 29, batch 950, loss[loss=0.1639, simple_loss=0.2492, pruned_loss=0.03933, over 7209.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2465, pruned_loss=0.03206, over 1409157.50 frames.], batch size: 22, lr: 2.70e-04
+2022-05-15 14:23:36,651 INFO [train.py:812] (1/8) Epoch 29, batch 1000, loss[loss=0.1212, simple_loss=0.2066, pruned_loss=0.01793, over 6751.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2449, pruned_loss=0.03132, over 1415132.48 frames.], batch size: 15, lr: 2.70e-04
+2022-05-15 14:24:36,129 INFO [train.py:812] (1/8) Epoch 29, batch 1050, loss[loss=0.1546, simple_loss=0.245, pruned_loss=0.0321, over 7410.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2454, pruned_loss=0.03106, over 1420667.40 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:25:35,351 INFO [train.py:812] (1/8) Epoch 29, batch 1100, loss[loss=0.1625, simple_loss=0.245, pruned_loss=0.04, over 7277.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2452, pruned_loss=0.03099, over 1422849.16 frames.], batch size: 17, lr: 2.70e-04
+2022-05-15 14:26:34,876 INFO [train.py:812] (1/8) Epoch 29, batch 1150, loss[loss=0.1669, simple_loss=0.2545, pruned_loss=0.03965, over 7097.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2452, pruned_loss=0.03093, over 1421879.69 frames.], batch size: 28, lr: 2.70e-04
+2022-05-15 14:27:33,674 INFO [train.py:812] (1/8) Epoch 29, batch 1200, loss[loss=0.1736, simple_loss=0.2623, pruned_loss=0.04251, over 7083.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2461, pruned_loss=0.03136, over 1424013.70 frames.], batch size: 28, lr: 2.70e-04
+2022-05-15 14:28:32,476 INFO [train.py:812] (1/8) Epoch 29, batch 1250, loss[loss=0.1658, simple_loss=0.2617, pruned_loss=0.03496, over 7215.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2458, pruned_loss=0.03144, over 1418997.81 frames.], batch size: 22, lr: 2.70e-04
+2022-05-15 14:29:29,506 INFO [train.py:812] (1/8) Epoch 29, batch 1300, loss[loss=0.1453, simple_loss=0.2436, pruned_loss=0.02352, over 7153.00 frames.], tot_loss[loss=0.154, simple_loss=0.245, pruned_loss=0.03151, over 1420985.90 frames.], batch size: 20, lr: 2.69e-04
+2022-05-15 14:30:28,427 INFO [train.py:812] (1/8) Epoch 29, batch 1350, loss[loss=0.1683, simple_loss=0.2629, pruned_loss=0.03688, over 7118.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2444, pruned_loss=0.03128, over 1425912.40 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:31:27,369 INFO [train.py:812] (1/8) Epoch 29, batch 1400, loss[loss=0.1457, simple_loss=0.2254, pruned_loss=0.03305, over 7275.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2445, pruned_loss=0.03121, over 1427459.23 frames.], batch size: 17, lr: 2.69e-04
+2022-05-15 14:32:26,339 INFO [train.py:812] (1/8) Epoch 29, batch 1450, loss[loss=0.1638, simple_loss=0.2552, pruned_loss=0.03614, over 7293.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2442, pruned_loss=0.03107, over 1431104.57 frames.], batch size: 24, lr: 2.69e-04
+2022-05-15 14:33:24,394 INFO [train.py:812] (1/8) Epoch 29, batch 1500, loss[loss=0.156, simple_loss=0.2435, pruned_loss=0.03423, over 7327.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2448, pruned_loss=0.03123, over 1428378.31 frames.], batch size: 20, lr: 2.69e-04
+2022-05-15 14:34:23,842 INFO [train.py:812] (1/8) Epoch 29, batch 1550, loss[loss=0.1644, simple_loss=0.2591, pruned_loss=0.03491, over 7224.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2444, pruned_loss=0.03096, over 1430128.00 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:35:22,637 INFO [train.py:812] (1/8) Epoch 29, batch 1600, loss[loss=0.1358, simple_loss=0.2182, pruned_loss=0.02669, over 6823.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2448, pruned_loss=0.03112, over 1426410.49 frames.], batch size: 15, lr: 2.69e-04
+2022-05-15 14:36:22,718 INFO [train.py:812] (1/8) Epoch 29, batch 1650, loss[loss=0.1563, simple_loss=0.2377, pruned_loss=0.03741, over 7217.00 frames.], tot_loss[loss=0.1527, simple_loss=0.244, pruned_loss=0.03068, over 1429229.29 frames.], batch size: 16, lr: 2.69e-04
+2022-05-15 14:37:22,111 INFO [train.py:812] (1/8) Epoch 29, batch 1700, loss[loss=0.1266, simple_loss=0.2143, pruned_loss=0.0194, over 7260.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2441, pruned_loss=0.03052, over 1431266.98 frames.], batch size: 19, lr: 2.69e-04
+2022-05-15 14:38:21,734 INFO [train.py:812] (1/8) Epoch 29, batch 1750, loss[loss=0.1342, simple_loss=0.2289, pruned_loss=0.01977, over 7122.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2439, pruned_loss=0.03035, over 1433545.49 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:39:20,858 INFO [train.py:812] (1/8) Epoch 29, batch 1800, loss[loss=0.1588, simple_loss=0.2389, pruned_loss=0.03933, over 7008.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2434, pruned_loss=0.0305, over 1423101.13 frames.], batch size: 16, lr: 2.69e-04
+2022-05-15 14:40:20,287 INFO [train.py:812] (1/8) Epoch 29, batch 1850, loss[loss=0.1391, simple_loss=0.2226, pruned_loss=0.02776, over 7401.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03079, over 1425705.66 frames.], batch size: 18, lr: 2.69e-04
+2022-05-15 14:41:18,732 INFO [train.py:812] (1/8) Epoch 29, batch 1900, loss[loss=0.1416, simple_loss=0.2341, pruned_loss=0.0246, over 7126.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2443, pruned_loss=0.03072, over 1426642.66 frames.], batch size: 26, lr: 2.69e-04
+2022-05-15 14:42:17,745 INFO [train.py:812] (1/8) Epoch 29, batch 1950, loss[loss=0.1644, simple_loss=0.2597, pruned_loss=0.03452, over 7285.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2444, pruned_loss=0.0309, over 1428613.69 frames.], batch size: 25, lr: 2.69e-04
+2022-05-15 14:43:16,653 INFO [train.py:812] (1/8) Epoch 29, batch 2000, loss[loss=0.156, simple_loss=0.255, pruned_loss=0.02855, over 7195.00 frames.], tot_loss[loss=0.153, simple_loss=0.2442, pruned_loss=0.03086, over 1431773.31 frames.], batch size: 23, lr: 2.69e-04
+2022-05-15 14:44:14,142 INFO [train.py:812] (1/8) Epoch 29, batch 2050, loss[loss=0.1375, simple_loss=0.2347, pruned_loss=0.02014, over 7320.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2445, pruned_loss=0.03107, over 1425190.06 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:45:11,932 INFO [train.py:812] (1/8) Epoch 29, batch 2100, loss[loss=0.1756, simple_loss=0.2698, pruned_loss=0.04073, over 7308.00 frames.], tot_loss[loss=0.1529, simple_loss=0.244, pruned_loss=0.03085, over 1426442.95 frames.], batch size: 25, lr: 2.69e-04
+2022-05-15 14:46:11,706 INFO [train.py:812] (1/8) Epoch 29, batch 2150, loss[loss=0.1531, simple_loss=0.2375, pruned_loss=0.03439, over 7215.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2443, pruned_loss=0.0307, over 1428081.04 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:47:09,924 INFO [train.py:812] (1/8) Epoch 29, batch 2200, loss[loss=0.1766, simple_loss=0.2707, pruned_loss=0.04126, over 7330.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2444, pruned_loss=0.03091, over 1422520.14 frames.], batch size: 25, lr: 2.69e-04
+2022-05-15 14:48:08,326 INFO [train.py:812] (1/8) Epoch 29, batch 2250, loss[loss=0.1472, simple_loss=0.243, pruned_loss=0.02565, over 7111.00 frames.], tot_loss[loss=0.153, simple_loss=0.2443, pruned_loss=0.03085, over 1426427.03 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 14:49:05,771 INFO [train.py:812] (1/8) Epoch 29, batch 2300, loss[loss=0.1479, simple_loss=0.2386, pruned_loss=0.02857, over 7291.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2445, pruned_loss=0.03094, over 1427823.71 frames.], batch size: 24, lr: 2.68e-04
+2022-05-15 14:50:03,881 INFO [train.py:812] (1/8) Epoch 29, batch 2350, loss[loss=0.139, simple_loss=0.2321, pruned_loss=0.02297, over 7060.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2448, pruned_loss=0.03105, over 1424854.99 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:51:02,206 INFO [train.py:812] (1/8) Epoch 29, batch 2400, loss[loss=0.1299, simple_loss=0.2096, pruned_loss=0.02509, over 7357.00 frames.], tot_loss[loss=0.153, simple_loss=0.244, pruned_loss=0.03104, over 1426363.79 frames.], batch size: 19, lr: 2.68e-04
+2022-05-15 14:51:59,585 INFO [train.py:812] (1/8) Epoch 29, batch 2450, loss[loss=0.1406, simple_loss=0.2404, pruned_loss=0.0204, over 7120.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2456, pruned_loss=0.03195, over 1416885.54 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 14:52:57,617 INFO [train.py:812] (1/8) Epoch 29, batch 2500, loss[loss=0.1378, simple_loss=0.214, pruned_loss=0.03083, over 7417.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2452, pruned_loss=0.0318, over 1420389.95 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:53:56,708 INFO [train.py:812] (1/8) Epoch 29, batch 2550, loss[loss=0.1581, simple_loss=0.2438, pruned_loss=0.03623, over 7150.00 frames.], tot_loss[loss=0.154, simple_loss=0.245, pruned_loss=0.03155, over 1418183.57 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:54:55,317 INFO [train.py:812] (1/8) Epoch 29, batch 2600, loss[loss=0.1632, simple_loss=0.261, pruned_loss=0.03265, over 7205.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2448, pruned_loss=0.03155, over 1416596.72 frames.], batch size: 23, lr: 2.68e-04
+2022-05-15 14:56:04,287 INFO [train.py:812] (1/8) Epoch 29, batch 2650, loss[loss=0.134, simple_loss=0.2157, pruned_loss=0.02614, over 7430.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2449, pruned_loss=0.03136, over 1419547.99 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:57:02,552 INFO [train.py:812] (1/8) Epoch 29, batch 2700, loss[loss=0.1767, simple_loss=0.2576, pruned_loss=0.04789, over 5213.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2441, pruned_loss=0.03148, over 1419860.14 frames.], batch size: 53, lr: 2.68e-04
+2022-05-15 14:58:00,032 INFO [train.py:812] (1/8) Epoch 29, batch 2750, loss[loss=0.1469, simple_loss=0.2438, pruned_loss=0.02503, over 7316.00 frames.], tot_loss[loss=0.1543, simple_loss=0.245, pruned_loss=0.03174, over 1415550.16 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 14:59:07,972 INFO [train.py:812] (1/8) Epoch 29, batch 2800, loss[loss=0.158, simple_loss=0.2544, pruned_loss=0.03082, over 7330.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2457, pruned_loss=0.03159, over 1417638.65 frames.], batch size: 22, lr: 2.68e-04
+2022-05-15 15:00:06,410 INFO [train.py:812] (1/8) Epoch 29, batch 2850, loss[loss=0.1317, simple_loss=0.2245, pruned_loss=0.01947, over 7255.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2447, pruned_loss=0.03122, over 1417944.88 frames.], batch size: 19, lr: 2.68e-04
+2022-05-15 15:01:14,250 INFO [train.py:812] (1/8) Epoch 29, batch 2900, loss[loss=0.1505, simple_loss=0.2371, pruned_loss=0.03192, over 7278.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2448, pruned_loss=0.03099, over 1417151.13 frames.], batch size: 17, lr: 2.68e-04
+2022-05-15 15:02:42,659 INFO [train.py:812] (1/8) Epoch 29, batch 2950, loss[loss=0.1217, simple_loss=0.2029, pruned_loss=0.0203, over 7128.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2441, pruned_loss=0.0309, over 1417050.88 frames.], batch size: 17, lr: 2.68e-04
+2022-05-15 15:03:40,342 INFO [train.py:812] (1/8) Epoch 29, batch 3000, loss[loss=0.1479, simple_loss=0.2349, pruned_loss=0.03039, over 7235.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2448, pruned_loss=0.03112, over 1418390.75 frames.], batch size: 20, lr: 2.68e-04
+2022-05-15 15:03:40,343 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 15:03:47,851 INFO [train.py:841] (1/8) Epoch 29, validation: loss=0.153, simple_loss=0.2498, pruned_loss=0.02809, over 698248.00 frames.
+2022-05-15 15:04:46,862 INFO [train.py:812] (1/8) Epoch 29, batch 3050, loss[loss=0.1461, simple_loss=0.2363, pruned_loss=0.02796, over 7149.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.03071, over 1421485.08 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 15:05:54,527 INFO [train.py:812] (1/8) Epoch 29, batch 3100, loss[loss=0.1365, simple_loss=0.2148, pruned_loss=0.02908, over 7266.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2433, pruned_loss=0.03046, over 1418735.00 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 15:06:53,595 INFO [train.py:812] (1/8) Epoch 29, batch 3150, loss[loss=0.1969, simple_loss=0.2958, pruned_loss=0.04898, over 7216.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2452, pruned_loss=0.03101, over 1422629.12 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 15:07:52,383 INFO [train.py:812] (1/8) Epoch 29, batch 3200, loss[loss=0.149, simple_loss=0.257, pruned_loss=0.02052, over 7111.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2455, pruned_loss=0.031, over 1422507.45 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 15:08:52,059 INFO [train.py:812] (1/8) Epoch 29, batch 3250, loss[loss=0.1128, simple_loss=0.199, pruned_loss=0.01334, over 7159.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2444, pruned_loss=0.03054, over 1421393.16 frames.], batch size: 16, lr: 2.67e-04
+2022-05-15 15:09:50,374 INFO [train.py:812] (1/8) Epoch 29, batch 3300, loss[loss=0.1533, simple_loss=0.2471, pruned_loss=0.0298, over 7220.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2461, pruned_loss=0.03135, over 1421106.99 frames.], batch size: 21, lr: 2.67e-04
+2022-05-15 15:10:48,351 INFO [train.py:812] (1/8) Epoch 29, batch 3350, loss[loss=0.1728, simple_loss=0.2739, pruned_loss=0.03584, over 7098.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03137, over 1418547.94 frames.], batch size: 28, lr: 2.67e-04
+2022-05-15 15:11:47,206 INFO [train.py:812] (1/8) Epoch 29, batch 3400, loss[loss=0.1458, simple_loss=0.2283, pruned_loss=0.03164, over 7062.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2456, pruned_loss=0.03139, over 1417253.81 frames.], batch size: 18, lr: 2.67e-04
+2022-05-15 15:12:46,918 INFO [train.py:812] (1/8) Epoch 29, batch 3450, loss[loss=0.1229, simple_loss=0.2099, pruned_loss=0.01801, over 7269.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2457, pruned_loss=0.03143, over 1419952.85 frames.], batch size: 17, lr: 2.67e-04
+2022-05-15 15:13:45,907 INFO [train.py:812] (1/8) Epoch 29, batch 3500, loss[loss=0.1575, simple_loss=0.2536, pruned_loss=0.03072, over 6701.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2453, pruned_loss=0.03097, over 1419181.11 frames.], batch size: 31, lr: 2.67e-04
+2022-05-15 15:14:51,715 INFO [train.py:812] (1/8) Epoch 29, batch 3550, loss[loss=0.149, simple_loss=0.2437, pruned_loss=0.02717, over 7291.00 frames.], tot_loss[loss=0.153, simple_loss=0.2445, pruned_loss=0.0307, over 1422802.56 frames.], batch size: 18, lr: 2.67e-04
+2022-05-15 15:15:51,046 INFO [train.py:812] (1/8) Epoch 29, batch 3600, loss[loss=0.1644, simple_loss=0.2372, pruned_loss=0.04581, over 7266.00 frames.], tot_loss[loss=0.1534, simple_loss=0.245, pruned_loss=0.03089, over 1423180.84 frames.], batch size: 16, lr: 2.67e-04
+2022-05-15 15:16:50,747 INFO [train.py:812] (1/8) Epoch 29, batch 3650, loss[loss=0.136, simple_loss=0.239, pruned_loss=0.01657, over 7343.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2447, pruned_loss=0.03101, over 1426241.34 frames.], batch size: 22, lr: 2.67e-04
+2022-05-15 15:17:49,900 INFO [train.py:812] (1/8) Epoch 29, batch 3700, loss[loss=0.1687, simple_loss=0.2683, pruned_loss=0.03455, over 7207.00 frames.], tot_loss[loss=0.1527, simple_loss=0.244, pruned_loss=0.03067, over 1426300.22 frames.], batch size: 23, lr: 2.67e-04
+2022-05-15 15:18:49,042 INFO [train.py:812] (1/8) Epoch 29, batch 3750, loss[loss=0.2043, simple_loss=0.2922, pruned_loss=0.0582, over 5320.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2444, pruned_loss=0.03102, over 1426208.75 frames.], batch size: 52, lr: 2.67e-04
+2022-05-15 15:19:48,067 INFO [train.py:812] (1/8) Epoch 29, batch 3800, loss[loss=0.1394, simple_loss=0.2302, pruned_loss=0.0243, over 7433.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2451, pruned_loss=0.03101, over 1426362.77 frames.], batch size: 20, lr: 2.67e-04
+2022-05-15 15:20:46,937 INFO [train.py:812] (1/8) Epoch 29, batch 3850, loss[loss=0.1588, simple_loss=0.245, pruned_loss=0.03633, over 7394.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2452, pruned_loss=0.03072, over 1427260.45 frames.], batch size: 23, lr: 2.67e-04
+2022-05-15 15:21:44,966 INFO [train.py:812] (1/8) Epoch 29, batch 3900, loss[loss=0.1467, simple_loss=0.2359, pruned_loss=0.0288, over 7266.00 frames.], tot_loss[loss=0.1541, simple_loss=0.246, pruned_loss=0.0311, over 1430300.68 frames.], batch size: 24, lr: 2.67e-04
+2022-05-15 15:22:44,171 INFO [train.py:812] (1/8) Epoch 29, batch 3950, loss[loss=0.1263, simple_loss=0.2122, pruned_loss=0.02022, over 7418.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2468, pruned_loss=0.03116, over 1431066.89 frames.], batch size: 18, lr: 2.67e-04
+2022-05-15 15:23:43,017 INFO [train.py:812] (1/8) Epoch 29, batch 4000, loss[loss=0.1443, simple_loss=0.243, pruned_loss=0.02277, over 7336.00 frames.], tot_loss[loss=0.154, simple_loss=0.2462, pruned_loss=0.03084, over 1430758.01 frames.], batch size: 22, lr: 2.67e-04
+2022-05-15 15:24:42,293 INFO [train.py:812] (1/8) Epoch 29, batch 4050, loss[loss=0.1351, simple_loss=0.2209, pruned_loss=0.02461, over 7287.00 frames.], tot_loss[loss=0.1547, simple_loss=0.247, pruned_loss=0.03117, over 1429494.53 frames.], batch size: 17, lr: 2.67e-04
+2022-05-15 15:25:40,980 INFO [train.py:812] (1/8) Epoch 29, batch 4100, loss[loss=0.1514, simple_loss=0.25, pruned_loss=0.02641, over 7329.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2471, pruned_loss=0.03105, over 1429813.18 frames.], batch size: 22, lr: 2.67e-04
+2022-05-15 15:26:40,398 INFO [train.py:812] (1/8) Epoch 29, batch 4150, loss[loss=0.1467, simple_loss=0.2414, pruned_loss=0.02602, over 7322.00 frames.], tot_loss[loss=0.154, simple_loss=0.2465, pruned_loss=0.03077, over 1424111.74 frames.], batch size: 21, lr: 2.67e-04
+2022-05-15 15:27:39,253 INFO [train.py:812] (1/8) Epoch 29, batch 4200, loss[loss=0.1516, simple_loss=0.2388, pruned_loss=0.03218, over 7263.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2467, pruned_loss=0.03092, over 1421082.41 frames.], batch size: 19, lr: 2.66e-04
+2022-05-15 15:28:38,676 INFO [train.py:812] (1/8) Epoch 29, batch 4250, loss[loss=0.1522, simple_loss=0.2484, pruned_loss=0.02798, over 6924.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2462, pruned_loss=0.03114, over 1420930.96 frames.], batch size: 32, lr: 2.66e-04
+2022-05-15 15:29:36,730 INFO [train.py:812] (1/8) Epoch 29, batch 4300, loss[loss=0.1365, simple_loss=0.2281, pruned_loss=0.02246, over 7157.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2452, pruned_loss=0.03049, over 1417651.02 frames.], batch size: 18, lr: 2.66e-04
+2022-05-15 15:30:35,686 INFO [train.py:812] (1/8) Epoch 29, batch 4350, loss[loss=0.1478, simple_loss=0.2468, pruned_loss=0.02441, over 7319.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2452, pruned_loss=0.03072, over 1419843.42 frames.], batch size: 21, lr: 2.66e-04
+2022-05-15 15:31:34,531 INFO [train.py:812] (1/8) Epoch 29, batch 4400, loss[loss=0.1902, simple_loss=0.286, pruned_loss=0.04717, over 7304.00 frames.], tot_loss[loss=0.154, simple_loss=0.2462, pruned_loss=0.03091, over 1410734.13 frames.], batch size: 24, lr: 2.66e-04
+2022-05-15 15:32:33,466 INFO [train.py:812] (1/8) Epoch 29, batch 4450, loss[loss=0.1486, simple_loss=0.2461, pruned_loss=0.02553, over 6437.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2464, pruned_loss=0.03107, over 1403025.36 frames.], batch size: 37, lr: 2.66e-04
+2022-05-15 15:33:31,921 INFO [train.py:812] (1/8) Epoch 29, batch 4500, loss[loss=0.1692, simple_loss=0.2745, pruned_loss=0.03194, over 7210.00 frames.], tot_loss[loss=0.1549, simple_loss=0.247, pruned_loss=0.03142, over 1379457.62 frames.], batch size: 22, lr: 2.66e-04
+2022-05-15 15:34:29,703 INFO [train.py:812] (1/8) Epoch 29, batch 4550, loss[loss=0.1677, simple_loss=0.2552, pruned_loss=0.0401, over 5046.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2483, pruned_loss=0.03236, over 1360669.63 frames.], batch size: 52, lr: 2.66e-04
+2022-05-15 15:35:40,750 INFO [train.py:812] (1/8) Epoch 30, batch 0, loss[loss=0.1398, simple_loss=0.2336, pruned_loss=0.02299, over 7333.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2336, pruned_loss=0.02299, over 7333.00 frames.], batch size: 20, lr: 2.62e-04
+2022-05-15 15:36:39,957 INFO [train.py:812] (1/8) Epoch 30, batch 50, loss[loss=0.1206, simple_loss=0.202, pruned_loss=0.01961, over 7278.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2431, pruned_loss=0.02929, over 324637.79 frames.], batch size: 18, lr: 2.62e-04
+2022-05-15 15:37:39,032 INFO [train.py:812] (1/8) Epoch 30, batch 100, loss[loss=0.1461, simple_loss=0.2301, pruned_loss=0.03107, over 7288.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03052, over 572540.59 frames.], batch size: 17, lr: 2.62e-04
+2022-05-15 15:38:38,755 INFO [train.py:812] (1/8) Epoch 30, batch 150, loss[loss=0.165, simple_loss=0.2592, pruned_loss=0.03537, over 7306.00 frames.], tot_loss[loss=0.153, simple_loss=0.2445, pruned_loss=0.03076, over 750515.45 frames.], batch size: 24, lr: 2.62e-04
+2022-05-15 15:39:36,194 INFO [train.py:812] (1/8) Epoch 30, batch 200, loss[loss=0.1367, simple_loss=0.2245, pruned_loss=0.02452, over 7343.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03139, over 899539.14 frames.], batch size: 19, lr: 2.61e-04
+2022-05-15 15:40:35,800 INFO [train.py:812] (1/8) Epoch 30, batch 250, loss[loss=0.1194, simple_loss=0.2052, pruned_loss=0.01676, over 7181.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2463, pruned_loss=0.03132, over 1017130.69 frames.], batch size: 16, lr: 2.61e-04
+2022-05-15 15:41:34,908 INFO [train.py:812] (1/8) Epoch 30, batch 300, loss[loss=0.1403, simple_loss=0.2208, pruned_loss=0.02985, over 7275.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2467, pruned_loss=0.03157, over 1109637.28 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:42:33,927 INFO [train.py:812] (1/8) Epoch 30, batch 350, loss[loss=0.1557, simple_loss=0.2542, pruned_loss=0.02857, over 7325.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03134, over 1182828.87 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:43:32,154 INFO [train.py:812] (1/8) Epoch 30, batch 400, loss[loss=0.151, simple_loss=0.2502, pruned_loss=0.02587, over 7329.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2452, pruned_loss=0.03055, over 1238213.15 frames.], batch size: 24, lr: 2.61e-04
+2022-05-15 15:44:30,920 INFO [train.py:812] (1/8) Epoch 30, batch 450, loss[loss=0.161, simple_loss=0.2553, pruned_loss=0.03341, over 7420.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2443, pruned_loss=0.03042, over 1280220.49 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:45:28,628 INFO [train.py:812] (1/8) Epoch 30, batch 500, loss[loss=0.1293, simple_loss=0.2186, pruned_loss=0.02003, over 7314.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2443, pruned_loss=0.0306, over 1308691.77 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:46:27,332 INFO [train.py:812] (1/8) Epoch 30, batch 550, loss[loss=0.171, simple_loss=0.2638, pruned_loss=0.03907, over 7274.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2449, pruned_loss=0.03098, over 1335819.62 frames.], batch size: 24, lr: 2.61e-04
+2022-05-15 15:47:24,856 INFO [train.py:812] (1/8) Epoch 30, batch 600, loss[loss=0.173, simple_loss=0.2656, pruned_loss=0.04015, over 7210.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2445, pruned_loss=0.03092, over 1351331.62 frames.], batch size: 22, lr: 2.61e-04
+2022-05-15 15:48:22,460 INFO [train.py:812] (1/8) Epoch 30, batch 650, loss[loss=0.1472, simple_loss=0.2376, pruned_loss=0.02841, over 7075.00 frames.], tot_loss[loss=0.1535, simple_loss=0.245, pruned_loss=0.03095, over 1366191.58 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:49:20,309 INFO [train.py:812] (1/8) Epoch 30, batch 700, loss[loss=0.1494, simple_loss=0.2416, pruned_loss=0.02861, over 7329.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2458, pruned_loss=0.03124, over 1374821.61 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:50:18,870 INFO [train.py:812] (1/8) Epoch 30, batch 750, loss[loss=0.1497, simple_loss=0.2404, pruned_loss=0.02946, over 7233.00 frames.], tot_loss[loss=0.1544, simple_loss=0.246, pruned_loss=0.03137, over 1380879.40 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:51:17,429 INFO [train.py:812] (1/8) Epoch 30, batch 800, loss[loss=0.1365, simple_loss=0.2316, pruned_loss=0.0207, over 7344.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2449, pruned_loss=0.03118, over 1387437.15 frames.], batch size: 22, lr: 2.61e-04
+2022-05-15 15:52:16,551 INFO [train.py:812] (1/8) Epoch 30, batch 850, loss[loss=0.131, simple_loss=0.2189, pruned_loss=0.02158, over 7061.00 frames.], tot_loss[loss=0.1528, simple_loss=0.244, pruned_loss=0.0308, over 1397014.98 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:53:14,183 INFO [train.py:812] (1/8) Epoch 30, batch 900, loss[loss=0.1489, simple_loss=0.2388, pruned_loss=0.02951, over 7217.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2437, pruned_loss=0.03073, over 1401394.36 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:54:13,183 INFO [train.py:812] (1/8) Epoch 30, batch 950, loss[loss=0.141, simple_loss=0.234, pruned_loss=0.02405, over 7114.00 frames.], tot_loss[loss=0.153, simple_loss=0.2444, pruned_loss=0.0308, over 1407104.14 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:55:11,579 INFO [train.py:812] (1/8) Epoch 30, batch 1000, loss[loss=0.1784, simple_loss=0.2759, pruned_loss=0.04046, over 7141.00 frames.], tot_loss[loss=0.154, simple_loss=0.2461, pruned_loss=0.03101, over 1410816.24 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:56:10,066 INFO [train.py:812] (1/8) Epoch 30, batch 1050, loss[loss=0.1237, simple_loss=0.2135, pruned_loss=0.01691, over 7282.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2462, pruned_loss=0.03122, over 1407790.48 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:57:08,268 INFO [train.py:812] (1/8) Epoch 30, batch 1100, loss[loss=0.1384, simple_loss=0.2363, pruned_loss=0.02031, over 7327.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2473, pruned_loss=0.03153, over 1417178.21 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:58:07,689 INFO [train.py:812] (1/8) Epoch 30, batch 1150, loss[loss=0.1337, simple_loss=0.2168, pruned_loss=0.02525, over 6998.00 frames.], tot_loss[loss=0.1548, simple_loss=0.247, pruned_loss=0.03133, over 1418764.32 frames.], batch size: 16, lr: 2.61e-04
+2022-05-15 15:59:06,107 INFO [train.py:812] (1/8) Epoch 30, batch 1200, loss[loss=0.1362, simple_loss=0.2271, pruned_loss=0.02264, over 7167.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2471, pruned_loss=0.03129, over 1422995.64 frames.], batch size: 19, lr: 2.61e-04
+2022-05-15 16:00:14,954 INFO [train.py:812] (1/8) Epoch 30, batch 1250, loss[loss=0.1654, simple_loss=0.2612, pruned_loss=0.03477, over 5198.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2462, pruned_loss=0.03111, over 1418446.49 frames.], batch size: 52, lr: 2.60e-04
+2022-05-15 16:01:13,727 INFO [train.py:812] (1/8) Epoch 30, batch 1300, loss[loss=0.1501, simple_loss=0.2488, pruned_loss=0.02573, over 7332.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2457, pruned_loss=0.03092, over 1419916.83 frames.], batch size: 22, lr: 2.60e-04
+2022-05-15 16:02:13,354 INFO [train.py:812] (1/8) Epoch 30, batch 1350, loss[loss=0.1567, simple_loss=0.2498, pruned_loss=0.03181, over 6290.00 frames.], tot_loss[loss=0.154, simple_loss=0.2456, pruned_loss=0.03126, over 1420050.25 frames.], batch size: 37, lr: 2.60e-04
+2022-05-15 16:03:12,431 INFO [train.py:812] (1/8) Epoch 30, batch 1400, loss[loss=0.1296, simple_loss=0.2117, pruned_loss=0.02376, over 7219.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2449, pruned_loss=0.03123, over 1420579.19 frames.], batch size: 16, lr: 2.60e-04
+2022-05-15 16:04:10,792 INFO [train.py:812] (1/8) Epoch 30, batch 1450, loss[loss=0.1434, simple_loss=0.2433, pruned_loss=0.02179, over 7122.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2452, pruned_loss=0.03121, over 1419183.59 frames.], batch size: 21, lr: 2.60e-04
+2022-05-15 16:05:09,033 INFO [train.py:812] (1/8) Epoch 30, batch 1500, loss[loss=0.1552, simple_loss=0.2426, pruned_loss=0.03387, over 7264.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2453, pruned_loss=0.03122, over 1418608.82 frames.], batch size: 19, lr: 2.60e-04
+2022-05-15 16:06:06,396 INFO [train.py:812] (1/8) Epoch 30, batch 1550, loss[loss=0.1759, simple_loss=0.261, pruned_loss=0.04538, over 7212.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2454, pruned_loss=0.03116, over 1418705.05 frames.], batch size: 23, lr: 2.60e-04
+2022-05-15 16:07:03,131 INFO [train.py:812] (1/8) Epoch 30, batch 1600, loss[loss=0.1465, simple_loss=0.2439, pruned_loss=0.02455, over 7320.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2458, pruned_loss=0.03132, over 1419336.44 frames.], batch size: 21, lr: 2.60e-04
+2022-05-15 16:08:02,735 INFO [train.py:812] (1/8) Epoch 30, batch 1650, loss[loss=0.155, simple_loss=0.2554, pruned_loss=0.0273, over 7172.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2448, pruned_loss=0.03071, over 1423362.88 frames.], batch size: 26, lr: 2.60e-04
+2022-05-15 16:09:00,133 INFO [train.py:812] (1/8) Epoch 30, batch 1700, loss[loss=0.1824, simple_loss=0.268, pruned_loss=0.04837, over 7125.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2451, pruned_loss=0.0308, over 1426148.48 frames.], batch size: 17, lr: 2.60e-04
+2022-05-15 16:09:58,742 INFO [train.py:812] (1/8) Epoch 30, batch 1750, loss[loss=0.14, simple_loss=0.2334, pruned_loss=0.02334, over 7154.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2452, pruned_loss=0.0311, over 1421942.16 frames.], batch size: 20, lr: 2.60e-04
+2022-05-15 16:10:56,861 INFO [train.py:812] (1/8) Epoch 30, batch 1800, loss[loss=0.1871, simple_loss=0.2867, pruned_loss=0.04373, over 5053.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2454, pruned_loss=0.0311, over 1419587.83 frames.], batch size: 52, lr: 2.60e-04
+2022-05-15 16:11:55,154 INFO [train.py:812] (1/8) Epoch 30, batch 1850, loss[loss=0.1783, simple_loss=0.2678, pruned_loss=0.04445, over 7116.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2448, pruned_loss=0.03121, over 1423591.29 frames.], batch size: 21, lr: 2.60e-04
+2022-05-15 16:12:53,278 INFO [train.py:812] (1/8) Epoch 30, batch 1900, loss[loss=0.1248, simple_loss=0.2073, pruned_loss=0.02115, over 7223.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2448, pruned_loss=0.03104, over 1426337.16 frames.], batch size: 16, lr: 2.60e-04
+2022-05-15 16:13:52,787 INFO [train.py:812] (1/8) Epoch 30, batch 1950, loss[loss=0.1327, simple_loss=0.2252, pruned_loss=0.02008, over 7270.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2449, pruned_loss=0.03094, over 1427474.98 frames.], batch size: 17, lr: 2.60e-04
+2022-05-15 16:14:51,455 INFO [train.py:812] (1/8) Epoch 30, batch 2000, loss[loss=0.159, simple_loss=0.2515, pruned_loss=0.03327, over 7329.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2453, pruned_loss=0.03094, over 1429041.00 frames.], batch size: 22, lr: 2.60e-04
+2022-05-15 16:15:50,920 INFO [train.py:812] (1/8) Epoch 30, batch 2050, loss[loss=0.2116, simple_loss=0.3011, pruned_loss=0.06105, over 7197.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2454, pruned_loss=0.03111, over 1429340.66 frames.], batch size: 23, lr: 2.60e-04
+2022-05-15 16:16:49,864 INFO [train.py:812] (1/8) Epoch 30, batch 2100, loss[loss=0.1585, simple_loss=0.2501, pruned_loss=0.03344, over 7147.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2463, pruned_loss=0.03144, over 1428322.25 frames.], batch size: 20, lr: 2.60e-04
+2022-05-15 16:17:48,125 INFO [train.py:812] (1/8) Epoch 30, batch 2150, loss[loss=0.1363, simple_loss=0.2163, pruned_loss=0.02818, over 7126.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2457, pruned_loss=0.03106, over 1427500.59 frames.], batch size: 17, lr: 2.60e-04
+2022-05-15 16:18:47,071 INFO [train.py:812] (1/8) Epoch 30, batch 2200, loss[loss=0.1789, simple_loss=0.2743, pruned_loss=0.04177, over 7282.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2454, pruned_loss=0.03119, over 1421884.39 frames.], batch size: 24, lr: 2.60e-04
+2022-05-15 16:19:45,891 INFO [train.py:812] (1/8) Epoch 30, batch 2250, loss[loss=0.1972, simple_loss=0.2768, pruned_loss=0.05877, over 7165.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03139, over 1421536.67 frames.], batch size: 26, lr: 2.59e-04
+2022-05-15 16:20:43,570 INFO [train.py:812] (1/8) Epoch 30, batch 2300, loss[loss=0.1529, simple_loss=0.2511, pruned_loss=0.02732, over 7331.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03129, over 1418475.20 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:21:42,619 INFO [train.py:812] (1/8) Epoch 30, batch 2350, loss[loss=0.1607, simple_loss=0.2533, pruned_loss=0.034, over 7332.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2454, pruned_loss=0.03107, over 1420380.68 frames.], batch size: 22, lr: 2.59e-04
+2022-05-15 16:22:41,693 INFO [train.py:812] (1/8) Epoch 30, batch 2400, loss[loss=0.1723, simple_loss=0.2737, pruned_loss=0.03544, over 7294.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2459, pruned_loss=0.03117, over 1422546.72 frames.], batch size: 25, lr: 2.59e-04
+2022-05-15 16:23:41,325 INFO [train.py:812] (1/8) Epoch 30, batch 2450, loss[loss=0.1508, simple_loss=0.2531, pruned_loss=0.02423, over 7132.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2441, pruned_loss=0.03027, over 1426514.28 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:24:39,673 INFO [train.py:812] (1/8) Epoch 30, batch 2500, loss[loss=0.1443, simple_loss=0.2216, pruned_loss=0.03346, over 7213.00 frames.], tot_loss[loss=0.1522, simple_loss=0.244, pruned_loss=0.03019, over 1430909.53 frames.], batch size: 16, lr: 2.59e-04
+2022-05-15 16:25:38,958 INFO [train.py:812] (1/8) Epoch 30, batch 2550, loss[loss=0.1409, simple_loss=0.2234, pruned_loss=0.02922, over 7402.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03051, over 1428238.59 frames.], batch size: 18, lr: 2.59e-04
+2022-05-15 16:26:37,713 INFO [train.py:812] (1/8) Epoch 30, batch 2600, loss[loss=0.1543, simple_loss=0.2564, pruned_loss=0.02609, over 7119.00 frames.], tot_loss[loss=0.1524, simple_loss=0.244, pruned_loss=0.03038, over 1427659.12 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:27:37,200 INFO [train.py:812] (1/8) Epoch 30, batch 2650, loss[loss=0.1402, simple_loss=0.2246, pruned_loss=0.02788, over 7146.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2433, pruned_loss=0.03004, over 1430281.61 frames.], batch size: 17, lr: 2.59e-04
+2022-05-15 16:28:36,167 INFO [train.py:812] (1/8) Epoch 30, batch 2700, loss[loss=0.1672, simple_loss=0.2648, pruned_loss=0.03479, over 7113.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2445, pruned_loss=0.03048, over 1430070.98 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:29:34,402 INFO [train.py:812] (1/8) Epoch 30, batch 2750, loss[loss=0.1525, simple_loss=0.2423, pruned_loss=0.03139, over 7239.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2451, pruned_loss=0.03066, over 1425852.17 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:30:32,046 INFO [train.py:812] (1/8) Epoch 30, batch 2800, loss[loss=0.156, simple_loss=0.2602, pruned_loss=0.02588, over 7336.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2456, pruned_loss=0.03073, over 1424074.49 frames.], batch size: 22, lr: 2.59e-04
+2022-05-15 16:31:31,631 INFO [train.py:812] (1/8) Epoch 30, batch 2850, loss[loss=0.1563, simple_loss=0.251, pruned_loss=0.03078, over 7234.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2453, pruned_loss=0.03101, over 1418132.84 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:32:29,831 INFO [train.py:812] (1/8) Epoch 30, batch 2900, loss[loss=0.126, simple_loss=0.2104, pruned_loss=0.0208, over 7006.00 frames.], tot_loss[loss=0.153, simple_loss=0.2445, pruned_loss=0.0307, over 1421917.38 frames.], batch size: 16, lr: 2.59e-04
+2022-05-15 16:33:36,391 INFO [train.py:812] (1/8) Epoch 30, batch 2950, loss[loss=0.1457, simple_loss=0.2405, pruned_loss=0.02546, over 6542.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2441, pruned_loss=0.03075, over 1422864.07 frames.], batch size: 38, lr: 2.59e-04
+2022-05-15 16:34:35,491 INFO [train.py:812] (1/8) Epoch 30, batch 3000, loss[loss=0.1481, simple_loss=0.2482, pruned_loss=0.02394, over 7131.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2445, pruned_loss=0.03083, over 1425667.40 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:34:35,492 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 16:34:43,057 INFO [train.py:841] (1/8) Epoch 30, validation: loss=0.1528, simple_loss=0.2494, pruned_loss=0.02809, over 698248.00 frames.
+2022-05-15 16:35:41,820 INFO [train.py:812] (1/8) Epoch 30, batch 3050, loss[loss=0.1638, simple_loss=0.2579, pruned_loss=0.03482, over 7115.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2442, pruned_loss=0.03036, over 1427021.83 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:36:40,855 INFO [train.py:812] (1/8) Epoch 30, batch 3100, loss[loss=0.1477, simple_loss=0.2545, pruned_loss=0.02039, over 7424.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2444, pruned_loss=0.03037, over 1427190.60 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:37:40,503 INFO [train.py:812] (1/8) Epoch 30, batch 3150, loss[loss=0.1491, simple_loss=0.2475, pruned_loss=0.02533, over 7158.00 frames.], tot_loss[loss=0.152, simple_loss=0.2434, pruned_loss=0.03033, over 1422844.88 frames.], batch size: 18, lr: 2.59e-04
+2022-05-15 16:38:39,689 INFO [train.py:812] (1/8) Epoch 30, batch 3200, loss[loss=0.1368, simple_loss=0.2201, pruned_loss=0.02674, over 7260.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2428, pruned_loss=0.03017, over 1425780.57 frames.], batch size: 19, lr: 2.59e-04
+2022-05-15 16:39:38,880 INFO [train.py:812] (1/8) Epoch 30, batch 3250, loss[loss=0.1251, simple_loss=0.223, pruned_loss=0.01363, over 7097.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2431, pruned_loss=0.03048, over 1420743.12 frames.], batch size: 28, lr: 2.59e-04
+2022-05-15 16:40:36,553 INFO [train.py:812] (1/8) Epoch 30, batch 3300, loss[loss=0.1686, simple_loss=0.2592, pruned_loss=0.03896, over 7338.00 frames.], tot_loss[loss=0.1526, simple_loss=0.244, pruned_loss=0.0306, over 1424184.33 frames.], batch size: 20, lr: 2.58e-04
+2022-05-15 16:41:35,380 INFO [train.py:812] (1/8) Epoch 30, batch 3350, loss[loss=0.134, simple_loss=0.215, pruned_loss=0.02651, over 7304.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2433, pruned_loss=0.03052, over 1428482.12 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 16:42:33,354 INFO [train.py:812] (1/8) Epoch 30, batch 3400, loss[loss=0.2027, simple_loss=0.2939, pruned_loss=0.05571, over 4827.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2433, pruned_loss=0.03056, over 1424397.80 frames.], batch size: 52, lr: 2.58e-04
+2022-05-15 16:43:31,883 INFO [train.py:812] (1/8) Epoch 30, batch 3450, loss[loss=0.1525, simple_loss=0.2505, pruned_loss=0.02724, over 7327.00 frames.], tot_loss[loss=0.1527, simple_loss=0.244, pruned_loss=0.03064, over 1421348.85 frames.], batch size: 24, lr: 2.58e-04
+2022-05-15 16:44:30,364 INFO [train.py:812] (1/8) Epoch 30, batch 3500, loss[loss=0.1899, simple_loss=0.2861, pruned_loss=0.04688, over 7209.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2454, pruned_loss=0.03157, over 1423069.36 frames.], batch size: 26, lr: 2.58e-04
+2022-05-15 16:45:29,366 INFO [train.py:812] (1/8) Epoch 30, batch 3550, loss[loss=0.1496, simple_loss=0.2429, pruned_loss=0.0281, over 7166.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2448, pruned_loss=0.03132, over 1423014.52 frames.], batch size: 18, lr: 2.58e-04
+2022-05-15 16:46:28,177 INFO [train.py:812] (1/8) Epoch 30, batch 3600, loss[loss=0.1529, simple_loss=0.2409, pruned_loss=0.03248, over 7246.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2451, pruned_loss=0.03132, over 1427616.25 frames.], batch size: 19, lr: 2.58e-04
+2022-05-15 16:47:27,379 INFO [train.py:812] (1/8) Epoch 30, batch 3650, loss[loss=0.1538, simple_loss=0.2506, pruned_loss=0.02845, over 6857.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2447, pruned_loss=0.03116, over 1429764.74 frames.], batch size: 31, lr: 2.58e-04
+2022-05-15 16:48:25,013 INFO [train.py:812] (1/8) Epoch 30, batch 3700, loss[loss=0.1559, simple_loss=0.2373, pruned_loss=0.03726, over 7259.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2453, pruned_loss=0.03152, over 1429983.36 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 16:49:23,811 INFO [train.py:812] (1/8) Epoch 30, batch 3750, loss[loss=0.1631, simple_loss=0.2642, pruned_loss=0.031, over 7103.00 frames.], tot_loss[loss=0.1534, simple_loss=0.245, pruned_loss=0.03091, over 1433241.30 frames.], batch size: 28, lr: 2.58e-04
+2022-05-15 16:50:21,241 INFO [train.py:812] (1/8) Epoch 30, batch 3800, loss[loss=0.1831, simple_loss=0.2844, pruned_loss=0.04089, over 7202.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2468, pruned_loss=0.03152, over 1424417.48 frames.], batch size: 22, lr: 2.58e-04
+2022-05-15 16:51:18,883 INFO [train.py:812] (1/8) Epoch 30, batch 3850, loss[loss=0.1379, simple_loss=0.2181, pruned_loss=0.02883, over 6796.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2453, pruned_loss=0.03081, over 1425096.23 frames.], batch size: 15, lr: 2.58e-04
+2022-05-15 16:52:16,796 INFO [train.py:812] (1/8) Epoch 30, batch 3900, loss[loss=0.1296, simple_loss=0.2194, pruned_loss=0.0199, over 7141.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2452, pruned_loss=0.03054, over 1425181.89 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 16:53:15,075 INFO [train.py:812] (1/8) Epoch 30, batch 3950, loss[loss=0.1664, simple_loss=0.2539, pruned_loss=0.0394, over 7375.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2457, pruned_loss=0.03082, over 1420374.85 frames.], batch size: 23, lr: 2.58e-04
+2022-05-15 16:54:13,793 INFO [train.py:812] (1/8) Epoch 30, batch 4000, loss[loss=0.1546, simple_loss=0.2432, pruned_loss=0.03294, over 7292.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2474, pruned_loss=0.03149, over 1419306.04 frames.], batch size: 25, lr: 2.58e-04
+2022-05-15 16:55:12,874 INFO [train.py:812] (1/8) Epoch 30, batch 4050, loss[loss=0.1573, simple_loss=0.2557, pruned_loss=0.02948, over 7115.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2465, pruned_loss=0.0312, over 1420310.24 frames.], batch size: 28, lr: 2.58e-04
+2022-05-15 16:56:10,891 INFO [train.py:812] (1/8) Epoch 30, batch 4100, loss[loss=0.1646, simple_loss=0.2712, pruned_loss=0.02903, over 7322.00 frames.], tot_loss[loss=0.154, simple_loss=0.2461, pruned_loss=0.0309, over 1422412.08 frames.], batch size: 21, lr: 2.58e-04
+2022-05-15 16:57:19,277 INFO [train.py:812] (1/8) Epoch 30, batch 4150, loss[loss=0.1675, simple_loss=0.2496, pruned_loss=0.04266, over 7210.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2457, pruned_loss=0.03093, over 1422640.73 frames.], batch size: 21, lr: 2.58e-04
+2022-05-15 16:58:17,932 INFO [train.py:812] (1/8) Epoch 30, batch 4200, loss[loss=0.1429, simple_loss=0.2438, pruned_loss=0.02099, over 7441.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2465, pruned_loss=0.03119, over 1423867.07 frames.], batch size: 20, lr: 2.58e-04
+2022-05-15 16:59:24,875 INFO [train.py:812] (1/8) Epoch 30, batch 4250, loss[loss=0.1638, simple_loss=0.2551, pruned_loss=0.03622, over 7384.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2472, pruned_loss=0.03132, over 1418239.95 frames.], batch size: 23, lr: 2.58e-04
+2022-05-15 17:00:23,120 INFO [train.py:812] (1/8) Epoch 30, batch 4300, loss[loss=0.1571, simple_loss=0.2281, pruned_loss=0.04306, over 7285.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2464, pruned_loss=0.03095, over 1421311.02 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 17:01:31,699 INFO [train.py:812] (1/8) Epoch 30, batch 4350, loss[loss=0.1414, simple_loss=0.2348, pruned_loss=0.02403, over 7223.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2446, pruned_loss=0.0308, over 1422866.05 frames.], batch size: 20, lr: 2.58e-04
+2022-05-15 17:02:30,807 INFO [train.py:812] (1/8) Epoch 30, batch 4400, loss[loss=0.1785, simple_loss=0.2714, pruned_loss=0.04286, over 7237.00 frames.], tot_loss[loss=0.1527, simple_loss=0.244, pruned_loss=0.03063, over 1418947.00 frames.], batch size: 20, lr: 2.57e-04
+2022-05-15 17:03:47,892 INFO [train.py:812] (1/8) Epoch 30, batch 4450, loss[loss=0.1391, simple_loss=0.2373, pruned_loss=0.02047, over 6314.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2433, pruned_loss=0.0301, over 1413858.47 frames.], batch size: 37, lr: 2.57e-04
+2022-05-15 17:04:54,629 INFO [train.py:812] (1/8) Epoch 30, batch 4500, loss[loss=0.1961, simple_loss=0.2754, pruned_loss=0.0584, over 5224.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.03076, over 1399183.42 frames.], batch size: 54, lr: 2.57e-04
+2022-05-15 17:05:52,204 INFO [train.py:812] (1/8) Epoch 30, batch 4550, loss[loss=0.1819, simple_loss=0.2791, pruned_loss=0.04238, over 4807.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2477, pruned_loss=0.03231, over 1358124.48 frames.], batch size: 53, lr: 2.57e-04
+2022-05-15 17:07:08,080 INFO [train.py:812] (1/8) Epoch 31, batch 0, loss[loss=0.1565, simple_loss=0.2541, pruned_loss=0.02945, over 7333.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2541, pruned_loss=0.02945, over 7333.00 frames.], batch size: 20, lr: 2.53e-04
+2022-05-15 17:08:07,409 INFO [train.py:812] (1/8) Epoch 31, batch 50, loss[loss=0.146, simple_loss=0.2456, pruned_loss=0.02321, over 7260.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2458, pruned_loss=0.02985, over 317129.20 frames.], batch size: 19, lr: 2.53e-04
+2022-05-15 17:09:06,200 INFO [train.py:812] (1/8) Epoch 31, batch 100, loss[loss=0.1706, simple_loss=0.261, pruned_loss=0.0401, over 7389.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2455, pruned_loss=0.03031, over 561429.38 frames.], batch size: 23, lr: 2.53e-04
+2022-05-15 17:10:05,005 INFO [train.py:812] (1/8) Epoch 31, batch 150, loss[loss=0.1661, simple_loss=0.2603, pruned_loss=0.03593, over 7220.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03018, over 756802.64 frames.], batch size: 22, lr: 2.53e-04
+2022-05-15 17:11:03,888 INFO [train.py:812] (1/8) Epoch 31, batch 200, loss[loss=0.1709, simple_loss=0.2544, pruned_loss=0.04372, over 4848.00 frames.], tot_loss[loss=0.1515, simple_loss=0.243, pruned_loss=0.02998, over 901668.67 frames.], batch size: 52, lr: 2.53e-04
+2022-05-15 17:12:02,426 INFO [train.py:812] (1/8) Epoch 31, batch 250, loss[loss=0.1746, simple_loss=0.2604, pruned_loss=0.04435, over 7304.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2446, pruned_loss=0.03038, over 1015356.79 frames.], batch size: 25, lr: 2.53e-04
+2022-05-15 17:13:01,761 INFO [train.py:812] (1/8) Epoch 31, batch 300, loss[loss=0.1569, simple_loss=0.2524, pruned_loss=0.03065, over 7325.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2445, pruned_loss=0.03011, over 1107188.29 frames.], batch size: 21, lr: 2.53e-04
+2022-05-15 17:13:59,733 INFO [train.py:812] (1/8) Epoch 31, batch 350, loss[loss=0.1501, simple_loss=0.2443, pruned_loss=0.02797, over 7160.00 frames.], tot_loss[loss=0.153, simple_loss=0.2452, pruned_loss=0.03041, over 1174472.05 frames.], batch size: 18, lr: 2.53e-04
+2022-05-15 17:14:57,249 INFO [train.py:812] (1/8) Epoch 31, batch 400, loss[loss=0.1448, simple_loss=0.2346, pruned_loss=0.02752, over 7216.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2454, pruned_loss=0.03055, over 1224875.12 frames.], batch size: 21, lr: 2.53e-04
+2022-05-15 17:15:56,105 INFO [train.py:812] (1/8) Epoch 31, batch 450, loss[loss=0.1388, simple_loss=0.2454, pruned_loss=0.01611, over 7144.00 frames.], tot_loss[loss=0.153, simple_loss=0.2451, pruned_loss=0.03044, over 1266531.74 frames.], batch size: 26, lr: 2.53e-04
+2022-05-15 17:16:55,561 INFO [train.py:812] (1/8) Epoch 31, batch 500, loss[loss=0.1429, simple_loss=0.2173, pruned_loss=0.0342, over 7292.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2445, pruned_loss=0.03041, over 1301334.23 frames.], batch size: 17, lr: 2.53e-04
+2022-05-15 17:17:54,441 INFO [train.py:812] (1/8) Epoch 31, batch 550, loss[loss=0.1476, simple_loss=0.2464, pruned_loss=0.02436, over 7408.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2454, pruned_loss=0.03073, over 1327636.69 frames.], batch size: 21, lr: 2.53e-04
+2022-05-15 17:18:53,064 INFO [train.py:812] (1/8) Epoch 31, batch 600, loss[loss=0.1606, simple_loss=0.2465, pruned_loss=0.03733, over 7071.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2466, pruned_loss=0.03121, over 1347162.55 frames.], batch size: 18, lr: 2.53e-04
+2022-05-15 17:19:50,582 INFO [train.py:812] (1/8) Epoch 31, batch 650, loss[loss=0.1587, simple_loss=0.2544, pruned_loss=0.03148, over 7147.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2458, pruned_loss=0.03069, over 1368266.70 frames.], batch size: 20, lr: 2.53e-04
+2022-05-15 17:20:49,367 INFO [train.py:812] (1/8) Epoch 31, batch 700, loss[loss=0.1327, simple_loss=0.2115, pruned_loss=0.02694, over 7250.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2451, pruned_loss=0.03089, over 1379322.74 frames.], batch size: 16, lr: 2.52e-04
+2022-05-15 17:21:47,379 INFO [train.py:812] (1/8) Epoch 31, batch 750, loss[loss=0.1632, simple_loss=0.2594, pruned_loss=0.03351, over 7230.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2449, pruned_loss=0.03068, over 1386725.24 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:22:46,122 INFO [train.py:812] (1/8) Epoch 31, batch 800, loss[loss=0.1442, simple_loss=0.2407, pruned_loss=0.02383, over 7322.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2453, pruned_loss=0.03061, over 1394953.35 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:23:44,737 INFO [train.py:812] (1/8) Epoch 31, batch 850, loss[loss=0.1422, simple_loss=0.2323, pruned_loss=0.02604, over 7422.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2446, pruned_loss=0.03028, over 1398392.05 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:24:43,291 INFO [train.py:812] (1/8) Epoch 31, batch 900, loss[loss=0.1624, simple_loss=0.2402, pruned_loss=0.04237, over 7208.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2446, pruned_loss=0.03027, over 1404275.24 frames.], batch size: 16, lr: 2.52e-04
+2022-05-15 17:25:42,280 INFO [train.py:812] (1/8) Epoch 31, batch 950, loss[loss=0.1521, simple_loss=0.2459, pruned_loss=0.02913, over 7044.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2442, pruned_loss=0.03053, over 1405808.43 frames.], batch size: 28, lr: 2.52e-04
+2022-05-15 17:26:41,335 INFO [train.py:812] (1/8) Epoch 31, batch 1000, loss[loss=0.1465, simple_loss=0.2452, pruned_loss=0.02388, over 7339.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2437, pruned_loss=0.03048, over 1408344.86 frames.], batch size: 22, lr: 2.52e-04
+2022-05-15 17:27:40,597 INFO [train.py:812] (1/8) Epoch 31, batch 1050, loss[loss=0.1513, simple_loss=0.25, pruned_loss=0.02633, over 7075.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.03021, over 1410965.55 frames.], batch size: 28, lr: 2.52e-04
+2022-05-15 17:28:39,407 INFO [train.py:812] (1/8) Epoch 31, batch 1100, loss[loss=0.1568, simple_loss=0.2492, pruned_loss=0.0322, over 7070.00 frames.], tot_loss[loss=0.1514, simple_loss=0.243, pruned_loss=0.02987, over 1414856.75 frames.], batch size: 18, lr: 2.52e-04
+2022-05-15 17:29:38,118 INFO [train.py:812] (1/8) Epoch 31, batch 1150, loss[loss=0.134, simple_loss=0.2201, pruned_loss=0.02395, over 7058.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2424, pruned_loss=0.02984, over 1416484.45 frames.], batch size: 18, lr: 2.52e-04
+2022-05-15 17:30:36,856 INFO [train.py:812] (1/8) Epoch 31, batch 1200, loss[loss=0.1692, simple_loss=0.261, pruned_loss=0.03868, over 7199.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2423, pruned_loss=0.02964, over 1417964.70 frames.], batch size: 22, lr: 2.52e-04
+2022-05-15 17:31:36,136 INFO [train.py:812] (1/8) Epoch 31, batch 1250, loss[loss=0.1348, simple_loss=0.2252, pruned_loss=0.02224, over 7397.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2428, pruned_loss=0.02971, over 1417919.40 frames.], batch size: 18, lr: 2.52e-04
+2022-05-15 17:32:35,753 INFO [train.py:812] (1/8) Epoch 31, batch 1300, loss[loss=0.1831, simple_loss=0.2723, pruned_loss=0.0469, over 7137.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2428, pruned_loss=0.03002, over 1417094.19 frames.], batch size: 26, lr: 2.52e-04
+2022-05-15 17:33:34,085 INFO [train.py:812] (1/8) Epoch 31, batch 1350, loss[loss=0.1285, simple_loss=0.2228, pruned_loss=0.01713, over 7126.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2445, pruned_loss=0.03059, over 1414006.72 frames.], batch size: 17, lr: 2.52e-04
+2022-05-15 17:34:32,630 INFO [train.py:812] (1/8) Epoch 31, batch 1400, loss[loss=0.1645, simple_loss=0.2668, pruned_loss=0.03106, over 7327.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2448, pruned_loss=0.03023, over 1418295.30 frames.], batch size: 22, lr: 2.52e-04
+2022-05-15 17:35:31,410 INFO [train.py:812] (1/8) Epoch 31, batch 1450, loss[loss=0.1456, simple_loss=0.2492, pruned_loss=0.02102, over 7146.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2453, pruned_loss=0.03046, over 1419238.42 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:36:30,346 INFO [train.py:812] (1/8) Epoch 31, batch 1500, loss[loss=0.1542, simple_loss=0.2552, pruned_loss=0.02658, over 7307.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2459, pruned_loss=0.03033, over 1425196.76 frames.], batch size: 25, lr: 2.52e-04
+2022-05-15 17:37:27,933 INFO [train.py:812] (1/8) Epoch 31, batch 1550, loss[loss=0.1826, simple_loss=0.2704, pruned_loss=0.04741, over 7282.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.03003, over 1426599.17 frames.], batch size: 25, lr: 2.52e-04
+2022-05-15 17:38:27,308 INFO [train.py:812] (1/8) Epoch 31, batch 1600, loss[loss=0.1541, simple_loss=0.2515, pruned_loss=0.02837, over 7261.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2439, pruned_loss=0.03034, over 1427872.59 frames.], batch size: 19, lr: 2.52e-04
+2022-05-15 17:39:26,051 INFO [train.py:812] (1/8) Epoch 31, batch 1650, loss[loss=0.1622, simple_loss=0.2597, pruned_loss=0.03241, over 7118.00 frames.], tot_loss[loss=0.1531, simple_loss=0.245, pruned_loss=0.03058, over 1428466.05 frames.], batch size: 21, lr: 2.52e-04
+2022-05-15 17:40:24,533 INFO [train.py:812] (1/8) Epoch 31, batch 1700, loss[loss=0.1636, simple_loss=0.2608, pruned_loss=0.0332, over 7304.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2429, pruned_loss=0.03003, over 1425276.63 frames.], batch size: 24, lr: 2.52e-04
+2022-05-15 17:41:22,577 INFO [train.py:812] (1/8) Epoch 31, batch 1750, loss[loss=0.1506, simple_loss=0.2477, pruned_loss=0.02675, over 7393.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2434, pruned_loss=0.03011, over 1427628.45 frames.], batch size: 23, lr: 2.52e-04
+2022-05-15 17:42:21,639 INFO [train.py:812] (1/8) Epoch 31, batch 1800, loss[loss=0.1429, simple_loss=0.232, pruned_loss=0.02689, over 7438.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2431, pruned_loss=0.03021, over 1423931.69 frames.], batch size: 20, lr: 2.51e-04
+2022-05-15 17:43:20,014 INFO [train.py:812] (1/8) Epoch 31, batch 1850, loss[loss=0.1435, simple_loss=0.22, pruned_loss=0.03348, over 7118.00 frames.], tot_loss[loss=0.151, simple_loss=0.2427, pruned_loss=0.0297, over 1422640.64 frames.], batch size: 17, lr: 2.51e-04
+2022-05-15 17:44:19,011 INFO [train.py:812] (1/8) Epoch 31, batch 1900, loss[loss=0.1326, simple_loss=0.222, pruned_loss=0.02159, over 7325.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2426, pruned_loss=0.02954, over 1426553.86 frames.], batch size: 20, lr: 2.51e-04
+2022-05-15 17:45:17,758 INFO [train.py:812] (1/8) Epoch 31, batch 1950, loss[loss=0.1626, simple_loss=0.257, pruned_loss=0.03415, over 7371.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2422, pruned_loss=0.02945, over 1425801.56 frames.], batch size: 23, lr: 2.51e-04
+2022-05-15 17:46:16,479 INFO [train.py:812] (1/8) Epoch 31, batch 2000, loss[loss=0.1469, simple_loss=0.2383, pruned_loss=0.02772, over 7163.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2415, pruned_loss=0.02936, over 1427352.91 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:47:15,235 INFO [train.py:812] (1/8) Epoch 31, batch 2050, loss[loss=0.1727, simple_loss=0.2663, pruned_loss=0.03958, over 7222.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2409, pruned_loss=0.02921, over 1424706.39 frames.], batch size: 22, lr: 2.51e-04
+2022-05-15 17:48:13,817 INFO [train.py:812] (1/8) Epoch 31, batch 2100, loss[loss=0.1587, simple_loss=0.2501, pruned_loss=0.03371, over 7160.00 frames.], tot_loss[loss=0.151, simple_loss=0.2428, pruned_loss=0.0296, over 1423129.72 frames.], batch size: 19, lr: 2.51e-04
+2022-05-15 17:49:12,920 INFO [train.py:812] (1/8) Epoch 31, batch 2150, loss[loss=0.1311, simple_loss=0.2247, pruned_loss=0.01871, over 7156.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02906, over 1426657.02 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:50:11,053 INFO [train.py:812] (1/8) Epoch 31, batch 2200, loss[loss=0.1391, simple_loss=0.233, pruned_loss=0.02257, over 7068.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.02927, over 1428379.26 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:51:08,611 INFO [train.py:812] (1/8) Epoch 31, batch 2250, loss[loss=0.1844, simple_loss=0.2871, pruned_loss=0.04082, over 7204.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2449, pruned_loss=0.02996, over 1427901.12 frames.], batch size: 23, lr: 2.51e-04
+2022-05-15 17:52:08,121 INFO [train.py:812] (1/8) Epoch 31, batch 2300, loss[loss=0.1484, simple_loss=0.2377, pruned_loss=0.02957, over 7247.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2445, pruned_loss=0.03003, over 1429960.93 frames.], batch size: 19, lr: 2.51e-04
+2022-05-15 17:53:06,341 INFO [train.py:812] (1/8) Epoch 31, batch 2350, loss[loss=0.1364, simple_loss=0.2294, pruned_loss=0.02173, over 7065.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2446, pruned_loss=0.03031, over 1430020.93 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:54:10,963 INFO [train.py:812] (1/8) Epoch 31, batch 2400, loss[loss=0.1508, simple_loss=0.2512, pruned_loss=0.0252, over 7216.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2443, pruned_loss=0.03038, over 1428590.94 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 17:55:08,408 INFO [train.py:812] (1/8) Epoch 31, batch 2450, loss[loss=0.1554, simple_loss=0.2551, pruned_loss=0.02784, over 7230.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2451, pruned_loss=0.03038, over 1424313.42 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 17:56:07,148 INFO [train.py:812] (1/8) Epoch 31, batch 2500, loss[loss=0.1608, simple_loss=0.2529, pruned_loss=0.03438, over 7321.00 frames.], tot_loss[loss=0.152, simple_loss=0.2443, pruned_loss=0.02985, over 1426979.57 frames.], batch size: 22, lr: 2.51e-04
+2022-05-15 17:57:05,892 INFO [train.py:812] (1/8) Epoch 31, batch 2550, loss[loss=0.1557, simple_loss=0.2558, pruned_loss=0.02777, over 7180.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2444, pruned_loss=0.02987, over 1429127.63 frames.], batch size: 23, lr: 2.51e-04
+2022-05-15 17:58:14,113 INFO [train.py:812] (1/8) Epoch 31, batch 2600, loss[loss=0.1439, simple_loss=0.2259, pruned_loss=0.03094, over 7397.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03018, over 1428256.73 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:59:11,568 INFO [train.py:812] (1/8) Epoch 31, batch 2650, loss[loss=0.1688, simple_loss=0.2671, pruned_loss=0.03532, over 7410.00 frames.], tot_loss[loss=0.153, simple_loss=0.2448, pruned_loss=0.03056, over 1425390.74 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 18:00:10,469 INFO [train.py:812] (1/8) Epoch 31, batch 2700, loss[loss=0.1631, simple_loss=0.2562, pruned_loss=0.03503, over 7308.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2452, pruned_loss=0.03071, over 1419009.95 frames.], batch size: 25, lr: 2.51e-04
+2022-05-15 18:01:09,675 INFO [train.py:812] (1/8) Epoch 31, batch 2750, loss[loss=0.157, simple_loss=0.2456, pruned_loss=0.0342, over 7146.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2449, pruned_loss=0.03072, over 1419841.35 frames.], batch size: 20, lr: 2.51e-04
+2022-05-15 18:02:08,944 INFO [train.py:812] (1/8) Epoch 31, batch 2800, loss[loss=0.1482, simple_loss=0.2421, pruned_loss=0.02715, over 7163.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2453, pruned_loss=0.03104, over 1422016.51 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 18:03:06,858 INFO [train.py:812] (1/8) Epoch 31, batch 2850, loss[loss=0.16, simple_loss=0.2584, pruned_loss=0.0308, over 7185.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2458, pruned_loss=0.03113, over 1420080.67 frames.], batch size: 22, lr: 2.51e-04
+2022-05-15 18:04:06,623 INFO [train.py:812] (1/8) Epoch 31, batch 2900, loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.02917, over 7098.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2455, pruned_loss=0.03107, over 1425037.47 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 18:05:04,895 INFO [train.py:812] (1/8) Epoch 31, batch 2950, loss[loss=0.1338, simple_loss=0.2249, pruned_loss=0.02133, over 7272.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2453, pruned_loss=0.03095, over 1424483.83 frames.], batch size: 19, lr: 2.50e-04
+2022-05-15 18:06:03,444 INFO [train.py:812] (1/8) Epoch 31, batch 3000, loss[loss=0.1464, simple_loss=0.2422, pruned_loss=0.0253, over 7337.00 frames.], tot_loss[loss=0.1524, simple_loss=0.244, pruned_loss=0.03037, over 1424332.58 frames.], batch size: 20, lr: 2.50e-04
+2022-05-15 18:06:03,446 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 18:06:10,970 INFO [train.py:841] (1/8) Epoch 31, validation: loss=0.1541, simple_loss=0.25, pruned_loss=0.02913, over 698248.00 frames.
+2022-05-15 18:07:09,530 INFO [train.py:812] (1/8) Epoch 31, batch 3050, loss[loss=0.1349, simple_loss=0.2203, pruned_loss=0.02478, over 7001.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2443, pruned_loss=0.03043, over 1423569.80 frames.], batch size: 16, lr: 2.50e-04
+2022-05-15 18:08:09,160 INFO [train.py:812] (1/8) Epoch 31, batch 3100, loss[loss=0.1527, simple_loss=0.2445, pruned_loss=0.03046, over 7297.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2441, pruned_loss=0.03055, over 1427261.26 frames.], batch size: 25, lr: 2.50e-04
+2022-05-15 18:09:08,139 INFO [train.py:812] (1/8) Epoch 31, batch 3150, loss[loss=0.1518, simple_loss=0.2324, pruned_loss=0.03565, over 6989.00 frames.], tot_loss[loss=0.153, simple_loss=0.2445, pruned_loss=0.03073, over 1425753.52 frames.], batch size: 16, lr: 2.50e-04
+2022-05-15 18:10:05,062 INFO [train.py:812] (1/8) Epoch 31, batch 3200, loss[loss=0.1367, simple_loss=0.2347, pruned_loss=0.01936, over 7202.00 frames.], tot_loss[loss=0.1526, simple_loss=0.244, pruned_loss=0.03058, over 1417472.77 frames.], batch size: 23, lr: 2.50e-04
+2022-05-15 18:11:03,076 INFO [train.py:812] (1/8) Epoch 31, batch 3250, loss[loss=0.1792, simple_loss=0.283, pruned_loss=0.03771, over 7151.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2452, pruned_loss=0.03077, over 1416663.73 frames.], batch size: 20, lr: 2.50e-04
+2022-05-15 18:12:02,665 INFO [train.py:812] (1/8) Epoch 31, batch 3300, loss[loss=0.1485, simple_loss=0.2288, pruned_loss=0.03412, over 7277.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2445, pruned_loss=0.03063, over 1422756.21 frames.], batch size: 17, lr: 2.50e-04
+2022-05-15 18:13:01,602 INFO [train.py:812] (1/8) Epoch 31, batch 3350, loss[loss=0.1578, simple_loss=0.2659, pruned_loss=0.02486, over 7226.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2445, pruned_loss=0.03067, over 1421139.13 frames.], batch size: 21, lr: 2.50e-04
+2022-05-15 18:14:00,862 INFO [train.py:812] (1/8) Epoch 31, batch 3400, loss[loss=0.1785, simple_loss=0.2708, pruned_loss=0.04313, over 7323.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2437, pruned_loss=0.03032, over 1421714.51 frames.], batch size: 25, lr: 2.50e-04
+2022-05-15 18:14:57,858 INFO [train.py:812] (1/8) Epoch 31, batch 3450, loss[loss=0.1603, simple_loss=0.2564, pruned_loss=0.03214, over 6354.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2449, pruned_loss=0.03038, over 1426110.33 frames.], batch size: 37, lr: 2.50e-04
+2022-05-15 18:15:56,017 INFO [train.py:812] (1/8) Epoch 31, batch 3500, loss[loss=0.1897, simple_loss=0.2874, pruned_loss=0.04597, over 7362.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2454, pruned_loss=0.03047, over 1427969.71 frames.], batch size: 23, lr: 2.50e-04
+2022-05-15 18:16:54,988 INFO [train.py:812] (1/8) Epoch 31, batch 3550, loss[loss=0.1389, simple_loss=0.2259, pruned_loss=0.02597, over 7423.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2458, pruned_loss=0.03074, over 1428951.43 frames.], batch size: 20, lr: 2.50e-04
+2022-05-15 18:17:52,436 INFO [train.py:812] (1/8) Epoch 31, batch 3600, loss[loss=0.1584, simple_loss=0.2537, pruned_loss=0.03149, over 7292.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2465, pruned_loss=0.03095, over 1423969.72 frames.], batch size: 24, lr: 2.50e-04
+2022-05-15 18:18:51,253 INFO [train.py:812] (1/8) Epoch 31, batch 3650, loss[loss=0.139, simple_loss=0.2218, pruned_loss=0.02809, over 7147.00 frames.], tot_loss[loss=0.154, simple_loss=0.2464, pruned_loss=0.03085, over 1422797.06 frames.], batch size: 17, lr: 2.50e-04
+2022-05-15 18:19:50,562 INFO [train.py:812] (1/8) Epoch 31, batch 3700, loss[loss=0.1276, simple_loss=0.2138, pruned_loss=0.02066, over 7269.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2449, pruned_loss=0.03033, over 1425198.99 frames.], batch size: 17, lr: 2.50e-04
+2022-05-15 18:20:49,308 INFO [train.py:812] (1/8) Epoch 31, batch 3750, loss[loss=0.151, simple_loss=0.2434, pruned_loss=0.02928, over 7265.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2445, pruned_loss=0.03049, over 1423303.80 frames.], batch size: 19, lr: 2.50e-04
+2022-05-15 18:21:49,296 INFO [train.py:812] (1/8) Epoch 31, batch 3800, loss[loss=0.1309, simple_loss=0.2166, pruned_loss=0.02264, over 7300.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2442, pruned_loss=0.0306, over 1425749.16 frames.], batch size: 18, lr: 2.50e-04
+2022-05-15 18:22:47,388 INFO [train.py:812] (1/8) Epoch 31, batch 3850, loss[loss=0.1326, simple_loss=0.2206, pruned_loss=0.02232, over 7069.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2447, pruned_loss=0.03058, over 1425155.57 frames.], batch size: 18, lr: 2.50e-04
+2022-05-15 18:23:45,724 INFO [train.py:812] (1/8) Epoch 31, batch 3900, loss[loss=0.1495, simple_loss=0.2402, pruned_loss=0.02944, over 7265.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2452, pruned_loss=0.0308, over 1428869.78 frames.], batch size: 24, lr: 2.50e-04
+2022-05-15 18:24:43,604 INFO [train.py:812] (1/8) Epoch 31, batch 3950, loss[loss=0.1444, simple_loss=0.2344, pruned_loss=0.02726, over 7361.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2451, pruned_loss=0.0311, over 1428847.06 frames.], batch size: 19, lr: 2.50e-04
+2022-05-15 18:25:41,721 INFO [train.py:812] (1/8) Epoch 31, batch 4000, loss[loss=0.154, simple_loss=0.2443, pruned_loss=0.03187, over 7163.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2456, pruned_loss=0.03149, over 1427345.70 frames.], batch size: 18, lr: 2.50e-04
+2022-05-15 18:26:41,012 INFO [train.py:812] (1/8) Epoch 31, batch 4050, loss[loss=0.1618, simple_loss=0.2515, pruned_loss=0.03611, over 7279.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2455, pruned_loss=0.03128, over 1426364.89 frames.], batch size: 24, lr: 2.49e-04
+2022-05-15 18:27:40,595 INFO [train.py:812] (1/8) Epoch 31, batch 4100, loss[loss=0.1408, simple_loss=0.2259, pruned_loss=0.02782, over 7156.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2457, pruned_loss=0.03122, over 1427619.57 frames.], batch size: 19, lr: 2.49e-04
+2022-05-15 18:28:39,540 INFO [train.py:812] (1/8) Epoch 31, batch 4150, loss[loss=0.1633, simple_loss=0.2705, pruned_loss=0.02803, over 7113.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2459, pruned_loss=0.03096, over 1429688.03 frames.], batch size: 21, lr: 2.49e-04
+2022-05-15 18:29:38,566 INFO [train.py:812] (1/8) Epoch 31, batch 4200, loss[loss=0.1317, simple_loss=0.2246, pruned_loss=0.01939, over 6798.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2447, pruned_loss=0.03039, over 1430962.91 frames.], batch size: 15, lr: 2.49e-04
+2022-05-15 18:30:36,497 INFO [train.py:812] (1/8) Epoch 31, batch 4250, loss[loss=0.1679, simple_loss=0.2559, pruned_loss=0.0399, over 7130.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2447, pruned_loss=0.03045, over 1426897.80 frames.], batch size: 26, lr: 2.49e-04
+2022-05-15 18:31:35,777 INFO [train.py:812] (1/8) Epoch 31, batch 4300, loss[loss=0.1434, simple_loss=0.242, pruned_loss=0.02239, over 7329.00 frames.], tot_loss[loss=0.152, simple_loss=0.2438, pruned_loss=0.03011, over 1429375.99 frames.], batch size: 24, lr: 2.49e-04
+2022-05-15 18:32:33,469 INFO [train.py:812] (1/8) Epoch 31, batch 4350, loss[loss=0.1476, simple_loss=0.2493, pruned_loss=0.02295, over 7123.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2447, pruned_loss=0.03014, over 1421278.98 frames.], batch size: 21, lr: 2.49e-04
+2022-05-15 18:33:32,233 INFO [train.py:812] (1/8) Epoch 31, batch 4400, loss[loss=0.1504, simple_loss=0.2492, pruned_loss=0.02582, over 7126.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2444, pruned_loss=0.0301, over 1411475.91 frames.], batch size: 21, lr: 2.49e-04
+2022-05-15 18:34:30,889 INFO [train.py:812] (1/8) Epoch 31, batch 4450, loss[loss=0.159, simple_loss=0.2557, pruned_loss=0.03117, over 6265.00 frames.], tot_loss[loss=0.153, simple_loss=0.2448, pruned_loss=0.03053, over 1409975.69 frames.], batch size: 37, lr: 2.49e-04
+2022-05-15 18:35:30,065 INFO [train.py:812] (1/8) Epoch 31, batch 4500, loss[loss=0.1624, simple_loss=0.2598, pruned_loss=0.03252, over 6486.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2462, pruned_loss=0.03116, over 1386211.68 frames.], batch size: 38, lr: 2.49e-04
+2022-05-15 18:36:28,940 INFO [train.py:812] (1/8) Epoch 31, batch 4550, loss[loss=0.1518, simple_loss=0.2503, pruned_loss=0.0266, over 5389.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2476, pruned_loss=0.03194, over 1356187.20 frames.], batch size: 52, lr: 2.49e-04
+2022-05-15 18:37:36,646 INFO [train.py:812] (1/8) Epoch 32, batch 0, loss[loss=0.143, simple_loss=0.2386, pruned_loss=0.02372, over 5146.00 frames.], tot_loss[loss=0.143, simple_loss=0.2386, pruned_loss=0.02372, over 5146.00 frames.], batch size: 52, lr: 2.45e-04
+2022-05-15 18:38:34,879 INFO [train.py:812] (1/8) Epoch 32, batch 50, loss[loss=0.1588, simple_loss=0.2499, pruned_loss=0.03387, over 6340.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2505, pruned_loss=0.03161, over 319844.58 frames.], batch size: 37, lr: 2.45e-04
+2022-05-15 18:39:33,407 INFO [train.py:812] (1/8) Epoch 32, batch 100, loss[loss=0.1596, simple_loss=0.2466, pruned_loss=0.03627, over 7287.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2463, pruned_loss=0.03076, over 566639.97 frames.], batch size: 25, lr: 2.45e-04
+2022-05-15 18:40:32,481 INFO [train.py:812] (1/8) Epoch 32, batch 150, loss[loss=0.1574, simple_loss=0.2519, pruned_loss=0.0314, over 7177.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2452, pruned_loss=0.03028, over 758133.46 frames.], batch size: 26, lr: 2.45e-04
+2022-05-15 18:41:31,093 INFO [train.py:812] (1/8) Epoch 32, batch 200, loss[loss=0.1268, simple_loss=0.2116, pruned_loss=0.02103, over 7424.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2438, pruned_loss=0.02982, over 904358.44 frames.], batch size: 17, lr: 2.45e-04
+2022-05-15 18:42:29,421 INFO [train.py:812] (1/8) Epoch 32, batch 250, loss[loss=0.1892, simple_loss=0.2897, pruned_loss=0.04437, over 7273.00 frames.], tot_loss[loss=0.1518, simple_loss=0.244, pruned_loss=0.02985, over 1024100.04 frames.], batch size: 24, lr: 2.45e-04
+2022-05-15 18:43:28,938 INFO [train.py:812] (1/8) Epoch 32, batch 300, loss[loss=0.1982, simple_loss=0.2886, pruned_loss=0.05394, over 7312.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2453, pruned_loss=0.03049, over 1114663.33 frames.], batch size: 24, lr: 2.45e-04
+2022-05-15 18:44:28,379 INFO [train.py:812] (1/8) Epoch 32, batch 350, loss[loss=0.1545, simple_loss=0.2482, pruned_loss=0.03042, over 7095.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2452, pruned_loss=0.03052, over 1182059.00 frames.], batch size: 28, lr: 2.45e-04
+2022-05-15 18:45:27,073 INFO [train.py:812] (1/8) Epoch 32, batch 400, loss[loss=0.142, simple_loss=0.2446, pruned_loss=0.01973, over 7140.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2451, pruned_loss=0.03063, over 1236832.36 frames.], batch size: 26, lr: 2.45e-04
+2022-05-15 18:46:25,916 INFO [train.py:812] (1/8) Epoch 32, batch 450, loss[loss=0.1579, simple_loss=0.2546, pruned_loss=0.03062, over 7322.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2445, pruned_loss=0.03029, over 1277667.70 frames.], batch size: 21, lr: 2.45e-04
+2022-05-15 18:47:25,087 INFO [train.py:812] (1/8) Epoch 32, batch 500, loss[loss=0.1572, simple_loss=0.2527, pruned_loss=0.03086, over 7338.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2445, pruned_loss=0.0301, over 1313375.79 frames.], batch size: 22, lr: 2.45e-04
+2022-05-15 18:48:23,112 INFO [train.py:812] (1/8) Epoch 32, batch 550, loss[loss=0.1554, simple_loss=0.2579, pruned_loss=0.02651, over 7343.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.03023, over 1341377.97 frames.], batch size: 22, lr: 2.45e-04
+2022-05-15 18:49:22,857 INFO [train.py:812] (1/8) Epoch 32, batch 600, loss[loss=0.1225, simple_loss=0.208, pruned_loss=0.01849, over 7145.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03017, over 1363947.72 frames.], batch size: 17, lr: 2.45e-04
+2022-05-15 18:50:21,229 INFO [train.py:812] (1/8) Epoch 32, batch 650, loss[loss=0.1292, simple_loss=0.2184, pruned_loss=0.01999, over 7004.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2435, pruned_loss=0.0298, over 1380154.56 frames.], batch size: 16, lr: 2.45e-04
+2022-05-15 18:51:18,823 INFO [train.py:812] (1/8) Epoch 32, batch 700, loss[loss=0.1589, simple_loss=0.25, pruned_loss=0.03395, over 7206.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2439, pruned_loss=0.02948, over 1388867.75 frames.], batch size: 23, lr: 2.45e-04
+2022-05-15 18:52:17,786 INFO [train.py:812] (1/8) Epoch 32, batch 750, loss[loss=0.1563, simple_loss=0.2528, pruned_loss=0.02996, over 7125.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2444, pruned_loss=0.03001, over 1397549.56 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 18:53:17,316 INFO [train.py:812] (1/8) Epoch 32, batch 800, loss[loss=0.125, simple_loss=0.2159, pruned_loss=0.01703, over 7272.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.02963, over 1402677.42 frames.], batch size: 18, lr: 2.44e-04
+2022-05-15 18:54:15,846 INFO [train.py:812] (1/8) Epoch 32, batch 850, loss[loss=0.1665, simple_loss=0.2711, pruned_loss=0.03095, over 7297.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2452, pruned_loss=0.03012, over 1409313.55 frames.], batch size: 25, lr: 2.44e-04
+2022-05-15 18:55:14,234 INFO [train.py:812] (1/8) Epoch 32, batch 900, loss[loss=0.1693, simple_loss=0.252, pruned_loss=0.04332, over 7342.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2461, pruned_loss=0.0303, over 1411895.71 frames.], batch size: 22, lr: 2.44e-04
+2022-05-15 18:56:22,072 INFO [train.py:812] (1/8) Epoch 32, batch 950, loss[loss=0.1435, simple_loss=0.2237, pruned_loss=0.03159, over 7195.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2447, pruned_loss=0.03015, over 1413730.23 frames.], batch size: 16, lr: 2.44e-04
+2022-05-15 18:57:31,055 INFO [train.py:812] (1/8) Epoch 32, batch 1000, loss[loss=0.1557, simple_loss=0.2473, pruned_loss=0.03208, over 7417.00 frames.], tot_loss[loss=0.1519, simple_loss=0.244, pruned_loss=0.02989, over 1417168.39 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 18:58:30,364 INFO [train.py:812] (1/8) Epoch 32, batch 1050, loss[loss=0.1664, simple_loss=0.2568, pruned_loss=0.03799, over 7240.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.02965, over 1421544.21 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 18:59:29,288 INFO [train.py:812] (1/8) Epoch 32, batch 1100, loss[loss=0.1696, simple_loss=0.2653, pruned_loss=0.03692, over 7216.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.0295, over 1419592.90 frames.], batch size: 22, lr: 2.44e-04
+2022-05-15 19:00:36,742 INFO [train.py:812] (1/8) Epoch 32, batch 1150, loss[loss=0.1257, simple_loss=0.2062, pruned_loss=0.02261, over 7132.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02957, over 1422674.96 frames.], batch size: 17, lr: 2.44e-04
+2022-05-15 19:01:36,491 INFO [train.py:812] (1/8) Epoch 32, batch 1200, loss[loss=0.151, simple_loss=0.253, pruned_loss=0.02448, over 7417.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2433, pruned_loss=0.02957, over 1425058.57 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 19:02:45,181 INFO [train.py:812] (1/8) Epoch 32, batch 1250, loss[loss=0.1585, simple_loss=0.2468, pruned_loss=0.03508, over 7178.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2443, pruned_loss=0.02996, over 1419202.80 frames.], batch size: 23, lr: 2.44e-04
+2022-05-15 19:03:53,730 INFO [train.py:812] (1/8) Epoch 32, batch 1300, loss[loss=0.186, simple_loss=0.2827, pruned_loss=0.04463, over 7150.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2445, pruned_loss=0.03029, over 1424178.30 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:05:00,943 INFO [train.py:812] (1/8) Epoch 32, batch 1350, loss[loss=0.1585, simple_loss=0.2472, pruned_loss=0.03487, over 7342.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2444, pruned_loss=0.03035, over 1422454.31 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:05:59,744 INFO [train.py:812] (1/8) Epoch 32, batch 1400, loss[loss=0.1553, simple_loss=0.2428, pruned_loss=0.03387, over 7241.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2429, pruned_loss=0.02982, over 1422604.53 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:06:57,264 INFO [train.py:812] (1/8) Epoch 32, batch 1450, loss[loss=0.154, simple_loss=0.2506, pruned_loss=0.02866, over 7325.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2435, pruned_loss=0.03, over 1424563.81 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:08:05,679 INFO [train.py:812] (1/8) Epoch 32, batch 1500, loss[loss=0.1729, simple_loss=0.2625, pruned_loss=0.04167, over 5070.00 frames.], tot_loss[loss=0.151, simple_loss=0.2428, pruned_loss=0.02959, over 1423220.27 frames.], batch size: 52, lr: 2.44e-04
+2022-05-15 19:09:04,122 INFO [train.py:812] (1/8) Epoch 32, batch 1550, loss[loss=0.1299, simple_loss=0.2101, pruned_loss=0.02487, over 7404.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2426, pruned_loss=0.02962, over 1423141.26 frames.], batch size: 18, lr: 2.44e-04
+2022-05-15 19:10:03,423 INFO [train.py:812] (1/8) Epoch 32, batch 1600, loss[loss=0.1613, simple_loss=0.2545, pruned_loss=0.03404, over 7199.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2427, pruned_loss=0.02976, over 1418364.30 frames.], batch size: 23, lr: 2.44e-04
+2022-05-15 19:11:01,503 INFO [train.py:812] (1/8) Epoch 32, batch 1650, loss[loss=0.146, simple_loss=0.2358, pruned_loss=0.02805, over 7412.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2434, pruned_loss=0.03014, over 1417345.12 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 19:12:00,712 INFO [train.py:812] (1/8) Epoch 32, batch 1700, loss[loss=0.1474, simple_loss=0.2409, pruned_loss=0.02699, over 7121.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2436, pruned_loss=0.03038, over 1411919.69 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 19:12:59,707 INFO [train.py:812] (1/8) Epoch 32, batch 1750, loss[loss=0.1705, simple_loss=0.254, pruned_loss=0.04353, over 5224.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2442, pruned_loss=0.03047, over 1410070.74 frames.], batch size: 52, lr: 2.44e-04
+2022-05-15 19:14:04,607 INFO [train.py:812] (1/8) Epoch 32, batch 1800, loss[loss=0.1576, simple_loss=0.2586, pruned_loss=0.02825, over 7229.00 frames.], tot_loss[loss=0.1529, simple_loss=0.245, pruned_loss=0.03044, over 1411728.08 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:15:03,155 INFO [train.py:812] (1/8) Epoch 32, batch 1850, loss[loss=0.139, simple_loss=0.2173, pruned_loss=0.03038, over 7004.00 frames.], tot_loss[loss=0.1529, simple_loss=0.245, pruned_loss=0.03045, over 1406080.74 frames.], batch size: 16, lr: 2.44e-04
+2022-05-15 19:16:02,088 INFO [train.py:812] (1/8) Epoch 32, batch 1900, loss[loss=0.1356, simple_loss=0.2239, pruned_loss=0.02372, over 7361.00 frames.], tot_loss[loss=0.152, simple_loss=0.2439, pruned_loss=0.02998, over 1412193.97 frames.], batch size: 19, lr: 2.44e-04
+2022-05-15 19:17:00,600 INFO [train.py:812] (1/8) Epoch 32, batch 1950, loss[loss=0.148, simple_loss=0.2382, pruned_loss=0.0289, over 7363.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2435, pruned_loss=0.03001, over 1418314.33 frames.], batch size: 19, lr: 2.43e-04
+2022-05-15 19:18:00,436 INFO [train.py:812] (1/8) Epoch 32, batch 2000, loss[loss=0.1375, simple_loss=0.2217, pruned_loss=0.0267, over 7289.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.02966, over 1420069.05 frames.], batch size: 18, lr: 2.43e-04
+2022-05-15 19:18:57,517 INFO [train.py:812] (1/8) Epoch 32, batch 2050, loss[loss=0.1687, simple_loss=0.2679, pruned_loss=0.03476, over 7137.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2434, pruned_loss=0.02964, over 1416366.31 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:19:56,227 INFO [train.py:812] (1/8) Epoch 32, batch 2100, loss[loss=0.153, simple_loss=0.2365, pruned_loss=0.0348, over 7212.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2449, pruned_loss=0.03018, over 1416585.98 frames.], batch size: 16, lr: 2.43e-04
+2022-05-15 19:20:54,966 INFO [train.py:812] (1/8) Epoch 32, batch 2150, loss[loss=0.1545, simple_loss=0.2592, pruned_loss=0.0249, over 7207.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2449, pruned_loss=0.03006, over 1420434.21 frames.], batch size: 21, lr: 2.43e-04
+2022-05-15 19:21:53,682 INFO [train.py:812] (1/8) Epoch 32, batch 2200, loss[loss=0.1576, simple_loss=0.2525, pruned_loss=0.03135, over 7138.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2449, pruned_loss=0.03034, over 1423250.27 frames.], batch size: 26, lr: 2.43e-04
+2022-05-15 19:22:52,766 INFO [train.py:812] (1/8) Epoch 32, batch 2250, loss[loss=0.1404, simple_loss=0.2319, pruned_loss=0.02441, over 7061.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2446, pruned_loss=0.03016, over 1424355.39 frames.], batch size: 18, lr: 2.43e-04
+2022-05-15 19:23:52,307 INFO [train.py:812] (1/8) Epoch 32, batch 2300, loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02905, over 7331.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2443, pruned_loss=0.03028, over 1421435.84 frames.], batch size: 22, lr: 2.43e-04
+2022-05-15 19:24:49,716 INFO [train.py:812] (1/8) Epoch 32, batch 2350, loss[loss=0.1428, simple_loss=0.216, pruned_loss=0.0348, over 7275.00 frames.], tot_loss[loss=0.1529, simple_loss=0.245, pruned_loss=0.03039, over 1425176.80 frames.], batch size: 17, lr: 2.43e-04
+2022-05-15 19:25:48,451 INFO [train.py:812] (1/8) Epoch 32, batch 2400, loss[loss=0.1291, simple_loss=0.235, pruned_loss=0.0116, over 7327.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2453, pruned_loss=0.03068, over 1421395.61 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:26:47,722 INFO [train.py:812] (1/8) Epoch 32, batch 2450, loss[loss=0.1758, simple_loss=0.2712, pruned_loss=0.04023, over 7173.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2452, pruned_loss=0.03089, over 1422541.30 frames.], batch size: 26, lr: 2.43e-04
+2022-05-15 19:27:46,277 INFO [train.py:812] (1/8) Epoch 32, batch 2500, loss[loss=0.1384, simple_loss=0.2203, pruned_loss=0.02825, over 7262.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2451, pruned_loss=0.03061, over 1424592.47 frames.], batch size: 17, lr: 2.43e-04
+2022-05-15 19:28:44,158 INFO [train.py:812] (1/8) Epoch 32, batch 2550, loss[loss=0.1675, simple_loss=0.2666, pruned_loss=0.03418, over 7329.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.03022, over 1422517.71 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:29:41,413 INFO [train.py:812] (1/8) Epoch 32, batch 2600, loss[loss=0.1286, simple_loss=0.2145, pruned_loss=0.02129, over 7139.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.03024, over 1420808.22 frames.], batch size: 17, lr: 2.43e-04
+2022-05-15 19:30:39,820 INFO [train.py:812] (1/8) Epoch 32, batch 2650, loss[loss=0.169, simple_loss=0.2622, pruned_loss=0.03794, over 7154.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2444, pruned_loss=0.03021, over 1423097.73 frames.], batch size: 26, lr: 2.43e-04
+2022-05-15 19:31:39,427 INFO [train.py:812] (1/8) Epoch 32, batch 2700, loss[loss=0.152, simple_loss=0.246, pruned_loss=0.02899, over 7316.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03014, over 1422607.92 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:32:37,299 INFO [train.py:812] (1/8) Epoch 32, batch 2750, loss[loss=0.1663, simple_loss=0.2596, pruned_loss=0.03646, over 7029.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2441, pruned_loss=0.02989, over 1424906.53 frames.], batch size: 28, lr: 2.43e-04
+2022-05-15 19:33:35,465 INFO [train.py:812] (1/8) Epoch 32, batch 2800, loss[loss=0.1226, simple_loss=0.2091, pruned_loss=0.01802, over 7405.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2433, pruned_loss=0.02988, over 1424290.52 frames.], batch size: 18, lr: 2.43e-04
+2022-05-15 19:34:34,368 INFO [train.py:812] (1/8) Epoch 32, batch 2850, loss[loss=0.1654, simple_loss=0.2627, pruned_loss=0.03398, over 6501.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2434, pruned_loss=0.02982, over 1420801.91 frames.], batch size: 38, lr: 2.43e-04
+2022-05-15 19:35:32,672 INFO [train.py:812] (1/8) Epoch 32, batch 2900, loss[loss=0.1452, simple_loss=0.2348, pruned_loss=0.02777, over 7228.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2443, pruned_loss=0.02995, over 1424483.99 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:36:30,941 INFO [train.py:812] (1/8) Epoch 32, batch 2950, loss[loss=0.1466, simple_loss=0.2501, pruned_loss=0.02153, over 7194.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2449, pruned_loss=0.02986, over 1416696.85 frames.], batch size: 23, lr: 2.43e-04
+2022-05-15 19:37:29,687 INFO [train.py:812] (1/8) Epoch 32, batch 3000, loss[loss=0.1487, simple_loss=0.2493, pruned_loss=0.02405, over 7438.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2457, pruned_loss=0.03042, over 1417947.39 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:37:29,687 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 19:37:37,095 INFO [train.py:841] (1/8) Epoch 32, validation: loss=0.1532, simple_loss=0.2494, pruned_loss=0.02852, over 698248.00 frames.
+2022-05-15 19:38:35,485 INFO [train.py:812] (1/8) Epoch 32, batch 3050, loss[loss=0.1499, simple_loss=0.2521, pruned_loss=0.02388, over 7268.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2451, pruned_loss=0.03036, over 1421701.56 frames.], batch size: 25, lr: 2.43e-04
+2022-05-15 19:39:34,743 INFO [train.py:812] (1/8) Epoch 32, batch 3100, loss[loss=0.1441, simple_loss=0.24, pruned_loss=0.02411, over 7063.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2449, pruned_loss=0.03046, over 1424991.04 frames.], batch size: 28, lr: 2.42e-04
+2022-05-15 19:40:34,133 INFO [train.py:812] (1/8) Epoch 32, batch 3150, loss[loss=0.1224, simple_loss=0.206, pruned_loss=0.01936, over 7283.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2444, pruned_loss=0.03063, over 1423049.73 frames.], batch size: 17, lr: 2.42e-04
+2022-05-15 19:41:32,537 INFO [train.py:812] (1/8) Epoch 32, batch 3200, loss[loss=0.1566, simple_loss=0.2497, pruned_loss=0.0318, over 7109.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2449, pruned_loss=0.03045, over 1425415.59 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 19:42:31,646 INFO [train.py:812] (1/8) Epoch 32, batch 3250, loss[loss=0.1625, simple_loss=0.2565, pruned_loss=0.0342, over 7350.00 frames.], tot_loss[loss=0.1531, simple_loss=0.245, pruned_loss=0.03058, over 1426829.54 frames.], batch size: 22, lr: 2.42e-04
+2022-05-15 19:43:31,273 INFO [train.py:812] (1/8) Epoch 32, batch 3300, loss[loss=0.1468, simple_loss=0.2496, pruned_loss=0.02206, over 7420.00 frames.], tot_loss[loss=0.153, simple_loss=0.2448, pruned_loss=0.03057, over 1423023.38 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:44:30,449 INFO [train.py:812] (1/8) Epoch 32, batch 3350, loss[loss=0.1488, simple_loss=0.2481, pruned_loss=0.02473, over 7322.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2432, pruned_loss=0.02984, over 1425344.93 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 19:45:29,623 INFO [train.py:812] (1/8) Epoch 32, batch 3400, loss[loss=0.1594, simple_loss=0.255, pruned_loss=0.03189, over 7327.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2446, pruned_loss=0.03053, over 1422596.84 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:46:27,574 INFO [train.py:812] (1/8) Epoch 32, batch 3450, loss[loss=0.1582, simple_loss=0.2547, pruned_loss=0.03084, over 7213.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2449, pruned_loss=0.03026, over 1425738.46 frames.], batch size: 22, lr: 2.42e-04
+2022-05-15 19:47:26,352 INFO [train.py:812] (1/8) Epoch 32, batch 3500, loss[loss=0.1646, simple_loss=0.2595, pruned_loss=0.0348, over 7304.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2457, pruned_loss=0.03035, over 1429077.33 frames.], batch size: 24, lr: 2.42e-04
+2022-05-15 19:48:25,217 INFO [train.py:812] (1/8) Epoch 32, batch 3550, loss[loss=0.1745, simple_loss=0.2707, pruned_loss=0.03917, over 7376.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2446, pruned_loss=0.03029, over 1432306.38 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:49:24,693 INFO [train.py:812] (1/8) Epoch 32, batch 3600, loss[loss=0.1474, simple_loss=0.2568, pruned_loss=0.019, over 6435.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2436, pruned_loss=0.02992, over 1429551.74 frames.], batch size: 38, lr: 2.42e-04
+2022-05-15 19:50:24,029 INFO [train.py:812] (1/8) Epoch 32, batch 3650, loss[loss=0.1413, simple_loss=0.2352, pruned_loss=0.02369, over 7239.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2442, pruned_loss=0.02985, over 1429404.50 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:51:24,137 INFO [train.py:812] (1/8) Epoch 32, batch 3700, loss[loss=0.1319, simple_loss=0.2178, pruned_loss=0.023, over 7134.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02949, over 1430782.22 frames.], batch size: 17, lr: 2.42e-04
+2022-05-15 19:52:22,800 INFO [train.py:812] (1/8) Epoch 32, batch 3750, loss[loss=0.1669, simple_loss=0.2654, pruned_loss=0.03415, over 7201.00 frames.], tot_loss[loss=0.1517, simple_loss=0.244, pruned_loss=0.02971, over 1424594.42 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:53:21,632 INFO [train.py:812] (1/8) Epoch 32, batch 3800, loss[loss=0.1553, simple_loss=0.2464, pruned_loss=0.03209, over 7380.00 frames.], tot_loss[loss=0.1527, simple_loss=0.245, pruned_loss=0.03015, over 1425605.90 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:54:19,352 INFO [train.py:812] (1/8) Epoch 32, batch 3850, loss[loss=0.1337, simple_loss=0.2305, pruned_loss=0.01846, over 7432.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03029, over 1427366.41 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:55:27,960 INFO [train.py:812] (1/8) Epoch 32, batch 3900, loss[loss=0.1518, simple_loss=0.2442, pruned_loss=0.02971, over 7161.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2448, pruned_loss=0.03013, over 1429129.36 frames.], batch size: 18, lr: 2.42e-04
+2022-05-15 19:56:25,326 INFO [train.py:812] (1/8) Epoch 32, batch 3950, loss[loss=0.1725, simple_loss=0.2734, pruned_loss=0.03582, over 7229.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2451, pruned_loss=0.03052, over 1424558.88 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 19:57:24,490 INFO [train.py:812] (1/8) Epoch 32, batch 4000, loss[loss=0.1207, simple_loss=0.2077, pruned_loss=0.01685, over 7425.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2447, pruned_loss=0.0305, over 1421799.93 frames.], batch size: 18, lr: 2.42e-04
+2022-05-15 19:58:22,813 INFO [train.py:812] (1/8) Epoch 32, batch 4050, loss[loss=0.1836, simple_loss=0.2809, pruned_loss=0.04318, over 7367.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2453, pruned_loss=0.03078, over 1420050.45 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:59:20,912 INFO [train.py:812] (1/8) Epoch 32, batch 4100, loss[loss=0.185, simple_loss=0.2695, pruned_loss=0.05028, over 7194.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2462, pruned_loss=0.03077, over 1418260.58 frames.], batch size: 22, lr: 2.42e-04
+2022-05-15 20:00:19,819 INFO [train.py:812] (1/8) Epoch 32, batch 4150, loss[loss=0.1718, simple_loss=0.2643, pruned_loss=0.03968, over 7206.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2455, pruned_loss=0.03068, over 1421919.55 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 20:01:19,546 INFO [train.py:812] (1/8) Epoch 32, batch 4200, loss[loss=0.1462, simple_loss=0.2435, pruned_loss=0.02442, over 7332.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.03022, over 1422372.88 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 20:02:17,829 INFO [train.py:812] (1/8) Epoch 32, batch 4250, loss[loss=0.1386, simple_loss=0.2367, pruned_loss=0.02028, over 7245.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2437, pruned_loss=0.03028, over 1421030.73 frames.], batch size: 19, lr: 2.42e-04
+2022-05-15 20:03:17,413 INFO [train.py:812] (1/8) Epoch 32, batch 4300, loss[loss=0.1377, simple_loss=0.2243, pruned_loss=0.02552, over 7404.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2432, pruned_loss=0.02982, over 1420431.64 frames.], batch size: 18, lr: 2.42e-04
+2022-05-15 20:04:16,084 INFO [train.py:812] (1/8) Epoch 32, batch 4350, loss[loss=0.1522, simple_loss=0.2375, pruned_loss=0.03345, over 7165.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2437, pruned_loss=0.03023, over 1420591.44 frames.], batch size: 18, lr: 2.41e-04
+2022-05-15 20:05:14,959 INFO [train.py:812] (1/8) Epoch 32, batch 4400, loss[loss=0.1429, simple_loss=0.2375, pruned_loss=0.0241, over 7307.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2442, pruned_loss=0.0305, over 1406578.34 frames.], batch size: 25, lr: 2.41e-04
+2022-05-15 20:06:12,566 INFO [train.py:812] (1/8) Epoch 32, batch 4450, loss[loss=0.1302, simple_loss=0.2158, pruned_loss=0.02228, over 7245.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2442, pruned_loss=0.03058, over 1403328.08 frames.], batch size: 16, lr: 2.41e-04
+2022-05-15 20:07:11,380 INFO [train.py:812] (1/8) Epoch 32, batch 4500, loss[loss=0.1763, simple_loss=0.2684, pruned_loss=0.04216, over 6720.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2451, pruned_loss=0.03083, over 1394491.72 frames.], batch size: 31, lr: 2.41e-04
+2022-05-15 20:08:09,915 INFO [train.py:812] (1/8) Epoch 32, batch 4550, loss[loss=0.1606, simple_loss=0.2578, pruned_loss=0.03168, over 4859.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2449, pruned_loss=0.03127, over 1355245.76 frames.], batch size: 52, lr: 2.41e-04
+2022-05-15 20:09:17,633 INFO [train.py:812] (1/8) Epoch 33, batch 0, loss[loss=0.1654, simple_loss=0.2636, pruned_loss=0.03365, over 6857.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2636, pruned_loss=0.03365, over 6857.00 frames.], batch size: 31, lr: 2.38e-04
+2022-05-15 20:10:15,652 INFO [train.py:812] (1/8) Epoch 33, batch 50, loss[loss=0.165, simple_loss=0.2479, pruned_loss=0.04105, over 5269.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2443, pruned_loss=0.02938, over 314393.54 frames.], batch size: 53, lr: 2.38e-04
+2022-05-15 20:11:14,518 INFO [train.py:812] (1/8) Epoch 33, batch 100, loss[loss=0.1636, simple_loss=0.2654, pruned_loss=0.03092, over 6335.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2442, pruned_loss=0.02958, over 558614.34 frames.], batch size: 37, lr: 2.38e-04
+2022-05-15 20:12:13,172 INFO [train.py:812] (1/8) Epoch 33, batch 150, loss[loss=0.1639, simple_loss=0.2612, pruned_loss=0.03335, over 7196.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2463, pruned_loss=0.02995, over 751154.24 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:13:12,823 INFO [train.py:812] (1/8) Epoch 33, batch 200, loss[loss=0.1372, simple_loss=0.2194, pruned_loss=0.02749, over 7001.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2454, pruned_loss=0.03024, over 893918.69 frames.], batch size: 16, lr: 2.37e-04
+2022-05-15 20:14:10,208 INFO [train.py:812] (1/8) Epoch 33, batch 250, loss[loss=0.1455, simple_loss=0.2475, pruned_loss=0.02177, over 7232.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2451, pruned_loss=0.02994, over 1009437.21 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:15:08,986 INFO [train.py:812] (1/8) Epoch 33, batch 300, loss[loss=0.1678, simple_loss=0.2716, pruned_loss=0.03201, over 6779.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2467, pruned_loss=0.03077, over 1092865.88 frames.], batch size: 31, lr: 2.37e-04
+2022-05-15 20:16:07,540 INFO [train.py:812] (1/8) Epoch 33, batch 350, loss[loss=0.1327, simple_loss=0.2211, pruned_loss=0.02215, over 7415.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2455, pruned_loss=0.03043, over 1163476.21 frames.], batch size: 18, lr: 2.37e-04
+2022-05-15 20:17:07,052 INFO [train.py:812] (1/8) Epoch 33, batch 400, loss[loss=0.1507, simple_loss=0.2354, pruned_loss=0.03306, over 7430.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2445, pruned_loss=0.03032, over 1221592.53 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:18:06,471 INFO [train.py:812] (1/8) Epoch 33, batch 450, loss[loss=0.1666, simple_loss=0.2642, pruned_loss=0.03456, over 6597.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2436, pruned_loss=0.02994, over 1263647.01 frames.], batch size: 31, lr: 2.37e-04
+2022-05-15 20:19:06,084 INFO [train.py:812] (1/8) Epoch 33, batch 500, loss[loss=0.1949, simple_loss=0.2808, pruned_loss=0.0545, over 7199.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2442, pruned_loss=0.03009, over 1301563.12 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:20:04,291 INFO [train.py:812] (1/8) Epoch 33, batch 550, loss[loss=0.1505, simple_loss=0.2461, pruned_loss=0.02745, over 7320.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2449, pruned_loss=0.03007, over 1330457.89 frames.], batch size: 21, lr: 2.37e-04
+2022-05-15 20:21:03,107 INFO [train.py:812] (1/8) Epoch 33, batch 600, loss[loss=0.1743, simple_loss=0.2621, pruned_loss=0.04324, over 7288.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2452, pruned_loss=0.03059, over 1347842.25 frames.], batch size: 24, lr: 2.37e-04
+2022-05-15 20:22:00,734 INFO [train.py:812] (1/8) Epoch 33, batch 650, loss[loss=0.1493, simple_loss=0.2431, pruned_loss=0.02772, over 7183.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2446, pruned_loss=0.03015, over 1364821.96 frames.], batch size: 26, lr: 2.37e-04
+2022-05-15 20:23:00,272 INFO [train.py:812] (1/8) Epoch 33, batch 700, loss[loss=0.1447, simple_loss=0.2226, pruned_loss=0.03344, over 7147.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2447, pruned_loss=0.03008, over 1374707.48 frames.], batch size: 17, lr: 2.37e-04
+2022-05-15 20:23:58,662 INFO [train.py:812] (1/8) Epoch 33, batch 750, loss[loss=0.1688, simple_loss=0.2698, pruned_loss=0.03395, over 7220.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2444, pruned_loss=0.03014, over 1380563.19 frames.], batch size: 21, lr: 2.37e-04
+2022-05-15 20:24:57,930 INFO [train.py:812] (1/8) Epoch 33, batch 800, loss[loss=0.1666, simple_loss=0.2504, pruned_loss=0.04137, over 7430.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2429, pruned_loss=0.02991, over 1391946.30 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:25:55,917 INFO [train.py:812] (1/8) Epoch 33, batch 850, loss[loss=0.1709, simple_loss=0.2681, pruned_loss=0.03684, over 7392.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02973, over 1399353.82 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:26:54,546 INFO [train.py:812] (1/8) Epoch 33, batch 900, loss[loss=0.1303, simple_loss=0.2237, pruned_loss=0.01845, over 7204.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2421, pruned_loss=0.02944, over 1408707.55 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:27:51,777 INFO [train.py:812] (1/8) Epoch 33, batch 950, loss[loss=0.1419, simple_loss=0.2298, pruned_loss=0.02702, over 7424.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2426, pruned_loss=0.02949, over 1413564.86 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:28:51,357 INFO [train.py:812] (1/8) Epoch 33, batch 1000, loss[loss=0.1535, simple_loss=0.2551, pruned_loss=0.02598, over 7202.00 frames.], tot_loss[loss=0.15, simple_loss=0.2417, pruned_loss=0.02919, over 1413176.60 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:29:49,404 INFO [train.py:812] (1/8) Epoch 33, batch 1050, loss[loss=0.1597, simple_loss=0.263, pruned_loss=0.02825, over 7083.00 frames.], tot_loss[loss=0.151, simple_loss=0.2431, pruned_loss=0.02949, over 1412848.48 frames.], batch size: 28, lr: 2.37e-04
+2022-05-15 20:30:48,560 INFO [train.py:812] (1/8) Epoch 33, batch 1100, loss[loss=0.1528, simple_loss=0.2466, pruned_loss=0.02953, over 7329.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2428, pruned_loss=0.02948, over 1418026.75 frames.], batch size: 24, lr: 2.37e-04
+2022-05-15 20:31:47,040 INFO [train.py:812] (1/8) Epoch 33, batch 1150, loss[loss=0.1517, simple_loss=0.242, pruned_loss=0.03072, over 7214.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2424, pruned_loss=0.02893, over 1418951.71 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:32:51,447 INFO [train.py:812] (1/8) Epoch 33, batch 1200, loss[loss=0.182, simple_loss=0.28, pruned_loss=0.04207, over 7156.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2436, pruned_loss=0.02931, over 1421639.05 frames.], batch size: 26, lr: 2.37e-04
+2022-05-15 20:33:50,443 INFO [train.py:812] (1/8) Epoch 33, batch 1250, loss[loss=0.1554, simple_loss=0.2526, pruned_loss=0.02908, over 6414.00 frames.], tot_loss[loss=0.151, simple_loss=0.2437, pruned_loss=0.02921, over 1421251.54 frames.], batch size: 38, lr: 2.37e-04
+2022-05-15 20:34:50,211 INFO [train.py:812] (1/8) Epoch 33, batch 1300, loss[loss=0.1619, simple_loss=0.2591, pruned_loss=0.03237, over 7224.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2429, pruned_loss=0.02919, over 1421969.80 frames.], batch size: 21, lr: 2.37e-04
+2022-05-15 20:35:49,523 INFO [train.py:812] (1/8) Epoch 33, batch 1350, loss[loss=0.1337, simple_loss=0.2169, pruned_loss=0.02524, over 7297.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02921, over 1420999.08 frames.], batch size: 17, lr: 2.37e-04
+2022-05-15 20:36:48,925 INFO [train.py:812] (1/8) Epoch 33, batch 1400, loss[loss=0.1706, simple_loss=0.2682, pruned_loss=0.03651, over 7144.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2428, pruned_loss=0.0295, over 1422031.31 frames.], batch size: 20, lr: 2.36e-04
+2022-05-15 20:37:47,494 INFO [train.py:812] (1/8) Epoch 33, batch 1450, loss[loss=0.1431, simple_loss=0.2443, pruned_loss=0.02096, over 6809.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2427, pruned_loss=0.02945, over 1425242.23 frames.], batch size: 31, lr: 2.36e-04
+2022-05-15 20:38:46,318 INFO [train.py:812] (1/8) Epoch 33, batch 1500, loss[loss=0.1646, simple_loss=0.2535, pruned_loss=0.03782, over 4962.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2437, pruned_loss=0.03001, over 1422434.59 frames.], batch size: 52, lr: 2.36e-04
+2022-05-15 20:39:44,936 INFO [train.py:812] (1/8) Epoch 33, batch 1550, loss[loss=0.1532, simple_loss=0.2572, pruned_loss=0.02461, over 7223.00 frames.], tot_loss[loss=0.152, simple_loss=0.244, pruned_loss=0.03001, over 1418175.59 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:40:43,840 INFO [train.py:812] (1/8) Epoch 33, batch 1600, loss[loss=0.1493, simple_loss=0.2414, pruned_loss=0.02862, over 7415.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2437, pruned_loss=0.03001, over 1420661.20 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:41:42,719 INFO [train.py:812] (1/8) Epoch 33, batch 1650, loss[loss=0.1518, simple_loss=0.2428, pruned_loss=0.03042, over 7222.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2439, pruned_loss=0.0302, over 1421681.65 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:42:41,747 INFO [train.py:812] (1/8) Epoch 33, batch 1700, loss[loss=0.1429, simple_loss=0.2411, pruned_loss=0.02231, over 7265.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02968, over 1424364.86 frames.], batch size: 24, lr: 2.36e-04
+2022-05-15 20:43:40,825 INFO [train.py:812] (1/8) Epoch 33, batch 1750, loss[loss=0.1494, simple_loss=0.2464, pruned_loss=0.0262, over 7030.00 frames.], tot_loss[loss=0.1526, simple_loss=0.245, pruned_loss=0.03006, over 1417026.01 frames.], batch size: 28, lr: 2.36e-04
+2022-05-15 20:44:40,001 INFO [train.py:812] (1/8) Epoch 33, batch 1800, loss[loss=0.1319, simple_loss=0.2215, pruned_loss=0.02111, over 7254.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2441, pruned_loss=0.02983, over 1420053.21 frames.], batch size: 19, lr: 2.36e-04
+2022-05-15 20:45:38,879 INFO [train.py:812] (1/8) Epoch 33, batch 1850, loss[loss=0.1417, simple_loss=0.2386, pruned_loss=0.02244, over 7319.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2443, pruned_loss=0.0301, over 1423229.36 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:46:37,342 INFO [train.py:812] (1/8) Epoch 33, batch 1900, loss[loss=0.1926, simple_loss=0.2883, pruned_loss=0.04846, over 7375.00 frames.], tot_loss[loss=0.152, simple_loss=0.244, pruned_loss=0.03005, over 1425747.02 frames.], batch size: 23, lr: 2.36e-04
+2022-05-15 20:47:35,891 INFO [train.py:812] (1/8) Epoch 33, batch 1950, loss[loss=0.1575, simple_loss=0.2483, pruned_loss=0.03335, over 7290.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2439, pruned_loss=0.03024, over 1424047.70 frames.], batch size: 24, lr: 2.36e-04
+2022-05-15 20:48:34,902 INFO [train.py:812] (1/8) Epoch 33, batch 2000, loss[loss=0.151, simple_loss=0.2515, pruned_loss=0.02525, over 6548.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2438, pruned_loss=0.03039, over 1425586.23 frames.], batch size: 38, lr: 2.36e-04
+2022-05-15 20:49:32,711 INFO [train.py:812] (1/8) Epoch 33, batch 2050, loss[loss=0.1426, simple_loss=0.2281, pruned_loss=0.02859, over 7159.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2439, pruned_loss=0.03047, over 1426044.94 frames.], batch size: 18, lr: 2.36e-04
+2022-05-15 20:50:32,326 INFO [train.py:812] (1/8) Epoch 33, batch 2100, loss[loss=0.1306, simple_loss=0.2216, pruned_loss=0.01976, over 7165.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2438, pruned_loss=0.03063, over 1428002.05 frames.], batch size: 19, lr: 2.36e-04
+2022-05-15 20:51:30,239 INFO [train.py:812] (1/8) Epoch 33, batch 2150, loss[loss=0.1506, simple_loss=0.2285, pruned_loss=0.03637, over 7425.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2439, pruned_loss=0.03049, over 1429092.22 frames.], batch size: 18, lr: 2.36e-04
+2022-05-15 20:52:28,388 INFO [train.py:812] (1/8) Epoch 33, batch 2200, loss[loss=0.184, simple_loss=0.2817, pruned_loss=0.0432, over 5306.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.03068, over 1423718.52 frames.], batch size: 52, lr: 2.36e-04
+2022-05-15 20:53:26,615 INFO [train.py:812] (1/8) Epoch 33, batch 2250, loss[loss=0.1713, simple_loss=0.2634, pruned_loss=0.03955, over 7210.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2443, pruned_loss=0.0306, over 1420980.30 frames.], batch size: 26, lr: 2.36e-04
+2022-05-15 20:54:25,517 INFO [train.py:812] (1/8) Epoch 33, batch 2300, loss[loss=0.1789, simple_loss=0.264, pruned_loss=0.04691, over 7193.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2438, pruned_loss=0.03045, over 1419369.00 frames.], batch size: 22, lr: 2.36e-04
+2022-05-15 20:55:24,370 INFO [train.py:812] (1/8) Epoch 33, batch 2350, loss[loss=0.1321, simple_loss=0.215, pruned_loss=0.02454, over 6808.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2426, pruned_loss=0.0298, over 1421976.14 frames.], batch size: 15, lr: 2.36e-04
+2022-05-15 20:56:22,964 INFO [train.py:812] (1/8) Epoch 33, batch 2400, loss[loss=0.1694, simple_loss=0.2587, pruned_loss=0.04003, over 7420.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2423, pruned_loss=0.02965, over 1423486.10 frames.], batch size: 20, lr: 2.36e-04
+2022-05-15 20:57:40,441 INFO [train.py:812] (1/8) Epoch 33, batch 2450, loss[loss=0.1339, simple_loss=0.2295, pruned_loss=0.01909, over 7250.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2427, pruned_loss=0.02986, over 1425729.30 frames.], batch size: 19, lr: 2.36e-04
+2022-05-15 20:58:40,011 INFO [train.py:812] (1/8) Epoch 33, batch 2500, loss[loss=0.1731, simple_loss=0.2608, pruned_loss=0.04267, over 7325.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2432, pruned_loss=0.02974, over 1427120.22 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:59:48,287 INFO [train.py:812] (1/8) Epoch 33, batch 2550, loss[loss=0.1479, simple_loss=0.2373, pruned_loss=0.02921, over 7378.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2431, pruned_loss=0.02981, over 1427360.79 frames.], batch size: 23, lr: 2.36e-04
+2022-05-15 21:00:46,741 INFO [train.py:812] (1/8) Epoch 33, batch 2600, loss[loss=0.1761, simple_loss=0.2784, pruned_loss=0.03688, over 7195.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2436, pruned_loss=0.02994, over 1427949.46 frames.], batch size: 23, lr: 2.36e-04
+2022-05-15 21:01:44,973 INFO [train.py:812] (1/8) Epoch 33, batch 2650, loss[loss=0.1438, simple_loss=0.2237, pruned_loss=0.03196, over 6787.00 frames.], tot_loss[loss=0.152, simple_loss=0.2442, pruned_loss=0.02996, over 1423203.89 frames.], batch size: 15, lr: 2.35e-04
+2022-05-15 21:02:52,791 INFO [train.py:812] (1/8) Epoch 33, batch 2700, loss[loss=0.1378, simple_loss=0.2352, pruned_loss=0.02021, over 7431.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2439, pruned_loss=0.02985, over 1424845.95 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:04:10,603 INFO [train.py:812] (1/8) Epoch 33, batch 2750, loss[loss=0.1376, simple_loss=0.225, pruned_loss=0.02516, over 7276.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2433, pruned_loss=0.02961, over 1425834.53 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:05:09,522 INFO [train.py:812] (1/8) Epoch 33, batch 2800, loss[loss=0.1578, simple_loss=0.2573, pruned_loss=0.02912, over 7204.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02936, over 1425136.86 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:06:07,222 INFO [train.py:812] (1/8) Epoch 33, batch 2850, loss[loss=0.1583, simple_loss=0.2588, pruned_loss=0.02887, over 7330.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.02922, over 1426146.69 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:07:06,363 INFO [train.py:812] (1/8) Epoch 33, batch 2900, loss[loss=0.1671, simple_loss=0.2589, pruned_loss=0.0376, over 7281.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02946, over 1425386.57 frames.], batch size: 25, lr: 2.35e-04
+2022-05-15 21:08:04,498 INFO [train.py:812] (1/8) Epoch 33, batch 2950, loss[loss=0.1362, simple_loss=0.2246, pruned_loss=0.02388, over 7435.00 frames.], tot_loss[loss=0.151, simple_loss=0.2434, pruned_loss=0.02927, over 1427689.13 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:09:12,196 INFO [train.py:812] (1/8) Epoch 33, batch 3000, loss[loss=0.1353, simple_loss=0.2321, pruned_loss=0.01928, over 7058.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2431, pruned_loss=0.02907, over 1426531.14 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:09:12,197 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 21:09:19,691 INFO [train.py:841] (1/8) Epoch 33, validation: loss=0.1535, simple_loss=0.2493, pruned_loss=0.02886, over 698248.00 frames.
+2022-05-15 21:10:18,076 INFO [train.py:812] (1/8) Epoch 33, batch 3050, loss[loss=0.1535, simple_loss=0.2511, pruned_loss=0.02791, over 6271.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2427, pruned_loss=0.02902, over 1422965.52 frames.], batch size: 37, lr: 2.35e-04
+2022-05-15 21:11:15,928 INFO [train.py:812] (1/8) Epoch 33, batch 3100, loss[loss=0.1544, simple_loss=0.2409, pruned_loss=0.03395, over 7384.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02904, over 1424064.03 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:12:14,893 INFO [train.py:812] (1/8) Epoch 33, batch 3150, loss[loss=0.1404, simple_loss=0.2268, pruned_loss=0.02701, over 7459.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.02892, over 1421876.14 frames.], batch size: 19, lr: 2.35e-04
+2022-05-15 21:13:13,027 INFO [train.py:812] (1/8) Epoch 33, batch 3200, loss[loss=0.1355, simple_loss=0.2178, pruned_loss=0.02664, over 6813.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.02936, over 1421428.26 frames.], batch size: 15, lr: 2.35e-04
+2022-05-15 21:14:11,714 INFO [train.py:812] (1/8) Epoch 33, batch 3250, loss[loss=0.1218, simple_loss=0.2096, pruned_loss=0.01704, over 7290.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2427, pruned_loss=0.0295, over 1418507.47 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:15:11,680 INFO [train.py:812] (1/8) Epoch 33, batch 3300, loss[loss=0.1688, simple_loss=0.2622, pruned_loss=0.03766, over 7236.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2424, pruned_loss=0.02957, over 1424232.30 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:16:10,458 INFO [train.py:812] (1/8) Epoch 33, batch 3350, loss[loss=0.139, simple_loss=0.2385, pruned_loss=0.01972, over 7325.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2427, pruned_loss=0.02942, over 1427927.69 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:17:09,953 INFO [train.py:812] (1/8) Epoch 33, batch 3400, loss[loss=0.1507, simple_loss=0.2301, pruned_loss=0.03568, over 7273.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.0294, over 1427866.59 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:18:09,758 INFO [train.py:812] (1/8) Epoch 33, batch 3450, loss[loss=0.1493, simple_loss=0.2394, pruned_loss=0.02961, over 7332.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02956, over 1431142.09 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:19:07,580 INFO [train.py:812] (1/8) Epoch 33, batch 3500, loss[loss=0.1654, simple_loss=0.2539, pruned_loss=0.03848, over 7387.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2446, pruned_loss=0.02976, over 1427840.20 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:20:05,732 INFO [train.py:812] (1/8) Epoch 33, batch 3550, loss[loss=0.1386, simple_loss=0.2231, pruned_loss=0.02704, over 7409.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2445, pruned_loss=0.02989, over 1426253.83 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:21:04,475 INFO [train.py:812] (1/8) Epoch 33, batch 3600, loss[loss=0.1394, simple_loss=0.2303, pruned_loss=0.02422, over 7314.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2447, pruned_loss=0.02984, over 1424203.40 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:22:03,599 INFO [train.py:812] (1/8) Epoch 33, batch 3650, loss[loss=0.1457, simple_loss=0.236, pruned_loss=0.02769, over 7325.00 frames.], tot_loss[loss=0.1515, simple_loss=0.244, pruned_loss=0.02951, over 1423093.47 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:23:02,537 INFO [train.py:812] (1/8) Epoch 33, batch 3700, loss[loss=0.125, simple_loss=0.2097, pruned_loss=0.02014, over 7281.00 frames.], tot_loss[loss=0.1524, simple_loss=0.245, pruned_loss=0.02987, over 1426350.12 frames.], batch size: 17, lr: 2.35e-04
+2022-05-15 21:24:01,175 INFO [train.py:812] (1/8) Epoch 33, batch 3750, loss[loss=0.16, simple_loss=0.2524, pruned_loss=0.03378, over 7225.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2445, pruned_loss=0.03, over 1426627.37 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:25:00,734 INFO [train.py:812] (1/8) Epoch 33, batch 3800, loss[loss=0.1467, simple_loss=0.2376, pruned_loss=0.02791, over 7195.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02971, over 1427061.57 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:25:58,513 INFO [train.py:812] (1/8) Epoch 33, batch 3850, loss[loss=0.1562, simple_loss=0.2564, pruned_loss=0.02796, over 7311.00 frames.], tot_loss[loss=0.151, simple_loss=0.2431, pruned_loss=0.02942, over 1428266.51 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:26:57,078 INFO [train.py:812] (1/8) Epoch 33, batch 3900, loss[loss=0.1342, simple_loss=0.226, pruned_loss=0.02121, over 6827.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2443, pruned_loss=0.03003, over 1428699.98 frames.], batch size: 15, lr: 2.35e-04
+2022-05-15 21:27:55,703 INFO [train.py:812] (1/8) Epoch 33, batch 3950, loss[loss=0.1299, simple_loss=0.2205, pruned_loss=0.01961, over 7404.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2457, pruned_loss=0.0306, over 1431589.84 frames.], batch size: 18, lr: 2.34e-04
+2022-05-15 21:28:55,479 INFO [train.py:812] (1/8) Epoch 33, batch 4000, loss[loss=0.1677, simple_loss=0.2591, pruned_loss=0.03814, over 6258.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2446, pruned_loss=0.02997, over 1432223.03 frames.], batch size: 37, lr: 2.34e-04
+2022-05-15 21:29:54,326 INFO [train.py:812] (1/8) Epoch 33, batch 4050, loss[loss=0.1282, simple_loss=0.2068, pruned_loss=0.02478, over 7276.00 frames.], tot_loss[loss=0.1517, simple_loss=0.244, pruned_loss=0.02971, over 1428041.38 frames.], batch size: 18, lr: 2.34e-04
+2022-05-15 21:30:52,668 INFO [train.py:812] (1/8) Epoch 33, batch 4100, loss[loss=0.1681, simple_loss=0.2654, pruned_loss=0.03546, over 7161.00 frames.], tot_loss[loss=0.152, simple_loss=0.2441, pruned_loss=0.02999, over 1422501.21 frames.], batch size: 26, lr: 2.34e-04
+2022-05-15 21:31:50,551 INFO [train.py:812] (1/8) Epoch 33, batch 4150, loss[loss=0.1388, simple_loss=0.2237, pruned_loss=0.02696, over 7240.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2439, pruned_loss=0.02955, over 1422466.91 frames.], batch size: 16, lr: 2.34e-04
+2022-05-15 21:32:49,110 INFO [train.py:812] (1/8) Epoch 33, batch 4200, loss[loss=0.1489, simple_loss=0.249, pruned_loss=0.02443, over 7261.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02928, over 1420715.87 frames.], batch size: 19, lr: 2.34e-04
+2022-05-15 21:33:48,275 INFO [train.py:812] (1/8) Epoch 33, batch 4250, loss[loss=0.1486, simple_loss=0.2359, pruned_loss=0.03059, over 7427.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2427, pruned_loss=0.02935, over 1421545.89 frames.], batch size: 20, lr: 2.34e-04
+2022-05-15 21:34:46,556 INFO [train.py:812] (1/8) Epoch 33, batch 4300, loss[loss=0.1708, simple_loss=0.2681, pruned_loss=0.03675, over 6759.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2437, pruned_loss=0.02946, over 1419344.09 frames.], batch size: 31, lr: 2.34e-04
+2022-05-15 21:35:44,808 INFO [train.py:812] (1/8) Epoch 33, batch 4350, loss[loss=0.137, simple_loss=0.2273, pruned_loss=0.02328, over 7216.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.02899, over 1414628.88 frames.], batch size: 21, lr: 2.34e-04
+2022-05-15 21:36:43,618 INFO [train.py:812] (1/8) Epoch 33, batch 4400, loss[loss=0.1513, simple_loss=0.2556, pruned_loss=0.02351, over 7150.00 frames.], tot_loss[loss=0.1497, simple_loss=0.242, pruned_loss=0.02865, over 1414370.06 frames.], batch size: 20, lr: 2.34e-04
+2022-05-15 21:37:42,036 INFO [train.py:812] (1/8) Epoch 33, batch 4450, loss[loss=0.1534, simple_loss=0.2513, pruned_loss=0.02776, over 7344.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2425, pruned_loss=0.02885, over 1408331.12 frames.], batch size: 22, lr: 2.34e-04
+2022-05-15 21:38:41,153 INFO [train.py:812] (1/8) Epoch 33, batch 4500, loss[loss=0.1383, simple_loss=0.2304, pruned_loss=0.02316, over 7155.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.0293, over 1397358.84 frames.], batch size: 20, lr: 2.34e-04
+2022-05-15 21:39:39,845 INFO [train.py:812] (1/8) Epoch 33, batch 4550, loss[loss=0.161, simple_loss=0.2461, pruned_loss=0.03798, over 5061.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02955, over 1375338.57 frames.], batch size: 52, lr: 2.34e-04
+2022-05-15 21:40:52,125 INFO [train.py:812] (1/8) Epoch 34, batch 0, loss[loss=0.1797, simple_loss=0.2707, pruned_loss=0.04434, over 7438.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2707, pruned_loss=0.04434, over 7438.00 frames.], batch size: 20, lr: 2.31e-04
+2022-05-15 21:41:51,335 INFO [train.py:812] (1/8) Epoch 34, batch 50, loss[loss=0.148, simple_loss=0.2408, pruned_loss=0.02763, over 7059.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2382, pruned_loss=0.02731, over 324506.92 frames.], batch size: 28, lr: 2.30e-04
+2022-05-15 21:42:51,066 INFO [train.py:812] (1/8) Epoch 34, batch 100, loss[loss=0.1712, simple_loss=0.2759, pruned_loss=0.03325, over 7116.00 frames.], tot_loss[loss=0.151, simple_loss=0.2429, pruned_loss=0.02959, over 565986.78 frames.], batch size: 21, lr: 2.30e-04
+2022-05-15 21:43:50,308 INFO [train.py:812] (1/8) Epoch 34, batch 150, loss[loss=0.1355, simple_loss=0.2212, pruned_loss=0.02486, over 7074.00 frames.], tot_loss[loss=0.152, simple_loss=0.2429, pruned_loss=0.03054, over 756559.23 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:44:49,635 INFO [train.py:812] (1/8) Epoch 34, batch 200, loss[loss=0.1735, simple_loss=0.25, pruned_loss=0.0485, over 7284.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2423, pruned_loss=0.02994, over 906532.38 frames.], batch size: 17, lr: 2.30e-04
+2022-05-15 21:45:48,781 INFO [train.py:812] (1/8) Epoch 34, batch 250, loss[loss=0.1758, simple_loss=0.2608, pruned_loss=0.04536, over 5178.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2415, pruned_loss=0.02985, over 1013783.12 frames.], batch size: 52, lr: 2.30e-04
+2022-05-15 21:46:48,757 INFO [train.py:812] (1/8) Epoch 34, batch 300, loss[loss=0.2022, simple_loss=0.2799, pruned_loss=0.06223, over 7379.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2426, pruned_loss=0.03039, over 1103773.06 frames.], batch size: 23, lr: 2.30e-04
+2022-05-15 21:47:46,235 INFO [train.py:812] (1/8) Epoch 34, batch 350, loss[loss=0.1311, simple_loss=0.2126, pruned_loss=0.0248, over 7132.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2442, pruned_loss=0.03066, over 1168287.20 frames.], batch size: 17, lr: 2.30e-04
+2022-05-15 21:48:46,234 INFO [train.py:812] (1/8) Epoch 34, batch 400, loss[loss=0.1843, simple_loss=0.2782, pruned_loss=0.04517, over 7410.00 frames.], tot_loss[loss=0.152, simple_loss=0.2434, pruned_loss=0.03024, over 1229750.02 frames.], batch size: 21, lr: 2.30e-04
+2022-05-15 21:49:44,745 INFO [train.py:812] (1/8) Epoch 34, batch 450, loss[loss=0.1345, simple_loss=0.2181, pruned_loss=0.02548, over 7420.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2436, pruned_loss=0.03001, over 1274673.12 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:50:44,153 INFO [train.py:812] (1/8) Epoch 34, batch 500, loss[loss=0.1738, simple_loss=0.266, pruned_loss=0.04082, over 7286.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2447, pruned_loss=0.03036, over 1306170.23 frames.], batch size: 24, lr: 2.30e-04
+2022-05-15 21:51:42,509 INFO [train.py:812] (1/8) Epoch 34, batch 550, loss[loss=0.1622, simple_loss=0.267, pruned_loss=0.02871, over 6379.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.03003, over 1329908.67 frames.], batch size: 38, lr: 2.30e-04
+2022-05-15 21:52:57,377 INFO [train.py:812] (1/8) Epoch 34, batch 600, loss[loss=0.1742, simple_loss=0.2778, pruned_loss=0.03532, over 7289.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02955, over 1352461.18 frames.], batch size: 25, lr: 2.30e-04
+2022-05-15 21:53:55,931 INFO [train.py:812] (1/8) Epoch 34, batch 650, loss[loss=0.1423, simple_loss=0.2296, pruned_loss=0.0275, over 7157.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2445, pruned_loss=0.02971, over 1371044.38 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:54:54,859 INFO [train.py:812] (1/8) Epoch 34, batch 700, loss[loss=0.1317, simple_loss=0.2167, pruned_loss=0.02337, over 7135.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2432, pruned_loss=0.02966, over 1377718.83 frames.], batch size: 17, lr: 2.30e-04
+2022-05-15 21:55:51,390 INFO [train.py:812] (1/8) Epoch 34, batch 750, loss[loss=0.1612, simple_loss=0.2593, pruned_loss=0.03158, over 7199.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2439, pruned_loss=0.02981, over 1388998.41 frames.], batch size: 23, lr: 2.30e-04
+2022-05-15 21:56:50,468 INFO [train.py:812] (1/8) Epoch 34, batch 800, loss[loss=0.1279, simple_loss=0.2173, pruned_loss=0.01926, over 7279.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2441, pruned_loss=0.02977, over 1394969.37 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:57:49,847 INFO [train.py:812] (1/8) Epoch 34, batch 850, loss[loss=0.1483, simple_loss=0.242, pruned_loss=0.02734, over 6576.00 frames.], tot_loss[loss=0.1516, simple_loss=0.244, pruned_loss=0.02958, over 1405025.78 frames.], batch size: 38, lr: 2.30e-04
+2022-05-15 21:58:48,165 INFO [train.py:812] (1/8) Epoch 34, batch 900, loss[loss=0.1982, simple_loss=0.2863, pruned_loss=0.05506, over 4965.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2435, pruned_loss=0.02934, over 1410124.40 frames.], batch size: 52, lr: 2.30e-04
+2022-05-15 21:59:45,323 INFO [train.py:812] (1/8) Epoch 34, batch 950, loss[loss=0.136, simple_loss=0.2227, pruned_loss=0.02468, over 7289.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2434, pruned_loss=0.02953, over 1407865.32 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 22:00:43,719 INFO [train.py:812] (1/8) Epoch 34, batch 1000, loss[loss=0.1393, simple_loss=0.2416, pruned_loss=0.01845, over 7440.00 frames.], tot_loss[loss=0.151, simple_loss=0.243, pruned_loss=0.02949, over 1408769.18 frames.], batch size: 20, lr: 2.30e-04
+2022-05-15 22:01:41,765 INFO [train.py:812] (1/8) Epoch 34, batch 1050, loss[loss=0.1353, simple_loss=0.228, pruned_loss=0.02123, over 7162.00 frames.], tot_loss[loss=0.151, simple_loss=0.2431, pruned_loss=0.02943, over 1414865.87 frames.], batch size: 19, lr: 2.30e-04
+2022-05-15 22:02:40,795 INFO [train.py:812] (1/8) Epoch 34, batch 1100, loss[loss=0.1517, simple_loss=0.2463, pruned_loss=0.02857, over 6305.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02917, over 1412928.79 frames.], batch size: 37, lr: 2.30e-04
+2022-05-15 22:03:39,414 INFO [train.py:812] (1/8) Epoch 34, batch 1150, loss[loss=0.1494, simple_loss=0.2426, pruned_loss=0.02813, over 7438.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.02891, over 1415890.02 frames.], batch size: 20, lr: 2.30e-04
+2022-05-15 22:04:38,149 INFO [train.py:812] (1/8) Epoch 34, batch 1200, loss[loss=0.1588, simple_loss=0.2495, pruned_loss=0.03405, over 7210.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2425, pruned_loss=0.02917, over 1420414.26 frames.], batch size: 23, lr: 2.30e-04
+2022-05-15 22:05:35,709 INFO [train.py:812] (1/8) Epoch 34, batch 1250, loss[loss=0.1491, simple_loss=0.2496, pruned_loss=0.02424, over 7328.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2426, pruned_loss=0.0292, over 1418727.60 frames.], batch size: 22, lr: 2.30e-04
+2022-05-15 22:06:34,730 INFO [train.py:812] (1/8) Epoch 34, batch 1300, loss[loss=0.1497, simple_loss=0.2515, pruned_loss=0.02396, over 7262.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2422, pruned_loss=0.02932, over 1417911.13 frames.], batch size: 26, lr: 2.30e-04
+2022-05-15 22:07:33,165 INFO [train.py:812] (1/8) Epoch 34, batch 1350, loss[loss=0.1464, simple_loss=0.2461, pruned_loss=0.02329, over 7223.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2419, pruned_loss=0.02914, over 1419809.65 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:08:32,141 INFO [train.py:812] (1/8) Epoch 34, batch 1400, loss[loss=0.1482, simple_loss=0.2407, pruned_loss=0.02784, over 7253.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2408, pruned_loss=0.02871, over 1422362.67 frames.], batch size: 19, lr: 2.29e-04
+2022-05-15 22:09:31,090 INFO [train.py:812] (1/8) Epoch 34, batch 1450, loss[loss=0.1506, simple_loss=0.2485, pruned_loss=0.0263, over 7409.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2411, pruned_loss=0.02857, over 1425913.29 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:10:29,318 INFO [train.py:812] (1/8) Epoch 34, batch 1500, loss[loss=0.1679, simple_loss=0.2625, pruned_loss=0.03658, over 7366.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2427, pruned_loss=0.02905, over 1424336.06 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:11:28,514 INFO [train.py:812] (1/8) Epoch 34, batch 1550, loss[loss=0.1396, simple_loss=0.2315, pruned_loss=0.02385, over 7300.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2428, pruned_loss=0.02937, over 1422263.39 frames.], batch size: 24, lr: 2.29e-04
+2022-05-15 22:12:27,927 INFO [train.py:812] (1/8) Epoch 34, batch 1600, loss[loss=0.13, simple_loss=0.2275, pruned_loss=0.01619, over 7314.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2434, pruned_loss=0.02923, over 1423940.01 frames.], batch size: 20, lr: 2.29e-04
+2022-05-15 22:13:26,012 INFO [train.py:812] (1/8) Epoch 34, batch 1650, loss[loss=0.1459, simple_loss=0.239, pruned_loss=0.02641, over 7215.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02951, over 1423615.51 frames.], batch size: 22, lr: 2.29e-04
+2022-05-15 22:14:25,166 INFO [train.py:812] (1/8) Epoch 34, batch 1700, loss[loss=0.1619, simple_loss=0.2627, pruned_loss=0.03055, over 7375.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2444, pruned_loss=0.02961, over 1427142.37 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:15:24,022 INFO [train.py:812] (1/8) Epoch 34, batch 1750, loss[loss=0.166, simple_loss=0.2558, pruned_loss=0.03816, over 7104.00 frames.], tot_loss[loss=0.1524, simple_loss=0.245, pruned_loss=0.02991, over 1422368.51 frames.], batch size: 28, lr: 2.29e-04
+2022-05-15 22:16:22,627 INFO [train.py:812] (1/8) Epoch 34, batch 1800, loss[loss=0.1223, simple_loss=0.2062, pruned_loss=0.01925, over 7278.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2443, pruned_loss=0.02965, over 1423198.96 frames.], batch size: 17, lr: 2.29e-04
+2022-05-15 22:17:21,610 INFO [train.py:812] (1/8) Epoch 34, batch 1850, loss[loss=0.1659, simple_loss=0.2723, pruned_loss=0.02978, over 7333.00 frames.], tot_loss[loss=0.1519, simple_loss=0.244, pruned_loss=0.02986, over 1414607.06 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:18:20,754 INFO [train.py:812] (1/8) Epoch 34, batch 1900, loss[loss=0.1462, simple_loss=0.2374, pruned_loss=0.02752, over 6774.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2442, pruned_loss=0.02974, over 1410043.08 frames.], batch size: 31, lr: 2.29e-04
+2022-05-15 22:19:17,932 INFO [train.py:812] (1/8) Epoch 34, batch 1950, loss[loss=0.1468, simple_loss=0.2284, pruned_loss=0.03263, over 6976.00 frames.], tot_loss[loss=0.152, simple_loss=0.2441, pruned_loss=0.02994, over 1416109.79 frames.], batch size: 16, lr: 2.29e-04
+2022-05-15 22:20:16,780 INFO [train.py:812] (1/8) Epoch 34, batch 2000, loss[loss=0.148, simple_loss=0.2369, pruned_loss=0.02957, over 7397.00 frames.], tot_loss[loss=0.152, simple_loss=0.2441, pruned_loss=0.02993, over 1420970.82 frames.], batch size: 18, lr: 2.29e-04
+2022-05-15 22:21:15,729 INFO [train.py:812] (1/8) Epoch 34, batch 2050, loss[loss=0.1619, simple_loss=0.2568, pruned_loss=0.03347, over 7147.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02951, over 1420662.88 frames.], batch size: 26, lr: 2.29e-04
+2022-05-15 22:22:14,733 INFO [train.py:812] (1/8) Epoch 34, batch 2100, loss[loss=0.1524, simple_loss=0.2434, pruned_loss=0.03073, over 7182.00 frames.], tot_loss[loss=0.152, simple_loss=0.2443, pruned_loss=0.02984, over 1423919.64 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:23:12,293 INFO [train.py:812] (1/8) Epoch 34, batch 2150, loss[loss=0.156, simple_loss=0.2558, pruned_loss=0.02813, over 7290.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2435, pruned_loss=0.02973, over 1423704.84 frames.], batch size: 24, lr: 2.29e-04
+2022-05-15 22:24:11,549 INFO [train.py:812] (1/8) Epoch 34, batch 2200, loss[loss=0.1386, simple_loss=0.2381, pruned_loss=0.0195, over 7316.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2444, pruned_loss=0.02969, over 1426599.91 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:25:10,883 INFO [train.py:812] (1/8) Epoch 34, batch 2250, loss[loss=0.13, simple_loss=0.2122, pruned_loss=0.02385, over 7278.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.02994, over 1422447.15 frames.], batch size: 18, lr: 2.29e-04
+2022-05-15 22:26:09,579 INFO [train.py:812] (1/8) Epoch 34, batch 2300, loss[loss=0.1282, simple_loss=0.22, pruned_loss=0.01823, over 7154.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2451, pruned_loss=0.03006, over 1423322.03 frames.], batch size: 19, lr: 2.29e-04
+2022-05-15 22:27:07,999 INFO [train.py:812] (1/8) Epoch 34, batch 2350, loss[loss=0.1576, simple_loss=0.2407, pruned_loss=0.03726, over 7153.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02947, over 1424423.38 frames.], batch size: 19, lr: 2.29e-04
+2022-05-15 22:28:06,469 INFO [train.py:812] (1/8) Epoch 34, batch 2400, loss[loss=0.1566, simple_loss=0.2506, pruned_loss=0.03133, over 7380.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2427, pruned_loss=0.02943, over 1425286.64 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:29:04,650 INFO [train.py:812] (1/8) Epoch 34, batch 2450, loss[loss=0.1547, simple_loss=0.2568, pruned_loss=0.02625, over 7226.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2434, pruned_loss=0.02959, over 1419172.35 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:30:04,442 INFO [train.py:812] (1/8) Epoch 34, batch 2500, loss[loss=0.1377, simple_loss=0.2304, pruned_loss=0.02251, over 6997.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2436, pruned_loss=0.02952, over 1417672.87 frames.], batch size: 16, lr: 2.29e-04
+2022-05-15 22:31:02,269 INFO [train.py:812] (1/8) Epoch 34, batch 2550, loss[loss=0.1656, simple_loss=0.2619, pruned_loss=0.03468, over 7331.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2434, pruned_loss=0.02959, over 1419462.10 frames.], batch size: 22, lr: 2.29e-04
+2022-05-15 22:32:00,051 INFO [train.py:812] (1/8) Epoch 34, batch 2600, loss[loss=0.1497, simple_loss=0.238, pruned_loss=0.0307, over 7070.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02972, over 1419215.08 frames.], batch size: 18, lr: 2.29e-04
+2022-05-15 22:32:58,089 INFO [train.py:812] (1/8) Epoch 34, batch 2650, loss[loss=0.1572, simple_loss=0.2426, pruned_loss=0.0359, over 7345.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.02922, over 1420439.38 frames.], batch size: 22, lr: 2.29e-04
+2022-05-15 22:33:56,979 INFO [train.py:812] (1/8) Epoch 34, batch 2700, loss[loss=0.1281, simple_loss=0.2117, pruned_loss=0.02219, over 7291.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.02939, over 1425115.97 frames.], batch size: 18, lr: 2.28e-04
+2022-05-15 22:34:55,317 INFO [train.py:812] (1/8) Epoch 34, batch 2750, loss[loss=0.1684, simple_loss=0.2634, pruned_loss=0.03668, over 7311.00 frames.], tot_loss[loss=0.151, simple_loss=0.2429, pruned_loss=0.02959, over 1424138.93 frames.], batch size: 21, lr: 2.28e-04
+2022-05-15 22:35:54,067 INFO [train.py:812] (1/8) Epoch 34, batch 2800, loss[loss=0.1161, simple_loss=0.198, pruned_loss=0.01712, over 7400.00 frames.], tot_loss[loss=0.151, simple_loss=0.2433, pruned_loss=0.02934, over 1429156.15 frames.], batch size: 18, lr: 2.28e-04
+2022-05-15 22:36:52,776 INFO [train.py:812] (1/8) Epoch 34, batch 2850, loss[loss=0.1713, simple_loss=0.2681, pruned_loss=0.03725, over 7204.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2434, pruned_loss=0.02914, over 1429986.23 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:37:50,503 INFO [train.py:812] (1/8) Epoch 34, batch 2900, loss[loss=0.1366, simple_loss=0.231, pruned_loss=0.02108, over 7145.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2427, pruned_loss=0.02891, over 1426470.77 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:38:49,634 INFO [train.py:812] (1/8) Epoch 34, batch 2950, loss[loss=0.1365, simple_loss=0.2323, pruned_loss=0.02036, over 7142.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2417, pruned_loss=0.02888, over 1426553.88 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:39:49,335 INFO [train.py:812] (1/8) Epoch 34, batch 3000, loss[loss=0.1606, simple_loss=0.2552, pruned_loss=0.03299, over 7363.00 frames.], tot_loss[loss=0.1503, simple_loss=0.242, pruned_loss=0.02924, over 1426675.52 frames.], batch size: 19, lr: 2.28e-04
+2022-05-15 22:39:49,336 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-15 22:39:56,839 INFO [train.py:841] (1/8) Epoch 34, validation: loss=0.1534, simple_loss=0.2492, pruned_loss=0.02878, over 698248.00 frames.
+2022-05-15 22:40:55,233 INFO [train.py:812] (1/8) Epoch 34, batch 3050, loss[loss=0.1514, simple_loss=0.2479, pruned_loss=0.0274, over 7358.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2433, pruned_loss=0.02955, over 1427336.07 frames.], batch size: 19, lr: 2.28e-04
+2022-05-15 22:41:53,733 INFO [train.py:812] (1/8) Epoch 34, batch 3100, loss[loss=0.1451, simple_loss=0.2173, pruned_loss=0.03644, over 6797.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2432, pruned_loss=0.02959, over 1428402.39 frames.], batch size: 15, lr: 2.28e-04
+2022-05-15 22:42:52,704 INFO [train.py:812] (1/8) Epoch 34, batch 3150, loss[loss=0.1422, simple_loss=0.2222, pruned_loss=0.03113, over 7290.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.02927, over 1428419.32 frames.], batch size: 17, lr: 2.28e-04
+2022-05-15 22:43:51,469 INFO [train.py:812] (1/8) Epoch 34, batch 3200, loss[loss=0.1789, simple_loss=0.2602, pruned_loss=0.04877, over 4906.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2431, pruned_loss=0.02974, over 1423844.20 frames.], batch size: 52, lr: 2.28e-04
+2022-05-15 22:44:49,458 INFO [train.py:812] (1/8) Epoch 34, batch 3250, loss[loss=0.1465, simple_loss=0.2393, pruned_loss=0.02688, over 7126.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2426, pruned_loss=0.02982, over 1421795.44 frames.], batch size: 17, lr: 2.28e-04
+2022-05-15 22:45:48,017 INFO [train.py:812] (1/8) Epoch 34, batch 3300, loss[loss=0.1522, simple_loss=0.2408, pruned_loss=0.03174, over 7109.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2426, pruned_loss=0.02997, over 1418644.38 frames.], batch size: 28, lr: 2.28e-04
+2022-05-15 22:46:47,351 INFO [train.py:812] (1/8) Epoch 34, batch 3350, loss[loss=0.1522, simple_loss=0.2452, pruned_loss=0.02962, over 7140.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2417, pruned_loss=0.02959, over 1421749.95 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:47:45,308 INFO [train.py:812] (1/8) Epoch 34, batch 3400, loss[loss=0.16, simple_loss=0.2518, pruned_loss=0.03414, over 7202.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2426, pruned_loss=0.02976, over 1422343.35 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:48:43,910 INFO [train.py:812] (1/8) Epoch 34, batch 3450, loss[loss=0.1491, simple_loss=0.2359, pruned_loss=0.03111, over 7005.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2418, pruned_loss=0.02935, over 1427561.95 frames.], batch size: 16, lr: 2.28e-04
+2022-05-15 22:49:41,431 INFO [train.py:812] (1/8) Epoch 34, batch 3500, loss[loss=0.1763, simple_loss=0.2697, pruned_loss=0.04143, over 7184.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2439, pruned_loss=0.02976, over 1429626.15 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:50:38,735 INFO [train.py:812] (1/8) Epoch 34, batch 3550, loss[loss=0.1365, simple_loss=0.2251, pruned_loss=0.02395, over 7288.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2426, pruned_loss=0.02926, over 1431242.54 frames.], batch size: 17, lr: 2.28e-04
+2022-05-15 22:51:37,802 INFO [train.py:812] (1/8) Epoch 34, batch 3600, loss[loss=0.1424, simple_loss=0.2328, pruned_loss=0.02594, over 7324.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2426, pruned_loss=0.02927, over 1433806.37 frames.], batch size: 21, lr: 2.28e-04
+2022-05-15 22:52:35,098 INFO [train.py:812] (1/8) Epoch 34, batch 3650, loss[loss=0.1665, simple_loss=0.2571, pruned_loss=0.03798, over 6387.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2433, pruned_loss=0.02949, over 1428647.81 frames.], batch size: 37, lr: 2.28e-04
+2022-05-15 22:53:34,810 INFO [train.py:812] (1/8) Epoch 34, batch 3700, loss[loss=0.1501, simple_loss=0.2481, pruned_loss=0.02603, over 7242.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2418, pruned_loss=0.02929, over 1423769.68 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:54:33,348 INFO [train.py:812] (1/8) Epoch 34, batch 3750, loss[loss=0.1646, simple_loss=0.2559, pruned_loss=0.03668, over 7290.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2415, pruned_loss=0.02935, over 1420807.61 frames.], batch size: 24, lr: 2.28e-04
+2022-05-15 22:55:32,411 INFO [train.py:812] (1/8) Epoch 34, batch 3800, loss[loss=0.1338, simple_loss=0.2288, pruned_loss=0.01943, over 7146.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2422, pruned_loss=0.02931, over 1424960.68 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:56:31,634 INFO [train.py:812] (1/8) Epoch 34, batch 3850, loss[loss=0.1539, simple_loss=0.2573, pruned_loss=0.02525, over 7220.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02912, over 1426933.44 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:57:28,722 INFO [train.py:812] (1/8) Epoch 34, batch 3900, loss[loss=0.1721, simple_loss=0.2581, pruned_loss=0.04304, over 7196.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2428, pruned_loss=0.02949, over 1425303.41 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:58:46,456 INFO [train.py:812] (1/8) Epoch 34, batch 3950, loss[loss=0.1339, simple_loss=0.2363, pruned_loss=0.01579, over 7321.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2429, pruned_loss=0.02969, over 1422799.26 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:59:45,595 INFO [train.py:812] (1/8) Epoch 34, batch 4000, loss[loss=0.1464, simple_loss=0.2334, pruned_loss=0.02974, over 7077.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02942, over 1423007.93 frames.], batch size: 18, lr: 2.28e-04
+2022-05-15 23:00:53,106 INFO [train.py:812] (1/8) Epoch 34, batch 4050, loss[loss=0.1491, simple_loss=0.246, pruned_loss=0.02607, over 7193.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2434, pruned_loss=0.02961, over 1418206.61 frames.], batch size: 26, lr: 2.27e-04
+2022-05-15 23:01:51,478 INFO [train.py:812] (1/8) Epoch 34, batch 4100, loss[loss=0.1597, simple_loss=0.2549, pruned_loss=0.03227, over 6330.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2438, pruned_loss=0.02955, over 1419534.36 frames.], batch size: 37, lr: 2.27e-04
+2022-05-15 23:02:49,401 INFO [train.py:812] (1/8) Epoch 34, batch 4150, loss[loss=0.1357, simple_loss=0.2269, pruned_loss=0.02223, over 7399.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2442, pruned_loss=0.02981, over 1418579.13 frames.], batch size: 18, lr: 2.27e-04
+2022-05-15 23:03:57,829 INFO [train.py:812] (1/8) Epoch 34, batch 4200, loss[loss=0.1414, simple_loss=0.2427, pruned_loss=0.02007, over 7241.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2443, pruned_loss=0.03001, over 1421655.88 frames.], batch size: 20, lr: 2.27e-04
+2022-05-15 23:05:06,376 INFO [train.py:812] (1/8) Epoch 34, batch 4250, loss[loss=0.1264, simple_loss=0.2107, pruned_loss=0.02104, over 7122.00 frames.], tot_loss[loss=0.1527, simple_loss=0.245, pruned_loss=0.03023, over 1420324.87 frames.], batch size: 17, lr: 2.27e-04
+2022-05-15 23:06:05,068 INFO [train.py:812] (1/8) Epoch 34, batch 4300, loss[loss=0.1272, simple_loss=0.2159, pruned_loss=0.01928, over 6987.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2448, pruned_loss=0.0299, over 1420363.28 frames.], batch size: 16, lr: 2.27e-04
+2022-05-15 23:07:13,189 INFO [train.py:812] (1/8) Epoch 34, batch 4350, loss[loss=0.1353, simple_loss=0.2157, pruned_loss=0.02748, over 6764.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2462, pruned_loss=0.03073, over 1416602.83 frames.], batch size: 15, lr: 2.27e-04
+2022-05-15 23:08:12,764 INFO [train.py:812] (1/8) Epoch 34, batch 4400, loss[loss=0.1278, simple_loss=0.2151, pruned_loss=0.02029, over 7176.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2453, pruned_loss=0.03062, over 1416991.92 frames.], batch size: 18, lr: 2.27e-04
+2022-05-15 23:09:11,150 INFO [train.py:812] (1/8) Epoch 34, batch 4450, loss[loss=0.1413, simple_loss=0.2352, pruned_loss=0.02363, over 7193.00 frames.], tot_loss[loss=0.1531, simple_loss=0.245, pruned_loss=0.03057, over 1402556.77 frames.], batch size: 23, lr: 2.27e-04
+2022-05-15 23:10:19,456 INFO [train.py:812] (1/8) Epoch 34, batch 4500, loss[loss=0.1741, simple_loss=0.2592, pruned_loss=0.04449, over 5193.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2451, pruned_loss=0.03064, over 1393486.54 frames.], batch size: 52, lr: 2.27e-04
+2022-05-15 23:11:16,027 INFO [train.py:812] (1/8) Epoch 34, batch 4550, loss[loss=0.173, simple_loss=0.2639, pruned_loss=0.04108, over 4827.00 frames.], tot_loss[loss=0.155, simple_loss=0.2474, pruned_loss=0.03132, over 1352726.08 frames.], batch size: 52, lr: 2.27e-04
+2022-05-15 23:12:20,547 INFO [train.py:812] (1/8) Epoch 35, batch 0, loss[loss=0.1666, simple_loss=0.2591, pruned_loss=0.03709, over 7240.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2591, pruned_loss=0.03709, over 7240.00 frames.], batch size: 20, lr: 2.24e-04
+2022-05-15 23:13:24,532 INFO [train.py:812] (1/8) Epoch 35, batch 50, loss[loss=0.1686, simple_loss=0.2774, pruned_loss=0.0299, over 7297.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2441, pruned_loss=0.03065, over 318314.76 frames.], batch size: 24, lr: 2.24e-04
+2022-05-15 23:14:23,044 INFO [train.py:812] (1/8) Epoch 35, batch 100, loss[loss=0.1554, simple_loss=0.2612, pruned_loss=0.02485, over 7126.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02911, over 567447.16 frames.], batch size: 26, lr: 2.24e-04
+2022-05-15 23:15:22,491 INFO [train.py:812] (1/8) Epoch 35, batch 150, loss[loss=0.1765, simple_loss=0.265, pruned_loss=0.04402, over 7392.00 frames.], tot_loss[loss=0.151, simple_loss=0.2432, pruned_loss=0.02939, over 760304.25 frames.], batch size: 23, lr: 2.24e-04
+2022-05-15 23:16:21,262 INFO [train.py:812] (1/8) Epoch 35, batch 200, loss[loss=0.1493, simple_loss=0.234, pruned_loss=0.03226, over 7063.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2437, pruned_loss=0.03035, over 909887.51 frames.], batch size: 18, lr: 2.24e-04
+2022-05-15 23:17:21,132 INFO [train.py:812] (1/8) Epoch 35, batch 250, loss[loss=0.1485, simple_loss=0.2477, pruned_loss=0.02464, over 7237.00 frames.], tot_loss[loss=0.1523, simple_loss=0.244, pruned_loss=0.03027, over 1027264.22 frames.], batch size: 20, lr: 2.24e-04
+2022-05-15 23:18:18,846 INFO [train.py:812] (1/8) Epoch 35, batch 300, loss[loss=0.1269, simple_loss=0.224, pruned_loss=0.01486, over 7154.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2428, pruned_loss=0.03004, over 1113350.82 frames.], batch size: 19, lr: 2.24e-04
+2022-05-15 23:19:18,447 INFO [train.py:812] (1/8) Epoch 35, batch 350, loss[loss=0.1715, simple_loss=0.2627, pruned_loss=0.04021, over 7185.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02943, over 1185707.47 frames.], batch size: 23, lr: 2.24e-04
+2022-05-15 23:20:16,874 INFO [train.py:812] (1/8) Epoch 35, batch 400, loss[loss=0.1483, simple_loss=0.2399, pruned_loss=0.02839, over 7330.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2436, pruned_loss=0.02974, over 1239938.27 frames.], batch size: 20, lr: 2.24e-04
+2022-05-15 23:21:15,059 INFO [train.py:812] (1/8) Epoch 35, batch 450, loss[loss=0.1787, simple_loss=0.2849, pruned_loss=0.0362, over 6770.00 frames.], tot_loss[loss=0.151, simple_loss=0.2427, pruned_loss=0.02967, over 1284930.01 frames.], batch size: 31, lr: 2.24e-04
+2022-05-15 23:22:13,109 INFO [train.py:812] (1/8) Epoch 35, batch 500, loss[loss=0.1546, simple_loss=0.2473, pruned_loss=0.03097, over 7325.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2423, pruned_loss=0.0295, over 1315190.86 frames.], batch size: 20, lr: 2.23e-04
+2022-05-15 23:23:12,699 INFO [train.py:812] (1/8) Epoch 35, batch 550, loss[loss=0.1521, simple_loss=0.2353, pruned_loss=0.03443, over 7057.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2419, pruned_loss=0.0294, over 1335346.58 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:24:10,892 INFO [train.py:812] (1/8) Epoch 35, batch 600, loss[loss=0.154, simple_loss=0.2578, pruned_loss=0.02514, over 7347.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2432, pruned_loss=0.02955, over 1354317.55 frames.], batch size: 22, lr: 2.23e-04
+2022-05-15 23:25:10,096 INFO [train.py:812] (1/8) Epoch 35, batch 650, loss[loss=0.136, simple_loss=0.2242, pruned_loss=0.0239, over 7164.00 frames.], tot_loss[loss=0.1516, simple_loss=0.244, pruned_loss=0.02955, over 1373011.01 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:26:08,921 INFO [train.py:812] (1/8) Epoch 35, batch 700, loss[loss=0.1637, simple_loss=0.2601, pruned_loss=0.0336, over 7256.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2436, pruned_loss=0.02939, over 1386585.79 frames.], batch size: 17, lr: 2.23e-04
+2022-05-15 23:27:08,855 INFO [train.py:812] (1/8) Epoch 35, batch 750, loss[loss=0.1481, simple_loss=0.2411, pruned_loss=0.02756, over 7266.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.02935, over 1394247.58 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:28:07,094 INFO [train.py:812] (1/8) Epoch 35, batch 800, loss[loss=0.1513, simple_loss=0.2519, pruned_loss=0.02537, over 7232.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2429, pruned_loss=0.02922, over 1403040.84 frames.], batch size: 21, lr: 2.23e-04
+2022-05-15 23:29:06,741 INFO [train.py:812] (1/8) Epoch 35, batch 850, loss[loss=0.1718, simple_loss=0.2781, pruned_loss=0.03272, over 7295.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2441, pruned_loss=0.02951, over 1403090.08 frames.], batch size: 24, lr: 2.23e-04
+2022-05-15 23:30:05,620 INFO [train.py:812] (1/8) Epoch 35, batch 900, loss[loss=0.1737, simple_loss=0.2492, pruned_loss=0.04904, over 5125.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02943, over 1406547.15 frames.], batch size: 53, lr: 2.23e-04
+2022-05-15 23:31:04,508 INFO [train.py:812] (1/8) Epoch 35, batch 950, loss[loss=0.183, simple_loss=0.2629, pruned_loss=0.05154, over 7247.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2426, pruned_loss=0.02944, over 1409923.52 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:32:02,577 INFO [train.py:812] (1/8) Epoch 35, batch 1000, loss[loss=0.1715, simple_loss=0.2638, pruned_loss=0.03956, over 6876.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2425, pruned_loss=0.0294, over 1411588.96 frames.], batch size: 31, lr: 2.23e-04
+2022-05-15 23:33:01,150 INFO [train.py:812] (1/8) Epoch 35, batch 1050, loss[loss=0.1631, simple_loss=0.2593, pruned_loss=0.03345, over 7425.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2424, pruned_loss=0.02953, over 1415670.74 frames.], batch size: 21, lr: 2.23e-04
+2022-05-15 23:33:59,692 INFO [train.py:812] (1/8) Epoch 35, batch 1100, loss[loss=0.1311, simple_loss=0.2331, pruned_loss=0.01459, over 7346.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2417, pruned_loss=0.029, over 1420164.56 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:34:58,676 INFO [train.py:812] (1/8) Epoch 35, batch 1150, loss[loss=0.1583, simple_loss=0.2538, pruned_loss=0.03142, over 7197.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2422, pruned_loss=0.02898, over 1421636.93 frames.], batch size: 23, lr: 2.23e-04
+2022-05-15 23:35:56,590 INFO [train.py:812] (1/8) Epoch 35, batch 1200, loss[loss=0.1361, simple_loss=0.2273, pruned_loss=0.02242, over 7278.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2423, pruned_loss=0.0292, over 1425420.62 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:36:54,998 INFO [train.py:812] (1/8) Epoch 35, batch 1250, loss[loss=0.1675, simple_loss=0.2659, pruned_loss=0.03453, over 7337.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02897, over 1424218.05 frames.], batch size: 22, lr: 2.23e-04
+2022-05-15 23:37:53,441 INFO [train.py:812] (1/8) Epoch 35, batch 1300, loss[loss=0.166, simple_loss=0.2591, pruned_loss=0.03645, over 7052.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2438, pruned_loss=0.02948, over 1420014.11 frames.], batch size: 28, lr: 2.23e-04
+2022-05-15 23:38:52,780 INFO [train.py:812] (1/8) Epoch 35, batch 1350, loss[loss=0.1604, simple_loss=0.2531, pruned_loss=0.03389, over 7127.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2441, pruned_loss=0.02969, over 1423099.09 frames.], batch size: 28, lr: 2.23e-04
+2022-05-15 23:39:51,264 INFO [train.py:812] (1/8) Epoch 35, batch 1400, loss[loss=0.1393, simple_loss=0.2321, pruned_loss=0.02328, over 7317.00 frames.], tot_loss[loss=0.152, simple_loss=0.2441, pruned_loss=0.02992, over 1420981.41 frames.], batch size: 20, lr: 2.23e-04
+2022-05-15 23:40:50,632 INFO [train.py:812] (1/8) Epoch 35, batch 1450, loss[loss=0.1457, simple_loss=0.2336, pruned_loss=0.02894, over 7254.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2435, pruned_loss=0.02986, over 1418444.65 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:41:50,036 INFO [train.py:812] (1/8) Epoch 35, batch 1500, loss[loss=0.1271, simple_loss=0.2198, pruned_loss=0.01717, over 7136.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2439, pruned_loss=0.02981, over 1419499.40 frames.], batch size: 17, lr: 2.23e-04
+2022-05-15 23:42:48,885 INFO [train.py:812] (1/8) Epoch 35, batch 1550, loss[loss=0.2001, simple_loss=0.3001, pruned_loss=0.05006, over 7224.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2447, pruned_loss=0.03015, over 1419428.17 frames.], batch size: 21, lr: 2.23e-04
+2022-05-15 23:43:47,277 INFO [train.py:812] (1/8) Epoch 35, batch 1600, loss[loss=0.16, simple_loss=0.2538, pruned_loss=0.03308, over 7148.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2439, pruned_loss=0.02968, over 1421382.58 frames.], batch size: 28, lr: 2.23e-04
+2022-05-15 23:44:46,447 INFO [train.py:812] (1/8) Epoch 35, batch 1650, loss[loss=0.1303, simple_loss=0.2133, pruned_loss=0.02367, over 7406.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2434, pruned_loss=0.0295, over 1427010.54 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:45:45,294 INFO [train.py:812] (1/8) Epoch 35, batch 1700, loss[loss=0.1685, simple_loss=0.2445, pruned_loss=0.04623, over 5204.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2428, pruned_loss=0.0294, over 1426527.97 frames.], batch size: 52, lr: 2.23e-04
+2022-05-15 23:46:45,277 INFO [train.py:812] (1/8) Epoch 35, batch 1750, loss[loss=0.1348, simple_loss=0.2246, pruned_loss=0.02246, over 7154.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.02911, over 1425111.12 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:47:44,612 INFO [train.py:812] (1/8) Epoch 35, batch 1800, loss[loss=0.1492, simple_loss=0.2423, pruned_loss=0.02802, over 7300.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2417, pruned_loss=0.02882, over 1428858.13 frames.], batch size: 25, lr: 2.23e-04
+2022-05-15 23:48:43,675 INFO [train.py:812] (1/8) Epoch 35, batch 1850, loss[loss=0.1437, simple_loss=0.2389, pruned_loss=0.02426, over 7053.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2414, pruned_loss=0.0286, over 1425462.48 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:49:42,134 INFO [train.py:812] (1/8) Epoch 35, batch 1900, loss[loss=0.1659, simple_loss=0.2515, pruned_loss=0.04012, over 7392.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2411, pruned_loss=0.02858, over 1424714.13 frames.], batch size: 23, lr: 2.22e-04
+2022-05-15 23:50:50,952 INFO [train.py:812] (1/8) Epoch 35, batch 1950, loss[loss=0.138, simple_loss=0.2277, pruned_loss=0.02412, over 7168.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2422, pruned_loss=0.02897, over 1423860.56 frames.], batch size: 18, lr: 2.22e-04
+2022-05-15 23:51:48,108 INFO [train.py:812] (1/8) Epoch 35, batch 2000, loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.03172, over 6434.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02906, over 1419287.86 frames.], batch size: 38, lr: 2.22e-04
+2022-05-15 23:52:46,831 INFO [train.py:812] (1/8) Epoch 35, batch 2050, loss[loss=0.1599, simple_loss=0.2585, pruned_loss=0.03069, over 7112.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2423, pruned_loss=0.02918, over 1421011.10 frames.], batch size: 21, lr: 2.22e-04
+2022-05-15 23:53:45,605 INFO [train.py:812] (1/8) Epoch 35, batch 2100, loss[loss=0.151, simple_loss=0.2527, pruned_loss=0.02465, over 7416.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2435, pruned_loss=0.02967, over 1423972.23 frames.], batch size: 21, lr: 2.22e-04
+2022-05-15 23:54:43,304 INFO [train.py:812] (1/8) Epoch 35, batch 2150, loss[loss=0.1475, simple_loss=0.245, pruned_loss=0.02498, over 6412.00 frames.], tot_loss[loss=0.1507, simple_loss=0.243, pruned_loss=0.02921, over 1427306.07 frames.], batch size: 37, lr: 2.22e-04
+2022-05-15 23:55:40,398 INFO [train.py:812] (1/8) Epoch 35, batch 2200, loss[loss=0.1637, simple_loss=0.254, pruned_loss=0.03675, over 7426.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02929, over 1424355.95 frames.], batch size: 20, lr: 2.22e-04
+2022-05-15 23:56:39,590 INFO [train.py:812] (1/8) Epoch 35, batch 2250, loss[loss=0.146, simple_loss=0.2271, pruned_loss=0.0324, over 7279.00 frames.], tot_loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.02886, over 1422100.97 frames.], batch size: 18, lr: 2.22e-04
+2022-05-15 23:57:38,196 INFO [train.py:812] (1/8) Epoch 35, batch 2300, loss[loss=0.14, simple_loss=0.2337, pruned_loss=0.02314, over 7239.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02912, over 1419056.95 frames.], batch size: 26, lr: 2.22e-04
+2022-05-15 23:58:36,519 INFO [train.py:812] (1/8) Epoch 35, batch 2350, loss[loss=0.1582, simple_loss=0.2535, pruned_loss=0.03149, over 7051.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2431, pruned_loss=0.02886, over 1417680.20 frames.], batch size: 28, lr: 2.22e-04
+2022-05-15 23:59:34,361 INFO [train.py:812] (1/8) Epoch 35, batch 2400, loss[loss=0.1245, simple_loss=0.2155, pruned_loss=0.01674, over 7016.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2432, pruned_loss=0.02886, over 1422730.44 frames.], batch size: 16, lr: 2.22e-04
+2022-05-16 00:00:32,005 INFO [train.py:812] (1/8) Epoch 35, batch 2450, loss[loss=0.1387, simple_loss=0.2318, pruned_loss=0.02284, over 7430.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2423, pruned_loss=0.0284, over 1423092.40 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:01:31,440 INFO [train.py:812] (1/8) Epoch 35, batch 2500, loss[loss=0.189, simple_loss=0.2872, pruned_loss=0.04534, over 6406.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.02873, over 1424314.45 frames.], batch size: 37, lr: 2.22e-04
+2022-05-16 00:02:30,471 INFO [train.py:812] (1/8) Epoch 35, batch 2550, loss[loss=0.1442, simple_loss=0.2294, pruned_loss=0.02949, over 7119.00 frames.], tot_loss[loss=0.1497, simple_loss=0.242, pruned_loss=0.02869, over 1424013.47 frames.], batch size: 21, lr: 2.22e-04
+2022-05-16 00:03:28,736 INFO [train.py:812] (1/8) Epoch 35, batch 2600, loss[loss=0.1734, simple_loss=0.2604, pruned_loss=0.04321, over 7211.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2416, pruned_loss=0.02853, over 1424068.03 frames.], batch size: 22, lr: 2.22e-04
+2022-05-16 00:04:26,540 INFO [train.py:812] (1/8) Epoch 35, batch 2650, loss[loss=0.1615, simple_loss=0.2532, pruned_loss=0.0349, over 7182.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2422, pruned_loss=0.02902, over 1422293.01 frames.], batch size: 23, lr: 2.22e-04
+2022-05-16 00:05:25,227 INFO [train.py:812] (1/8) Epoch 35, batch 2700, loss[loss=0.1607, simple_loss=0.2624, pruned_loss=0.02949, over 7114.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2424, pruned_loss=0.02906, over 1423795.36 frames.], batch size: 21, lr: 2.22e-04
+2022-05-16 00:06:24,236 INFO [train.py:812] (1/8) Epoch 35, batch 2750, loss[loss=0.1499, simple_loss=0.2503, pruned_loss=0.02476, over 7314.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2427, pruned_loss=0.02923, over 1423515.00 frames.], batch size: 21, lr: 2.22e-04
+2022-05-16 00:07:23,048 INFO [train.py:812] (1/8) Epoch 35, batch 2800, loss[loss=0.1675, simple_loss=0.2602, pruned_loss=0.03746, over 7341.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2439, pruned_loss=0.02971, over 1424816.51 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:08:20,726 INFO [train.py:812] (1/8) Epoch 35, batch 2850, loss[loss=0.137, simple_loss=0.2323, pruned_loss=0.0209, over 7156.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2439, pruned_loss=0.02955, over 1423414.75 frames.], batch size: 19, lr: 2.22e-04
+2022-05-16 00:09:20,167 INFO [train.py:812] (1/8) Epoch 35, batch 2900, loss[loss=0.1509, simple_loss=0.2492, pruned_loss=0.02634, over 6333.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2445, pruned_loss=0.03, over 1422649.27 frames.], batch size: 37, lr: 2.22e-04
+2022-05-16 00:10:18,328 INFO [train.py:812] (1/8) Epoch 35, batch 2950, loss[loss=0.1299, simple_loss=0.2262, pruned_loss=0.01685, over 7162.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2456, pruned_loss=0.03055, over 1417274.45 frames.], batch size: 16, lr: 2.22e-04
+2022-05-16 00:11:17,548 INFO [train.py:812] (1/8) Epoch 35, batch 3000, loss[loss=0.1606, simple_loss=0.2574, pruned_loss=0.03188, over 7363.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2446, pruned_loss=0.02978, over 1421160.06 frames.], batch size: 23, lr: 2.22e-04
+2022-05-16 00:11:17,549 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-16 00:11:25,088 INFO [train.py:841] (1/8) Epoch 35, validation: loss=0.1528, simple_loss=0.2485, pruned_loss=0.02851, over 698248.00 frames.
+2022-05-16 00:12:24,392 INFO [train.py:812] (1/8) Epoch 35, batch 3050, loss[loss=0.1574, simple_loss=0.2516, pruned_loss=0.0316, over 7236.00 frames.], tot_loss[loss=0.1523, simple_loss=0.245, pruned_loss=0.02978, over 1423735.06 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:13:22,726 INFO [train.py:812] (1/8) Epoch 35, batch 3100, loss[loss=0.1501, simple_loss=0.247, pruned_loss=0.02659, over 7382.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2446, pruned_loss=0.02961, over 1420761.57 frames.], batch size: 23, lr: 2.22e-04
+2022-05-16 00:14:22,592 INFO [train.py:812] (1/8) Epoch 35, batch 3150, loss[loss=0.1603, simple_loss=0.2413, pruned_loss=0.03969, over 7204.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2431, pruned_loss=0.0293, over 1422801.01 frames.], batch size: 22, lr: 2.22e-04
+2022-05-16 00:15:21,752 INFO [train.py:812] (1/8) Epoch 35, batch 3200, loss[loss=0.1411, simple_loss=0.2317, pruned_loss=0.02529, over 7203.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2433, pruned_loss=0.02908, over 1427274.09 frames.], batch size: 22, lr: 2.22e-04
+2022-05-16 00:16:21,600 INFO [train.py:812] (1/8) Epoch 35, batch 3250, loss[loss=0.1514, simple_loss=0.2382, pruned_loss=0.0323, over 7435.00 frames.], tot_loss[loss=0.151, simple_loss=0.2436, pruned_loss=0.0292, over 1425351.04 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:17:21,157 INFO [train.py:812] (1/8) Epoch 35, batch 3300, loss[loss=0.1502, simple_loss=0.2407, pruned_loss=0.02986, over 7427.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2436, pruned_loss=0.02894, over 1426449.18 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:18:19,926 INFO [train.py:812] (1/8) Epoch 35, batch 3350, loss[loss=0.1392, simple_loss=0.2368, pruned_loss=0.02074, over 7423.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2432, pruned_loss=0.0288, over 1430218.10 frames.], batch size: 20, lr: 2.21e-04
+2022-05-16 00:19:17,060 INFO [train.py:812] (1/8) Epoch 35, batch 3400, loss[loss=0.1482, simple_loss=0.2334, pruned_loss=0.03151, over 7278.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02908, over 1426389.26 frames.], batch size: 18, lr: 2.21e-04
+2022-05-16 00:20:15,911 INFO [train.py:812] (1/8) Epoch 35, batch 3450, loss[loss=0.1348, simple_loss=0.2261, pruned_loss=0.02175, over 6994.00 frames.], tot_loss[loss=0.1504, simple_loss=0.243, pruned_loss=0.02896, over 1429463.00 frames.], batch size: 16, lr: 2.21e-04
+2022-05-16 00:21:14,729 INFO [train.py:812] (1/8) Epoch 35, batch 3500, loss[loss=0.146, simple_loss=0.2378, pruned_loss=0.02709, over 7326.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02882, over 1427774.32 frames.], batch size: 22, lr: 2.21e-04
+2022-05-16 00:22:12,827 INFO [train.py:812] (1/8) Epoch 35, batch 3550, loss[loss=0.1625, simple_loss=0.2587, pruned_loss=0.03316, over 6791.00 frames.], tot_loss[loss=0.15, simple_loss=0.2421, pruned_loss=0.02898, over 1420302.68 frames.], batch size: 31, lr: 2.21e-04
+2022-05-16 00:23:10,734 INFO [train.py:812] (1/8) Epoch 35, batch 3600, loss[loss=0.1624, simple_loss=0.246, pruned_loss=0.0394, over 7201.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2423, pruned_loss=0.02919, over 1419139.02 frames.], batch size: 22, lr: 2.21e-04
+2022-05-16 00:24:08,620 INFO [train.py:812] (1/8) Epoch 35, batch 3650, loss[loss=0.1514, simple_loss=0.2492, pruned_loss=0.02673, over 7291.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2433, pruned_loss=0.0295, over 1420604.73 frames.], batch size: 25, lr: 2.21e-04
+2022-05-16 00:25:06,950 INFO [train.py:812] (1/8) Epoch 35, batch 3700, loss[loss=0.1509, simple_loss=0.2507, pruned_loss=0.02554, over 6403.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.02906, over 1420205.69 frames.], batch size: 38, lr: 2.21e-04
+2022-05-16 00:26:05,700 INFO [train.py:812] (1/8) Epoch 35, batch 3750, loss[loss=0.1493, simple_loss=0.2404, pruned_loss=0.0291, over 5047.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2424, pruned_loss=0.02874, over 1417856.91 frames.], batch size: 53, lr: 2.21e-04
+2022-05-16 00:27:04,267 INFO [train.py:812] (1/8) Epoch 35, batch 3800, loss[loss=0.1432, simple_loss=0.2348, pruned_loss=0.02584, over 6744.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2429, pruned_loss=0.0288, over 1418238.91 frames.], batch size: 31, lr: 2.21e-04
+2022-05-16 00:28:02,112 INFO [train.py:812] (1/8) Epoch 35, batch 3850, loss[loss=0.1755, simple_loss=0.2692, pruned_loss=0.04089, over 7287.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2426, pruned_loss=0.02899, over 1421179.96 frames.], batch size: 24, lr: 2.21e-04
+2022-05-16 00:29:00,962 INFO [train.py:812] (1/8) Epoch 35, batch 3900, loss[loss=0.1479, simple_loss=0.2303, pruned_loss=0.03276, over 6805.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02962, over 1417664.91 frames.], batch size: 15, lr: 2.21e-04
+2022-05-16 00:30:00,066 INFO [train.py:812] (1/8) Epoch 35, batch 3950, loss[loss=0.1541, simple_loss=0.2404, pruned_loss=0.03396, over 7123.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2427, pruned_loss=0.02946, over 1417579.11 frames.], batch size: 17, lr: 2.21e-04
+2022-05-16 00:30:58,306 INFO [train.py:812] (1/8) Epoch 35, batch 4000, loss[loss=0.1444, simple_loss=0.2211, pruned_loss=0.03386, over 6994.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2424, pruned_loss=0.0291, over 1417183.74 frames.], batch size: 16, lr: 2.21e-04
+2022-05-16 00:32:02,092 INFO [train.py:812] (1/8) Epoch 35, batch 4050, loss[loss=0.1385, simple_loss=0.2396, pruned_loss=0.01872, over 6421.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2428, pruned_loss=0.0289, over 1419930.26 frames.], batch size: 37, lr: 2.21e-04
+2022-05-16 00:33:00,887 INFO [train.py:812] (1/8) Epoch 35, batch 4100, loss[loss=0.1642, simple_loss=0.2574, pruned_loss=0.03555, over 7218.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02937, over 1425748.63 frames.], batch size: 21, lr: 2.21e-04
+2022-05-16 00:33:59,516 INFO [train.py:812] (1/8) Epoch 35, batch 4150, loss[loss=0.1576, simple_loss=0.2552, pruned_loss=0.03001, over 7323.00 frames.], tot_loss[loss=0.151, simple_loss=0.2431, pruned_loss=0.0295, over 1424203.27 frames.], batch size: 21, lr: 2.21e-04
+2022-05-16 00:34:58,346 INFO [train.py:812] (1/8) Epoch 35, batch 4200, loss[loss=0.1352, simple_loss=0.2245, pruned_loss=0.02294, over 7320.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2432, pruned_loss=0.02968, over 1421978.87 frames.], batch size: 21, lr: 2.21e-04
+2022-05-16 00:35:57,141 INFO [train.py:812] (1/8) Epoch 35, batch 4250, loss[loss=0.1365, simple_loss=0.2219, pruned_loss=0.02552, over 7292.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02936, over 1426257.65 frames.], batch size: 17, lr: 2.21e-04
+2022-05-16 00:36:55,255 INFO [train.py:812] (1/8) Epoch 35, batch 4300, loss[loss=0.1507, simple_loss=0.2469, pruned_loss=0.02723, over 7211.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2424, pruned_loss=0.0293, over 1417723.63 frames.], batch size: 26, lr: 2.21e-04
+2022-05-16 00:37:53,242 INFO [train.py:812] (1/8) Epoch 35, batch 4350, loss[loss=0.1755, simple_loss=0.2588, pruned_loss=0.04606, over 7318.00 frames.], tot_loss[loss=0.1513, simple_loss=0.243, pruned_loss=0.02985, over 1414137.39 frames.], batch size: 24, lr: 2.21e-04
+2022-05-16 00:38:52,040 INFO [train.py:812] (1/8) Epoch 35, batch 4400, loss[loss=0.1348, simple_loss=0.2284, pruned_loss=0.02056, over 7165.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2434, pruned_loss=0.02942, over 1409516.82 frames.], batch size: 19, lr: 2.21e-04
+2022-05-16 00:39:50,157 INFO [train.py:812] (1/8) Epoch 35, batch 4450, loss[loss=0.1639, simple_loss=0.2677, pruned_loss=0.02999, over 6760.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2436, pruned_loss=0.02951, over 1393746.14 frames.], batch size: 31, lr: 2.21e-04
+2022-05-16 00:40:48,500 INFO [train.py:812] (1/8) Epoch 35, batch 4500, loss[loss=0.1569, simple_loss=0.2512, pruned_loss=0.03129, over 7136.00 frames.], tot_loss[loss=0.1516, simple_loss=0.244, pruned_loss=0.02964, over 1380061.98 frames.], batch size: 26, lr: 2.21e-04
+2022-05-16 00:41:45,654 INFO [train.py:812] (1/8) Epoch 35, batch 4550, loss[loss=0.1716, simple_loss=0.2642, pruned_loss=0.03953, over 5019.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2461, pruned_loss=0.03082, over 1354593.89 frames.], batch size: 52, lr: 2.21e-04
+2022-05-16 00:42:50,920 INFO [train.py:812] (1/8) Epoch 36, batch 0, loss[loss=0.1262, simple_loss=0.2216, pruned_loss=0.01541, over 7336.00 frames.], tot_loss[loss=0.1262, simple_loss=0.2216, pruned_loss=0.01541, over 7336.00 frames.], batch size: 20, lr: 2.18e-04
+2022-05-16 00:43:50,522 INFO [train.py:812] (1/8) Epoch 36, batch 50, loss[loss=0.1563, simple_loss=0.2471, pruned_loss=0.03271, over 7440.00 frames.], tot_loss[loss=0.152, simple_loss=0.2452, pruned_loss=0.0294, over 317214.75 frames.], batch size: 20, lr: 2.18e-04
+2022-05-16 00:44:48,781 INFO [train.py:812] (1/8) Epoch 36, batch 100, loss[loss=0.1826, simple_loss=0.2605, pruned_loss=0.05236, over 5228.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2435, pruned_loss=0.02883, over 562850.69 frames.], batch size: 52, lr: 2.17e-04
+2022-05-16 00:45:47,229 INFO [train.py:812] (1/8) Epoch 36, batch 150, loss[loss=0.1458, simple_loss=0.2535, pruned_loss=0.01906, over 7221.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02919, over 752079.41 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 00:46:46,271 INFO [train.py:812] (1/8) Epoch 36, batch 200, loss[loss=0.1468, simple_loss=0.2476, pruned_loss=0.02302, over 7308.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2429, pruned_loss=0.02944, over 902766.24 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 00:47:45,332 INFO [train.py:812] (1/8) Epoch 36, batch 250, loss[loss=0.137, simple_loss=0.2226, pruned_loss=0.02567, over 7154.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2415, pruned_loss=0.02875, over 1022297.37 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 00:48:43,650 INFO [train.py:812] (1/8) Epoch 36, batch 300, loss[loss=0.1623, simple_loss=0.2537, pruned_loss=0.0354, over 7149.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2415, pruned_loss=0.02864, over 1107157.05 frames.], batch size: 26, lr: 2.17e-04
+2022-05-16 00:49:42,217 INFO [train.py:812] (1/8) Epoch 36, batch 350, loss[loss=0.1422, simple_loss=0.2434, pruned_loss=0.02052, over 6762.00 frames.], tot_loss[loss=0.149, simple_loss=0.2417, pruned_loss=0.02821, over 1176734.03 frames.], batch size: 31, lr: 2.17e-04
+2022-05-16 00:50:40,179 INFO [train.py:812] (1/8) Epoch 36, batch 400, loss[loss=0.1551, simple_loss=0.2443, pruned_loss=0.03295, over 7200.00 frames.], tot_loss[loss=0.1493, simple_loss=0.242, pruned_loss=0.02831, over 1232507.25 frames.], batch size: 22, lr: 2.17e-04
+2022-05-16 00:51:39,737 INFO [train.py:812] (1/8) Epoch 36, batch 450, loss[loss=0.1682, simple_loss=0.2682, pruned_loss=0.03404, over 7163.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2432, pruned_loss=0.02896, over 1279570.56 frames.], batch size: 26, lr: 2.17e-04
+2022-05-16 00:52:38,605 INFO [train.py:812] (1/8) Epoch 36, batch 500, loss[loss=0.165, simple_loss=0.2611, pruned_loss=0.0345, over 7200.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2438, pruned_loss=0.02933, over 1311524.38 frames.], batch size: 23, lr: 2.17e-04
+2022-05-16 00:53:37,425 INFO [train.py:812] (1/8) Epoch 36, batch 550, loss[loss=0.15, simple_loss=0.24, pruned_loss=0.02996, over 7432.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2437, pruned_loss=0.02897, over 1337389.94 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 00:54:35,746 INFO [train.py:812] (1/8) Epoch 36, batch 600, loss[loss=0.1877, simple_loss=0.2736, pruned_loss=0.05094, over 7226.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02915, over 1360056.47 frames.], batch size: 23, lr: 2.17e-04
+2022-05-16 00:55:34,848 INFO [train.py:812] (1/8) Epoch 36, batch 650, loss[loss=0.1454, simple_loss=0.2281, pruned_loss=0.03139, over 7165.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2417, pruned_loss=0.02888, over 1374480.32 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 00:56:33,799 INFO [train.py:812] (1/8) Epoch 36, batch 700, loss[loss=0.1429, simple_loss=0.2282, pruned_loss=0.02874, over 7273.00 frames.], tot_loss[loss=0.15, simple_loss=0.2414, pruned_loss=0.02926, over 1385312.64 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 00:57:42,560 INFO [train.py:812] (1/8) Epoch 36, batch 750, loss[loss=0.1442, simple_loss=0.2487, pruned_loss=0.01984, over 7340.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2425, pruned_loss=0.02962, over 1385408.04 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 00:58:59,876 INFO [train.py:812] (1/8) Epoch 36, batch 800, loss[loss=0.1497, simple_loss=0.2443, pruned_loss=0.02759, over 7408.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2427, pruned_loss=0.02929, over 1393603.61 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 00:59:58,241 INFO [train.py:812] (1/8) Epoch 36, batch 850, loss[loss=0.1453, simple_loss=0.2472, pruned_loss=0.0217, over 7219.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2427, pruned_loss=0.02903, over 1395611.44 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 01:00:57,358 INFO [train.py:812] (1/8) Epoch 36, batch 900, loss[loss=0.1518, simple_loss=0.2456, pruned_loss=0.02899, over 6787.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2426, pruned_loss=0.02893, over 1402033.10 frames.], batch size: 31, lr: 2.17e-04
+2022-05-16 01:01:55,206 INFO [train.py:812] (1/8) Epoch 36, batch 950, loss[loss=0.1316, simple_loss=0.2126, pruned_loss=0.02529, over 6995.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2426, pruned_loss=0.0289, over 1405196.70 frames.], batch size: 16, lr: 2.17e-04
+2022-05-16 01:03:03,176 INFO [train.py:812] (1/8) Epoch 36, batch 1000, loss[loss=0.1338, simple_loss=0.2311, pruned_loss=0.01821, over 7280.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2421, pruned_loss=0.02867, over 1407014.15 frames.], batch size: 17, lr: 2.17e-04
+2022-05-16 01:04:02,085 INFO [train.py:812] (1/8) Epoch 36, batch 1050, loss[loss=0.1293, simple_loss=0.2254, pruned_loss=0.01663, over 7352.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2417, pruned_loss=0.02844, over 1407241.17 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 01:05:09,925 INFO [train.py:812] (1/8) Epoch 36, batch 1100, loss[loss=0.1756, simple_loss=0.2827, pruned_loss=0.03431, over 7208.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2432, pruned_loss=0.02889, over 1407973.75 frames.], batch size: 22, lr: 2.17e-04
+2022-05-16 01:06:19,080 INFO [train.py:812] (1/8) Epoch 36, batch 1150, loss[loss=0.1467, simple_loss=0.2425, pruned_loss=0.02545, over 7285.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2419, pruned_loss=0.0284, over 1412776.99 frames.], batch size: 24, lr: 2.17e-04
+2022-05-16 01:07:18,007 INFO [train.py:812] (1/8) Epoch 36, batch 1200, loss[loss=0.1267, simple_loss=0.2155, pruned_loss=0.01896, over 7283.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02912, over 1408563.64 frames.], batch size: 17, lr: 2.17e-04
+2022-05-16 01:08:16,990 INFO [train.py:812] (1/8) Epoch 36, batch 1250, loss[loss=0.1237, simple_loss=0.2101, pruned_loss=0.01864, over 6999.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02915, over 1409905.89 frames.], batch size: 16, lr: 2.17e-04
+2022-05-16 01:09:23,813 INFO [train.py:812] (1/8) Epoch 36, batch 1300, loss[loss=0.1358, simple_loss=0.2162, pruned_loss=0.02773, over 7151.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2433, pruned_loss=0.02919, over 1414136.17 frames.], batch size: 17, lr: 2.17e-04
+2022-05-16 01:10:23,375 INFO [train.py:812] (1/8) Epoch 36, batch 1350, loss[loss=0.1358, simple_loss=0.222, pruned_loss=0.02478, over 7257.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.02901, over 1418976.56 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 01:11:21,654 INFO [train.py:812] (1/8) Epoch 36, batch 1400, loss[loss=0.1385, simple_loss=0.2221, pruned_loss=0.02747, over 7001.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2435, pruned_loss=0.02932, over 1417233.36 frames.], batch size: 16, lr: 2.17e-04
+2022-05-16 01:12:20,395 INFO [train.py:812] (1/8) Epoch 36, batch 1450, loss[loss=0.1177, simple_loss=0.2037, pruned_loss=0.01585, over 6811.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02912, over 1414169.70 frames.], batch size: 15, lr: 2.17e-04
+2022-05-16 01:13:19,133 INFO [train.py:812] (1/8) Epoch 36, batch 1500, loss[loss=0.1496, simple_loss=0.2559, pruned_loss=0.02167, over 7319.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02911, over 1418195.12 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 01:14:17,141 INFO [train.py:812] (1/8) Epoch 36, batch 1550, loss[loss=0.1401, simple_loss=0.2347, pruned_loss=0.02279, over 7241.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2431, pruned_loss=0.02892, over 1420321.19 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 01:15:14,897 INFO [train.py:812] (1/8) Epoch 36, batch 1600, loss[loss=0.158, simple_loss=0.2513, pruned_loss=0.03238, over 7387.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.0288, over 1420325.42 frames.], batch size: 23, lr: 2.16e-04
+2022-05-16 01:16:13,262 INFO [train.py:812] (1/8) Epoch 36, batch 1650, loss[loss=0.1407, simple_loss=0.2301, pruned_loss=0.0257, over 7159.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2426, pruned_loss=0.02883, over 1421817.03 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:17:10,674 INFO [train.py:812] (1/8) Epoch 36, batch 1700, loss[loss=0.1677, simple_loss=0.2658, pruned_loss=0.03483, over 7278.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2437, pruned_loss=0.02906, over 1423667.70 frames.], batch size: 25, lr: 2.16e-04
+2022-05-16 01:18:09,640 INFO [train.py:812] (1/8) Epoch 36, batch 1750, loss[loss=0.1341, simple_loss=0.2121, pruned_loss=0.02803, over 7276.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2435, pruned_loss=0.02915, over 1419831.35 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:19:07,095 INFO [train.py:812] (1/8) Epoch 36, batch 1800, loss[loss=0.1668, simple_loss=0.2648, pruned_loss=0.0344, over 7188.00 frames.], tot_loss[loss=0.152, simple_loss=0.2447, pruned_loss=0.02965, over 1421993.63 frames.], batch size: 23, lr: 2.16e-04
+2022-05-16 01:20:05,573 INFO [train.py:812] (1/8) Epoch 36, batch 1850, loss[loss=0.152, simple_loss=0.2458, pruned_loss=0.02913, over 7120.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2445, pruned_loss=0.02959, over 1424200.68 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:21:04,169 INFO [train.py:812] (1/8) Epoch 36, batch 1900, loss[loss=0.1612, simple_loss=0.2537, pruned_loss=0.03434, over 6720.00 frames.], tot_loss[loss=0.152, simple_loss=0.2445, pruned_loss=0.0298, over 1424972.84 frames.], batch size: 31, lr: 2.16e-04
+2022-05-16 01:22:03,011 INFO [train.py:812] (1/8) Epoch 36, batch 1950, loss[loss=0.1575, simple_loss=0.2525, pruned_loss=0.03127, over 7236.00 frames.], tot_loss[loss=0.151, simple_loss=0.2431, pruned_loss=0.02949, over 1422958.17 frames.], batch size: 20, lr: 2.16e-04
+2022-05-16 01:23:01,526 INFO [train.py:812] (1/8) Epoch 36, batch 2000, loss[loss=0.1499, simple_loss=0.2305, pruned_loss=0.03469, over 7021.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2443, pruned_loss=0.02972, over 1420307.24 frames.], batch size: 16, lr: 2.16e-04
+2022-05-16 01:24:00,266 INFO [train.py:812] (1/8) Epoch 36, batch 2050, loss[loss=0.1568, simple_loss=0.2471, pruned_loss=0.03327, over 7319.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2438, pruned_loss=0.02945, over 1425500.82 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:24:59,289 INFO [train.py:812] (1/8) Epoch 36, batch 2100, loss[loss=0.1572, simple_loss=0.248, pruned_loss=0.0332, over 7419.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.02945, over 1424128.03 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:25:59,145 INFO [train.py:812] (1/8) Epoch 36, batch 2150, loss[loss=0.1263, simple_loss=0.2151, pruned_loss=0.01877, over 7252.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.02908, over 1427166.47 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:26:58,703 INFO [train.py:812] (1/8) Epoch 36, batch 2200, loss[loss=0.1251, simple_loss=0.2162, pruned_loss=0.01699, over 7411.00 frames.], tot_loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.02882, over 1426384.56 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:27:57,341 INFO [train.py:812] (1/8) Epoch 36, batch 2250, loss[loss=0.1454, simple_loss=0.2421, pruned_loss=0.02439, over 7330.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2429, pruned_loss=0.02876, over 1423212.26 frames.], batch size: 22, lr: 2.16e-04
+2022-05-16 01:28:55,638 INFO [train.py:812] (1/8) Epoch 36, batch 2300, loss[loss=0.1264, simple_loss=0.2089, pruned_loss=0.02194, over 7129.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2418, pruned_loss=0.02877, over 1425677.93 frames.], batch size: 17, lr: 2.16e-04
+2022-05-16 01:29:55,111 INFO [train.py:812] (1/8) Epoch 36, batch 2350, loss[loss=0.1576, simple_loss=0.2487, pruned_loss=0.03328, over 4971.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2424, pruned_loss=0.02893, over 1423936.72 frames.], batch size: 52, lr: 2.16e-04
+2022-05-16 01:30:54,429 INFO [train.py:812] (1/8) Epoch 36, batch 2400, loss[loss=0.1531, simple_loss=0.2467, pruned_loss=0.02979, over 7406.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2425, pruned_loss=0.0288, over 1427187.59 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:31:54,045 INFO [train.py:812] (1/8) Epoch 36, batch 2450, loss[loss=0.1366, simple_loss=0.2403, pruned_loss=0.01643, over 7171.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2422, pruned_loss=0.0285, over 1422206.18 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:32:52,232 INFO [train.py:812] (1/8) Epoch 36, batch 2500, loss[loss=0.147, simple_loss=0.2413, pruned_loss=0.02635, over 7139.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2421, pruned_loss=0.02842, over 1425833.94 frames.], batch size: 20, lr: 2.16e-04
+2022-05-16 01:33:51,371 INFO [train.py:812] (1/8) Epoch 36, batch 2550, loss[loss=0.1476, simple_loss=0.2368, pruned_loss=0.02914, over 7361.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2428, pruned_loss=0.0285, over 1423903.60 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:34:50,036 INFO [train.py:812] (1/8) Epoch 36, batch 2600, loss[loss=0.1289, simple_loss=0.2198, pruned_loss=0.01902, over 7164.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2427, pruned_loss=0.02828, over 1424416.85 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:35:48,593 INFO [train.py:812] (1/8) Epoch 36, batch 2650, loss[loss=0.2136, simple_loss=0.2954, pruned_loss=0.06595, over 4897.00 frames.], tot_loss[loss=0.1502, simple_loss=0.243, pruned_loss=0.02876, over 1422558.75 frames.], batch size: 52, lr: 2.16e-04
+2022-05-16 01:36:46,990 INFO [train.py:812] (1/8) Epoch 36, batch 2700, loss[loss=0.1626, simple_loss=0.2528, pruned_loss=0.03624, over 7307.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2426, pruned_loss=0.02857, over 1424138.09 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:37:45,791 INFO [train.py:812] (1/8) Epoch 36, batch 2750, loss[loss=0.159, simple_loss=0.2514, pruned_loss=0.03329, over 7113.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2428, pruned_loss=0.02891, over 1426189.50 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:38:44,965 INFO [train.py:812] (1/8) Epoch 36, batch 2800, loss[loss=0.1655, simple_loss=0.2532, pruned_loss=0.03886, over 7198.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2414, pruned_loss=0.02874, over 1427576.37 frames.], batch size: 22, lr: 2.16e-04
+2022-05-16 01:39:44,894 INFO [train.py:812] (1/8) Epoch 36, batch 2850, loss[loss=0.1238, simple_loss=0.2071, pruned_loss=0.02031, over 7283.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2407, pruned_loss=0.02873, over 1428130.81 frames.], batch size: 17, lr: 2.16e-04
+2022-05-16 01:40:43,915 INFO [train.py:812] (1/8) Epoch 36, batch 2900, loss[loss=0.1348, simple_loss=0.2296, pruned_loss=0.01995, over 7244.00 frames.], tot_loss[loss=0.148, simple_loss=0.2393, pruned_loss=0.02831, over 1426617.69 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:41:42,647 INFO [train.py:812] (1/8) Epoch 36, batch 2950, loss[loss=0.1415, simple_loss=0.2265, pruned_loss=0.02828, over 7158.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2404, pruned_loss=0.02854, over 1424794.19 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:42:41,191 INFO [train.py:812] (1/8) Epoch 36, batch 3000, loss[loss=0.1455, simple_loss=0.2299, pruned_loss=0.03061, over 7163.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2416, pruned_loss=0.02898, over 1421615.99 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:42:41,192 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-16 01:42:48,528 INFO [train.py:841] (1/8) Epoch 36, validation: loss=0.1533, simple_loss=0.2487, pruned_loss=0.02893, over 698248.00 frames.
+2022-05-16 01:43:48,423 INFO [train.py:812] (1/8) Epoch 36, batch 3050, loss[loss=0.1786, simple_loss=0.2788, pruned_loss=0.03917, over 7282.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.0288, over 1424260.08 frames.], batch size: 24, lr: 2.16e-04
+2022-05-16 01:44:47,692 INFO [train.py:812] (1/8) Epoch 36, batch 3100, loss[loss=0.1483, simple_loss=0.246, pruned_loss=0.02529, over 7280.00 frames.], tot_loss[loss=0.15, simple_loss=0.2424, pruned_loss=0.02881, over 1428497.21 frames.], batch size: 25, lr: 2.15e-04
+2022-05-16 01:45:47,522 INFO [train.py:812] (1/8) Epoch 36, batch 3150, loss[loss=0.1678, simple_loss=0.2581, pruned_loss=0.03873, over 7378.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2419, pruned_loss=0.02861, over 1427075.81 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 01:46:46,138 INFO [train.py:812] (1/8) Epoch 36, batch 3200, loss[loss=0.125, simple_loss=0.2088, pruned_loss=0.02064, over 7154.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2418, pruned_loss=0.02871, over 1420498.82 frames.], batch size: 17, lr: 2.15e-04
+2022-05-16 01:47:45,901 INFO [train.py:812] (1/8) Epoch 36, batch 3250, loss[loss=0.1646, simple_loss=0.2575, pruned_loss=0.03586, over 4669.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2423, pruned_loss=0.0293, over 1418003.33 frames.], batch size: 52, lr: 2.15e-04
+2022-05-16 01:48:53,227 INFO [train.py:812] (1/8) Epoch 36, batch 3300, loss[loss=0.1432, simple_loss=0.2284, pruned_loss=0.02898, over 7198.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02909, over 1421920.23 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 01:49:52,247 INFO [train.py:812] (1/8) Epoch 36, batch 3350, loss[loss=0.158, simple_loss=0.2545, pruned_loss=0.03074, over 7198.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2431, pruned_loss=0.02909, over 1425335.55 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 01:50:50,253 INFO [train.py:812] (1/8) Epoch 36, batch 3400, loss[loss=0.151, simple_loss=0.2523, pruned_loss=0.02484, over 7262.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2427, pruned_loss=0.02902, over 1424415.72 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 01:51:53,848 INFO [train.py:812] (1/8) Epoch 36, batch 3450, loss[loss=0.1385, simple_loss=0.2209, pruned_loss=0.02806, over 7257.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2422, pruned_loss=0.02853, over 1422434.16 frames.], batch size: 17, lr: 2.15e-04
+2022-05-16 01:52:52,274 INFO [train.py:812] (1/8) Epoch 36, batch 3500, loss[loss=0.1743, simple_loss=0.2797, pruned_loss=0.03444, over 7415.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2424, pruned_loss=0.02875, over 1419111.86 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 01:53:50,969 INFO [train.py:812] (1/8) Epoch 36, batch 3550, loss[loss=0.1662, simple_loss=0.2673, pruned_loss=0.0325, over 7099.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2427, pruned_loss=0.02878, over 1423002.17 frames.], batch size: 28, lr: 2.15e-04
+2022-05-16 01:54:49,015 INFO [train.py:812] (1/8) Epoch 36, batch 3600, loss[loss=0.1484, simple_loss=0.2403, pruned_loss=0.02826, over 7295.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2428, pruned_loss=0.02849, over 1421426.18 frames.], batch size: 25, lr: 2.15e-04
+2022-05-16 01:55:48,169 INFO [train.py:812] (1/8) Epoch 36, batch 3650, loss[loss=0.1643, simple_loss=0.2582, pruned_loss=0.03522, over 7303.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2432, pruned_loss=0.02871, over 1424054.80 frames.], batch size: 24, lr: 2.15e-04
+2022-05-16 01:56:46,031 INFO [train.py:812] (1/8) Epoch 36, batch 3700, loss[loss=0.144, simple_loss=0.244, pruned_loss=0.02197, over 7114.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2432, pruned_loss=0.02915, over 1427286.87 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 01:57:44,752 INFO [train.py:812] (1/8) Epoch 36, batch 3750, loss[loss=0.1389, simple_loss=0.232, pruned_loss=0.02287, over 7330.00 frames.], tot_loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.02887, over 1426905.07 frames.], batch size: 22, lr: 2.15e-04
+2022-05-16 01:58:43,593 INFO [train.py:812] (1/8) Epoch 36, batch 3800, loss[loss=0.1479, simple_loss=0.2331, pruned_loss=0.03132, over 7367.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2439, pruned_loss=0.02936, over 1428660.78 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 01:59:42,783 INFO [train.py:812] (1/8) Epoch 36, batch 3850, loss[loss=0.1274, simple_loss=0.2126, pruned_loss=0.02109, over 6989.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2441, pruned_loss=0.02973, over 1424016.85 frames.], batch size: 16, lr: 2.15e-04
+2022-05-16 02:00:41,792 INFO [train.py:812] (1/8) Epoch 36, batch 3900, loss[loss=0.1489, simple_loss=0.2458, pruned_loss=0.02598, over 7191.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2433, pruned_loss=0.02959, over 1425563.34 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 02:01:40,061 INFO [train.py:812] (1/8) Epoch 36, batch 3950, loss[loss=0.1477, simple_loss=0.2476, pruned_loss=0.0239, over 6800.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2442, pruned_loss=0.02959, over 1424094.46 frames.], batch size: 31, lr: 2.15e-04
+2022-05-16 02:02:38,471 INFO [train.py:812] (1/8) Epoch 36, batch 4000, loss[loss=0.157, simple_loss=0.2469, pruned_loss=0.03348, over 7009.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2446, pruned_loss=0.02938, over 1423879.14 frames.], batch size: 28, lr: 2.15e-04
+2022-05-16 02:03:36,276 INFO [train.py:812] (1/8) Epoch 36, batch 4050, loss[loss=0.1556, simple_loss=0.2507, pruned_loss=0.03029, over 7224.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2431, pruned_loss=0.02891, over 1426528.85 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 02:04:34,901 INFO [train.py:812] (1/8) Epoch 36, batch 4100, loss[loss=0.1181, simple_loss=0.206, pruned_loss=0.01507, over 7120.00 frames.], tot_loss[loss=0.1503, simple_loss=0.243, pruned_loss=0.02882, over 1426685.77 frames.], batch size: 17, lr: 2.15e-04
+2022-05-16 02:05:34,475 INFO [train.py:812] (1/8) Epoch 36, batch 4150, loss[loss=0.1525, simple_loss=0.2507, pruned_loss=0.02713, over 7195.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2422, pruned_loss=0.02852, over 1418605.80 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 02:06:32,907 INFO [train.py:812] (1/8) Epoch 36, batch 4200, loss[loss=0.145, simple_loss=0.2413, pruned_loss=0.02436, over 7242.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2421, pruned_loss=0.02858, over 1416204.61 frames.], batch size: 20, lr: 2.15e-04
+2022-05-16 02:07:31,846 INFO [train.py:812] (1/8) Epoch 36, batch 4250, loss[loss=0.1487, simple_loss=0.2537, pruned_loss=0.02187, over 7214.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.0287, over 1415054.09 frames.], batch size: 22, lr: 2.15e-04
+2022-05-16 02:08:30,999 INFO [train.py:812] (1/8) Epoch 36, batch 4300, loss[loss=0.165, simple_loss=0.2588, pruned_loss=0.03562, over 7196.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2422, pruned_loss=0.02853, over 1410853.18 frames.], batch size: 22, lr: 2.15e-04
+2022-05-16 02:09:30,588 INFO [train.py:812] (1/8) Epoch 36, batch 4350, loss[loss=0.1404, simple_loss=0.234, pruned_loss=0.02339, over 7435.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2408, pruned_loss=0.02837, over 1411216.55 frames.], batch size: 20, lr: 2.15e-04
+2022-05-16 02:10:29,630 INFO [train.py:812] (1/8) Epoch 36, batch 4400, loss[loss=0.1414, simple_loss=0.2343, pruned_loss=0.02423, over 7367.00 frames.], tot_loss[loss=0.1481, simple_loss=0.24, pruned_loss=0.02804, over 1415497.85 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 02:11:29,739 INFO [train.py:812] (1/8) Epoch 36, batch 4450, loss[loss=0.1306, simple_loss=0.2291, pruned_loss=0.01607, over 7220.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2391, pruned_loss=0.02785, over 1405054.13 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 02:12:28,143 INFO [train.py:812] (1/8) Epoch 36, batch 4500, loss[loss=0.1378, simple_loss=0.2292, pruned_loss=0.02318, over 7217.00 frames.], tot_loss[loss=0.1483, simple_loss=0.24, pruned_loss=0.02825, over 1393348.11 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 02:13:26,414 INFO [train.py:812] (1/8) Epoch 36, batch 4550, loss[loss=0.1308, simple_loss=0.2251, pruned_loss=0.01824, over 7263.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2417, pruned_loss=0.02951, over 1356039.12 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 02:14:35,967 INFO [train.py:812] (1/8) Epoch 37, batch 0, loss[loss=0.1428, simple_loss=0.2323, pruned_loss=0.02664, over 7346.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2323, pruned_loss=0.02664, over 7346.00 frames.], batch size: 22, lr: 2.12e-04
+2022-05-16 02:15:34,999 INFO [train.py:812] (1/8) Epoch 37, batch 50, loss[loss=0.126, simple_loss=0.2072, pruned_loss=0.02243, over 7074.00 frames.], tot_loss[loss=0.1512, simple_loss=0.244, pruned_loss=0.02914, over 321196.29 frames.], batch size: 18, lr: 2.12e-04
+2022-05-16 02:16:33,774 INFO [train.py:812] (1/8) Epoch 37, batch 100, loss[loss=0.1666, simple_loss=0.2578, pruned_loss=0.03774, over 7319.00 frames.], tot_loss[loss=0.1512, simple_loss=0.244, pruned_loss=0.02919, over 566884.63 frames.], batch size: 20, lr: 2.12e-04
+2022-05-16 02:17:32,745 INFO [train.py:812] (1/8) Epoch 37, batch 150, loss[loss=0.143, simple_loss=0.2341, pruned_loss=0.02599, over 7025.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2442, pruned_loss=0.02978, over 754635.25 frames.], batch size: 28, lr: 2.11e-04
+2022-05-16 02:18:31,114 INFO [train.py:812] (1/8) Epoch 37, batch 200, loss[loss=0.1403, simple_loss=0.2407, pruned_loss=0.01992, over 7328.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2459, pruned_loss=0.0304, over 905967.42 frames.], batch size: 21, lr: 2.11e-04
+2022-05-16 02:19:29,652 INFO [train.py:812] (1/8) Epoch 37, batch 250, loss[loss=0.1306, simple_loss=0.2214, pruned_loss=0.01986, over 7267.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2439, pruned_loss=0.02937, over 1018274.69 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:20:28,586 INFO [train.py:812] (1/8) Epoch 37, batch 300, loss[loss=0.1624, simple_loss=0.2575, pruned_loss=0.03363, over 7337.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2433, pruned_loss=0.02951, over 1104541.60 frames.], batch size: 22, lr: 2.11e-04
+2022-05-16 02:21:27,113 INFO [train.py:812] (1/8) Epoch 37, batch 350, loss[loss=0.138, simple_loss=0.2332, pruned_loss=0.02141, over 7162.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2436, pruned_loss=0.02935, over 1173665.05 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:22:25,668 INFO [train.py:812] (1/8) Epoch 37, batch 400, loss[loss=0.1653, simple_loss=0.2615, pruned_loss=0.03453, over 7234.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02914, over 1232803.33 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:23:24,546 INFO [train.py:812] (1/8) Epoch 37, batch 450, loss[loss=0.1405, simple_loss=0.2312, pruned_loss=0.02496, over 7147.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2427, pruned_loss=0.02872, over 1277177.23 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:24:21,847 INFO [train.py:812] (1/8) Epoch 37, batch 500, loss[loss=0.1385, simple_loss=0.2323, pruned_loss=0.0223, over 7239.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2426, pruned_loss=0.02888, over 1306498.75 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:25:21,127 INFO [train.py:812] (1/8) Epoch 37, batch 550, loss[loss=0.1318, simple_loss=0.2266, pruned_loss=0.01848, over 7069.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2428, pruned_loss=0.02884, over 1322788.80 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:26:19,466 INFO [train.py:812] (1/8) Epoch 37, batch 600, loss[loss=0.1588, simple_loss=0.2495, pruned_loss=0.03408, over 7445.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.02888, over 1348069.09 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:27:18,098 INFO [train.py:812] (1/8) Epoch 37, batch 650, loss[loss=0.1242, simple_loss=0.2152, pruned_loss=0.0166, over 7136.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2403, pruned_loss=0.02852, over 1367433.91 frames.], batch size: 17, lr: 2.11e-04
+2022-05-16 02:28:16,741 INFO [train.py:812] (1/8) Epoch 37, batch 700, loss[loss=0.1326, simple_loss=0.235, pruned_loss=0.01504, over 7229.00 frames.], tot_loss[loss=0.1478, simple_loss=0.24, pruned_loss=0.02782, over 1380160.66 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:29:16,760 INFO [train.py:812] (1/8) Epoch 37, batch 750, loss[loss=0.1404, simple_loss=0.2283, pruned_loss=0.02626, over 7160.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2402, pruned_loss=0.02779, over 1388651.08 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:30:15,259 INFO [train.py:812] (1/8) Epoch 37, batch 800, loss[loss=0.1374, simple_loss=0.2189, pruned_loss=0.02794, over 7419.00 frames.], tot_loss[loss=0.148, simple_loss=0.2399, pruned_loss=0.02804, over 1398942.24 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:31:14,047 INFO [train.py:812] (1/8) Epoch 37, batch 850, loss[loss=0.1365, simple_loss=0.2234, pruned_loss=0.02482, over 7260.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2403, pruned_loss=0.02818, over 1398078.13 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:32:12,864 INFO [train.py:812] (1/8) Epoch 37, batch 900, loss[loss=0.1383, simple_loss=0.2315, pruned_loss=0.0225, over 7070.00 frames.], tot_loss[loss=0.148, simple_loss=0.2402, pruned_loss=0.02793, over 1407063.53 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:33:11,828 INFO [train.py:812] (1/8) Epoch 37, batch 950, loss[loss=0.1221, simple_loss=0.2007, pruned_loss=0.02174, over 7292.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2399, pruned_loss=0.02811, over 1410605.55 frames.], batch size: 17, lr: 2.11e-04
+2022-05-16 02:34:09,790 INFO [train.py:812] (1/8) Epoch 37, batch 1000, loss[loss=0.1886, simple_loss=0.2871, pruned_loss=0.045, over 6855.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2402, pruned_loss=0.02811, over 1412942.19 frames.], batch size: 31, lr: 2.11e-04
+2022-05-16 02:35:08,649 INFO [train.py:812] (1/8) Epoch 37, batch 1050, loss[loss=0.1712, simple_loss=0.2765, pruned_loss=0.03294, over 7391.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2404, pruned_loss=0.02838, over 1417319.09 frames.], batch size: 23, lr: 2.11e-04
+2022-05-16 02:36:07,862 INFO [train.py:812] (1/8) Epoch 37, batch 1100, loss[loss=0.1646, simple_loss=0.2719, pruned_loss=0.02868, over 7224.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2407, pruned_loss=0.02855, over 1419456.82 frames.], batch size: 21, lr: 2.11e-04
+2022-05-16 02:37:06,614 INFO [train.py:812] (1/8) Epoch 37, batch 1150, loss[loss=0.1418, simple_loss=0.2296, pruned_loss=0.02706, over 4751.00 frames.], tot_loss[loss=0.149, simple_loss=0.241, pruned_loss=0.02851, over 1417758.58 frames.], batch size: 52, lr: 2.11e-04
+2022-05-16 02:38:04,304 INFO [train.py:812] (1/8) Epoch 37, batch 1200, loss[loss=0.1555, simple_loss=0.2517, pruned_loss=0.02963, over 7153.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2429, pruned_loss=0.0291, over 1419773.86 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:39:03,405 INFO [train.py:812] (1/8) Epoch 37, batch 1250, loss[loss=0.1601, simple_loss=0.2512, pruned_loss=0.03455, over 7211.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2434, pruned_loss=0.02909, over 1420552.09 frames.], batch size: 22, lr: 2.11e-04
+2022-05-16 02:40:01,885 INFO [train.py:812] (1/8) Epoch 37, batch 1300, loss[loss=0.1348, simple_loss=0.2201, pruned_loss=0.02476, over 7137.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2441, pruned_loss=0.02924, over 1422383.28 frames.], batch size: 17, lr: 2.11e-04
+2022-05-16 02:41:00,874 INFO [train.py:812] (1/8) Epoch 37, batch 1350, loss[loss=0.1375, simple_loss=0.2315, pruned_loss=0.02177, over 7079.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2439, pruned_loss=0.02929, over 1417825.93 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:41:59,965 INFO [train.py:812] (1/8) Epoch 37, batch 1400, loss[loss=0.1293, simple_loss=0.2118, pruned_loss=0.02345, over 6987.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2431, pruned_loss=0.02889, over 1417970.62 frames.], batch size: 16, lr: 2.11e-04
+2022-05-16 02:42:58,487 INFO [train.py:812] (1/8) Epoch 37, batch 1450, loss[loss=0.1457, simple_loss=0.2396, pruned_loss=0.02588, over 7273.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2425, pruned_loss=0.02861, over 1419893.27 frames.], batch size: 24, lr: 2.11e-04
+2022-05-16 02:43:56,632 INFO [train.py:812] (1/8) Epoch 37, batch 1500, loss[loss=0.161, simple_loss=0.2605, pruned_loss=0.03074, over 7293.00 frames.], tot_loss[loss=0.15, simple_loss=0.2424, pruned_loss=0.02877, over 1416131.96 frames.], batch size: 24, lr: 2.11e-04
+2022-05-16 02:44:55,813 INFO [train.py:812] (1/8) Epoch 37, batch 1550, loss[loss=0.1439, simple_loss=0.2358, pruned_loss=0.02601, over 6730.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.02892, over 1410412.16 frames.], batch size: 31, lr: 2.11e-04
+2022-05-16 02:45:54,003 INFO [train.py:812] (1/8) Epoch 37, batch 1600, loss[loss=0.1715, simple_loss=0.2576, pruned_loss=0.04268, over 7384.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2421, pruned_loss=0.02903, over 1410845.72 frames.], batch size: 23, lr: 2.11e-04
+2022-05-16 02:46:52,093 INFO [train.py:812] (1/8) Epoch 37, batch 1650, loss[loss=0.159, simple_loss=0.2604, pruned_loss=0.02885, over 7200.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02895, over 1414416.63 frames.], batch size: 22, lr: 2.11e-04
+2022-05-16 02:47:50,659 INFO [train.py:812] (1/8) Epoch 37, batch 1700, loss[loss=0.1404, simple_loss=0.2252, pruned_loss=0.02776, over 7149.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.02893, over 1412980.73 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:48:48,767 INFO [train.py:812] (1/8) Epoch 37, batch 1750, loss[loss=0.1646, simple_loss=0.2525, pruned_loss=0.0383, over 7355.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2424, pruned_loss=0.02921, over 1407925.79 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 02:49:47,208 INFO [train.py:812] (1/8) Epoch 37, batch 1800, loss[loss=0.1551, simple_loss=0.257, pruned_loss=0.02664, over 7284.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02911, over 1410777.37 frames.], batch size: 24, lr: 2.10e-04
+2022-05-16 02:50:46,343 INFO [train.py:812] (1/8) Epoch 37, batch 1850, loss[loss=0.1303, simple_loss=0.2158, pruned_loss=0.02239, over 7267.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2421, pruned_loss=0.02903, over 1410841.77 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 02:51:45,052 INFO [train.py:812] (1/8) Epoch 37, batch 1900, loss[loss=0.1385, simple_loss=0.23, pruned_loss=0.02353, over 6855.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02918, over 1417028.54 frames.], batch size: 31, lr: 2.10e-04
+2022-05-16 02:52:44,044 INFO [train.py:812] (1/8) Epoch 37, batch 1950, loss[loss=0.1421, simple_loss=0.2395, pruned_loss=0.02237, over 7214.00 frames.], tot_loss[loss=0.1498, simple_loss=0.242, pruned_loss=0.0288, over 1420734.51 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 02:53:42,347 INFO [train.py:812] (1/8) Epoch 37, batch 2000, loss[loss=0.1349, simple_loss=0.2271, pruned_loss=0.02137, over 7402.00 frames.], tot_loss[loss=0.1497, simple_loss=0.242, pruned_loss=0.02868, over 1417697.17 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 02:54:41,771 INFO [train.py:812] (1/8) Epoch 37, batch 2050, loss[loss=0.1397, simple_loss=0.2456, pruned_loss=0.0169, over 7230.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2417, pruned_loss=0.02841, over 1420389.25 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 02:55:38,573 INFO [train.py:812] (1/8) Epoch 37, batch 2100, loss[loss=0.1691, simple_loss=0.2636, pruned_loss=0.03733, over 7145.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2419, pruned_loss=0.02857, over 1420553.10 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 02:56:46,818 INFO [train.py:812] (1/8) Epoch 37, batch 2150, loss[loss=0.1612, simple_loss=0.2522, pruned_loss=0.03514, over 7414.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2423, pruned_loss=0.02865, over 1418888.32 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 02:57:45,156 INFO [train.py:812] (1/8) Epoch 37, batch 2200, loss[loss=0.1308, simple_loss=0.2174, pruned_loss=0.02212, over 7256.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2424, pruned_loss=0.02863, over 1419991.24 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 02:58:53,432 INFO [train.py:812] (1/8) Epoch 37, batch 2250, loss[loss=0.1793, simple_loss=0.2902, pruned_loss=0.03421, over 7155.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2432, pruned_loss=0.02893, over 1420735.85 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 03:00:01,340 INFO [train.py:812] (1/8) Epoch 37, batch 2300, loss[loss=0.1696, simple_loss=0.266, pruned_loss=0.03656, over 7208.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2434, pruned_loss=0.02913, over 1420278.11 frames.], batch size: 23, lr: 2.10e-04
+2022-05-16 03:01:00,994 INFO [train.py:812] (1/8) Epoch 37, batch 2350, loss[loss=0.1283, simple_loss=0.2057, pruned_loss=0.02549, over 7279.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2432, pruned_loss=0.0292, over 1413335.60 frames.], batch size: 17, lr: 2.10e-04
+2022-05-16 03:01:59,217 INFO [train.py:812] (1/8) Epoch 37, batch 2400, loss[loss=0.1668, simple_loss=0.2668, pruned_loss=0.03335, over 7304.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2438, pruned_loss=0.02922, over 1419092.42 frames.], batch size: 25, lr: 2.10e-04
+2022-05-16 03:02:57,110 INFO [train.py:812] (1/8) Epoch 37, batch 2450, loss[loss=0.1602, simple_loss=0.2578, pruned_loss=0.03134, over 7176.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2435, pruned_loss=0.02906, over 1424587.21 frames.], batch size: 26, lr: 2.10e-04
+2022-05-16 03:04:04,664 INFO [train.py:812] (1/8) Epoch 37, batch 2500, loss[loss=0.154, simple_loss=0.2533, pruned_loss=0.02734, over 7162.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2425, pruned_loss=0.02857, over 1427148.59 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 03:05:04,379 INFO [train.py:812] (1/8) Epoch 37, batch 2550, loss[loss=0.1698, simple_loss=0.2602, pruned_loss=0.0397, over 7277.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2421, pruned_loss=0.0285, over 1428089.14 frames.], batch size: 24, lr: 2.10e-04
+2022-05-16 03:06:02,646 INFO [train.py:812] (1/8) Epoch 37, batch 2600, loss[loss=0.1411, simple_loss=0.2257, pruned_loss=0.02826, over 6823.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.02873, over 1424488.46 frames.], batch size: 15, lr: 2.10e-04
+2022-05-16 03:07:21,594 INFO [train.py:812] (1/8) Epoch 37, batch 2650, loss[loss=0.1716, simple_loss=0.2585, pruned_loss=0.04237, over 7202.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.02901, over 1427467.65 frames.], batch size: 22, lr: 2.10e-04
+2022-05-16 03:08:19,637 INFO [train.py:812] (1/8) Epoch 37, batch 2700, loss[loss=0.1661, simple_loss=0.2542, pruned_loss=0.03893, over 6363.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02882, over 1423418.03 frames.], batch size: 38, lr: 2.10e-04
+2022-05-16 03:09:18,867 INFO [train.py:812] (1/8) Epoch 37, batch 2750, loss[loss=0.1628, simple_loss=0.2473, pruned_loss=0.03916, over 5010.00 frames.], tot_loss[loss=0.15, simple_loss=0.2424, pruned_loss=0.02876, over 1423959.34 frames.], batch size: 52, lr: 2.10e-04
+2022-05-16 03:10:17,005 INFO [train.py:812] (1/8) Epoch 37, batch 2800, loss[loss=0.1445, simple_loss=0.2282, pruned_loss=0.03037, over 7276.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2414, pruned_loss=0.02844, over 1428530.90 frames.], batch size: 18, lr: 2.10e-04
+2022-05-16 03:11:34,307 INFO [train.py:812] (1/8) Epoch 37, batch 2850, loss[loss=0.146, simple_loss=0.2478, pruned_loss=0.02213, over 6623.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2419, pruned_loss=0.02842, over 1428151.09 frames.], batch size: 38, lr: 2.10e-04
+2022-05-16 03:12:32,635 INFO [train.py:812] (1/8) Epoch 37, batch 2900, loss[loss=0.1317, simple_loss=0.2124, pruned_loss=0.02548, over 6997.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2421, pruned_loss=0.02833, over 1429931.30 frames.], batch size: 16, lr: 2.10e-04
+2022-05-16 03:13:31,853 INFO [train.py:812] (1/8) Epoch 37, batch 2950, loss[loss=0.1382, simple_loss=0.2317, pruned_loss=0.0223, over 7420.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2419, pruned_loss=0.02818, over 1426445.17 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 03:14:30,566 INFO [train.py:812] (1/8) Epoch 37, batch 3000, loss[loss=0.1441, simple_loss=0.2465, pruned_loss=0.02087, over 7226.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2426, pruned_loss=0.02884, over 1422748.54 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 03:14:30,567 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-16 03:14:38,087 INFO [train.py:841] (1/8) Epoch 37, validation: loss=0.1539, simple_loss=0.2491, pruned_loss=0.02931, over 698248.00 frames.
+2022-05-16 03:15:37,667 INFO [train.py:812] (1/8) Epoch 37, batch 3050, loss[loss=0.1473, simple_loss=0.2306, pruned_loss=0.03203, over 7196.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2422, pruned_loss=0.02896, over 1421352.94 frames.], batch size: 16, lr: 2.10e-04
+2022-05-16 03:16:36,460 INFO [train.py:812] (1/8) Epoch 37, batch 3100, loss[loss=0.1501, simple_loss=0.2414, pruned_loss=0.02936, over 7079.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.02923, over 1419503.75 frames.], batch size: 18, lr: 2.10e-04
+2022-05-16 03:17:34,872 INFO [train.py:812] (1/8) Epoch 37, batch 3150, loss[loss=0.1342, simple_loss=0.2234, pruned_loss=0.02251, over 7002.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2424, pruned_loss=0.0293, over 1417413.08 frames.], batch size: 16, lr: 2.10e-04
+2022-05-16 03:18:33,953 INFO [train.py:812] (1/8) Epoch 37, batch 3200, loss[loss=0.1592, simple_loss=0.2473, pruned_loss=0.03552, over 4870.00 frames.], tot_loss[loss=0.151, simple_loss=0.2428, pruned_loss=0.02959, over 1417682.29 frames.], batch size: 52, lr: 2.10e-04
+2022-05-16 03:19:33,513 INFO [train.py:812] (1/8) Epoch 37, batch 3250, loss[loss=0.1604, simple_loss=0.256, pruned_loss=0.03242, over 7184.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2431, pruned_loss=0.02967, over 1416689.15 frames.], batch size: 22, lr: 2.10e-04
+2022-05-16 03:20:31,431 INFO [train.py:812] (1/8) Epoch 37, batch 3300, loss[loss=0.1392, simple_loss=0.2386, pruned_loss=0.0199, over 7414.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02971, over 1413611.86 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 03:21:29,306 INFO [train.py:812] (1/8) Epoch 37, batch 3350, loss[loss=0.1884, simple_loss=0.2776, pruned_loss=0.04953, over 7401.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2438, pruned_loss=0.02972, over 1410763.04 frames.], batch size: 23, lr: 2.09e-04
+2022-05-16 03:22:27,827 INFO [train.py:812] (1/8) Epoch 37, batch 3400, loss[loss=0.1376, simple_loss=0.2227, pruned_loss=0.02628, over 7139.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02947, over 1416232.32 frames.], batch size: 17, lr: 2.09e-04
+2022-05-16 03:23:27,198 INFO [train.py:812] (1/8) Epoch 37, batch 3450, loss[loss=0.1168, simple_loss=0.1979, pruned_loss=0.01784, over 7267.00 frames.], tot_loss[loss=0.151, simple_loss=0.2428, pruned_loss=0.02962, over 1419192.60 frames.], batch size: 17, lr: 2.09e-04
+2022-05-16 03:24:25,218 INFO [train.py:812] (1/8) Epoch 37, batch 3500, loss[loss=0.1429, simple_loss=0.2389, pruned_loss=0.02346, over 7351.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02973, over 1417174.31 frames.], batch size: 19, lr: 2.09e-04
+2022-05-16 03:25:24,377 INFO [train.py:812] (1/8) Epoch 37, batch 3550, loss[loss=0.1213, simple_loss=0.2115, pruned_loss=0.01557, over 6770.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02921, over 1414578.02 frames.], batch size: 15, lr: 2.09e-04
+2022-05-16 03:26:23,185 INFO [train.py:812] (1/8) Epoch 37, batch 3600, loss[loss=0.1329, simple_loss=0.2217, pruned_loss=0.02205, over 7005.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02879, over 1421402.62 frames.], batch size: 16, lr: 2.09e-04
+2022-05-16 03:27:22,033 INFO [train.py:812] (1/8) Epoch 37, batch 3650, loss[loss=0.1921, simple_loss=0.2744, pruned_loss=0.05493, over 7150.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2415, pruned_loss=0.02854, over 1423522.68 frames.], batch size: 19, lr: 2.09e-04
+2022-05-16 03:28:20,580 INFO [train.py:812] (1/8) Epoch 37, batch 3700, loss[loss=0.1732, simple_loss=0.2583, pruned_loss=0.04403, over 7243.00 frames.], tot_loss[loss=0.149, simple_loss=0.241, pruned_loss=0.02846, over 1426912.99 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:29:19,683 INFO [train.py:812] (1/8) Epoch 37, batch 3750, loss[loss=0.1721, simple_loss=0.2748, pruned_loss=0.03464, over 7296.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.02883, over 1423567.20 frames.], batch size: 24, lr: 2.09e-04
+2022-05-16 03:30:17,092 INFO [train.py:812] (1/8) Epoch 37, batch 3800, loss[loss=0.1282, simple_loss=0.2122, pruned_loss=0.02212, over 7262.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2414, pruned_loss=0.02865, over 1424773.92 frames.], batch size: 17, lr: 2.09e-04
+2022-05-16 03:31:15,851 INFO [train.py:812] (1/8) Epoch 37, batch 3850, loss[loss=0.1776, simple_loss=0.2709, pruned_loss=0.04218, over 4857.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2413, pruned_loss=0.0289, over 1423773.42 frames.], batch size: 52, lr: 2.09e-04
+2022-05-16 03:32:12,583 INFO [train.py:812] (1/8) Epoch 37, batch 3900, loss[loss=0.1525, simple_loss=0.2428, pruned_loss=0.03112, over 7321.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2412, pruned_loss=0.02882, over 1425264.50 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:33:11,475 INFO [train.py:812] (1/8) Epoch 37, batch 3950, loss[loss=0.143, simple_loss=0.2352, pruned_loss=0.02539, over 7276.00 frames.], tot_loss[loss=0.1502, simple_loss=0.242, pruned_loss=0.02917, over 1426078.93 frames.], batch size: 18, lr: 2.09e-04
+2022-05-16 03:34:09,777 INFO [train.py:812] (1/8) Epoch 37, batch 4000, loss[loss=0.1298, simple_loss=0.2251, pruned_loss=0.01731, over 7156.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2417, pruned_loss=0.02868, over 1427015.81 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:35:09,215 INFO [train.py:812] (1/8) Epoch 37, batch 4050, loss[loss=0.1628, simple_loss=0.2625, pruned_loss=0.03149, over 7145.00 frames.], tot_loss[loss=0.149, simple_loss=0.2413, pruned_loss=0.02835, over 1426562.77 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:36:06,888 INFO [train.py:812] (1/8) Epoch 37, batch 4100, loss[loss=0.1463, simple_loss=0.2497, pruned_loss=0.0215, over 7302.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2423, pruned_loss=0.02862, over 1424063.65 frames.], batch size: 25, lr: 2.09e-04
+2022-05-16 03:37:05,678 INFO [train.py:812] (1/8) Epoch 37, batch 4150, loss[loss=0.1578, simple_loss=0.2504, pruned_loss=0.03256, over 7226.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2418, pruned_loss=0.02879, over 1425858.77 frames.], batch size: 21, lr: 2.09e-04
+2022-05-16 03:38:02,984 INFO [train.py:812] (1/8) Epoch 37, batch 4200, loss[loss=0.1492, simple_loss=0.2458, pruned_loss=0.02625, over 7327.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2414, pruned_loss=0.02844, over 1428502.02 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:39:02,446 INFO [train.py:812] (1/8) Epoch 37, batch 4250, loss[loss=0.1341, simple_loss=0.2219, pruned_loss=0.02318, over 7201.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2412, pruned_loss=0.02892, over 1431006.37 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:40:00,851 INFO [train.py:812] (1/8) Epoch 37, batch 4300, loss[loss=0.149, simple_loss=0.2435, pruned_loss=0.02725, over 7332.00 frames.], tot_loss[loss=0.1503, simple_loss=0.242, pruned_loss=0.02932, over 1425919.09 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:41:00,626 INFO [train.py:812] (1/8) Epoch 37, batch 4350, loss[loss=0.154, simple_loss=0.2563, pruned_loss=0.02583, over 7320.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2421, pruned_loss=0.02911, over 1430534.13 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:41:59,223 INFO [train.py:812] (1/8) Epoch 37, batch 4400, loss[loss=0.171, simple_loss=0.2626, pruned_loss=0.03969, over 7331.00 frames.], tot_loss[loss=0.1499, simple_loss=0.242, pruned_loss=0.02889, over 1422758.83 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:42:59,059 INFO [train.py:812] (1/8) Epoch 37, batch 4450, loss[loss=0.124, simple_loss=0.2086, pruned_loss=0.01968, over 7408.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02905, over 1421104.47 frames.], batch size: 18, lr: 2.09e-04
+2022-05-16 03:43:58,022 INFO [train.py:812] (1/8) Epoch 37, batch 4500, loss[loss=0.1297, simple_loss=0.2162, pruned_loss=0.02163, over 7270.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2424, pruned_loss=0.029, over 1415865.68 frames.], batch size: 18, lr: 2.09e-04
+2022-05-16 03:44:56,286 INFO [train.py:812] (1/8) Epoch 37, batch 4550, loss[loss=0.1546, simple_loss=0.2563, pruned_loss=0.02642, over 6234.00 frames.], tot_loss[loss=0.1516, simple_loss=0.244, pruned_loss=0.02963, over 1392796.47 frames.], batch size: 37, lr: 2.09e-04
+2022-05-16 03:46:01,496 INFO [train.py:812] (1/8) Epoch 38, batch 0, loss[loss=0.1283, simple_loss=0.2225, pruned_loss=0.01704, over 7365.00 frames.], tot_loss[loss=0.1283, simple_loss=0.2225, pruned_loss=0.01704, over 7365.00 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:47:10,799 INFO [train.py:812] (1/8) Epoch 38, batch 50, loss[loss=0.15, simple_loss=0.2453, pruned_loss=0.02736, over 6436.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2382, pruned_loss=0.02744, over 322563.42 frames.], batch size: 38, lr: 2.06e-04
+2022-05-16 03:48:09,433 INFO [train.py:812] (1/8) Epoch 38, batch 100, loss[loss=0.1528, simple_loss=0.2412, pruned_loss=0.0322, over 7243.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02917, over 559152.85 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:49:08,228 INFO [train.py:812] (1/8) Epoch 38, batch 150, loss[loss=0.1465, simple_loss=0.2381, pruned_loss=0.02742, over 7362.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2433, pruned_loss=0.02955, over 747335.74 frames.], batch size: 23, lr: 2.06e-04
+2022-05-16 03:50:07,560 INFO [train.py:812] (1/8) Epoch 38, batch 200, loss[loss=0.1524, simple_loss=0.2542, pruned_loss=0.02529, over 7407.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2433, pruned_loss=0.02991, over 895405.59 frames.], batch size: 21, lr: 2.06e-04
+2022-05-16 03:51:06,653 INFO [train.py:812] (1/8) Epoch 38, batch 250, loss[loss=0.1485, simple_loss=0.2542, pruned_loss=0.02137, over 7356.00 frames.], tot_loss[loss=0.151, simple_loss=0.243, pruned_loss=0.02954, over 1013588.48 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:52:05,089 INFO [train.py:812] (1/8) Epoch 38, batch 300, loss[loss=0.1534, simple_loss=0.2481, pruned_loss=0.02932, over 7227.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02891, over 1104483.80 frames.], batch size: 20, lr: 2.06e-04
+2022-05-16 03:53:04,650 INFO [train.py:812] (1/8) Epoch 38, batch 350, loss[loss=0.1211, simple_loss=0.2085, pruned_loss=0.01683, over 7262.00 frames.], tot_loss[loss=0.1498, simple_loss=0.242, pruned_loss=0.02878, over 1171745.13 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:54:02,512 INFO [train.py:812] (1/8) Epoch 38, batch 400, loss[loss=0.151, simple_loss=0.2286, pruned_loss=0.03666, over 7258.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2409, pruned_loss=0.02823, over 1232407.03 frames.], batch size: 17, lr: 2.06e-04
+2022-05-16 03:55:02,018 INFO [train.py:812] (1/8) Epoch 38, batch 450, loss[loss=0.1418, simple_loss=0.2463, pruned_loss=0.01863, over 7112.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2407, pruned_loss=0.02826, over 1275799.25 frames.], batch size: 21, lr: 2.06e-04
+2022-05-16 03:56:00,722 INFO [train.py:812] (1/8) Epoch 38, batch 500, loss[loss=0.1229, simple_loss=0.2144, pruned_loss=0.0157, over 7280.00 frames.], tot_loss[loss=0.148, simple_loss=0.2399, pruned_loss=0.028, over 1311919.16 frames.], batch size: 18, lr: 2.06e-04
+2022-05-16 03:56:58,586 INFO [train.py:812] (1/8) Epoch 38, batch 550, loss[loss=0.1272, simple_loss=0.2235, pruned_loss=0.01549, over 7334.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2406, pruned_loss=0.02809, over 1335956.86 frames.], batch size: 20, lr: 2.06e-04
+2022-05-16 03:57:56,241 INFO [train.py:812] (1/8) Epoch 38, batch 600, loss[loss=0.171, simple_loss=0.2616, pruned_loss=0.04025, over 7380.00 frames.], tot_loss[loss=0.1495, simple_loss=0.242, pruned_loss=0.02847, over 1357569.10 frames.], batch size: 23, lr: 2.06e-04
+2022-05-16 03:58:54,201 INFO [train.py:812] (1/8) Epoch 38, batch 650, loss[loss=0.1535, simple_loss=0.2502, pruned_loss=0.02836, over 7329.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2423, pruned_loss=0.0285, over 1374095.62 frames.], batch size: 22, lr: 2.06e-04
+2022-05-16 03:59:53,354 INFO [train.py:812] (1/8) Epoch 38, batch 700, loss[loss=0.1532, simple_loss=0.2432, pruned_loss=0.03161, over 7166.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2423, pruned_loss=0.02845, over 1386164.48 frames.], batch size: 18, lr: 2.06e-04
+2022-05-16 04:00:52,139 INFO [train.py:812] (1/8) Epoch 38, batch 750, loss[loss=0.1669, simple_loss=0.2618, pruned_loss=0.03597, over 7396.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2423, pruned_loss=0.02806, over 1400673.69 frames.], batch size: 23, lr: 2.05e-04
+2022-05-16 04:01:50,316 INFO [train.py:812] (1/8) Epoch 38, batch 800, loss[loss=0.1312, simple_loss=0.2175, pruned_loss=0.02242, over 7408.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2423, pruned_loss=0.02801, over 1408183.73 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:02:49,129 INFO [train.py:812] (1/8) Epoch 38, batch 850, loss[loss=0.1577, simple_loss=0.2496, pruned_loss=0.03286, over 7359.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2427, pruned_loss=0.02789, over 1411325.98 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:03:47,716 INFO [train.py:812] (1/8) Epoch 38, batch 900, loss[loss=0.1507, simple_loss=0.2503, pruned_loss=0.02557, over 7283.00 frames.], tot_loss[loss=0.149, simple_loss=0.242, pruned_loss=0.02799, over 1412564.77 frames.], batch size: 24, lr: 2.05e-04
+2022-05-16 04:04:46,205 INFO [train.py:812] (1/8) Epoch 38, batch 950, loss[loss=0.1627, simple_loss=0.2453, pruned_loss=0.04004, over 7261.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2422, pruned_loss=0.02806, over 1417884.64 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:05:44,604 INFO [train.py:812] (1/8) Epoch 38, batch 1000, loss[loss=0.156, simple_loss=0.2478, pruned_loss=0.0321, over 7194.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2425, pruned_loss=0.02802, over 1420021.91 frames.], batch size: 22, lr: 2.05e-04
+2022-05-16 04:06:43,932 INFO [train.py:812] (1/8) Epoch 38, batch 1050, loss[loss=0.1545, simple_loss=0.2523, pruned_loss=0.02836, over 7325.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2425, pruned_loss=0.02821, over 1421054.64 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:07:41,763 INFO [train.py:812] (1/8) Epoch 38, batch 1100, loss[loss=0.129, simple_loss=0.2214, pruned_loss=0.01826, over 6810.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2426, pruned_loss=0.02834, over 1423952.37 frames.], batch size: 15, lr: 2.05e-04
+2022-05-16 04:08:41,050 INFO [train.py:812] (1/8) Epoch 38, batch 1150, loss[loss=0.1444, simple_loss=0.2275, pruned_loss=0.03066, over 7287.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2427, pruned_loss=0.02855, over 1420528.90 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:09:40,641 INFO [train.py:812] (1/8) Epoch 38, batch 1200, loss[loss=0.1376, simple_loss=0.2288, pruned_loss=0.02318, over 7157.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2433, pruned_loss=0.02853, over 1422308.30 frames.], batch size: 26, lr: 2.05e-04
+2022-05-16 04:10:39,702 INFO [train.py:812] (1/8) Epoch 38, batch 1250, loss[loss=0.1631, simple_loss=0.2566, pruned_loss=0.03477, over 6466.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2434, pruned_loss=0.02862, over 1426514.75 frames.], batch size: 38, lr: 2.05e-04
+2022-05-16 04:11:38,497 INFO [train.py:812] (1/8) Epoch 38, batch 1300, loss[loss=0.1249, simple_loss=0.2133, pruned_loss=0.01825, over 7292.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2438, pruned_loss=0.02896, over 1425608.96 frames.], batch size: 17, lr: 2.05e-04
+2022-05-16 04:12:36,173 INFO [train.py:812] (1/8) Epoch 38, batch 1350, loss[loss=0.1469, simple_loss=0.2451, pruned_loss=0.02436, over 7124.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2424, pruned_loss=0.02872, over 1419936.57 frames.], batch size: 21, lr: 2.05e-04
+2022-05-16 04:13:33,879 INFO [train.py:812] (1/8) Epoch 38, batch 1400, loss[loss=0.171, simple_loss=0.2636, pruned_loss=0.03919, over 7282.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2426, pruned_loss=0.02908, over 1420302.85 frames.], batch size: 24, lr: 2.05e-04
+2022-05-16 04:14:32,886 INFO [train.py:812] (1/8) Epoch 38, batch 1450, loss[loss=0.1686, simple_loss=0.2512, pruned_loss=0.04298, over 7211.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02913, over 1425275.58 frames.], batch size: 22, lr: 2.05e-04
+2022-05-16 04:15:31,391 INFO [train.py:812] (1/8) Epoch 38, batch 1500, loss[loss=0.1435, simple_loss=0.2426, pruned_loss=0.02219, over 7299.00 frames.], tot_loss[loss=0.1507, simple_loss=0.243, pruned_loss=0.02915, over 1426005.96 frames.], batch size: 25, lr: 2.05e-04
+2022-05-16 04:16:30,126 INFO [train.py:812] (1/8) Epoch 38, batch 1550, loss[loss=0.1508, simple_loss=0.2455, pruned_loss=0.02804, over 7251.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02913, over 1423060.13 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:17:27,389 INFO [train.py:812] (1/8) Epoch 38, batch 1600, loss[loss=0.1273, simple_loss=0.2156, pruned_loss=0.01954, over 7262.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.02925, over 1425547.22 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:18:25,538 INFO [train.py:812] (1/8) Epoch 38, batch 1650, loss[loss=0.1842, simple_loss=0.279, pruned_loss=0.04468, over 7045.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2434, pruned_loss=0.02941, over 1425266.55 frames.], batch size: 28, lr: 2.05e-04
+2022-05-16 04:19:24,093 INFO [train.py:812] (1/8) Epoch 38, batch 1700, loss[loss=0.1365, simple_loss=0.2253, pruned_loss=0.02382, over 7152.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.02926, over 1424016.91 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:20:24,538 INFO [train.py:812] (1/8) Epoch 38, batch 1750, loss[loss=0.1632, simple_loss=0.2546, pruned_loss=0.03591, over 5015.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2424, pruned_loss=0.02918, over 1422060.74 frames.], batch size: 52, lr: 2.05e-04
+2022-05-16 04:21:23,193 INFO [train.py:812] (1/8) Epoch 38, batch 1800, loss[loss=0.1405, simple_loss=0.2422, pruned_loss=0.01939, over 7330.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2414, pruned_loss=0.02883, over 1419961.90 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:22:21,145 INFO [train.py:812] (1/8) Epoch 38, batch 1850, loss[loss=0.1403, simple_loss=0.2236, pruned_loss=0.02848, over 7292.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2414, pruned_loss=0.02849, over 1422337.11 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:23:20,157 INFO [train.py:812] (1/8) Epoch 38, batch 1900, loss[loss=0.1551, simple_loss=0.2373, pruned_loss=0.03648, over 7194.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02894, over 1425228.60 frames.], batch size: 16, lr: 2.05e-04
+2022-05-16 04:24:18,771 INFO [train.py:812] (1/8) Epoch 38, batch 1950, loss[loss=0.1477, simple_loss=0.2336, pruned_loss=0.03093, over 7259.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02911, over 1427536.77 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:25:17,616 INFO [train.py:812] (1/8) Epoch 38, batch 2000, loss[loss=0.1343, simple_loss=0.2183, pruned_loss=0.02517, over 7405.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2429, pruned_loss=0.02906, over 1426248.09 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:26:16,387 INFO [train.py:812] (1/8) Epoch 38, batch 2050, loss[loss=0.139, simple_loss=0.232, pruned_loss=0.023, over 7254.00 frames.], tot_loss[loss=0.151, simple_loss=0.2435, pruned_loss=0.02928, over 1423318.06 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:27:14,045 INFO [train.py:812] (1/8) Epoch 38, batch 2100, loss[loss=0.157, simple_loss=0.2481, pruned_loss=0.03298, over 7143.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02951, over 1417978.57 frames.], batch size: 26, lr: 2.05e-04
+2022-05-16 04:28:12,421 INFO [train.py:812] (1/8) Epoch 38, batch 2150, loss[loss=0.1398, simple_loss=0.2375, pruned_loss=0.02104, over 7072.00 frames.], tot_loss[loss=0.151, simple_loss=0.2433, pruned_loss=0.02935, over 1417420.57 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:29:11,063 INFO [train.py:812] (1/8) Epoch 38, batch 2200, loss[loss=0.1395, simple_loss=0.2325, pruned_loss=0.02331, over 7065.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2439, pruned_loss=0.02915, over 1418644.43 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:30:15,081 INFO [train.py:812] (1/8) Epoch 38, batch 2250, loss[loss=0.1587, simple_loss=0.2547, pruned_loss=0.03135, over 6449.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2439, pruned_loss=0.0292, over 1417656.84 frames.], batch size: 38, lr: 2.05e-04
+2022-05-16 04:31:14,135 INFO [train.py:812] (1/8) Epoch 38, batch 2300, loss[loss=0.1521, simple_loss=0.2534, pruned_loss=0.02535, over 7074.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2436, pruned_loss=0.02865, over 1422025.81 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:32:13,290 INFO [train.py:812] (1/8) Epoch 38, batch 2350, loss[loss=0.1521, simple_loss=0.2386, pruned_loss=0.03282, over 7332.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2433, pruned_loss=0.0288, over 1419910.47 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:33:12,215 INFO [train.py:812] (1/8) Epoch 38, batch 2400, loss[loss=0.1458, simple_loss=0.2242, pruned_loss=0.03364, over 7395.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.02878, over 1424882.04 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:34:10,720 INFO [train.py:812] (1/8) Epoch 38, batch 2450, loss[loss=0.1264, simple_loss=0.2184, pruned_loss=0.01716, over 7327.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.02865, over 1426340.73 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:35:08,794 INFO [train.py:812] (1/8) Epoch 38, batch 2500, loss[loss=0.1643, simple_loss=0.2537, pruned_loss=0.03747, over 7169.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2421, pruned_loss=0.02852, over 1426754.78 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:36:06,685 INFO [train.py:812] (1/8) Epoch 38, batch 2550, loss[loss=0.1466, simple_loss=0.2359, pruned_loss=0.02869, over 7172.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2419, pruned_loss=0.02861, over 1424166.70 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:37:05,280 INFO [train.py:812] (1/8) Epoch 38, batch 2600, loss[loss=0.1599, simple_loss=0.2455, pruned_loss=0.03715, over 7432.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2407, pruned_loss=0.02801, over 1423285.19 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:38:03,417 INFO [train.py:812] (1/8) Epoch 38, batch 2650, loss[loss=0.1815, simple_loss=0.2651, pruned_loss=0.04899, over 7197.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2411, pruned_loss=0.02838, over 1424525.43 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 04:39:01,019 INFO [train.py:812] (1/8) Epoch 38, batch 2700, loss[loss=0.1463, simple_loss=0.2471, pruned_loss=0.02271, over 7242.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2405, pruned_loss=0.028, over 1424059.23 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:39:59,840 INFO [train.py:812] (1/8) Epoch 38, batch 2750, loss[loss=0.1278, simple_loss=0.2253, pruned_loss=0.01512, over 7367.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2408, pruned_loss=0.02817, over 1424881.22 frames.], batch size: 19, lr: 2.04e-04
+2022-05-16 04:40:57,545 INFO [train.py:812] (1/8) Epoch 38, batch 2800, loss[loss=0.1369, simple_loss=0.2352, pruned_loss=0.0193, over 7292.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2408, pruned_loss=0.02811, over 1422538.65 frames.], batch size: 24, lr: 2.04e-04
+2022-05-16 04:41:55,564 INFO [train.py:812] (1/8) Epoch 38, batch 2850, loss[loss=0.1332, simple_loss=0.2333, pruned_loss=0.01658, over 7421.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2407, pruned_loss=0.02808, over 1423078.33 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 04:42:54,111 INFO [train.py:812] (1/8) Epoch 38, batch 2900, loss[loss=0.138, simple_loss=0.2213, pruned_loss=0.02734, over 7148.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2407, pruned_loss=0.02843, over 1423484.50 frames.], batch size: 17, lr: 2.04e-04
+2022-05-16 04:43:53,030 INFO [train.py:812] (1/8) Epoch 38, batch 2950, loss[loss=0.1209, simple_loss=0.2038, pruned_loss=0.01904, over 7413.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2406, pruned_loss=0.02832, over 1428196.08 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:44:52,007 INFO [train.py:812] (1/8) Epoch 38, batch 3000, loss[loss=0.1473, simple_loss=0.2457, pruned_loss=0.0244, over 7201.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2401, pruned_loss=0.02777, over 1427259.48 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 04:44:52,008 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-16 04:44:59,416 INFO [train.py:841] (1/8) Epoch 38, validation: loss=0.1532, simple_loss=0.2484, pruned_loss=0.02898, over 698248.00 frames.
+2022-05-16 04:45:58,535 INFO [train.py:812] (1/8) Epoch 38, batch 3050, loss[loss=0.1363, simple_loss=0.2229, pruned_loss=0.0248, over 7175.00 frames.], tot_loss[loss=0.149, simple_loss=0.2411, pruned_loss=0.0284, over 1428093.49 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:46:56,197 INFO [train.py:812] (1/8) Epoch 38, batch 3100, loss[loss=0.1611, simple_loss=0.2553, pruned_loss=0.03344, over 7198.00 frames.], tot_loss[loss=0.1497, simple_loss=0.242, pruned_loss=0.02874, over 1420240.73 frames.], batch size: 22, lr: 2.04e-04
+2022-05-16 04:47:54,527 INFO [train.py:812] (1/8) Epoch 38, batch 3150, loss[loss=0.177, simple_loss=0.2558, pruned_loss=0.04908, over 7373.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02883, over 1419385.66 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 04:48:52,447 INFO [train.py:812] (1/8) Epoch 38, batch 3200, loss[loss=0.1568, simple_loss=0.2552, pruned_loss=0.02924, over 7120.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2418, pruned_loss=0.02895, over 1424058.45 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 04:49:51,335 INFO [train.py:812] (1/8) Epoch 38, batch 3250, loss[loss=0.1393, simple_loss=0.2285, pruned_loss=0.0251, over 7265.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2414, pruned_loss=0.02865, over 1425582.94 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:50:49,194 INFO [train.py:812] (1/8) Epoch 38, batch 3300, loss[loss=0.1491, simple_loss=0.2504, pruned_loss=0.02391, over 7234.00 frames.], tot_loss[loss=0.1488, simple_loss=0.241, pruned_loss=0.02832, over 1424749.50 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:51:47,394 INFO [train.py:812] (1/8) Epoch 38, batch 3350, loss[loss=0.1662, simple_loss=0.2564, pruned_loss=0.03805, over 7205.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2421, pruned_loss=0.02857, over 1425612.72 frames.], batch size: 22, lr: 2.04e-04
+2022-05-16 04:52:45,596 INFO [train.py:812] (1/8) Epoch 38, batch 3400, loss[loss=0.144, simple_loss=0.2445, pruned_loss=0.02174, over 6708.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2419, pruned_loss=0.02834, over 1429726.45 frames.], batch size: 31, lr: 2.04e-04
+2022-05-16 04:53:45,203 INFO [train.py:812] (1/8) Epoch 38, batch 3450, loss[loss=0.1516, simple_loss=0.2454, pruned_loss=0.02888, over 7437.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2417, pruned_loss=0.02807, over 1430925.20 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:54:43,554 INFO [train.py:812] (1/8) Epoch 38, batch 3500, loss[loss=0.147, simple_loss=0.2454, pruned_loss=0.02428, over 7238.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2417, pruned_loss=0.02827, over 1429283.21 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:55:41,790 INFO [train.py:812] (1/8) Epoch 38, batch 3550, loss[loss=0.1689, simple_loss=0.26, pruned_loss=0.03891, over 7154.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2431, pruned_loss=0.02853, over 1430053.81 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:56:49,630 INFO [train.py:812] (1/8) Epoch 38, batch 3600, loss[loss=0.1644, simple_loss=0.2541, pruned_loss=0.03731, over 6730.00 frames.], tot_loss[loss=0.1501, simple_loss=0.243, pruned_loss=0.02861, over 1428012.31 frames.], batch size: 31, lr: 2.04e-04
+2022-05-16 04:57:48,361 INFO [train.py:812] (1/8) Epoch 38, batch 3650, loss[loss=0.1649, simple_loss=0.2532, pruned_loss=0.03833, over 7080.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2431, pruned_loss=0.02868, over 1430966.68 frames.], batch size: 28, lr: 2.04e-04
+2022-05-16 04:58:46,156 INFO [train.py:812] (1/8) Epoch 38, batch 3700, loss[loss=0.1563, simple_loss=0.2519, pruned_loss=0.03033, over 7282.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2427, pruned_loss=0.02875, over 1423429.86 frames.], batch size: 24, lr: 2.04e-04
+2022-05-16 05:00:03,393 INFO [train.py:812] (1/8) Epoch 38, batch 3750, loss[loss=0.1639, simple_loss=0.2556, pruned_loss=0.03613, over 7167.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2431, pruned_loss=0.02886, over 1418771.59 frames.], batch size: 19, lr: 2.04e-04
+2022-05-16 05:01:01,781 INFO [train.py:812] (1/8) Epoch 38, batch 3800, loss[loss=0.1544, simple_loss=0.2423, pruned_loss=0.03323, over 7358.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.02904, over 1418667.89 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 05:02:01,296 INFO [train.py:812] (1/8) Epoch 38, batch 3850, loss[loss=0.1503, simple_loss=0.2548, pruned_loss=0.02289, over 7094.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02885, over 1420585.46 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 05:03:01,098 INFO [train.py:812] (1/8) Epoch 38, batch 3900, loss[loss=0.1394, simple_loss=0.2373, pruned_loss=0.02075, over 7321.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2424, pruned_loss=0.02923, over 1422107.79 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 05:03:59,301 INFO [train.py:812] (1/8) Epoch 38, batch 3950, loss[loss=0.1519, simple_loss=0.2398, pruned_loss=0.03199, over 7206.00 frames.], tot_loss[loss=0.15, simple_loss=0.2418, pruned_loss=0.02915, over 1416851.44 frames.], batch size: 22, lr: 2.04e-04
+2022-05-16 05:04:56,835 INFO [train.py:812] (1/8) Epoch 38, batch 4000, loss[loss=0.1448, simple_loss=0.2392, pruned_loss=0.02519, over 7155.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2419, pruned_loss=0.02917, over 1417608.96 frames.], batch size: 19, lr: 2.04e-04
+2022-05-16 05:06:06,114 INFO [train.py:812] (1/8) Epoch 38, batch 4050, loss[loss=0.1348, simple_loss=0.2264, pruned_loss=0.02161, over 7277.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2415, pruned_loss=0.02886, over 1411577.50 frames.], batch size: 17, lr: 2.04e-04
+2022-05-16 05:07:14,542 INFO [train.py:812] (1/8) Epoch 38, batch 4100, loss[loss=0.1314, simple_loss=0.2342, pruned_loss=0.01434, over 7216.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.0289, over 1413505.36 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 05:08:13,921 INFO [train.py:812] (1/8) Epoch 38, batch 4150, loss[loss=0.1377, simple_loss=0.2327, pruned_loss=0.02138, over 7254.00 frames.], tot_loss[loss=0.1491, simple_loss=0.241, pruned_loss=0.02863, over 1412658.43 frames.], batch size: 19, lr: 2.03e-04
+2022-05-16 05:09:21,216 INFO [train.py:812] (1/8) Epoch 38, batch 4200, loss[loss=0.1488, simple_loss=0.2398, pruned_loss=0.02891, over 7315.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2407, pruned_loss=0.02822, over 1413747.03 frames.], batch size: 24, lr: 2.03e-04
+2022-05-16 05:10:29,482 INFO [train.py:812] (1/8) Epoch 38, batch 4250, loss[loss=0.1427, simple_loss=0.2408, pruned_loss=0.02233, over 7233.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2407, pruned_loss=0.02796, over 1415010.49 frames.], batch size: 20, lr: 2.03e-04
+2022-05-16 05:11:27,933 INFO [train.py:812] (1/8) Epoch 38, batch 4300, loss[loss=0.1857, simple_loss=0.2713, pruned_loss=0.05007, over 4885.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2394, pruned_loss=0.02762, over 1412315.96 frames.], batch size: 53, lr: 2.03e-04
+2022-05-16 05:12:26,586 INFO [train.py:812] (1/8) Epoch 38, batch 4350, loss[loss=0.1346, simple_loss=0.2199, pruned_loss=0.02469, over 7014.00 frames.], tot_loss[loss=0.147, simple_loss=0.2386, pruned_loss=0.02768, over 1415249.14 frames.], batch size: 16, lr: 2.03e-04
+2022-05-16 05:13:26,094 INFO [train.py:812] (1/8) Epoch 38, batch 4400, loss[loss=0.1309, simple_loss=0.2192, pruned_loss=0.02123, over 6774.00 frames.], tot_loss[loss=0.1461, simple_loss=0.238, pruned_loss=0.02716, over 1415364.88 frames.], batch size: 15, lr: 2.03e-04
+2022-05-16 05:14:25,869 INFO [train.py:812] (1/8) Epoch 38, batch 4450, loss[loss=0.1642, simple_loss=0.2458, pruned_loss=0.0413, over 6784.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2385, pruned_loss=0.02792, over 1407164.86 frames.], batch size: 15, lr: 2.03e-04
+2022-05-16 05:15:24,201 INFO [train.py:812] (1/8) Epoch 38, batch 4500, loss[loss=0.1637, simple_loss=0.2534, pruned_loss=0.03697, over 6498.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2392, pruned_loss=0.02852, over 1383528.12 frames.], batch size: 38, lr: 2.03e-04
+2022-05-16 05:16:23,034 INFO [train.py:812] (1/8) Epoch 38, batch 4550, loss[loss=0.1828, simple_loss=0.2717, pruned_loss=0.04694, over 5399.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2383, pruned_loss=0.02864, over 1357995.57 frames.], batch size: 52, lr: 2.03e-04
+2022-05-16 05:17:28,540 INFO [train.py:812] (1/8) Epoch 39, batch 0, loss[loss=0.17, simple_loss=0.2735, pruned_loss=0.03326, over 7250.00 frames.], tot_loss[loss=0.17, simple_loss=0.2735, pruned_loss=0.03326, over 7250.00 frames.], batch size: 19, lr: 2.01e-04
+2022-05-16 05:18:26,916 INFO [train.py:812] (1/8) Epoch 39, batch 50, loss[loss=0.1642, simple_loss=0.2612, pruned_loss=0.0336, over 7144.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2418, pruned_loss=0.02686, over 320300.00 frames.], batch size: 20, lr: 2.01e-04
+2022-05-16 05:19:25,798 INFO [train.py:812] (1/8) Epoch 39, batch 100, loss[loss=0.1577, simple_loss=0.2571, pruned_loss=0.02919, over 6798.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2429, pruned_loss=0.02814, over 565997.76 frames.], batch size: 31, lr: 2.01e-04
+2022-05-16 05:20:24,081 INFO [train.py:812] (1/8) Epoch 39, batch 150, loss[loss=0.1635, simple_loss=0.247, pruned_loss=0.03996, over 7167.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2414, pruned_loss=0.02852, over 755262.21 frames.], batch size: 18, lr: 2.01e-04
+2022-05-16 05:21:22,515 INFO [train.py:812] (1/8) Epoch 39, batch 200, loss[loss=0.1272, simple_loss=0.2276, pruned_loss=0.01346, over 7429.00 frames.], tot_loss[loss=0.1493, simple_loss=0.242, pruned_loss=0.02824, over 901333.06 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:22:20,441 INFO [train.py:812] (1/8) Epoch 39, batch 250, loss[loss=0.1541, simple_loss=0.2512, pruned_loss=0.02852, over 6281.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2424, pruned_loss=0.02818, over 1017337.20 frames.], batch size: 37, lr: 2.00e-04
+2022-05-16 05:23:19,074 INFO [train.py:812] (1/8) Epoch 39, batch 300, loss[loss=0.15, simple_loss=0.2435, pruned_loss=0.02822, over 7442.00 frames.], tot_loss[loss=0.149, simple_loss=0.2419, pruned_loss=0.02808, over 1112260.68 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:24:17,715 INFO [train.py:812] (1/8) Epoch 39, batch 350, loss[loss=0.1566, simple_loss=0.2452, pruned_loss=0.03396, over 7291.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2411, pruned_loss=0.02837, over 1178936.62 frames.], batch size: 24, lr: 2.00e-04
+2022-05-16 05:25:17,174 INFO [train.py:812] (1/8) Epoch 39, batch 400, loss[loss=0.1545, simple_loss=0.2365, pruned_loss=0.03627, over 7220.00 frames.], tot_loss[loss=0.1489, simple_loss=0.241, pruned_loss=0.02847, over 1228315.96 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:26:16,269 INFO [train.py:812] (1/8) Epoch 39, batch 450, loss[loss=0.1686, simple_loss=0.258, pruned_loss=0.03957, over 7194.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2414, pruned_loss=0.02893, over 1274112.84 frames.], batch size: 23, lr: 2.00e-04
+2022-05-16 05:27:15,051 INFO [train.py:812] (1/8) Epoch 39, batch 500, loss[loss=0.1439, simple_loss=0.241, pruned_loss=0.02341, over 7137.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2414, pruned_loss=0.02906, over 1301555.97 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:28:14,649 INFO [train.py:812] (1/8) Epoch 39, batch 550, loss[loss=0.1451, simple_loss=0.2463, pruned_loss=0.02192, over 7421.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2412, pruned_loss=0.02891, over 1326801.39 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:29:14,830 INFO [train.py:812] (1/8) Epoch 39, batch 600, loss[loss=0.1586, simple_loss=0.2443, pruned_loss=0.03643, over 7159.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2421, pruned_loss=0.02903, over 1345439.86 frames.], batch size: 18, lr: 2.00e-04
+2022-05-16 05:30:14,586 INFO [train.py:812] (1/8) Epoch 39, batch 650, loss[loss=0.1376, simple_loss=0.2239, pruned_loss=0.02568, over 7296.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.02894, over 1364978.89 frames.], batch size: 17, lr: 2.00e-04
+2022-05-16 05:31:13,691 INFO [train.py:812] (1/8) Epoch 39, batch 700, loss[loss=0.1325, simple_loss=0.2215, pruned_loss=0.02173, over 6828.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2408, pruned_loss=0.02856, over 1377144.17 frames.], batch size: 15, lr: 2.00e-04
+2022-05-16 05:32:12,656 INFO [train.py:812] (1/8) Epoch 39, batch 750, loss[loss=0.1437, simple_loss=0.2412, pruned_loss=0.02313, over 6570.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2405, pruned_loss=0.02841, over 1386078.87 frames.], batch size: 38, lr: 2.00e-04
+2022-05-16 05:33:12,255 INFO [train.py:812] (1/8) Epoch 39, batch 800, loss[loss=0.1542, simple_loss=0.2446, pruned_loss=0.03186, over 7237.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2403, pruned_loss=0.02802, over 1398910.79 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:34:10,572 INFO [train.py:812] (1/8) Epoch 39, batch 850, loss[loss=0.163, simple_loss=0.2532, pruned_loss=0.03637, over 7090.00 frames.], tot_loss[loss=0.1477, simple_loss=0.24, pruned_loss=0.02772, over 1405013.90 frames.], batch size: 28, lr: 2.00e-04
+2022-05-16 05:35:08,793 INFO [train.py:812] (1/8) Epoch 39, batch 900, loss[loss=0.16, simple_loss=0.2625, pruned_loss=0.02869, over 7414.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2406, pruned_loss=0.02795, over 1403930.44 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:36:07,909 INFO [train.py:812] (1/8) Epoch 39, batch 950, loss[loss=0.1368, simple_loss=0.2199, pruned_loss=0.02682, over 7126.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2415, pruned_loss=0.02854, over 1404713.54 frames.], batch size: 17, lr: 2.00e-04
+2022-05-16 05:37:07,629 INFO [train.py:812] (1/8) Epoch 39, batch 1000, loss[loss=0.1409, simple_loss=0.2327, pruned_loss=0.02459, over 7360.00 frames.], tot_loss[loss=0.149, simple_loss=0.2414, pruned_loss=0.0283, over 1408198.30 frames.], batch size: 19, lr: 2.00e-04
+2022-05-16 05:38:06,526 INFO [train.py:812] (1/8) Epoch 39, batch 1050, loss[loss=0.1678, simple_loss=0.2542, pruned_loss=0.04074, over 6857.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2408, pruned_loss=0.02819, over 1410659.55 frames.], batch size: 31, lr: 2.00e-04
+2022-05-16 05:39:05,052 INFO [train.py:812] (1/8) Epoch 39, batch 1100, loss[loss=0.1611, simple_loss=0.2572, pruned_loss=0.03247, over 7381.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2404, pruned_loss=0.02815, over 1414886.31 frames.], batch size: 23, lr: 2.00e-04
+2022-05-16 05:40:03,844 INFO [train.py:812] (1/8) Epoch 39, batch 1150, loss[loss=0.1375, simple_loss=0.2237, pruned_loss=0.02562, over 7279.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2397, pruned_loss=0.02796, over 1418447.85 frames.], batch size: 18, lr: 2.00e-04
+2022-05-16 05:41:02,325 INFO [train.py:812] (1/8) Epoch 39, batch 1200, loss[loss=0.1458, simple_loss=0.2376, pruned_loss=0.02703, over 6740.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2402, pruned_loss=0.0283, over 1420016.38 frames.], batch size: 31, lr: 2.00e-04
+2022-05-16 05:42:00,509 INFO [train.py:812] (1/8) Epoch 39, batch 1250, loss[loss=0.1272, simple_loss=0.2194, pruned_loss=0.01752, over 7423.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2401, pruned_loss=0.02803, over 1421420.47 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:42:59,464 INFO [train.py:812] (1/8) Epoch 39, batch 1300, loss[loss=0.1257, simple_loss=0.2099, pruned_loss=0.02071, over 7269.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2394, pruned_loss=0.02787, over 1425048.58 frames.], batch size: 17, lr: 2.00e-04
+2022-05-16 05:43:56,593 INFO [train.py:812] (1/8) Epoch 39, batch 1350, loss[loss=0.1441, simple_loss=0.24, pruned_loss=0.02412, over 7315.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2401, pruned_loss=0.02786, over 1425654.80 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:45:05,763 INFO [train.py:812] (1/8) Epoch 39, batch 1400, loss[loss=0.1276, simple_loss=0.219, pruned_loss=0.01809, over 7162.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2403, pruned_loss=0.02805, over 1426006.74 frames.], batch size: 19, lr: 2.00e-04
+2022-05-16 05:46:03,929 INFO [train.py:812] (1/8) Epoch 39, batch 1450, loss[loss=0.1613, simple_loss=0.2557, pruned_loss=0.03346, over 7296.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2414, pruned_loss=0.02807, over 1426053.32 frames.], batch size: 25, lr: 2.00e-04
+2022-05-16 05:47:01,550 INFO [train.py:812] (1/8) Epoch 39, batch 1500, loss[loss=0.1591, simple_loss=0.2621, pruned_loss=0.02804, over 7126.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2424, pruned_loss=0.02853, over 1424397.25 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:48:00,114 INFO [train.py:812] (1/8) Epoch 39, batch 1550, loss[loss=0.1553, simple_loss=0.2498, pruned_loss=0.03045, over 7209.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2415, pruned_loss=0.0285, over 1423891.81 frames.], batch size: 22, lr: 2.00e-04
+2022-05-16 05:48:59,841 INFO [train.py:812] (1/8) Epoch 39, batch 1600, loss[loss=0.1555, simple_loss=0.247, pruned_loss=0.03206, over 6772.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2419, pruned_loss=0.02911, over 1426358.37 frames.], batch size: 31, lr: 2.00e-04
+2022-05-16 05:49:57,806 INFO [train.py:812] (1/8) Epoch 39, batch 1650, loss[loss=0.1615, simple_loss=0.2547, pruned_loss=0.0341, over 7227.00 frames.], tot_loss[loss=0.1499, simple_loss=0.242, pruned_loss=0.02885, over 1425318.89 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:51:01,158 INFO [train.py:812] (1/8) Epoch 39, batch 1700, loss[loss=0.1501, simple_loss=0.2459, pruned_loss=0.02715, over 7070.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2424, pruned_loss=0.02863, over 1426815.65 frames.], batch size: 28, lr: 2.00e-04
+2022-05-16 05:51:59,355 INFO [train.py:812] (1/8) Epoch 39, batch 1750, loss[loss=0.1429, simple_loss=0.2389, pruned_loss=0.02348, over 7437.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2429, pruned_loss=0.02863, over 1426147.78 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:52:58,520 INFO [train.py:812] (1/8) Epoch 39, batch 1800, loss[loss=0.1537, simple_loss=0.2434, pruned_loss=0.03202, over 7194.00 frames.], tot_loss[loss=0.1502, simple_loss=0.243, pruned_loss=0.02875, over 1424044.09 frames.], batch size: 23, lr: 2.00e-04
+2022-05-16 05:53:57,502 INFO [train.py:812] (1/8) Epoch 39, batch 1850, loss[loss=0.1431, simple_loss=0.2326, pruned_loss=0.0268, over 7144.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2421, pruned_loss=0.02844, over 1421652.44 frames.], batch size: 19, lr: 2.00e-04
+2022-05-16 05:54:55,921 INFO [train.py:812] (1/8) Epoch 39, batch 1900, loss[loss=0.1245, simple_loss=0.2088, pruned_loss=0.02012, over 7280.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2413, pruned_loss=0.0282, over 1425033.49 frames.], batch size: 18, lr: 2.00e-04
+2022-05-16 05:55:54,019 INFO [train.py:812] (1/8) Epoch 39, batch 1950, loss[loss=0.1581, simple_loss=0.2548, pruned_loss=0.03072, over 7325.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2413, pruned_loss=0.02779, over 1425948.96 frames.], batch size: 21, lr: 1.99e-04
+2022-05-16 05:56:52,308 INFO [train.py:812] (1/8) Epoch 39, batch 2000, loss[loss=0.1334, simple_loss=0.2252, pruned_loss=0.02078, over 7260.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2416, pruned_loss=0.02788, over 1424479.84 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 05:57:50,320 INFO [train.py:812] (1/8) Epoch 39, batch 2050, loss[loss=0.1339, simple_loss=0.2327, pruned_loss=0.01752, over 7323.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2413, pruned_loss=0.02761, over 1422059.23 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 05:58:49,541 INFO [train.py:812] (1/8) Epoch 39, batch 2100, loss[loss=0.1321, simple_loss=0.2183, pruned_loss=0.02297, over 7246.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2416, pruned_loss=0.0279, over 1423019.39 frames.], batch size: 16, lr: 1.99e-04
+2022-05-16 05:59:47,697 INFO [train.py:812] (1/8) Epoch 39, batch 2150, loss[loss=0.1396, simple_loss=0.2321, pruned_loss=0.02354, over 7265.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2414, pruned_loss=0.0279, over 1422057.45 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:00:46,894 INFO [train.py:812] (1/8) Epoch 39, batch 2200, loss[loss=0.1657, simple_loss=0.2556, pruned_loss=0.03793, over 7208.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2421, pruned_loss=0.02805, over 1422361.52 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:01:45,964 INFO [train.py:812] (1/8) Epoch 39, batch 2250, loss[loss=0.1533, simple_loss=0.2459, pruned_loss=0.03034, over 7151.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2411, pruned_loss=0.02782, over 1424589.20 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:02:45,409 INFO [train.py:812] (1/8) Epoch 39, batch 2300, loss[loss=0.1198, simple_loss=0.2156, pruned_loss=0.012, over 7155.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2415, pruned_loss=0.02818, over 1424264.79 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:03:45,431 INFO [train.py:812] (1/8) Epoch 39, batch 2350, loss[loss=0.1597, simple_loss=0.2595, pruned_loss=0.02994, over 7241.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2406, pruned_loss=0.02794, over 1426066.08 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:04:43,842 INFO [train.py:812] (1/8) Epoch 39, batch 2400, loss[loss=0.148, simple_loss=0.2469, pruned_loss=0.02451, over 7151.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2404, pruned_loss=0.028, over 1428358.02 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:05:41,789 INFO [train.py:812] (1/8) Epoch 39, batch 2450, loss[loss=0.1328, simple_loss=0.218, pruned_loss=0.02377, over 7406.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2397, pruned_loss=0.02788, over 1429118.98 frames.], batch size: 18, lr: 1.99e-04
+2022-05-16 06:06:40,884 INFO [train.py:812] (1/8) Epoch 39, batch 2500, loss[loss=0.1368, simple_loss=0.2207, pruned_loss=0.02642, over 7405.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2394, pruned_loss=0.02745, over 1427514.81 frames.], batch size: 18, lr: 1.99e-04
+2022-05-16 06:07:38,136 INFO [train.py:812] (1/8) Epoch 39, batch 2550, loss[loss=0.1433, simple_loss=0.2373, pruned_loss=0.02462, over 7428.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2398, pruned_loss=0.02753, over 1432092.02 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:08:37,365 INFO [train.py:812] (1/8) Epoch 39, batch 2600, loss[loss=0.1472, simple_loss=0.25, pruned_loss=0.02219, over 7217.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2406, pruned_loss=0.02767, over 1429586.51 frames.], batch size: 26, lr: 1.99e-04
+2022-05-16 06:09:36,147 INFO [train.py:812] (1/8) Epoch 39, batch 2650, loss[loss=0.1412, simple_loss=0.2364, pruned_loss=0.02301, over 7071.00 frames.], tot_loss[loss=0.148, simple_loss=0.2405, pruned_loss=0.0278, over 1430471.02 frames.], batch size: 28, lr: 1.99e-04
+2022-05-16 06:10:34,086 INFO [train.py:812] (1/8) Epoch 39, batch 2700, loss[loss=0.1694, simple_loss=0.2644, pruned_loss=0.03721, over 7296.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2406, pruned_loss=0.02787, over 1428665.11 frames.], batch size: 25, lr: 1.99e-04
+2022-05-16 06:11:32,678 INFO [train.py:812] (1/8) Epoch 39, batch 2750, loss[loss=0.1313, simple_loss=0.228, pruned_loss=0.0173, over 7158.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2408, pruned_loss=0.02786, over 1429334.82 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:12:31,342 INFO [train.py:812] (1/8) Epoch 39, batch 2800, loss[loss=0.1431, simple_loss=0.2416, pruned_loss=0.02234, over 7331.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2413, pruned_loss=0.02812, over 1426314.53 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:13:29,183 INFO [train.py:812] (1/8) Epoch 39, batch 2850, loss[loss=0.1419, simple_loss=0.2389, pruned_loss=0.02241, over 6310.00 frames.], tot_loss[loss=0.1485, simple_loss=0.241, pruned_loss=0.02803, over 1426632.20 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:14:28,564 INFO [train.py:812] (1/8) Epoch 39, batch 2900, loss[loss=0.1593, simple_loss=0.2571, pruned_loss=0.03074, over 7320.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2414, pruned_loss=0.02813, over 1425152.32 frames.], batch size: 21, lr: 1.99e-04
+2022-05-16 06:15:27,563 INFO [train.py:812] (1/8) Epoch 39, batch 2950, loss[loss=0.1528, simple_loss=0.249, pruned_loss=0.02833, over 7338.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2411, pruned_loss=0.02801, over 1428468.06 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:16:26,919 INFO [train.py:812] (1/8) Epoch 39, batch 3000, loss[loss=0.1581, simple_loss=0.2668, pruned_loss=0.02463, over 7236.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2422, pruned_loss=0.02819, over 1429457.43 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:16:26,920 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-16 06:16:34,436 INFO [train.py:841] (1/8) Epoch 39, validation: loss=0.153, simple_loss=0.2484, pruned_loss=0.02885, over 698248.00 frames.
+2022-05-16 06:17:33,444 INFO [train.py:812] (1/8) Epoch 39, batch 3050, loss[loss=0.1554, simple_loss=0.2422, pruned_loss=0.03429, over 7117.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2425, pruned_loss=0.02853, over 1425607.67 frames.], batch size: 17, lr: 1.99e-04
+2022-05-16 06:18:32,173 INFO [train.py:812] (1/8) Epoch 39, batch 3100, loss[loss=0.1664, simple_loss=0.2618, pruned_loss=0.03549, over 6517.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2428, pruned_loss=0.02879, over 1417745.29 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:19:30,263 INFO [train.py:812] (1/8) Epoch 39, batch 3150, loss[loss=0.1557, simple_loss=0.2546, pruned_loss=0.02837, over 7408.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2437, pruned_loss=0.02888, over 1423644.21 frames.], batch size: 21, lr: 1.99e-04
+2022-05-16 06:20:28,868 INFO [train.py:812] (1/8) Epoch 39, batch 3200, loss[loss=0.159, simple_loss=0.2586, pruned_loss=0.02973, over 6582.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2434, pruned_loss=0.02863, over 1424779.89 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:21:26,205 INFO [train.py:812] (1/8) Epoch 39, batch 3250, loss[loss=0.1412, simple_loss=0.2355, pruned_loss=0.02342, over 6486.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2432, pruned_loss=0.0286, over 1424674.63 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:22:25,456 INFO [train.py:812] (1/8) Epoch 39, batch 3300, loss[loss=0.1484, simple_loss=0.2357, pruned_loss=0.0306, over 7157.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2428, pruned_loss=0.02837, over 1424700.91 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:23:24,289 INFO [train.py:812] (1/8) Epoch 39, batch 3350, loss[loss=0.142, simple_loss=0.2277, pruned_loss=0.02818, over 7134.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2423, pruned_loss=0.02821, over 1425856.69 frames.], batch size: 17, lr: 1.99e-04
+2022-05-16 06:24:23,018 INFO [train.py:812] (1/8) Epoch 39, batch 3400, loss[loss=0.1643, simple_loss=0.2509, pruned_loss=0.03881, over 7352.00 frames.], tot_loss[loss=0.1494, simple_loss=0.242, pruned_loss=0.02839, over 1426859.60 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:25:22,173 INFO [train.py:812] (1/8) Epoch 39, batch 3450, loss[loss=0.1608, simple_loss=0.2554, pruned_loss=0.03315, over 7205.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2417, pruned_loss=0.02844, over 1419008.96 frames.], batch size: 23, lr: 1.99e-04
+2022-05-16 06:26:21,455 INFO [train.py:812] (1/8) Epoch 39, batch 3500, loss[loss=0.1439, simple_loss=0.2291, pruned_loss=0.02936, over 7161.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2418, pruned_loss=0.02847, over 1420787.21 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:27:20,248 INFO [train.py:812] (1/8) Epoch 39, batch 3550, loss[loss=0.1551, simple_loss=0.2617, pruned_loss=0.02419, over 7329.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2416, pruned_loss=0.02863, over 1423978.14 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:28:19,534 INFO [train.py:812] (1/8) Epoch 39, batch 3600, loss[loss=0.1486, simple_loss=0.2335, pruned_loss=0.03183, over 7276.00 frames.], tot_loss[loss=0.149, simple_loss=0.2415, pruned_loss=0.02827, over 1424819.98 frames.], batch size: 18, lr: 1.99e-04
+2022-05-16 06:29:17,985 INFO [train.py:812] (1/8) Epoch 39, batch 3650, loss[loss=0.1412, simple_loss=0.2383, pruned_loss=0.02206, over 7039.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2416, pruned_loss=0.02801, over 1426108.81 frames.], batch size: 28, lr: 1.99e-04
+2022-05-16 06:30:16,880 INFO [train.py:812] (1/8) Epoch 39, batch 3700, loss[loss=0.1461, simple_loss=0.245, pruned_loss=0.02361, over 6237.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2417, pruned_loss=0.02793, over 1423008.64 frames.], batch size: 37, lr: 1.99e-04
+2022-05-16 06:31:16,258 INFO [train.py:812] (1/8) Epoch 39, batch 3750, loss[loss=0.176, simple_loss=0.2638, pruned_loss=0.04413, over 7186.00 frames.], tot_loss[loss=0.1484, simple_loss=0.241, pruned_loss=0.02794, over 1416472.92 frames.], batch size: 23, lr: 1.98e-04
+2022-05-16 06:32:15,549 INFO [train.py:812] (1/8) Epoch 39, batch 3800, loss[loss=0.1371, simple_loss=0.2325, pruned_loss=0.02089, over 7358.00 frames.], tot_loss[loss=0.149, simple_loss=0.2414, pruned_loss=0.02827, over 1422543.78 frames.], batch size: 19, lr: 1.98e-04
+2022-05-16 06:33:12,747 INFO [train.py:812] (1/8) Epoch 39, batch 3850, loss[loss=0.2131, simple_loss=0.2906, pruned_loss=0.06777, over 4982.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.02841, over 1419823.42 frames.], batch size: 52, lr: 1.98e-04
+2022-05-16 06:34:10,687 INFO [train.py:812] (1/8) Epoch 39, batch 3900, loss[loss=0.1589, simple_loss=0.2443, pruned_loss=0.03679, over 7037.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2418, pruned_loss=0.02831, over 1419978.21 frames.], batch size: 28, lr: 1.98e-04
+2022-05-16 06:35:09,062 INFO [train.py:812] (1/8) Epoch 39, batch 3950, loss[loss=0.18, simple_loss=0.2693, pruned_loss=0.04537, over 7320.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2419, pruned_loss=0.02816, over 1422006.21 frames.], batch size: 25, lr: 1.98e-04
+2022-05-16 06:36:07,269 INFO [train.py:812] (1/8) Epoch 39, batch 4000, loss[loss=0.1243, simple_loss=0.2187, pruned_loss=0.015, over 6764.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2422, pruned_loss=0.02801, over 1423828.39 frames.], batch size: 31, lr: 1.98e-04
+2022-05-16 06:37:03,578 INFO [train.py:812] (1/8) Epoch 39, batch 4050, loss[loss=0.1533, simple_loss=0.2601, pruned_loss=0.02321, over 6791.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2429, pruned_loss=0.02818, over 1422980.87 frames.], batch size: 31, lr: 1.98e-04
+2022-05-16 06:38:02,732 INFO [train.py:812] (1/8) Epoch 39, batch 4100, loss[loss=0.139, simple_loss=0.2456, pruned_loss=0.01624, over 7221.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2419, pruned_loss=0.02839, over 1421972.39 frames.], batch size: 21, lr: 1.98e-04
+2022-05-16 06:39:01,684 INFO [train.py:812] (1/8) Epoch 39, batch 4150, loss[loss=0.1414, simple_loss=0.2331, pruned_loss=0.02488, over 7229.00 frames.], tot_loss[loss=0.1493, simple_loss=0.242, pruned_loss=0.02829, over 1420307.74 frames.], batch size: 21, lr: 1.98e-04
+2022-05-16 06:40:00,308 INFO [train.py:812] (1/8) Epoch 39, batch 4200, loss[loss=0.1366, simple_loss=0.2363, pruned_loss=0.01847, over 6687.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2415, pruned_loss=0.02804, over 1419981.75 frames.], batch size: 31, lr: 1.98e-04
+2022-05-16 06:40:58,790 INFO [train.py:812] (1/8) Epoch 39, batch 4250, loss[loss=0.1371, simple_loss=0.2222, pruned_loss=0.02598, over 7145.00 frames.], tot_loss[loss=0.148, simple_loss=0.2404, pruned_loss=0.02783, over 1416967.69 frames.], batch size: 17, lr: 1.98e-04
+2022-05-16 06:41:58,203 INFO [train.py:812] (1/8) Epoch 39, batch 4300, loss[loss=0.1642, simple_loss=0.2568, pruned_loss=0.03583, over 7305.00 frames.], tot_loss[loss=0.1493, simple_loss=0.242, pruned_loss=0.02824, over 1418139.56 frames.], batch size: 25, lr: 1.98e-04
+2022-05-16 06:42:57,002 INFO [train.py:812] (1/8) Epoch 39, batch 4350, loss[loss=0.1352, simple_loss=0.2185, pruned_loss=0.02595, over 7439.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2426, pruned_loss=0.0285, over 1413629.16 frames.], batch size: 20, lr: 1.98e-04
+2022-05-16 06:43:56,267 INFO [train.py:812] (1/8) Epoch 39, batch 4400, loss[loss=0.1511, simple_loss=0.2315, pruned_loss=0.03539, over 7341.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2441, pruned_loss=0.029, over 1412066.97 frames.], batch size: 22, lr: 1.98e-04
+2022-05-16 06:44:54,116 INFO [train.py:812] (1/8) Epoch 39, batch 4450, loss[loss=0.1317, simple_loss=0.2113, pruned_loss=0.02601, over 7002.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2446, pruned_loss=0.02908, over 1400176.80 frames.], batch size: 16, lr: 1.98e-04
+2022-05-16 06:45:52,378 INFO [train.py:812] (1/8) Epoch 39, batch 4500, loss[loss=0.1519, simple_loss=0.2427, pruned_loss=0.03059, over 7159.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2447, pruned_loss=0.0293, over 1389267.27 frames.], batch size: 18, lr: 1.98e-04
+2022-05-16 06:46:49,711 INFO [train.py:812] (1/8) Epoch 39, batch 4550, loss[loss=0.2028, simple_loss=0.3051, pruned_loss=0.05023, over 4952.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2467, pruned_loss=0.03055, over 1349990.66 frames.], batch size: 53, lr: 1.98e-04
+2022-05-16 06:47:54,901 INFO [train.py:812] (1/8) Epoch 40, batch 0, loss[loss=0.19, simple_loss=0.2895, pruned_loss=0.04523, over 7302.00 frames.], tot_loss[loss=0.19, simple_loss=0.2895, pruned_loss=0.04523, over 7302.00 frames.], batch size: 24, lr: 1.96e-04
+2022-05-16 06:48:53,196 INFO [train.py:812] (1/8) Epoch 40, batch 50, loss[loss=0.1225, simple_loss=0.2082, pruned_loss=0.01843, over 7285.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2431, pruned_loss=0.0286, over 317507.18 frames.], batch size: 17, lr: 1.95e-04
+2022-05-16 06:49:52,149 INFO [train.py:812] (1/8) Epoch 40, batch 100, loss[loss=0.152, simple_loss=0.2475, pruned_loss=0.02827, over 7362.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2414, pruned_loss=0.02787, over 562838.47 frames.], batch size: 19, lr: 1.95e-04
+2022-05-16 06:50:51,448 INFO [train.py:812] (1/8) Epoch 40, batch 150, loss[loss=0.1457, simple_loss=0.2417, pruned_loss=0.02486, over 7228.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2388, pruned_loss=0.02816, over 755623.23 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 06:51:50,275 INFO [train.py:812] (1/8) Epoch 40, batch 200, loss[loss=0.1412, simple_loss=0.2267, pruned_loss=0.02788, over 7408.00 frames.], tot_loss[loss=0.1498, simple_loss=0.242, pruned_loss=0.02874, over 903341.42 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 06:52:48,881 INFO [train.py:812] (1/8) Epoch 40, batch 250, loss[loss=0.1426, simple_loss=0.2422, pruned_loss=0.02145, over 7126.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2415, pruned_loss=0.02851, over 1015946.57 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 06:53:47,833 INFO [train.py:812] (1/8) Epoch 40, batch 300, loss[loss=0.1557, simple_loss=0.2454, pruned_loss=0.03299, over 7293.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2416, pruned_loss=0.02801, over 1106649.97 frames.], batch size: 24, lr: 1.95e-04
+2022-05-16 06:54:46,892 INFO [train.py:812] (1/8) Epoch 40, batch 350, loss[loss=0.1383, simple_loss=0.2376, pruned_loss=0.01948, over 7146.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2417, pruned_loss=0.02824, over 1171120.54 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 06:55:45,295 INFO [train.py:812] (1/8) Epoch 40, batch 400, loss[loss=0.164, simple_loss=0.2595, pruned_loss=0.0343, over 7190.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2423, pruned_loss=0.02835, over 1228851.10 frames.], batch size: 26, lr: 1.95e-04
+2022-05-16 06:56:53,571 INFO [train.py:812] (1/8) Epoch 40, batch 450, loss[loss=0.1798, simple_loss=0.2663, pruned_loss=0.04665, over 7302.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2416, pruned_loss=0.02829, over 1273425.85 frames.], batch size: 25, lr: 1.95e-04
+2022-05-16 06:57:52,469 INFO [train.py:812] (1/8) Epoch 40, batch 500, loss[loss=0.1307, simple_loss=0.2279, pruned_loss=0.01671, over 7317.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2408, pruned_loss=0.02817, over 1305636.75 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 06:58:59,581 INFO [train.py:812] (1/8) Epoch 40, batch 550, loss[loss=0.152, simple_loss=0.2515, pruned_loss=0.0262, over 7237.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2411, pruned_loss=0.02853, over 1326951.91 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 06:59:58,456 INFO [train.py:812] (1/8) Epoch 40, batch 600, loss[loss=0.1411, simple_loss=0.2277, pruned_loss=0.02728, over 7255.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2408, pruned_loss=0.02831, over 1348413.79 frames.], batch size: 19, lr: 1.95e-04
+2022-05-16 07:01:07,486 INFO [train.py:812] (1/8) Epoch 40, batch 650, loss[loss=0.1611, simple_loss=0.2633, pruned_loss=0.02948, over 7231.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2407, pruned_loss=0.02826, over 1367187.72 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 07:02:07,010 INFO [train.py:812] (1/8) Epoch 40, batch 700, loss[loss=0.1181, simple_loss=0.2004, pruned_loss=0.01787, over 7281.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2412, pruned_loss=0.02832, over 1380854.54 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 07:03:06,178 INFO [train.py:812] (1/8) Epoch 40, batch 750, loss[loss=0.1174, simple_loss=0.21, pruned_loss=0.01242, over 7364.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2403, pruned_loss=0.02798, over 1386606.32 frames.], batch size: 19, lr: 1.95e-04
+2022-05-16 07:04:05,434 INFO [train.py:812] (1/8) Epoch 40, batch 800, loss[loss=0.1521, simple_loss=0.2454, pruned_loss=0.02935, over 7437.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2407, pruned_loss=0.02791, over 1396201.85 frames.], batch size: 22, lr: 1.95e-04
+2022-05-16 07:05:03,686 INFO [train.py:812] (1/8) Epoch 40, batch 850, loss[loss=0.1188, simple_loss=0.2095, pruned_loss=0.01409, over 7137.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2421, pruned_loss=0.02838, over 1403135.78 frames.], batch size: 17, lr: 1.95e-04
+2022-05-16 07:06:12,338 INFO [train.py:812] (1/8) Epoch 40, batch 900, loss[loss=0.1587, simple_loss=0.2561, pruned_loss=0.03069, over 7197.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2424, pruned_loss=0.02841, over 1408549.02 frames.], batch size: 23, lr: 1.95e-04
+2022-05-16 07:07:10,692 INFO [train.py:812] (1/8) Epoch 40, batch 950, loss[loss=0.1853, simple_loss=0.2642, pruned_loss=0.05316, over 5185.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2429, pruned_loss=0.0287, over 1411409.71 frames.], batch size: 52, lr: 1.95e-04
+2022-05-16 07:08:20,197 INFO [train.py:812] (1/8) Epoch 40, batch 1000, loss[loss=0.1409, simple_loss=0.2478, pruned_loss=0.01702, over 7118.00 frames.], tot_loss[loss=0.1504, simple_loss=0.243, pruned_loss=0.02891, over 1410431.02 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:09:19,149 INFO [train.py:812] (1/8) Epoch 40, batch 1050, loss[loss=0.1615, simple_loss=0.2604, pruned_loss=0.03132, over 7227.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2433, pruned_loss=0.02908, over 1409775.15 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:10:42,476 INFO [train.py:812] (1/8) Epoch 40, batch 1100, loss[loss=0.1487, simple_loss=0.2333, pruned_loss=0.03201, over 7170.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2424, pruned_loss=0.0289, over 1408023.22 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 07:11:40,909 INFO [train.py:812] (1/8) Epoch 40, batch 1150, loss[loss=0.1579, simple_loss=0.2448, pruned_loss=0.0355, over 6762.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2416, pruned_loss=0.02858, over 1415443.43 frames.], batch size: 31, lr: 1.95e-04
+2022-05-16 07:12:38,504 INFO [train.py:812] (1/8) Epoch 40, batch 1200, loss[loss=0.1617, simple_loss=0.2526, pruned_loss=0.03543, over 6425.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2417, pruned_loss=0.02859, over 1417954.56 frames.], batch size: 38, lr: 1.95e-04
+2022-05-16 07:13:37,101 INFO [train.py:812] (1/8) Epoch 40, batch 1250, loss[loss=0.1605, simple_loss=0.265, pruned_loss=0.02798, over 7295.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2417, pruned_loss=0.02873, over 1422157.09 frames.], batch size: 25, lr: 1.95e-04
+2022-05-16 07:14:35,233 INFO [train.py:812] (1/8) Epoch 40, batch 1300, loss[loss=0.17, simple_loss=0.2759, pruned_loss=0.03201, over 7427.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2413, pruned_loss=0.02826, over 1423006.29 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 07:15:33,955 INFO [train.py:812] (1/8) Epoch 40, batch 1350, loss[loss=0.1806, simple_loss=0.2665, pruned_loss=0.04731, over 6616.00 frames.], tot_loss[loss=0.149, simple_loss=0.2413, pruned_loss=0.02834, over 1421494.99 frames.], batch size: 38, lr: 1.95e-04
+2022-05-16 07:16:32,343 INFO [train.py:812] (1/8) Epoch 40, batch 1400, loss[loss=0.1693, simple_loss=0.2605, pruned_loss=0.03907, over 6534.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2414, pruned_loss=0.02823, over 1423583.41 frames.], batch size: 38, lr: 1.95e-04
+2022-05-16 07:17:30,661 INFO [train.py:812] (1/8) Epoch 40, batch 1450, loss[loss=0.1502, simple_loss=0.2454, pruned_loss=0.02746, over 7206.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2412, pruned_loss=0.02814, over 1425580.31 frames.], batch size: 23, lr: 1.95e-04
+2022-05-16 07:18:29,816 INFO [train.py:812] (1/8) Epoch 40, batch 1500, loss[loss=0.1175, simple_loss=0.2002, pruned_loss=0.01744, over 7130.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2415, pruned_loss=0.02816, over 1426199.91 frames.], batch size: 17, lr: 1.95e-04
+2022-05-16 07:19:28,055 INFO [train.py:812] (1/8) Epoch 40, batch 1550, loss[loss=0.1544, simple_loss=0.2489, pruned_loss=0.02994, over 7182.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2413, pruned_loss=0.0283, over 1424362.95 frames.], batch size: 23, lr: 1.95e-04
+2022-05-16 07:20:27,056 INFO [train.py:812] (1/8) Epoch 40, batch 1600, loss[loss=0.1638, simple_loss=0.258, pruned_loss=0.03478, over 7166.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.02874, over 1426758.70 frames.], batch size: 28, lr: 1.95e-04
+2022-05-16 07:21:25,480 INFO [train.py:812] (1/8) Epoch 40, batch 1650, loss[loss=0.1942, simple_loss=0.2795, pruned_loss=0.05445, over 4930.00 frames.], tot_loss[loss=0.1495, simple_loss=0.242, pruned_loss=0.02852, over 1420925.01 frames.], batch size: 52, lr: 1.95e-04
+2022-05-16 07:22:23,881 INFO [train.py:812] (1/8) Epoch 40, batch 1700, loss[loss=0.1318, simple_loss=0.2174, pruned_loss=0.02307, over 7011.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02882, over 1413206.57 frames.], batch size: 16, lr: 1.95e-04
+2022-05-16 07:23:23,273 INFO [train.py:812] (1/8) Epoch 40, batch 1750, loss[loss=0.1835, simple_loss=0.2758, pruned_loss=0.04566, over 7315.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2418, pruned_loss=0.02902, over 1414459.39 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:24:22,406 INFO [train.py:812] (1/8) Epoch 40, batch 1800, loss[loss=0.1552, simple_loss=0.2558, pruned_loss=0.02729, over 7338.00 frames.], tot_loss[loss=0.1504, simple_loss=0.243, pruned_loss=0.02889, over 1417439.79 frames.], batch size: 22, lr: 1.95e-04
+2022-05-16 07:25:21,049 INFO [train.py:812] (1/8) Epoch 40, batch 1850, loss[loss=0.1611, simple_loss=0.2473, pruned_loss=0.03752, over 7078.00 frames.], tot_loss[loss=0.15, simple_loss=0.2424, pruned_loss=0.02884, over 1420274.23 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 07:26:20,231 INFO [train.py:812] (1/8) Epoch 40, batch 1900, loss[loss=0.1506, simple_loss=0.2399, pruned_loss=0.0306, over 7150.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2422, pruned_loss=0.02846, over 1423639.03 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:27:17,886 INFO [train.py:812] (1/8) Epoch 40, batch 1950, loss[loss=0.1819, simple_loss=0.2583, pruned_loss=0.05275, over 5167.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2424, pruned_loss=0.02856, over 1418209.14 frames.], batch size: 53, lr: 1.94e-04
+2022-05-16 07:28:16,416 INFO [train.py:812] (1/8) Epoch 40, batch 2000, loss[loss=0.1495, simple_loss=0.2428, pruned_loss=0.02807, over 7069.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2419, pruned_loss=0.02842, over 1422161.36 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:29:15,099 INFO [train.py:812] (1/8) Epoch 40, batch 2050, loss[loss=0.1592, simple_loss=0.2478, pruned_loss=0.03527, over 7428.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2421, pruned_loss=0.02864, over 1425832.46 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:30:14,378 INFO [train.py:812] (1/8) Epoch 40, batch 2100, loss[loss=0.1266, simple_loss=0.2161, pruned_loss=0.01854, over 7424.00 frames.], tot_loss[loss=0.1494, simple_loss=0.242, pruned_loss=0.02836, over 1424689.34 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:31:12,651 INFO [train.py:812] (1/8) Epoch 40, batch 2150, loss[loss=0.172, simple_loss=0.2812, pruned_loss=0.03144, over 7148.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2415, pruned_loss=0.02799, over 1428479.80 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:32:11,376 INFO [train.py:812] (1/8) Epoch 40, batch 2200, loss[loss=0.1458, simple_loss=0.2345, pruned_loss=0.02853, over 7234.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2405, pruned_loss=0.02729, over 1430431.90 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:33:10,319 INFO [train.py:812] (1/8) Epoch 40, batch 2250, loss[loss=0.1541, simple_loss=0.2505, pruned_loss=0.02884, over 7207.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2404, pruned_loss=0.02731, over 1428688.40 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:34:08,379 INFO [train.py:812] (1/8) Epoch 40, batch 2300, loss[loss=0.1222, simple_loss=0.2098, pruned_loss=0.01727, over 7441.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2397, pruned_loss=0.02728, over 1426049.63 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:35:07,170 INFO [train.py:812] (1/8) Epoch 40, batch 2350, loss[loss=0.1601, simple_loss=0.2599, pruned_loss=0.03013, over 7346.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2386, pruned_loss=0.02727, over 1425454.41 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:36:06,634 INFO [train.py:812] (1/8) Epoch 40, batch 2400, loss[loss=0.1661, simple_loss=0.2546, pruned_loss=0.03875, over 7215.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2382, pruned_loss=0.0272, over 1426386.28 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:37:04,713 INFO [train.py:812] (1/8) Epoch 40, batch 2450, loss[loss=0.1683, simple_loss=0.267, pruned_loss=0.03483, over 7030.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2394, pruned_loss=0.02758, over 1421216.51 frames.], batch size: 28, lr: 1.94e-04
+2022-05-16 07:38:03,596 INFO [train.py:812] (1/8) Epoch 40, batch 2500, loss[loss=0.1339, simple_loss=0.2305, pruned_loss=0.01862, over 7414.00 frames.], tot_loss[loss=0.1469, simple_loss=0.239, pruned_loss=0.02739, over 1418642.32 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:39:02,631 INFO [train.py:812] (1/8) Epoch 40, batch 2550, loss[loss=0.1555, simple_loss=0.2477, pruned_loss=0.03164, over 7070.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2401, pruned_loss=0.0278, over 1418469.90 frames.], batch size: 28, lr: 1.94e-04
+2022-05-16 07:40:02,272 INFO [train.py:812] (1/8) Epoch 40, batch 2600, loss[loss=0.137, simple_loss=0.2388, pruned_loss=0.01754, over 7336.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2398, pruned_loss=0.02785, over 1418631.91 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:40:59,592 INFO [train.py:812] (1/8) Epoch 40, batch 2650, loss[loss=0.1312, simple_loss=0.222, pruned_loss=0.0202, over 7178.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2405, pruned_loss=0.02798, over 1420949.25 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:42:08,101 INFO [train.py:812] (1/8) Epoch 40, batch 2700, loss[loss=0.151, simple_loss=0.246, pruned_loss=0.028, over 7226.00 frames.], tot_loss[loss=0.1484, simple_loss=0.241, pruned_loss=0.02793, over 1422837.09 frames.], batch size: 26, lr: 1.94e-04
+2022-05-16 07:43:06,184 INFO [train.py:812] (1/8) Epoch 40, batch 2750, loss[loss=0.1731, simple_loss=0.2783, pruned_loss=0.03395, over 7286.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2407, pruned_loss=0.02748, over 1425991.28 frames.], batch size: 24, lr: 1.94e-04
+2022-05-16 07:44:05,701 INFO [train.py:812] (1/8) Epoch 40, batch 2800, loss[loss=0.1494, simple_loss=0.2404, pruned_loss=0.02919, over 7071.00 frames.], tot_loss[loss=0.1482, simple_loss=0.241, pruned_loss=0.02769, over 1423038.27 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:45:02,891 INFO [train.py:812] (1/8) Epoch 40, batch 2850, loss[loss=0.139, simple_loss=0.2308, pruned_loss=0.02358, over 6598.00 frames.], tot_loss[loss=0.1484, simple_loss=0.241, pruned_loss=0.02789, over 1419485.51 frames.], batch size: 38, lr: 1.94e-04
+2022-05-16 07:46:01,098 INFO [train.py:812] (1/8) Epoch 40, batch 2900, loss[loss=0.127, simple_loss=0.223, pruned_loss=0.01553, over 7060.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2406, pruned_loss=0.02751, over 1419833.99 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:46:58,667 INFO [train.py:812] (1/8) Epoch 40, batch 2950, loss[loss=0.1842, simple_loss=0.2697, pruned_loss=0.04929, over 7296.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.0282, over 1419442.87 frames.], batch size: 24, lr: 1.94e-04
+2022-05-16 07:47:56,494 INFO [train.py:812] (1/8) Epoch 40, batch 3000, loss[loss=0.1644, simple_loss=0.2671, pruned_loss=0.03088, over 7345.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2424, pruned_loss=0.02845, over 1413349.22 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:47:56,495 INFO [train.py:832] (1/8) Computing validation loss
+2022-05-16 07:48:04,107 INFO [train.py:841] (1/8) Epoch 40, validation: loss=0.1534, simple_loss=0.2485, pruned_loss=0.02916, over 698248.00 frames.
+2022-05-16 07:49:02,574 INFO [train.py:812] (1/8) Epoch 40, batch 3050, loss[loss=0.1362, simple_loss=0.2299, pruned_loss=0.02127, over 7354.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2421, pruned_loss=0.02851, over 1414706.86 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:50:01,839 INFO [train.py:812] (1/8) Epoch 40, batch 3100, loss[loss=0.1576, simple_loss=0.2595, pruned_loss=0.02783, over 7174.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2424, pruned_loss=0.02848, over 1417522.54 frames.], batch size: 26, lr: 1.94e-04
+2022-05-16 07:51:00,387 INFO [train.py:812] (1/8) Epoch 40, batch 3150, loss[loss=0.1464, simple_loss=0.2429, pruned_loss=0.02489, over 7151.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2431, pruned_loss=0.02866, over 1421106.88 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:51:59,400 INFO [train.py:812] (1/8) Epoch 40, batch 3200, loss[loss=0.1614, simple_loss=0.25, pruned_loss=0.03635, over 5077.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2432, pruned_loss=0.02867, over 1420950.14 frames.], batch size: 52, lr: 1.94e-04
+2022-05-16 07:52:57,279 INFO [train.py:812] (1/8) Epoch 40, batch 3250, loss[loss=0.1646, simple_loss=0.2555, pruned_loss=0.0368, over 7377.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2437, pruned_loss=0.02884, over 1420067.08 frames.], batch size: 23, lr: 1.94e-04
+2022-05-16 07:53:57,053 INFO [train.py:812] (1/8) Epoch 40, batch 3300, loss[loss=0.1803, simple_loss=0.2781, pruned_loss=0.04127, over 7105.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2424, pruned_loss=0.02868, over 1418839.85 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:54:55,916 INFO [train.py:812] (1/8) Epoch 40, batch 3350, loss[loss=0.1588, simple_loss=0.2519, pruned_loss=0.03285, over 7109.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2419, pruned_loss=0.02839, over 1417356.94 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:55:55,672 INFO [train.py:812] (1/8) Epoch 40, batch 3400, loss[loss=0.1511, simple_loss=0.2562, pruned_loss=0.02301, over 7161.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2413, pruned_loss=0.0284, over 1417482.85 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:56:54,697 INFO [train.py:812] (1/8) Epoch 40, batch 3450, loss[loss=0.1402, simple_loss=0.2268, pruned_loss=0.02675, over 7275.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2414, pruned_loss=0.02842, over 1416135.84 frames.], batch size: 17, lr: 1.94e-04
+2022-05-16 07:57:54,431 INFO [train.py:812] (1/8) Epoch 40, batch 3500, loss[loss=0.1715, simple_loss=0.2625, pruned_loss=0.04028, over 7327.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2419, pruned_loss=0.02856, over 1418213.28 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:58:53,140 INFO [train.py:812] (1/8) Epoch 40, batch 3550, loss[loss=0.1395, simple_loss=0.2283, pruned_loss=0.02538, over 7059.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2404, pruned_loss=0.02818, over 1419252.80 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:59:51,373 INFO [train.py:812] (1/8) Epoch 40, batch 3600, loss[loss=0.1509, simple_loss=0.2485, pruned_loss=0.02665, over 5195.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2406, pruned_loss=0.02803, over 1416417.02 frames.], batch size: 54, lr: 1.94e-04
+2022-05-16 08:00:51,211 INFO [train.py:812] (1/8) Epoch 40, batch 3650, loss[loss=0.1611, simple_loss=0.2631, pruned_loss=0.02954, over 6631.00 frames.], tot_loss[loss=0.149, simple_loss=0.2416, pruned_loss=0.02817, over 1418399.37 frames.], batch size: 38, lr: 1.94e-04
+2022-05-16 08:01:49,905 INFO [train.py:812] (1/8) Epoch 40, batch 3700, loss[loss=0.1386, simple_loss=0.2224, pruned_loss=0.02743, over 7146.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2414, pruned_loss=0.02791, over 1422227.43 frames.], batch size: 17, lr: 1.94e-04
+2022-05-16 08:02:46,995 INFO [train.py:812] (1/8) Epoch 40, batch 3750, loss[loss=0.148, simple_loss=0.2326, pruned_loss=0.03172, over 7350.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2421, pruned_loss=0.02848, over 1419103.25 frames.], batch size: 19, lr: 1.93e-04
+2022-05-16 08:03:45,477 INFO [train.py:812] (1/8) Epoch 40, batch 3800, loss[loss=0.1086, simple_loss=0.1961, pruned_loss=0.01053, over 7015.00 frames.], tot_loss[loss=0.149, simple_loss=0.2415, pruned_loss=0.02825, over 1422950.17 frames.], batch size: 16, lr: 1.93e-04
+2022-05-16 08:04:42,347 INFO [train.py:812] (1/8) Epoch 40, batch 3850, loss[loss=0.1334, simple_loss=0.2288, pruned_loss=0.01898, over 7407.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2404, pruned_loss=0.0275, over 1420110.41 frames.], batch size: 21, lr: 1.93e-04
+2022-05-16 08:05:41,373 INFO [train.py:812] (1/8) Epoch 40, batch 3900, loss[loss=0.1832, simple_loss=0.286, pruned_loss=0.04025, over 7197.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2402, pruned_loss=0.02728, over 1421208.42 frames.], batch size: 23, lr: 1.93e-04
+2022-05-16 08:06:40,227 INFO [train.py:812] (1/8) Epoch 40, batch 3950, loss[loss=0.1398, simple_loss=0.2315, pruned_loss=0.02405, over 7068.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2393, pruned_loss=0.02748, over 1416216.46 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:07:38,726 INFO [train.py:812] (1/8) Epoch 40, batch 4000, loss[loss=0.1252, simple_loss=0.2104, pruned_loss=0.02, over 7134.00 frames.], tot_loss[loss=0.148, simple_loss=0.24, pruned_loss=0.02796, over 1416685.80 frames.], batch size: 17, lr: 1.93e-04
+2022-05-16 08:08:36,087 INFO [train.py:812] (1/8) Epoch 40, batch 4050, loss[loss=0.1739, simple_loss=0.2756, pruned_loss=0.03611, over 7211.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2405, pruned_loss=0.02807, over 1420995.96 frames.], batch size: 22, lr: 1.93e-04
+2022-05-16 08:09:35,651 INFO [train.py:812] (1/8) Epoch 40, batch 4100, loss[loss=0.1437, simple_loss=0.2336, pruned_loss=0.02691, over 7228.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2406, pruned_loss=0.02815, over 1421175.78 frames.], batch size: 20, lr: 1.93e-04
+2022-05-16 08:10:34,177 INFO [train.py:812] (1/8) Epoch 40, batch 4150, loss[loss=0.1409, simple_loss=0.2317, pruned_loss=0.02506, over 7285.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2408, pruned_loss=0.02808, over 1423522.32 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:11:32,964 INFO [train.py:812] (1/8) Epoch 40, batch 4200, loss[loss=0.1263, simple_loss=0.2087, pruned_loss=0.02189, over 7154.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2408, pruned_loss=0.0282, over 1424260.96 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:12:31,940 INFO [train.py:812] (1/8) Epoch 40, batch 4250, loss[loss=0.1309, simple_loss=0.2228, pruned_loss=0.01952, over 7313.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2411, pruned_loss=0.0285, over 1418860.01 frames.], batch size: 21, lr: 1.93e-04
+2022-05-16 08:13:30,181 INFO [train.py:812] (1/8) Epoch 40, batch 4300, loss[loss=0.1243, simple_loss=0.2203, pruned_loss=0.01408, over 7161.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2407, pruned_loss=0.0282, over 1419093.19 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:14:29,470 INFO [train.py:812] (1/8) Epoch 40, batch 4350, loss[loss=0.1531, simple_loss=0.2402, pruned_loss=0.033, over 7327.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2409, pruned_loss=0.02823, over 1420128.08 frames.], batch size: 20, lr: 1.93e-04
+2022-05-16 08:15:29,012 INFO [train.py:812] (1/8) Epoch 40, batch 4400, loss[loss=0.1416, simple_loss=0.2332, pruned_loss=0.02496, over 6802.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2406, pruned_loss=0.0278, over 1421401.84 frames.], batch size: 31, lr: 1.93e-04
+2022-05-16 08:16:26,681 INFO [train.py:812] (1/8) Epoch 40, batch 4450, loss[loss=0.1423, simple_loss=0.2345, pruned_loss=0.0251, over 7166.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2407, pruned_loss=0.02805, over 1408593.08 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:17:25,845 INFO [train.py:812] (1/8) Epoch 40, batch 4500, loss[loss=0.1603, simple_loss=0.2657, pruned_loss=0.02739, over 7222.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2417, pruned_loss=0.02824, over 1401074.22 frames.], batch size: 21, lr: 1.93e-04
+2022-05-16 08:18:25,883 INFO [train.py:812] (1/8) Epoch 40, batch 4550, loss[loss=0.1243, simple_loss=0.2134, pruned_loss=0.01762, over 6762.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2385, pruned_loss=0.0277, over 1393034.96 frames.], batch size: 15, lr: 1.93e-04
+2022-05-16 08:19:10,327 INFO [train.py:1030] (1/8) Done!