diff --git "a/exp/log/log-train-2022-04-28-06-39-03-2" "b/exp/log/log-train-2022-04-28-06-39-03-2"
new file mode 100644--- /dev/null
+++ "b/exp/log/log-train-2022-04-28-06-39-03-2"
@@ -0,0 +1,3784 @@
+2022-04-28 06:39:03,119 INFO [train.py:827] (2/8) Training started
+2022-04-28 06:39:03,119 INFO [train.py:837] (2/8) Device: cuda:2
+2022-04-28 06:39:03,161 INFO [train.py:846] (2/8) {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.14', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '3b83183234d0f1d8391872630551c5af7c491ed2', 'k2-git-date': 'Tue Apr 12 08:26:41 2022', 'lhotse-version': '1.1.0.dev+missing.version.file', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'deeper-conformer', 'icefall-git-sha1': 'd79f5fe-dirty', 'icefall-git-date': 'Mon Apr 25 17:26:43 2022', 'icefall-path': '/ceph-fj/fangjun/open-source-2/icefall-deeper-conformer', 'k2-path': '/ceph-fj/fangjun/open-source-2/k2-multi-2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-fj/fangjun/open-source-2/lhotse-multi-3/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-7-0309102938-68688b4cbd-xhtcg', 'IP address': '10.48.32.137'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 40, 'start_epoch': 0, 'start_batch': 0, 'exp_dir': PosixPath('pruned_transducer_stateless4/exp-L'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'initial_lr': 0.003, 'lr_batches': 5000, 'lr_epochs': 6, 'context_size': 2, 'prune_range': 5, 'lm_scale': 0.25, 'am_scale': 0.0, 'simple_loss_scale': 0.5, 'seed': 42, 'print_diagnostics': False, 'save_every_n': 8000, 'keep_last_k': 20, 'use_fp16': False, 'num_encoder_layers': 18, 'dim_feedforward': 2048, 'nhead': 8, 'encoder_dim': 512, 'decoder_dim': 512, 'joiner_dim': 512, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'blank_id': 0, 'vocab_size': 500}
+2022-04-28 06:39:03,161 INFO [train.py:848] (2/8) About to create model
+2022-04-28 06:39:03,699 INFO [train.py:852] (2/8) Number of model parameters: 118129516
+2022-04-28 06:39:09,606 INFO [train.py:858] (2/8) Using DDP
+2022-04-28 06:39:10,513 INFO [asr_datamodule.py:391] (2/8) About to get train-clean-100 cuts
+2022-04-28 06:39:16,615 INFO [asr_datamodule.py:398] (2/8) About to get train-clean-360 cuts
+2022-04-28 06:39:41,354 INFO [asr_datamodule.py:405] (2/8) About to get train-other-500 cuts
+2022-04-28 06:40:23,641 INFO [asr_datamodule.py:209] (2/8) Enable MUSAN
+2022-04-28 06:40:23,641 INFO [asr_datamodule.py:210] (2/8) About to get Musan cuts
+2022-04-28 06:40:24,903 INFO [asr_datamodule.py:238] (2/8) Enable SpecAugment
+2022-04-28 06:40:24,903 INFO [asr_datamodule.py:239] (2/8) Time warp factor: 80
+2022-04-28 06:40:24,903 INFO [asr_datamodule.py:251] (2/8) Num frame mask: 10
+2022-04-28 06:40:24,903 INFO [asr_datamodule.py:264] (2/8) About to create train dataset
+2022-04-28 06:40:24,903 INFO [asr_datamodule.py:292] (2/8) Using BucketingSampler.
+2022-04-28 06:40:29,506 INFO [asr_datamodule.py:308] (2/8) About to create train dataloader
+2022-04-28 06:40:29,507 INFO [asr_datamodule.py:412] (2/8) About to get dev-clean cuts
+2022-04-28 06:40:29,772 INFO [asr_datamodule.py:417] (2/8) About to get dev-other cuts
+2022-04-28 06:40:29,899 INFO [asr_datamodule.py:339] (2/8) About to create dev dataset
+2022-04-28 06:40:29,910 INFO [asr_datamodule.py:358] (2/8) About to create dev dataloader
+2022-04-28 06:40:29,910 INFO [train.py:987] (2/8) Sanity check -- see if any of the batches in epoch 0 would cause OOM.
+2022-04-28 06:40:42,725 INFO [distributed.py:874] (2/8) Reducer buckets have been rebuilt in this iteration.
+2022-04-28 06:41:17,065 INFO [train.py:763] (2/8) Epoch 0, batch 0, loss[loss=0.6506, simple_loss=1.301, pruned_loss=7.054, over 7296.00 frames.], tot_loss[loss=0.6506, simple_loss=1.301, pruned_loss=7.054, over 7296.00 frames.], batch size: 17, lr: 3.00e-03
+2022-04-28 06:42:23,562 INFO [train.py:763] (2/8) Epoch 0, batch 50, loss[loss=0.5172, simple_loss=1.034, pruned_loss=6.697, over 7163.00 frames.], tot_loss[loss=0.57, simple_loss=1.14, pruned_loss=6.958, over 323641.55 frames.], batch size: 19, lr: 3.00e-03
+2022-04-28 06:43:30,296 INFO [train.py:763] (2/8) Epoch 0, batch 100, loss[loss=0.4273, simple_loss=0.8546, pruned_loss=6.647, over 7009.00 frames.], tot_loss[loss=0.5125, simple_loss=1.025, pruned_loss=6.878, over 566898.99 frames.], batch size: 16, lr: 3.00e-03
+2022-04-28 06:44:37,535 INFO [train.py:763] (2/8) Epoch 0, batch 150, loss[loss=0.356, simple_loss=0.712, pruned_loss=6.575, over 6980.00 frames.], tot_loss[loss=0.4775, simple_loss=0.955, pruned_loss=6.862, over 757960.79 frames.], batch size: 16, lr: 3.00e-03
+2022-04-28 06:45:44,955 INFO [train.py:763] (2/8) Epoch 0, batch 200, loss[loss=0.445, simple_loss=0.89, pruned_loss=6.89, over 7300.00 frames.], tot_loss[loss=0.453, simple_loss=0.9061, pruned_loss=6.84, over 908055.36 frames.], batch size: 25, lr: 3.00e-03
+2022-04-28 06:46:50,978 INFO [train.py:763] (2/8) Epoch 0, batch 250, loss[loss=0.4348, simple_loss=0.8695, pruned_loss=6.762, over 7314.00 frames.], tot_loss[loss=0.4383, simple_loss=0.8765, pruned_loss=6.807, over 1016466.32 frames.], batch size: 21, lr: 3.00e-03
+2022-04-28 06:47:58,723 INFO [train.py:763] (2/8) Epoch 0, batch 300, loss[loss=0.4247, simple_loss=0.8494, pruned_loss=6.752, over 7299.00 frames.], tot_loss[loss=0.4256, simple_loss=0.8512, pruned_loss=6.774, over 1108793.90 frames.], batch size: 25, lr: 3.00e-03
+2022-04-28 06:49:06,196 INFO [train.py:763] (2/8) Epoch 0, batch 350, loss[loss=0.3754, simple_loss=0.7509, pruned_loss=6.61, over 7264.00 frames.], tot_loss[loss=0.4145, simple_loss=0.8291, pruned_loss=6.734, over 1178310.31 frames.], batch size: 19, lr: 3.00e-03
+2022-04-28 06:50:12,115 INFO [train.py:763] (2/8) Epoch 0, batch 400, loss[loss=0.386, simple_loss=0.7721, pruned_loss=6.685, over 7422.00 frames.], tot_loss[loss=0.4037, simple_loss=0.8074, pruned_loss=6.702, over 1231527.53 frames.], batch size: 21, lr: 3.00e-03
+2022-04-28 06:51:17,801 INFO [train.py:763] (2/8) Epoch 0, batch 450, loss[loss=0.3368, simple_loss=0.6737, pruned_loss=6.602, over 7409.00 frames.], tot_loss[loss=0.3909, simple_loss=0.7818, pruned_loss=6.683, over 1266470.44 frames.], batch size: 21, lr: 2.99e-03
+2022-04-28 06:52:24,497 INFO [train.py:763] (2/8) Epoch 0, batch 500, loss[loss=0.3191, simple_loss=0.6382, pruned_loss=6.75, over 7223.00 frames.], tot_loss[loss=0.3752, simple_loss=0.7504, pruned_loss=6.674, over 1302545.74 frames.], batch size: 22, lr: 2.99e-03
+2022-04-28 06:53:29,995 INFO [train.py:763] (2/8) Epoch 0, batch 550, loss[loss=0.3329, simple_loss=0.6657, pruned_loss=6.766, over 7338.00 frames.], tot_loss[loss=0.3611, simple_loss=0.7222, pruned_loss=6.675, over 1328824.69 frames.], batch size: 22, lr: 2.99e-03
+2022-04-28 06:54:36,568 INFO [train.py:763] (2/8) Epoch 0, batch 600, loss[loss=0.2659, simple_loss=0.5319, pruned_loss=6.633, over 7119.00 frames.], tot_loss[loss=0.3446, simple_loss=0.6892, pruned_loss=6.664, over 1350008.93 frames.], batch size: 21, lr: 2.99e-03
+2022-04-28 06:55:42,122 INFO [train.py:763] (2/8) Epoch 0, batch 650, loss[loss=0.2529, simple_loss=0.5058, pruned_loss=6.596, over 7013.00 frames.], tot_loss[loss=0.331, simple_loss=0.662, pruned_loss=6.653, over 1368533.50 frames.], batch size: 16, lr: 2.99e-03
+2022-04-28 06:56:47,771 INFO [train.py:763] (2/8) Epoch 0, batch 700, loss[loss=0.2995, simple_loss=0.599, pruned_loss=6.745, over 7197.00 frames.], tot_loss[loss=0.3173, simple_loss=0.6346, pruned_loss=6.637, over 1379447.11 frames.], batch size: 23, lr: 2.99e-03
+2022-04-28 06:57:54,483 INFO [train.py:763] (2/8) Epoch 0, batch 750, loss[loss=0.2422, simple_loss=0.4844, pruned_loss=6.474, over 7297.00 frames.], tot_loss[loss=0.3047, simple_loss=0.6094, pruned_loss=6.623, over 1391728.06 frames.], batch size: 17, lr: 2.98e-03
+2022-04-28 06:59:01,266 INFO [train.py:763] (2/8) Epoch 0, batch 800, loss[loss=0.2705, simple_loss=0.541, pruned_loss=6.617, over 7100.00 frames.], tot_loss[loss=0.2944, simple_loss=0.5889, pruned_loss=6.614, over 1397287.60 frames.], batch size: 21, lr: 2.98e-03
+2022-04-28 07:00:07,430 INFO [train.py:763] (2/8) Epoch 0, batch 850, loss[loss=0.2645, simple_loss=0.5289, pruned_loss=6.611, over 7213.00 frames.], tot_loss[loss=0.2851, simple_loss=0.5701, pruned_loss=6.601, over 1403384.56 frames.], batch size: 21, lr: 2.98e-03
+2022-04-28 07:01:13,425 INFO [train.py:763] (2/8) Epoch 0, batch 900, loss[loss=0.2783, simple_loss=0.5566, pruned_loss=6.69, over 7308.00 frames.], tot_loss[loss=0.2764, simple_loss=0.5528, pruned_loss=6.588, over 1407651.70 frames.], batch size: 21, lr: 2.98e-03
+2022-04-28 07:02:19,009 INFO [train.py:763] (2/8) Epoch 0, batch 950, loss[loss=0.2239, simple_loss=0.4479, pruned_loss=6.547, over 7015.00 frames.], tot_loss[loss=0.2707, simple_loss=0.5414, pruned_loss=6.584, over 1405297.46 frames.], batch size: 16, lr: 2.97e-03
+2022-04-28 07:03:26,143 INFO [train.py:763] (2/8) Epoch 0, batch 1000, loss[loss=0.2247, simple_loss=0.4495, pruned_loss=6.525, over 6982.00 frames.], tot_loss[loss=0.2644, simple_loss=0.5288, pruned_loss=6.58, over 1406385.65 frames.], batch size: 16, lr: 2.97e-03
+2022-04-28 07:04:32,975 INFO [train.py:763] (2/8) Epoch 0, batch 1050, loss[loss=0.2123, simple_loss=0.4247, pruned_loss=6.475, over 6988.00 frames.], tot_loss[loss=0.2594, simple_loss=0.5187, pruned_loss=6.574, over 1408859.01 frames.], batch size: 16, lr: 2.97e-03
+2022-04-28 07:05:39,528 INFO [train.py:763] (2/8) Epoch 0, batch 1100, loss[loss=0.2316, simple_loss=0.4631, pruned_loss=6.604, over 7209.00 frames.], tot_loss[loss=0.2538, simple_loss=0.5077, pruned_loss=6.576, over 1412958.75 frames.], batch size: 22, lr: 2.96e-03
+2022-04-28 07:06:46,910 INFO [train.py:763] (2/8) Epoch 0, batch 1150, loss[loss=0.2389, simple_loss=0.4777, pruned_loss=6.613, over 6844.00 frames.], tot_loss[loss=0.2481, simple_loss=0.4961, pruned_loss=6.569, over 1413758.23 frames.], batch size: 31, lr: 2.96e-03
+2022-04-28 07:07:52,781 INFO [train.py:763] (2/8) Epoch 0, batch 1200, loss[loss=0.2468, simple_loss=0.4937, pruned_loss=6.691, over 7158.00 frames.], tot_loss[loss=0.2433, simple_loss=0.4867, pruned_loss=6.569, over 1422064.93 frames.], batch size: 26, lr: 2.96e-03
+2022-04-28 07:08:58,128 INFO [train.py:763] (2/8) Epoch 0, batch 1250, loss[loss=0.2474, simple_loss=0.4947, pruned_loss=6.721, over 7383.00 frames.], tot_loss[loss=0.2401, simple_loss=0.4801, pruned_loss=6.574, over 1414893.79 frames.], batch size: 23, lr: 2.95e-03
+2022-04-28 07:10:04,041 INFO [train.py:763] (2/8) Epoch 0, batch 1300, loss[loss=0.2453, simple_loss=0.4907, pruned_loss=6.725, over 7300.00 frames.], tot_loss[loss=0.2361, simple_loss=0.4722, pruned_loss=6.579, over 1422344.93 frames.], batch size: 24, lr: 2.95e-03
+2022-04-28 07:11:09,798 INFO [train.py:763] (2/8) Epoch 0, batch 1350, loss[loss=0.2177, simple_loss=0.4354, pruned_loss=6.527, over 7150.00 frames.], tot_loss[loss=0.232, simple_loss=0.4641, pruned_loss=6.576, over 1423721.98 frames.], batch size: 20, lr: 2.95e-03
+2022-04-28 07:12:15,112 INFO [train.py:763] (2/8) Epoch 0, batch 1400, loss[loss=0.2084, simple_loss=0.4169, pruned_loss=6.531, over 7304.00 frames.], tot_loss[loss=0.2306, simple_loss=0.4612, pruned_loss=6.586, over 1420255.88 frames.], batch size: 24, lr: 2.94e-03
+2022-04-28 07:13:21,015 INFO [train.py:763] (2/8) Epoch 0, batch 1450, loss[loss=0.1943, simple_loss=0.3886, pruned_loss=6.408, over 7154.00 frames.], tot_loss[loss=0.2277, simple_loss=0.4553, pruned_loss=6.583, over 1420438.74 frames.], batch size: 17, lr: 2.94e-03
+2022-04-28 07:14:26,709 INFO [train.py:763] (2/8) Epoch 0, batch 1500, loss[loss=0.2391, simple_loss=0.4782, pruned_loss=6.708, over 7296.00 frames.], tot_loss[loss=0.2252, simple_loss=0.4505, pruned_loss=6.578, over 1423780.93 frames.], batch size: 24, lr: 2.94e-03
+2022-04-28 07:15:32,246 INFO [train.py:763] (2/8) Epoch 0, batch 1550, loss[loss=0.2297, simple_loss=0.4593, pruned_loss=6.624, over 7122.00 frames.], tot_loss[loss=0.2231, simple_loss=0.4462, pruned_loss=6.577, over 1423567.68 frames.], batch size: 21, lr: 2.93e-03
+2022-04-28 07:16:38,326 INFO [train.py:763] (2/8) Epoch 0, batch 1600, loss[loss=0.2265, simple_loss=0.453, pruned_loss=6.653, over 7326.00 frames.], tot_loss[loss=0.2213, simple_loss=0.4427, pruned_loss=6.574, over 1420977.21 frames.], batch size: 20, lr: 2.93e-03
+2022-04-28 07:17:45,335 INFO [train.py:763] (2/8) Epoch 0, batch 1650, loss[loss=0.1889, simple_loss=0.3779, pruned_loss=6.471, over 7165.00 frames.], tot_loss[loss=0.219, simple_loss=0.4379, pruned_loss=6.571, over 1422693.39 frames.], batch size: 18, lr: 2.92e-03
+2022-04-28 07:18:51,994 INFO [train.py:763] (2/8) Epoch 0, batch 1700, loss[loss=0.2267, simple_loss=0.4534, pruned_loss=6.59, over 6197.00 frames.], tot_loss[loss=0.2175, simple_loss=0.4349, pruned_loss=6.569, over 1417327.27 frames.], batch size: 37, lr: 2.92e-03
+2022-04-28 07:19:58,694 INFO [train.py:763] (2/8) Epoch 0, batch 1750, loss[loss=0.2252, simple_loss=0.4504, pruned_loss=6.517, over 6495.00 frames.], tot_loss[loss=0.215, simple_loss=0.4299, pruned_loss=6.569, over 1417354.97 frames.], batch size: 37, lr: 2.91e-03
+2022-04-28 07:21:06,364 INFO [train.py:763] (2/8) Epoch 0, batch 1800, loss[loss=0.2216, simple_loss=0.4431, pruned_loss=6.564, over 7086.00 frames.], tot_loss[loss=0.2133, simple_loss=0.4267, pruned_loss=6.565, over 1417974.35 frames.], batch size: 28, lr: 2.91e-03
+2022-04-28 07:22:12,421 INFO [train.py:763] (2/8) Epoch 0, batch 1850, loss[loss=0.2439, simple_loss=0.4878, pruned_loss=6.396, over 5311.00 frames.], tot_loss[loss=0.2115, simple_loss=0.4231, pruned_loss=6.563, over 1419180.86 frames.], batch size: 52, lr: 2.91e-03
+2022-04-28 07:23:18,916 INFO [train.py:763] (2/8) Epoch 0, batch 1900, loss[loss=0.2043, simple_loss=0.4086, pruned_loss=6.534, over 7269.00 frames.], tot_loss[loss=0.2099, simple_loss=0.4199, pruned_loss=6.564, over 1420195.67 frames.], batch size: 19, lr: 2.90e-03
+2022-04-28 07:24:26,524 INFO [train.py:763] (2/8) Epoch 0, batch 1950, loss[loss=0.2086, simple_loss=0.4171, pruned_loss=6.703, over 7316.00 frames.], tot_loss[loss=0.209, simple_loss=0.418, pruned_loss=6.567, over 1423479.59 frames.], batch size: 21, lr: 2.90e-03
+2022-04-28 07:25:34,069 INFO [train.py:763] (2/8) Epoch 0, batch 2000, loss[loss=0.1849, simple_loss=0.3698, pruned_loss=6.432, over 6782.00 frames.], tot_loss[loss=0.2071, simple_loss=0.4143, pruned_loss=6.565, over 1424250.07 frames.], batch size: 15, lr: 2.89e-03
+2022-04-28 07:26:39,959 INFO [train.py:763] (2/8) Epoch 0, batch 2050, loss[loss=0.2178, simple_loss=0.4355, pruned_loss=6.678, over 7168.00 frames.], tot_loss[loss=0.2059, simple_loss=0.4119, pruned_loss=6.564, over 1422693.60 frames.], batch size: 26, lr: 2.89e-03
+2022-04-28 07:27:45,820 INFO [train.py:763] (2/8) Epoch 0, batch 2100, loss[loss=0.1901, simple_loss=0.3803, pruned_loss=6.53, over 7163.00 frames.], tot_loss[loss=0.2053, simple_loss=0.4107, pruned_loss=6.567, over 1419075.32 frames.], batch size: 18, lr: 2.88e-03
+2022-04-28 07:28:51,549 INFO [train.py:763] (2/8) Epoch 0, batch 2150, loss[loss=0.2213, simple_loss=0.4426, pruned_loss=6.653, over 7341.00 frames.], tot_loss[loss=0.2039, simple_loss=0.4079, pruned_loss=6.572, over 1423279.01 frames.], batch size: 22, lr: 2.88e-03
+2022-04-28 07:29:57,475 INFO [train.py:763] (2/8) Epoch 0, batch 2200, loss[loss=0.191, simple_loss=0.3821, pruned_loss=6.504, over 7297.00 frames.], tot_loss[loss=0.2033, simple_loss=0.4066, pruned_loss=6.579, over 1422516.49 frames.], batch size: 25, lr: 2.87e-03
+2022-04-28 07:31:03,287 INFO [train.py:763] (2/8) Epoch 0, batch 2250, loss[loss=0.2222, simple_loss=0.4445, pruned_loss=6.623, over 7209.00 frames.], tot_loss[loss=0.2021, simple_loss=0.4041, pruned_loss=6.576, over 1420823.96 frames.], batch size: 21, lr: 2.86e-03
+2022-04-28 07:32:08,988 INFO [train.py:763] (2/8) Epoch 0, batch 2300, loss[loss=0.1732, simple_loss=0.3463, pruned_loss=6.496, over 7249.00 frames.], tot_loss[loss=0.2027, simple_loss=0.4053, pruned_loss=6.576, over 1415019.26 frames.], batch size: 19, lr: 2.86e-03
+2022-04-28 07:33:14,406 INFO [train.py:763] (2/8) Epoch 0, batch 2350, loss[loss=0.2464, simple_loss=0.4929, pruned_loss=6.634, over 4769.00 frames.], tot_loss[loss=0.2027, simple_loss=0.4054, pruned_loss=6.583, over 1414409.16 frames.], batch size: 52, lr: 2.85e-03
+2022-04-28 07:34:20,286 INFO [train.py:763] (2/8) Epoch 0, batch 2400, loss[loss=0.1783, simple_loss=0.3566, pruned_loss=6.498, over 7437.00 frames.], tot_loss[loss=0.2015, simple_loss=0.403, pruned_loss=6.581, over 1410521.62 frames.], batch size: 20, lr: 2.85e-03
+2022-04-28 07:35:25,714 INFO [train.py:763] (2/8) Epoch 0, batch 2450, loss[loss=0.2284, simple_loss=0.4569, pruned_loss=6.705, over 5134.00 frames.], tot_loss[loss=0.2005, simple_loss=0.401, pruned_loss=6.58, over 1411129.36 frames.], batch size: 53, lr: 2.84e-03
+2022-04-28 07:36:32,806 INFO [train.py:763] (2/8) Epoch 0, batch 2500, loss[loss=0.193, simple_loss=0.3859, pruned_loss=6.64, over 7325.00 frames.], tot_loss[loss=0.1995, simple_loss=0.3989, pruned_loss=6.581, over 1417635.61 frames.], batch size: 20, lr: 2.84e-03
+2022-04-28 07:37:40,454 INFO [train.py:763] (2/8) Epoch 0, batch 2550, loss[loss=0.1839, simple_loss=0.3679, pruned_loss=6.521, over 7405.00 frames.], tot_loss[loss=0.1997, simple_loss=0.3994, pruned_loss=6.591, over 1418500.35 frames.], batch size: 18, lr: 2.83e-03
+2022-04-28 07:38:46,542 INFO [train.py:763] (2/8) Epoch 0, batch 2600, loss[loss=0.2141, simple_loss=0.4282, pruned_loss=6.672, over 7232.00 frames.], tot_loss[loss=0.1982, simple_loss=0.3964, pruned_loss=6.594, over 1421362.11 frames.], batch size: 20, lr: 2.83e-03
+2022-04-28 07:39:52,333 INFO [train.py:763] (2/8) Epoch 0, batch 2650, loss[loss=0.1741, simple_loss=0.3481, pruned_loss=6.517, over 7234.00 frames.], tot_loss[loss=0.197, simple_loss=0.394, pruned_loss=6.594, over 1422850.41 frames.], batch size: 20, lr: 2.82e-03
+2022-04-28 07:40:58,202 INFO [train.py:763] (2/8) Epoch 0, batch 2700, loss[loss=0.2029, simple_loss=0.4058, pruned_loss=6.592, over 7132.00 frames.], tot_loss[loss=0.1966, simple_loss=0.3933, pruned_loss=6.595, over 1422097.03 frames.], batch size: 20, lr: 2.81e-03
+2022-04-28 07:42:03,315 INFO [train.py:763] (2/8) Epoch 0, batch 2750, loss[loss=0.196, simple_loss=0.392, pruned_loss=6.545, over 7318.00 frames.], tot_loss[loss=0.1965, simple_loss=0.393, pruned_loss=6.6, over 1423103.94 frames.], batch size: 20, lr: 2.81e-03
+2022-04-28 07:43:09,945 INFO [train.py:763] (2/8) Epoch 0, batch 2800, loss[loss=0.1992, simple_loss=0.3984, pruned_loss=6.598, over 7147.00 frames.], tot_loss[loss=0.1965, simple_loss=0.3931, pruned_loss=6.604, over 1421784.23 frames.], batch size: 20, lr: 2.80e-03
+2022-04-28 07:44:16,826 INFO [train.py:763] (2/8) Epoch 0, batch 2850, loss[loss=0.1982, simple_loss=0.3965, pruned_loss=6.558, over 7358.00 frames.], tot_loss[loss=0.195, simple_loss=0.39, pruned_loss=6.6, over 1425229.45 frames.], batch size: 19, lr: 2.80e-03
+2022-04-28 07:45:22,335 INFO [train.py:763] (2/8) Epoch 0, batch 2900, loss[loss=0.1802, simple_loss=0.3604, pruned_loss=6.592, over 7311.00 frames.], tot_loss[loss=0.1954, simple_loss=0.3908, pruned_loss=6.607, over 1421082.26 frames.], batch size: 20, lr: 2.79e-03
+2022-04-28 07:46:27,652 INFO [train.py:763] (2/8) Epoch 0, batch 2950, loss[loss=0.1982, simple_loss=0.3963, pruned_loss=6.569, over 7152.00 frames.], tot_loss[loss=0.1938, simple_loss=0.3875, pruned_loss=6.602, over 1417057.00 frames.], batch size: 26, lr: 2.78e-03
+2022-04-28 07:47:32,887 INFO [train.py:763] (2/8) Epoch 0, batch 3000, loss[loss=0.3324, simple_loss=0.3719, pruned_loss=1.464, over 7283.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3879, pruned_loss=6.578, over 1420556.07 frames.], batch size: 17, lr: 2.78e-03
+2022-04-28 07:47:32,888 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-28 07:47:50,998 INFO [train.py:792] (2/8) Epoch 0, validation: loss=2.072, simple_loss=0.4419, pruned_loss=1.851, over 698248.00 frames.
+2022-04-28 07:48:57,673 INFO [train.py:763] (2/8) Epoch 0, batch 3050, loss[loss=0.2979, simple_loss=0.41, pruned_loss=0.9292, over 6373.00 frames.], tot_loss[loss=0.2516, simple_loss=0.3976, pruned_loss=5.39, over 1420698.26 frames.], batch size: 38, lr: 2.77e-03
+2022-04-28 07:50:04,083 INFO [train.py:763] (2/8) Epoch 0, batch 3100, loss[loss=0.2479, simple_loss=0.3877, pruned_loss=0.5406, over 7411.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3926, pruned_loss=4.332, over 1426122.06 frames.], batch size: 21, lr: 2.77e-03
+2022-04-28 07:51:10,053 INFO [train.py:763] (2/8) Epoch 0, batch 3150, loss[loss=0.2057, simple_loss=0.35, pruned_loss=0.3073, over 7415.00 frames.], tot_loss[loss=0.2468, simple_loss=0.3881, pruned_loss=3.46, over 1427075.09 frames.], batch size: 21, lr: 2.76e-03
+2022-04-28 07:52:16,816 INFO [train.py:763] (2/8) Epoch 0, batch 3200, loss[loss=0.243, simple_loss=0.4234, pruned_loss=0.3131, over 7278.00 frames.], tot_loss[loss=0.2412, simple_loss=0.3867, pruned_loss=2.768, over 1423136.62 frames.], batch size: 24, lr: 2.75e-03
+2022-04-28 07:53:24,320 INFO [train.py:763] (2/8) Epoch 0, batch 3250, loss[loss=0.2259, simple_loss=0.3981, pruned_loss=0.2679, over 7149.00 frames.], tot_loss[loss=0.236, simple_loss=0.3858, pruned_loss=2.212, over 1423101.91 frames.], batch size: 20, lr: 2.75e-03
+2022-04-28 07:54:30,946 INFO [train.py:763] (2/8) Epoch 0, batch 3300, loss[loss=0.2178, simple_loss=0.3891, pruned_loss=0.233, over 7405.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3859, pruned_loss=1.78, over 1418910.22 frames.], batch size: 23, lr: 2.74e-03
+2022-04-28 07:55:37,617 INFO [train.py:763] (2/8) Epoch 0, batch 3350, loss[loss=0.2368, simple_loss=0.4199, pruned_loss=0.2684, over 7289.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3859, pruned_loss=1.432, over 1423414.83 frames.], batch size: 24, lr: 2.73e-03
+2022-04-28 07:56:43,234 INFO [train.py:763] (2/8) Epoch 0, batch 3400, loss[loss=0.2053, simple_loss=0.3707, pruned_loss=0.1998, over 7256.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3858, pruned_loss=1.162, over 1423849.53 frames.], batch size: 19, lr: 2.73e-03
+2022-04-28 07:57:49,070 INFO [train.py:763] (2/8) Epoch 0, batch 3450, loss[loss=0.206, simple_loss=0.3746, pruned_loss=0.1865, over 7311.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3838, pruned_loss=0.9498, over 1423335.00 frames.], batch size: 25, lr: 2.72e-03
+2022-04-28 07:58:54,326 INFO [train.py:763] (2/8) Epoch 0, batch 3500, loss[loss=0.2269, simple_loss=0.4091, pruned_loss=0.223, over 7133.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3838, pruned_loss=0.7845, over 1421812.44 frames.], batch size: 26, lr: 2.72e-03
+2022-04-28 08:00:00,010 INFO [train.py:763] (2/8) Epoch 0, batch 3550, loss[loss=0.2231, simple_loss=0.4064, pruned_loss=0.1986, over 7218.00 frames.], tot_loss[loss=0.2162, simple_loss=0.3813, pruned_loss=0.6515, over 1422843.50 frames.], batch size: 21, lr: 2.71e-03
+2022-04-28 08:01:06,047 INFO [train.py:763] (2/8) Epoch 0, batch 3600, loss[loss=0.1797, simple_loss=0.3318, pruned_loss=0.1381, over 7010.00 frames.], tot_loss[loss=0.2138, simple_loss=0.3796, pruned_loss=0.5484, over 1421309.00 frames.], batch size: 16, lr: 2.70e-03
+2022-04-28 08:02:21,059 INFO [train.py:763] (2/8) Epoch 0, batch 3650, loss[loss=0.2199, simple_loss=0.3988, pruned_loss=0.2044, over 7219.00 frames.], tot_loss[loss=0.2113, simple_loss=0.3775, pruned_loss=0.4657, over 1421824.87 frames.], batch size: 21, lr: 2.70e-03
+2022-04-28 08:04:03,464 INFO [train.py:763] (2/8) Epoch 0, batch 3700, loss[loss=0.2002, simple_loss=0.3654, pruned_loss=0.1745, over 6731.00 frames.], tot_loss[loss=0.2095, simple_loss=0.3759, pruned_loss=0.4011, over 1426528.30 frames.], batch size: 31, lr: 2.69e-03
+2022-04-28 08:05:34,886 INFO [train.py:763] (2/8) Epoch 0, batch 3750, loss[loss=0.1794, simple_loss=0.3298, pruned_loss=0.1453, over 7277.00 frames.], tot_loss[loss=0.2081, simple_loss=0.375, pruned_loss=0.3523, over 1417750.19 frames.], batch size: 18, lr: 2.68e-03
+2022-04-28 08:06:40,595 INFO [train.py:763] (2/8) Epoch 0, batch 3800, loss[loss=0.1698, simple_loss=0.3152, pruned_loss=0.1223, over 7130.00 frames.], tot_loss[loss=0.2065, simple_loss=0.3734, pruned_loss=0.3116, over 1417544.90 frames.], batch size: 17, lr: 2.68e-03
+2022-04-28 08:07:46,188 INFO [train.py:763] (2/8) Epoch 0, batch 3850, loss[loss=0.1887, simple_loss=0.3495, pruned_loss=0.1393, over 7134.00 frames.], tot_loss[loss=0.2051, simple_loss=0.3721, pruned_loss=0.2782, over 1422952.39 frames.], batch size: 17, lr: 2.67e-03
+2022-04-28 08:08:52,445 INFO [train.py:763] (2/8) Epoch 0, batch 3900, loss[loss=0.1876, simple_loss=0.3433, pruned_loss=0.16, over 6820.00 frames.], tot_loss[loss=0.2046, simple_loss=0.372, pruned_loss=0.2545, over 1419175.61 frames.], batch size: 15, lr: 2.66e-03
+2022-04-28 08:09:58,856 INFO [train.py:763] (2/8) Epoch 0, batch 3950, loss[loss=0.1684, simple_loss=0.3101, pruned_loss=0.1329, over 6765.00 frames.], tot_loss[loss=0.204, simple_loss=0.3716, pruned_loss=0.2358, over 1417088.35 frames.], batch size: 15, lr: 2.66e-03
+2022-04-28 08:11:04,202 INFO [train.py:763] (2/8) Epoch 0, batch 4000, loss[loss=0.1943, simple_loss=0.3614, pruned_loss=0.1363, over 7325.00 frames.], tot_loss[loss=0.2036, simple_loss=0.3716, pruned_loss=0.2197, over 1419860.70 frames.], batch size: 21, lr: 2.65e-03
+2022-04-28 08:12:09,507 INFO [train.py:763] (2/8) Epoch 0, batch 4050, loss[loss=0.2122, simple_loss=0.3924, pruned_loss=0.1598, over 7061.00 frames.], tot_loss[loss=0.2024, simple_loss=0.3701, pruned_loss=0.2057, over 1420906.73 frames.], batch size: 28, lr: 2.64e-03
+2022-04-28 08:13:15,837 INFO [train.py:763] (2/8) Epoch 0, batch 4100, loss[loss=0.1798, simple_loss=0.3323, pruned_loss=0.1365, over 7258.00 frames.], tot_loss[loss=0.2013, simple_loss=0.3686, pruned_loss=0.1946, over 1420867.23 frames.], batch size: 19, lr: 2.64e-03
+2022-04-28 08:14:22,418 INFO [train.py:763] (2/8) Epoch 0, batch 4150, loss[loss=0.1777, simple_loss=0.3288, pruned_loss=0.1329, over 7064.00 frames.], tot_loss[loss=0.2007, simple_loss=0.368, pruned_loss=0.1859, over 1425446.82 frames.], batch size: 18, lr: 2.63e-03
+2022-04-28 08:15:27,426 INFO [train.py:763] (2/8) Epoch 0, batch 4200, loss[loss=0.2132, simple_loss=0.3907, pruned_loss=0.1791, over 7210.00 frames.], tot_loss[loss=0.2, simple_loss=0.3673, pruned_loss=0.1792, over 1424090.06 frames.], batch size: 22, lr: 2.63e-03
+2022-04-28 08:16:32,482 INFO [train.py:763] (2/8) Epoch 0, batch 4250, loss[loss=0.2108, simple_loss=0.3872, pruned_loss=0.172, over 7425.00 frames.], tot_loss[loss=0.2015, simple_loss=0.37, pruned_loss=0.177, over 1422932.68 frames.], batch size: 20, lr: 2.62e-03
+2022-04-28 08:17:38,263 INFO [train.py:763] (2/8) Epoch 0, batch 4300, loss[loss=0.2169, simple_loss=0.3999, pruned_loss=0.1699, over 7036.00 frames.], tot_loss[loss=0.2022, simple_loss=0.3715, pruned_loss=0.1742, over 1422530.15 frames.], batch size: 28, lr: 2.61e-03
+2022-04-28 08:18:43,768 INFO [train.py:763] (2/8) Epoch 0, batch 4350, loss[loss=0.1921, simple_loss=0.359, pruned_loss=0.1258, over 7438.00 frames.], tot_loss[loss=0.2023, simple_loss=0.3717, pruned_loss=0.1711, over 1426113.41 frames.], batch size: 20, lr: 2.61e-03
+2022-04-28 08:19:48,915 INFO [train.py:763] (2/8) Epoch 0, batch 4400, loss[loss=0.1893, simple_loss=0.3489, pruned_loss=0.1483, over 7281.00 frames.], tot_loss[loss=0.2027, simple_loss=0.3726, pruned_loss=0.1691, over 1424113.82 frames.], batch size: 18, lr: 2.60e-03
+2022-04-28 08:20:54,080 INFO [train.py:763] (2/8) Epoch 0, batch 4450, loss[loss=0.1648, simple_loss=0.3097, pruned_loss=0.09964, over 7424.00 frames.], tot_loss[loss=0.2028, simple_loss=0.373, pruned_loss=0.167, over 1423735.15 frames.], batch size: 20, lr: 2.59e-03
+2022-04-28 08:21:59,569 INFO [train.py:763] (2/8) Epoch 0, batch 4500, loss[loss=0.2114, simple_loss=0.3893, pruned_loss=0.168, over 6274.00 frames.], tot_loss[loss=0.2024, simple_loss=0.3725, pruned_loss=0.1651, over 1414567.11 frames.], batch size: 37, lr: 2.59e-03
+2022-04-28 08:23:05,614 INFO [train.py:763] (2/8) Epoch 0, batch 4550, loss[loss=0.2317, simple_loss=0.421, pruned_loss=0.2122, over 5020.00 frames.], tot_loss[loss=0.2034, simple_loss=0.3742, pruned_loss=0.1653, over 1395779.40 frames.], batch size: 52, lr: 2.58e-03
+2022-04-28 08:24:44,865 INFO [train.py:763] (2/8) Epoch 1, batch 0, loss[loss=0.2148, simple_loss=0.3955, pruned_loss=0.17, over 7186.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3955, pruned_loss=0.17, over 7186.00 frames.], batch size: 26, lr: 2.56e-03
+2022-04-28 08:25:50,517 INFO [train.py:763] (2/8) Epoch 1, batch 50, loss[loss=0.1924, simple_loss=0.3581, pruned_loss=0.1333, over 7234.00 frames.], tot_loss[loss=0.2031, simple_loss=0.3737, pruned_loss=0.1621, over 312334.29 frames.], batch size: 20, lr: 2.55e-03
+2022-04-28 08:26:56,236 INFO [train.py:763] (2/8) Epoch 1, batch 100, loss[loss=0.2007, simple_loss=0.3714, pruned_loss=0.1497, over 7429.00 frames.], tot_loss[loss=0.1964, simple_loss=0.3629, pruned_loss=0.1497, over 560142.16 frames.], batch size: 20, lr: 2.54e-03
+2022-04-28 08:28:01,394 INFO [train.py:763] (2/8) Epoch 1, batch 150, loss[loss=0.1902, simple_loss=0.3551, pruned_loss=0.1264, over 7334.00 frames.], tot_loss[loss=0.1954, simple_loss=0.3615, pruned_loss=0.1467, over 751010.46 frames.], batch size: 20, lr: 2.54e-03
+2022-04-28 08:29:06,943 INFO [train.py:763] (2/8) Epoch 1, batch 200, loss[loss=0.1816, simple_loss=0.3358, pruned_loss=0.1368, over 7146.00 frames.], tot_loss[loss=0.1947, simple_loss=0.3602, pruned_loss=0.146, over 900925.62 frames.], batch size: 19, lr: 2.53e-03
+2022-04-28 08:30:12,402 INFO [train.py:763] (2/8) Epoch 1, batch 250, loss[loss=0.226, simple_loss=0.4119, pruned_loss=0.2005, over 7371.00 frames.], tot_loss[loss=0.1951, simple_loss=0.3608, pruned_loss=0.1467, over 1015562.20 frames.], batch size: 23, lr: 2.53e-03
+2022-04-28 08:31:17,598 INFO [train.py:763] (2/8) Epoch 1, batch 300, loss[loss=0.1952, simple_loss=0.3632, pruned_loss=0.1356, over 7268.00 frames.], tot_loss[loss=0.1949, simple_loss=0.3607, pruned_loss=0.145, over 1104697.28 frames.], batch size: 19, lr: 2.52e-03
+2022-04-28 08:32:23,176 INFO [train.py:763] (2/8) Epoch 1, batch 350, loss[loss=0.1839, simple_loss=0.3425, pruned_loss=0.1267, over 7224.00 frames.], tot_loss[loss=0.1945, simple_loss=0.3599, pruned_loss=0.1448, over 1173552.78 frames.], batch size: 21, lr: 2.51e-03
+2022-04-28 08:33:29,293 INFO [train.py:763] (2/8) Epoch 1, batch 400, loss[loss=0.2096, simple_loss=0.388, pruned_loss=0.1563, over 7151.00 frames.], tot_loss[loss=0.1953, simple_loss=0.3614, pruned_loss=0.146, over 1230362.31 frames.], batch size: 20, lr: 2.51e-03
+2022-04-28 08:34:36,145 INFO [train.py:763] (2/8) Epoch 1, batch 450, loss[loss=0.1772, simple_loss=0.3287, pruned_loss=0.1284, over 7158.00 frames.], tot_loss[loss=0.195, simple_loss=0.361, pruned_loss=0.145, over 1276044.00 frames.], batch size: 19, lr: 2.50e-03
+2022-04-28 08:35:42,349 INFO [train.py:763] (2/8) Epoch 1, batch 500, loss[loss=0.2026, simple_loss=0.3745, pruned_loss=0.1536, over 7170.00 frames.], tot_loss[loss=0.1951, simple_loss=0.3612, pruned_loss=0.1446, over 1307596.84 frames.], batch size: 18, lr: 2.49e-03
+2022-04-28 08:36:48,842 INFO [train.py:763] (2/8) Epoch 1, batch 550, loss[loss=0.1823, simple_loss=0.3416, pruned_loss=0.1149, over 7356.00 frames.], tot_loss[loss=0.1944, simple_loss=0.36, pruned_loss=0.1437, over 1332429.00 frames.], batch size: 19, lr: 2.49e-03
+2022-04-28 08:37:55,691 INFO [train.py:763] (2/8) Epoch 1, batch 600, loss[loss=0.2057, simple_loss=0.3781, pruned_loss=0.1665, over 7389.00 frames.], tot_loss[loss=0.1953, simple_loss=0.3619, pruned_loss=0.1439, over 1354069.71 frames.], batch size: 23, lr: 2.48e-03
+2022-04-28 08:39:01,282 INFO [train.py:763] (2/8) Epoch 1, batch 650, loss[loss=0.178, simple_loss=0.3309, pruned_loss=0.1251, over 7276.00 frames.], tot_loss[loss=0.1946, simple_loss=0.3605, pruned_loss=0.1432, over 1368160.03 frames.], batch size: 18, lr: 2.48e-03
+2022-04-28 08:40:06,977 INFO [train.py:763] (2/8) Epoch 1, batch 700, loss[loss=0.2146, simple_loss=0.395, pruned_loss=0.1711, over 4988.00 frames.], tot_loss[loss=0.1941, simple_loss=0.3598, pruned_loss=0.1422, over 1379525.16 frames.], batch size: 52, lr: 2.47e-03
+2022-04-28 08:41:12,395 INFO [train.py:763] (2/8) Epoch 1, batch 750, loss[loss=0.1847, simple_loss=0.3442, pruned_loss=0.1263, over 7271.00 frames.], tot_loss[loss=0.194, simple_loss=0.3598, pruned_loss=0.1411, over 1391101.09 frames.], batch size: 19, lr: 2.46e-03
+2022-04-28 08:42:18,199 INFO [train.py:763] (2/8) Epoch 1, batch 800, loss[loss=0.1886, simple_loss=0.3488, pruned_loss=0.1416, over 7057.00 frames.], tot_loss[loss=0.1928, simple_loss=0.3578, pruned_loss=0.1389, over 1401022.22 frames.], batch size: 18, lr: 2.46e-03
+2022-04-28 08:43:24,112 INFO [train.py:763] (2/8) Epoch 1, batch 850, loss[loss=0.2033, simple_loss=0.3778, pruned_loss=0.1444, over 7309.00 frames.], tot_loss[loss=0.1923, simple_loss=0.357, pruned_loss=0.1376, over 1408462.84 frames.], batch size: 20, lr: 2.45e-03
+2022-04-28 08:44:29,822 INFO [train.py:763] (2/8) Epoch 1, batch 900, loss[loss=0.183, simple_loss=0.3411, pruned_loss=0.1245, over 7446.00 frames.], tot_loss[loss=0.1916, simple_loss=0.356, pruned_loss=0.1365, over 1412895.97 frames.], batch size: 20, lr: 2.45e-03
+2022-04-28 08:45:35,247 INFO [train.py:763] (2/8) Epoch 1, batch 950, loss[loss=0.1707, simple_loss=0.3211, pruned_loss=0.1017, over 7243.00 frames.], tot_loss[loss=0.1926, simple_loss=0.3576, pruned_loss=0.1382, over 1415241.72 frames.], batch size: 19, lr: 2.44e-03
+2022-04-28 08:46:40,815 INFO [train.py:763] (2/8) Epoch 1, batch 1000, loss[loss=0.2274, simple_loss=0.416, pruned_loss=0.1941, over 6655.00 frames.], tot_loss[loss=0.1923, simple_loss=0.3569, pruned_loss=0.1381, over 1417033.47 frames.], batch size: 31, lr: 2.43e-03
+2022-04-28 08:47:46,476 INFO [train.py:763] (2/8) Epoch 1, batch 1050, loss[loss=0.1754, simple_loss=0.3274, pruned_loss=0.1169, over 7428.00 frames.], tot_loss[loss=0.1914, simple_loss=0.3553, pruned_loss=0.137, over 1418846.60 frames.], batch size: 20, lr: 2.43e-03
+2022-04-28 08:48:51,690 INFO [train.py:763] (2/8) Epoch 1, batch 1100, loss[loss=0.179, simple_loss=0.3342, pruned_loss=0.1195, over 7164.00 frames.], tot_loss[loss=0.1908, simple_loss=0.3546, pruned_loss=0.135, over 1420415.72 frames.], batch size: 18, lr: 2.42e-03
+2022-04-28 08:49:57,302 INFO [train.py:763] (2/8) Epoch 1, batch 1150, loss[loss=0.1883, simple_loss=0.3504, pruned_loss=0.1311, over 7229.00 frames.], tot_loss[loss=0.1899, simple_loss=0.353, pruned_loss=0.134, over 1423262.55 frames.], batch size: 20, lr: 2.41e-03
+2022-04-28 08:51:02,488 INFO [train.py:763] (2/8) Epoch 1, batch 1200, loss[loss=0.2021, simple_loss=0.375, pruned_loss=0.1457, over 6983.00 frames.], tot_loss[loss=0.1897, simple_loss=0.3526, pruned_loss=0.1336, over 1422587.24 frames.], batch size: 28, lr: 2.41e-03
+2022-04-28 08:52:07,803 INFO [train.py:763] (2/8) Epoch 1, batch 1250, loss[loss=0.1859, simple_loss=0.3427, pruned_loss=0.145, over 7268.00 frames.], tot_loss[loss=0.1897, simple_loss=0.3527, pruned_loss=0.1329, over 1421868.00 frames.], batch size: 18, lr: 2.40e-03
+2022-04-28 08:53:12,957 INFO [train.py:763] (2/8) Epoch 1, batch 1300, loss[loss=0.1911, simple_loss=0.3584, pruned_loss=0.1191, over 7225.00 frames.], tot_loss[loss=0.1901, simple_loss=0.3536, pruned_loss=0.1335, over 1416335.83 frames.], batch size: 21, lr: 2.40e-03
+2022-04-28 08:54:18,348 INFO [train.py:763] (2/8) Epoch 1, batch 1350, loss[loss=0.1601, simple_loss=0.3015, pruned_loss=0.09318, over 7275.00 frames.], tot_loss[loss=0.189, simple_loss=0.3516, pruned_loss=0.1316, over 1419773.76 frames.], batch size: 17, lr: 2.39e-03
+2022-04-28 08:55:23,445 INFO [train.py:763] (2/8) Epoch 1, batch 1400, loss[loss=0.1913, simple_loss=0.3577, pruned_loss=0.1243, over 7214.00 frames.], tot_loss[loss=0.1895, simple_loss=0.3526, pruned_loss=0.1324, over 1418644.43 frames.], batch size: 21, lr: 2.39e-03
+2022-04-28 08:56:28,946 INFO [train.py:763] (2/8) Epoch 1, batch 1450, loss[loss=0.3118, simple_loss=0.3551, pruned_loss=0.1343, over 7134.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3544, pruned_loss=0.1352, over 1423053.79 frames.], batch size: 26, lr: 2.38e-03
+2022-04-28 08:57:34,411 INFO [train.py:763] (2/8) Epoch 1, batch 1500, loss[loss=0.3258, simple_loss=0.3692, pruned_loss=0.1412, over 6417.00 frames.], tot_loss[loss=0.2397, simple_loss=0.3565, pruned_loss=0.1371, over 1422477.54 frames.], batch size: 38, lr: 2.37e-03
+2022-04-28 08:58:40,147 INFO [train.py:763] (2/8) Epoch 1, batch 1550, loss[loss=0.2711, simple_loss=0.3331, pruned_loss=0.1045, over 7427.00 frames.], tot_loss[loss=0.2567, simple_loss=0.3578, pruned_loss=0.1366, over 1425546.40 frames.], batch size: 20, lr: 2.37e-03
+2022-04-28 08:59:47,366 INFO [train.py:763] (2/8) Epoch 1, batch 1600, loss[loss=0.2824, simple_loss=0.3277, pruned_loss=0.1186, over 7165.00 frames.], tot_loss[loss=0.2674, simple_loss=0.3563, pruned_loss=0.135, over 1425172.75 frames.], batch size: 18, lr: 2.36e-03
+2022-04-28 09:00:52,891 INFO [train.py:763] (2/8) Epoch 1, batch 1650, loss[loss=0.2587, simple_loss=0.3324, pruned_loss=0.09256, over 7429.00 frames.], tot_loss[loss=0.2747, simple_loss=0.3549, pruned_loss=0.1329, over 1425597.40 frames.], batch size: 20, lr: 2.36e-03
+2022-04-28 09:01:59,213 INFO [train.py:763] (2/8) Epoch 1, batch 1700, loss[loss=0.338, simple_loss=0.391, pruned_loss=0.1425, over 7428.00 frames.], tot_loss[loss=0.2819, simple_loss=0.3556, pruned_loss=0.1319, over 1424433.04 frames.], batch size: 21, lr: 2.35e-03
+2022-04-28 09:03:06,111 INFO [train.py:763] (2/8) Epoch 1, batch 1750, loss[loss=0.2724, simple_loss=0.3262, pruned_loss=0.1093, over 7292.00 frames.], tot_loss[loss=0.2886, simple_loss=0.3576, pruned_loss=0.1314, over 1423287.81 frames.], batch size: 18, lr: 2.34e-03
+2022-04-28 09:04:13,392 INFO [train.py:763] (2/8) Epoch 1, batch 1800, loss[loss=0.2905, simple_loss=0.3355, pruned_loss=0.1227, over 7371.00 frames.], tot_loss[loss=0.2924, simple_loss=0.3571, pruned_loss=0.1306, over 1424156.95 frames.], batch size: 19, lr: 2.34e-03
+2022-04-28 09:05:20,641 INFO [train.py:763] (2/8) Epoch 1, batch 1850, loss[loss=0.2996, simple_loss=0.3562, pruned_loss=0.1215, over 7329.00 frames.], tot_loss[loss=0.2934, simple_loss=0.3552, pruned_loss=0.1288, over 1424776.57 frames.], batch size: 20, lr: 2.33e-03
+2022-04-28 09:06:26,265 INFO [train.py:763] (2/8) Epoch 1, batch 1900, loss[loss=0.2647, simple_loss=0.3211, pruned_loss=0.1041, over 7010.00 frames.], tot_loss[loss=0.2963, simple_loss=0.3565, pruned_loss=0.1282, over 1428779.99 frames.], batch size: 16, lr: 2.33e-03
+2022-04-28 09:07:32,756 INFO [train.py:763] (2/8) Epoch 1, batch 1950, loss[loss=0.2709, simple_loss=0.3249, pruned_loss=0.1084, over 7295.00 frames.], tot_loss[loss=0.2985, simple_loss=0.357, pruned_loss=0.1279, over 1429307.40 frames.], batch size: 18, lr: 2.32e-03
+2022-04-28 09:08:38,159 INFO [train.py:763] (2/8) Epoch 1, batch 2000, loss[loss=0.3099, simple_loss=0.368, pruned_loss=0.1259, over 7117.00 frames.], tot_loss[loss=0.3019, simple_loss=0.3586, pruned_loss=0.1288, over 1423453.95 frames.], batch size: 21, lr: 2.32e-03
+2022-04-28 09:09:44,438 INFO [train.py:763] (2/8) Epoch 1, batch 2050, loss[loss=0.3277, simple_loss=0.3806, pruned_loss=0.1375, over 7089.00 frames.], tot_loss[loss=0.3024, simple_loss=0.3578, pruned_loss=0.1282, over 1424996.89 frames.], batch size: 28, lr: 2.31e-03
+2022-04-28 09:10:49,767 INFO [train.py:763] (2/8) Epoch 1, batch 2100, loss[loss=0.2711, simple_loss=0.3295, pruned_loss=0.1064, over 7408.00 frames.], tot_loss[loss=0.3016, simple_loss=0.3573, pruned_loss=0.1266, over 1425910.65 frames.], batch size: 18, lr: 2.31e-03
+2022-04-28 09:11:55,362 INFO [train.py:763] (2/8) Epoch 1, batch 2150, loss[loss=0.2938, simple_loss=0.3548, pruned_loss=0.1164, over 7403.00 frames.], tot_loss[loss=0.301, simple_loss=0.3568, pruned_loss=0.1255, over 1424080.95 frames.], batch size: 21, lr: 2.30e-03
+2022-04-28 09:13:01,254 INFO [train.py:763] (2/8) Epoch 1, batch 2200, loss[loss=0.2772, simple_loss=0.3474, pruned_loss=0.1035, over 7104.00 frames.], tot_loss[loss=0.3004, simple_loss=0.3557, pruned_loss=0.1248, over 1423074.97 frames.], batch size: 21, lr: 2.29e-03
+2022-04-28 09:14:06,867 INFO [train.py:763] (2/8) Epoch 1, batch 2250, loss[loss=0.283, simple_loss=0.3595, pruned_loss=0.1033, over 7209.00 frames.], tot_loss[loss=0.2989, simple_loss=0.3547, pruned_loss=0.1233, over 1424113.61 frames.], batch size: 21, lr: 2.29e-03
+2022-04-28 09:15:14,109 INFO [train.py:763] (2/8) Epoch 1, batch 2300, loss[loss=0.3728, simple_loss=0.4048, pruned_loss=0.1704, over 7202.00 frames.], tot_loss[loss=0.2993, simple_loss=0.3551, pruned_loss=0.1232, over 1424487.70 frames.], batch size: 22, lr: 2.28e-03
+2022-04-28 09:16:21,354 INFO [train.py:763] (2/8) Epoch 1, batch 2350, loss[loss=0.3144, simple_loss=0.3717, pruned_loss=0.1286, over 7225.00 frames.], tot_loss[loss=0.2993, simple_loss=0.3548, pruned_loss=0.123, over 1423513.52 frames.], batch size: 20, lr: 2.28e-03
+2022-04-28 09:17:26,497 INFO [train.py:763] (2/8) Epoch 1, batch 2400, loss[loss=0.3049, simple_loss=0.3783, pruned_loss=0.1158, over 7313.00 frames.], tot_loss[loss=0.2985, simple_loss=0.3545, pruned_loss=0.1221, over 1423126.64 frames.], batch size: 21, lr: 2.27e-03
+2022-04-28 09:18:31,928 INFO [train.py:763] (2/8) Epoch 1, batch 2450, loss[loss=0.282, simple_loss=0.3385, pruned_loss=0.1127, over 7328.00 frames.], tot_loss[loss=0.2992, simple_loss=0.3552, pruned_loss=0.1222, over 1425840.45 frames.], batch size: 21, lr: 2.27e-03
+2022-04-28 09:19:37,095 INFO [train.py:763] (2/8) Epoch 1, batch 2500, loss[loss=0.3586, simple_loss=0.3993, pruned_loss=0.159, over 7197.00 frames.], tot_loss[loss=0.2993, simple_loss=0.3553, pruned_loss=0.1221, over 1426489.64 frames.], batch size: 26, lr: 2.26e-03
+2022-04-28 09:20:43,297 INFO [train.py:763] (2/8) Epoch 1, batch 2550, loss[loss=0.2471, simple_loss=0.3165, pruned_loss=0.08884, over 6969.00 frames.], tot_loss[loss=0.2991, simple_loss=0.3553, pruned_loss=0.1219, over 1426457.58 frames.], batch size: 16, lr: 2.26e-03
+2022-04-28 09:21:48,825 INFO [train.py:763] (2/8) Epoch 1, batch 2600, loss[loss=0.3114, simple_loss=0.3702, pruned_loss=0.1263, over 7166.00 frames.], tot_loss[loss=0.2983, simple_loss=0.3547, pruned_loss=0.1212, over 1428722.21 frames.], batch size: 26, lr: 2.25e-03
+2022-04-28 09:22:54,014 INFO [train.py:763] (2/8) Epoch 1, batch 2650, loss[loss=0.3662, simple_loss=0.3926, pruned_loss=0.17, over 6628.00 frames.], tot_loss[loss=0.2977, simple_loss=0.3543, pruned_loss=0.1208, over 1427943.15 frames.], batch size: 38, lr: 2.25e-03
+2022-04-28 09:24:00,439 INFO [train.py:763] (2/8) Epoch 1, batch 2700, loss[loss=0.3086, simple_loss=0.3687, pruned_loss=0.1242, over 6691.00 frames.], tot_loss[loss=0.297, simple_loss=0.3535, pruned_loss=0.1204, over 1426880.15 frames.], batch size: 31, lr: 2.24e-03
+2022-04-28 09:25:06,553 INFO [train.py:763] (2/8) Epoch 1, batch 2750, loss[loss=0.2846, simple_loss=0.3577, pruned_loss=0.1058, over 7292.00 frames.], tot_loss[loss=0.296, simple_loss=0.3526, pruned_loss=0.1198, over 1424259.78 frames.], batch size: 24, lr: 2.24e-03
+2022-04-28 09:26:12,248 INFO [train.py:763] (2/8) Epoch 1, batch 2800, loss[loss=0.3078, simple_loss=0.3708, pruned_loss=0.1225, over 7212.00 frames.], tot_loss[loss=0.2947, simple_loss=0.3519, pruned_loss=0.1188, over 1426702.66 frames.], batch size: 23, lr: 2.23e-03
+2022-04-28 09:27:17,543 INFO [train.py:763] (2/8) Epoch 1, batch 2850, loss[loss=0.3, simple_loss=0.3755, pruned_loss=0.1123, over 7290.00 frames.], tot_loss[loss=0.2931, simple_loss=0.351, pruned_loss=0.1177, over 1425979.71 frames.], batch size: 24, lr: 2.23e-03
+2022-04-28 09:28:22,519 INFO [train.py:763] (2/8) Epoch 1, batch 2900, loss[loss=0.2775, simple_loss=0.3426, pruned_loss=0.1062, over 7218.00 frames.], tot_loss[loss=0.294, simple_loss=0.352, pruned_loss=0.1181, over 1422016.21 frames.], batch size: 20, lr: 2.22e-03
+2022-04-28 09:29:27,934 INFO [train.py:763] (2/8) Epoch 1, batch 2950, loss[loss=0.281, simple_loss=0.3443, pruned_loss=0.1088, over 7241.00 frames.], tot_loss[loss=0.2921, simple_loss=0.3506, pruned_loss=0.1168, over 1422305.56 frames.], batch size: 20, lr: 2.22e-03
+2022-04-28 09:30:33,551 INFO [train.py:763] (2/8) Epoch 1, batch 3000, loss[loss=0.239, simple_loss=0.3003, pruned_loss=0.08887, over 7282.00 frames.], tot_loss[loss=0.2904, simple_loss=0.3497, pruned_loss=0.1157, over 1425584.59 frames.], batch size: 17, lr: 2.21e-03
+2022-04-28 09:30:33,552 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-28 09:30:49,514 INFO [train.py:792] (2/8) Epoch 1, validation: loss=0.217, simple_loss=0.3099, pruned_loss=0.06207, over 698248.00 frames.
+2022-04-28 09:31:55,881 INFO [train.py:763] (2/8) Epoch 1, batch 3050, loss[loss=0.2898, simple_loss=0.3411, pruned_loss=0.1193, over 7279.00 frames.], tot_loss[loss=0.2914, simple_loss=0.3504, pruned_loss=0.1162, over 1421121.78 frames.], batch size: 18, lr: 2.20e-03
+2022-04-28 09:33:01,967 INFO [train.py:763] (2/8) Epoch 1, batch 3100, loss[loss=0.3732, simple_loss=0.3965, pruned_loss=0.175, over 4723.00 frames.], tot_loss[loss=0.2917, simple_loss=0.351, pruned_loss=0.1162, over 1420676.97 frames.], batch size: 53, lr: 2.20e-03
+2022-04-28 09:34:07,382 INFO [train.py:763] (2/8) Epoch 1, batch 3150, loss[loss=0.229, simple_loss=0.2999, pruned_loss=0.07909, over 7280.00 frames.], tot_loss[loss=0.2913, simple_loss=0.3511, pruned_loss=0.1158, over 1423237.44 frames.], batch size: 16, lr: 2.19e-03
+2022-04-28 09:35:13,544 INFO [train.py:763] (2/8) Epoch 1, batch 3200, loss[loss=0.3644, simple_loss=0.3963, pruned_loss=0.1663, over 4993.00 frames.], tot_loss[loss=0.2935, simple_loss=0.3526, pruned_loss=0.1172, over 1412379.83 frames.], batch size: 52, lr: 2.19e-03
+2022-04-28 09:36:19,394 INFO [train.py:763] (2/8) Epoch 1, batch 3250, loss[loss=0.3004, simple_loss=0.3719, pruned_loss=0.1144, over 7198.00 frames.], tot_loss[loss=0.2923, simple_loss=0.3523, pruned_loss=0.1162, over 1415185.67 frames.], batch size: 23, lr: 2.18e-03
+2022-04-28 09:37:26,020 INFO [train.py:763] (2/8) Epoch 1, batch 3300, loss[loss=0.3056, simple_loss=0.3673, pruned_loss=0.1219, over 7210.00 frames.], tot_loss[loss=0.2902, simple_loss=0.3506, pruned_loss=0.1149, over 1420273.54 frames.], batch size: 22, lr: 2.18e-03
+2022-04-28 09:38:31,142 INFO [train.py:763] (2/8) Epoch 1, batch 3350, loss[loss=0.2936, simple_loss=0.3593, pruned_loss=0.114, over 7176.00 frames.], tot_loss[loss=0.2907, simple_loss=0.3518, pruned_loss=0.1148, over 1423183.73 frames.], batch size: 26, lr: 2.18e-03
+2022-04-28 09:39:36,456 INFO [train.py:763] (2/8) Epoch 1, batch 3400, loss[loss=0.2093, simple_loss=0.2788, pruned_loss=0.06991, over 7130.00 frames.], tot_loss[loss=0.2886, simple_loss=0.3501, pruned_loss=0.1135, over 1424027.20 frames.], batch size: 17, lr: 2.17e-03
+2022-04-28 09:40:52,290 INFO [train.py:763] (2/8) Epoch 1, batch 3450, loss[loss=0.2934, simple_loss=0.3676, pruned_loss=0.1096, over 7303.00 frames.], tot_loss[loss=0.2874, simple_loss=0.3494, pruned_loss=0.1127, over 1426211.22 frames.], batch size: 24, lr: 2.17e-03
+2022-04-28 09:41:59,069 INFO [train.py:763] (2/8) Epoch 1, batch 3500, loss[loss=0.3816, simple_loss=0.422, pruned_loss=0.1706, over 6440.00 frames.], tot_loss[loss=0.2872, simple_loss=0.3494, pruned_loss=0.1126, over 1423706.31 frames.], batch size: 37, lr: 2.16e-03
+2022-04-28 09:43:05,800 INFO [train.py:763] (2/8) Epoch 1, batch 3550, loss[loss=0.2966, simple_loss=0.37, pruned_loss=0.1116, over 7298.00 frames.], tot_loss[loss=0.2868, simple_loss=0.3494, pruned_loss=0.1121, over 1423834.32 frames.], batch size: 25, lr: 2.16e-03
+2022-04-28 09:44:12,971 INFO [train.py:763] (2/8) Epoch 1, batch 3600, loss[loss=0.2983, simple_loss=0.357, pruned_loss=0.1198, over 7232.00 frames.], tot_loss[loss=0.2869, simple_loss=0.3496, pruned_loss=0.1121, over 1425196.91 frames.], batch size: 20, lr: 2.15e-03
+2022-04-28 09:45:20,591 INFO [train.py:763] (2/8) Epoch 1, batch 3650, loss[loss=0.2454, simple_loss=0.3084, pruned_loss=0.09119, over 6766.00 frames.], tot_loss[loss=0.2864, simple_loss=0.3492, pruned_loss=0.1118, over 1426740.84 frames.], batch size: 15, lr: 2.15e-03
+2022-04-28 09:46:27,937 INFO [train.py:763] (2/8) Epoch 1, batch 3700, loss[loss=0.2487, simple_loss=0.3244, pruned_loss=0.08647, over 7159.00 frames.], tot_loss[loss=0.2867, simple_loss=0.3501, pruned_loss=0.1117, over 1428894.57 frames.], batch size: 19, lr: 2.14e-03
+2022-04-28 09:47:33,409 INFO [train.py:763] (2/8) Epoch 1, batch 3750, loss[loss=0.2965, simple_loss=0.368, pruned_loss=0.1125, over 7278.00 frames.], tot_loss[loss=0.2863, simple_loss=0.3501, pruned_loss=0.1112, over 1429876.54 frames.], batch size: 24, lr: 2.14e-03
+2022-04-28 09:48:38,884 INFO [train.py:763] (2/8) Epoch 1, batch 3800, loss[loss=0.2436, simple_loss=0.3081, pruned_loss=0.08949, over 6775.00 frames.], tot_loss[loss=0.2848, simple_loss=0.3484, pruned_loss=0.1106, over 1429495.42 frames.], batch size: 15, lr: 2.13e-03
+2022-04-28 09:49:44,144 INFO [train.py:763] (2/8) Epoch 1, batch 3850, loss[loss=0.3107, simple_loss=0.3734, pruned_loss=0.124, over 7138.00 frames.], tot_loss[loss=0.2846, simple_loss=0.3487, pruned_loss=0.1102, over 1430897.46 frames.], batch size: 26, lr: 2.13e-03
+2022-04-28 09:50:49,543 INFO [train.py:763] (2/8) Epoch 1, batch 3900, loss[loss=0.2881, simple_loss=0.3621, pruned_loss=0.107, over 7310.00 frames.], tot_loss[loss=0.2857, simple_loss=0.3495, pruned_loss=0.1109, over 1429355.47 frames.], batch size: 24, lr: 2.12e-03
+2022-04-28 09:51:55,497 INFO [train.py:763] (2/8) Epoch 1, batch 3950, loss[loss=0.2873, simple_loss=0.3588, pruned_loss=0.1079, over 7111.00 frames.], tot_loss[loss=0.2851, simple_loss=0.3489, pruned_loss=0.1107, over 1426537.94 frames.], batch size: 21, lr: 2.12e-03
+2022-04-28 09:53:01,241 INFO [train.py:763] (2/8) Epoch 1, batch 4000, loss[loss=0.3288, simple_loss=0.3857, pruned_loss=0.136, over 7203.00 frames.], tot_loss[loss=0.2836, simple_loss=0.3481, pruned_loss=0.1096, over 1427687.77 frames.], batch size: 22, lr: 2.11e-03
+2022-04-28 09:54:07,048 INFO [train.py:763] (2/8) Epoch 1, batch 4050, loss[loss=0.2933, simple_loss=0.3552, pruned_loss=0.1157, over 6679.00 frames.], tot_loss[loss=0.2836, simple_loss=0.348, pruned_loss=0.1096, over 1425426.47 frames.], batch size: 31, lr: 2.11e-03
+2022-04-28 09:55:12,317 INFO [train.py:763] (2/8) Epoch 1, batch 4100, loss[loss=0.2924, simple_loss=0.3517, pruned_loss=0.1165, over 7214.00 frames.], tot_loss[loss=0.2838, simple_loss=0.3485, pruned_loss=0.1095, over 1420209.56 frames.], batch size: 21, lr: 2.10e-03
+2022-04-28 09:56:17,394 INFO [train.py:763] (2/8) Epoch 1, batch 4150, loss[loss=0.3008, simple_loss=0.3604, pruned_loss=0.1206, over 6743.00 frames.], tot_loss[loss=0.2823, simple_loss=0.3473, pruned_loss=0.1086, over 1419065.85 frames.], batch size: 31, lr: 2.10e-03
+2022-04-28 09:57:22,843 INFO [train.py:763] (2/8) Epoch 1, batch 4200, loss[loss=0.2474, simple_loss=0.3119, pruned_loss=0.09144, over 7281.00 frames.], tot_loss[loss=0.2825, simple_loss=0.3471, pruned_loss=0.1089, over 1417439.49 frames.], batch size: 18, lr: 2.10e-03
+2022-04-28 09:58:27,890 INFO [train.py:763] (2/8) Epoch 1, batch 4250, loss[loss=0.1968, simple_loss=0.2642, pruned_loss=0.06469, over 7274.00 frames.], tot_loss[loss=0.2846, simple_loss=0.3481, pruned_loss=0.1106, over 1413051.76 frames.], batch size: 18, lr: 2.09e-03
+2022-04-28 09:59:34,311 INFO [train.py:763] (2/8) Epoch 1, batch 4300, loss[loss=0.3368, simple_loss=0.3917, pruned_loss=0.1409, over 7317.00 frames.], tot_loss[loss=0.2847, simple_loss=0.348, pruned_loss=0.1107, over 1412360.45 frames.], batch size: 25, lr: 2.09e-03
+2022-04-28 10:00:39,970 INFO [train.py:763] (2/8) Epoch 1, batch 4350, loss[loss=0.2358, simple_loss=0.3034, pruned_loss=0.08409, over 6979.00 frames.], tot_loss[loss=0.2855, simple_loss=0.3487, pruned_loss=0.1112, over 1413126.81 frames.], batch size: 16, lr: 2.08e-03
+2022-04-28 10:01:45,335 INFO [train.py:763] (2/8) Epoch 1, batch 4400, loss[loss=0.2602, simple_loss=0.3351, pruned_loss=0.09269, over 7315.00 frames.], tot_loss[loss=0.2839, simple_loss=0.3475, pruned_loss=0.1101, over 1408013.45 frames.], batch size: 21, lr: 2.08e-03
+2022-04-28 10:02:50,265 INFO [train.py:763] (2/8) Epoch 1, batch 4450, loss[loss=0.3007, simple_loss=0.3508, pruned_loss=0.1253, over 6503.00 frames.], tot_loss[loss=0.285, simple_loss=0.3484, pruned_loss=0.1108, over 1400608.63 frames.], batch size: 38, lr: 2.07e-03
+2022-04-28 10:03:55,334 INFO [train.py:763] (2/8) Epoch 1, batch 4500, loss[loss=0.3174, simple_loss=0.3626, pruned_loss=0.1361, over 6587.00 frames.], tot_loss[loss=0.2855, simple_loss=0.3479, pruned_loss=0.1115, over 1386099.60 frames.], batch size: 38, lr: 2.07e-03
+2022-04-28 10:04:59,433 INFO [train.py:763] (2/8) Epoch 1, batch 4550, loss[loss=0.3231, simple_loss=0.3596, pruned_loss=0.1433, over 4783.00 frames.], tot_loss[loss=0.2896, simple_loss=0.3509, pruned_loss=0.1142, over 1356053.02 frames.], batch size: 52, lr: 2.06e-03
+2022-04-28 10:06:27,053 INFO [train.py:763] (2/8) Epoch 2, batch 0, loss[loss=0.2727, simple_loss=0.3255, pruned_loss=0.11, over 7269.00 frames.], tot_loss[loss=0.2727, simple_loss=0.3255, pruned_loss=0.11, over 7269.00 frames.], batch size: 17, lr: 2.02e-03
+2022-04-28 10:07:33,518 INFO [train.py:763] (2/8) Epoch 2, batch 50, loss[loss=0.2731, simple_loss=0.3411, pruned_loss=0.1025, over 7309.00 frames.], tot_loss[loss=0.281, simple_loss=0.345, pruned_loss=0.1085, over 321418.85 frames.], batch size: 25, lr: 2.02e-03
+2022-04-28 10:08:39,163 INFO [train.py:763] (2/8) Epoch 2, batch 100, loss[loss=0.3019, simple_loss=0.3524, pruned_loss=0.1257, over 6973.00 frames.], tot_loss[loss=0.2732, simple_loss=0.3399, pruned_loss=0.1032, over 568758.43 frames.], batch size: 16, lr: 2.01e-03
+2022-04-28 10:09:45,122 INFO [train.py:763] (2/8) Epoch 2, batch 150, loss[loss=0.3056, simple_loss=0.3544, pruned_loss=0.1284, over 6686.00 frames.], tot_loss[loss=0.2689, simple_loss=0.3362, pruned_loss=0.1008, over 761535.48 frames.], batch size: 31, lr: 2.01e-03
+2022-04-28 10:10:50,697 INFO [train.py:763] (2/8) Epoch 2, batch 200, loss[loss=0.2248, simple_loss=0.2925, pruned_loss=0.07858, over 6774.00 frames.], tot_loss[loss=0.2719, simple_loss=0.3384, pruned_loss=0.1028, over 900395.65 frames.], batch size: 15, lr: 2.00e-03
+2022-04-28 10:11:56,041 INFO [train.py:763] (2/8) Epoch 2, batch 250, loss[loss=0.2648, simple_loss=0.3335, pruned_loss=0.09804, over 7361.00 frames.], tot_loss[loss=0.2732, simple_loss=0.3395, pruned_loss=0.1035, over 1010756.21 frames.], batch size: 19, lr: 2.00e-03
+2022-04-28 10:13:01,576 INFO [train.py:763] (2/8) Epoch 2, batch 300, loss[loss=0.3054, simple_loss=0.3653, pruned_loss=0.1228, over 6752.00 frames.], tot_loss[loss=0.2766, simple_loss=0.3426, pruned_loss=0.1053, over 1100315.56 frames.], batch size: 31, lr: 2.00e-03
+2022-04-28 10:14:07,025 INFO [train.py:763] (2/8) Epoch 2, batch 350, loss[loss=0.2597, simple_loss=0.344, pruned_loss=0.08769, over 7318.00 frames.], tot_loss[loss=0.276, simple_loss=0.3428, pruned_loss=0.1046, over 1171513.78 frames.], batch size: 21, lr: 1.99e-03
+2022-04-28 10:15:12,736 INFO [train.py:763] (2/8) Epoch 2, batch 400, loss[loss=0.2794, simple_loss=0.3442, pruned_loss=0.1072, over 7290.00 frames.], tot_loss[loss=0.2774, simple_loss=0.3439, pruned_loss=0.1054, over 1221677.05 frames.], batch size: 24, lr: 1.99e-03
+2022-04-28 10:16:17,702 INFO [train.py:763] (2/8) Epoch 2, batch 450, loss[loss=0.2914, simple_loss=0.3654, pruned_loss=0.1087, over 7208.00 frames.], tot_loss[loss=0.2783, simple_loss=0.3448, pruned_loss=0.1059, over 1261587.05 frames.], batch size: 22, lr: 1.98e-03
+2022-04-28 10:17:41,016 INFO [train.py:763] (2/8) Epoch 2, batch 500, loss[loss=0.1974, simple_loss=0.2766, pruned_loss=0.05908, over 6992.00 frames.], tot_loss[loss=0.2755, simple_loss=0.3423, pruned_loss=0.1044, over 1299744.30 frames.], batch size: 16, lr: 1.98e-03
+2022-04-28 10:19:24,488 INFO [train.py:763] (2/8) Epoch 2, batch 550, loss[loss=0.3317, simple_loss=0.3897, pruned_loss=0.1369, over 7220.00 frames.], tot_loss[loss=0.2753, simple_loss=0.3425, pruned_loss=0.104, over 1330362.45 frames.], batch size: 21, lr: 1.98e-03
+2022-04-28 10:20:31,147 INFO [train.py:763] (2/8) Epoch 2, batch 600, loss[loss=0.3845, simple_loss=0.4339, pruned_loss=0.1676, over 7246.00 frames.], tot_loss[loss=0.2736, simple_loss=0.3412, pruned_loss=0.103, over 1351415.49 frames.], batch size: 25, lr: 1.97e-03
+2022-04-28 10:21:56,819 INFO [train.py:763] (2/8) Epoch 2, batch 650, loss[loss=0.2285, simple_loss=0.3005, pruned_loss=0.07828, over 7359.00 frames.], tot_loss[loss=0.2747, simple_loss=0.3418, pruned_loss=0.1038, over 1366764.56 frames.], batch size: 19, lr: 1.97e-03
+2022-04-28 10:23:03,990 INFO [train.py:763] (2/8) Epoch 2, batch 700, loss[loss=0.2808, simple_loss=0.3553, pruned_loss=0.1032, over 7209.00 frames.], tot_loss[loss=0.2737, simple_loss=0.3414, pruned_loss=0.103, over 1376830.20 frames.], batch size: 21, lr: 1.96e-03
+2022-04-28 10:24:09,346 INFO [train.py:763] (2/8) Epoch 2, batch 750, loss[loss=0.2763, simple_loss=0.3528, pruned_loss=0.0999, over 7176.00 frames.], tot_loss[loss=0.2739, simple_loss=0.3419, pruned_loss=0.1029, over 1390184.67 frames.], batch size: 23, lr: 1.96e-03
+2022-04-28 10:25:14,621 INFO [train.py:763] (2/8) Epoch 2, batch 800, loss[loss=0.3221, simple_loss=0.3766, pruned_loss=0.1338, over 7202.00 frames.], tot_loss[loss=0.2742, simple_loss=0.342, pruned_loss=0.1032, over 1400890.75 frames.], batch size: 23, lr: 1.96e-03
+2022-04-28 10:26:20,184 INFO [train.py:763] (2/8) Epoch 2, batch 850, loss[loss=0.303, simple_loss=0.3702, pruned_loss=0.1179, over 7296.00 frames.], tot_loss[loss=0.273, simple_loss=0.3411, pruned_loss=0.1025, over 1408922.40 frames.], batch size: 25, lr: 1.95e-03
+2022-04-28 10:27:26,275 INFO [train.py:763] (2/8) Epoch 2, batch 900, loss[loss=0.2453, simple_loss=0.3191, pruned_loss=0.08575, over 7077.00 frames.], tot_loss[loss=0.2759, simple_loss=0.3435, pruned_loss=0.1042, over 1411340.05 frames.], batch size: 18, lr: 1.95e-03
+2022-04-28 10:28:31,599 INFO [train.py:763] (2/8) Epoch 2, batch 950, loss[loss=0.2909, simple_loss=0.3628, pruned_loss=0.1095, over 7144.00 frames.], tot_loss[loss=0.2736, simple_loss=0.3421, pruned_loss=0.1026, over 1416879.97 frames.], batch size: 20, lr: 1.94e-03
+2022-04-28 10:29:36,670 INFO [train.py:763] (2/8) Epoch 2, batch 1000, loss[loss=0.3057, simple_loss=0.364, pruned_loss=0.1237, over 6722.00 frames.], tot_loss[loss=0.2741, simple_loss=0.3429, pruned_loss=0.1027, over 1416470.50 frames.], batch size: 31, lr: 1.94e-03
+2022-04-28 10:30:41,950 INFO [train.py:763] (2/8) Epoch 2, batch 1050, loss[loss=0.2376, simple_loss=0.3099, pruned_loss=0.0826, over 7297.00 frames.], tot_loss[loss=0.2736, simple_loss=0.3424, pruned_loss=0.1024, over 1414604.54 frames.], batch size: 18, lr: 1.94e-03
+2022-04-28 10:31:48,320 INFO [train.py:763] (2/8) Epoch 2, batch 1100, loss[loss=0.2717, simple_loss=0.3447, pruned_loss=0.09938, over 7219.00 frames.], tot_loss[loss=0.2754, simple_loss=0.3441, pruned_loss=0.1033, over 1419891.59 frames.], batch size: 21, lr: 1.93e-03
+2022-04-28 10:32:55,818 INFO [train.py:763] (2/8) Epoch 2, batch 1150, loss[loss=0.2558, simple_loss=0.3349, pruned_loss=0.08839, over 7229.00 frames.], tot_loss[loss=0.2734, simple_loss=0.3419, pruned_loss=0.1025, over 1420633.58 frames.], batch size: 20, lr: 1.93e-03
+2022-04-28 10:34:03,562 INFO [train.py:763] (2/8) Epoch 2, batch 1200, loss[loss=0.2575, simple_loss=0.3262, pruned_loss=0.09442, over 7431.00 frames.], tot_loss[loss=0.2709, simple_loss=0.3399, pruned_loss=0.1009, over 1424778.66 frames.], batch size: 20, lr: 1.93e-03
+2022-04-28 10:35:11,224 INFO [train.py:763] (2/8) Epoch 2, batch 1250, loss[loss=0.2732, simple_loss=0.35, pruned_loss=0.09821, over 7424.00 frames.], tot_loss[loss=0.2694, simple_loss=0.3388, pruned_loss=0.1001, over 1424842.10 frames.], batch size: 21, lr: 1.92e-03
+2022-04-28 10:36:17,275 INFO [train.py:763] (2/8) Epoch 2, batch 1300, loss[loss=0.2713, simple_loss=0.3501, pruned_loss=0.09625, over 7311.00 frames.], tot_loss[loss=0.2682, simple_loss=0.338, pruned_loss=0.0992, over 1426158.96 frames.], batch size: 21, lr: 1.92e-03
+2022-04-28 10:37:22,330 INFO [train.py:763] (2/8) Epoch 2, batch 1350, loss[loss=0.2863, simple_loss=0.3378, pruned_loss=0.1174, over 7430.00 frames.], tot_loss[loss=0.2702, simple_loss=0.3397, pruned_loss=0.1003, over 1426116.00 frames.], batch size: 20, lr: 1.91e-03
+2022-04-28 10:38:27,401 INFO [train.py:763] (2/8) Epoch 2, batch 1400, loss[loss=0.2669, simple_loss=0.329, pruned_loss=0.1024, over 7158.00 frames.], tot_loss[loss=0.2715, simple_loss=0.3408, pruned_loss=0.1011, over 1422489.12 frames.], batch size: 19, lr: 1.91e-03
+2022-04-28 10:39:32,820 INFO [train.py:763] (2/8) Epoch 2, batch 1450, loss[loss=0.2941, simple_loss=0.3452, pruned_loss=0.1215, over 7130.00 frames.], tot_loss[loss=0.2716, simple_loss=0.3408, pruned_loss=0.1012, over 1419985.32 frames.], batch size: 17, lr: 1.91e-03
+2022-04-28 10:40:38,388 INFO [train.py:763] (2/8) Epoch 2, batch 1500, loss[loss=0.3124, simple_loss=0.3792, pruned_loss=0.1228, over 7311.00 frames.], tot_loss[loss=0.2727, simple_loss=0.3415, pruned_loss=0.1019, over 1418474.66 frames.], batch size: 21, lr: 1.90e-03
+2022-04-28 10:41:43,972 INFO [train.py:763] (2/8) Epoch 2, batch 1550, loss[loss=0.2544, simple_loss=0.3399, pruned_loss=0.08449, over 7170.00 frames.], tot_loss[loss=0.271, simple_loss=0.3405, pruned_loss=0.1008, over 1422685.87 frames.], batch size: 19, lr: 1.90e-03
+2022-04-28 10:42:49,541 INFO [train.py:763] (2/8) Epoch 2, batch 1600, loss[loss=0.2478, simple_loss=0.3254, pruned_loss=0.08512, over 7160.00 frames.], tot_loss[loss=0.269, simple_loss=0.3394, pruned_loss=0.09928, over 1424331.27 frames.], batch size: 19, lr: 1.90e-03
+2022-04-28 10:43:56,342 INFO [train.py:763] (2/8) Epoch 2, batch 1650, loss[loss=0.2596, simple_loss=0.3365, pruned_loss=0.09136, over 7436.00 frames.], tot_loss[loss=0.2691, simple_loss=0.3394, pruned_loss=0.09942, over 1426682.49 frames.], batch size: 20, lr: 1.89e-03
+2022-04-28 10:45:02,820 INFO [train.py:763] (2/8) Epoch 2, batch 1700, loss[loss=0.2342, simple_loss=0.3209, pruned_loss=0.07374, over 7140.00 frames.], tot_loss[loss=0.2705, simple_loss=0.3403, pruned_loss=0.1004, over 1417354.34 frames.], batch size: 20, lr: 1.89e-03
+2022-04-28 10:46:08,588 INFO [train.py:763] (2/8) Epoch 2, batch 1750, loss[loss=0.2668, simple_loss=0.3366, pruned_loss=0.09854, over 7241.00 frames.], tot_loss[loss=0.2698, simple_loss=0.34, pruned_loss=0.09982, over 1424418.29 frames.], batch size: 20, lr: 1.88e-03
+2022-04-28 10:47:13,946 INFO [train.py:763] (2/8) Epoch 2, batch 1800, loss[loss=0.2692, simple_loss=0.3498, pruned_loss=0.09432, over 7123.00 frames.], tot_loss[loss=0.27, simple_loss=0.34, pruned_loss=0.1, over 1416700.46 frames.], batch size: 21, lr: 1.88e-03
+2022-04-28 10:48:20,966 INFO [train.py:763] (2/8) Epoch 2, batch 1850, loss[loss=0.268, simple_loss=0.3442, pruned_loss=0.09595, over 7404.00 frames.], tot_loss[loss=0.2684, simple_loss=0.3382, pruned_loss=0.09929, over 1418974.27 frames.], batch size: 21, lr: 1.88e-03
+2022-04-28 10:49:26,577 INFO [train.py:763] (2/8) Epoch 2, batch 1900, loss[loss=0.2665, simple_loss=0.3413, pruned_loss=0.09583, over 7166.00 frames.], tot_loss[loss=0.268, simple_loss=0.3379, pruned_loss=0.09904, over 1416268.53 frames.], batch size: 18, lr: 1.87e-03
+2022-04-28 10:50:31,920 INFO [train.py:763] (2/8) Epoch 2, batch 1950, loss[loss=0.3401, simple_loss=0.3885, pruned_loss=0.1459, over 6842.00 frames.], tot_loss[loss=0.2679, simple_loss=0.3375, pruned_loss=0.09913, over 1417600.74 frames.], batch size: 31, lr: 1.87e-03
+2022-04-28 10:51:37,332 INFO [train.py:763] (2/8) Epoch 2, batch 2000, loss[loss=0.2374, simple_loss=0.3189, pruned_loss=0.07793, over 7163.00 frames.], tot_loss[loss=0.2666, simple_loss=0.3364, pruned_loss=0.09839, over 1421225.30 frames.], batch size: 19, lr: 1.87e-03
+2022-04-28 10:52:43,638 INFO [train.py:763] (2/8) Epoch 2, batch 2050, loss[loss=0.367, simple_loss=0.397, pruned_loss=0.1685, over 5280.00 frames.], tot_loss[loss=0.2701, simple_loss=0.3393, pruned_loss=0.1004, over 1421070.59 frames.], batch size: 52, lr: 1.86e-03
+2022-04-28 10:53:49,749 INFO [train.py:763] (2/8) Epoch 2, batch 2100, loss[loss=0.2774, simple_loss=0.3622, pruned_loss=0.09626, over 7310.00 frames.], tot_loss[loss=0.27, simple_loss=0.3399, pruned_loss=0.1, over 1424333.59 frames.], batch size: 21, lr: 1.86e-03
+2022-04-28 10:54:55,189 INFO [train.py:763] (2/8) Epoch 2, batch 2150, loss[loss=0.2911, simple_loss=0.3636, pruned_loss=0.1093, over 7224.00 frames.], tot_loss[loss=0.268, simple_loss=0.3386, pruned_loss=0.09869, over 1425986.59 frames.], batch size: 20, lr: 1.86e-03
+2022-04-28 10:56:00,714 INFO [train.py:763] (2/8) Epoch 2, batch 2200, loss[loss=0.2454, simple_loss=0.3421, pruned_loss=0.0744, over 7142.00 frames.], tot_loss[loss=0.2672, simple_loss=0.3379, pruned_loss=0.09821, over 1424397.30 frames.], batch size: 20, lr: 1.85e-03
+2022-04-28 10:57:05,941 INFO [train.py:763] (2/8) Epoch 2, batch 2250, loss[loss=0.2599, simple_loss=0.3383, pruned_loss=0.09072, over 7317.00 frames.], tot_loss[loss=0.2674, simple_loss=0.3384, pruned_loss=0.09823, over 1424544.21 frames.], batch size: 20, lr: 1.85e-03
+2022-04-28 10:58:11,383 INFO [train.py:763] (2/8) Epoch 2, batch 2300, loss[loss=0.2241, simple_loss=0.3114, pruned_loss=0.06837, over 7363.00 frames.], tot_loss[loss=0.2685, simple_loss=0.3387, pruned_loss=0.09918, over 1413418.66 frames.], batch size: 19, lr: 1.85e-03
+2022-04-28 10:59:16,565 INFO [train.py:763] (2/8) Epoch 2, batch 2350, loss[loss=0.2214, simple_loss=0.2956, pruned_loss=0.07362, over 7253.00 frames.], tot_loss[loss=0.2673, simple_loss=0.3377, pruned_loss=0.09843, over 1414575.39 frames.], batch size: 19, lr: 1.84e-03
+2022-04-28 11:00:21,739 INFO [train.py:763] (2/8) Epoch 2, batch 2400, loss[loss=0.2687, simple_loss=0.3406, pruned_loss=0.09838, over 7254.00 frames.], tot_loss[loss=0.2681, simple_loss=0.3386, pruned_loss=0.09885, over 1417641.96 frames.], batch size: 19, lr: 1.84e-03
+2022-04-28 11:01:26,802 INFO [train.py:763] (2/8) Epoch 2, batch 2450, loss[loss=0.2834, simple_loss=0.3441, pruned_loss=0.1113, over 7250.00 frames.], tot_loss[loss=0.2668, simple_loss=0.3378, pruned_loss=0.09792, over 1415552.17 frames.], batch size: 20, lr: 1.84e-03
+2022-04-28 11:02:32,495 INFO [train.py:763] (2/8) Epoch 2, batch 2500, loss[loss=0.2668, simple_loss=0.3318, pruned_loss=0.1009, over 7158.00 frames.], tot_loss[loss=0.2663, simple_loss=0.3372, pruned_loss=0.09768, over 1414903.24 frames.], batch size: 19, lr: 1.83e-03
+2022-04-28 11:03:38,312 INFO [train.py:763] (2/8) Epoch 2, batch 2550, loss[loss=0.285, simple_loss=0.3545, pruned_loss=0.1077, over 7223.00 frames.], tot_loss[loss=0.2659, simple_loss=0.3365, pruned_loss=0.09764, over 1414267.38 frames.], batch size: 21, lr: 1.83e-03
+2022-04-28 11:04:44,220 INFO [train.py:763] (2/8) Epoch 2, batch 2600, loss[loss=0.2743, simple_loss=0.3441, pruned_loss=0.1023, over 7280.00 frames.], tot_loss[loss=0.264, simple_loss=0.3354, pruned_loss=0.09633, over 1420635.02 frames.], batch size: 18, lr: 1.83e-03
+2022-04-28 11:05:50,132 INFO [train.py:763] (2/8) Epoch 2, batch 2650, loss[loss=0.2759, simple_loss=0.3438, pruned_loss=0.104, over 7323.00 frames.], tot_loss[loss=0.263, simple_loss=0.3346, pruned_loss=0.09566, over 1420076.52 frames.], batch size: 20, lr: 1.82e-03
+2022-04-28 11:06:55,491 INFO [train.py:763] (2/8) Epoch 2, batch 2700, loss[loss=0.2064, simple_loss=0.2822, pruned_loss=0.06528, over 7452.00 frames.], tot_loss[loss=0.2639, simple_loss=0.3352, pruned_loss=0.09625, over 1422016.56 frames.], batch size: 19, lr: 1.82e-03
+2022-04-28 11:08:01,948 INFO [train.py:763] (2/8) Epoch 2, batch 2750, loss[loss=0.3345, simple_loss=0.4035, pruned_loss=0.1328, over 7148.00 frames.], tot_loss[loss=0.2634, simple_loss=0.3351, pruned_loss=0.09591, over 1420966.26 frames.], batch size: 26, lr: 1.82e-03
+2022-04-28 11:09:07,549 INFO [train.py:763] (2/8) Epoch 2, batch 2800, loss[loss=0.3441, simple_loss=0.3796, pruned_loss=0.1543, over 4915.00 frames.], tot_loss[loss=0.2628, simple_loss=0.335, pruned_loss=0.09537, over 1419837.86 frames.], batch size: 55, lr: 1.81e-03
+2022-04-28 11:10:13,389 INFO [train.py:763] (2/8) Epoch 2, batch 2850, loss[loss=0.2713, simple_loss=0.3434, pruned_loss=0.09965, over 7220.00 frames.], tot_loss[loss=0.2635, simple_loss=0.3353, pruned_loss=0.09581, over 1422532.08 frames.], batch size: 21, lr: 1.81e-03
+2022-04-28 11:11:19,189 INFO [train.py:763] (2/8) Epoch 2, batch 2900, loss[loss=0.2716, simple_loss=0.3425, pruned_loss=0.1003, over 6461.00 frames.], tot_loss[loss=0.2628, simple_loss=0.3348, pruned_loss=0.09538, over 1418013.42 frames.], batch size: 38, lr: 1.81e-03
+2022-04-28 11:12:24,868 INFO [train.py:763] (2/8) Epoch 2, batch 2950, loss[loss=0.282, simple_loss=0.349, pruned_loss=0.1075, over 7240.00 frames.], tot_loss[loss=0.2646, simple_loss=0.336, pruned_loss=0.0966, over 1417085.01 frames.], batch size: 26, lr: 1.80e-03
+2022-04-28 11:13:30,376 INFO [train.py:763] (2/8) Epoch 2, batch 3000, loss[loss=0.2595, simple_loss=0.3328, pruned_loss=0.09313, over 7340.00 frames.], tot_loss[loss=0.2632, simple_loss=0.3352, pruned_loss=0.09559, over 1420342.18 frames.], batch size: 22, lr: 1.80e-03
+2022-04-28 11:13:30,377 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-28 11:13:45,774 INFO [train.py:792] (2/8) Epoch 2, validation: loss=0.2017, simple_loss=0.3052, pruned_loss=0.04915, over 698248.00 frames.
+2022-04-28 11:14:51,523 INFO [train.py:763] (2/8) Epoch 2, batch 3050, loss[loss=0.2636, simple_loss=0.3326, pruned_loss=0.09724, over 7416.00 frames.], tot_loss[loss=0.2624, simple_loss=0.3348, pruned_loss=0.095, over 1425330.03 frames.], batch size: 21, lr: 1.80e-03
+2022-04-28 11:15:57,113 INFO [train.py:763] (2/8) Epoch 2, batch 3100, loss[loss=0.2449, simple_loss=0.3033, pruned_loss=0.09331, over 7288.00 frames.], tot_loss[loss=0.2617, simple_loss=0.3342, pruned_loss=0.09463, over 1427933.27 frames.], batch size: 18, lr: 1.79e-03
+2022-04-28 11:17:02,753 INFO [train.py:763] (2/8) Epoch 2, batch 3150, loss[loss=0.242, simple_loss=0.3262, pruned_loss=0.07894, over 7215.00 frames.], tot_loss[loss=0.2618, simple_loss=0.3338, pruned_loss=0.09491, over 1422476.31 frames.], batch size: 21, lr: 1.79e-03
+2022-04-28 11:18:08,968 INFO [train.py:763] (2/8) Epoch 2, batch 3200, loss[loss=0.2517, simple_loss=0.3283, pruned_loss=0.08757, over 7368.00 frames.], tot_loss[loss=0.263, simple_loss=0.3351, pruned_loss=0.09544, over 1425928.68 frames.], batch size: 23, lr: 1.79e-03
+2022-04-28 11:19:14,934 INFO [train.py:763] (2/8) Epoch 2, batch 3250, loss[loss=0.284, simple_loss=0.3529, pruned_loss=0.1075, over 7159.00 frames.], tot_loss[loss=0.2646, simple_loss=0.3369, pruned_loss=0.09613, over 1426729.61 frames.], batch size: 19, lr: 1.79e-03
+2022-04-28 11:20:20,951 INFO [train.py:763] (2/8) Epoch 2, batch 3300, loss[loss=0.2788, simple_loss=0.3471, pruned_loss=0.1053, over 7142.00 frames.], tot_loss[loss=0.262, simple_loss=0.3348, pruned_loss=0.09459, over 1429061.07 frames.], batch size: 26, lr: 1.78e-03
+2022-04-28 11:21:25,808 INFO [train.py:763] (2/8) Epoch 2, batch 3350, loss[loss=0.2555, simple_loss=0.3195, pruned_loss=0.09577, over 7283.00 frames.], tot_loss[loss=0.2639, simple_loss=0.3361, pruned_loss=0.09585, over 1425820.67 frames.], batch size: 18, lr: 1.78e-03
+2022-04-28 11:22:30,850 INFO [train.py:763] (2/8) Epoch 2, batch 3400, loss[loss=0.2769, simple_loss=0.3323, pruned_loss=0.1107, over 7416.00 frames.], tot_loss[loss=0.2644, simple_loss=0.3368, pruned_loss=0.09601, over 1423829.14 frames.], batch size: 18, lr: 1.78e-03
+2022-04-28 11:23:36,216 INFO [train.py:763] (2/8) Epoch 2, batch 3450, loss[loss=0.2483, simple_loss=0.3297, pruned_loss=0.08342, over 7258.00 frames.], tot_loss[loss=0.2637, simple_loss=0.3357, pruned_loss=0.0958, over 1420166.41 frames.], batch size: 19, lr: 1.77e-03
+2022-04-28 11:24:41,578 INFO [train.py:763] (2/8) Epoch 2, batch 3500, loss[loss=0.2716, simple_loss=0.3529, pruned_loss=0.09519, over 7289.00 frames.], tot_loss[loss=0.2618, simple_loss=0.3343, pruned_loss=0.09465, over 1420568.64 frames.], batch size: 25, lr: 1.77e-03
+2022-04-28 11:25:47,024 INFO [train.py:763] (2/8) Epoch 2, batch 3550, loss[loss=0.3014, simple_loss=0.3667, pruned_loss=0.1181, over 7213.00 frames.], tot_loss[loss=0.2631, simple_loss=0.3352, pruned_loss=0.09547, over 1419409.72 frames.], batch size: 21, lr: 1.77e-03
+2022-04-28 11:26:52,369 INFO [train.py:763] (2/8) Epoch 2, batch 3600, loss[loss=0.2565, simple_loss=0.3416, pruned_loss=0.08573, over 7282.00 frames.], tot_loss[loss=0.2614, simple_loss=0.3337, pruned_loss=0.09457, over 1421137.48 frames.], batch size: 24, lr: 1.76e-03
+2022-04-28 11:27:57,952 INFO [train.py:763] (2/8) Epoch 2, batch 3650, loss[loss=0.3063, simple_loss=0.376, pruned_loss=0.1183, over 7366.00 frames.], tot_loss[loss=0.2611, simple_loss=0.3334, pruned_loss=0.09443, over 1420898.13 frames.], batch size: 23, lr: 1.76e-03
+2022-04-28 11:29:03,178 INFO [train.py:763] (2/8) Epoch 2, batch 3700, loss[loss=0.232, simple_loss=0.307, pruned_loss=0.07851, over 7408.00 frames.], tot_loss[loss=0.2615, simple_loss=0.3341, pruned_loss=0.09443, over 1416553.06 frames.], batch size: 18, lr: 1.76e-03
+2022-04-28 11:30:08,698 INFO [train.py:763] (2/8) Epoch 2, batch 3750, loss[loss=0.2183, simple_loss=0.3017, pruned_loss=0.06749, over 7283.00 frames.], tot_loss[loss=0.2602, simple_loss=0.3336, pruned_loss=0.09338, over 1422875.43 frames.], batch size: 18, lr: 1.76e-03
+2022-04-28 11:31:14,663 INFO [train.py:763] (2/8) Epoch 2, batch 3800, loss[loss=0.2561, simple_loss=0.3324, pruned_loss=0.08988, over 7156.00 frames.], tot_loss[loss=0.2595, simple_loss=0.3327, pruned_loss=0.0931, over 1423110.45 frames.], batch size: 18, lr: 1.75e-03
+2022-04-28 11:32:20,646 INFO [train.py:763] (2/8) Epoch 2, batch 3850, loss[loss=0.2462, simple_loss=0.326, pruned_loss=0.08321, over 7340.00 frames.], tot_loss[loss=0.2612, simple_loss=0.3336, pruned_loss=0.09437, over 1422676.99 frames.], batch size: 22, lr: 1.75e-03
+2022-04-28 11:33:26,575 INFO [train.py:763] (2/8) Epoch 2, batch 3900, loss[loss=0.2947, simple_loss=0.36, pruned_loss=0.1148, over 7325.00 frames.], tot_loss[loss=0.2598, simple_loss=0.3329, pruned_loss=0.09334, over 1424703.44 frames.], batch size: 20, lr: 1.75e-03
+2022-04-28 11:34:31,993 INFO [train.py:763] (2/8) Epoch 2, batch 3950, loss[loss=0.2755, simple_loss=0.3488, pruned_loss=0.1011, over 7335.00 frames.], tot_loss[loss=0.2604, simple_loss=0.3332, pruned_loss=0.09385, over 1421375.22 frames.], batch size: 21, lr: 1.74e-03
+2022-04-28 11:35:37,599 INFO [train.py:763] (2/8) Epoch 2, batch 4000, loss[loss=0.2727, simple_loss=0.3504, pruned_loss=0.09755, over 7328.00 frames.], tot_loss[loss=0.2597, simple_loss=0.3328, pruned_loss=0.0933, over 1425817.47 frames.], batch size: 22, lr: 1.74e-03
+2022-04-28 11:36:44,082 INFO [train.py:763] (2/8) Epoch 2, batch 4050, loss[loss=0.256, simple_loss=0.3341, pruned_loss=0.08892, over 7441.00 frames.], tot_loss[loss=0.259, simple_loss=0.3322, pruned_loss=0.09288, over 1426505.65 frames.], batch size: 20, lr: 1.74e-03
+2022-04-28 11:37:49,241 INFO [train.py:763] (2/8) Epoch 2, batch 4100, loss[loss=0.2855, simple_loss=0.351, pruned_loss=0.11, over 7065.00 frames.], tot_loss[loss=0.2599, simple_loss=0.333, pruned_loss=0.0934, over 1417027.05 frames.], batch size: 18, lr: 1.73e-03
+2022-04-28 11:38:54,188 INFO [train.py:763] (2/8) Epoch 2, batch 4150, loss[loss=0.2445, simple_loss=0.3399, pruned_loss=0.07453, over 7121.00 frames.], tot_loss[loss=0.2601, simple_loss=0.3337, pruned_loss=0.09325, over 1421842.19 frames.], batch size: 21, lr: 1.73e-03
+2022-04-28 11:40:00,863 INFO [train.py:763] (2/8) Epoch 2, batch 4200, loss[loss=0.2691, simple_loss=0.3378, pruned_loss=0.1002, over 7110.00 frames.], tot_loss[loss=0.2609, simple_loss=0.3342, pruned_loss=0.0938, over 1420998.30 frames.], batch size: 28, lr: 1.73e-03
+2022-04-28 11:41:07,989 INFO [train.py:763] (2/8) Epoch 2, batch 4250, loss[loss=0.27, simple_loss=0.3469, pruned_loss=0.09656, over 7217.00 frames.], tot_loss[loss=0.2592, simple_loss=0.3326, pruned_loss=0.09287, over 1422111.69 frames.], batch size: 22, lr: 1.73e-03
+2022-04-28 11:42:14,752 INFO [train.py:763] (2/8) Epoch 2, batch 4300, loss[loss=0.2515, simple_loss=0.3286, pruned_loss=0.08714, over 7067.00 frames.], tot_loss[loss=0.2612, simple_loss=0.334, pruned_loss=0.09426, over 1423903.48 frames.], batch size: 18, lr: 1.72e-03
+2022-04-28 11:43:21,899 INFO [train.py:763] (2/8) Epoch 2, batch 4350, loss[loss=0.2322, simple_loss=0.3282, pruned_loss=0.06817, over 7140.00 frames.], tot_loss[loss=0.2605, simple_loss=0.3334, pruned_loss=0.09384, over 1424842.01 frames.], batch size: 20, lr: 1.72e-03
+2022-04-28 11:44:27,743 INFO [train.py:763] (2/8) Epoch 2, batch 4400, loss[loss=0.2937, simple_loss=0.3674, pruned_loss=0.11, over 7284.00 frames.], tot_loss[loss=0.2606, simple_loss=0.3329, pruned_loss=0.09416, over 1419551.29 frames.], batch size: 25, lr: 1.72e-03
+2022-04-28 11:45:33,248 INFO [train.py:763] (2/8) Epoch 2, batch 4450, loss[loss=0.2648, simple_loss=0.3501, pruned_loss=0.08972, over 7333.00 frames.], tot_loss[loss=0.2604, simple_loss=0.3334, pruned_loss=0.09369, over 1411983.93 frames.], batch size: 22, lr: 1.71e-03
+2022-04-28 11:46:38,402 INFO [train.py:763] (2/8) Epoch 2, batch 4500, loss[loss=0.2931, simple_loss=0.3599, pruned_loss=0.1131, over 7113.00 frames.], tot_loss[loss=0.2608, simple_loss=0.3343, pruned_loss=0.09361, over 1406359.10 frames.], batch size: 21, lr: 1.71e-03
+2022-04-28 11:47:42,631 INFO [train.py:763] (2/8) Epoch 2, batch 4550, loss[loss=0.3394, simple_loss=0.3926, pruned_loss=0.1431, over 6241.00 frames.], tot_loss[loss=0.2646, simple_loss=0.3372, pruned_loss=0.09601, over 1378441.33 frames.], batch size: 37, lr: 1.71e-03
+2022-04-28 11:49:10,863 INFO [train.py:763] (2/8) Epoch 3, batch 0, loss[loss=0.2385, simple_loss=0.3306, pruned_loss=0.07317, over 7196.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3306, pruned_loss=0.07317, over 7196.00 frames.], batch size: 23, lr: 1.66e-03
+2022-04-28 11:50:17,403 INFO [train.py:763] (2/8) Epoch 3, batch 50, loss[loss=0.2278, simple_loss=0.3102, pruned_loss=0.07274, over 7276.00 frames.], tot_loss[loss=0.2485, simple_loss=0.3239, pruned_loss=0.08651, over 317912.16 frames.], batch size: 17, lr: 1.66e-03
+2022-04-28 11:51:23,920 INFO [train.py:763] (2/8) Epoch 3, batch 100, loss[loss=0.2305, simple_loss=0.294, pruned_loss=0.08349, over 7284.00 frames.], tot_loss[loss=0.2471, simple_loss=0.3221, pruned_loss=0.086, over 564468.20 frames.], batch size: 17, lr: 1.65e-03
+2022-04-28 11:52:29,494 INFO [train.py:763] (2/8) Epoch 3, batch 150, loss[loss=0.2328, simple_loss=0.3199, pruned_loss=0.07284, over 7344.00 frames.], tot_loss[loss=0.2488, simple_loss=0.3243, pruned_loss=0.08663, over 754980.53 frames.], batch size: 22, lr: 1.65e-03
+2022-04-28 11:53:34,973 INFO [train.py:763] (2/8) Epoch 3, batch 200, loss[loss=0.298, simple_loss=0.3687, pruned_loss=0.1136, over 7187.00 frames.], tot_loss[loss=0.2522, simple_loss=0.3273, pruned_loss=0.08858, over 904086.73 frames.], batch size: 23, lr: 1.65e-03
+2022-04-28 11:54:40,981 INFO [train.py:763] (2/8) Epoch 3, batch 250, loss[loss=0.2982, simple_loss=0.3712, pruned_loss=0.1126, over 7320.00 frames.], tot_loss[loss=0.2552, simple_loss=0.3303, pruned_loss=0.09001, over 1016736.27 frames.], batch size: 22, lr: 1.64e-03
+2022-04-28 11:55:46,611 INFO [train.py:763] (2/8) Epoch 3, batch 300, loss[loss=0.2721, simple_loss=0.3536, pruned_loss=0.09529, over 7378.00 frames.], tot_loss[loss=0.2522, simple_loss=0.328, pruned_loss=0.08825, over 1111219.70 frames.], batch size: 23, lr: 1.64e-03
+2022-04-28 11:56:52,027 INFO [train.py:763] (2/8) Epoch 3, batch 350, loss[loss=0.2444, simple_loss=0.3332, pruned_loss=0.07779, over 7320.00 frames.], tot_loss[loss=0.2522, simple_loss=0.3282, pruned_loss=0.08809, over 1183253.42 frames.], batch size: 21, lr: 1.64e-03
+2022-04-28 11:57:57,843 INFO [train.py:763] (2/8) Epoch 3, batch 400, loss[loss=0.2276, simple_loss=0.3115, pruned_loss=0.07181, over 7232.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3274, pruned_loss=0.08823, over 1232299.00 frames.], batch size: 20, lr: 1.64e-03
+2022-04-28 11:59:03,270 INFO [train.py:763] (2/8) Epoch 3, batch 450, loss[loss=0.2418, simple_loss=0.3282, pruned_loss=0.07767, over 7144.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3262, pruned_loss=0.08708, over 1273859.35 frames.], batch size: 20, lr: 1.63e-03
+2022-04-28 12:00:09,020 INFO [train.py:763] (2/8) Epoch 3, batch 500, loss[loss=0.2117, simple_loss=0.2989, pruned_loss=0.06222, over 7159.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3283, pruned_loss=0.08831, over 1302856.90 frames.], batch size: 19, lr: 1.63e-03
+2022-04-28 12:01:14,925 INFO [train.py:763] (2/8) Epoch 3, batch 550, loss[loss=0.2318, simple_loss=0.3157, pruned_loss=0.074, over 7174.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3283, pruned_loss=0.08833, over 1329055.80 frames.], batch size: 18, lr: 1.63e-03
+2022-04-28 12:02:20,842 INFO [train.py:763] (2/8) Epoch 3, batch 600, loss[loss=0.2671, simple_loss=0.3506, pruned_loss=0.09178, over 6383.00 frames.], tot_loss[loss=0.2515, simple_loss=0.3273, pruned_loss=0.08787, over 1347049.38 frames.], batch size: 37, lr: 1.63e-03
+2022-04-28 12:03:27,783 INFO [train.py:763] (2/8) Epoch 3, batch 650, loss[loss=0.2768, simple_loss=0.34, pruned_loss=0.1068, over 7429.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3274, pruned_loss=0.0881, over 1367502.35 frames.], batch size: 20, lr: 1.62e-03
+2022-04-28 12:04:35,115 INFO [train.py:763] (2/8) Epoch 3, batch 700, loss[loss=0.2776, simple_loss=0.3465, pruned_loss=0.1044, over 7249.00 frames.], tot_loss[loss=0.2501, simple_loss=0.3261, pruned_loss=0.08706, over 1385223.66 frames.], batch size: 24, lr: 1.62e-03
+2022-04-28 12:05:41,308 INFO [train.py:763] (2/8) Epoch 3, batch 750, loss[loss=0.2774, simple_loss=0.3475, pruned_loss=0.1037, over 7311.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3258, pruned_loss=0.08732, over 1393056.17 frames.], batch size: 24, lr: 1.62e-03
+2022-04-28 12:06:46,990 INFO [train.py:763] (2/8) Epoch 3, batch 800, loss[loss=0.2393, simple_loss=0.3141, pruned_loss=0.08223, over 7253.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3262, pruned_loss=0.08725, over 1397080.37 frames.], batch size: 19, lr: 1.62e-03
+2022-04-28 12:07:53,462 INFO [train.py:763] (2/8) Epoch 3, batch 850, loss[loss=0.1817, simple_loss=0.2801, pruned_loss=0.04166, over 7066.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3263, pruned_loss=0.08707, over 1407542.85 frames.], batch size: 18, lr: 1.61e-03
+2022-04-28 12:09:00,225 INFO [train.py:763] (2/8) Epoch 3, batch 900, loss[loss=0.3074, simple_loss=0.3755, pruned_loss=0.1197, over 7107.00 frames.], tot_loss[loss=0.2492, simple_loss=0.3255, pruned_loss=0.08647, over 1414744.99 frames.], batch size: 21, lr: 1.61e-03
+2022-04-28 12:10:06,503 INFO [train.py:763] (2/8) Epoch 3, batch 950, loss[loss=0.2438, simple_loss=0.3403, pruned_loss=0.07368, over 7196.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3266, pruned_loss=0.08688, over 1419890.49 frames.], batch size: 26, lr: 1.61e-03
+2022-04-28 12:11:12,746 INFO [train.py:763] (2/8) Epoch 3, batch 1000, loss[loss=0.2646, simple_loss=0.322, pruned_loss=0.1036, over 7293.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3264, pruned_loss=0.08718, over 1419739.01 frames.], batch size: 18, lr: 1.61e-03
+2022-04-28 12:12:18,771 INFO [train.py:763] (2/8) Epoch 3, batch 1050, loss[loss=0.289, simple_loss=0.358, pruned_loss=0.11, over 6841.00 frames.], tot_loss[loss=0.2516, simple_loss=0.3275, pruned_loss=0.08784, over 1419066.24 frames.], batch size: 31, lr: 1.60e-03
+2022-04-28 12:13:24,397 INFO [train.py:763] (2/8) Epoch 3, batch 1100, loss[loss=0.2385, simple_loss=0.3321, pruned_loss=0.07241, over 7415.00 frames.], tot_loss[loss=0.2511, simple_loss=0.3273, pruned_loss=0.08744, over 1420305.23 frames.], batch size: 21, lr: 1.60e-03
+2022-04-28 12:14:28,836 INFO [train.py:763] (2/8) Epoch 3, batch 1150, loss[loss=0.3296, simple_loss=0.3872, pruned_loss=0.136, over 7322.00 frames.], tot_loss[loss=0.2524, simple_loss=0.3287, pruned_loss=0.08804, over 1417849.47 frames.], batch size: 21, lr: 1.60e-03
+2022-04-28 12:15:35,085 INFO [train.py:763] (2/8) Epoch 3, batch 1200, loss[loss=0.2522, simple_loss=0.3305, pruned_loss=0.08693, over 7313.00 frames.], tot_loss[loss=0.2523, simple_loss=0.329, pruned_loss=0.08777, over 1415560.00 frames.], batch size: 21, lr: 1.60e-03
+2022-04-28 12:16:40,629 INFO [train.py:763] (2/8) Epoch 3, batch 1250, loss[loss=0.2203, simple_loss=0.2832, pruned_loss=0.07864, over 7212.00 frames.], tot_loss[loss=0.252, simple_loss=0.3288, pruned_loss=0.08763, over 1413789.01 frames.], batch size: 16, lr: 1.59e-03
+2022-04-28 12:17:46,144 INFO [train.py:763] (2/8) Epoch 3, batch 1300, loss[loss=0.2418, simple_loss=0.3356, pruned_loss=0.07396, over 7195.00 frames.], tot_loss[loss=0.2509, simple_loss=0.3277, pruned_loss=0.08705, over 1417332.05 frames.], batch size: 23, lr: 1.59e-03
+2022-04-28 12:18:51,889 INFO [train.py:763] (2/8) Epoch 3, batch 1350, loss[loss=0.2318, simple_loss=0.3124, pruned_loss=0.07563, over 7241.00 frames.], tot_loss[loss=0.2516, simple_loss=0.3282, pruned_loss=0.0875, over 1416906.18 frames.], batch size: 20, lr: 1.59e-03
+2022-04-28 12:19:57,900 INFO [train.py:763] (2/8) Epoch 3, batch 1400, loss[loss=0.2714, simple_loss=0.3548, pruned_loss=0.09405, over 7197.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3283, pruned_loss=0.08771, over 1419843.80 frames.], batch size: 22, lr: 1.59e-03
+2022-04-28 12:21:03,055 INFO [train.py:763] (2/8) Epoch 3, batch 1450, loss[loss=0.2702, simple_loss=0.3461, pruned_loss=0.09717, over 7310.00 frames.], tot_loss[loss=0.2513, simple_loss=0.3282, pruned_loss=0.08721, over 1421875.83 frames.], batch size: 24, lr: 1.59e-03
+2022-04-28 12:22:08,501 INFO [train.py:763] (2/8) Epoch 3, batch 1500, loss[loss=0.2881, simple_loss=0.3494, pruned_loss=0.1134, over 7312.00 frames.], tot_loss[loss=0.2501, simple_loss=0.3272, pruned_loss=0.0865, over 1419239.51 frames.], batch size: 24, lr: 1.58e-03
+2022-04-28 12:23:13,997 INFO [train.py:763] (2/8) Epoch 3, batch 1550, loss[loss=0.308, simple_loss=0.3644, pruned_loss=0.1258, over 5167.00 frames.], tot_loss[loss=0.2503, simple_loss=0.3274, pruned_loss=0.08663, over 1417507.00 frames.], batch size: 52, lr: 1.58e-03
+2022-04-28 12:24:20,147 INFO [train.py:763] (2/8) Epoch 3, batch 1600, loss[loss=0.2362, simple_loss=0.3222, pruned_loss=0.07509, over 7335.00 frames.], tot_loss[loss=0.251, simple_loss=0.3282, pruned_loss=0.08691, over 1413920.78 frames.], batch size: 25, lr: 1.58e-03
+2022-04-28 12:25:26,868 INFO [train.py:763] (2/8) Epoch 3, batch 1650, loss[loss=0.2342, simple_loss=0.3259, pruned_loss=0.07122, over 7329.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3257, pruned_loss=0.08543, over 1415120.96 frames.], batch size: 20, lr: 1.58e-03
+2022-04-28 12:26:34,037 INFO [train.py:763] (2/8) Epoch 3, batch 1700, loss[loss=0.2501, simple_loss=0.3192, pruned_loss=0.09052, over 7146.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3259, pruned_loss=0.08537, over 1419057.94 frames.], batch size: 20, lr: 1.57e-03
+2022-04-28 12:27:40,151 INFO [train.py:763] (2/8) Epoch 3, batch 1750, loss[loss=0.3091, simple_loss=0.3772, pruned_loss=0.1205, over 7215.00 frames.], tot_loss[loss=0.2498, simple_loss=0.3271, pruned_loss=0.08622, over 1418295.18 frames.], batch size: 22, lr: 1.57e-03
+2022-04-28 12:28:45,187 INFO [train.py:763] (2/8) Epoch 3, batch 1800, loss[loss=0.2256, simple_loss=0.3069, pruned_loss=0.07217, over 7220.00 frames.], tot_loss[loss=0.2522, simple_loss=0.3292, pruned_loss=0.08762, over 1420086.12 frames.], batch size: 21, lr: 1.57e-03
+2022-04-28 12:29:50,457 INFO [train.py:763] (2/8) Epoch 3, batch 1850, loss[loss=0.2717, simple_loss=0.3346, pruned_loss=0.1044, over 7145.00 frames.], tot_loss[loss=0.2527, simple_loss=0.3295, pruned_loss=0.08796, over 1419594.14 frames.], batch size: 17, lr: 1.57e-03
+2022-04-28 12:30:57,294 INFO [train.py:763] (2/8) Epoch 3, batch 1900, loss[loss=0.2245, simple_loss=0.3065, pruned_loss=0.07125, over 7160.00 frames.], tot_loss[loss=0.2528, simple_loss=0.3294, pruned_loss=0.08813, over 1423001.19 frames.], batch size: 19, lr: 1.56e-03
+2022-04-28 12:32:03,218 INFO [train.py:763] (2/8) Epoch 3, batch 1950, loss[loss=0.2784, simple_loss=0.348, pruned_loss=0.1044, over 6276.00 frames.], tot_loss[loss=0.2518, simple_loss=0.329, pruned_loss=0.0873, over 1427956.32 frames.], batch size: 37, lr: 1.56e-03
+2022-04-28 12:33:17,823 INFO [train.py:763] (2/8) Epoch 3, batch 2000, loss[loss=0.2604, simple_loss=0.3397, pruned_loss=0.09057, over 7103.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3285, pruned_loss=0.08653, over 1425252.30 frames.], batch size: 21, lr: 1.56e-03
+2022-04-28 12:35:10,044 INFO [train.py:763] (2/8) Epoch 3, batch 2050, loss[loss=0.2507, simple_loss=0.33, pruned_loss=0.0857, over 6822.00 frames.], tot_loss[loss=0.2503, simple_loss=0.3281, pruned_loss=0.08624, over 1422631.41 frames.], batch size: 31, lr: 1.56e-03
+2022-04-28 12:36:15,497 INFO [train.py:763] (2/8) Epoch 3, batch 2100, loss[loss=0.2452, simple_loss=0.3273, pruned_loss=0.08155, over 7320.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3268, pruned_loss=0.08486, over 1421261.16 frames.], batch size: 21, lr: 1.56e-03
+2022-04-28 12:37:29,639 INFO [train.py:763] (2/8) Epoch 3, batch 2150, loss[loss=0.2193, simple_loss=0.3075, pruned_loss=0.06551, over 7339.00 frames.], tot_loss[loss=0.2472, simple_loss=0.3255, pruned_loss=0.08439, over 1423301.18 frames.], batch size: 22, lr: 1.55e-03
+2022-04-28 12:38:44,718 INFO [train.py:763] (2/8) Epoch 3, batch 2200, loss[loss=0.2279, simple_loss=0.3216, pruned_loss=0.06714, over 7210.00 frames.], tot_loss[loss=0.2451, simple_loss=0.3238, pruned_loss=0.08321, over 1425604.10 frames.], batch size: 21, lr: 1.55e-03
+2022-04-28 12:40:02,462 INFO [train.py:763] (2/8) Epoch 3, batch 2250, loss[loss=0.3043, simple_loss=0.3542, pruned_loss=0.1272, over 4991.00 frames.], tot_loss[loss=0.2469, simple_loss=0.3251, pruned_loss=0.08429, over 1427866.90 frames.], batch size: 52, lr: 1.55e-03
+2022-04-28 12:41:07,751 INFO [train.py:763] (2/8) Epoch 3, batch 2300, loss[loss=0.2489, simple_loss=0.3228, pruned_loss=0.08754, over 7167.00 frames.], tot_loss[loss=0.2473, simple_loss=0.3256, pruned_loss=0.0845, over 1430361.58 frames.], batch size: 19, lr: 1.55e-03
+2022-04-28 12:42:14,639 INFO [train.py:763] (2/8) Epoch 3, batch 2350, loss[loss=0.2534, simple_loss=0.335, pruned_loss=0.0859, over 7328.00 frames.], tot_loss[loss=0.246, simple_loss=0.3243, pruned_loss=0.08386, over 1431516.92 frames.], batch size: 20, lr: 1.54e-03
+2022-04-28 12:43:19,978 INFO [train.py:763] (2/8) Epoch 3, batch 2400, loss[loss=0.2526, simple_loss=0.3378, pruned_loss=0.08368, over 7302.00 frames.], tot_loss[loss=0.247, simple_loss=0.3255, pruned_loss=0.08422, over 1433353.29 frames.], batch size: 25, lr: 1.54e-03
+2022-04-28 12:44:25,913 INFO [train.py:763] (2/8) Epoch 3, batch 2450, loss[loss=0.3014, simple_loss=0.369, pruned_loss=0.1169, over 7354.00 frames.], tot_loss[loss=0.248, simple_loss=0.3263, pruned_loss=0.0849, over 1436305.20 frames.], batch size: 23, lr: 1.54e-03
+2022-04-28 12:45:31,559 INFO [train.py:763] (2/8) Epoch 3, batch 2500, loss[loss=0.2416, simple_loss=0.3116, pruned_loss=0.08583, over 7155.00 frames.], tot_loss[loss=0.2493, simple_loss=0.3269, pruned_loss=0.08578, over 1433662.36 frames.], batch size: 19, lr: 1.54e-03
+2022-04-28 12:46:36,891 INFO [train.py:763] (2/8) Epoch 3, batch 2550, loss[loss=0.2529, simple_loss=0.321, pruned_loss=0.0924, over 7404.00 frames.], tot_loss[loss=0.2507, simple_loss=0.3274, pruned_loss=0.08698, over 1425972.15 frames.], batch size: 18, lr: 1.54e-03
+2022-04-28 12:47:42,407 INFO [train.py:763] (2/8) Epoch 3, batch 2600, loss[loss=0.2401, simple_loss=0.3247, pruned_loss=0.0777, over 7238.00 frames.], tot_loss[loss=0.2532, simple_loss=0.3296, pruned_loss=0.0884, over 1425934.53 frames.], batch size: 20, lr: 1.53e-03
+2022-04-28 12:48:47,820 INFO [train.py:763] (2/8) Epoch 3, batch 2650, loss[loss=0.2534, simple_loss=0.3106, pruned_loss=0.09811, over 6999.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3294, pruned_loss=0.08778, over 1419318.21 frames.], batch size: 16, lr: 1.53e-03
+2022-04-28 12:49:52,899 INFO [train.py:763] (2/8) Epoch 3, batch 2700, loss[loss=0.2132, simple_loss=0.2881, pruned_loss=0.06922, over 6765.00 frames.], tot_loss[loss=0.2511, simple_loss=0.3287, pruned_loss=0.0868, over 1417681.12 frames.], batch size: 15, lr: 1.53e-03
+2022-04-28 12:50:58,279 INFO [train.py:763] (2/8) Epoch 3, batch 2750, loss[loss=0.2353, simple_loss=0.3117, pruned_loss=0.07943, over 7260.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3282, pruned_loss=0.08607, over 1421233.08 frames.], batch size: 19, lr: 1.53e-03
+2022-04-28 12:52:03,625 INFO [train.py:763] (2/8) Epoch 3, batch 2800, loss[loss=0.1986, simple_loss=0.2794, pruned_loss=0.05892, over 7156.00 frames.], tot_loss[loss=0.2481, simple_loss=0.3264, pruned_loss=0.08493, over 1424346.64 frames.], batch size: 19, lr: 1.53e-03
+2022-04-28 12:53:09,245 INFO [train.py:763] (2/8) Epoch 3, batch 2850, loss[loss=0.2909, simple_loss=0.357, pruned_loss=0.1124, over 5110.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3248, pruned_loss=0.08418, over 1423905.28 frames.], batch size: 52, lr: 1.52e-03
+2022-04-28 12:54:14,535 INFO [train.py:763] (2/8) Epoch 3, batch 2900, loss[loss=0.2533, simple_loss=0.3427, pruned_loss=0.0819, over 6801.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3245, pruned_loss=0.08384, over 1424245.23 frames.], batch size: 31, lr: 1.52e-03
+2022-04-28 12:55:20,286 INFO [train.py:763] (2/8) Epoch 3, batch 2950, loss[loss=0.2371, simple_loss=0.3215, pruned_loss=0.07634, over 7023.00 frames.], tot_loss[loss=0.245, simple_loss=0.3236, pruned_loss=0.08314, over 1428153.79 frames.], batch size: 28, lr: 1.52e-03
+2022-04-28 12:56:25,609 INFO [train.py:763] (2/8) Epoch 3, batch 3000, loss[loss=0.2709, simple_loss=0.3434, pruned_loss=0.09926, over 7151.00 frames.], tot_loss[loss=0.2465, simple_loss=0.3251, pruned_loss=0.08395, over 1426603.14 frames.], batch size: 20, lr: 1.52e-03
+2022-04-28 12:56:25,610 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-28 12:56:40,877 INFO [train.py:792] (2/8) Epoch 3, validation: loss=0.1917, simple_loss=0.2967, pruned_loss=0.04336, over 698248.00 frames.
+2022-04-28 12:57:46,579 INFO [train.py:763] (2/8) Epoch 3, batch 3050, loss[loss=0.2348, simple_loss=0.3333, pruned_loss=0.06813, over 7116.00 frames.], tot_loss[loss=0.2466, simple_loss=0.325, pruned_loss=0.08412, over 1421965.77 frames.], batch size: 21, lr: 1.51e-03
+2022-04-28 12:58:52,511 INFO [train.py:763] (2/8) Epoch 3, batch 3100, loss[loss=0.2709, simple_loss=0.3537, pruned_loss=0.09405, over 7306.00 frames.], tot_loss[loss=0.2464, simple_loss=0.3246, pruned_loss=0.08416, over 1419010.48 frames.], batch size: 24, lr: 1.51e-03
+2022-04-28 12:59:58,113 INFO [train.py:763] (2/8) Epoch 3, batch 3150, loss[loss=0.2426, simple_loss=0.326, pruned_loss=0.07955, over 7289.00 frames.], tot_loss[loss=0.2459, simple_loss=0.3242, pruned_loss=0.08384, over 1423875.69 frames.], batch size: 25, lr: 1.51e-03
+2022-04-28 13:01:03,461 INFO [train.py:763] (2/8) Epoch 3, batch 3200, loss[loss=0.2339, simple_loss=0.3117, pruned_loss=0.07801, over 7060.00 frames.], tot_loss[loss=0.2443, simple_loss=0.3231, pruned_loss=0.08275, over 1424636.96 frames.], batch size: 18, lr: 1.51e-03
+2022-04-28 13:02:09,451 INFO [train.py:763] (2/8) Epoch 3, batch 3250, loss[loss=0.2123, simple_loss=0.2964, pruned_loss=0.0641, over 7256.00 frames.], tot_loss[loss=0.2462, simple_loss=0.3246, pruned_loss=0.0839, over 1424795.40 frames.], batch size: 19, lr: 1.51e-03
+2022-04-28 13:03:16,230 INFO [train.py:763] (2/8) Epoch 3, batch 3300, loss[loss=0.2717, simple_loss=0.3467, pruned_loss=0.09833, over 7215.00 frames.], tot_loss[loss=0.2457, simple_loss=0.3245, pruned_loss=0.08347, over 1423468.06 frames.], batch size: 23, lr: 1.50e-03
+2022-04-28 13:04:22,924 INFO [train.py:763] (2/8) Epoch 3, batch 3350, loss[loss=0.2808, simple_loss=0.356, pruned_loss=0.1028, over 6324.00 frames.], tot_loss[loss=0.2457, simple_loss=0.3239, pruned_loss=0.08375, over 1421669.91 frames.], batch size: 37, lr: 1.50e-03
+2022-04-28 13:05:28,640 INFO [train.py:763] (2/8) Epoch 3, batch 3400, loss[loss=0.242, simple_loss=0.2957, pruned_loss=0.09415, over 6997.00 frames.], tot_loss[loss=0.2458, simple_loss=0.3238, pruned_loss=0.08391, over 1422221.55 frames.], batch size: 16, lr: 1.50e-03
+2022-04-28 13:06:35,005 INFO [train.py:763] (2/8) Epoch 3, batch 3450, loss[loss=0.2063, simple_loss=0.2908, pruned_loss=0.06095, over 7165.00 frames.], tot_loss[loss=0.2437, simple_loss=0.322, pruned_loss=0.08272, over 1426899.90 frames.], batch size: 18, lr: 1.50e-03
+2022-04-28 13:07:42,190 INFO [train.py:763] (2/8) Epoch 3, batch 3500, loss[loss=0.2894, simple_loss=0.3507, pruned_loss=0.1141, over 7389.00 frames.], tot_loss[loss=0.243, simple_loss=0.3213, pruned_loss=0.08232, over 1428600.46 frames.], batch size: 23, lr: 1.50e-03
+2022-04-28 13:08:48,562 INFO [train.py:763] (2/8) Epoch 3, batch 3550, loss[loss=0.3092, simple_loss=0.3657, pruned_loss=0.1264, over 7286.00 frames.], tot_loss[loss=0.2421, simple_loss=0.3201, pruned_loss=0.08206, over 1429264.51 frames.], batch size: 24, lr: 1.49e-03
+2022-04-28 13:09:55,524 INFO [train.py:763] (2/8) Epoch 3, batch 3600, loss[loss=0.2354, simple_loss=0.3001, pruned_loss=0.08536, over 6985.00 frames.], tot_loss[loss=0.2432, simple_loss=0.3214, pruned_loss=0.08253, over 1428010.33 frames.], batch size: 16, lr: 1.49e-03
+2022-04-28 13:11:02,048 INFO [train.py:763] (2/8) Epoch 3, batch 3650, loss[loss=0.206, simple_loss=0.2915, pruned_loss=0.06022, over 7130.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3211, pruned_loss=0.08238, over 1427775.43 frames.], batch size: 17, lr: 1.49e-03
+2022-04-28 13:12:07,901 INFO [train.py:763] (2/8) Epoch 3, batch 3700, loss[loss=0.1992, simple_loss=0.2721, pruned_loss=0.06312, over 7010.00 frames.], tot_loss[loss=0.2425, simple_loss=0.3206, pruned_loss=0.08218, over 1427057.72 frames.], batch size: 16, lr: 1.49e-03
+2022-04-28 13:13:15,358 INFO [train.py:763] (2/8) Epoch 3, batch 3750, loss[loss=0.235, simple_loss=0.3155, pruned_loss=0.07722, over 7437.00 frames.], tot_loss[loss=0.2412, simple_loss=0.3192, pruned_loss=0.08157, over 1425101.10 frames.], batch size: 20, lr: 1.49e-03
+2022-04-28 13:14:22,355 INFO [train.py:763] (2/8) Epoch 3, batch 3800, loss[loss=0.2362, simple_loss=0.3206, pruned_loss=0.07589, over 7457.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3208, pruned_loss=0.08239, over 1421809.80 frames.], batch size: 19, lr: 1.48e-03
+2022-04-28 13:15:29,714 INFO [train.py:763] (2/8) Epoch 3, batch 3850, loss[loss=0.2193, simple_loss=0.2955, pruned_loss=0.07158, over 7421.00 frames.], tot_loss[loss=0.2413, simple_loss=0.3198, pruned_loss=0.08137, over 1425124.62 frames.], batch size: 18, lr: 1.48e-03
+2022-04-28 13:16:35,236 INFO [train.py:763] (2/8) Epoch 3, batch 3900, loss[loss=0.2912, simple_loss=0.3523, pruned_loss=0.1151, over 5182.00 frames.], tot_loss[loss=0.2418, simple_loss=0.3203, pruned_loss=0.08163, over 1426332.44 frames.], batch size: 52, lr: 1.48e-03
+2022-04-28 13:17:41,250 INFO [train.py:763] (2/8) Epoch 3, batch 3950, loss[loss=0.212, simple_loss=0.2808, pruned_loss=0.07162, over 6755.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3206, pruned_loss=0.08234, over 1424509.48 frames.], batch size: 15, lr: 1.48e-03
+2022-04-28 13:18:46,784 INFO [train.py:763] (2/8) Epoch 3, batch 4000, loss[loss=0.255, simple_loss=0.3352, pruned_loss=0.08743, over 7211.00 frames.], tot_loss[loss=0.244, simple_loss=0.3216, pruned_loss=0.08317, over 1416605.40 frames.], batch size: 21, lr: 1.48e-03
+2022-04-28 13:19:52,128 INFO [train.py:763] (2/8) Epoch 3, batch 4050, loss[loss=0.2596, simple_loss=0.339, pruned_loss=0.09011, over 7413.00 frames.], tot_loss[loss=0.2442, simple_loss=0.322, pruned_loss=0.08325, over 1419011.15 frames.], batch size: 21, lr: 1.47e-03
+2022-04-28 13:20:58,240 INFO [train.py:763] (2/8) Epoch 3, batch 4100, loss[loss=0.2697, simple_loss=0.3312, pruned_loss=0.1041, over 6191.00 frames.], tot_loss[loss=0.2434, simple_loss=0.3217, pruned_loss=0.08255, over 1421141.26 frames.], batch size: 37, lr: 1.47e-03
+2022-04-28 13:22:04,068 INFO [train.py:763] (2/8) Epoch 3, batch 4150, loss[loss=0.2511, simple_loss=0.3154, pruned_loss=0.09338, over 7004.00 frames.], tot_loss[loss=0.2427, simple_loss=0.3209, pruned_loss=0.08224, over 1422919.55 frames.], batch size: 16, lr: 1.47e-03
+2022-04-28 13:23:11,043 INFO [train.py:763] (2/8) Epoch 3, batch 4200, loss[loss=0.2236, simple_loss=0.3106, pruned_loss=0.06827, over 7151.00 frames.], tot_loss[loss=0.2421, simple_loss=0.3207, pruned_loss=0.08171, over 1421499.12 frames.], batch size: 19, lr: 1.47e-03
+2022-04-28 13:24:18,325 INFO [train.py:763] (2/8) Epoch 3, batch 4250, loss[loss=0.2032, simple_loss=0.2873, pruned_loss=0.05954, over 7370.00 frames.], tot_loss[loss=0.2417, simple_loss=0.3199, pruned_loss=0.08179, over 1412765.48 frames.], batch size: 19, lr: 1.47e-03
+2022-04-28 13:25:24,086 INFO [train.py:763] (2/8) Epoch 3, batch 4300, loss[loss=0.2531, simple_loss=0.3214, pruned_loss=0.09246, over 7351.00 frames.], tot_loss[loss=0.2412, simple_loss=0.3189, pruned_loss=0.0817, over 1411177.58 frames.], batch size: 19, lr: 1.47e-03
+2022-04-28 13:26:29,893 INFO [train.py:763] (2/8) Epoch 3, batch 4350, loss[loss=0.2753, simple_loss=0.357, pruned_loss=0.09683, over 6569.00 frames.], tot_loss[loss=0.2388, simple_loss=0.3165, pruned_loss=0.0805, over 1409226.30 frames.], batch size: 38, lr: 1.46e-03
+2022-04-28 13:27:35,680 INFO [train.py:763] (2/8) Epoch 3, batch 4400, loss[loss=0.2147, simple_loss=0.2953, pruned_loss=0.06703, over 7070.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3155, pruned_loss=0.08012, over 1409398.45 frames.], batch size: 18, lr: 1.46e-03
+2022-04-28 13:28:41,561 INFO [train.py:763] (2/8) Epoch 3, batch 4450, loss[loss=0.2553, simple_loss=0.3378, pruned_loss=0.08637, over 7382.00 frames.], tot_loss[loss=0.2376, simple_loss=0.315, pruned_loss=0.08008, over 1399989.35 frames.], batch size: 23, lr: 1.46e-03
+2022-04-28 13:29:46,948 INFO [train.py:763] (2/8) Epoch 3, batch 4500, loss[loss=0.245, simple_loss=0.3301, pruned_loss=0.07998, over 6542.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3157, pruned_loss=0.0802, over 1395494.44 frames.], batch size: 38, lr: 1.46e-03
+2022-04-28 13:30:51,038 INFO [train.py:763] (2/8) Epoch 3, batch 4550, loss[loss=0.2838, simple_loss=0.3494, pruned_loss=0.1091, over 5590.00 frames.], tot_loss[loss=0.242, simple_loss=0.3193, pruned_loss=0.08237, over 1361142.35 frames.], batch size: 53, lr: 1.46e-03
+2022-04-28 13:32:20,223 INFO [train.py:763] (2/8) Epoch 4, batch 0, loss[loss=0.2693, simple_loss=0.3503, pruned_loss=0.09417, over 7179.00 frames.], tot_loss[loss=0.2693, simple_loss=0.3503, pruned_loss=0.09417, over 7179.00 frames.], batch size: 23, lr: 1.40e-03
+2022-04-28 13:33:26,502 INFO [train.py:763] (2/8) Epoch 4, batch 50, loss[loss=0.2714, simple_loss=0.3473, pruned_loss=0.09778, over 7339.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3217, pruned_loss=0.08201, over 320738.81 frames.], batch size: 22, lr: 1.40e-03
+2022-04-28 13:34:31,939 INFO [train.py:763] (2/8) Epoch 4, batch 100, loss[loss=0.2514, simple_loss=0.3439, pruned_loss=0.07943, over 7336.00 frames.], tot_loss[loss=0.2415, simple_loss=0.3217, pruned_loss=0.08065, over 566959.81 frames.], batch size: 22, lr: 1.40e-03
+2022-04-28 13:35:37,379 INFO [train.py:763] (2/8) Epoch 4, batch 150, loss[loss=0.3115, simple_loss=0.3558, pruned_loss=0.1336, over 5146.00 frames.], tot_loss[loss=0.2417, simple_loss=0.3217, pruned_loss=0.08083, over 755725.04 frames.], batch size: 52, lr: 1.40e-03
+2022-04-28 13:36:43,011 INFO [train.py:763] (2/8) Epoch 4, batch 200, loss[loss=0.2039, simple_loss=0.2912, pruned_loss=0.05829, over 7165.00 frames.], tot_loss[loss=0.2416, simple_loss=0.3212, pruned_loss=0.08102, over 904276.41 frames.], batch size: 19, lr: 1.40e-03
+2022-04-28 13:37:48,977 INFO [train.py:763] (2/8) Epoch 4, batch 250, loss[loss=0.2865, simple_loss=0.3493, pruned_loss=0.1119, over 7336.00 frames.], tot_loss[loss=0.243, simple_loss=0.3235, pruned_loss=0.0813, over 1022231.81 frames.], batch size: 22, lr: 1.39e-03
+2022-04-28 13:38:55,650 INFO [train.py:763] (2/8) Epoch 4, batch 300, loss[loss=0.1984, simple_loss=0.2836, pruned_loss=0.05658, over 7279.00 frames.], tot_loss[loss=0.2388, simple_loss=0.3201, pruned_loss=0.07876, over 1114231.73 frames.], batch size: 17, lr: 1.39e-03
+2022-04-28 13:40:02,791 INFO [train.py:763] (2/8) Epoch 4, batch 350, loss[loss=0.2168, simple_loss=0.297, pruned_loss=0.06828, over 7159.00 frames.], tot_loss[loss=0.238, simple_loss=0.3192, pruned_loss=0.07844, over 1181301.29 frames.], batch size: 19, lr: 1.39e-03
+2022-04-28 13:41:09,480 INFO [train.py:763] (2/8) Epoch 4, batch 400, loss[loss=0.2165, simple_loss=0.302, pruned_loss=0.0655, over 7097.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3185, pruned_loss=0.07865, over 1232691.44 frames.], batch size: 28, lr: 1.39e-03
+2022-04-28 13:42:15,463 INFO [train.py:763] (2/8) Epoch 4, batch 450, loss[loss=0.2456, simple_loss=0.3274, pruned_loss=0.08189, over 6997.00 frames.], tot_loss[loss=0.237, simple_loss=0.318, pruned_loss=0.07802, over 1273699.65 frames.], batch size: 28, lr: 1.39e-03
+2022-04-28 13:43:21,270 INFO [train.py:763] (2/8) Epoch 4, batch 500, loss[loss=0.2521, simple_loss=0.3316, pruned_loss=0.08636, over 7315.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3168, pruned_loss=0.07732, over 1308771.54 frames.], batch size: 21, lr: 1.39e-03
+2022-04-28 13:44:28,334 INFO [train.py:763] (2/8) Epoch 4, batch 550, loss[loss=0.2624, simple_loss=0.3389, pruned_loss=0.09295, over 6942.00 frames.], tot_loss[loss=0.2358, simple_loss=0.3168, pruned_loss=0.0774, over 1333783.92 frames.], batch size: 31, lr: 1.38e-03
+2022-04-28 13:45:33,789 INFO [train.py:763] (2/8) Epoch 4, batch 600, loss[loss=0.2166, simple_loss=0.3023, pruned_loss=0.06541, over 7434.00 frames.], tot_loss[loss=0.235, simple_loss=0.3159, pruned_loss=0.07703, over 1356285.15 frames.], batch size: 17, lr: 1.38e-03
+2022-04-28 13:46:39,055 INFO [train.py:763] (2/8) Epoch 4, batch 650, loss[loss=0.2129, simple_loss=0.3009, pruned_loss=0.06249, over 7332.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3164, pruned_loss=0.07753, over 1370971.25 frames.], batch size: 20, lr: 1.38e-03
+2022-04-28 13:47:44,002 INFO [train.py:763] (2/8) Epoch 4, batch 700, loss[loss=0.2601, simple_loss=0.3636, pruned_loss=0.07828, over 7285.00 frames.], tot_loss[loss=0.2372, simple_loss=0.3181, pruned_loss=0.07817, over 1380797.84 frames.], batch size: 25, lr: 1.38e-03
+2022-04-28 13:48:49,477 INFO [train.py:763] (2/8) Epoch 4, batch 750, loss[loss=0.2324, simple_loss=0.3032, pruned_loss=0.08083, over 7071.00 frames.], tot_loss[loss=0.2368, simple_loss=0.317, pruned_loss=0.07833, over 1385197.82 frames.], batch size: 18, lr: 1.38e-03
+2022-04-28 13:49:55,001 INFO [train.py:763] (2/8) Epoch 4, batch 800, loss[loss=0.2276, simple_loss=0.3079, pruned_loss=0.07363, over 7065.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3135, pruned_loss=0.07618, over 1396095.67 frames.], batch size: 18, lr: 1.38e-03
+2022-04-28 13:50:59,965 INFO [train.py:763] (2/8) Epoch 4, batch 850, loss[loss=0.2061, simple_loss=0.2882, pruned_loss=0.06206, over 7071.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3137, pruned_loss=0.07653, over 1394802.77 frames.], batch size: 18, lr: 1.37e-03
+2022-04-28 13:52:05,755 INFO [train.py:763] (2/8) Epoch 4, batch 900, loss[loss=0.2137, simple_loss=0.2945, pruned_loss=0.06647, over 7321.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3145, pruned_loss=0.0769, over 1402062.99 frames.], batch size: 21, lr: 1.37e-03
+2022-04-28 13:53:12,230 INFO [train.py:763] (2/8) Epoch 4, batch 950, loss[loss=0.2541, simple_loss=0.3351, pruned_loss=0.08654, over 7073.00 frames.], tot_loss[loss=0.2346, simple_loss=0.3153, pruned_loss=0.07701, over 1405542.19 frames.], batch size: 28, lr: 1.37e-03
+2022-04-28 13:54:19,381 INFO [train.py:763] (2/8) Epoch 4, batch 1000, loss[loss=0.2055, simple_loss=0.2871, pruned_loss=0.0619, over 7072.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3145, pruned_loss=0.07664, over 1410378.10 frames.], batch size: 18, lr: 1.37e-03
+2022-04-28 13:55:24,900 INFO [train.py:763] (2/8) Epoch 4, batch 1050, loss[loss=0.2528, simple_loss=0.3365, pruned_loss=0.08458, over 7296.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3152, pruned_loss=0.07644, over 1416242.96 frames.], batch size: 24, lr: 1.37e-03
+2022-04-28 13:56:29,979 INFO [train.py:763] (2/8) Epoch 4, batch 1100, loss[loss=0.3293, simple_loss=0.3808, pruned_loss=0.1389, over 6490.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3169, pruned_loss=0.07789, over 1412015.80 frames.], batch size: 38, lr: 1.37e-03
+2022-04-28 13:57:36,084 INFO [train.py:763] (2/8) Epoch 4, batch 1150, loss[loss=0.2595, simple_loss=0.3324, pruned_loss=0.09332, over 7442.00 frames.], tot_loss[loss=0.2362, simple_loss=0.3175, pruned_loss=0.07748, over 1414606.69 frames.], batch size: 20, lr: 1.36e-03
+2022-04-28 13:58:41,141 INFO [train.py:763] (2/8) Epoch 4, batch 1200, loss[loss=0.2162, simple_loss=0.3058, pruned_loss=0.06332, over 6338.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3167, pruned_loss=0.07723, over 1416901.27 frames.], batch size: 37, lr: 1.36e-03
+2022-04-28 13:59:46,357 INFO [train.py:763] (2/8) Epoch 4, batch 1250, loss[loss=0.2342, simple_loss=0.3197, pruned_loss=0.07437, over 7255.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3165, pruned_loss=0.07738, over 1412775.15 frames.], batch size: 19, lr: 1.36e-03
+2022-04-28 14:00:51,528 INFO [train.py:763] (2/8) Epoch 4, batch 1300, loss[loss=0.2191, simple_loss=0.3023, pruned_loss=0.06795, over 7334.00 frames.], tot_loss[loss=0.2354, simple_loss=0.3168, pruned_loss=0.07702, over 1415996.61 frames.], batch size: 20, lr: 1.36e-03
+2022-04-28 14:01:57,420 INFO [train.py:763] (2/8) Epoch 4, batch 1350, loss[loss=0.2175, simple_loss=0.2948, pruned_loss=0.07009, over 7136.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3167, pruned_loss=0.07653, over 1422822.05 frames.], batch size: 17, lr: 1.36e-03
+2022-04-28 14:03:02,787 INFO [train.py:763] (2/8) Epoch 4, batch 1400, loss[loss=0.2191, simple_loss=0.3088, pruned_loss=0.06471, over 7219.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3183, pruned_loss=0.07725, over 1418945.58 frames.], batch size: 20, lr: 1.36e-03
+2022-04-28 14:04:07,962 INFO [train.py:763] (2/8) Epoch 4, batch 1450, loss[loss=0.2528, simple_loss=0.3148, pruned_loss=0.09536, over 6999.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3187, pruned_loss=0.0775, over 1419557.20 frames.], batch size: 16, lr: 1.35e-03
+2022-04-28 14:05:14,089 INFO [train.py:763] (2/8) Epoch 4, batch 1500, loss[loss=0.2135, simple_loss=0.3056, pruned_loss=0.06075, over 7337.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3163, pruned_loss=0.07591, over 1423106.62 frames.], batch size: 20, lr: 1.35e-03
+2022-04-28 14:06:19,704 INFO [train.py:763] (2/8) Epoch 4, batch 1550, loss[loss=0.3093, simple_loss=0.3771, pruned_loss=0.1207, over 7384.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3149, pruned_loss=0.07542, over 1425489.09 frames.], batch size: 23, lr: 1.35e-03
+2022-04-28 14:07:24,976 INFO [train.py:763] (2/8) Epoch 4, batch 1600, loss[loss=0.2529, simple_loss=0.3349, pruned_loss=0.08543, over 7280.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3144, pruned_loss=0.07519, over 1424686.26 frames.], batch size: 25, lr: 1.35e-03
+2022-04-28 14:08:30,204 INFO [train.py:763] (2/8) Epoch 4, batch 1650, loss[loss=0.22, simple_loss=0.3175, pruned_loss=0.06128, over 7121.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3148, pruned_loss=0.07552, over 1422010.09 frames.], batch size: 21, lr: 1.35e-03
+2022-04-28 14:09:35,798 INFO [train.py:763] (2/8) Epoch 4, batch 1700, loss[loss=0.3206, simple_loss=0.386, pruned_loss=0.1276, over 7333.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3148, pruned_loss=0.0755, over 1424002.46 frames.], batch size: 22, lr: 1.35e-03
+2022-04-28 14:10:42,768 INFO [train.py:763] (2/8) Epoch 4, batch 1750, loss[loss=0.2481, simple_loss=0.3311, pruned_loss=0.08255, over 7276.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3137, pruned_loss=0.07527, over 1423471.10 frames.], batch size: 24, lr: 1.34e-03
+2022-04-28 14:11:49,091 INFO [train.py:763] (2/8) Epoch 4, batch 1800, loss[loss=0.2363, simple_loss=0.3128, pruned_loss=0.07991, over 7328.00 frames.], tot_loss[loss=0.234, simple_loss=0.3151, pruned_loss=0.07639, over 1425887.20 frames.], batch size: 21, lr: 1.34e-03
+2022-04-28 14:12:54,649 INFO [train.py:763] (2/8) Epoch 4, batch 1850, loss[loss=0.2988, simple_loss=0.3587, pruned_loss=0.1194, over 6388.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3159, pruned_loss=0.07688, over 1426093.28 frames.], batch size: 38, lr: 1.34e-03
+2022-04-28 14:13:59,949 INFO [train.py:763] (2/8) Epoch 4, batch 1900, loss[loss=0.248, simple_loss=0.333, pruned_loss=0.08147, over 7111.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3145, pruned_loss=0.07587, over 1427747.13 frames.], batch size: 21, lr: 1.34e-03
+2022-04-28 14:15:05,360 INFO [train.py:763] (2/8) Epoch 4, batch 1950, loss[loss=0.1926, simple_loss=0.2736, pruned_loss=0.05586, over 7152.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3144, pruned_loss=0.07511, over 1428055.75 frames.], batch size: 18, lr: 1.34e-03
+2022-04-28 14:16:10,981 INFO [train.py:763] (2/8) Epoch 4, batch 2000, loss[loss=0.2207, simple_loss=0.3132, pruned_loss=0.06408, over 7327.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3136, pruned_loss=0.0746, over 1425589.32 frames.], batch size: 25, lr: 1.34e-03
+2022-04-28 14:17:16,769 INFO [train.py:763] (2/8) Epoch 4, batch 2050, loss[loss=0.2542, simple_loss=0.3467, pruned_loss=0.08089, over 7308.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3131, pruned_loss=0.0746, over 1430308.09 frames.], batch size: 24, lr: 1.34e-03
+2022-04-28 14:18:22,257 INFO [train.py:763] (2/8) Epoch 4, batch 2100, loss[loss=0.1769, simple_loss=0.2562, pruned_loss=0.04881, over 7403.00 frames.], tot_loss[loss=0.2302, simple_loss=0.3121, pruned_loss=0.07418, over 1433267.02 frames.], batch size: 18, lr: 1.33e-03
+2022-04-28 14:19:27,835 INFO [train.py:763] (2/8) Epoch 4, batch 2150, loss[loss=0.2514, simple_loss=0.3224, pruned_loss=0.09022, over 7064.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3145, pruned_loss=0.07553, over 1432166.44 frames.], batch size: 18, lr: 1.33e-03
+2022-04-28 14:20:34,205 INFO [train.py:763] (2/8) Epoch 4, batch 2200, loss[loss=0.2195, simple_loss=0.3099, pruned_loss=0.06458, over 7338.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3147, pruned_loss=0.07592, over 1433816.15 frames.], batch size: 22, lr: 1.33e-03
+2022-04-28 14:21:39,758 INFO [train.py:763] (2/8) Epoch 4, batch 2250, loss[loss=0.2368, simple_loss=0.3187, pruned_loss=0.07751, over 7381.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3145, pruned_loss=0.07531, over 1431634.20 frames.], batch size: 23, lr: 1.33e-03
+2022-04-28 14:22:45,296 INFO [train.py:763] (2/8) Epoch 4, batch 2300, loss[loss=0.2162, simple_loss=0.2909, pruned_loss=0.07079, over 7273.00 frames.], tot_loss[loss=0.233, simple_loss=0.3148, pruned_loss=0.07557, over 1430291.36 frames.], batch size: 17, lr: 1.33e-03
+2022-04-28 14:23:50,800 INFO [train.py:763] (2/8) Epoch 4, batch 2350, loss[loss=0.2449, simple_loss=0.3151, pruned_loss=0.08738, over 7436.00 frames.], tot_loss[loss=0.2347, simple_loss=0.3162, pruned_loss=0.07657, over 1434024.45 frames.], batch size: 18, lr: 1.33e-03
+2022-04-28 14:24:56,453 INFO [train.py:763] (2/8) Epoch 4, batch 2400, loss[loss=0.2608, simple_loss=0.3544, pruned_loss=0.08361, over 7220.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3158, pruned_loss=0.07621, over 1435907.09 frames.], batch size: 21, lr: 1.32e-03
+2022-04-28 14:26:01,945 INFO [train.py:763] (2/8) Epoch 4, batch 2450, loss[loss=0.2173, simple_loss=0.2964, pruned_loss=0.06915, over 7271.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3157, pruned_loss=0.07594, over 1435396.73 frames.], batch size: 18, lr: 1.32e-03
+2022-04-28 14:27:09,071 INFO [train.py:763] (2/8) Epoch 4, batch 2500, loss[loss=0.2447, simple_loss=0.3418, pruned_loss=0.07382, over 7208.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3145, pruned_loss=0.07528, over 1433506.12 frames.], batch size: 22, lr: 1.32e-03
+2022-04-28 14:28:14,995 INFO [train.py:763] (2/8) Epoch 4, batch 2550, loss[loss=0.2319, simple_loss=0.3123, pruned_loss=0.07571, over 7151.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3152, pruned_loss=0.07569, over 1433799.45 frames.], batch size: 20, lr: 1.32e-03
+2022-04-28 14:29:20,316 INFO [train.py:763] (2/8) Epoch 4, batch 2600, loss[loss=0.2103, simple_loss=0.3035, pruned_loss=0.05859, over 7314.00 frames.], tot_loss[loss=0.2344, simple_loss=0.316, pruned_loss=0.0764, over 1432112.19 frames.], batch size: 21, lr: 1.32e-03
+2022-04-28 14:30:26,098 INFO [train.py:763] (2/8) Epoch 4, batch 2650, loss[loss=0.2012, simple_loss=0.281, pruned_loss=0.06077, over 7008.00 frames.], tot_loss[loss=0.2336, simple_loss=0.3154, pruned_loss=0.07592, over 1430409.80 frames.], batch size: 16, lr: 1.32e-03
+2022-04-28 14:31:31,705 INFO [train.py:763] (2/8) Epoch 4, batch 2700, loss[loss=0.1957, simple_loss=0.2798, pruned_loss=0.05585, over 7269.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3153, pruned_loss=0.07568, over 1432856.54 frames.], batch size: 18, lr: 1.32e-03
+2022-04-28 14:32:38,235 INFO [train.py:763] (2/8) Epoch 4, batch 2750, loss[loss=0.2292, simple_loss=0.3131, pruned_loss=0.07272, over 7352.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3153, pruned_loss=0.07554, over 1433209.92 frames.], batch size: 19, lr: 1.31e-03
+2022-04-28 14:33:43,916 INFO [train.py:763] (2/8) Epoch 4, batch 2800, loss[loss=0.1888, simple_loss=0.2797, pruned_loss=0.04896, over 7137.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3145, pruned_loss=0.07497, over 1433765.23 frames.], batch size: 17, lr: 1.31e-03
+2022-04-28 14:34:49,325 INFO [train.py:763] (2/8) Epoch 4, batch 2850, loss[loss=0.2672, simple_loss=0.3471, pruned_loss=0.09362, over 6600.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3151, pruned_loss=0.07518, over 1430574.48 frames.], batch size: 31, lr: 1.31e-03
+2022-04-28 14:35:55,984 INFO [train.py:763] (2/8) Epoch 4, batch 2900, loss[loss=0.2157, simple_loss=0.3195, pruned_loss=0.05592, over 7280.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3154, pruned_loss=0.07502, over 1428482.63 frames.], batch size: 24, lr: 1.31e-03
+2022-04-28 14:37:01,944 INFO [train.py:763] (2/8) Epoch 4, batch 2950, loss[loss=0.2581, simple_loss=0.3351, pruned_loss=0.09054, over 7330.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3135, pruned_loss=0.07449, over 1427731.89 frames.], batch size: 22, lr: 1.31e-03
+2022-04-28 14:38:07,791 INFO [train.py:763] (2/8) Epoch 4, batch 3000, loss[loss=0.271, simple_loss=0.3493, pruned_loss=0.09632, over 7176.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3142, pruned_loss=0.07507, over 1424260.95 frames.], batch size: 26, lr: 1.31e-03
+2022-04-28 14:38:07,792 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-28 14:38:23,246 INFO [train.py:792] (2/8) Epoch 4, validation: loss=0.1809, simple_loss=0.2865, pruned_loss=0.03766, over 698248.00 frames.
+2022-04-28 14:39:28,673 INFO [train.py:763] (2/8) Epoch 4, batch 3050, loss[loss=0.2543, simple_loss=0.3428, pruned_loss=0.08297, over 7207.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3149, pruned_loss=0.07497, over 1428762.70 frames.], batch size: 22, lr: 1.31e-03
+2022-04-28 14:40:34,109 INFO [train.py:763] (2/8) Epoch 4, batch 3100, loss[loss=0.2306, simple_loss=0.3164, pruned_loss=0.07243, over 7232.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3144, pruned_loss=0.0746, over 1427140.53 frames.], batch size: 20, lr: 1.30e-03
+2022-04-28 14:41:39,917 INFO [train.py:763] (2/8) Epoch 4, batch 3150, loss[loss=0.2394, simple_loss=0.3342, pruned_loss=0.07228, over 7307.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3147, pruned_loss=0.07446, over 1427979.09 frames.], batch size: 25, lr: 1.30e-03
+2022-04-28 14:42:46,505 INFO [train.py:763] (2/8) Epoch 4, batch 3200, loss[loss=0.1901, simple_loss=0.2785, pruned_loss=0.05085, over 7354.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3137, pruned_loss=0.074, over 1428701.80 frames.], batch size: 19, lr: 1.30e-03
+2022-04-28 14:43:52,375 INFO [train.py:763] (2/8) Epoch 4, batch 3250, loss[loss=0.2127, simple_loss=0.2969, pruned_loss=0.06424, over 7168.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3125, pruned_loss=0.07337, over 1427489.70 frames.], batch size: 18, lr: 1.30e-03
+2022-04-28 14:44:57,964 INFO [train.py:763] (2/8) Epoch 4, batch 3300, loss[loss=0.253, simple_loss=0.3329, pruned_loss=0.08658, over 7150.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3141, pruned_loss=0.07469, over 1422602.73 frames.], batch size: 26, lr: 1.30e-03
+2022-04-28 14:46:03,552 INFO [train.py:763] (2/8) Epoch 4, batch 3350, loss[loss=0.3175, simple_loss=0.3754, pruned_loss=0.1298, over 7122.00 frames.], tot_loss[loss=0.231, simple_loss=0.3138, pruned_loss=0.07411, over 1425132.78 frames.], batch size: 21, lr: 1.30e-03
+2022-04-28 14:47:08,813 INFO [train.py:763] (2/8) Epoch 4, batch 3400, loss[loss=0.2063, simple_loss=0.3098, pruned_loss=0.05139, over 7240.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3141, pruned_loss=0.07431, over 1426561.58 frames.], batch size: 20, lr: 1.30e-03
+2022-04-28 14:48:14,156 INFO [train.py:763] (2/8) Epoch 4, batch 3450, loss[loss=0.2381, simple_loss=0.3274, pruned_loss=0.07441, over 7206.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3146, pruned_loss=0.07496, over 1426725.18 frames.], batch size: 23, lr: 1.29e-03
+2022-04-28 14:49:37,444 INFO [train.py:763] (2/8) Epoch 4, batch 3500, loss[loss=0.2405, simple_loss=0.3235, pruned_loss=0.07875, over 7326.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3147, pruned_loss=0.07492, over 1429819.34 frames.], batch size: 20, lr: 1.29e-03
+2022-04-28 14:50:52,143 INFO [train.py:763] (2/8) Epoch 4, batch 3550, loss[loss=0.2724, simple_loss=0.35, pruned_loss=0.09744, over 7415.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3145, pruned_loss=0.07485, over 1424531.51 frames.], batch size: 21, lr: 1.29e-03
+2022-04-28 14:51:57,839 INFO [train.py:763] (2/8) Epoch 4, batch 3600, loss[loss=0.2228, simple_loss=0.3003, pruned_loss=0.07263, over 7259.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3137, pruned_loss=0.07434, over 1420695.95 frames.], batch size: 19, lr: 1.29e-03
+2022-04-28 14:53:23,229 INFO [train.py:763] (2/8) Epoch 4, batch 3650, loss[loss=0.2682, simple_loss=0.3413, pruned_loss=0.09755, over 6786.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3147, pruned_loss=0.07521, over 1415963.99 frames.], batch size: 31, lr: 1.29e-03
+2022-04-28 14:54:39,012 INFO [train.py:763] (2/8) Epoch 4, batch 3700, loss[loss=0.1902, simple_loss=0.2783, pruned_loss=0.05101, over 7162.00 frames.], tot_loss[loss=0.2298, simple_loss=0.312, pruned_loss=0.07375, over 1420270.12 frames.], batch size: 18, lr: 1.29e-03
+2022-04-28 14:55:53,480 INFO [train.py:763] (2/8) Epoch 4, batch 3750, loss[loss=0.1887, simple_loss=0.2596, pruned_loss=0.05886, over 6748.00 frames.], tot_loss[loss=0.2292, simple_loss=0.312, pruned_loss=0.07318, over 1420857.67 frames.], batch size: 15, lr: 1.29e-03
+2022-04-28 14:56:59,178 INFO [train.py:763] (2/8) Epoch 4, batch 3800, loss[loss=0.2226, simple_loss=0.2981, pruned_loss=0.07355, over 7277.00 frames.], tot_loss[loss=0.2295, simple_loss=0.3123, pruned_loss=0.07338, over 1421816.85 frames.], batch size: 18, lr: 1.28e-03
+2022-04-28 14:58:05,502 INFO [train.py:763] (2/8) Epoch 4, batch 3850, loss[loss=0.2122, simple_loss=0.3076, pruned_loss=0.05844, over 7409.00 frames.], tot_loss[loss=0.2303, simple_loss=0.3129, pruned_loss=0.07386, over 1421061.66 frames.], batch size: 21, lr: 1.28e-03
+2022-04-28 14:59:11,122 INFO [train.py:763] (2/8) Epoch 4, batch 3900, loss[loss=0.2019, simple_loss=0.2969, pruned_loss=0.05343, over 7170.00 frames.], tot_loss[loss=0.2303, simple_loss=0.3127, pruned_loss=0.07394, over 1418396.28 frames.], batch size: 18, lr: 1.28e-03
+2022-04-28 15:00:16,490 INFO [train.py:763] (2/8) Epoch 4, batch 3950, loss[loss=0.2753, simple_loss=0.351, pruned_loss=0.09981, over 7412.00 frames.], tot_loss[loss=0.2303, simple_loss=0.3124, pruned_loss=0.07408, over 1415648.99 frames.], batch size: 21, lr: 1.28e-03
+2022-04-28 15:01:21,847 INFO [train.py:763] (2/8) Epoch 4, batch 4000, loss[loss=0.2185, simple_loss=0.3027, pruned_loss=0.06711, over 7433.00 frames.], tot_loss[loss=0.2304, simple_loss=0.313, pruned_loss=0.07387, over 1418495.40 frames.], batch size: 20, lr: 1.28e-03
+2022-04-28 15:02:27,493 INFO [train.py:763] (2/8) Epoch 4, batch 4050, loss[loss=0.2408, simple_loss=0.3332, pruned_loss=0.07418, over 7233.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3126, pruned_loss=0.07407, over 1420677.57 frames.], batch size: 21, lr: 1.28e-03
+2022-04-28 15:03:34,095 INFO [train.py:763] (2/8) Epoch 4, batch 4100, loss[loss=0.204, simple_loss=0.2798, pruned_loss=0.06412, over 7283.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3142, pruned_loss=0.07452, over 1417586.95 frames.], batch size: 18, lr: 1.28e-03
+2022-04-28 15:04:40,945 INFO [train.py:763] (2/8) Epoch 4, batch 4150, loss[loss=0.2234, simple_loss=0.3142, pruned_loss=0.06632, over 7224.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3156, pruned_loss=0.07547, over 1415447.55 frames.], batch size: 22, lr: 1.27e-03
+2022-04-28 15:05:47,253 INFO [train.py:763] (2/8) Epoch 4, batch 4200, loss[loss=0.206, simple_loss=0.2899, pruned_loss=0.06103, over 7141.00 frames.], tot_loss[loss=0.232, simple_loss=0.3148, pruned_loss=0.07462, over 1414150.64 frames.], batch size: 17, lr: 1.27e-03
+2022-04-28 15:06:53,139 INFO [train.py:763] (2/8) Epoch 4, batch 4250, loss[loss=0.212, simple_loss=0.3001, pruned_loss=0.06196, over 7070.00 frames.], tot_loss[loss=0.231, simple_loss=0.3142, pruned_loss=0.07394, over 1415153.32 frames.], batch size: 18, lr: 1.27e-03
+2022-04-28 15:07:59,468 INFO [train.py:763] (2/8) Epoch 4, batch 4300, loss[loss=0.2226, simple_loss=0.3048, pruned_loss=0.07015, over 7140.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3152, pruned_loss=0.07418, over 1415532.31 frames.], batch size: 20, lr: 1.27e-03
+2022-04-28 15:09:04,572 INFO [train.py:763] (2/8) Epoch 4, batch 4350, loss[loss=0.2298, simple_loss=0.3309, pruned_loss=0.06437, over 7418.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3158, pruned_loss=0.07449, over 1414038.16 frames.], batch size: 21, lr: 1.27e-03
+2022-04-28 15:10:09,732 INFO [train.py:763] (2/8) Epoch 4, batch 4400, loss[loss=0.2056, simple_loss=0.2977, pruned_loss=0.05671, over 7255.00 frames.], tot_loss[loss=0.233, simple_loss=0.316, pruned_loss=0.07499, over 1410406.66 frames.], batch size: 19, lr: 1.27e-03
+2022-04-28 15:11:14,748 INFO [train.py:763] (2/8) Epoch 4, batch 4450, loss[loss=0.2312, simple_loss=0.3124, pruned_loss=0.07497, over 6679.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3162, pruned_loss=0.07506, over 1404499.53 frames.], batch size: 31, lr: 1.27e-03
+2022-04-28 15:12:19,722 INFO [train.py:763] (2/8) Epoch 4, batch 4500, loss[loss=0.2833, simple_loss=0.3512, pruned_loss=0.1077, over 5011.00 frames.], tot_loss[loss=0.2337, simple_loss=0.3169, pruned_loss=0.07524, over 1395425.18 frames.], batch size: 54, lr: 1.27e-03
+2022-04-28 15:13:25,331 INFO [train.py:763] (2/8) Epoch 4, batch 4550, loss[loss=0.2586, simple_loss=0.3281, pruned_loss=0.09457, over 4732.00 frames.], tot_loss[loss=0.2399, simple_loss=0.3207, pruned_loss=0.07952, over 1341339.07 frames.], batch size: 52, lr: 1.26e-03
+2022-04-28 15:14:53,613 INFO [train.py:763] (2/8) Epoch 5, batch 0, loss[loss=0.244, simple_loss=0.3203, pruned_loss=0.08385, over 7155.00 frames.], tot_loss[loss=0.244, simple_loss=0.3203, pruned_loss=0.08385, over 7155.00 frames.], batch size: 19, lr: 1.21e-03
+2022-04-28 15:15:59,876 INFO [train.py:763] (2/8) Epoch 5, batch 50, loss[loss=0.2612, simple_loss=0.3379, pruned_loss=0.09222, over 5131.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3107, pruned_loss=0.07189, over 318500.72 frames.], batch size: 52, lr: 1.21e-03
+2022-04-28 15:17:05,482 INFO [train.py:763] (2/8) Epoch 5, batch 100, loss[loss=0.2072, simple_loss=0.2948, pruned_loss=0.05978, over 7150.00 frames.], tot_loss[loss=0.2279, simple_loss=0.3121, pruned_loss=0.07183, over 561696.64 frames.], batch size: 20, lr: 1.21e-03
+2022-04-28 15:18:11,201 INFO [train.py:763] (2/8) Epoch 5, batch 150, loss[loss=0.2261, simple_loss=0.3118, pruned_loss=0.07019, over 6706.00 frames.], tot_loss[loss=0.227, simple_loss=0.3115, pruned_loss=0.07127, over 750079.76 frames.], batch size: 31, lr: 1.21e-03
+2022-04-28 15:19:17,536 INFO [train.py:763] (2/8) Epoch 5, batch 200, loss[loss=0.1883, simple_loss=0.2706, pruned_loss=0.053, over 7403.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3115, pruned_loss=0.07088, over 899348.25 frames.], batch size: 18, lr: 1.21e-03
+2022-04-28 15:20:23,011 INFO [train.py:763] (2/8) Epoch 5, batch 250, loss[loss=0.2238, simple_loss=0.3133, pruned_loss=0.06716, over 7325.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3111, pruned_loss=0.07075, over 1019180.19 frames.], batch size: 22, lr: 1.21e-03
+2022-04-28 15:21:29,010 INFO [train.py:763] (2/8) Epoch 5, batch 300, loss[loss=0.2114, simple_loss=0.3071, pruned_loss=0.05787, over 7231.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3096, pruned_loss=0.07035, over 1112382.66 frames.], batch size: 20, lr: 1.21e-03
+2022-04-28 15:22:35,195 INFO [train.py:763] (2/8) Epoch 5, batch 350, loss[loss=0.2098, simple_loss=0.2977, pruned_loss=0.06098, over 7324.00 frames.], tot_loss[loss=0.2239, simple_loss=0.308, pruned_loss=0.06989, over 1185284.68 frames.], batch size: 20, lr: 1.20e-03
+2022-04-28 15:23:40,933 INFO [train.py:763] (2/8) Epoch 5, batch 400, loss[loss=0.267, simple_loss=0.352, pruned_loss=0.09101, over 7380.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3109, pruned_loss=0.07124, over 1236869.90 frames.], batch size: 23, lr: 1.20e-03
+2022-04-28 15:24:46,895 INFO [train.py:763] (2/8) Epoch 5, batch 450, loss[loss=0.2258, simple_loss=0.2964, pruned_loss=0.07766, over 6816.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3108, pruned_loss=0.07094, over 1279683.62 frames.], batch size: 15, lr: 1.20e-03
+2022-04-28 15:25:52,436 INFO [train.py:763] (2/8) Epoch 5, batch 500, loss[loss=0.28, simple_loss=0.3484, pruned_loss=0.1058, over 4651.00 frames.], tot_loss[loss=0.226, simple_loss=0.3106, pruned_loss=0.0707, over 1308309.38 frames.], batch size: 52, lr: 1.20e-03
+2022-04-28 15:26:57,642 INFO [train.py:763] (2/8) Epoch 5, batch 550, loss[loss=0.2262, simple_loss=0.3191, pruned_loss=0.06666, over 6587.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3107, pruned_loss=0.07097, over 1332807.67 frames.], batch size: 38, lr: 1.20e-03
+2022-04-28 15:28:04,517 INFO [train.py:763] (2/8) Epoch 5, batch 600, loss[loss=0.2031, simple_loss=0.3022, pruned_loss=0.05198, over 7142.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3093, pruned_loss=0.07072, over 1352131.42 frames.], batch size: 20, lr: 1.20e-03
+2022-04-28 15:29:09,665 INFO [train.py:763] (2/8) Epoch 5, batch 650, loss[loss=0.185, simple_loss=0.2861, pruned_loss=0.04194, over 7421.00 frames.], tot_loss[loss=0.226, simple_loss=0.3099, pruned_loss=0.07099, over 1367014.32 frames.], batch size: 21, lr: 1.20e-03
+2022-04-28 15:30:15,009 INFO [train.py:763] (2/8) Epoch 5, batch 700, loss[loss=0.2153, simple_loss=0.293, pruned_loss=0.06877, over 6756.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3106, pruned_loss=0.07083, over 1378067.92 frames.], batch size: 15, lr: 1.20e-03
+2022-04-28 15:31:20,297 INFO [train.py:763] (2/8) Epoch 5, batch 750, loss[loss=0.2401, simple_loss=0.3267, pruned_loss=0.07676, over 7215.00 frames.], tot_loss[loss=0.227, simple_loss=0.3115, pruned_loss=0.07127, over 1387805.70 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:32:25,890 INFO [train.py:763] (2/8) Epoch 5, batch 800, loss[loss=0.1991, simple_loss=0.2893, pruned_loss=0.05446, over 7215.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3092, pruned_loss=0.0701, over 1398621.89 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:33:31,212 INFO [train.py:763] (2/8) Epoch 5, batch 850, loss[loss=0.2852, simple_loss=0.3738, pruned_loss=0.09829, over 7195.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3094, pruned_loss=0.06978, over 1404373.30 frames.], batch size: 23, lr: 1.19e-03
+2022-04-28 15:34:36,540 INFO [train.py:763] (2/8) Epoch 5, batch 900, loss[loss=0.2436, simple_loss=0.3343, pruned_loss=0.07642, over 7410.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3114, pruned_loss=0.07117, over 1406243.59 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:35:42,331 INFO [train.py:763] (2/8) Epoch 5, batch 950, loss[loss=0.2494, simple_loss=0.2979, pruned_loss=0.1005, over 7147.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3122, pruned_loss=0.07171, over 1406158.96 frames.], batch size: 17, lr: 1.19e-03
+2022-04-28 15:36:47,761 INFO [train.py:763] (2/8) Epoch 5, batch 1000, loss[loss=0.2112, simple_loss=0.3048, pruned_loss=0.05876, over 7420.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3117, pruned_loss=0.07108, over 1408932.12 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:37:53,893 INFO [train.py:763] (2/8) Epoch 5, batch 1050, loss[loss=0.2293, simple_loss=0.3052, pruned_loss=0.07666, over 7320.00 frames.], tot_loss[loss=0.2262, simple_loss=0.3112, pruned_loss=0.07056, over 1413300.63 frames.], batch size: 20, lr: 1.19e-03
+2022-04-28 15:39:10,230 INFO [train.py:763] (2/8) Epoch 5, batch 1100, loss[loss=0.2186, simple_loss=0.3106, pruned_loss=0.06333, over 7316.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3116, pruned_loss=0.07077, over 1409046.27 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:40:16,760 INFO [train.py:763] (2/8) Epoch 5, batch 1150, loss[loss=0.1951, simple_loss=0.2944, pruned_loss=0.04797, over 7144.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3121, pruned_loss=0.0705, over 1413928.09 frames.], batch size: 20, lr: 1.19e-03
+2022-04-28 15:41:22,500 INFO [train.py:763] (2/8) Epoch 5, batch 1200, loss[loss=0.2426, simple_loss=0.3161, pruned_loss=0.08457, over 7196.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3109, pruned_loss=0.06995, over 1415022.86 frames.], batch size: 26, lr: 1.18e-03
+2022-04-28 15:42:28,996 INFO [train.py:763] (2/8) Epoch 5, batch 1250, loss[loss=0.25, simple_loss=0.3388, pruned_loss=0.08061, over 7149.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3097, pruned_loss=0.06993, over 1413905.18 frames.], batch size: 20, lr: 1.18e-03
+2022-04-28 15:43:35,956 INFO [train.py:763] (2/8) Epoch 5, batch 1300, loss[loss=0.261, simple_loss=0.3305, pruned_loss=0.09573, over 7354.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3102, pruned_loss=0.07118, over 1412251.93 frames.], batch size: 19, lr: 1.18e-03
+2022-04-28 15:44:42,292 INFO [train.py:763] (2/8) Epoch 5, batch 1350, loss[loss=0.2521, simple_loss=0.3389, pruned_loss=0.08259, over 7070.00 frames.], tot_loss[loss=0.2255, simple_loss=0.3095, pruned_loss=0.07075, over 1415076.63 frames.], batch size: 28, lr: 1.18e-03
+2022-04-28 15:45:48,503 INFO [train.py:763] (2/8) Epoch 5, batch 1400, loss[loss=0.2299, simple_loss=0.3183, pruned_loss=0.07071, over 7323.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3092, pruned_loss=0.07027, over 1419034.91 frames.], batch size: 20, lr: 1.18e-03
+2022-04-28 15:46:53,763 INFO [train.py:763] (2/8) Epoch 5, batch 1450, loss[loss=0.2213, simple_loss=0.3189, pruned_loss=0.06188, over 7424.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3091, pruned_loss=0.07011, over 1420877.80 frames.], batch size: 20, lr: 1.18e-03
+2022-04-28 15:47:59,046 INFO [train.py:763] (2/8) Epoch 5, batch 1500, loss[loss=0.2148, simple_loss=0.3073, pruned_loss=0.06113, over 7140.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3092, pruned_loss=0.0701, over 1421288.16 frames.], batch size: 20, lr: 1.18e-03
+2022-04-28 15:49:04,606 INFO [train.py:763] (2/8) Epoch 5, batch 1550, loss[loss=0.1907, simple_loss=0.2772, pruned_loss=0.05215, over 7284.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3091, pruned_loss=0.0699, over 1423346.32 frames.], batch size: 17, lr: 1.18e-03
+2022-04-28 15:50:09,898 INFO [train.py:763] (2/8) Epoch 5, batch 1600, loss[loss=0.2025, simple_loss=0.296, pruned_loss=0.05456, over 7435.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3091, pruned_loss=0.07011, over 1416877.73 frames.], batch size: 20, lr: 1.17e-03
+2022-04-28 15:51:15,386 INFO [train.py:763] (2/8) Epoch 5, batch 1650, loss[loss=0.2477, simple_loss=0.3308, pruned_loss=0.08231, over 7314.00 frames.], tot_loss[loss=0.2247, simple_loss=0.309, pruned_loss=0.07017, over 1416515.95 frames.], batch size: 25, lr: 1.17e-03
+2022-04-28 15:52:21,474 INFO [train.py:763] (2/8) Epoch 5, batch 1700, loss[loss=0.2432, simple_loss=0.3201, pruned_loss=0.08315, over 7200.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3096, pruned_loss=0.0705, over 1414629.62 frames.], batch size: 22, lr: 1.17e-03
+2022-04-28 15:53:26,972 INFO [train.py:763] (2/8) Epoch 5, batch 1750, loss[loss=0.2219, simple_loss=0.301, pruned_loss=0.07137, over 7269.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3097, pruned_loss=0.07076, over 1411386.21 frames.], batch size: 18, lr: 1.17e-03
+2022-04-28 15:54:32,245 INFO [train.py:763] (2/8) Epoch 5, batch 1800, loss[loss=0.2754, simple_loss=0.3434, pruned_loss=0.1037, over 4710.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3096, pruned_loss=0.07017, over 1413033.91 frames.], batch size: 53, lr: 1.17e-03
+2022-04-28 15:55:37,876 INFO [train.py:763] (2/8) Epoch 5, batch 1850, loss[loss=0.1936, simple_loss=0.2767, pruned_loss=0.05519, over 7169.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3098, pruned_loss=0.07072, over 1416489.50 frames.], batch size: 18, lr: 1.17e-03
+2022-04-28 15:56:43,237 INFO [train.py:763] (2/8) Epoch 5, batch 1900, loss[loss=0.194, simple_loss=0.2711, pruned_loss=0.05852, over 7135.00 frames.], tot_loss[loss=0.2248, simple_loss=0.309, pruned_loss=0.0703, over 1416027.50 frames.], batch size: 17, lr: 1.17e-03
+2022-04-28 15:57:48,603 INFO [train.py:763] (2/8) Epoch 5, batch 1950, loss[loss=0.2536, simple_loss=0.335, pruned_loss=0.08609, over 7133.00 frames.], tot_loss[loss=0.2253, simple_loss=0.31, pruned_loss=0.07026, over 1420483.64 frames.], batch size: 21, lr: 1.17e-03
+2022-04-28 15:58:54,741 INFO [train.py:763] (2/8) Epoch 5, batch 2000, loss[loss=0.2124, simple_loss=0.2953, pruned_loss=0.06472, over 7283.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3097, pruned_loss=0.07022, over 1423756.96 frames.], batch size: 18, lr: 1.17e-03
+2022-04-28 15:59:59,952 INFO [train.py:763] (2/8) Epoch 5, batch 2050, loss[loss=0.2481, simple_loss=0.3326, pruned_loss=0.08183, over 7101.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3109, pruned_loss=0.07086, over 1423858.03 frames.], batch size: 28, lr: 1.16e-03
+2022-04-28 16:01:06,582 INFO [train.py:763] (2/8) Epoch 5, batch 2100, loss[loss=0.2136, simple_loss=0.3077, pruned_loss=0.05974, over 6216.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3112, pruned_loss=0.07112, over 1425504.34 frames.], batch size: 37, lr: 1.16e-03
+2022-04-28 16:02:12,116 INFO [train.py:763] (2/8) Epoch 5, batch 2150, loss[loss=0.1988, simple_loss=0.296, pruned_loss=0.05078, over 7140.00 frames.], tot_loss[loss=0.2255, simple_loss=0.3104, pruned_loss=0.07025, over 1430300.77 frames.], batch size: 20, lr: 1.16e-03
+2022-04-28 16:03:17,456 INFO [train.py:763] (2/8) Epoch 5, batch 2200, loss[loss=0.2254, simple_loss=0.3118, pruned_loss=0.0695, over 7148.00 frames.], tot_loss[loss=0.2241, simple_loss=0.3088, pruned_loss=0.06964, over 1427423.53 frames.], batch size: 20, lr: 1.16e-03
+2022-04-28 16:04:22,912 INFO [train.py:763] (2/8) Epoch 5, batch 2250, loss[loss=0.2046, simple_loss=0.289, pruned_loss=0.06004, over 7358.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3092, pruned_loss=0.07017, over 1426048.70 frames.], batch size: 19, lr: 1.16e-03
+2022-04-28 16:05:29,056 INFO [train.py:763] (2/8) Epoch 5, batch 2300, loss[loss=0.2427, simple_loss=0.3327, pruned_loss=0.0763, over 7294.00 frames.], tot_loss[loss=0.2248, simple_loss=0.309, pruned_loss=0.07028, over 1422835.74 frames.], batch size: 24, lr: 1.16e-03
+2022-04-28 16:06:35,241 INFO [train.py:763] (2/8) Epoch 5, batch 2350, loss[loss=0.246, simple_loss=0.338, pruned_loss=0.07704, over 7205.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3077, pruned_loss=0.06954, over 1421831.88 frames.], batch size: 21, lr: 1.16e-03
+2022-04-28 16:07:41,474 INFO [train.py:763] (2/8) Epoch 5, batch 2400, loss[loss=0.2316, simple_loss=0.3163, pruned_loss=0.07345, over 7313.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3075, pruned_loss=0.0695, over 1422022.74 frames.], batch size: 20, lr: 1.16e-03
+2022-04-28 16:08:47,664 INFO [train.py:763] (2/8) Epoch 5, batch 2450, loss[loss=0.2089, simple_loss=0.2808, pruned_loss=0.06853, over 6832.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3071, pruned_loss=0.06896, over 1421355.56 frames.], batch size: 15, lr: 1.16e-03
+2022-04-28 16:09:52,912 INFO [train.py:763] (2/8) Epoch 5, batch 2500, loss[loss=0.2355, simple_loss=0.3212, pruned_loss=0.07489, over 7340.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3077, pruned_loss=0.06886, over 1420513.03 frames.], batch size: 22, lr: 1.15e-03
+2022-04-28 16:10:59,312 INFO [train.py:763] (2/8) Epoch 5, batch 2550, loss[loss=0.1805, simple_loss=0.2618, pruned_loss=0.0496, over 6871.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3077, pruned_loss=0.06881, over 1422669.83 frames.], batch size: 15, lr: 1.15e-03
+2022-04-28 16:12:05,353 INFO [train.py:763] (2/8) Epoch 5, batch 2600, loss[loss=0.2469, simple_loss=0.344, pruned_loss=0.07494, over 7316.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3085, pruned_loss=0.06919, over 1425585.02 frames.], batch size: 21, lr: 1.15e-03
+2022-04-28 16:13:10,876 INFO [train.py:763] (2/8) Epoch 5, batch 2650, loss[loss=0.2114, simple_loss=0.314, pruned_loss=0.0544, over 7320.00 frames.], tot_loss[loss=0.2241, simple_loss=0.3091, pruned_loss=0.06957, over 1423437.73 frames.], batch size: 25, lr: 1.15e-03
+2022-04-28 16:14:16,437 INFO [train.py:763] (2/8) Epoch 5, batch 2700, loss[loss=0.1993, simple_loss=0.2823, pruned_loss=0.05816, over 6798.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3081, pruned_loss=0.06864, over 1425538.91 frames.], batch size: 15, lr: 1.15e-03
+2022-04-28 16:15:15,065 INFO [train.py:763] (2/8) Epoch 5, batch 2750, loss[loss=0.2417, simple_loss=0.3284, pruned_loss=0.07754, over 7234.00 frames.], tot_loss[loss=0.2223, simple_loss=0.3083, pruned_loss=0.06818, over 1423436.24 frames.], batch size: 20, lr: 1.15e-03
+2022-04-28 16:16:11,914 INFO [train.py:763] (2/8) Epoch 5, batch 2800, loss[loss=0.1771, simple_loss=0.2712, pruned_loss=0.04155, over 7273.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3083, pruned_loss=0.06853, over 1421366.99 frames.], batch size: 18, lr: 1.15e-03
+2022-04-28 16:17:08,596 INFO [train.py:763] (2/8) Epoch 5, batch 2850, loss[loss=0.2101, simple_loss=0.275, pruned_loss=0.07264, over 7276.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3081, pruned_loss=0.0686, over 1418383.40 frames.], batch size: 17, lr: 1.15e-03
+2022-04-28 16:18:06,395 INFO [train.py:763] (2/8) Epoch 5, batch 2900, loss[loss=0.2307, simple_loss=0.3189, pruned_loss=0.07125, over 6795.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3079, pruned_loss=0.06861, over 1420855.80 frames.], batch size: 31, lr: 1.15e-03
+2022-04-28 16:19:04,267 INFO [train.py:763] (2/8) Epoch 5, batch 2950, loss[loss=0.1916, simple_loss=0.2996, pruned_loss=0.04184, over 7147.00 frames.], tot_loss[loss=0.2227, simple_loss=0.308, pruned_loss=0.06865, over 1420808.55 frames.], batch size: 20, lr: 1.14e-03
+2022-04-28 16:19:58,109 INFO [train.py:763] (2/8) Epoch 5, batch 3000, loss[loss=0.2716, simple_loss=0.346, pruned_loss=0.09862, over 7229.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3091, pruned_loss=0.06928, over 1419577.73 frames.], batch size: 20, lr: 1.14e-03
+2022-04-28 16:19:58,110 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-28 16:20:13,356 INFO [train.py:792] (2/8) Epoch 5, validation: loss=0.1791, simple_loss=0.2847, pruned_loss=0.03677, over 698248.00 frames.
+2022-04-28 16:21:19,338 INFO [train.py:763] (2/8) Epoch 5, batch 3050, loss[loss=0.2295, simple_loss=0.3192, pruned_loss=0.06993, over 7194.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3078, pruned_loss=0.06826, over 1425758.84 frames.], batch size: 23, lr: 1.14e-03
+2022-04-28 16:22:24,936 INFO [train.py:763] (2/8) Epoch 5, batch 3100, loss[loss=0.193, simple_loss=0.2893, pruned_loss=0.04837, over 7335.00 frames.], tot_loss[loss=0.2212, simple_loss=0.3069, pruned_loss=0.06781, over 1423963.43 frames.], batch size: 22, lr: 1.14e-03
+2022-04-28 16:23:30,170 INFO [train.py:763] (2/8) Epoch 5, batch 3150, loss[loss=0.246, simple_loss=0.3282, pruned_loss=0.08194, over 7190.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3072, pruned_loss=0.06788, over 1424008.31 frames.], batch size: 23, lr: 1.14e-03
+2022-04-28 16:24:36,696 INFO [train.py:763] (2/8) Epoch 5, batch 3200, loss[loss=0.2464, simple_loss=0.3288, pruned_loss=0.08199, over 7229.00 frames.], tot_loss[loss=0.2223, simple_loss=0.3078, pruned_loss=0.06837, over 1424918.97 frames.], batch size: 21, lr: 1.14e-03
+2022-04-28 16:25:42,632 INFO [train.py:763] (2/8) Epoch 5, batch 3250, loss[loss=0.2386, simple_loss=0.317, pruned_loss=0.08011, over 7363.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3074, pruned_loss=0.06761, over 1425338.02 frames.], batch size: 19, lr: 1.14e-03
+2022-04-28 16:26:48,947 INFO [train.py:763] (2/8) Epoch 5, batch 3300, loss[loss=0.2361, simple_loss=0.3245, pruned_loss=0.07381, over 7202.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3087, pruned_loss=0.06814, over 1420913.98 frames.], batch size: 23, lr: 1.14e-03
+2022-04-28 16:27:54,257 INFO [train.py:763] (2/8) Epoch 5, batch 3350, loss[loss=0.1861, simple_loss=0.2835, pruned_loss=0.04433, over 7249.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3083, pruned_loss=0.0682, over 1425650.87 frames.], batch size: 19, lr: 1.14e-03
+2022-04-28 16:28:59,511 INFO [train.py:763] (2/8) Epoch 5, batch 3400, loss[loss=0.215, simple_loss=0.3025, pruned_loss=0.06374, over 7304.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3082, pruned_loss=0.06831, over 1425354.50 frames.], batch size: 24, lr: 1.14e-03
+2022-04-28 16:30:05,193 INFO [train.py:763] (2/8) Epoch 5, batch 3450, loss[loss=0.281, simple_loss=0.3555, pruned_loss=0.1032, over 7409.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3102, pruned_loss=0.06911, over 1427577.17 frames.], batch size: 21, lr: 1.13e-03
+2022-04-28 16:31:11,003 INFO [train.py:763] (2/8) Epoch 5, batch 3500, loss[loss=0.2489, simple_loss=0.3359, pruned_loss=0.08093, over 7207.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3086, pruned_loss=0.0689, over 1423961.98 frames.], batch size: 22, lr: 1.13e-03
+2022-04-28 16:32:16,129 INFO [train.py:763] (2/8) Epoch 5, batch 3550, loss[loss=0.2237, simple_loss=0.3052, pruned_loss=0.07109, over 7310.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3088, pruned_loss=0.06878, over 1426846.69 frames.], batch size: 21, lr: 1.13e-03
+2022-04-28 16:33:21,406 INFO [train.py:763] (2/8) Epoch 5, batch 3600, loss[loss=0.2234, simple_loss=0.2977, pruned_loss=0.0746, over 7163.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3079, pruned_loss=0.06856, over 1428072.78 frames.], batch size: 18, lr: 1.13e-03
+2022-04-28 16:34:27,110 INFO [train.py:763] (2/8) Epoch 5, batch 3650, loss[loss=0.2078, simple_loss=0.3004, pruned_loss=0.05762, over 7419.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3073, pruned_loss=0.06826, over 1427500.27 frames.], batch size: 21, lr: 1.13e-03
+2022-04-28 16:35:34,070 INFO [train.py:763] (2/8) Epoch 5, batch 3700, loss[loss=0.2248, simple_loss=0.3208, pruned_loss=0.06443, over 7237.00 frames.], tot_loss[loss=0.221, simple_loss=0.3065, pruned_loss=0.06773, over 1425431.93 frames.], batch size: 20, lr: 1.13e-03
+2022-04-28 16:36:39,370 INFO [train.py:763] (2/8) Epoch 5, batch 3750, loss[loss=0.2567, simple_loss=0.3301, pruned_loss=0.09166, over 7388.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3069, pruned_loss=0.06834, over 1423649.84 frames.], batch size: 23, lr: 1.13e-03
+2022-04-28 16:37:46,338 INFO [train.py:763] (2/8) Epoch 5, batch 3800, loss[loss=0.2306, simple_loss=0.3159, pruned_loss=0.07267, over 7233.00 frames.], tot_loss[loss=0.2217, simple_loss=0.3063, pruned_loss=0.06852, over 1418681.46 frames.], batch size: 20, lr: 1.13e-03
+2022-04-28 16:38:51,768 INFO [train.py:763] (2/8) Epoch 5, batch 3850, loss[loss=0.1965, simple_loss=0.2918, pruned_loss=0.05056, over 7422.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3073, pruned_loss=0.06857, over 1419471.45 frames.], batch size: 20, lr: 1.13e-03
+2022-04-28 16:39:57,098 INFO [train.py:763] (2/8) Epoch 5, batch 3900, loss[loss=0.2064, simple_loss=0.2852, pruned_loss=0.06382, over 7396.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3077, pruned_loss=0.06885, over 1424046.51 frames.], batch size: 18, lr: 1.13e-03
+2022-04-28 16:41:04,041 INFO [train.py:763] (2/8) Epoch 5, batch 3950, loss[loss=0.2553, simple_loss=0.3494, pruned_loss=0.08062, over 7293.00 frames.], tot_loss[loss=0.221, simple_loss=0.3063, pruned_loss=0.06781, over 1423747.56 frames.], batch size: 24, lr: 1.12e-03
+2022-04-28 16:42:10,954 INFO [train.py:763] (2/8) Epoch 5, batch 4000, loss[loss=0.2439, simple_loss=0.3202, pruned_loss=0.08376, over 7185.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3061, pruned_loss=0.06748, over 1426683.18 frames.], batch size: 23, lr: 1.12e-03
+2022-04-28 16:43:18,247 INFO [train.py:763] (2/8) Epoch 5, batch 4050, loss[loss=0.234, simple_loss=0.3198, pruned_loss=0.07406, over 7288.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3063, pruned_loss=0.06734, over 1427600.33 frames.], batch size: 24, lr: 1.12e-03
+2022-04-28 16:44:25,533 INFO [train.py:763] (2/8) Epoch 5, batch 4100, loss[loss=0.2469, simple_loss=0.3106, pruned_loss=0.09159, over 7404.00 frames.], tot_loss[loss=0.22, simple_loss=0.3053, pruned_loss=0.06736, over 1427625.21 frames.], batch size: 18, lr: 1.12e-03
+2022-04-28 16:45:32,375 INFO [train.py:763] (2/8) Epoch 5, batch 4150, loss[loss=0.2185, simple_loss=0.3134, pruned_loss=0.06178, over 6757.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3047, pruned_loss=0.06709, over 1426758.82 frames.], batch size: 31, lr: 1.12e-03
+2022-04-28 16:46:39,132 INFO [train.py:763] (2/8) Epoch 5, batch 4200, loss[loss=0.2463, simple_loss=0.3273, pruned_loss=0.08265, over 7118.00 frames.], tot_loss[loss=0.2193, simple_loss=0.3044, pruned_loss=0.06712, over 1428412.61 frames.], batch size: 21, lr: 1.12e-03
+2022-04-28 16:47:45,469 INFO [train.py:763] (2/8) Epoch 5, batch 4250, loss[loss=0.2477, simple_loss=0.3298, pruned_loss=0.08283, over 7375.00 frames.], tot_loss[loss=0.2208, simple_loss=0.3056, pruned_loss=0.06795, over 1428515.41 frames.], batch size: 23, lr: 1.12e-03
+2022-04-28 16:48:52,194 INFO [train.py:763] (2/8) Epoch 5, batch 4300, loss[loss=0.1981, simple_loss=0.2874, pruned_loss=0.05438, over 7062.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3052, pruned_loss=0.06777, over 1423641.48 frames.], batch size: 18, lr: 1.12e-03
+2022-04-28 16:49:59,886 INFO [train.py:763] (2/8) Epoch 5, batch 4350, loss[loss=0.2126, simple_loss=0.3026, pruned_loss=0.06127, over 7225.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3055, pruned_loss=0.06818, over 1424193.38 frames.], batch size: 21, lr: 1.12e-03
+2022-04-28 16:51:07,553 INFO [train.py:763] (2/8) Epoch 5, batch 4400, loss[loss=0.1883, simple_loss=0.2806, pruned_loss=0.04803, over 7423.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3046, pruned_loss=0.06793, over 1422291.29 frames.], batch size: 20, lr: 1.12e-03
+2022-04-28 16:52:13,247 INFO [train.py:763] (2/8) Epoch 5, batch 4450, loss[loss=0.1916, simple_loss=0.2751, pruned_loss=0.054, over 7275.00 frames.], tot_loss[loss=0.22, simple_loss=0.304, pruned_loss=0.068, over 1407683.47 frames.], batch size: 17, lr: 1.11e-03
+2022-04-28 16:53:19,248 INFO [train.py:763] (2/8) Epoch 5, batch 4500, loss[loss=0.2214, simple_loss=0.3152, pruned_loss=0.06379, over 7228.00 frames.], tot_loss[loss=0.2183, simple_loss=0.302, pruned_loss=0.06731, over 1406761.66 frames.], batch size: 20, lr: 1.11e-03
+2022-04-28 16:54:23,898 INFO [train.py:763] (2/8) Epoch 5, batch 4550, loss[loss=0.2862, simple_loss=0.3622, pruned_loss=0.1051, over 5152.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3053, pruned_loss=0.07022, over 1356952.16 frames.], batch size: 52, lr: 1.11e-03
+2022-04-28 16:55:51,897 INFO [train.py:763] (2/8) Epoch 6, batch 0, loss[loss=0.2101, simple_loss=0.2883, pruned_loss=0.06599, over 7416.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2883, pruned_loss=0.06599, over 7416.00 frames.], batch size: 18, lr: 1.07e-03
+2022-04-28 16:56:58,093 INFO [train.py:763] (2/8) Epoch 6, batch 50, loss[loss=0.1823, simple_loss=0.2637, pruned_loss=0.05051, over 7400.00 frames.], tot_loss[loss=0.2125, simple_loss=0.2987, pruned_loss=0.06318, over 322815.50 frames.], batch size: 18, lr: 1.07e-03
+2022-04-28 16:58:04,025 INFO [train.py:763] (2/8) Epoch 6, batch 100, loss[loss=0.1803, simple_loss=0.278, pruned_loss=0.04135, over 7150.00 frames.], tot_loss[loss=0.2116, simple_loss=0.2992, pruned_loss=0.06206, over 568076.77 frames.], batch size: 19, lr: 1.06e-03
+2022-04-28 16:59:09,767 INFO [train.py:763] (2/8) Epoch 6, batch 150, loss[loss=0.2061, simple_loss=0.2981, pruned_loss=0.05702, over 7147.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3024, pruned_loss=0.06405, over 757943.75 frames.], batch size: 19, lr: 1.06e-03
+2022-04-28 17:00:15,498 INFO [train.py:763] (2/8) Epoch 6, batch 200, loss[loss=0.2443, simple_loss=0.3357, pruned_loss=0.07647, over 7375.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3028, pruned_loss=0.06316, over 906405.67 frames.], batch size: 23, lr: 1.06e-03
+2022-04-28 17:01:29,826 INFO [train.py:763] (2/8) Epoch 6, batch 250, loss[loss=0.1994, simple_loss=0.3051, pruned_loss=0.04687, over 7149.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3024, pruned_loss=0.06325, over 1020693.78 frames.], batch size: 20, lr: 1.06e-03
+2022-04-28 17:02:45,512 INFO [train.py:763] (2/8) Epoch 6, batch 300, loss[loss=0.182, simple_loss=0.2604, pruned_loss=0.05181, over 6820.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3037, pruned_loss=0.06484, over 1106789.49 frames.], batch size: 15, lr: 1.06e-03
+2022-04-28 17:03:59,803 INFO [train.py:763] (2/8) Epoch 6, batch 350, loss[loss=0.1865, simple_loss=0.2853, pruned_loss=0.04383, over 7118.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3028, pruned_loss=0.06441, over 1177047.43 frames.], batch size: 21, lr: 1.06e-03
+2022-04-28 17:05:05,096 INFO [train.py:763] (2/8) Epoch 6, batch 400, loss[loss=0.2195, simple_loss=0.2999, pruned_loss=0.06953, over 7169.00 frames.], tot_loss[loss=0.2169, simple_loss=0.3038, pruned_loss=0.06497, over 1229882.45 frames.], batch size: 18, lr: 1.06e-03
+2022-04-28 17:06:20,537 INFO [train.py:763] (2/8) Epoch 6, batch 450, loss[loss=0.2009, simple_loss=0.2827, pruned_loss=0.05953, over 7370.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3038, pruned_loss=0.0649, over 1275641.13 frames.], batch size: 19, lr: 1.06e-03
+2022-04-28 17:07:44,114 INFO [train.py:763] (2/8) Epoch 6, batch 500, loss[loss=0.1985, simple_loss=0.2852, pruned_loss=0.05588, over 6197.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3044, pruned_loss=0.065, over 1304927.12 frames.], batch size: 37, lr: 1.06e-03
+2022-04-28 17:08:59,112 INFO [train.py:763] (2/8) Epoch 6, batch 550, loss[loss=0.2237, simple_loss=0.3261, pruned_loss=0.06063, over 7125.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3029, pruned_loss=0.06397, over 1330268.84 frames.], batch size: 21, lr: 1.06e-03
+2022-04-28 17:10:13,641 INFO [train.py:763] (2/8) Epoch 6, batch 600, loss[loss=0.2514, simple_loss=0.3334, pruned_loss=0.08473, over 7058.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3044, pruned_loss=0.06456, over 1348650.42 frames.], batch size: 28, lr: 1.06e-03
+2022-04-28 17:11:19,489 INFO [train.py:763] (2/8) Epoch 6, batch 650, loss[loss=0.2963, simple_loss=0.3545, pruned_loss=0.119, over 4714.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3038, pruned_loss=0.06446, over 1364583.71 frames.], batch size: 53, lr: 1.05e-03
+2022-04-28 17:12:25,176 INFO [train.py:763] (2/8) Epoch 6, batch 700, loss[loss=0.2227, simple_loss=0.3056, pruned_loss=0.0699, over 7160.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3021, pruned_loss=0.06374, over 1378149.32 frames.], batch size: 18, lr: 1.05e-03
+2022-04-28 17:13:31,496 INFO [train.py:763] (2/8) Epoch 6, batch 750, loss[loss=0.2332, simple_loss=0.3167, pruned_loss=0.07486, over 6738.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3022, pruned_loss=0.06382, over 1390598.15 frames.], batch size: 31, lr: 1.05e-03
+2022-04-28 17:14:37,092 INFO [train.py:763] (2/8) Epoch 6, batch 800, loss[loss=0.2526, simple_loss=0.3386, pruned_loss=0.08334, over 7333.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3029, pruned_loss=0.06459, over 1391910.38 frames.], batch size: 20, lr: 1.05e-03
+2022-04-28 17:15:43,491 INFO [train.py:763] (2/8) Epoch 6, batch 850, loss[loss=0.2009, simple_loss=0.2921, pruned_loss=0.05481, over 7291.00 frames.], tot_loss[loss=0.2161, simple_loss=0.303, pruned_loss=0.06462, over 1398627.47 frames.], batch size: 24, lr: 1.05e-03
+2022-04-28 17:16:48,950 INFO [train.py:763] (2/8) Epoch 6, batch 900, loss[loss=0.2349, simple_loss=0.3271, pruned_loss=0.07134, over 7381.00 frames.], tot_loss[loss=0.216, simple_loss=0.303, pruned_loss=0.0645, over 1404057.45 frames.], batch size: 23, lr: 1.05e-03
+2022-04-28 17:17:54,043 INFO [train.py:763] (2/8) Epoch 6, batch 950, loss[loss=0.2635, simple_loss=0.3626, pruned_loss=0.08216, over 7390.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3037, pruned_loss=0.06481, over 1408216.92 frames.], batch size: 23, lr: 1.05e-03
+2022-04-28 17:18:59,561 INFO [train.py:763] (2/8) Epoch 6, batch 1000, loss[loss=0.2278, simple_loss=0.3174, pruned_loss=0.06914, over 7371.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3037, pruned_loss=0.06523, over 1410128.80 frames.], batch size: 23, lr: 1.05e-03
+2022-04-28 17:20:06,060 INFO [train.py:763] (2/8) Epoch 6, batch 1050, loss[loss=0.2174, simple_loss=0.3071, pruned_loss=0.06386, over 7157.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3039, pruned_loss=0.06452, over 1417069.22 frames.], batch size: 19, lr: 1.05e-03
+2022-04-28 17:21:12,149 INFO [train.py:763] (2/8) Epoch 6, batch 1100, loss[loss=0.2405, simple_loss=0.3302, pruned_loss=0.07539, over 7253.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3033, pruned_loss=0.06426, over 1420232.78 frames.], batch size: 25, lr: 1.05e-03
+2022-04-28 17:22:18,728 INFO [train.py:763] (2/8) Epoch 6, batch 1150, loss[loss=0.1916, simple_loss=0.2724, pruned_loss=0.05536, over 7136.00 frames.], tot_loss[loss=0.215, simple_loss=0.3026, pruned_loss=0.06368, over 1418942.43 frames.], batch size: 17, lr: 1.05e-03
+2022-04-28 17:23:26,111 INFO [train.py:763] (2/8) Epoch 6, batch 1200, loss[loss=0.2022, simple_loss=0.2791, pruned_loss=0.06264, over 6841.00 frames.], tot_loss[loss=0.2159, simple_loss=0.303, pruned_loss=0.06438, over 1412898.13 frames.], batch size: 15, lr: 1.04e-03
+2022-04-28 17:24:33,314 INFO [train.py:763] (2/8) Epoch 6, batch 1250, loss[loss=0.2461, simple_loss=0.3288, pruned_loss=0.08176, over 7234.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3025, pruned_loss=0.06435, over 1415950.22 frames.], batch size: 20, lr: 1.04e-03
+2022-04-28 17:25:39,226 INFO [train.py:763] (2/8) Epoch 6, batch 1300, loss[loss=0.2113, simple_loss=0.2833, pruned_loss=0.06963, over 7286.00 frames.], tot_loss[loss=0.2152, simple_loss=0.302, pruned_loss=0.0642, over 1416955.20 frames.], batch size: 17, lr: 1.04e-03
+2022-04-28 17:26:44,442 INFO [train.py:763] (2/8) Epoch 6, batch 1350, loss[loss=0.2139, simple_loss=0.3069, pruned_loss=0.06044, over 7418.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3021, pruned_loss=0.06412, over 1421801.61 frames.], batch size: 21, lr: 1.04e-03
+2022-04-28 17:27:49,616 INFO [train.py:763] (2/8) Epoch 6, batch 1400, loss[loss=0.208, simple_loss=0.2967, pruned_loss=0.05964, over 7158.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3026, pruned_loss=0.06433, over 1419701.06 frames.], batch size: 19, lr: 1.04e-03
+2022-04-28 17:28:55,362 INFO [train.py:763] (2/8) Epoch 6, batch 1450, loss[loss=0.2117, simple_loss=0.3058, pruned_loss=0.05884, over 6669.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3024, pruned_loss=0.06408, over 1420172.91 frames.], batch size: 31, lr: 1.04e-03
+2022-04-28 17:30:00,746 INFO [train.py:763] (2/8) Epoch 6, batch 1500, loss[loss=0.2221, simple_loss=0.3157, pruned_loss=0.06427, over 7417.00 frames.], tot_loss[loss=0.2146, simple_loss=0.302, pruned_loss=0.06354, over 1423407.82 frames.], batch size: 21, lr: 1.04e-03
+2022-04-28 17:31:05,970 INFO [train.py:763] (2/8) Epoch 6, batch 1550, loss[loss=0.265, simple_loss=0.3573, pruned_loss=0.08633, over 7152.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3028, pruned_loss=0.06387, over 1417818.13 frames.], batch size: 26, lr: 1.04e-03
+2022-04-28 17:32:11,538 INFO [train.py:763] (2/8) Epoch 6, batch 1600, loss[loss=0.2054, simple_loss=0.2989, pruned_loss=0.05597, over 7122.00 frames.], tot_loss[loss=0.2144, simple_loss=0.302, pruned_loss=0.0634, over 1424287.65 frames.], batch size: 21, lr: 1.04e-03
+2022-04-28 17:33:16,935 INFO [train.py:763] (2/8) Epoch 6, batch 1650, loss[loss=0.1765, simple_loss=0.2662, pruned_loss=0.04341, over 7069.00 frames.], tot_loss[loss=0.2141, simple_loss=0.3015, pruned_loss=0.06334, over 1418245.98 frames.], batch size: 18, lr: 1.04e-03
+2022-04-28 17:34:24,083 INFO [train.py:763] (2/8) Epoch 6, batch 1700, loss[loss=0.2092, simple_loss=0.3112, pruned_loss=0.05365, over 7206.00 frames.], tot_loss[loss=0.2138, simple_loss=0.301, pruned_loss=0.06326, over 1417628.83 frames.], batch size: 22, lr: 1.04e-03
+2022-04-28 17:35:30,119 INFO [train.py:763] (2/8) Epoch 6, batch 1750, loss[loss=0.2377, simple_loss=0.3343, pruned_loss=0.0705, over 7341.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3016, pruned_loss=0.06374, over 1413085.04 frames.], batch size: 22, lr: 1.04e-03
+2022-04-28 17:36:35,223 INFO [train.py:763] (2/8) Epoch 6, batch 1800, loss[loss=0.2324, simple_loss=0.3184, pruned_loss=0.07319, over 7318.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3028, pruned_loss=0.06391, over 1415622.73 frames.], batch size: 25, lr: 1.03e-03
+2022-04-28 17:37:41,009 INFO [train.py:763] (2/8) Epoch 6, batch 1850, loss[loss=0.2016, simple_loss=0.281, pruned_loss=0.06108, over 6983.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3027, pruned_loss=0.06399, over 1417510.91 frames.], batch size: 16, lr: 1.03e-03
+2022-04-28 17:38:46,197 INFO [train.py:763] (2/8) Epoch 6, batch 1900, loss[loss=0.2212, simple_loss=0.3039, pruned_loss=0.06927, over 7061.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3018, pruned_loss=0.0636, over 1414247.09 frames.], batch size: 18, lr: 1.03e-03
+2022-04-28 17:39:52,666 INFO [train.py:763] (2/8) Epoch 6, batch 1950, loss[loss=0.2474, simple_loss=0.3221, pruned_loss=0.08632, over 7290.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3018, pruned_loss=0.06431, over 1417397.99 frames.], batch size: 18, lr: 1.03e-03
+2022-04-28 17:40:59,180 INFO [train.py:763] (2/8) Epoch 6, batch 2000, loss[loss=0.2343, simple_loss=0.3231, pruned_loss=0.0727, over 7310.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3019, pruned_loss=0.06423, over 1418097.22 frames.], batch size: 25, lr: 1.03e-03
+2022-04-28 17:42:06,054 INFO [train.py:763] (2/8) Epoch 6, batch 2050, loss[loss=0.2534, simple_loss=0.3379, pruned_loss=0.08447, over 7271.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3035, pruned_loss=0.06544, over 1415340.12 frames.], batch size: 24, lr: 1.03e-03
+2022-04-28 17:43:12,551 INFO [train.py:763] (2/8) Epoch 6, batch 2100, loss[loss=0.1931, simple_loss=0.2776, pruned_loss=0.05431, over 6991.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3029, pruned_loss=0.06524, over 1418303.25 frames.], batch size: 16, lr: 1.03e-03
+2022-04-28 17:44:19,358 INFO [train.py:763] (2/8) Epoch 6, batch 2150, loss[loss=0.218, simple_loss=0.3101, pruned_loss=0.06292, over 7399.00 frames.], tot_loss[loss=0.2169, simple_loss=0.3034, pruned_loss=0.06521, over 1423924.32 frames.], batch size: 21, lr: 1.03e-03
+2022-04-28 17:45:25,693 INFO [train.py:763] (2/8) Epoch 6, batch 2200, loss[loss=0.1901, simple_loss=0.2558, pruned_loss=0.0622, over 7131.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3032, pruned_loss=0.06489, over 1422389.30 frames.], batch size: 17, lr: 1.03e-03
+2022-04-28 17:46:32,096 INFO [train.py:763] (2/8) Epoch 6, batch 2250, loss[loss=0.2072, simple_loss=0.2807, pruned_loss=0.06685, over 7278.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3034, pruned_loss=0.06499, over 1417266.35 frames.], batch size: 17, lr: 1.03e-03
+2022-04-28 17:47:38,685 INFO [train.py:763] (2/8) Epoch 6, batch 2300, loss[loss=0.2264, simple_loss=0.3159, pruned_loss=0.06841, over 7211.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3035, pruned_loss=0.06533, over 1419884.48 frames.], batch size: 23, lr: 1.03e-03
+2022-04-28 17:48:44,942 INFO [train.py:763] (2/8) Epoch 6, batch 2350, loss[loss=0.2063, simple_loss=0.3042, pruned_loss=0.05416, over 7415.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3033, pruned_loss=0.06543, over 1417553.85 frames.], batch size: 21, lr: 1.02e-03
+2022-04-28 17:49:50,848 INFO [train.py:763] (2/8) Epoch 6, batch 2400, loss[loss=0.1672, simple_loss=0.2614, pruned_loss=0.03651, over 7270.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3023, pruned_loss=0.06456, over 1421758.47 frames.], batch size: 18, lr: 1.02e-03
+2022-04-28 17:50:56,967 INFO [train.py:763] (2/8) Epoch 6, batch 2450, loss[loss=0.2516, simple_loss=0.3392, pruned_loss=0.08202, over 7415.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3023, pruned_loss=0.06446, over 1417842.87 frames.], batch size: 21, lr: 1.02e-03
+2022-04-28 17:52:02,800 INFO [train.py:763] (2/8) Epoch 6, batch 2500, loss[loss=0.2474, simple_loss=0.3284, pruned_loss=0.08319, over 7325.00 frames.], tot_loss[loss=0.216, simple_loss=0.3026, pruned_loss=0.06468, over 1416825.95 frames.], batch size: 21, lr: 1.02e-03
+2022-04-28 17:53:08,640 INFO [train.py:763] (2/8) Epoch 6, batch 2550, loss[loss=0.2369, simple_loss=0.3188, pruned_loss=0.07744, over 7416.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3028, pruned_loss=0.06417, over 1423326.04 frames.], batch size: 20, lr: 1.02e-03
+2022-04-28 17:54:14,766 INFO [train.py:763] (2/8) Epoch 6, batch 2600, loss[loss=0.2074, simple_loss=0.2997, pruned_loss=0.05756, over 7170.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3029, pruned_loss=0.06436, over 1417922.42 frames.], batch size: 18, lr: 1.02e-03
+2022-04-28 17:55:21,044 INFO [train.py:763] (2/8) Epoch 6, batch 2650, loss[loss=0.2208, simple_loss=0.2943, pruned_loss=0.07363, over 7155.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3025, pruned_loss=0.06454, over 1417393.47 frames.], batch size: 18, lr: 1.02e-03
+2022-04-28 17:56:26,529 INFO [train.py:763] (2/8) Epoch 6, batch 2700, loss[loss=0.1877, simple_loss=0.2775, pruned_loss=0.04894, over 7194.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3028, pruned_loss=0.06437, over 1419532.31 frames.], batch size: 16, lr: 1.02e-03
+2022-04-28 17:57:32,627 INFO [train.py:763] (2/8) Epoch 6, batch 2750, loss[loss=0.1705, simple_loss=0.2612, pruned_loss=0.03984, over 7405.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3035, pruned_loss=0.06473, over 1419846.59 frames.], batch size: 18, lr: 1.02e-03
+2022-04-28 17:58:39,118 INFO [train.py:763] (2/8) Epoch 6, batch 2800, loss[loss=0.1828, simple_loss=0.2696, pruned_loss=0.04802, over 6981.00 frames.], tot_loss[loss=0.216, simple_loss=0.3029, pruned_loss=0.06461, over 1417971.14 frames.], batch size: 16, lr: 1.02e-03
+2022-04-28 17:59:46,047 INFO [train.py:763] (2/8) Epoch 6, batch 2850, loss[loss=0.2097, simple_loss=0.3109, pruned_loss=0.05425, over 7329.00 frames.], tot_loss[loss=0.2138, simple_loss=0.3008, pruned_loss=0.06341, over 1422486.14 frames.], batch size: 21, lr: 1.02e-03
+2022-04-28 18:00:52,206 INFO [train.py:763] (2/8) Epoch 6, batch 2900, loss[loss=0.2788, simple_loss=0.3403, pruned_loss=0.1087, over 4979.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3009, pruned_loss=0.06331, over 1424535.05 frames.], batch size: 52, lr: 1.02e-03
+2022-04-28 18:01:57,560 INFO [train.py:763] (2/8) Epoch 6, batch 2950, loss[loss=0.2083, simple_loss=0.3057, pruned_loss=0.05545, over 7294.00 frames.], tot_loss[loss=0.2151, simple_loss=0.3025, pruned_loss=0.06386, over 1424736.01 frames.], batch size: 25, lr: 1.01e-03
+2022-04-28 18:03:03,518 INFO [train.py:763] (2/8) Epoch 6, batch 3000, loss[loss=0.2564, simple_loss=0.3321, pruned_loss=0.09028, over 7166.00 frames.], tot_loss[loss=0.2162, simple_loss=0.3032, pruned_loss=0.06458, over 1426490.73 frames.], batch size: 26, lr: 1.01e-03
+2022-04-28 18:03:03,519 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-28 18:03:18,818 INFO [train.py:792] (2/8) Epoch 6, validation: loss=0.1749, simple_loss=0.2793, pruned_loss=0.03525, over 698248.00 frames.
+2022-04-28 18:04:24,347 INFO [train.py:763] (2/8) Epoch 6, batch 3050, loss[loss=0.2408, simple_loss=0.3231, pruned_loss=0.07927, over 7142.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3034, pruned_loss=0.06475, over 1426668.20 frames.], batch size: 26, lr: 1.01e-03
+2022-04-28 18:05:30,257 INFO [train.py:763] (2/8) Epoch 6, batch 3100, loss[loss=0.2302, simple_loss=0.3197, pruned_loss=0.07039, over 7162.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3031, pruned_loss=0.06425, over 1424044.84 frames.], batch size: 26, lr: 1.01e-03
+2022-04-28 18:06:36,927 INFO [train.py:763] (2/8) Epoch 6, batch 3150, loss[loss=0.2141, simple_loss=0.2937, pruned_loss=0.06728, over 7062.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3029, pruned_loss=0.06398, over 1427219.92 frames.], batch size: 28, lr: 1.01e-03
+2022-04-28 18:07:42,730 INFO [train.py:763] (2/8) Epoch 6, batch 3200, loss[loss=0.2487, simple_loss=0.3374, pruned_loss=0.07996, over 7342.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3029, pruned_loss=0.06385, over 1423446.34 frames.], batch size: 22, lr: 1.01e-03
+2022-04-28 18:08:48,606 INFO [train.py:763] (2/8) Epoch 6, batch 3250, loss[loss=0.2979, simple_loss=0.3686, pruned_loss=0.1135, over 7067.00 frames.], tot_loss[loss=0.215, simple_loss=0.3023, pruned_loss=0.06385, over 1423092.16 frames.], batch size: 28, lr: 1.01e-03
+2022-04-28 18:09:54,854 INFO [train.py:763] (2/8) Epoch 6, batch 3300, loss[loss=0.1908, simple_loss=0.3006, pruned_loss=0.04048, over 7154.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3037, pruned_loss=0.06389, over 1418984.89 frames.], batch size: 20, lr: 1.01e-03
+2022-04-28 18:11:00,639 INFO [train.py:763] (2/8) Epoch 6, batch 3350, loss[loss=0.2144, simple_loss=0.2995, pruned_loss=0.06464, over 7169.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3044, pruned_loss=0.06437, over 1420291.36 frames.], batch size: 19, lr: 1.01e-03
+2022-04-28 18:12:05,973 INFO [train.py:763] (2/8) Epoch 6, batch 3400, loss[loss=0.2468, simple_loss=0.3309, pruned_loss=0.08133, over 7112.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3045, pruned_loss=0.06431, over 1422772.03 frames.], batch size: 21, lr: 1.01e-03
+2022-04-28 18:13:11,469 INFO [train.py:763] (2/8) Epoch 6, batch 3450, loss[loss=0.2204, simple_loss=0.3279, pruned_loss=0.05647, over 7281.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3037, pruned_loss=0.06364, over 1420768.99 frames.], batch size: 24, lr: 1.01e-03
+2022-04-28 18:14:16,738 INFO [train.py:763] (2/8) Epoch 6, batch 3500, loss[loss=0.2222, simple_loss=0.3144, pruned_loss=0.06495, over 7223.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3037, pruned_loss=0.06341, over 1423211.15 frames.], batch size: 21, lr: 1.01e-03
+2022-04-28 18:15:22,305 INFO [train.py:763] (2/8) Epoch 6, batch 3550, loss[loss=0.233, simple_loss=0.3234, pruned_loss=0.07125, over 7400.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3037, pruned_loss=0.06338, over 1424701.33 frames.], batch size: 23, lr: 1.01e-03
+2022-04-28 18:16:27,533 INFO [train.py:763] (2/8) Epoch 6, batch 3600, loss[loss=0.212, simple_loss=0.3097, pruned_loss=0.05716, over 7212.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3035, pruned_loss=0.06346, over 1425850.29 frames.], batch size: 21, lr: 1.00e-03
+2022-04-28 18:17:32,790 INFO [train.py:763] (2/8) Epoch 6, batch 3650, loss[loss=0.2347, simple_loss=0.3239, pruned_loss=0.07276, over 7063.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3027, pruned_loss=0.06296, over 1422826.33 frames.], batch size: 28, lr: 1.00e-03
+2022-04-28 18:18:39,442 INFO [train.py:763] (2/8) Epoch 6, batch 3700, loss[loss=0.2511, simple_loss=0.3208, pruned_loss=0.09067, over 7437.00 frames.], tot_loss[loss=0.213, simple_loss=0.3011, pruned_loss=0.06251, over 1424231.52 frames.], batch size: 20, lr: 1.00e-03
+2022-04-28 18:19:44,868 INFO [train.py:763] (2/8) Epoch 6, batch 3750, loss[loss=0.2685, simple_loss=0.34, pruned_loss=0.09853, over 5056.00 frames.], tot_loss[loss=0.2139, simple_loss=0.3017, pruned_loss=0.06309, over 1424126.74 frames.], batch size: 52, lr: 1.00e-03
+2022-04-28 18:20:50,220 INFO [train.py:763] (2/8) Epoch 6, batch 3800, loss[loss=0.192, simple_loss=0.2733, pruned_loss=0.05539, over 7354.00 frames.], tot_loss[loss=0.2134, simple_loss=0.3015, pruned_loss=0.06271, over 1420917.07 frames.], batch size: 19, lr: 1.00e-03
+2022-04-28 18:21:56,430 INFO [train.py:763] (2/8) Epoch 6, batch 3850, loss[loss=0.2351, simple_loss=0.3042, pruned_loss=0.08303, over 7126.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3007, pruned_loss=0.0628, over 1423764.64 frames.], batch size: 17, lr: 1.00e-03
+2022-04-28 18:23:02,741 INFO [train.py:763] (2/8) Epoch 6, batch 3900, loss[loss=0.2193, simple_loss=0.2972, pruned_loss=0.07069, over 7150.00 frames.], tot_loss[loss=0.2129, simple_loss=0.3002, pruned_loss=0.06283, over 1424867.73 frames.], batch size: 18, lr: 1.00e-03
+2022-04-28 18:24:08,623 INFO [train.py:763] (2/8) Epoch 6, batch 3950, loss[loss=0.2177, simple_loss=0.3125, pruned_loss=0.06146, over 7338.00 frames.], tot_loss[loss=0.2122, simple_loss=0.2995, pruned_loss=0.06245, over 1426353.93 frames.], batch size: 22, lr: 9.99e-04
+2022-04-28 18:25:14,068 INFO [train.py:763] (2/8) Epoch 6, batch 4000, loss[loss=0.2435, simple_loss=0.3306, pruned_loss=0.07824, over 6711.00 frames.], tot_loss[loss=0.2116, simple_loss=0.2993, pruned_loss=0.06198, over 1430740.30 frames.], batch size: 31, lr: 9.98e-04
+2022-04-28 18:26:19,660 INFO [train.py:763] (2/8) Epoch 6, batch 4050, loss[loss=0.1955, simple_loss=0.2767, pruned_loss=0.0572, over 7172.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2989, pruned_loss=0.06192, over 1428955.51 frames.], batch size: 18, lr: 9.98e-04
+2022-04-28 18:27:25,496 INFO [train.py:763] (2/8) Epoch 6, batch 4100, loss[loss=0.2042, simple_loss=0.3013, pruned_loss=0.05359, over 7112.00 frames.], tot_loss[loss=0.212, simple_loss=0.2993, pruned_loss=0.06235, over 1424560.73 frames.], batch size: 21, lr: 9.97e-04
+2022-04-28 18:28:32,060 INFO [train.py:763] (2/8) Epoch 6, batch 4150, loss[loss=0.1933, simple_loss=0.2906, pruned_loss=0.04797, over 7208.00 frames.], tot_loss[loss=0.2117, simple_loss=0.2991, pruned_loss=0.06215, over 1425248.51 frames.], batch size: 23, lr: 9.96e-04
+2022-04-28 18:29:37,829 INFO [train.py:763] (2/8) Epoch 6, batch 4200, loss[loss=0.1929, simple_loss=0.2757, pruned_loss=0.05509, over 7301.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2984, pruned_loss=0.06154, over 1427668.55 frames.], batch size: 17, lr: 9.95e-04
+2022-04-28 18:30:43,249 INFO [train.py:763] (2/8) Epoch 6, batch 4250, loss[loss=0.2145, simple_loss=0.2943, pruned_loss=0.06736, over 7434.00 frames.], tot_loss[loss=0.213, simple_loss=0.3001, pruned_loss=0.06294, over 1423181.98 frames.], batch size: 20, lr: 9.95e-04
+2022-04-28 18:31:48,726 INFO [train.py:763] (2/8) Epoch 6, batch 4300, loss[loss=0.2127, simple_loss=0.3102, pruned_loss=0.05758, over 7238.00 frames.], tot_loss[loss=0.214, simple_loss=0.3013, pruned_loss=0.06337, over 1417445.86 frames.], batch size: 20, lr: 9.94e-04
+2022-04-28 18:32:54,884 INFO [train.py:763] (2/8) Epoch 6, batch 4350, loss[loss=0.2113, simple_loss=0.303, pruned_loss=0.05981, over 6501.00 frames.], tot_loss[loss=0.2139, simple_loss=0.3015, pruned_loss=0.0631, over 1411536.75 frames.], batch size: 38, lr: 9.93e-04
+2022-04-28 18:34:00,597 INFO [train.py:763] (2/8) Epoch 6, batch 4400, loss[loss=0.219, simple_loss=0.3153, pruned_loss=0.06136, over 6769.00 frames.], tot_loss[loss=0.2134, simple_loss=0.3007, pruned_loss=0.06301, over 1413389.79 frames.], batch size: 31, lr: 9.92e-04
+2022-04-28 18:35:07,310 INFO [train.py:763] (2/8) Epoch 6, batch 4450, loss[loss=0.2539, simple_loss=0.3332, pruned_loss=0.08734, over 7211.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3007, pruned_loss=0.06329, over 1408897.29 frames.], batch size: 22, lr: 9.92e-04
+2022-04-28 18:36:23,318 INFO [train.py:763] (2/8) Epoch 6, batch 4500, loss[loss=0.2293, simple_loss=0.3243, pruned_loss=0.06715, over 7201.00 frames.], tot_loss[loss=0.2135, simple_loss=0.3011, pruned_loss=0.06295, over 1406744.25 frames.], batch size: 22, lr: 9.91e-04
+2022-04-28 18:37:28,287 INFO [train.py:763] (2/8) Epoch 6, batch 4550, loss[loss=0.2993, simple_loss=0.3693, pruned_loss=0.1147, over 4484.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3034, pruned_loss=0.06393, over 1390470.74 frames.], batch size: 52, lr: 9.90e-04
+2022-04-28 18:38:57,444 INFO [train.py:763] (2/8) Epoch 7, batch 0, loss[loss=0.2162, simple_loss=0.3161, pruned_loss=0.05813, over 7333.00 frames.], tot_loss[loss=0.2162, simple_loss=0.3161, pruned_loss=0.05813, over 7333.00 frames.], batch size: 22, lr: 9.49e-04
+2022-04-28 18:40:02,639 INFO [train.py:763] (2/8) Epoch 7, batch 50, loss[loss=0.2247, simple_loss=0.2991, pruned_loss=0.07518, over 7140.00 frames.], tot_loss[loss=0.2184, simple_loss=0.3076, pruned_loss=0.06457, over 320577.13 frames.], batch size: 17, lr: 9.48e-04
+2022-04-28 18:41:07,849 INFO [train.py:763] (2/8) Epoch 7, batch 100, loss[loss=0.2213, simple_loss=0.3074, pruned_loss=0.06764, over 7299.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3038, pruned_loss=0.06183, over 568792.95 frames.], batch size: 25, lr: 9.48e-04
+2022-04-28 18:42:13,272 INFO [train.py:763] (2/8) Epoch 7, batch 150, loss[loss=0.2527, simple_loss=0.3388, pruned_loss=0.08326, over 7115.00 frames.], tot_loss[loss=0.2124, simple_loss=0.3017, pruned_loss=0.06152, over 757942.20 frames.], batch size: 21, lr: 9.47e-04
+2022-04-28 18:43:19,108 INFO [train.py:763] (2/8) Epoch 7, batch 200, loss[loss=0.2151, simple_loss=0.3211, pruned_loss=0.05457, over 7206.00 frames.], tot_loss[loss=0.2119, simple_loss=0.3017, pruned_loss=0.06108, over 906887.72 frames.], batch size: 22, lr: 9.46e-04
+2022-04-28 18:44:24,612 INFO [train.py:763] (2/8) Epoch 7, batch 250, loss[loss=0.2214, simple_loss=0.3194, pruned_loss=0.06169, over 7124.00 frames.], tot_loss[loss=0.2116, simple_loss=0.3011, pruned_loss=0.06107, over 1020180.62 frames.], batch size: 21, lr: 9.46e-04
+2022-04-28 18:45:29,823 INFO [train.py:763] (2/8) Epoch 7, batch 300, loss[loss=0.2001, simple_loss=0.29, pruned_loss=0.05508, over 7064.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2999, pruned_loss=0.06024, over 1106322.70 frames.], batch size: 18, lr: 9.45e-04
+2022-04-28 18:46:35,547 INFO [train.py:763] (2/8) Epoch 7, batch 350, loss[loss=0.2109, simple_loss=0.2964, pruned_loss=0.06272, over 7102.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2994, pruned_loss=0.06099, over 1178616.50 frames.], batch size: 21, lr: 9.44e-04
+2022-04-28 18:47:40,822 INFO [train.py:763] (2/8) Epoch 7, batch 400, loss[loss=0.2751, simple_loss=0.335, pruned_loss=0.1076, over 5122.00 frames.], tot_loss[loss=0.211, simple_loss=0.2996, pruned_loss=0.06114, over 1232100.56 frames.], batch size: 52, lr: 9.43e-04
+2022-04-28 18:48:46,395 INFO [train.py:763] (2/8) Epoch 7, batch 450, loss[loss=0.1795, simple_loss=0.2662, pruned_loss=0.04643, over 7186.00 frames.], tot_loss[loss=0.21, simple_loss=0.2984, pruned_loss=0.06074, over 1273821.54 frames.], batch size: 16, lr: 9.43e-04
+2022-04-28 18:49:51,763 INFO [train.py:763] (2/8) Epoch 7, batch 500, loss[loss=0.2107, simple_loss=0.3068, pruned_loss=0.05731, over 7213.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2986, pruned_loss=0.06041, over 1306219.87 frames.], batch size: 23, lr: 9.42e-04
+2022-04-28 18:50:57,359 INFO [train.py:763] (2/8) Epoch 7, batch 550, loss[loss=0.2215, simple_loss=0.3139, pruned_loss=0.06456, over 7213.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2984, pruned_loss=0.06023, over 1333503.61 frames.], batch size: 23, lr: 9.41e-04
+2022-04-28 18:52:02,630 INFO [train.py:763] (2/8) Epoch 7, batch 600, loss[loss=0.215, simple_loss=0.3133, pruned_loss=0.05838, over 7217.00 frames.], tot_loss[loss=0.2112, simple_loss=0.3002, pruned_loss=0.06114, over 1353591.48 frames.], batch size: 21, lr: 9.41e-04
+2022-04-28 18:53:08,460 INFO [train.py:763] (2/8) Epoch 7, batch 650, loss[loss=0.1739, simple_loss=0.2717, pruned_loss=0.03804, over 7258.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2995, pruned_loss=0.06089, over 1368697.26 frames.], batch size: 19, lr: 9.40e-04
+2022-04-28 18:54:13,816 INFO [train.py:763] (2/8) Epoch 7, batch 700, loss[loss=0.2578, simple_loss=0.3309, pruned_loss=0.09229, over 5245.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2991, pruned_loss=0.06037, over 1376641.15 frames.], batch size: 54, lr: 9.39e-04
+2022-04-28 18:55:19,473 INFO [train.py:763] (2/8) Epoch 7, batch 750, loss[loss=0.1955, simple_loss=0.2814, pruned_loss=0.05481, over 7364.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2987, pruned_loss=0.06009, over 1385766.86 frames.], batch size: 19, lr: 9.39e-04
+2022-04-28 18:56:26,108 INFO [train.py:763] (2/8) Epoch 7, batch 800, loss[loss=0.2397, simple_loss=0.3285, pruned_loss=0.07543, over 6272.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2996, pruned_loss=0.06031, over 1390215.45 frames.], batch size: 37, lr: 9.38e-04
+2022-04-28 18:57:33,276 INFO [train.py:763] (2/8) Epoch 7, batch 850, loss[loss=0.1896, simple_loss=0.2686, pruned_loss=0.05533, over 7418.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2975, pruned_loss=0.05979, over 1399107.57 frames.], batch size: 18, lr: 9.37e-04
+2022-04-28 18:58:40,225 INFO [train.py:763] (2/8) Epoch 7, batch 900, loss[loss=0.2197, simple_loss=0.3026, pruned_loss=0.06836, over 6817.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2973, pruned_loss=0.05989, over 1398776.19 frames.], batch size: 31, lr: 9.36e-04
+2022-04-28 18:59:46,945 INFO [train.py:763] (2/8) Epoch 7, batch 950, loss[loss=0.2163, simple_loss=0.3106, pruned_loss=0.061, over 7242.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2982, pruned_loss=0.06014, over 1404353.65 frames.], batch size: 20, lr: 9.36e-04
+2022-04-28 19:00:52,050 INFO [train.py:763] (2/8) Epoch 7, batch 1000, loss[loss=0.2092, simple_loss=0.2943, pruned_loss=0.06206, over 7218.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2986, pruned_loss=0.06016, over 1408795.51 frames.], batch size: 21, lr: 9.35e-04
+2022-04-28 19:01:58,577 INFO [train.py:763] (2/8) Epoch 7, batch 1050, loss[loss=0.1717, simple_loss=0.2542, pruned_loss=0.04455, over 7126.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2993, pruned_loss=0.06059, over 1406634.64 frames.], batch size: 17, lr: 9.34e-04
+2022-04-28 19:03:05,227 INFO [train.py:763] (2/8) Epoch 7, batch 1100, loss[loss=0.2413, simple_loss=0.3318, pruned_loss=0.07536, over 7206.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2996, pruned_loss=0.06071, over 1411662.44 frames.], batch size: 22, lr: 9.34e-04
+2022-04-28 19:04:11,928 INFO [train.py:763] (2/8) Epoch 7, batch 1150, loss[loss=0.278, simple_loss=0.3394, pruned_loss=0.1083, over 5063.00 frames.], tot_loss[loss=0.2117, simple_loss=0.3007, pruned_loss=0.06131, over 1416792.32 frames.], batch size: 52, lr: 9.33e-04
+2022-04-28 19:05:18,437 INFO [train.py:763] (2/8) Epoch 7, batch 1200, loss[loss=0.1848, simple_loss=0.2862, pruned_loss=0.04168, over 7148.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2995, pruned_loss=0.06072, over 1420392.12 frames.], batch size: 20, lr: 9.32e-04
+2022-04-28 19:06:24,029 INFO [train.py:763] (2/8) Epoch 7, batch 1250, loss[loss=0.1631, simple_loss=0.2502, pruned_loss=0.038, over 7291.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2989, pruned_loss=0.06095, over 1418978.92 frames.], batch size: 18, lr: 9.32e-04
+2022-04-28 19:07:30,156 INFO [train.py:763] (2/8) Epoch 7, batch 1300, loss[loss=0.204, simple_loss=0.306, pruned_loss=0.05099, over 7145.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2994, pruned_loss=0.06105, over 1415560.27 frames.], batch size: 20, lr: 9.31e-04
+2022-04-28 19:08:35,479 INFO [train.py:763] (2/8) Epoch 7, batch 1350, loss[loss=0.194, simple_loss=0.3023, pruned_loss=0.04288, over 7158.00 frames.], tot_loss[loss=0.2103, simple_loss=0.299, pruned_loss=0.06075, over 1414580.78 frames.], batch size: 19, lr: 9.30e-04
+2022-04-28 19:09:41,317 INFO [train.py:763] (2/8) Epoch 7, batch 1400, loss[loss=0.1858, simple_loss=0.2688, pruned_loss=0.05138, over 7269.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2996, pruned_loss=0.06081, over 1415648.00 frames.], batch size: 18, lr: 9.30e-04
+2022-04-28 19:10:48,151 INFO [train.py:763] (2/8) Epoch 7, batch 1450, loss[loss=0.2355, simple_loss=0.3148, pruned_loss=0.07808, over 7151.00 frames.], tot_loss[loss=0.21, simple_loss=0.2992, pruned_loss=0.06039, over 1415178.57 frames.], batch size: 18, lr: 9.29e-04
+2022-04-28 19:11:54,398 INFO [train.py:763] (2/8) Epoch 7, batch 1500, loss[loss=0.1646, simple_loss=0.2515, pruned_loss=0.03885, over 7408.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2973, pruned_loss=0.05975, over 1415426.16 frames.], batch size: 18, lr: 9.28e-04
+2022-04-28 19:12:59,475 INFO [train.py:763] (2/8) Epoch 7, batch 1550, loss[loss=0.2384, simple_loss=0.3273, pruned_loss=0.07481, over 7208.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2977, pruned_loss=0.05984, over 1420595.66 frames.], batch size: 22, lr: 9.28e-04
+2022-04-28 19:14:04,512 INFO [train.py:763] (2/8) Epoch 7, batch 1600, loss[loss=0.2119, simple_loss=0.3061, pruned_loss=0.05885, over 6308.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2987, pruned_loss=0.06022, over 1421277.07 frames.], batch size: 37, lr: 9.27e-04
+2022-04-28 19:15:09,642 INFO [train.py:763] (2/8) Epoch 7, batch 1650, loss[loss=0.2109, simple_loss=0.2975, pruned_loss=0.06219, over 7299.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2987, pruned_loss=0.06019, over 1419297.41 frames.], batch size: 24, lr: 9.26e-04
+2022-04-28 19:16:15,821 INFO [train.py:763] (2/8) Epoch 7, batch 1700, loss[loss=0.2068, simple_loss=0.3153, pruned_loss=0.04912, over 7326.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2995, pruned_loss=0.06035, over 1420635.85 frames.], batch size: 21, lr: 9.26e-04
+2022-04-28 19:17:22,172 INFO [train.py:763] (2/8) Epoch 7, batch 1750, loss[loss=0.1949, simple_loss=0.2949, pruned_loss=0.04745, over 7333.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2993, pruned_loss=0.06057, over 1420419.38 frames.], batch size: 22, lr: 9.25e-04
+2022-04-28 19:18:45,816 INFO [train.py:763] (2/8) Epoch 7, batch 1800, loss[loss=0.1972, simple_loss=0.2899, pruned_loss=0.05221, over 7339.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2979, pruned_loss=0.05978, over 1421417.93 frames.], batch size: 22, lr: 9.24e-04
+2022-04-28 19:19:59,990 INFO [train.py:763] (2/8) Epoch 7, batch 1850, loss[loss=0.2418, simple_loss=0.3178, pruned_loss=0.08287, over 7231.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2988, pruned_loss=0.0599, over 1422611.10 frames.], batch size: 20, lr: 9.24e-04
+2022-04-28 19:21:23,366 INFO [train.py:763] (2/8) Epoch 7, batch 1900, loss[loss=0.2133, simple_loss=0.3152, pruned_loss=0.05569, over 7298.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2968, pruned_loss=0.05903, over 1421387.63 frames.], batch size: 25, lr: 9.23e-04
+2022-04-28 19:22:40,067 INFO [train.py:763] (2/8) Epoch 7, batch 1950, loss[loss=0.1837, simple_loss=0.2723, pruned_loss=0.04754, over 7433.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2968, pruned_loss=0.05908, over 1426258.18 frames.], batch size: 17, lr: 9.22e-04
+2022-04-28 19:23:47,451 INFO [train.py:763] (2/8) Epoch 7, batch 2000, loss[loss=0.2351, simple_loss=0.3243, pruned_loss=0.07292, over 7120.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2969, pruned_loss=0.05912, over 1427140.45 frames.], batch size: 21, lr: 9.22e-04
+2022-04-28 19:25:02,867 INFO [train.py:763] (2/8) Epoch 7, batch 2050, loss[loss=0.2616, simple_loss=0.3314, pruned_loss=0.09591, over 5304.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2985, pruned_loss=0.06023, over 1421663.35 frames.], batch size: 53, lr: 9.21e-04
+2022-04-28 19:26:07,936 INFO [train.py:763] (2/8) Epoch 7, batch 2100, loss[loss=0.1829, simple_loss=0.2818, pruned_loss=0.042, over 7233.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2985, pruned_loss=0.05988, over 1418150.73 frames.], batch size: 20, lr: 9.20e-04
+2022-04-28 19:27:22,250 INFO [train.py:763] (2/8) Epoch 7, batch 2150, loss[loss=0.2045, simple_loss=0.2977, pruned_loss=0.05565, over 7199.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2988, pruned_loss=0.06029, over 1419717.25 frames.], batch size: 22, lr: 9.20e-04
+2022-04-28 19:28:27,686 INFO [train.py:763] (2/8) Epoch 7, batch 2200, loss[loss=0.2505, simple_loss=0.3196, pruned_loss=0.09065, over 7267.00 frames.], tot_loss[loss=0.209, simple_loss=0.2977, pruned_loss=0.06013, over 1418091.23 frames.], batch size: 24, lr: 9.19e-04
+2022-04-28 19:29:32,842 INFO [train.py:763] (2/8) Epoch 7, batch 2250, loss[loss=0.2424, simple_loss=0.3349, pruned_loss=0.07497, over 7212.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2973, pruned_loss=0.06057, over 1412518.47 frames.], batch size: 23, lr: 9.18e-04
+2022-04-28 19:30:38,169 INFO [train.py:763] (2/8) Epoch 7, batch 2300, loss[loss=0.1678, simple_loss=0.2534, pruned_loss=0.04109, over 7400.00 frames.], tot_loss[loss=0.209, simple_loss=0.297, pruned_loss=0.0605, over 1413238.83 frames.], batch size: 18, lr: 9.18e-04
+2022-04-28 19:31:43,911 INFO [train.py:763] (2/8) Epoch 7, batch 2350, loss[loss=0.1965, simple_loss=0.2773, pruned_loss=0.05791, over 7063.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2976, pruned_loss=0.06056, over 1413070.85 frames.], batch size: 18, lr: 9.17e-04
+2022-04-28 19:32:50,591 INFO [train.py:763] (2/8) Epoch 7, batch 2400, loss[loss=0.1979, simple_loss=0.2849, pruned_loss=0.05546, over 7259.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2972, pruned_loss=0.05997, over 1417374.48 frames.], batch size: 19, lr: 9.16e-04
+2022-04-28 19:33:55,901 INFO [train.py:763] (2/8) Epoch 7, batch 2450, loss[loss=0.226, simple_loss=0.3183, pruned_loss=0.06685, over 7294.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2982, pruned_loss=0.06009, over 1423660.63 frames.], batch size: 24, lr: 9.16e-04
+2022-04-28 19:35:01,300 INFO [train.py:763] (2/8) Epoch 7, batch 2500, loss[loss=0.2335, simple_loss=0.3255, pruned_loss=0.07078, over 7316.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2991, pruned_loss=0.061, over 1421478.01 frames.], batch size: 21, lr: 9.15e-04
+2022-04-28 19:36:06,924 INFO [train.py:763] (2/8) Epoch 7, batch 2550, loss[loss=0.2461, simple_loss=0.3163, pruned_loss=0.08793, over 7345.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2986, pruned_loss=0.06084, over 1425447.83 frames.], batch size: 19, lr: 9.14e-04
+2022-04-28 19:37:12,482 INFO [train.py:763] (2/8) Epoch 7, batch 2600, loss[loss=0.1996, simple_loss=0.2816, pruned_loss=0.05877, over 6760.00 frames.], tot_loss[loss=0.2095, simple_loss=0.298, pruned_loss=0.06053, over 1425429.58 frames.], batch size: 15, lr: 9.14e-04
+2022-04-28 19:38:17,712 INFO [train.py:763] (2/8) Epoch 7, batch 2650, loss[loss=0.1957, simple_loss=0.2978, pruned_loss=0.04679, over 7118.00 frames.], tot_loss[loss=0.2082, simple_loss=0.297, pruned_loss=0.05974, over 1427020.37 frames.], batch size: 21, lr: 9.13e-04
+2022-04-28 19:39:23,648 INFO [train.py:763] (2/8) Epoch 7, batch 2700, loss[loss=0.1683, simple_loss=0.2564, pruned_loss=0.04005, over 6876.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2957, pruned_loss=0.05935, over 1429054.86 frames.], batch size: 15, lr: 9.12e-04
+2022-04-28 19:40:30,717 INFO [train.py:763] (2/8) Epoch 7, batch 2750, loss[loss=0.1752, simple_loss=0.2578, pruned_loss=0.04628, over 7007.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2951, pruned_loss=0.05901, over 1427901.51 frames.], batch size: 16, lr: 9.12e-04
+2022-04-28 19:41:36,687 INFO [train.py:763] (2/8) Epoch 7, batch 2800, loss[loss=0.2568, simple_loss=0.3441, pruned_loss=0.08474, over 7142.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2963, pruned_loss=0.05918, over 1427929.41 frames.], batch size: 20, lr: 9.11e-04
+2022-04-28 19:42:43,484 INFO [train.py:763] (2/8) Epoch 7, batch 2850, loss[loss=0.258, simple_loss=0.3357, pruned_loss=0.09017, over 7183.00 frames.], tot_loss[loss=0.2082, simple_loss=0.297, pruned_loss=0.05971, over 1426318.80 frames.], batch size: 22, lr: 9.11e-04
+2022-04-28 19:43:49,293 INFO [train.py:763] (2/8) Epoch 7, batch 2900, loss[loss=0.1606, simple_loss=0.2555, pruned_loss=0.03289, over 7135.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2972, pruned_loss=0.05908, over 1425516.40 frames.], batch size: 17, lr: 9.10e-04
+2022-04-28 19:44:55,754 INFO [train.py:763] (2/8) Epoch 7, batch 2950, loss[loss=0.194, simple_loss=0.2892, pruned_loss=0.04941, over 7062.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2963, pruned_loss=0.05864, over 1424136.29 frames.], batch size: 18, lr: 9.09e-04
+2022-04-28 19:46:01,157 INFO [train.py:763] (2/8) Epoch 7, batch 3000, loss[loss=0.2969, simple_loss=0.3523, pruned_loss=0.1208, over 4668.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2979, pruned_loss=0.0597, over 1420674.88 frames.], batch size: 52, lr: 9.09e-04
+2022-04-28 19:46:01,158 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-28 19:46:16,423 INFO [train.py:792] (2/8) Epoch 7, validation: loss=0.1713, simple_loss=0.2754, pruned_loss=0.03361, over 698248.00 frames.
+2022-04-28 19:47:23,036 INFO [train.py:763] (2/8) Epoch 7, batch 3050, loss[loss=0.2152, simple_loss=0.3051, pruned_loss=0.06271, over 6478.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2976, pruned_loss=0.05985, over 1413763.13 frames.], batch size: 38, lr: 9.08e-04
+2022-04-28 19:48:28,731 INFO [train.py:763] (2/8) Epoch 7, batch 3100, loss[loss=0.1962, simple_loss=0.277, pruned_loss=0.05773, over 7267.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2968, pruned_loss=0.05921, over 1418214.81 frames.], batch size: 19, lr: 9.07e-04
+2022-04-28 19:49:34,312 INFO [train.py:763] (2/8) Epoch 7, batch 3150, loss[loss=0.1898, simple_loss=0.28, pruned_loss=0.0498, over 7427.00 frames.], tot_loss[loss=0.206, simple_loss=0.2952, pruned_loss=0.05836, over 1419756.21 frames.], batch size: 20, lr: 9.07e-04
+2022-04-28 19:50:39,917 INFO [train.py:763] (2/8) Epoch 7, batch 3200, loss[loss=0.1905, simple_loss=0.2787, pruned_loss=0.05116, over 7436.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2952, pruned_loss=0.05856, over 1422989.76 frames.], batch size: 20, lr: 9.06e-04
+2022-04-28 19:51:45,165 INFO [train.py:763] (2/8) Epoch 7, batch 3250, loss[loss=0.2054, simple_loss=0.3021, pruned_loss=0.05435, over 7001.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2964, pruned_loss=0.05906, over 1422703.83 frames.], batch size: 28, lr: 9.05e-04
+2022-04-28 19:52:50,674 INFO [train.py:763] (2/8) Epoch 7, batch 3300, loss[loss=0.2457, simple_loss=0.3229, pruned_loss=0.08423, over 6765.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2958, pruned_loss=0.05861, over 1421532.75 frames.], batch size: 31, lr: 9.05e-04
+2022-04-28 19:53:56,155 INFO [train.py:763] (2/8) Epoch 7, batch 3350, loss[loss=0.1911, simple_loss=0.2817, pruned_loss=0.05028, over 7435.00 frames.], tot_loss[loss=0.2065, simple_loss=0.296, pruned_loss=0.05854, over 1419151.23 frames.], batch size: 20, lr: 9.04e-04
+2022-04-28 19:55:01,740 INFO [train.py:763] (2/8) Epoch 7, batch 3400, loss[loss=0.2049, simple_loss=0.2836, pruned_loss=0.06307, over 6727.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2956, pruned_loss=0.05852, over 1417803.06 frames.], batch size: 31, lr: 9.04e-04
+2022-04-28 19:56:08,384 INFO [train.py:763] (2/8) Epoch 7, batch 3450, loss[loss=0.2022, simple_loss=0.2837, pruned_loss=0.06031, over 7408.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2969, pruned_loss=0.05932, over 1421108.98 frames.], batch size: 18, lr: 9.03e-04
+2022-04-28 19:57:15,787 INFO [train.py:763] (2/8) Epoch 7, batch 3500, loss[loss=0.2242, simple_loss=0.3131, pruned_loss=0.06765, over 7379.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2986, pruned_loss=0.06006, over 1420960.97 frames.], batch size: 23, lr: 9.02e-04
+2022-04-28 19:58:22,784 INFO [train.py:763] (2/8) Epoch 7, batch 3550, loss[loss=0.1888, simple_loss=0.2795, pruned_loss=0.04898, over 7259.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2983, pruned_loss=0.06038, over 1422183.78 frames.], batch size: 19, lr: 9.02e-04
+2022-04-28 19:59:29,955 INFO [train.py:763] (2/8) Epoch 7, batch 3600, loss[loss=0.1907, simple_loss=0.2725, pruned_loss=0.05441, over 7284.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2966, pruned_loss=0.05993, over 1420698.15 frames.], batch size: 17, lr: 9.01e-04
+2022-04-28 20:00:37,036 INFO [train.py:763] (2/8) Epoch 7, batch 3650, loss[loss=0.2362, simple_loss=0.3279, pruned_loss=0.07225, over 7419.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2979, pruned_loss=0.06023, over 1415478.56 frames.], batch size: 21, lr: 9.01e-04
+2022-04-28 20:01:42,539 INFO [train.py:763] (2/8) Epoch 7, batch 3700, loss[loss=0.2089, simple_loss=0.2917, pruned_loss=0.06304, over 7217.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2974, pruned_loss=0.05957, over 1419326.20 frames.], batch size: 21, lr: 9.00e-04
+2022-04-28 20:02:49,190 INFO [train.py:763] (2/8) Epoch 7, batch 3750, loss[loss=0.2112, simple_loss=0.3076, pruned_loss=0.05738, over 7167.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2965, pruned_loss=0.05929, over 1416463.56 frames.], batch size: 19, lr: 8.99e-04
+2022-04-28 20:03:54,759 INFO [train.py:763] (2/8) Epoch 7, batch 3800, loss[loss=0.2465, simple_loss=0.3292, pruned_loss=0.08189, over 7278.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2976, pruned_loss=0.05945, over 1419260.99 frames.], batch size: 24, lr: 8.99e-04
+2022-04-28 20:05:00,506 INFO [train.py:763] (2/8) Epoch 7, batch 3850, loss[loss=0.2074, simple_loss=0.311, pruned_loss=0.05185, over 7211.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2982, pruned_loss=0.0597, over 1417501.99 frames.], batch size: 21, lr: 8.98e-04
+2022-04-28 20:06:06,734 INFO [train.py:763] (2/8) Epoch 7, batch 3900, loss[loss=0.204, simple_loss=0.2983, pruned_loss=0.05483, over 7431.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2971, pruned_loss=0.05926, over 1421564.05 frames.], batch size: 20, lr: 8.97e-04
+2022-04-28 20:07:13,246 INFO [train.py:763] (2/8) Epoch 7, batch 3950, loss[loss=0.1741, simple_loss=0.266, pruned_loss=0.04109, over 7012.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2964, pruned_loss=0.05874, over 1423808.28 frames.], batch size: 16, lr: 8.97e-04
+2022-04-28 20:08:18,734 INFO [train.py:763] (2/8) Epoch 7, batch 4000, loss[loss=0.1905, simple_loss=0.2886, pruned_loss=0.04621, over 7141.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2972, pruned_loss=0.05899, over 1422509.03 frames.], batch size: 20, lr: 8.96e-04
+2022-04-28 20:09:23,867 INFO [train.py:763] (2/8) Epoch 7, batch 4050, loss[loss=0.2127, simple_loss=0.3057, pruned_loss=0.05984, over 7403.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2969, pruned_loss=0.05882, over 1425710.35 frames.], batch size: 21, lr: 8.96e-04
+2022-04-28 20:10:29,410 INFO [train.py:763] (2/8) Epoch 7, batch 4100, loss[loss=0.1844, simple_loss=0.2625, pruned_loss=0.05318, over 7272.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2972, pruned_loss=0.05918, over 1419370.38 frames.], batch size: 17, lr: 8.95e-04
+2022-04-28 20:11:34,144 INFO [train.py:763] (2/8) Epoch 7, batch 4150, loss[loss=0.2113, simple_loss=0.3053, pruned_loss=0.0587, over 7336.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2982, pruned_loss=0.05971, over 1413119.36 frames.], batch size: 22, lr: 8.94e-04
+2022-04-28 20:12:39,366 INFO [train.py:763] (2/8) Epoch 7, batch 4200, loss[loss=0.1964, simple_loss=0.2879, pruned_loss=0.05247, over 7150.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2984, pruned_loss=0.05945, over 1416253.65 frames.], batch size: 20, lr: 8.94e-04
+2022-04-28 20:13:44,887 INFO [train.py:763] (2/8) Epoch 7, batch 4250, loss[loss=0.2032, simple_loss=0.3023, pruned_loss=0.052, over 7206.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2979, pruned_loss=0.05921, over 1420102.99 frames.], batch size: 22, lr: 8.93e-04
+2022-04-28 20:14:50,387 INFO [train.py:763] (2/8) Epoch 7, batch 4300, loss[loss=0.275, simple_loss=0.3359, pruned_loss=0.1071, over 7319.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2977, pruned_loss=0.05937, over 1417931.68 frames.], batch size: 21, lr: 8.93e-04
+2022-04-28 20:15:55,682 INFO [train.py:763] (2/8) Epoch 7, batch 4350, loss[loss=0.2277, simple_loss=0.3241, pruned_loss=0.06561, over 7447.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2965, pruned_loss=0.05914, over 1414275.31 frames.], batch size: 22, lr: 8.92e-04
+2022-04-28 20:17:01,779 INFO [train.py:763] (2/8) Epoch 7, batch 4400, loss[loss=0.2416, simple_loss=0.3208, pruned_loss=0.08122, over 7089.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2956, pruned_loss=0.05905, over 1417656.04 frames.], batch size: 28, lr: 8.91e-04
+2022-04-28 20:18:08,978 INFO [train.py:763] (2/8) Epoch 7, batch 4450, loss[loss=0.2412, simple_loss=0.3346, pruned_loss=0.07386, over 7325.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2958, pruned_loss=0.05902, over 1417259.54 frames.], batch size: 20, lr: 8.91e-04
+2022-04-28 20:19:16,354 INFO [train.py:763] (2/8) Epoch 7, batch 4500, loss[loss=0.2037, simple_loss=0.2774, pruned_loss=0.06506, over 7166.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2949, pruned_loss=0.05845, over 1414530.88 frames.], batch size: 18, lr: 8.90e-04
+2022-04-28 20:20:24,250 INFO [train.py:763] (2/8) Epoch 7, batch 4550, loss[loss=0.1619, simple_loss=0.2464, pruned_loss=0.03867, over 7266.00 frames.], tot_loss[loss=0.207, simple_loss=0.2948, pruned_loss=0.05961, over 1397132.52 frames.], batch size: 17, lr: 8.90e-04
+2022-04-28 20:21:52,804 INFO [train.py:763] (2/8) Epoch 8, batch 0, loss[loss=0.2116, simple_loss=0.3028, pruned_loss=0.06024, over 7179.00 frames.], tot_loss[loss=0.2116, simple_loss=0.3028, pruned_loss=0.06024, over 7179.00 frames.], batch size: 23, lr: 8.54e-04
+2022-04-28 20:22:58,560 INFO [train.py:763] (2/8) Epoch 8, batch 50, loss[loss=0.2004, simple_loss=0.2972, pruned_loss=0.05177, over 7100.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2994, pruned_loss=0.0588, over 319242.50 frames.], batch size: 28, lr: 8.53e-04
+2022-04-28 20:24:03,942 INFO [train.py:763] (2/8) Epoch 8, batch 100, loss[loss=0.1978, simple_loss=0.3075, pruned_loss=0.04399, over 7230.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2932, pruned_loss=0.05605, over 566497.07 frames.], batch size: 20, lr: 8.53e-04
+2022-04-28 20:25:10,090 INFO [train.py:763] (2/8) Epoch 8, batch 150, loss[loss=0.2062, simple_loss=0.2968, pruned_loss=0.05786, over 4814.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2943, pruned_loss=0.05629, over 753034.65 frames.], batch size: 52, lr: 8.52e-04
+2022-04-28 20:26:16,004 INFO [train.py:763] (2/8) Epoch 8, batch 200, loss[loss=0.2224, simple_loss=0.3138, pruned_loss=0.0655, over 7209.00 frames.], tot_loss[loss=0.204, simple_loss=0.2947, pruned_loss=0.05659, over 902725.32 frames.], batch size: 22, lr: 8.51e-04
+2022-04-28 20:27:21,272 INFO [train.py:763] (2/8) Epoch 8, batch 250, loss[loss=0.2089, simple_loss=0.3024, pruned_loss=0.05769, over 7431.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2946, pruned_loss=0.05622, over 1018792.78 frames.], batch size: 20, lr: 8.51e-04
+2022-04-28 20:28:27,033 INFO [train.py:763] (2/8) Epoch 8, batch 300, loss[loss=0.1892, simple_loss=0.2923, pruned_loss=0.04305, over 7345.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2949, pruned_loss=0.05677, over 1104501.98 frames.], batch size: 22, lr: 8.50e-04
+2022-04-28 20:29:32,796 INFO [train.py:763] (2/8) Epoch 8, batch 350, loss[loss=0.1789, simple_loss=0.2751, pruned_loss=0.04131, over 7168.00 frames.], tot_loss[loss=0.2024, simple_loss=0.293, pruned_loss=0.05585, over 1179109.76 frames.], batch size: 19, lr: 8.50e-04
+2022-04-28 20:30:38,284 INFO [train.py:763] (2/8) Epoch 8, batch 400, loss[loss=0.1518, simple_loss=0.2426, pruned_loss=0.03053, over 7135.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2934, pruned_loss=0.05626, over 1238223.30 frames.], batch size: 17, lr: 8.49e-04
+2022-04-28 20:31:43,710 INFO [train.py:763] (2/8) Epoch 8, batch 450, loss[loss=0.1604, simple_loss=0.258, pruned_loss=0.03142, over 7264.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2923, pruned_loss=0.05558, over 1278491.80 frames.], batch size: 19, lr: 8.49e-04
+2022-04-28 20:32:50,560 INFO [train.py:763] (2/8) Epoch 8, batch 500, loss[loss=0.1665, simple_loss=0.255, pruned_loss=0.039, over 7409.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2931, pruned_loss=0.05636, over 1311100.11 frames.], batch size: 18, lr: 8.48e-04
+2022-04-28 20:33:57,709 INFO [train.py:763] (2/8) Epoch 8, batch 550, loss[loss=0.1847, simple_loss=0.2836, pruned_loss=0.04293, over 7074.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2918, pruned_loss=0.05531, over 1338568.61 frames.], batch size: 18, lr: 8.48e-04
+2022-04-28 20:35:03,797 INFO [train.py:763] (2/8) Epoch 8, batch 600, loss[loss=0.214, simple_loss=0.289, pruned_loss=0.06946, over 7445.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2922, pruned_loss=0.0553, over 1361005.79 frames.], batch size: 19, lr: 8.47e-04
+2022-04-28 20:36:09,107 INFO [train.py:763] (2/8) Epoch 8, batch 650, loss[loss=0.1916, simple_loss=0.2781, pruned_loss=0.05255, over 7369.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2923, pruned_loss=0.05562, over 1374527.53 frames.], batch size: 19, lr: 8.46e-04
+2022-04-28 20:37:14,550 INFO [train.py:763] (2/8) Epoch 8, batch 700, loss[loss=0.1892, simple_loss=0.278, pruned_loss=0.05021, over 7436.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2923, pruned_loss=0.05552, over 1387154.25 frames.], batch size: 20, lr: 8.46e-04
+2022-04-28 20:38:20,312 INFO [train.py:763] (2/8) Epoch 8, batch 750, loss[loss=0.1613, simple_loss=0.2549, pruned_loss=0.03386, over 7167.00 frames.], tot_loss[loss=0.2022, simple_loss=0.293, pruned_loss=0.0557, over 1390773.15 frames.], batch size: 18, lr: 8.45e-04
+2022-04-28 20:39:25,911 INFO [train.py:763] (2/8) Epoch 8, batch 800, loss[loss=0.2389, simple_loss=0.3226, pruned_loss=0.07764, over 7383.00 frames.], tot_loss[loss=0.202, simple_loss=0.2925, pruned_loss=0.05576, over 1397212.67 frames.], batch size: 23, lr: 8.45e-04
+2022-04-28 20:40:32,527 INFO [train.py:763] (2/8) Epoch 8, batch 850, loss[loss=0.2327, simple_loss=0.3227, pruned_loss=0.07131, over 7326.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2939, pruned_loss=0.05639, over 1402198.75 frames.], batch size: 21, lr: 8.44e-04
+2022-04-28 20:41:39,525 INFO [train.py:763] (2/8) Epoch 8, batch 900, loss[loss=0.2518, simple_loss=0.3391, pruned_loss=0.08222, over 7220.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2935, pruned_loss=0.05595, over 1411295.79 frames.], batch size: 21, lr: 8.44e-04
+2022-04-28 20:42:46,672 INFO [train.py:763] (2/8) Epoch 8, batch 950, loss[loss=0.181, simple_loss=0.2733, pruned_loss=0.04438, over 7327.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2946, pruned_loss=0.05649, over 1409600.54 frames.], batch size: 20, lr: 8.43e-04
+2022-04-28 20:43:53,790 INFO [train.py:763] (2/8) Epoch 8, batch 1000, loss[loss=0.2047, simple_loss=0.2995, pruned_loss=0.05494, over 7433.00 frames.], tot_loss[loss=0.2032, simple_loss=0.294, pruned_loss=0.05617, over 1413590.11 frames.], batch size: 20, lr: 8.43e-04
+2022-04-28 20:45:00,935 INFO [train.py:763] (2/8) Epoch 8, batch 1050, loss[loss=0.1848, simple_loss=0.2811, pruned_loss=0.04429, over 7268.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2927, pruned_loss=0.05536, over 1417331.70 frames.], batch size: 19, lr: 8.42e-04
+2022-04-28 20:46:07,159 INFO [train.py:763] (2/8) Epoch 8, batch 1100, loss[loss=0.1783, simple_loss=0.2592, pruned_loss=0.04874, over 7279.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2941, pruned_loss=0.05617, over 1420537.89 frames.], batch size: 17, lr: 8.41e-04
+2022-04-28 20:47:12,899 INFO [train.py:763] (2/8) Epoch 8, batch 1150, loss[loss=0.2056, simple_loss=0.3059, pruned_loss=0.05262, over 7300.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2932, pruned_loss=0.05546, over 1421467.82 frames.], batch size: 25, lr: 8.41e-04
+2022-04-28 20:48:18,239 INFO [train.py:763] (2/8) Epoch 8, batch 1200, loss[loss=0.184, simple_loss=0.2863, pruned_loss=0.04083, over 7427.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2928, pruned_loss=0.05585, over 1423367.71 frames.], batch size: 20, lr: 8.40e-04
+2022-04-28 20:49:23,426 INFO [train.py:763] (2/8) Epoch 8, batch 1250, loss[loss=0.1812, simple_loss=0.2643, pruned_loss=0.04905, over 6768.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2928, pruned_loss=0.05652, over 1418693.10 frames.], batch size: 15, lr: 8.40e-04
+2022-04-28 20:50:29,920 INFO [train.py:763] (2/8) Epoch 8, batch 1300, loss[loss=0.208, simple_loss=0.3065, pruned_loss=0.05478, over 7159.00 frames.], tot_loss[loss=0.204, simple_loss=0.2937, pruned_loss=0.05715, over 1415025.35 frames.], batch size: 19, lr: 8.39e-04
+2022-04-28 20:51:37,147 INFO [train.py:763] (2/8) Epoch 8, batch 1350, loss[loss=0.1908, simple_loss=0.2857, pruned_loss=0.04794, over 7437.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2932, pruned_loss=0.05677, over 1419641.43 frames.], batch size: 20, lr: 8.39e-04
+2022-04-28 20:52:43,209 INFO [train.py:763] (2/8) Epoch 8, batch 1400, loss[loss=0.2017, simple_loss=0.3001, pruned_loss=0.05162, over 7226.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2933, pruned_loss=0.0566, over 1416032.53 frames.], batch size: 21, lr: 8.38e-04
+2022-04-28 20:53:48,890 INFO [train.py:763] (2/8) Epoch 8, batch 1450, loss[loss=0.2048, simple_loss=0.3074, pruned_loss=0.05107, over 7321.00 frames.], tot_loss[loss=0.2023, simple_loss=0.292, pruned_loss=0.05634, over 1420513.47 frames.], batch size: 21, lr: 8.38e-04
+2022-04-28 20:54:55,522 INFO [train.py:763] (2/8) Epoch 8, batch 1500, loss[loss=0.2009, simple_loss=0.2998, pruned_loss=0.05101, over 7228.00 frames.], tot_loss[loss=0.202, simple_loss=0.2922, pruned_loss=0.05588, over 1422909.86 frames.], batch size: 20, lr: 8.37e-04
+2022-04-28 20:56:02,358 INFO [train.py:763] (2/8) Epoch 8, batch 1550, loss[loss=0.2038, simple_loss=0.2907, pruned_loss=0.05842, over 7212.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2923, pruned_loss=0.05595, over 1422078.85 frames.], batch size: 22, lr: 8.37e-04
+2022-04-28 20:57:08,582 INFO [train.py:763] (2/8) Epoch 8, batch 1600, loss[loss=0.1693, simple_loss=0.2663, pruned_loss=0.03614, over 7067.00 frames.], tot_loss[loss=0.2026, simple_loss=0.293, pruned_loss=0.05607, over 1420092.71 frames.], batch size: 18, lr: 8.36e-04
+2022-04-28 20:58:15,578 INFO [train.py:763] (2/8) Epoch 8, batch 1650, loss[loss=0.2014, simple_loss=0.2927, pruned_loss=0.05507, over 7125.00 frames.], tot_loss[loss=0.2025, simple_loss=0.293, pruned_loss=0.05595, over 1420921.73 frames.], batch size: 21, lr: 8.35e-04
+2022-04-28 20:59:22,334 INFO [train.py:763] (2/8) Epoch 8, batch 1700, loss[loss=0.2025, simple_loss=0.3074, pruned_loss=0.04883, over 7153.00 frames.], tot_loss[loss=0.203, simple_loss=0.2938, pruned_loss=0.05615, over 1419401.93 frames.], batch size: 20, lr: 8.35e-04
+2022-04-28 21:00:28,780 INFO [train.py:763] (2/8) Epoch 8, batch 1750, loss[loss=0.18, simple_loss=0.2719, pruned_loss=0.04399, over 7324.00 frames.], tot_loss[loss=0.203, simple_loss=0.2935, pruned_loss=0.0563, over 1421153.93 frames.], batch size: 21, lr: 8.34e-04
+2022-04-28 21:01:33,978 INFO [train.py:763] (2/8) Epoch 8, batch 1800, loss[loss=0.1978, simple_loss=0.2875, pruned_loss=0.05398, over 7230.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2938, pruned_loss=0.05675, over 1418003.94 frames.], batch size: 20, lr: 8.34e-04
+2022-04-28 21:02:39,280 INFO [train.py:763] (2/8) Epoch 8, batch 1850, loss[loss=0.1646, simple_loss=0.2605, pruned_loss=0.03439, over 7239.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2944, pruned_loss=0.05671, over 1421282.33 frames.], batch size: 20, lr: 8.33e-04
+2022-04-28 21:03:44,672 INFO [train.py:763] (2/8) Epoch 8, batch 1900, loss[loss=0.186, simple_loss=0.2867, pruned_loss=0.04258, over 7147.00 frames.], tot_loss[loss=0.2044, simple_loss=0.295, pruned_loss=0.05687, over 1419066.00 frames.], batch size: 19, lr: 8.33e-04
+2022-04-28 21:04:50,203 INFO [train.py:763] (2/8) Epoch 8, batch 1950, loss[loss=0.1896, simple_loss=0.2905, pruned_loss=0.04435, over 7114.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2946, pruned_loss=0.05665, over 1419888.33 frames.], batch size: 21, lr: 8.32e-04
+2022-04-28 21:05:55,496 INFO [train.py:763] (2/8) Epoch 8, batch 2000, loss[loss=0.2379, simple_loss=0.3198, pruned_loss=0.07799, over 7296.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2933, pruned_loss=0.05615, over 1420956.92 frames.], batch size: 24, lr: 8.32e-04
+2022-04-28 21:07:00,729 INFO [train.py:763] (2/8) Epoch 8, batch 2050, loss[loss=0.1619, simple_loss=0.2493, pruned_loss=0.03725, over 7275.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2936, pruned_loss=0.05657, over 1421606.32 frames.], batch size: 17, lr: 8.31e-04
+2022-04-28 21:08:05,934 INFO [train.py:763] (2/8) Epoch 8, batch 2100, loss[loss=0.1998, simple_loss=0.2922, pruned_loss=0.05364, over 7252.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2935, pruned_loss=0.05646, over 1422519.01 frames.], batch size: 19, lr: 8.31e-04
+2022-04-28 21:09:08,023 INFO [train.py:763] (2/8) Epoch 8, batch 2150, loss[loss=0.2028, simple_loss=0.293, pruned_loss=0.05627, over 7058.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2929, pruned_loss=0.05604, over 1424459.80 frames.], batch size: 18, lr: 8.30e-04
+2022-04-28 21:10:14,555 INFO [train.py:763] (2/8) Epoch 8, batch 2200, loss[loss=0.1895, simple_loss=0.2701, pruned_loss=0.05442, over 7280.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2925, pruned_loss=0.05637, over 1422717.89 frames.], batch size: 17, lr: 8.30e-04
+2022-04-28 21:11:21,395 INFO [train.py:763] (2/8) Epoch 8, batch 2250, loss[loss=0.179, simple_loss=0.2728, pruned_loss=0.04259, over 7165.00 frames.], tot_loss[loss=0.202, simple_loss=0.2919, pruned_loss=0.05606, over 1423778.58 frames.], batch size: 18, lr: 8.29e-04
+2022-04-28 21:12:26,806 INFO [train.py:763] (2/8) Epoch 8, batch 2300, loss[loss=0.2229, simple_loss=0.3099, pruned_loss=0.06799, over 7145.00 frames.], tot_loss[loss=0.203, simple_loss=0.293, pruned_loss=0.05649, over 1425045.95 frames.], batch size: 20, lr: 8.29e-04
+2022-04-28 21:13:32,123 INFO [train.py:763] (2/8) Epoch 8, batch 2350, loss[loss=0.2142, simple_loss=0.3117, pruned_loss=0.05835, over 6645.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2935, pruned_loss=0.05656, over 1423258.39 frames.], batch size: 31, lr: 8.28e-04
+2022-04-28 21:14:37,448 INFO [train.py:763] (2/8) Epoch 8, batch 2400, loss[loss=0.1597, simple_loss=0.2529, pruned_loss=0.03324, over 7283.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2941, pruned_loss=0.05674, over 1423459.30 frames.], batch size: 18, lr: 8.28e-04
+2022-04-28 21:15:42,875 INFO [train.py:763] (2/8) Epoch 8, batch 2450, loss[loss=0.1833, simple_loss=0.2751, pruned_loss=0.04576, over 7410.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2933, pruned_loss=0.056, over 1425588.76 frames.], batch size: 18, lr: 8.27e-04
+2022-04-28 21:16:48,162 INFO [train.py:763] (2/8) Epoch 8, batch 2500, loss[loss=0.1883, simple_loss=0.291, pruned_loss=0.04285, over 7198.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2943, pruned_loss=0.05643, over 1424430.99 frames.], batch size: 22, lr: 8.27e-04
+2022-04-28 21:17:53,461 INFO [train.py:763] (2/8) Epoch 8, batch 2550, loss[loss=0.1599, simple_loss=0.2525, pruned_loss=0.03363, over 7138.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2935, pruned_loss=0.05608, over 1422387.27 frames.], batch size: 17, lr: 8.26e-04
+2022-04-28 21:18:58,786 INFO [train.py:763] (2/8) Epoch 8, batch 2600, loss[loss=0.2177, simple_loss=0.3166, pruned_loss=0.05942, over 7358.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2938, pruned_loss=0.05637, over 1420512.93 frames.], batch size: 23, lr: 8.25e-04
+2022-04-28 21:20:03,877 INFO [train.py:763] (2/8) Epoch 8, batch 2650, loss[loss=0.2174, simple_loss=0.2976, pruned_loss=0.06857, over 5215.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2931, pruned_loss=0.05613, over 1419157.35 frames.], batch size: 52, lr: 8.25e-04
+2022-04-28 21:21:09,312 INFO [train.py:763] (2/8) Epoch 8, batch 2700, loss[loss=0.2177, simple_loss=0.3185, pruned_loss=0.05845, over 7334.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2939, pruned_loss=0.05616, over 1420095.20 frames.], batch size: 22, lr: 8.24e-04
+2022-04-28 21:22:14,613 INFO [train.py:763] (2/8) Epoch 8, batch 2750, loss[loss=0.2024, simple_loss=0.3037, pruned_loss=0.05056, over 7326.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2932, pruned_loss=0.05596, over 1424014.25 frames.], batch size: 20, lr: 8.24e-04
+2022-04-28 21:23:20,614 INFO [train.py:763] (2/8) Epoch 8, batch 2800, loss[loss=0.1928, simple_loss=0.2836, pruned_loss=0.05102, over 7201.00 frames.], tot_loss[loss=0.2036, simple_loss=0.294, pruned_loss=0.05659, over 1426981.97 frames.], batch size: 22, lr: 8.23e-04
+2022-04-28 21:24:26,771 INFO [train.py:763] (2/8) Epoch 8, batch 2850, loss[loss=0.2221, simple_loss=0.3145, pruned_loss=0.06485, over 7158.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2933, pruned_loss=0.05593, over 1428902.64 frames.], batch size: 19, lr: 8.23e-04
+2022-04-28 21:25:32,041 INFO [train.py:763] (2/8) Epoch 8, batch 2900, loss[loss=0.2219, simple_loss=0.3139, pruned_loss=0.06489, over 7320.00 frames.], tot_loss[loss=0.2019, simple_loss=0.293, pruned_loss=0.05544, over 1427301.20 frames.], batch size: 21, lr: 8.22e-04
+2022-04-28 21:26:37,468 INFO [train.py:763] (2/8) Epoch 8, batch 2950, loss[loss=0.165, simple_loss=0.2578, pruned_loss=0.03609, over 7275.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2938, pruned_loss=0.05583, over 1423383.40 frames.], batch size: 18, lr: 8.22e-04
+2022-04-28 21:27:43,084 INFO [train.py:763] (2/8) Epoch 8, batch 3000, loss[loss=0.2117, simple_loss=0.3057, pruned_loss=0.05886, over 7292.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2931, pruned_loss=0.05576, over 1422249.35 frames.], batch size: 24, lr: 8.21e-04
+2022-04-28 21:27:43,085 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-28 21:27:58,489 INFO [train.py:792] (2/8) Epoch 8, validation: loss=0.1715, simple_loss=0.2766, pruned_loss=0.03324, over 698248.00 frames.
+2022-04-28 21:29:04,150 INFO [train.py:763] (2/8) Epoch 8, batch 3050, loss[loss=0.1639, simple_loss=0.257, pruned_loss=0.03536, over 7325.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2933, pruned_loss=0.05579, over 1418342.86 frames.], batch size: 20, lr: 8.21e-04
+2022-04-28 21:30:09,329 INFO [train.py:763] (2/8) Epoch 8, batch 3100, loss[loss=0.2289, simple_loss=0.313, pruned_loss=0.07236, over 6614.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2944, pruned_loss=0.05625, over 1414000.02 frames.], batch size: 31, lr: 8.20e-04
+2022-04-28 21:31:14,874 INFO [train.py:763] (2/8) Epoch 8, batch 3150, loss[loss=0.1778, simple_loss=0.278, pruned_loss=0.03879, over 7164.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2934, pruned_loss=0.05564, over 1417664.63 frames.], batch size: 19, lr: 8.20e-04
+2022-04-28 21:32:20,532 INFO [train.py:763] (2/8) Epoch 8, batch 3200, loss[loss=0.2419, simple_loss=0.3324, pruned_loss=0.07565, over 7143.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2933, pruned_loss=0.05567, over 1420993.14 frames.], batch size: 20, lr: 8.19e-04
+2022-04-28 21:33:34,629 INFO [train.py:763] (2/8) Epoch 8, batch 3250, loss[loss=0.2611, simple_loss=0.3288, pruned_loss=0.09668, over 5020.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2936, pruned_loss=0.0556, over 1419440.41 frames.], batch size: 52, lr: 8.19e-04
+2022-04-28 21:34:51,669 INFO [train.py:763] (2/8) Epoch 8, batch 3300, loss[loss=0.2008, simple_loss=0.2936, pruned_loss=0.05402, over 7206.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2933, pruned_loss=0.05586, over 1419866.47 frames.], batch size: 22, lr: 8.18e-04
+2022-04-28 21:36:05,887 INFO [train.py:763] (2/8) Epoch 8, batch 3350, loss[loss=0.2027, simple_loss=0.3001, pruned_loss=0.05269, over 7253.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2933, pruned_loss=0.05591, over 1423950.55 frames.], batch size: 19, lr: 8.18e-04
+2022-04-28 21:37:39,076 INFO [train.py:763] (2/8) Epoch 8, batch 3400, loss[loss=0.2416, simple_loss=0.3367, pruned_loss=0.07324, over 6686.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2939, pruned_loss=0.05601, over 1422093.44 frames.], batch size: 31, lr: 8.17e-04
+2022-04-28 21:38:45,185 INFO [train.py:763] (2/8) Epoch 8, batch 3450, loss[loss=0.1764, simple_loss=0.2644, pruned_loss=0.04424, over 7399.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2945, pruned_loss=0.05627, over 1423981.74 frames.], batch size: 18, lr: 8.17e-04
+2022-04-28 21:40:00,473 INFO [train.py:763] (2/8) Epoch 8, batch 3500, loss[loss=0.2219, simple_loss=0.3093, pruned_loss=0.06723, over 7159.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2947, pruned_loss=0.0565, over 1425110.85 frames.], batch size: 19, lr: 8.16e-04
+2022-04-28 21:41:15,116 INFO [train.py:763] (2/8) Epoch 8, batch 3550, loss[loss=0.215, simple_loss=0.2864, pruned_loss=0.07173, over 7163.00 frames.], tot_loss[loss=0.203, simple_loss=0.2935, pruned_loss=0.05619, over 1426376.16 frames.], batch size: 18, lr: 8.16e-04
+2022-04-28 21:42:20,505 INFO [train.py:763] (2/8) Epoch 8, batch 3600, loss[loss=0.1693, simple_loss=0.2577, pruned_loss=0.04052, over 7288.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2936, pruned_loss=0.05612, over 1423849.14 frames.], batch size: 18, lr: 8.15e-04
+2022-04-28 21:43:26,011 INFO [train.py:763] (2/8) Epoch 8, batch 3650, loss[loss=0.181, simple_loss=0.2655, pruned_loss=0.04823, over 7135.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2929, pruned_loss=0.05581, over 1425087.34 frames.], batch size: 17, lr: 8.15e-04
+2022-04-28 21:44:39,928 INFO [train.py:763] (2/8) Epoch 8, batch 3700, loss[loss=0.2497, simple_loss=0.3342, pruned_loss=0.08259, over 7286.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2939, pruned_loss=0.05585, over 1425481.93 frames.], batch size: 25, lr: 8.14e-04
+2022-04-28 21:45:45,257 INFO [train.py:763] (2/8) Epoch 8, batch 3750, loss[loss=0.1775, simple_loss=0.278, pruned_loss=0.03849, over 7429.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2946, pruned_loss=0.056, over 1424472.55 frames.], batch size: 20, lr: 8.14e-04
+2022-04-28 21:46:51,547 INFO [train.py:763] (2/8) Epoch 8, batch 3800, loss[loss=0.1743, simple_loss=0.2588, pruned_loss=0.04485, over 7391.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2943, pruned_loss=0.05573, over 1427336.15 frames.], batch size: 18, lr: 8.13e-04
+2022-04-28 21:47:57,460 INFO [train.py:763] (2/8) Epoch 8, batch 3850, loss[loss=0.1747, simple_loss=0.2604, pruned_loss=0.04452, over 7306.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2938, pruned_loss=0.05567, over 1429240.44 frames.], batch size: 17, lr: 8.13e-04
+2022-04-28 21:49:03,315 INFO [train.py:763] (2/8) Epoch 8, batch 3900, loss[loss=0.2092, simple_loss=0.2961, pruned_loss=0.06118, over 5087.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2941, pruned_loss=0.05589, over 1426443.62 frames.], batch size: 52, lr: 8.12e-04
+2022-04-28 21:50:08,720 INFO [train.py:763] (2/8) Epoch 8, batch 3950, loss[loss=0.2032, simple_loss=0.3032, pruned_loss=0.05157, over 6702.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2938, pruned_loss=0.05557, over 1426722.79 frames.], batch size: 31, lr: 8.12e-04
+2022-04-28 21:51:14,795 INFO [train.py:763] (2/8) Epoch 8, batch 4000, loss[loss=0.2106, simple_loss=0.3116, pruned_loss=0.05474, over 7213.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2949, pruned_loss=0.05618, over 1426454.95 frames.], batch size: 21, lr: 8.11e-04
+2022-04-28 21:52:21,951 INFO [train.py:763] (2/8) Epoch 8, batch 4050, loss[loss=0.1875, simple_loss=0.2725, pruned_loss=0.05126, over 7408.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2935, pruned_loss=0.05544, over 1425550.00 frames.], batch size: 18, lr: 8.11e-04
+2022-04-28 21:53:28,734 INFO [train.py:763] (2/8) Epoch 8, batch 4100, loss[loss=0.1569, simple_loss=0.2359, pruned_loss=0.03895, over 7136.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2915, pruned_loss=0.05454, over 1425943.57 frames.], batch size: 17, lr: 8.10e-04
+2022-04-28 21:54:34,089 INFO [train.py:763] (2/8) Epoch 8, batch 4150, loss[loss=0.2279, simple_loss=0.3161, pruned_loss=0.06985, over 7116.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2915, pruned_loss=0.05463, over 1421144.03 frames.], batch size: 28, lr: 8.10e-04
+2022-04-28 21:55:39,787 INFO [train.py:763] (2/8) Epoch 8, batch 4200, loss[loss=0.1818, simple_loss=0.277, pruned_loss=0.04328, over 7338.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2897, pruned_loss=0.05384, over 1422669.55 frames.], batch size: 20, lr: 8.09e-04
+2022-04-28 21:56:45,194 INFO [train.py:763] (2/8) Epoch 8, batch 4250, loss[loss=0.1781, simple_loss=0.2606, pruned_loss=0.04782, over 7140.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2898, pruned_loss=0.05424, over 1419462.24 frames.], batch size: 17, lr: 8.09e-04
+2022-04-28 21:57:50,929 INFO [train.py:763] (2/8) Epoch 8, batch 4300, loss[loss=0.222, simple_loss=0.3245, pruned_loss=0.05975, over 7411.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2892, pruned_loss=0.05407, over 1415471.23 frames.], batch size: 21, lr: 8.08e-04
+2022-04-28 21:58:56,620 INFO [train.py:763] (2/8) Epoch 8, batch 4350, loss[loss=0.1761, simple_loss=0.2549, pruned_loss=0.04858, over 7274.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2893, pruned_loss=0.05395, over 1421300.15 frames.], batch size: 17, lr: 8.08e-04
+2022-04-28 22:00:02,325 INFO [train.py:763] (2/8) Epoch 8, batch 4400, loss[loss=0.2032, simple_loss=0.3068, pruned_loss=0.04981, over 7065.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2892, pruned_loss=0.05405, over 1416729.73 frames.], batch size: 28, lr: 8.07e-04
+2022-04-28 22:01:09,617 INFO [train.py:763] (2/8) Epoch 8, batch 4450, loss[loss=0.2217, simple_loss=0.3066, pruned_loss=0.06846, over 6990.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2879, pruned_loss=0.05378, over 1411739.16 frames.], batch size: 28, lr: 8.07e-04
+2022-04-28 22:02:15,952 INFO [train.py:763] (2/8) Epoch 8, batch 4500, loss[loss=0.1987, simple_loss=0.2995, pruned_loss=0.04902, over 7120.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2907, pruned_loss=0.05593, over 1393413.97 frames.], batch size: 28, lr: 8.07e-04
+2022-04-28 22:03:19,877 INFO [train.py:763] (2/8) Epoch 8, batch 4550, loss[loss=0.2411, simple_loss=0.328, pruned_loss=0.07713, over 6340.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2951, pruned_loss=0.05861, over 1352856.85 frames.], batch size: 37, lr: 8.06e-04
+2022-04-28 22:04:39,796 INFO [train.py:763] (2/8) Epoch 9, batch 0, loss[loss=0.1914, simple_loss=0.29, pruned_loss=0.04643, over 7409.00 frames.], tot_loss[loss=0.1914, simple_loss=0.29, pruned_loss=0.04643, over 7409.00 frames.], batch size: 21, lr: 7.75e-04
+2022-04-28 22:05:45,910 INFO [train.py:763] (2/8) Epoch 9, batch 50, loss[loss=0.2119, simple_loss=0.321, pruned_loss=0.05144, over 7209.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2956, pruned_loss=0.05784, over 321688.00 frames.], batch size: 23, lr: 7.74e-04
+2022-04-28 22:06:51,596 INFO [train.py:763] (2/8) Epoch 9, batch 100, loss[loss=0.24, simple_loss=0.3261, pruned_loss=0.07692, over 4742.00 frames.], tot_loss[loss=0.2026, simple_loss=0.292, pruned_loss=0.05659, over 558320.72 frames.], batch size: 52, lr: 7.74e-04
+2022-04-28 22:07:57,278 INFO [train.py:763] (2/8) Epoch 9, batch 150, loss[loss=0.1996, simple_loss=0.2932, pruned_loss=0.05297, over 7432.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2896, pruned_loss=0.05398, over 751148.62 frames.], batch size: 20, lr: 7.73e-04
+2022-04-28 22:09:03,713 INFO [train.py:763] (2/8) Epoch 9, batch 200, loss[loss=0.1987, simple_loss=0.2913, pruned_loss=0.05304, over 7434.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2899, pruned_loss=0.05376, over 898230.97 frames.], batch size: 20, lr: 7.73e-04
+2022-04-28 22:10:10,397 INFO [train.py:763] (2/8) Epoch 9, batch 250, loss[loss=0.2144, simple_loss=0.2893, pruned_loss=0.06979, over 7151.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2913, pruned_loss=0.05403, over 1010597.21 frames.], batch size: 18, lr: 7.72e-04
+2022-04-28 22:11:16,227 INFO [train.py:763] (2/8) Epoch 9, batch 300, loss[loss=0.1966, simple_loss=0.2958, pruned_loss=0.04874, over 7325.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2915, pruned_loss=0.05417, over 1104523.80 frames.], batch size: 20, lr: 7.72e-04
+2022-04-28 22:12:21,601 INFO [train.py:763] (2/8) Epoch 9, batch 350, loss[loss=0.1952, simple_loss=0.2826, pruned_loss=0.05384, over 7209.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2915, pruned_loss=0.05379, over 1172909.49 frames.], batch size: 23, lr: 7.71e-04
+2022-04-28 22:13:26,943 INFO [train.py:763] (2/8) Epoch 9, batch 400, loss[loss=0.2024, simple_loss=0.3028, pruned_loss=0.05103, over 7188.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2921, pruned_loss=0.05409, over 1223782.56 frames.], batch size: 26, lr: 7.71e-04
+2022-04-28 22:14:32,124 INFO [train.py:763] (2/8) Epoch 9, batch 450, loss[loss=0.2264, simple_loss=0.3054, pruned_loss=0.07371, over 6245.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2927, pruned_loss=0.05437, over 1262606.70 frames.], batch size: 37, lr: 7.71e-04
+2022-04-28 22:15:37,755 INFO [train.py:763] (2/8) Epoch 9, batch 500, loss[loss=0.2084, simple_loss=0.3031, pruned_loss=0.05688, over 7162.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2927, pruned_loss=0.05443, over 1297444.51 frames.], batch size: 19, lr: 7.70e-04
+2022-04-28 22:16:43,390 INFO [train.py:763] (2/8) Epoch 9, batch 550, loss[loss=0.1822, simple_loss=0.2722, pruned_loss=0.04613, over 7109.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2919, pruned_loss=0.05378, over 1325659.16 frames.], batch size: 17, lr: 7.70e-04
+2022-04-28 22:17:49,456 INFO [train.py:763] (2/8) Epoch 9, batch 600, loss[loss=0.2006, simple_loss=0.2866, pruned_loss=0.05731, over 7282.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2928, pruned_loss=0.05439, over 1346380.05 frames.], batch size: 18, lr: 7.69e-04
+2022-04-28 22:18:54,911 INFO [train.py:763] (2/8) Epoch 9, batch 650, loss[loss=0.2067, simple_loss=0.3025, pruned_loss=0.05549, over 7189.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2926, pruned_loss=0.05437, over 1362786.33 frames.], batch size: 26, lr: 7.69e-04
+2022-04-28 22:20:00,483 INFO [train.py:763] (2/8) Epoch 9, batch 700, loss[loss=0.2274, simple_loss=0.3154, pruned_loss=0.0697, over 7308.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2924, pruned_loss=0.05438, over 1377315.13 frames.], batch size: 25, lr: 7.68e-04
+2022-04-28 22:21:06,840 INFO [train.py:763] (2/8) Epoch 9, batch 750, loss[loss=0.2109, simple_loss=0.2965, pruned_loss=0.06265, over 7432.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2919, pruned_loss=0.05455, over 1386933.28 frames.], batch size: 20, lr: 7.68e-04
+2022-04-28 22:22:12,198 INFO [train.py:763] (2/8) Epoch 9, batch 800, loss[loss=0.1856, simple_loss=0.2862, pruned_loss=0.04254, over 7297.00 frames.], tot_loss[loss=0.1995, simple_loss=0.291, pruned_loss=0.05397, over 1394398.20 frames.], batch size: 24, lr: 7.67e-04
+2022-04-28 22:23:17,411 INFO [train.py:763] (2/8) Epoch 9, batch 850, loss[loss=0.1997, simple_loss=0.2977, pruned_loss=0.05091, over 6232.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2924, pruned_loss=0.05471, over 1398108.39 frames.], batch size: 37, lr: 7.67e-04
+2022-04-28 22:24:22,754 INFO [train.py:763] (2/8) Epoch 9, batch 900, loss[loss=0.224, simple_loss=0.314, pruned_loss=0.06699, over 7327.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2924, pruned_loss=0.05448, over 1407483.88 frames.], batch size: 21, lr: 7.66e-04
+2022-04-28 22:25:27,952 INFO [train.py:763] (2/8) Epoch 9, batch 950, loss[loss=0.1928, simple_loss=0.2909, pruned_loss=0.04737, over 7120.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2929, pruned_loss=0.05438, over 1406934.07 frames.], batch size: 26, lr: 7.66e-04
+2022-04-28 22:26:33,997 INFO [train.py:763] (2/8) Epoch 9, batch 1000, loss[loss=0.1674, simple_loss=0.2626, pruned_loss=0.03616, over 7325.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2919, pruned_loss=0.05388, over 1414277.73 frames.], batch size: 20, lr: 7.66e-04
+2022-04-28 22:27:40,361 INFO [train.py:763] (2/8) Epoch 9, batch 1050, loss[loss=0.2096, simple_loss=0.3117, pruned_loss=0.05377, over 7025.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2915, pruned_loss=0.05353, over 1416796.52 frames.], batch size: 28, lr: 7.65e-04
+2022-04-28 22:28:46,000 INFO [train.py:763] (2/8) Epoch 9, batch 1100, loss[loss=0.1915, simple_loss=0.2865, pruned_loss=0.0483, over 7078.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2908, pruned_loss=0.05319, over 1416992.71 frames.], batch size: 28, lr: 7.65e-04
+2022-04-28 22:29:52,328 INFO [train.py:763] (2/8) Epoch 9, batch 1150, loss[loss=0.1702, simple_loss=0.2653, pruned_loss=0.03757, over 7340.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2906, pruned_loss=0.05292, over 1420960.58 frames.], batch size: 20, lr: 7.64e-04
+2022-04-28 22:30:57,643 INFO [train.py:763] (2/8) Epoch 9, batch 1200, loss[loss=0.2137, simple_loss=0.3078, pruned_loss=0.05981, over 7198.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2913, pruned_loss=0.05359, over 1420229.14 frames.], batch size: 23, lr: 7.64e-04
+2022-04-28 22:32:04,403 INFO [train.py:763] (2/8) Epoch 9, batch 1250, loss[loss=0.173, simple_loss=0.2532, pruned_loss=0.04642, over 7272.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2917, pruned_loss=0.05425, over 1418487.97 frames.], batch size: 17, lr: 7.63e-04
+2022-04-28 22:33:11,154 INFO [train.py:763] (2/8) Epoch 9, batch 1300, loss[loss=0.1995, simple_loss=0.2807, pruned_loss=0.05913, over 6995.00 frames.], tot_loss[loss=0.2, simple_loss=0.2909, pruned_loss=0.05455, over 1416705.84 frames.], batch size: 16, lr: 7.63e-04
+2022-04-28 22:34:16,570 INFO [train.py:763] (2/8) Epoch 9, batch 1350, loss[loss=0.2013, simple_loss=0.2967, pruned_loss=0.05301, over 7328.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2908, pruned_loss=0.05469, over 1415454.07 frames.], batch size: 21, lr: 7.62e-04
+2022-04-28 22:35:21,674 INFO [train.py:763] (2/8) Epoch 9, batch 1400, loss[loss=0.2268, simple_loss=0.3131, pruned_loss=0.07023, over 7125.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2921, pruned_loss=0.05462, over 1418953.93 frames.], batch size: 21, lr: 7.62e-04
+2022-04-28 22:36:27,458 INFO [train.py:763] (2/8) Epoch 9, batch 1450, loss[loss=0.2735, simple_loss=0.3639, pruned_loss=0.09157, over 7295.00 frames.], tot_loss[loss=0.2, simple_loss=0.2911, pruned_loss=0.05443, over 1419919.57 frames.], batch size: 25, lr: 7.62e-04
+2022-04-28 22:37:33,360 INFO [train.py:763] (2/8) Epoch 9, batch 1500, loss[loss=0.1897, simple_loss=0.2749, pruned_loss=0.05221, over 5291.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2915, pruned_loss=0.05447, over 1416269.30 frames.], batch size: 53, lr: 7.61e-04
+2022-04-28 22:38:38,705 INFO [train.py:763] (2/8) Epoch 9, batch 1550, loss[loss=0.1941, simple_loss=0.2936, pruned_loss=0.04726, over 7362.00 frames.], tot_loss[loss=0.1994, simple_loss=0.291, pruned_loss=0.05393, over 1419924.39 frames.], batch size: 19, lr: 7.61e-04
+2022-04-28 22:39:43,987 INFO [train.py:763] (2/8) Epoch 9, batch 1600, loss[loss=0.1725, simple_loss=0.2688, pruned_loss=0.03808, over 7255.00 frames.], tot_loss[loss=0.1986, simple_loss=0.29, pruned_loss=0.05358, over 1418592.16 frames.], batch size: 19, lr: 7.60e-04
+2022-04-28 22:40:50,095 INFO [train.py:763] (2/8) Epoch 9, batch 1650, loss[loss=0.1992, simple_loss=0.2905, pruned_loss=0.05396, over 7414.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2894, pruned_loss=0.05376, over 1416097.85 frames.], batch size: 21, lr: 7.60e-04
+2022-04-28 22:41:56,339 INFO [train.py:763] (2/8) Epoch 9, batch 1700, loss[loss=0.2033, simple_loss=0.2987, pruned_loss=0.05398, over 7277.00 frames.], tot_loss[loss=0.199, simple_loss=0.2898, pruned_loss=0.05409, over 1413540.95 frames.], batch size: 24, lr: 7.59e-04
+2022-04-28 22:43:01,517 INFO [train.py:763] (2/8) Epoch 9, batch 1750, loss[loss=0.1662, simple_loss=0.2392, pruned_loss=0.04654, over 6744.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2905, pruned_loss=0.05442, over 1405278.26 frames.], batch size: 15, lr: 7.59e-04
+2022-04-28 22:44:07,084 INFO [train.py:763] (2/8) Epoch 9, batch 1800, loss[loss=0.2231, simple_loss=0.3181, pruned_loss=0.06401, over 7359.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2906, pruned_loss=0.05443, over 1410917.87 frames.], batch size: 19, lr: 7.59e-04
+2022-04-28 22:45:14,102 INFO [train.py:763] (2/8) Epoch 9, batch 1850, loss[loss=0.1931, simple_loss=0.2806, pruned_loss=0.05281, over 7366.00 frames.], tot_loss[loss=0.2, simple_loss=0.2907, pruned_loss=0.05465, over 1411619.85 frames.], batch size: 19, lr: 7.58e-04
+2022-04-28 22:46:21,652 INFO [train.py:763] (2/8) Epoch 9, batch 1900, loss[loss=0.175, simple_loss=0.269, pruned_loss=0.04052, over 7279.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2906, pruned_loss=0.05453, over 1416215.15 frames.], batch size: 18, lr: 7.58e-04
+2022-04-28 22:47:28,652 INFO [train.py:763] (2/8) Epoch 9, batch 1950, loss[loss=0.1901, simple_loss=0.2863, pruned_loss=0.04696, over 7199.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2899, pruned_loss=0.05469, over 1415003.79 frames.], batch size: 23, lr: 7.57e-04
+2022-04-28 22:48:34,053 INFO [train.py:763] (2/8) Epoch 9, batch 2000, loss[loss=0.1796, simple_loss=0.2859, pruned_loss=0.03665, over 7226.00 frames.], tot_loss[loss=0.1982, simple_loss=0.289, pruned_loss=0.05367, over 1418796.15 frames.], batch size: 20, lr: 7.57e-04
+2022-04-28 22:49:39,698 INFO [train.py:763] (2/8) Epoch 9, batch 2050, loss[loss=0.2148, simple_loss=0.3082, pruned_loss=0.06066, over 7185.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2892, pruned_loss=0.05332, over 1420363.84 frames.], batch size: 23, lr: 7.56e-04
+2022-04-28 22:50:45,162 INFO [train.py:763] (2/8) Epoch 9, batch 2100, loss[loss=0.2087, simple_loss=0.3015, pruned_loss=0.05794, over 7146.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2889, pruned_loss=0.05261, over 1424555.75 frames.], batch size: 20, lr: 7.56e-04
+2022-04-28 22:51:50,834 INFO [train.py:763] (2/8) Epoch 9, batch 2150, loss[loss=0.1876, simple_loss=0.276, pruned_loss=0.04957, over 7434.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2884, pruned_loss=0.05245, over 1426927.14 frames.], batch size: 18, lr: 7.56e-04
+2022-04-28 22:52:56,056 INFO [train.py:763] (2/8) Epoch 9, batch 2200, loss[loss=0.1953, simple_loss=0.2939, pruned_loss=0.04835, over 6353.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2892, pruned_loss=0.05252, over 1427209.45 frames.], batch size: 37, lr: 7.55e-04
+2022-04-28 22:54:01,585 INFO [train.py:763] (2/8) Epoch 9, batch 2250, loss[loss=0.198, simple_loss=0.2968, pruned_loss=0.04964, over 7326.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2894, pruned_loss=0.05279, over 1428660.29 frames.], batch size: 21, lr: 7.55e-04
+2022-04-28 22:55:07,218 INFO [train.py:763] (2/8) Epoch 9, batch 2300, loss[loss=0.2014, simple_loss=0.3005, pruned_loss=0.05117, over 7141.00 frames.], tot_loss[loss=0.1981, simple_loss=0.29, pruned_loss=0.05313, over 1426938.90 frames.], batch size: 20, lr: 7.54e-04
+2022-04-28 22:56:13,145 INFO [train.py:763] (2/8) Epoch 9, batch 2350, loss[loss=0.2204, simple_loss=0.3032, pruned_loss=0.06877, over 7218.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2896, pruned_loss=0.05312, over 1424802.24 frames.], batch size: 22, lr: 7.54e-04
+2022-04-28 22:57:18,358 INFO [train.py:763] (2/8) Epoch 9, batch 2400, loss[loss=0.1449, simple_loss=0.2449, pruned_loss=0.02249, over 7290.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2888, pruned_loss=0.05293, over 1426894.41 frames.], batch size: 18, lr: 7.53e-04
+2022-04-28 22:58:24,893 INFO [train.py:763] (2/8) Epoch 9, batch 2450, loss[loss=0.193, simple_loss=0.2777, pruned_loss=0.05417, over 7064.00 frames.], tot_loss[loss=0.1976, simple_loss=0.289, pruned_loss=0.05305, over 1430201.80 frames.], batch size: 18, lr: 7.53e-04
+2022-04-28 22:59:30,585 INFO [train.py:763] (2/8) Epoch 9, batch 2500, loss[loss=0.2239, simple_loss=0.3086, pruned_loss=0.06962, over 7317.00 frames.], tot_loss[loss=0.1979, simple_loss=0.289, pruned_loss=0.05336, over 1428112.34 frames.], batch size: 21, lr: 7.53e-04
+2022-04-28 23:00:35,853 INFO [train.py:763] (2/8) Epoch 9, batch 2550, loss[loss=0.222, simple_loss=0.3146, pruned_loss=0.06473, over 7216.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2884, pruned_loss=0.05316, over 1426329.98 frames.], batch size: 21, lr: 7.52e-04
+2022-04-28 23:01:42,059 INFO [train.py:763] (2/8) Epoch 9, batch 2600, loss[loss=0.1947, simple_loss=0.2883, pruned_loss=0.0505, over 7145.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2883, pruned_loss=0.05274, over 1429270.34 frames.], batch size: 26, lr: 7.52e-04
+2022-04-28 23:02:47,157 INFO [train.py:763] (2/8) Epoch 9, batch 2650, loss[loss=0.2065, simple_loss=0.3085, pruned_loss=0.05228, over 7337.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2896, pruned_loss=0.05334, over 1425400.31 frames.], batch size: 22, lr: 7.51e-04
+2022-04-28 23:03:53,443 INFO [train.py:763] (2/8) Epoch 9, batch 2700, loss[loss=0.2002, simple_loss=0.2999, pruned_loss=0.05026, over 6803.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2891, pruned_loss=0.05275, over 1426049.18 frames.], batch size: 31, lr: 7.51e-04
+2022-04-28 23:04:58,881 INFO [train.py:763] (2/8) Epoch 9, batch 2750, loss[loss=0.2036, simple_loss=0.3127, pruned_loss=0.04728, over 6882.00 frames.], tot_loss[loss=0.197, simple_loss=0.2886, pruned_loss=0.05276, over 1423812.42 frames.], batch size: 31, lr: 7.50e-04
+2022-04-28 23:06:04,514 INFO [train.py:763] (2/8) Epoch 9, batch 2800, loss[loss=0.233, simple_loss=0.3203, pruned_loss=0.07283, over 7402.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2884, pruned_loss=0.05265, over 1429461.28 frames.], batch size: 23, lr: 7.50e-04
+2022-04-28 23:07:09,868 INFO [train.py:763] (2/8) Epoch 9, batch 2850, loss[loss=0.234, simple_loss=0.3158, pruned_loss=0.07605, over 7337.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2889, pruned_loss=0.05308, over 1427354.83 frames.], batch size: 22, lr: 7.50e-04
+2022-04-28 23:08:15,553 INFO [train.py:763] (2/8) Epoch 9, batch 2900, loss[loss=0.2092, simple_loss=0.3141, pruned_loss=0.05213, over 7108.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2886, pruned_loss=0.05309, over 1426075.54 frames.], batch size: 21, lr: 7.49e-04
+2022-04-28 23:09:22,014 INFO [train.py:763] (2/8) Epoch 9, batch 2950, loss[loss=0.1658, simple_loss=0.2549, pruned_loss=0.03833, over 7276.00 frames.], tot_loss[loss=0.198, simple_loss=0.2886, pruned_loss=0.05368, over 1426402.80 frames.], batch size: 18, lr: 7.49e-04
+2022-04-28 23:10:28,989 INFO [train.py:763] (2/8) Epoch 9, batch 3000, loss[loss=0.1424, simple_loss=0.2322, pruned_loss=0.02629, over 7284.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2883, pruned_loss=0.05325, over 1425733.13 frames.], batch size: 17, lr: 7.48e-04
+2022-04-28 23:10:28,990 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-28 23:10:44,551 INFO [train.py:792] (2/8) Epoch 9, validation: loss=0.1713, simple_loss=0.276, pruned_loss=0.03324, over 698248.00 frames.
+2022-04-28 23:11:50,374 INFO [train.py:763] (2/8) Epoch 9, batch 3050, loss[loss=0.2123, simple_loss=0.2929, pruned_loss=0.06582, over 7161.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2883, pruned_loss=0.05349, over 1425195.95 frames.], batch size: 19, lr: 7.48e-04
+2022-04-28 23:12:55,856 INFO [train.py:763] (2/8) Epoch 9, batch 3100, loss[loss=0.1641, simple_loss=0.2817, pruned_loss=0.02332, over 7112.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2885, pruned_loss=0.05306, over 1428130.42 frames.], batch size: 21, lr: 7.47e-04
+2022-04-28 23:14:01,343 INFO [train.py:763] (2/8) Epoch 9, batch 3150, loss[loss=0.2113, simple_loss=0.3029, pruned_loss=0.05989, over 7325.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2884, pruned_loss=0.05251, over 1424712.29 frames.], batch size: 21, lr: 7.47e-04
+2022-04-28 23:15:07,614 INFO [train.py:763] (2/8) Epoch 9, batch 3200, loss[loss=0.1965, simple_loss=0.2838, pruned_loss=0.05458, over 7246.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2872, pruned_loss=0.05181, over 1425148.10 frames.], batch size: 20, lr: 7.47e-04
+2022-04-28 23:16:13,883 INFO [train.py:763] (2/8) Epoch 9, batch 3250, loss[loss=0.198, simple_loss=0.3051, pruned_loss=0.04544, over 7418.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2885, pruned_loss=0.05243, over 1426281.14 frames.], batch size: 21, lr: 7.46e-04
+2022-04-28 23:17:19,389 INFO [train.py:763] (2/8) Epoch 9, batch 3300, loss[loss=0.2002, simple_loss=0.3021, pruned_loss=0.04911, over 7205.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2891, pruned_loss=0.05261, over 1427429.11 frames.], batch size: 22, lr: 7.46e-04
+2022-04-28 23:18:25,151 INFO [train.py:763] (2/8) Epoch 9, batch 3350, loss[loss=0.2056, simple_loss=0.3058, pruned_loss=0.0527, over 7206.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2891, pruned_loss=0.05274, over 1428436.98 frames.], batch size: 23, lr: 7.45e-04
+2022-04-28 23:19:31,228 INFO [train.py:763] (2/8) Epoch 9, batch 3400, loss[loss=0.1828, simple_loss=0.2687, pruned_loss=0.04849, over 7280.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2887, pruned_loss=0.0528, over 1424417.31 frames.], batch size: 17, lr: 7.45e-04
+2022-04-28 23:20:36,535 INFO [train.py:763] (2/8) Epoch 9, batch 3450, loss[loss=0.2221, simple_loss=0.3218, pruned_loss=0.06125, over 7304.00 frames.], tot_loss[loss=0.198, simple_loss=0.2896, pruned_loss=0.05326, over 1424008.10 frames.], batch size: 24, lr: 7.45e-04
+2022-04-28 23:21:42,129 INFO [train.py:763] (2/8) Epoch 9, batch 3500, loss[loss=0.2127, simple_loss=0.3179, pruned_loss=0.05375, over 7411.00 frames.], tot_loss[loss=0.198, simple_loss=0.2895, pruned_loss=0.0533, over 1423429.32 frames.], batch size: 21, lr: 7.44e-04
+2022-04-28 23:22:49,851 INFO [train.py:763] (2/8) Epoch 9, batch 3550, loss[loss=0.2051, simple_loss=0.2992, pruned_loss=0.05553, over 7093.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2879, pruned_loss=0.05235, over 1426382.52 frames.], batch size: 28, lr: 7.44e-04
+2022-04-28 23:23:55,514 INFO [train.py:763] (2/8) Epoch 9, batch 3600, loss[loss=0.2047, simple_loss=0.2894, pruned_loss=0.05997, over 6985.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2878, pruned_loss=0.05247, over 1426857.29 frames.], batch size: 28, lr: 7.43e-04
+2022-04-28 23:25:02,070 INFO [train.py:763] (2/8) Epoch 9, batch 3650, loss[loss=0.159, simple_loss=0.2525, pruned_loss=0.03276, over 7072.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2878, pruned_loss=0.05244, over 1422739.36 frames.], batch size: 18, lr: 7.43e-04
+2022-04-28 23:26:07,305 INFO [train.py:763] (2/8) Epoch 9, batch 3700, loss[loss=0.1527, simple_loss=0.2384, pruned_loss=0.03353, over 7268.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2881, pruned_loss=0.0521, over 1424954.62 frames.], batch size: 17, lr: 7.43e-04
+2022-04-28 23:27:12,603 INFO [train.py:763] (2/8) Epoch 9, batch 3750, loss[loss=0.1967, simple_loss=0.2829, pruned_loss=0.05528, over 7166.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2887, pruned_loss=0.05252, over 1428176.26 frames.], batch size: 19, lr: 7.42e-04
+2022-04-28 23:28:17,822 INFO [train.py:763] (2/8) Epoch 9, batch 3800, loss[loss=0.2093, simple_loss=0.2993, pruned_loss=0.05966, over 7441.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2891, pruned_loss=0.05266, over 1426256.84 frames.], batch size: 20, lr: 7.42e-04
+2022-04-28 23:29:23,008 INFO [train.py:763] (2/8) Epoch 9, batch 3850, loss[loss=0.1676, simple_loss=0.2613, pruned_loss=0.03697, over 7070.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2897, pruned_loss=0.053, over 1425516.89 frames.], batch size: 18, lr: 7.41e-04
+2022-04-28 23:30:28,552 INFO [train.py:763] (2/8) Epoch 9, batch 3900, loss[loss=0.1912, simple_loss=0.2795, pruned_loss=0.05142, over 7158.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2896, pruned_loss=0.05284, over 1427417.60 frames.], batch size: 19, lr: 7.41e-04
+2022-04-28 23:31:35,175 INFO [train.py:763] (2/8) Epoch 9, batch 3950, loss[loss=0.2446, simple_loss=0.3202, pruned_loss=0.08451, over 5208.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2897, pruned_loss=0.05296, over 1421993.24 frames.], batch size: 52, lr: 7.41e-04
+2022-04-28 23:32:42,029 INFO [train.py:763] (2/8) Epoch 9, batch 4000, loss[loss=0.1846, simple_loss=0.2763, pruned_loss=0.04643, over 7249.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2901, pruned_loss=0.05278, over 1422709.53 frames.], batch size: 19, lr: 7.40e-04
+2022-04-28 23:33:47,286 INFO [train.py:763] (2/8) Epoch 9, batch 4050, loss[loss=0.1794, simple_loss=0.2639, pruned_loss=0.04743, over 7130.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2909, pruned_loss=0.05311, over 1423275.45 frames.], batch size: 17, lr: 7.40e-04
+2022-04-28 23:34:53,524 INFO [train.py:763] (2/8) Epoch 9, batch 4100, loss[loss=0.2185, simple_loss=0.3144, pruned_loss=0.06125, over 7323.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2905, pruned_loss=0.05284, over 1425164.12 frames.], batch size: 21, lr: 7.39e-04
+2022-04-28 23:35:59,478 INFO [train.py:763] (2/8) Epoch 9, batch 4150, loss[loss=0.1717, simple_loss=0.258, pruned_loss=0.04266, over 7427.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2901, pruned_loss=0.05261, over 1425406.29 frames.], batch size: 18, lr: 7.39e-04
+2022-04-28 23:37:04,697 INFO [train.py:763] (2/8) Epoch 9, batch 4200, loss[loss=0.1835, simple_loss=0.2807, pruned_loss=0.04316, over 7295.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2905, pruned_loss=0.05301, over 1427485.55 frames.], batch size: 24, lr: 7.39e-04
+2022-04-28 23:38:10,554 INFO [train.py:763] (2/8) Epoch 9, batch 4250, loss[loss=0.1721, simple_loss=0.2504, pruned_loss=0.04688, over 7261.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2908, pruned_loss=0.05309, over 1422869.10 frames.], batch size: 17, lr: 7.38e-04
+2022-04-28 23:39:16,463 INFO [train.py:763] (2/8) Epoch 9, batch 4300, loss[loss=0.2053, simple_loss=0.3028, pruned_loss=0.05387, over 7316.00 frames.], tot_loss[loss=0.198, simple_loss=0.2903, pruned_loss=0.05284, over 1416778.14 frames.], batch size: 24, lr: 7.38e-04
+2022-04-28 23:40:22,450 INFO [train.py:763] (2/8) Epoch 9, batch 4350, loss[loss=0.2562, simple_loss=0.3267, pruned_loss=0.09283, over 4968.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2917, pruned_loss=0.05349, over 1406678.17 frames.], batch size: 53, lr: 7.37e-04
+2022-04-28 23:41:28,471 INFO [train.py:763] (2/8) Epoch 9, batch 4400, loss[loss=0.2221, simple_loss=0.322, pruned_loss=0.06114, over 7201.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2916, pruned_loss=0.05347, over 1409477.90 frames.], batch size: 22, lr: 7.37e-04
+2022-04-28 23:42:35,220 INFO [train.py:763] (2/8) Epoch 9, batch 4450, loss[loss=0.2457, simple_loss=0.3198, pruned_loss=0.08578, over 5002.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2926, pruned_loss=0.05458, over 1394414.94 frames.], batch size: 52, lr: 7.37e-04
+2022-04-28 23:43:41,391 INFO [train.py:763] (2/8) Epoch 9, batch 4500, loss[loss=0.258, simple_loss=0.3415, pruned_loss=0.08721, over 7143.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2925, pruned_loss=0.0547, over 1390610.08 frames.], batch size: 20, lr: 7.36e-04
+2022-04-28 23:44:47,990 INFO [train.py:763] (2/8) Epoch 9, batch 4550, loss[loss=0.2328, simple_loss=0.3152, pruned_loss=0.07517, over 7197.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2923, pruned_loss=0.05548, over 1371370.16 frames.], batch size: 26, lr: 7.36e-04
+2022-04-28 23:46:26,278 INFO [train.py:763] (2/8) Epoch 10, batch 0, loss[loss=0.2376, simple_loss=0.3157, pruned_loss=0.07972, over 7424.00 frames.], tot_loss[loss=0.2376, simple_loss=0.3157, pruned_loss=0.07972, over 7424.00 frames.], batch size: 20, lr: 7.08e-04
+2022-04-28 23:47:32,323 INFO [train.py:763] (2/8) Epoch 10, batch 50, loss[loss=0.1931, simple_loss=0.2928, pruned_loss=0.04672, over 7436.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2897, pruned_loss=0.04959, over 323096.65 frames.], batch size: 20, lr: 7.08e-04
+2022-04-28 23:48:38,906 INFO [train.py:763] (2/8) Epoch 10, batch 100, loss[loss=0.1651, simple_loss=0.2556, pruned_loss=0.03732, over 7274.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2882, pruned_loss=0.05027, over 566821.90 frames.], batch size: 18, lr: 7.08e-04
+2022-04-28 23:49:55,132 INFO [train.py:763] (2/8) Epoch 10, batch 150, loss[loss=0.1781, simple_loss=0.2633, pruned_loss=0.04646, over 6773.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2901, pruned_loss=0.05126, over 759599.70 frames.], batch size: 15, lr: 7.07e-04
+2022-04-28 23:51:18,544 INFO [train.py:763] (2/8) Epoch 10, batch 200, loss[loss=0.1444, simple_loss=0.2326, pruned_loss=0.02815, over 7410.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2883, pruned_loss=0.05075, over 906823.00 frames.], batch size: 18, lr: 7.07e-04
+2022-04-28 23:52:32,862 INFO [train.py:763] (2/8) Epoch 10, batch 250, loss[loss=0.2214, simple_loss=0.3119, pruned_loss=0.06546, over 6403.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2862, pruned_loss=0.04965, over 1022059.26 frames.], batch size: 38, lr: 7.06e-04
+2022-04-28 23:53:48,227 INFO [train.py:763] (2/8) Epoch 10, batch 300, loss[loss=0.2505, simple_loss=0.3208, pruned_loss=0.09011, over 5133.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2863, pruned_loss=0.04975, over 1113567.39 frames.], batch size: 53, lr: 7.06e-04
+2022-04-28 23:54:53,615 INFO [train.py:763] (2/8) Epoch 10, batch 350, loss[loss=0.1964, simple_loss=0.295, pruned_loss=0.04893, over 6831.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2875, pruned_loss=0.05064, over 1185937.48 frames.], batch size: 31, lr: 7.06e-04
+2022-04-28 23:56:17,498 INFO [train.py:763] (2/8) Epoch 10, batch 400, loss[loss=0.2121, simple_loss=0.3013, pruned_loss=0.06147, over 7431.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2862, pruned_loss=0.05013, over 1240076.81 frames.], batch size: 20, lr: 7.05e-04
+2022-04-28 23:57:23,250 INFO [train.py:763] (2/8) Epoch 10, batch 450, loss[loss=0.2129, simple_loss=0.3056, pruned_loss=0.06008, over 7232.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2847, pruned_loss=0.04958, over 1280942.43 frames.], batch size: 20, lr: 7.05e-04
+2022-04-28 23:58:37,636 INFO [train.py:763] (2/8) Epoch 10, batch 500, loss[loss=0.2104, simple_loss=0.3012, pruned_loss=0.05977, over 7326.00 frames.], tot_loss[loss=0.192, simple_loss=0.285, pruned_loss=0.04949, over 1315536.07 frames.], batch size: 20, lr: 7.04e-04
+2022-04-28 23:59:42,722 INFO [train.py:763] (2/8) Epoch 10, batch 550, loss[loss=0.1871, simple_loss=0.2723, pruned_loss=0.05099, over 7068.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2857, pruned_loss=0.05005, over 1341056.77 frames.], batch size: 18, lr: 7.04e-04
+2022-04-29 00:00:47,811 INFO [train.py:763] (2/8) Epoch 10, batch 600, loss[loss=0.1712, simple_loss=0.2643, pruned_loss=0.03901, over 7002.00 frames.], tot_loss[loss=0.194, simple_loss=0.2868, pruned_loss=0.05062, over 1360150.10 frames.], batch size: 16, lr: 7.04e-04
+2022-04-29 00:01:53,005 INFO [train.py:763] (2/8) Epoch 10, batch 650, loss[loss=0.1584, simple_loss=0.2469, pruned_loss=0.03494, over 7129.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2868, pruned_loss=0.0507, over 1365239.75 frames.], batch size: 17, lr: 7.03e-04
+2022-04-29 00:02:58,036 INFO [train.py:763] (2/8) Epoch 10, batch 700, loss[loss=0.1909, simple_loss=0.2751, pruned_loss=0.05334, over 6815.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2881, pruned_loss=0.05111, over 1375563.49 frames.], batch size: 15, lr: 7.03e-04
+2022-04-29 00:04:03,192 INFO [train.py:763] (2/8) Epoch 10, batch 750, loss[loss=0.2045, simple_loss=0.2956, pruned_loss=0.0567, over 7136.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2871, pruned_loss=0.05093, over 1381495.16 frames.], batch size: 20, lr: 7.03e-04
+2022-04-29 00:05:08,471 INFO [train.py:763] (2/8) Epoch 10, batch 800, loss[loss=0.1935, simple_loss=0.2912, pruned_loss=0.04791, over 7134.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2859, pruned_loss=0.05012, over 1393535.77 frames.], batch size: 26, lr: 7.02e-04
+2022-04-29 00:06:13,823 INFO [train.py:763] (2/8) Epoch 10, batch 850, loss[loss=0.2357, simple_loss=0.3169, pruned_loss=0.07724, over 7332.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2858, pruned_loss=0.05007, over 1397276.94 frames.], batch size: 20, lr: 7.02e-04
+2022-04-29 00:07:19,240 INFO [train.py:763] (2/8) Epoch 10, batch 900, loss[loss=0.2105, simple_loss=0.2965, pruned_loss=0.06221, over 7436.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2867, pruned_loss=0.05052, over 1406447.14 frames.], batch size: 20, lr: 7.02e-04
+2022-04-29 00:08:24,539 INFO [train.py:763] (2/8) Epoch 10, batch 950, loss[loss=0.1556, simple_loss=0.2381, pruned_loss=0.03655, over 6992.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2865, pruned_loss=0.05035, over 1409059.44 frames.], batch size: 16, lr: 7.01e-04
+2022-04-29 00:09:29,920 INFO [train.py:763] (2/8) Epoch 10, batch 1000, loss[loss=0.1883, simple_loss=0.2901, pruned_loss=0.04326, over 7286.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2858, pruned_loss=0.04962, over 1412914.00 frames.], batch size: 25, lr: 7.01e-04
+2022-04-29 00:10:35,515 INFO [train.py:763] (2/8) Epoch 10, batch 1050, loss[loss=0.1957, simple_loss=0.2997, pruned_loss=0.04583, over 7270.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2883, pruned_loss=0.05067, over 1407435.42 frames.], batch size: 19, lr: 7.00e-04
+2022-04-29 00:11:41,108 INFO [train.py:763] (2/8) Epoch 10, batch 1100, loss[loss=0.1835, simple_loss=0.2698, pruned_loss=0.04865, over 7164.00 frames.], tot_loss[loss=0.195, simple_loss=0.2883, pruned_loss=0.05082, over 1412621.68 frames.], batch size: 18, lr: 7.00e-04
+2022-04-29 00:12:46,583 INFO [train.py:763] (2/8) Epoch 10, batch 1150, loss[loss=0.1758, simple_loss=0.262, pruned_loss=0.04483, over 7075.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2877, pruned_loss=0.05071, over 1417190.46 frames.], batch size: 18, lr: 7.00e-04
+2022-04-29 00:13:53,258 INFO [train.py:763] (2/8) Epoch 10, batch 1200, loss[loss=0.2064, simple_loss=0.2961, pruned_loss=0.05835, over 7266.00 frames.], tot_loss[loss=0.1935, simple_loss=0.286, pruned_loss=0.05048, over 1419809.62 frames.], batch size: 16, lr: 6.99e-04
+2022-04-29 00:14:58,978 INFO [train.py:763] (2/8) Epoch 10, batch 1250, loss[loss=0.181, simple_loss=0.2597, pruned_loss=0.05115, over 7117.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2849, pruned_loss=0.05003, over 1423743.06 frames.], batch size: 17, lr: 6.99e-04
+2022-04-29 00:16:04,760 INFO [train.py:763] (2/8) Epoch 10, batch 1300, loss[loss=0.1927, simple_loss=0.2944, pruned_loss=0.04552, over 7321.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2848, pruned_loss=0.04972, over 1420159.54 frames.], batch size: 21, lr: 6.99e-04
+2022-04-29 00:17:11,805 INFO [train.py:763] (2/8) Epoch 10, batch 1350, loss[loss=0.1823, simple_loss=0.2858, pruned_loss=0.0394, over 7324.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2848, pruned_loss=0.04986, over 1424400.12 frames.], batch size: 21, lr: 6.98e-04
+2022-04-29 00:18:18,353 INFO [train.py:763] (2/8) Epoch 10, batch 1400, loss[loss=0.1606, simple_loss=0.2524, pruned_loss=0.03439, over 7149.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2839, pruned_loss=0.04915, over 1427529.68 frames.], batch size: 19, lr: 6.98e-04
+2022-04-29 00:19:25,278 INFO [train.py:763] (2/8) Epoch 10, batch 1450, loss[loss=0.1821, simple_loss=0.2726, pruned_loss=0.04579, over 7290.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2849, pruned_loss=0.04933, over 1427580.27 frames.], batch size: 17, lr: 6.97e-04
+2022-04-29 00:20:30,749 INFO [train.py:763] (2/8) Epoch 10, batch 1500, loss[loss=0.195, simple_loss=0.292, pruned_loss=0.04903, over 7137.00 frames.], tot_loss[loss=0.192, simple_loss=0.2851, pruned_loss=0.04941, over 1426241.12 frames.], batch size: 28, lr: 6.97e-04
+2022-04-29 00:21:36,427 INFO [train.py:763] (2/8) Epoch 10, batch 1550, loss[loss=0.176, simple_loss=0.2742, pruned_loss=0.03886, over 7436.00 frames.], tot_loss[loss=0.1927, simple_loss=0.286, pruned_loss=0.04965, over 1424580.68 frames.], batch size: 20, lr: 6.97e-04
+2022-04-29 00:22:41,605 INFO [train.py:763] (2/8) Epoch 10, batch 1600, loss[loss=0.1918, simple_loss=0.29, pruned_loss=0.0468, over 6853.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2858, pruned_loss=0.04971, over 1418883.78 frames.], batch size: 31, lr: 6.96e-04
+2022-04-29 00:23:47,726 INFO [train.py:763] (2/8) Epoch 10, batch 1650, loss[loss=0.1734, simple_loss=0.2527, pruned_loss=0.04708, over 6830.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2861, pruned_loss=0.0501, over 1418097.48 frames.], batch size: 15, lr: 6.96e-04
+2022-04-29 00:24:52,734 INFO [train.py:763] (2/8) Epoch 10, batch 1700, loss[loss=0.1679, simple_loss=0.2575, pruned_loss=0.0391, over 6797.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2868, pruned_loss=0.05, over 1417151.10 frames.], batch size: 15, lr: 6.96e-04
+2022-04-29 00:25:58,395 INFO [train.py:763] (2/8) Epoch 10, batch 1750, loss[loss=0.195, simple_loss=0.293, pruned_loss=0.04844, over 7126.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2862, pruned_loss=0.05034, over 1413096.55 frames.], batch size: 21, lr: 6.95e-04
+2022-04-29 00:27:03,847 INFO [train.py:763] (2/8) Epoch 10, batch 1800, loss[loss=0.2529, simple_loss=0.3341, pruned_loss=0.08581, over 5156.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2869, pruned_loss=0.05061, over 1413625.03 frames.], batch size: 53, lr: 6.95e-04
+2022-04-29 00:28:10,763 INFO [train.py:763] (2/8) Epoch 10, batch 1850, loss[loss=0.2069, simple_loss=0.3018, pruned_loss=0.05594, over 6495.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2873, pruned_loss=0.05119, over 1417314.82 frames.], batch size: 38, lr: 6.95e-04
+2022-04-29 00:29:17,820 INFO [train.py:763] (2/8) Epoch 10, batch 1900, loss[loss=0.2225, simple_loss=0.3138, pruned_loss=0.06563, over 7319.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2867, pruned_loss=0.05079, over 1421836.15 frames.], batch size: 21, lr: 6.94e-04
+2022-04-29 00:30:24,811 INFO [train.py:763] (2/8) Epoch 10, batch 1950, loss[loss=0.1882, simple_loss=0.2921, pruned_loss=0.04211, over 7346.00 frames.], tot_loss[loss=0.194, simple_loss=0.2867, pruned_loss=0.05064, over 1421030.93 frames.], batch size: 19, lr: 6.94e-04
+2022-04-29 00:31:31,792 INFO [train.py:763] (2/8) Epoch 10, batch 2000, loss[loss=0.1572, simple_loss=0.2422, pruned_loss=0.03612, over 7181.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2871, pruned_loss=0.05067, over 1422492.72 frames.], batch size: 18, lr: 6.93e-04
+2022-04-29 00:32:38,659 INFO [train.py:763] (2/8) Epoch 10, batch 2050, loss[loss=0.1434, simple_loss=0.2333, pruned_loss=0.02678, over 7282.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2865, pruned_loss=0.05014, over 1424732.63 frames.], batch size: 17, lr: 6.93e-04
+2022-04-29 00:33:45,453 INFO [train.py:763] (2/8) Epoch 10, batch 2100, loss[loss=0.209, simple_loss=0.3014, pruned_loss=0.05826, over 7394.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2867, pruned_loss=0.05023, over 1425253.22 frames.], batch size: 23, lr: 6.93e-04
+2022-04-29 00:35:01,069 INFO [train.py:763] (2/8) Epoch 10, batch 2150, loss[loss=0.1774, simple_loss=0.2774, pruned_loss=0.03874, over 7168.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2868, pruned_loss=0.05032, over 1425544.83 frames.], batch size: 18, lr: 6.92e-04
+2022-04-29 00:36:06,563 INFO [train.py:763] (2/8) Epoch 10, batch 2200, loss[loss=0.2019, simple_loss=0.2986, pruned_loss=0.05256, over 7230.00 frames.], tot_loss[loss=0.1937, simple_loss=0.287, pruned_loss=0.05023, over 1424145.38 frames.], batch size: 20, lr: 6.92e-04
+2022-04-29 00:37:11,924 INFO [train.py:763] (2/8) Epoch 10, batch 2250, loss[loss=0.1896, simple_loss=0.2988, pruned_loss=0.04023, over 7341.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2879, pruned_loss=0.0505, over 1427583.46 frames.], batch size: 22, lr: 6.92e-04
+2022-04-29 00:38:17,408 INFO [train.py:763] (2/8) Epoch 10, batch 2300, loss[loss=0.1945, simple_loss=0.2862, pruned_loss=0.05142, over 7131.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2881, pruned_loss=0.05086, over 1427436.43 frames.], batch size: 26, lr: 6.91e-04
+2022-04-29 00:39:22,701 INFO [train.py:763] (2/8) Epoch 10, batch 2350, loss[loss=0.2495, simple_loss=0.3418, pruned_loss=0.07854, over 6852.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2876, pruned_loss=0.0509, over 1429619.73 frames.], batch size: 31, lr: 6.91e-04
+2022-04-29 00:40:27,864 INFO [train.py:763] (2/8) Epoch 10, batch 2400, loss[loss=0.1931, simple_loss=0.296, pruned_loss=0.0451, over 7325.00 frames.], tot_loss[loss=0.194, simple_loss=0.2867, pruned_loss=0.05061, over 1423135.91 frames.], batch size: 21, lr: 6.91e-04
+2022-04-29 00:41:33,297 INFO [train.py:763] (2/8) Epoch 10, batch 2450, loss[loss=0.172, simple_loss=0.2576, pruned_loss=0.04314, over 6974.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2861, pruned_loss=0.05042, over 1423010.00 frames.], batch size: 16, lr: 6.90e-04
+2022-04-29 00:42:38,512 INFO [train.py:763] (2/8) Epoch 10, batch 2500, loss[loss=0.181, simple_loss=0.278, pruned_loss=0.04202, over 7150.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2876, pruned_loss=0.05087, over 1421888.91 frames.], batch size: 19, lr: 6.90e-04
+2022-04-29 00:43:44,249 INFO [train.py:763] (2/8) Epoch 10, batch 2550, loss[loss=0.2111, simple_loss=0.2798, pruned_loss=0.07119, over 7212.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2866, pruned_loss=0.05045, over 1426186.85 frames.], batch size: 16, lr: 6.90e-04
+2022-04-29 00:44:51,065 INFO [train.py:763] (2/8) Epoch 10, batch 2600, loss[loss=0.2055, simple_loss=0.3017, pruned_loss=0.05461, over 7389.00 frames.], tot_loss[loss=0.193, simple_loss=0.2859, pruned_loss=0.05007, over 1428322.99 frames.], batch size: 23, lr: 6.89e-04
+2022-04-29 00:45:56,180 INFO [train.py:763] (2/8) Epoch 10, batch 2650, loss[loss=0.1624, simple_loss=0.2443, pruned_loss=0.0402, over 7009.00 frames.], tot_loss[loss=0.194, simple_loss=0.2868, pruned_loss=0.05062, over 1424402.50 frames.], batch size: 16, lr: 6.89e-04
+2022-04-29 00:47:01,610 INFO [train.py:763] (2/8) Epoch 10, batch 2700, loss[loss=0.1973, simple_loss=0.304, pruned_loss=0.04534, over 7411.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2873, pruned_loss=0.0509, over 1427127.24 frames.], batch size: 21, lr: 6.89e-04
+2022-04-29 00:48:08,163 INFO [train.py:763] (2/8) Epoch 10, batch 2750, loss[loss=0.1753, simple_loss=0.2625, pruned_loss=0.04404, over 7286.00 frames.], tot_loss[loss=0.193, simple_loss=0.2856, pruned_loss=0.05015, over 1425300.14 frames.], batch size: 18, lr: 6.88e-04
+2022-04-29 00:49:13,511 INFO [train.py:763] (2/8) Epoch 10, batch 2800, loss[loss=0.1828, simple_loss=0.2787, pruned_loss=0.04342, over 7158.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2857, pruned_loss=0.05021, over 1424576.44 frames.], batch size: 19, lr: 6.88e-04
+2022-04-29 00:50:19,051 INFO [train.py:763] (2/8) Epoch 10, batch 2850, loss[loss=0.183, simple_loss=0.2905, pruned_loss=0.03778, over 7324.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2847, pruned_loss=0.04944, over 1424537.42 frames.], batch size: 21, lr: 6.87e-04
+2022-04-29 00:51:24,554 INFO [train.py:763] (2/8) Epoch 10, batch 2900, loss[loss=0.2067, simple_loss=0.3102, pruned_loss=0.05165, over 7219.00 frames.], tot_loss[loss=0.191, simple_loss=0.2842, pruned_loss=0.04895, over 1427064.97 frames.], batch size: 23, lr: 6.87e-04
+2022-04-29 00:52:30,305 INFO [train.py:763] (2/8) Epoch 10, batch 2950, loss[loss=0.2198, simple_loss=0.3053, pruned_loss=0.06714, over 7192.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2851, pruned_loss=0.04891, over 1424600.79 frames.], batch size: 22, lr: 6.87e-04
+2022-04-29 00:53:36,005 INFO [train.py:763] (2/8) Epoch 10, batch 3000, loss[loss=0.1805, simple_loss=0.2694, pruned_loss=0.04578, over 7168.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2851, pruned_loss=0.04877, over 1423582.40 frames.], batch size: 18, lr: 6.86e-04
+2022-04-29 00:53:36,007 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 00:53:51,271 INFO [train.py:792] (2/8) Epoch 10, validation: loss=0.1689, simple_loss=0.2722, pruned_loss=0.03283, over 698248.00 frames.
+2022-04-29 00:54:57,778 INFO [train.py:763] (2/8) Epoch 10, batch 3050, loss[loss=0.1962, simple_loss=0.2921, pruned_loss=0.05015, over 7131.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2851, pruned_loss=0.04923, over 1427451.15 frames.], batch size: 26, lr: 6.86e-04
+2022-04-29 00:56:03,585 INFO [train.py:763] (2/8) Epoch 10, batch 3100, loss[loss=0.1574, simple_loss=0.241, pruned_loss=0.03688, over 7421.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2857, pruned_loss=0.04995, over 1425394.49 frames.], batch size: 18, lr: 6.86e-04
+2022-04-29 00:57:10,794 INFO [train.py:763] (2/8) Epoch 10, batch 3150, loss[loss=0.1642, simple_loss=0.25, pruned_loss=0.0392, over 7277.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2846, pruned_loss=0.04944, over 1427343.83 frames.], batch size: 18, lr: 6.85e-04
+2022-04-29 00:58:16,970 INFO [train.py:763] (2/8) Epoch 10, batch 3200, loss[loss=0.1837, simple_loss=0.2686, pruned_loss=0.04938, over 7153.00 frames.], tot_loss[loss=0.1924, simple_loss=0.285, pruned_loss=0.04993, over 1429003.06 frames.], batch size: 18, lr: 6.85e-04
+2022-04-29 00:59:22,560 INFO [train.py:763] (2/8) Epoch 10, batch 3250, loss[loss=0.1766, simple_loss=0.2682, pruned_loss=0.0425, over 7071.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2854, pruned_loss=0.05007, over 1430649.80 frames.], batch size: 18, lr: 6.85e-04
+2022-04-29 01:00:29,374 INFO [train.py:763] (2/8) Epoch 10, batch 3300, loss[loss=0.1973, simple_loss=0.3015, pruned_loss=0.04655, over 6248.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2856, pruned_loss=0.05071, over 1429717.72 frames.], batch size: 37, lr: 6.84e-04
+2022-04-29 01:01:36,445 INFO [train.py:763] (2/8) Epoch 10, batch 3350, loss[loss=0.1914, simple_loss=0.2787, pruned_loss=0.05204, over 7112.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2864, pruned_loss=0.05084, over 1424085.92 frames.], batch size: 21, lr: 6.84e-04
+2022-04-29 01:02:41,920 INFO [train.py:763] (2/8) Epoch 10, batch 3400, loss[loss=0.1798, simple_loss=0.2661, pruned_loss=0.0467, over 7004.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2859, pruned_loss=0.05036, over 1421779.55 frames.], batch size: 16, lr: 6.84e-04
+2022-04-29 01:03:47,409 INFO [train.py:763] (2/8) Epoch 10, batch 3450, loss[loss=0.2016, simple_loss=0.3006, pruned_loss=0.05128, over 7120.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2864, pruned_loss=0.05033, over 1424301.83 frames.], batch size: 21, lr: 6.83e-04
+2022-04-29 01:04:52,720 INFO [train.py:763] (2/8) Epoch 10, batch 3500, loss[loss=0.1636, simple_loss=0.2528, pruned_loss=0.03715, over 7409.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2861, pruned_loss=0.05024, over 1426278.28 frames.], batch size: 18, lr: 6.83e-04
+2022-04-29 01:05:58,210 INFO [train.py:763] (2/8) Epoch 10, batch 3550, loss[loss=0.2196, simple_loss=0.3167, pruned_loss=0.06123, over 6257.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2863, pruned_loss=0.0507, over 1424638.18 frames.], batch size: 37, lr: 6.83e-04
+2022-04-29 01:07:03,430 INFO [train.py:763] (2/8) Epoch 10, batch 3600, loss[loss=0.2241, simple_loss=0.303, pruned_loss=0.07255, over 6300.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2868, pruned_loss=0.0512, over 1420098.71 frames.], batch size: 37, lr: 6.82e-04
+2022-04-29 01:08:09,033 INFO [train.py:763] (2/8) Epoch 10, batch 3650, loss[loss=0.2096, simple_loss=0.3059, pruned_loss=0.05664, over 7111.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2865, pruned_loss=0.05037, over 1422130.81 frames.], batch size: 21, lr: 6.82e-04
+2022-04-29 01:09:14,316 INFO [train.py:763] (2/8) Epoch 10, batch 3700, loss[loss=0.2103, simple_loss=0.3003, pruned_loss=0.06016, over 7118.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2872, pruned_loss=0.05076, over 1418468.98 frames.], batch size: 21, lr: 6.82e-04
+2022-04-29 01:10:20,241 INFO [train.py:763] (2/8) Epoch 10, batch 3750, loss[loss=0.2086, simple_loss=0.3054, pruned_loss=0.05588, over 7437.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2873, pruned_loss=0.05047, over 1424167.22 frames.], batch size: 20, lr: 6.81e-04
+2022-04-29 01:11:26,039 INFO [train.py:763] (2/8) Epoch 10, batch 3800, loss[loss=0.2046, simple_loss=0.3041, pruned_loss=0.05253, over 7295.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2862, pruned_loss=0.0498, over 1422896.74 frames.], batch size: 24, lr: 6.81e-04
+2022-04-29 01:12:32,916 INFO [train.py:763] (2/8) Epoch 10, batch 3850, loss[loss=0.2279, simple_loss=0.3176, pruned_loss=0.06908, over 7207.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2866, pruned_loss=0.05024, over 1427373.35 frames.], batch size: 22, lr: 6.81e-04
+2022-04-29 01:13:40,342 INFO [train.py:763] (2/8) Epoch 10, batch 3900, loss[loss=0.1956, simple_loss=0.2915, pruned_loss=0.04983, over 7378.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2858, pruned_loss=0.04983, over 1428455.18 frames.], batch size: 23, lr: 6.80e-04
+2022-04-29 01:14:47,717 INFO [train.py:763] (2/8) Epoch 10, batch 3950, loss[loss=0.1743, simple_loss=0.2783, pruned_loss=0.03516, over 7431.00 frames.], tot_loss[loss=0.193, simple_loss=0.2861, pruned_loss=0.04991, over 1426629.15 frames.], batch size: 20, lr: 6.80e-04
+2022-04-29 01:15:53,611 INFO [train.py:763] (2/8) Epoch 10, batch 4000, loss[loss=0.192, simple_loss=0.2885, pruned_loss=0.04778, over 7225.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2866, pruned_loss=0.05083, over 1418459.76 frames.], batch size: 21, lr: 6.80e-04
+2022-04-29 01:17:00,540 INFO [train.py:763] (2/8) Epoch 10, batch 4050, loss[loss=0.1889, simple_loss=0.2749, pruned_loss=0.05142, over 7195.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2866, pruned_loss=0.05103, over 1418651.57 frames.], batch size: 22, lr: 6.79e-04
+2022-04-29 01:18:07,362 INFO [train.py:763] (2/8) Epoch 10, batch 4100, loss[loss=0.2403, simple_loss=0.3271, pruned_loss=0.07678, over 7218.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2867, pruned_loss=0.05095, over 1418331.90 frames.], batch size: 22, lr: 6.79e-04
+2022-04-29 01:19:14,028 INFO [train.py:763] (2/8) Epoch 10, batch 4150, loss[loss=0.1662, simple_loss=0.2668, pruned_loss=0.03284, over 6946.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2874, pruned_loss=0.05089, over 1415906.90 frames.], batch size: 31, lr: 6.79e-04
+2022-04-29 01:20:19,800 INFO [train.py:763] (2/8) Epoch 10, batch 4200, loss[loss=0.2148, simple_loss=0.3186, pruned_loss=0.0555, over 6969.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2872, pruned_loss=0.05062, over 1416194.51 frames.], batch size: 28, lr: 6.78e-04
+2022-04-29 01:21:26,028 INFO [train.py:763] (2/8) Epoch 10, batch 4250, loss[loss=0.2488, simple_loss=0.323, pruned_loss=0.08733, over 5353.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2867, pruned_loss=0.05071, over 1415709.35 frames.], batch size: 52, lr: 6.78e-04
+2022-04-29 01:22:31,074 INFO [train.py:763] (2/8) Epoch 10, batch 4300, loss[loss=0.2273, simple_loss=0.3196, pruned_loss=0.06748, over 5065.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2873, pruned_loss=0.05104, over 1411501.17 frames.], batch size: 52, lr: 6.78e-04
+2022-04-29 01:23:36,196 INFO [train.py:763] (2/8) Epoch 10, batch 4350, loss[loss=0.1557, simple_loss=0.2498, pruned_loss=0.03081, over 7232.00 frames.], tot_loss[loss=0.195, simple_loss=0.2878, pruned_loss=0.05108, over 1409294.63 frames.], batch size: 20, lr: 6.77e-04
+2022-04-29 01:24:41,258 INFO [train.py:763] (2/8) Epoch 10, batch 4400, loss[loss=0.1878, simple_loss=0.2848, pruned_loss=0.04542, over 7197.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2881, pruned_loss=0.05116, over 1414496.54 frames.], batch size: 22, lr: 6.77e-04
+2022-04-29 01:25:46,575 INFO [train.py:763] (2/8) Epoch 10, batch 4450, loss[loss=0.2082, simple_loss=0.304, pruned_loss=0.05614, over 7230.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2898, pruned_loss=0.05166, over 1416954.38 frames.], batch size: 20, lr: 6.77e-04
+2022-04-29 01:26:52,300 INFO [train.py:763] (2/8) Epoch 10, batch 4500, loss[loss=0.2734, simple_loss=0.3349, pruned_loss=0.1059, over 4998.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2908, pruned_loss=0.05213, over 1408955.34 frames.], batch size: 52, lr: 6.76e-04
+2022-04-29 01:27:57,100 INFO [train.py:763] (2/8) Epoch 10, batch 4550, loss[loss=0.2425, simple_loss=0.3304, pruned_loss=0.07727, over 5072.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2929, pruned_loss=0.05404, over 1345248.09 frames.], batch size: 53, lr: 6.76e-04
+2022-04-29 01:29:26,057 INFO [train.py:763] (2/8) Epoch 11, batch 0, loss[loss=0.1805, simple_loss=0.2799, pruned_loss=0.04054, over 7407.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2799, pruned_loss=0.04054, over 7407.00 frames.], batch size: 21, lr: 6.52e-04
+2022-04-29 01:30:32,264 INFO [train.py:763] (2/8) Epoch 11, batch 50, loss[loss=0.208, simple_loss=0.2931, pruned_loss=0.06146, over 5208.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2867, pruned_loss=0.0503, over 319371.05 frames.], batch size: 52, lr: 6.52e-04
+2022-04-29 01:31:38,376 INFO [train.py:763] (2/8) Epoch 11, batch 100, loss[loss=0.1783, simple_loss=0.2819, pruned_loss=0.03734, over 6208.00 frames.], tot_loss[loss=0.193, simple_loss=0.2857, pruned_loss=0.05014, over 558360.21 frames.], batch size: 37, lr: 6.51e-04
+2022-04-29 01:32:44,334 INFO [train.py:763] (2/8) Epoch 11, batch 150, loss[loss=0.1876, simple_loss=0.2681, pruned_loss=0.05349, over 7296.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2877, pruned_loss=0.05007, over 749110.22 frames.], batch size: 17, lr: 6.51e-04
+2022-04-29 01:33:50,247 INFO [train.py:763] (2/8) Epoch 11, batch 200, loss[loss=0.1862, simple_loss=0.2894, pruned_loss=0.04147, over 7203.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2886, pruned_loss=0.05035, over 897126.49 frames.], batch size: 22, lr: 6.51e-04
+2022-04-29 01:34:55,807 INFO [train.py:763] (2/8) Epoch 11, batch 250, loss[loss=0.1788, simple_loss=0.2675, pruned_loss=0.04502, over 6872.00 frames.], tot_loss[loss=0.1915, simple_loss=0.286, pruned_loss=0.04853, over 1015351.41 frames.], batch size: 31, lr: 6.50e-04
+2022-04-29 01:36:01,201 INFO [train.py:763] (2/8) Epoch 11, batch 300, loss[loss=0.2143, simple_loss=0.3086, pruned_loss=0.06002, over 7210.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2863, pruned_loss=0.04868, over 1099001.91 frames.], batch size: 22, lr: 6.50e-04
+2022-04-29 01:37:06,904 INFO [train.py:763] (2/8) Epoch 11, batch 350, loss[loss=0.1801, simple_loss=0.2872, pruned_loss=0.03649, over 7344.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2853, pruned_loss=0.04844, over 1166168.53 frames.], batch size: 22, lr: 6.50e-04
+2022-04-29 01:38:12,674 INFO [train.py:763] (2/8) Epoch 11, batch 400, loss[loss=0.1833, simple_loss=0.2906, pruned_loss=0.03799, over 7350.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2855, pruned_loss=0.04914, over 1221368.04 frames.], batch size: 22, lr: 6.49e-04
+2022-04-29 01:39:18,301 INFO [train.py:763] (2/8) Epoch 11, batch 450, loss[loss=0.1681, simple_loss=0.2656, pruned_loss=0.03531, over 7152.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2848, pruned_loss=0.04869, over 1269651.11 frames.], batch size: 19, lr: 6.49e-04
+2022-04-29 01:40:24,053 INFO [train.py:763] (2/8) Epoch 11, batch 500, loss[loss=0.1933, simple_loss=0.287, pruned_loss=0.0498, over 7385.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2845, pruned_loss=0.04845, over 1304643.65 frames.], batch size: 23, lr: 6.49e-04
+2022-04-29 01:41:30,078 INFO [train.py:763] (2/8) Epoch 11, batch 550, loss[loss=0.1542, simple_loss=0.2489, pruned_loss=0.02975, over 7407.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2832, pruned_loss=0.04805, over 1331167.55 frames.], batch size: 21, lr: 6.48e-04
+2022-04-29 01:42:36,718 INFO [train.py:763] (2/8) Epoch 11, batch 600, loss[loss=0.1993, simple_loss=0.3066, pruned_loss=0.04601, over 7325.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2829, pruned_loss=0.04782, over 1349234.15 frames.], batch size: 22, lr: 6.48e-04
+2022-04-29 01:43:44,063 INFO [train.py:763] (2/8) Epoch 11, batch 650, loss[loss=0.2116, simple_loss=0.3159, pruned_loss=0.05369, over 7378.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2816, pruned_loss=0.04711, over 1369769.56 frames.], batch size: 23, lr: 6.48e-04
+2022-04-29 01:44:51,065 INFO [train.py:763] (2/8) Epoch 11, batch 700, loss[loss=0.1889, simple_loss=0.2925, pruned_loss=0.04265, over 7331.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2828, pruned_loss=0.04736, over 1380619.34 frames.], batch size: 24, lr: 6.47e-04
+2022-04-29 01:45:57,535 INFO [train.py:763] (2/8) Epoch 11, batch 750, loss[loss=0.2083, simple_loss=0.302, pruned_loss=0.05728, over 7327.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2836, pruned_loss=0.04761, over 1386222.17 frames.], batch size: 20, lr: 6.47e-04
+2022-04-29 01:47:03,476 INFO [train.py:763] (2/8) Epoch 11, batch 800, loss[loss=0.169, simple_loss=0.2623, pruned_loss=0.03779, over 7416.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2833, pruned_loss=0.04761, over 1399750.67 frames.], batch size: 18, lr: 6.47e-04
+2022-04-29 01:48:08,961 INFO [train.py:763] (2/8) Epoch 11, batch 850, loss[loss=0.1899, simple_loss=0.292, pruned_loss=0.04392, over 6830.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2841, pruned_loss=0.04848, over 1403848.31 frames.], batch size: 31, lr: 6.46e-04
+2022-04-29 01:49:14,788 INFO [train.py:763] (2/8) Epoch 11, batch 900, loss[loss=0.1683, simple_loss=0.2808, pruned_loss=0.0279, over 7330.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2845, pruned_loss=0.04858, over 1408295.03 frames.], batch size: 22, lr: 6.46e-04
+2022-04-29 01:50:20,602 INFO [train.py:763] (2/8) Epoch 11, batch 950, loss[loss=0.1724, simple_loss=0.2678, pruned_loss=0.03853, over 7429.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2851, pruned_loss=0.04884, over 1412738.01 frames.], batch size: 20, lr: 6.46e-04
+2022-04-29 01:51:27,135 INFO [train.py:763] (2/8) Epoch 11, batch 1000, loss[loss=0.175, simple_loss=0.2727, pruned_loss=0.03858, over 7154.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2854, pruned_loss=0.04879, over 1415928.90 frames.], batch size: 19, lr: 6.46e-04
+2022-04-29 01:52:32,487 INFO [train.py:763] (2/8) Epoch 11, batch 1050, loss[loss=0.158, simple_loss=0.2468, pruned_loss=0.03466, over 6989.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2852, pruned_loss=0.04879, over 1415483.23 frames.], batch size: 16, lr: 6.45e-04
+2022-04-29 01:53:38,687 INFO [train.py:763] (2/8) Epoch 11, batch 1100, loss[loss=0.1725, simple_loss=0.2623, pruned_loss=0.04129, over 7171.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2864, pruned_loss=0.0491, over 1418832.66 frames.], batch size: 19, lr: 6.45e-04
+2022-04-29 01:54:45,796 INFO [train.py:763] (2/8) Epoch 11, batch 1150, loss[loss=0.2558, simple_loss=0.3243, pruned_loss=0.09358, over 5009.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2852, pruned_loss=0.04852, over 1421339.22 frames.], batch size: 53, lr: 6.45e-04
+2022-04-29 01:55:51,955 INFO [train.py:763] (2/8) Epoch 11, batch 1200, loss[loss=0.1852, simple_loss=0.2813, pruned_loss=0.04457, over 7113.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2851, pruned_loss=0.04816, over 1423873.19 frames.], batch size: 21, lr: 6.44e-04
+2022-04-29 01:56:57,795 INFO [train.py:763] (2/8) Epoch 11, batch 1250, loss[loss=0.1552, simple_loss=0.2402, pruned_loss=0.03506, over 6996.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2852, pruned_loss=0.0485, over 1424740.56 frames.], batch size: 16, lr: 6.44e-04
+2022-04-29 01:58:03,701 INFO [train.py:763] (2/8) Epoch 11, batch 1300, loss[loss=0.1899, simple_loss=0.2803, pruned_loss=0.04971, over 7330.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2843, pruned_loss=0.04777, over 1427380.44 frames.], batch size: 20, lr: 6.44e-04
+2022-04-29 01:59:10,163 INFO [train.py:763] (2/8) Epoch 11, batch 1350, loss[loss=0.1801, simple_loss=0.2815, pruned_loss=0.03939, over 7330.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2848, pruned_loss=0.04834, over 1424742.29 frames.], batch size: 21, lr: 6.43e-04
+2022-04-29 02:00:15,525 INFO [train.py:763] (2/8) Epoch 11, batch 1400, loss[loss=0.1921, simple_loss=0.298, pruned_loss=0.04314, over 7326.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2834, pruned_loss=0.04774, over 1421645.03 frames.], batch size: 21, lr: 6.43e-04
+2022-04-29 02:01:21,165 INFO [train.py:763] (2/8) Epoch 11, batch 1450, loss[loss=0.1759, simple_loss=0.2685, pruned_loss=0.04168, over 7067.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2837, pruned_loss=0.04771, over 1421856.33 frames.], batch size: 18, lr: 6.43e-04
+2022-04-29 02:02:28,453 INFO [train.py:763] (2/8) Epoch 11, batch 1500, loss[loss=0.2406, simple_loss=0.3288, pruned_loss=0.07615, over 7206.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2841, pruned_loss=0.04816, over 1426612.61 frames.], batch size: 23, lr: 6.42e-04
+2022-04-29 02:03:33,957 INFO [train.py:763] (2/8) Epoch 11, batch 1550, loss[loss=0.1989, simple_loss=0.2997, pruned_loss=0.04907, over 7237.00 frames.], tot_loss[loss=0.1893, simple_loss=0.283, pruned_loss=0.04776, over 1426050.41 frames.], batch size: 20, lr: 6.42e-04
+2022-04-29 02:04:39,633 INFO [train.py:763] (2/8) Epoch 11, batch 1600, loss[loss=0.1584, simple_loss=0.2571, pruned_loss=0.02982, over 7349.00 frames.], tot_loss[loss=0.1902, simple_loss=0.284, pruned_loss=0.04819, over 1426545.52 frames.], batch size: 19, lr: 6.42e-04
+2022-04-29 02:06:04,014 INFO [train.py:763] (2/8) Epoch 11, batch 1650, loss[loss=0.1779, simple_loss=0.29, pruned_loss=0.03292, over 7369.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2846, pruned_loss=0.04857, over 1426859.88 frames.], batch size: 23, lr: 6.42e-04
+2022-04-29 02:07:17,965 INFO [train.py:763] (2/8) Epoch 11, batch 1700, loss[loss=0.178, simple_loss=0.2739, pruned_loss=0.04102, over 7217.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2853, pruned_loss=0.04821, over 1427353.57 frames.], batch size: 21, lr: 6.41e-04
+2022-04-29 02:08:33,273 INFO [train.py:763] (2/8) Epoch 11, batch 1750, loss[loss=0.1979, simple_loss=0.2924, pruned_loss=0.05173, over 7195.00 frames.], tot_loss[loss=0.1916, simple_loss=0.286, pruned_loss=0.04861, over 1428615.80 frames.], batch size: 26, lr: 6.41e-04
+2022-04-29 02:09:47,985 INFO [train.py:763] (2/8) Epoch 11, batch 1800, loss[loss=0.1501, simple_loss=0.2375, pruned_loss=0.03136, over 6993.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2847, pruned_loss=0.04831, over 1429582.10 frames.], batch size: 16, lr: 6.41e-04
+2022-04-29 02:11:03,169 INFO [train.py:763] (2/8) Epoch 11, batch 1850, loss[loss=0.1914, simple_loss=0.2921, pruned_loss=0.0453, over 7097.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2849, pruned_loss=0.04878, over 1427295.82 frames.], batch size: 26, lr: 6.40e-04
+2022-04-29 02:12:18,076 INFO [train.py:763] (2/8) Epoch 11, batch 1900, loss[loss=0.1675, simple_loss=0.2604, pruned_loss=0.0373, over 7414.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2835, pruned_loss=0.04761, over 1428968.50 frames.], batch size: 20, lr: 6.40e-04
+2022-04-29 02:13:32,346 INFO [train.py:763] (2/8) Epoch 11, batch 1950, loss[loss=0.1525, simple_loss=0.2473, pruned_loss=0.02881, over 6988.00 frames.], tot_loss[loss=0.189, simple_loss=0.2829, pruned_loss=0.04761, over 1427987.66 frames.], batch size: 16, lr: 6.40e-04
+2022-04-29 02:14:38,123 INFO [train.py:763] (2/8) Epoch 11, batch 2000, loss[loss=0.2043, simple_loss=0.301, pruned_loss=0.05384, over 6357.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2841, pruned_loss=0.04844, over 1425902.74 frames.], batch size: 38, lr: 6.39e-04
+2022-04-29 02:15:44,445 INFO [train.py:763] (2/8) Epoch 11, batch 2050, loss[loss=0.1954, simple_loss=0.2971, pruned_loss=0.04688, over 7375.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2837, pruned_loss=0.0486, over 1423552.18 frames.], batch size: 23, lr: 6.39e-04
+2022-04-29 02:16:50,749 INFO [train.py:763] (2/8) Epoch 11, batch 2100, loss[loss=0.2064, simple_loss=0.3034, pruned_loss=0.05468, over 6963.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2828, pruned_loss=0.04798, over 1427892.46 frames.], batch size: 32, lr: 6.39e-04
+2022-04-29 02:17:57,122 INFO [train.py:763] (2/8) Epoch 11, batch 2150, loss[loss=0.1778, simple_loss=0.2578, pruned_loss=0.04891, over 7258.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2823, pruned_loss=0.04762, over 1423329.97 frames.], batch size: 16, lr: 6.38e-04
+2022-04-29 02:19:03,270 INFO [train.py:763] (2/8) Epoch 11, batch 2200, loss[loss=0.1906, simple_loss=0.2853, pruned_loss=0.04798, over 7431.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2823, pruned_loss=0.04775, over 1427251.25 frames.], batch size: 20, lr: 6.38e-04
+2022-04-29 02:20:09,532 INFO [train.py:763] (2/8) Epoch 11, batch 2250, loss[loss=0.1891, simple_loss=0.2836, pruned_loss=0.0473, over 7121.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2823, pruned_loss=0.04771, over 1425652.11 frames.], batch size: 17, lr: 6.38e-04
+2022-04-29 02:21:16,306 INFO [train.py:763] (2/8) Epoch 11, batch 2300, loss[loss=0.1973, simple_loss=0.2912, pruned_loss=0.05174, over 7361.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2837, pruned_loss=0.04833, over 1423865.87 frames.], batch size: 19, lr: 6.38e-04
+2022-04-29 02:22:22,088 INFO [train.py:763] (2/8) Epoch 11, batch 2350, loss[loss=0.2215, simple_loss=0.3066, pruned_loss=0.06818, over 7296.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2833, pruned_loss=0.04817, over 1426139.00 frames.], batch size: 24, lr: 6.37e-04
+2022-04-29 02:23:28,142 INFO [train.py:763] (2/8) Epoch 11, batch 2400, loss[loss=0.1814, simple_loss=0.2773, pruned_loss=0.04277, over 7109.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2844, pruned_loss=0.04853, over 1428380.13 frames.], batch size: 21, lr: 6.37e-04
+2022-04-29 02:24:33,619 INFO [train.py:763] (2/8) Epoch 11, batch 2450, loss[loss=0.1919, simple_loss=0.2838, pruned_loss=0.05001, over 7233.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2847, pruned_loss=0.04815, over 1426148.43 frames.], batch size: 20, lr: 6.37e-04
+2022-04-29 02:25:39,226 INFO [train.py:763] (2/8) Epoch 11, batch 2500, loss[loss=0.1606, simple_loss=0.2626, pruned_loss=0.02933, over 7073.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2843, pruned_loss=0.04822, over 1425187.21 frames.], batch size: 18, lr: 6.36e-04
+2022-04-29 02:26:45,644 INFO [train.py:763] (2/8) Epoch 11, batch 2550, loss[loss=0.1983, simple_loss=0.2832, pruned_loss=0.05665, over 7294.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2851, pruned_loss=0.04863, over 1427722.00 frames.], batch size: 17, lr: 6.36e-04
+2022-04-29 02:27:50,866 INFO [train.py:763] (2/8) Epoch 11, batch 2600, loss[loss=0.2195, simple_loss=0.3265, pruned_loss=0.05627, over 7284.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2854, pruned_loss=0.04893, over 1422859.81 frames.], batch size: 24, lr: 6.36e-04
+2022-04-29 02:28:56,393 INFO [train.py:763] (2/8) Epoch 11, batch 2650, loss[loss=0.1781, simple_loss=0.2705, pruned_loss=0.04288, over 7255.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2852, pruned_loss=0.04875, over 1419194.24 frames.], batch size: 19, lr: 6.36e-04
+2022-04-29 02:30:03,347 INFO [train.py:763] (2/8) Epoch 11, batch 2700, loss[loss=0.1977, simple_loss=0.296, pruned_loss=0.04965, over 7304.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2848, pruned_loss=0.04847, over 1422702.36 frames.], batch size: 25, lr: 6.35e-04
+2022-04-29 02:31:08,819 INFO [train.py:763] (2/8) Epoch 11, batch 2750, loss[loss=0.2049, simple_loss=0.298, pruned_loss=0.05592, over 7438.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2834, pruned_loss=0.04777, over 1425252.54 frames.], batch size: 20, lr: 6.35e-04
+2022-04-29 02:32:14,646 INFO [train.py:763] (2/8) Epoch 11, batch 2800, loss[loss=0.2231, simple_loss=0.3109, pruned_loss=0.06764, over 7121.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2835, pruned_loss=0.04763, over 1426258.73 frames.], batch size: 21, lr: 6.35e-04
+2022-04-29 02:33:21,112 INFO [train.py:763] (2/8) Epoch 11, batch 2850, loss[loss=0.1993, simple_loss=0.3073, pruned_loss=0.04561, over 7316.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2832, pruned_loss=0.04768, over 1428488.16 frames.], batch size: 21, lr: 6.34e-04
+2022-04-29 02:34:28,402 INFO [train.py:763] (2/8) Epoch 11, batch 2900, loss[loss=0.1825, simple_loss=0.282, pruned_loss=0.04152, over 7293.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2853, pruned_loss=0.0489, over 1424167.89 frames.], batch size: 24, lr: 6.34e-04
+2022-04-29 02:35:35,069 INFO [train.py:763] (2/8) Epoch 11, batch 2950, loss[loss=0.1849, simple_loss=0.2843, pruned_loss=0.04269, over 7221.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2856, pruned_loss=0.04935, over 1419744.37 frames.], batch size: 21, lr: 6.34e-04
+2022-04-29 02:36:40,643 INFO [train.py:763] (2/8) Epoch 11, batch 3000, loss[loss=0.1965, simple_loss=0.3039, pruned_loss=0.04454, over 7249.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2858, pruned_loss=0.04944, over 1421532.68 frames.], batch size: 25, lr: 6.33e-04
+2022-04-29 02:36:40,644 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 02:36:55,964 INFO [train.py:792] (2/8) Epoch 11, validation: loss=0.1677, simple_loss=0.2702, pruned_loss=0.03262, over 698248.00 frames.
+2022-04-29 02:38:01,323 INFO [train.py:763] (2/8) Epoch 11, batch 3050, loss[loss=0.202, simple_loss=0.2943, pruned_loss=0.05489, over 7381.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2866, pruned_loss=0.0494, over 1420066.32 frames.], batch size: 23, lr: 6.33e-04
+2022-04-29 02:39:06,996 INFO [train.py:763] (2/8) Epoch 11, batch 3100, loss[loss=0.192, simple_loss=0.2949, pruned_loss=0.04451, over 7328.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2846, pruned_loss=0.04844, over 1422378.44 frames.], batch size: 20, lr: 6.33e-04
+2022-04-29 02:40:14,523 INFO [train.py:763] (2/8) Epoch 11, batch 3150, loss[loss=0.1838, simple_loss=0.2834, pruned_loss=0.04213, over 7379.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2832, pruned_loss=0.04758, over 1423914.85 frames.], batch size: 23, lr: 6.33e-04
+2022-04-29 02:41:19,854 INFO [train.py:763] (2/8) Epoch 11, batch 3200, loss[loss=0.1984, simple_loss=0.2918, pruned_loss=0.05246, over 7112.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2827, pruned_loss=0.0471, over 1423718.14 frames.], batch size: 21, lr: 6.32e-04
+2022-04-29 02:42:26,202 INFO [train.py:763] (2/8) Epoch 11, batch 3250, loss[loss=0.2083, simple_loss=0.3127, pruned_loss=0.05196, over 7407.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2831, pruned_loss=0.04698, over 1425201.48 frames.], batch size: 21, lr: 6.32e-04
+2022-04-29 02:43:31,316 INFO [train.py:763] (2/8) Epoch 11, batch 3300, loss[loss=0.1654, simple_loss=0.2551, pruned_loss=0.03785, over 6995.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2836, pruned_loss=0.04662, over 1425960.64 frames.], batch size: 16, lr: 6.32e-04
+2022-04-29 02:44:36,747 INFO [train.py:763] (2/8) Epoch 11, batch 3350, loss[loss=0.1683, simple_loss=0.253, pruned_loss=0.0418, over 7282.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2831, pruned_loss=0.04677, over 1426389.61 frames.], batch size: 18, lr: 6.31e-04
+2022-04-29 02:45:42,396 INFO [train.py:763] (2/8) Epoch 11, batch 3400, loss[loss=0.2318, simple_loss=0.3208, pruned_loss=0.07139, over 6360.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2827, pruned_loss=0.0468, over 1420593.36 frames.], batch size: 38, lr: 6.31e-04
+2022-04-29 02:46:49,525 INFO [train.py:763] (2/8) Epoch 11, batch 3450, loss[loss=0.1919, simple_loss=0.2891, pruned_loss=0.04738, over 7125.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2822, pruned_loss=0.04679, over 1418784.48 frames.], batch size: 21, lr: 6.31e-04
+2022-04-29 02:47:56,121 INFO [train.py:763] (2/8) Epoch 11, batch 3500, loss[loss=0.1842, simple_loss=0.2814, pruned_loss=0.04352, over 7322.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2826, pruned_loss=0.04675, over 1424715.93 frames.], batch size: 21, lr: 6.31e-04
+2022-04-29 02:49:02,210 INFO [train.py:763] (2/8) Epoch 11, batch 3550, loss[loss=0.1707, simple_loss=0.2635, pruned_loss=0.03891, over 7015.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2829, pruned_loss=0.04689, over 1423361.88 frames.], batch size: 16, lr: 6.30e-04
+2022-04-29 02:50:08,006 INFO [train.py:763] (2/8) Epoch 11, batch 3600, loss[loss=0.2078, simple_loss=0.3054, pruned_loss=0.05504, over 7242.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2832, pruned_loss=0.04684, over 1425781.87 frames.], batch size: 20, lr: 6.30e-04
+2022-04-29 02:51:13,359 INFO [train.py:763] (2/8) Epoch 11, batch 3650, loss[loss=0.1725, simple_loss=0.2777, pruned_loss=0.03366, over 7424.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2834, pruned_loss=0.04687, over 1424726.49 frames.], batch size: 20, lr: 6.30e-04
+2022-04-29 02:52:20,064 INFO [train.py:763] (2/8) Epoch 11, batch 3700, loss[loss=0.1861, simple_loss=0.2994, pruned_loss=0.03637, over 6807.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2829, pruned_loss=0.0467, over 1421924.15 frames.], batch size: 31, lr: 6.29e-04
+2022-04-29 02:53:25,478 INFO [train.py:763] (2/8) Epoch 11, batch 3750, loss[loss=0.2169, simple_loss=0.3158, pruned_loss=0.05901, over 7373.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2833, pruned_loss=0.04692, over 1425980.76 frames.], batch size: 23, lr: 6.29e-04
+2022-04-29 02:54:30,949 INFO [train.py:763] (2/8) Epoch 11, batch 3800, loss[loss=0.1911, simple_loss=0.2934, pruned_loss=0.04439, over 7190.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2828, pruned_loss=0.04675, over 1429244.46 frames.], batch size: 26, lr: 6.29e-04
+2022-04-29 02:55:36,104 INFO [train.py:763] (2/8) Epoch 11, batch 3850, loss[loss=0.1914, simple_loss=0.2956, pruned_loss=0.04361, over 7124.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2831, pruned_loss=0.04696, over 1429129.56 frames.], batch size: 21, lr: 6.29e-04
+2022-04-29 02:56:41,382 INFO [train.py:763] (2/8) Epoch 11, batch 3900, loss[loss=0.1858, simple_loss=0.2802, pruned_loss=0.0457, over 7419.00 frames.], tot_loss[loss=0.1883, simple_loss=0.283, pruned_loss=0.04681, over 1429858.16 frames.], batch size: 20, lr: 6.28e-04
+2022-04-29 02:57:46,957 INFO [train.py:763] (2/8) Epoch 11, batch 3950, loss[loss=0.2414, simple_loss=0.3162, pruned_loss=0.08327, over 7228.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2828, pruned_loss=0.04723, over 1431662.26 frames.], batch size: 20, lr: 6.28e-04
+2022-04-29 02:58:52,090 INFO [train.py:763] (2/8) Epoch 11, batch 4000, loss[loss=0.1901, simple_loss=0.2891, pruned_loss=0.04556, over 7411.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2834, pruned_loss=0.04722, over 1426471.88 frames.], batch size: 21, lr: 6.28e-04
+2022-04-29 02:59:57,355 INFO [train.py:763] (2/8) Epoch 11, batch 4050, loss[loss=0.2017, simple_loss=0.2839, pruned_loss=0.05977, over 7438.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2842, pruned_loss=0.04802, over 1424726.08 frames.], batch size: 20, lr: 6.27e-04
+2022-04-29 03:01:03,189 INFO [train.py:763] (2/8) Epoch 11, batch 4100, loss[loss=0.2059, simple_loss=0.2952, pruned_loss=0.05834, over 7329.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2843, pruned_loss=0.04805, over 1421308.08 frames.], batch size: 20, lr: 6.27e-04
+2022-04-29 03:02:08,244 INFO [train.py:763] (2/8) Epoch 11, batch 4150, loss[loss=0.1762, simple_loss=0.2744, pruned_loss=0.03905, over 7243.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2842, pruned_loss=0.04784, over 1422510.82 frames.], batch size: 20, lr: 6.27e-04
+2022-04-29 03:03:14,694 INFO [train.py:763] (2/8) Epoch 11, batch 4200, loss[loss=0.1763, simple_loss=0.2745, pruned_loss=0.03909, over 7327.00 frames.], tot_loss[loss=0.191, simple_loss=0.2854, pruned_loss=0.04832, over 1421418.34 frames.], batch size: 22, lr: 6.27e-04
+2022-04-29 03:04:21,491 INFO [train.py:763] (2/8) Epoch 11, batch 4250, loss[loss=0.1742, simple_loss=0.2573, pruned_loss=0.04551, over 7414.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2848, pruned_loss=0.04823, over 1424082.47 frames.], batch size: 18, lr: 6.26e-04
+2022-04-29 03:05:27,591 INFO [train.py:763] (2/8) Epoch 11, batch 4300, loss[loss=0.1794, simple_loss=0.288, pruned_loss=0.03544, over 7235.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2833, pruned_loss=0.04758, over 1417565.89 frames.], batch size: 20, lr: 6.26e-04
+2022-04-29 03:06:35,253 INFO [train.py:763] (2/8) Epoch 11, batch 4350, loss[loss=0.1706, simple_loss=0.2709, pruned_loss=0.03513, over 7203.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2813, pruned_loss=0.04704, over 1419692.99 frames.], batch size: 22, lr: 6.26e-04
+2022-04-29 03:07:41,462 INFO [train.py:763] (2/8) Epoch 11, batch 4400, loss[loss=0.1724, simple_loss=0.2679, pruned_loss=0.03852, over 7314.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2819, pruned_loss=0.04764, over 1418332.54 frames.], batch size: 21, lr: 6.25e-04
+2022-04-29 03:08:47,762 INFO [train.py:763] (2/8) Epoch 11, batch 4450, loss[loss=0.1837, simple_loss=0.2815, pruned_loss=0.04295, over 6383.00 frames.], tot_loss[loss=0.1885, simple_loss=0.281, pruned_loss=0.04798, over 1405853.29 frames.], batch size: 37, lr: 6.25e-04
+2022-04-29 03:09:54,257 INFO [train.py:763] (2/8) Epoch 11, batch 4500, loss[loss=0.1928, simple_loss=0.2976, pruned_loss=0.04394, over 6394.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2817, pruned_loss=0.0489, over 1388373.75 frames.], batch size: 38, lr: 6.25e-04
+2022-04-29 03:10:59,840 INFO [train.py:763] (2/8) Epoch 11, batch 4550, loss[loss=0.2452, simple_loss=0.3281, pruned_loss=0.0811, over 4939.00 frames.], tot_loss[loss=0.1916, simple_loss=0.283, pruned_loss=0.05005, over 1350614.61 frames.], batch size: 53, lr: 6.25e-04
+2022-04-29 03:12:38,228 INFO [train.py:763] (2/8) Epoch 12, batch 0, loss[loss=0.2041, simple_loss=0.3021, pruned_loss=0.053, over 7149.00 frames.], tot_loss[loss=0.2041, simple_loss=0.3021, pruned_loss=0.053, over 7149.00 frames.], batch size: 20, lr: 6.03e-04
+2022-04-29 03:13:44,616 INFO [train.py:763] (2/8) Epoch 12, batch 50, loss[loss=0.1949, simple_loss=0.2907, pruned_loss=0.04952, over 7235.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2785, pruned_loss=0.04486, over 319113.33 frames.], batch size: 20, lr: 6.03e-04
+2022-04-29 03:14:50,355 INFO [train.py:763] (2/8) Epoch 12, batch 100, loss[loss=0.1831, simple_loss=0.2885, pruned_loss=0.03881, over 7197.00 frames.], tot_loss[loss=0.1879, simple_loss=0.283, pruned_loss=0.04637, over 565337.07 frames.], batch size: 23, lr: 6.03e-04
+2022-04-29 03:15:56,439 INFO [train.py:763] (2/8) Epoch 12, batch 150, loss[loss=0.2016, simple_loss=0.2945, pruned_loss=0.05431, over 7140.00 frames.], tot_loss[loss=0.187, simple_loss=0.283, pruned_loss=0.0455, over 754556.51 frames.], batch size: 20, lr: 6.03e-04
+2022-04-29 03:17:02,800 INFO [train.py:763] (2/8) Epoch 12, batch 200, loss[loss=0.1788, simple_loss=0.2693, pruned_loss=0.04414, over 7151.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2823, pruned_loss=0.0462, over 900534.17 frames.], batch size: 20, lr: 6.02e-04
+2022-04-29 03:18:09,053 INFO [train.py:763] (2/8) Epoch 12, batch 250, loss[loss=0.1846, simple_loss=0.2601, pruned_loss=0.05455, over 7181.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2821, pruned_loss=0.04651, over 1014701.94 frames.], batch size: 16, lr: 6.02e-04
+2022-04-29 03:19:15,280 INFO [train.py:763] (2/8) Epoch 12, batch 300, loss[loss=0.1768, simple_loss=0.2754, pruned_loss=0.03915, over 7147.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2813, pruned_loss=0.04612, over 1104765.11 frames.], batch size: 20, lr: 6.02e-04
+2022-04-29 03:20:20,569 INFO [train.py:763] (2/8) Epoch 12, batch 350, loss[loss=0.204, simple_loss=0.3032, pruned_loss=0.0524, over 7134.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2839, pruned_loss=0.04677, over 1176713.19 frames.], batch size: 28, lr: 6.01e-04
+2022-04-29 03:21:26,171 INFO [train.py:763] (2/8) Epoch 12, batch 400, loss[loss=0.1675, simple_loss=0.2607, pruned_loss=0.03712, over 7362.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2837, pruned_loss=0.04676, over 1233742.10 frames.], batch size: 19, lr: 6.01e-04
+2022-04-29 03:22:31,835 INFO [train.py:763] (2/8) Epoch 12, batch 450, loss[loss=0.1696, simple_loss=0.2768, pruned_loss=0.03122, over 7329.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2821, pruned_loss=0.0466, over 1277612.60 frames.], batch size: 21, lr: 6.01e-04
+2022-04-29 03:23:38,034 INFO [train.py:763] (2/8) Epoch 12, batch 500, loss[loss=0.1819, simple_loss=0.277, pruned_loss=0.04334, over 6398.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2803, pruned_loss=0.04563, over 1310596.69 frames.], batch size: 38, lr: 6.01e-04
+2022-04-29 03:24:43,943 INFO [train.py:763] (2/8) Epoch 12, batch 550, loss[loss=0.2265, simple_loss=0.3134, pruned_loss=0.0698, over 7366.00 frames.], tot_loss[loss=0.1868, simple_loss=0.281, pruned_loss=0.04623, over 1333037.28 frames.], batch size: 23, lr: 6.00e-04
+2022-04-29 03:25:49,962 INFO [train.py:763] (2/8) Epoch 12, batch 600, loss[loss=0.1399, simple_loss=0.2297, pruned_loss=0.02503, over 6780.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2804, pruned_loss=0.04639, over 1346579.85 frames.], batch size: 15, lr: 6.00e-04
+2022-04-29 03:26:55,891 INFO [train.py:763] (2/8) Epoch 12, batch 650, loss[loss=0.173, simple_loss=0.26, pruned_loss=0.04301, over 7269.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2816, pruned_loss=0.04656, over 1366613.08 frames.], batch size: 18, lr: 6.00e-04
+2022-04-29 03:28:02,296 INFO [train.py:763] (2/8) Epoch 12, batch 700, loss[loss=0.2309, simple_loss=0.3047, pruned_loss=0.07857, over 7242.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2819, pruned_loss=0.04681, over 1384606.30 frames.], batch size: 16, lr: 6.00e-04
+2022-04-29 03:29:07,991 INFO [train.py:763] (2/8) Epoch 12, batch 750, loss[loss=0.202, simple_loss=0.3055, pruned_loss=0.04923, over 7206.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2821, pruned_loss=0.04656, over 1396350.99 frames.], batch size: 23, lr: 5.99e-04
+2022-04-29 03:30:14,226 INFO [train.py:763] (2/8) Epoch 12, batch 800, loss[loss=0.189, simple_loss=0.2928, pruned_loss=0.04259, over 7211.00 frames.], tot_loss[loss=0.1876, simple_loss=0.282, pruned_loss=0.04664, over 1406122.38 frames.], batch size: 22, lr: 5.99e-04
+2022-04-29 03:31:20,649 INFO [train.py:763] (2/8) Epoch 12, batch 850, loss[loss=0.1804, simple_loss=0.2651, pruned_loss=0.04787, over 7139.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2821, pruned_loss=0.04657, over 1411769.88 frames.], batch size: 17, lr: 5.99e-04
+2022-04-29 03:32:27,842 INFO [train.py:763] (2/8) Epoch 12, batch 900, loss[loss=0.2135, simple_loss=0.3033, pruned_loss=0.06186, over 7322.00 frames.], tot_loss[loss=0.187, simple_loss=0.2815, pruned_loss=0.04621, over 1414974.82 frames.], batch size: 20, lr: 5.99e-04
+2022-04-29 03:33:44,134 INFO [train.py:763] (2/8) Epoch 12, batch 950, loss[loss=0.1638, simple_loss=0.277, pruned_loss=0.02534, over 7190.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2813, pruned_loss=0.04593, over 1415236.26 frames.], batch size: 26, lr: 5.98e-04
+2022-04-29 03:34:49,702 INFO [train.py:763] (2/8) Epoch 12, batch 1000, loss[loss=0.2032, simple_loss=0.3003, pruned_loss=0.05303, over 6322.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2821, pruned_loss=0.04628, over 1415066.23 frames.], batch size: 37, lr: 5.98e-04
+2022-04-29 03:35:56,174 INFO [train.py:763] (2/8) Epoch 12, batch 1050, loss[loss=0.1825, simple_loss=0.277, pruned_loss=0.04398, over 7259.00 frames.], tot_loss[loss=0.1865, simple_loss=0.281, pruned_loss=0.04603, over 1417206.73 frames.], batch size: 19, lr: 5.98e-04
+2022-04-29 03:37:02,295 INFO [train.py:763] (2/8) Epoch 12, batch 1100, loss[loss=0.2065, simple_loss=0.3005, pruned_loss=0.05627, over 7373.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2815, pruned_loss=0.0461, over 1422628.45 frames.], batch size: 23, lr: 5.97e-04
+2022-04-29 03:38:08,853 INFO [train.py:763] (2/8) Epoch 12, batch 1150, loss[loss=0.1853, simple_loss=0.2816, pruned_loss=0.04454, over 7320.00 frames.], tot_loss[loss=0.1865, simple_loss=0.281, pruned_loss=0.04598, over 1425134.26 frames.], batch size: 20, lr: 5.97e-04
+2022-04-29 03:39:15,118 INFO [train.py:763] (2/8) Epoch 12, batch 1200, loss[loss=0.2282, simple_loss=0.2984, pruned_loss=0.07905, over 4734.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2813, pruned_loss=0.04648, over 1421889.54 frames.], batch size: 52, lr: 5.97e-04
+2022-04-29 03:40:21,631 INFO [train.py:763] (2/8) Epoch 12, batch 1250, loss[loss=0.1923, simple_loss=0.2874, pruned_loss=0.04854, over 7152.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2812, pruned_loss=0.04602, over 1419213.19 frames.], batch size: 19, lr: 5.97e-04
+2022-04-29 03:41:28,264 INFO [train.py:763] (2/8) Epoch 12, batch 1300, loss[loss=0.1806, simple_loss=0.2783, pruned_loss=0.04142, over 7056.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2807, pruned_loss=0.0459, over 1419998.70 frames.], batch size: 18, lr: 5.96e-04
+2022-04-29 03:42:33,924 INFO [train.py:763] (2/8) Epoch 12, batch 1350, loss[loss=0.2421, simple_loss=0.3167, pruned_loss=0.08373, over 5211.00 frames.], tot_loss[loss=0.1878, simple_loss=0.282, pruned_loss=0.04683, over 1417161.78 frames.], batch size: 52, lr: 5.96e-04
+2022-04-29 03:43:39,825 INFO [train.py:763] (2/8) Epoch 12, batch 1400, loss[loss=0.2106, simple_loss=0.3066, pruned_loss=0.05726, over 7280.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2827, pruned_loss=0.0471, over 1416312.37 frames.], batch size: 25, lr: 5.96e-04
+2022-04-29 03:44:45,259 INFO [train.py:763] (2/8) Epoch 12, batch 1450, loss[loss=0.2129, simple_loss=0.3075, pruned_loss=0.05913, over 7320.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2834, pruned_loss=0.04753, over 1414402.67 frames.], batch size: 21, lr: 5.96e-04
+2022-04-29 03:45:51,846 INFO [train.py:763] (2/8) Epoch 12, batch 1500, loss[loss=0.2178, simple_loss=0.3091, pruned_loss=0.06329, over 7212.00 frames.], tot_loss[loss=0.189, simple_loss=0.2831, pruned_loss=0.04742, over 1418040.78 frames.], batch size: 23, lr: 5.95e-04
+2022-04-29 03:46:59,218 INFO [train.py:763] (2/8) Epoch 12, batch 1550, loss[loss=0.1815, simple_loss=0.2907, pruned_loss=0.03611, over 7052.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2833, pruned_loss=0.04726, over 1419635.88 frames.], batch size: 28, lr: 5.95e-04
+2022-04-29 03:48:05,681 INFO [train.py:763] (2/8) Epoch 12, batch 1600, loss[loss=0.2149, simple_loss=0.3061, pruned_loss=0.06178, over 7304.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2837, pruned_loss=0.04744, over 1419593.68 frames.], batch size: 25, lr: 5.95e-04
+2022-04-29 03:49:11,826 INFO [train.py:763] (2/8) Epoch 12, batch 1650, loss[loss=0.1973, simple_loss=0.3001, pruned_loss=0.0473, over 7266.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2828, pruned_loss=0.04701, over 1422376.99 frames.], batch size: 24, lr: 5.95e-04
+2022-04-29 03:50:17,592 INFO [train.py:763] (2/8) Epoch 12, batch 1700, loss[loss=0.1638, simple_loss=0.2593, pruned_loss=0.03413, over 7145.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2822, pruned_loss=0.04675, over 1418513.10 frames.], batch size: 17, lr: 5.94e-04
+2022-04-29 03:51:23,274 INFO [train.py:763] (2/8) Epoch 12, batch 1750, loss[loss=0.2152, simple_loss=0.2993, pruned_loss=0.06549, over 7154.00 frames.], tot_loss[loss=0.1864, simple_loss=0.281, pruned_loss=0.04592, over 1421316.87 frames.], batch size: 26, lr: 5.94e-04
+2022-04-29 03:52:29,186 INFO [train.py:763] (2/8) Epoch 12, batch 1800, loss[loss=0.1726, simple_loss=0.2587, pruned_loss=0.04319, over 6993.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2821, pruned_loss=0.04643, over 1427216.23 frames.], batch size: 16, lr: 5.94e-04
+2022-04-29 03:53:35,385 INFO [train.py:763] (2/8) Epoch 12, batch 1850, loss[loss=0.1973, simple_loss=0.3051, pruned_loss=0.04476, over 7333.00 frames.], tot_loss[loss=0.1872, simple_loss=0.282, pruned_loss=0.04624, over 1427685.71 frames.], batch size: 22, lr: 5.94e-04
+2022-04-29 03:54:41,515 INFO [train.py:763] (2/8) Epoch 12, batch 1900, loss[loss=0.1804, simple_loss=0.2736, pruned_loss=0.04361, over 7227.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2811, pruned_loss=0.04565, over 1428360.25 frames.], batch size: 20, lr: 5.93e-04
+2022-04-29 03:55:47,350 INFO [train.py:763] (2/8) Epoch 12, batch 1950, loss[loss=0.1592, simple_loss=0.2436, pruned_loss=0.03735, over 7263.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2809, pruned_loss=0.04566, over 1428489.96 frames.], batch size: 17, lr: 5.93e-04
+2022-04-29 03:56:53,844 INFO [train.py:763] (2/8) Epoch 12, batch 2000, loss[loss=0.1598, simple_loss=0.2509, pruned_loss=0.03433, over 7402.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2803, pruned_loss=0.04569, over 1428732.16 frames.], batch size: 17, lr: 5.93e-04
+2022-04-29 03:57:59,756 INFO [train.py:763] (2/8) Epoch 12, batch 2050, loss[loss=0.1585, simple_loss=0.2597, pruned_loss=0.0287, over 7153.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2806, pruned_loss=0.04623, over 1422013.54 frames.], batch size: 19, lr: 5.93e-04
+2022-04-29 03:59:05,457 INFO [train.py:763] (2/8) Epoch 12, batch 2100, loss[loss=0.2176, simple_loss=0.2966, pruned_loss=0.06929, over 7151.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2814, pruned_loss=0.04651, over 1421980.67 frames.], batch size: 19, lr: 5.92e-04
+2022-04-29 04:00:11,328 INFO [train.py:763] (2/8) Epoch 12, batch 2150, loss[loss=0.1729, simple_loss=0.2516, pruned_loss=0.04711, over 7278.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2812, pruned_loss=0.04599, over 1422981.58 frames.], batch size: 18, lr: 5.92e-04
+2022-04-29 04:01:17,159 INFO [train.py:763] (2/8) Epoch 12, batch 2200, loss[loss=0.1728, simple_loss=0.276, pruned_loss=0.03474, over 7328.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2809, pruned_loss=0.04586, over 1423314.81 frames.], batch size: 20, lr: 5.92e-04
+2022-04-29 04:02:23,225 INFO [train.py:763] (2/8) Epoch 12, batch 2250, loss[loss=0.1976, simple_loss=0.3059, pruned_loss=0.04461, over 7052.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2808, pruned_loss=0.04589, over 1421698.39 frames.], batch size: 28, lr: 5.91e-04
+2022-04-29 04:03:29,737 INFO [train.py:763] (2/8) Epoch 12, batch 2300, loss[loss=0.172, simple_loss=0.2754, pruned_loss=0.0343, over 7117.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2811, pruned_loss=0.04586, over 1425222.70 frames.], batch size: 21, lr: 5.91e-04
+2022-04-29 04:04:36,289 INFO [train.py:763] (2/8) Epoch 12, batch 2350, loss[loss=0.1858, simple_loss=0.2848, pruned_loss=0.04335, over 7152.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2815, pruned_loss=0.04604, over 1426270.59 frames.], batch size: 19, lr: 5.91e-04
+2022-04-29 04:05:42,052 INFO [train.py:763] (2/8) Epoch 12, batch 2400, loss[loss=0.168, simple_loss=0.253, pruned_loss=0.04147, over 7165.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2812, pruned_loss=0.04572, over 1427291.93 frames.], batch size: 17, lr: 5.91e-04
+2022-04-29 04:06:47,898 INFO [train.py:763] (2/8) Epoch 12, batch 2450, loss[loss=0.172, simple_loss=0.2742, pruned_loss=0.0349, over 7211.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2813, pruned_loss=0.04606, over 1425927.11 frames.], batch size: 21, lr: 5.90e-04
+2022-04-29 04:07:54,984 INFO [train.py:763] (2/8) Epoch 12, batch 2500, loss[loss=0.1807, simple_loss=0.2654, pruned_loss=0.04801, over 7272.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2821, pruned_loss=0.04673, over 1426580.25 frames.], batch size: 18, lr: 5.90e-04
+2022-04-29 04:09:01,285 INFO [train.py:763] (2/8) Epoch 12, batch 2550, loss[loss=0.1619, simple_loss=0.2511, pruned_loss=0.03634, over 7237.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2827, pruned_loss=0.04747, over 1428066.99 frames.], batch size: 16, lr: 5.90e-04
+2022-04-29 04:10:08,000 INFO [train.py:763] (2/8) Epoch 12, batch 2600, loss[loss=0.1657, simple_loss=0.2558, pruned_loss=0.03781, over 7214.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2825, pruned_loss=0.04778, over 1424209.01 frames.], batch size: 16, lr: 5.90e-04
+2022-04-29 04:11:13,658 INFO [train.py:763] (2/8) Epoch 12, batch 2650, loss[loss=0.1589, simple_loss=0.2474, pruned_loss=0.03515, over 7003.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2819, pruned_loss=0.04719, over 1422809.98 frames.], batch size: 16, lr: 5.89e-04
+2022-04-29 04:12:19,548 INFO [train.py:763] (2/8) Epoch 12, batch 2700, loss[loss=0.1579, simple_loss=0.2449, pruned_loss=0.03544, over 6995.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2812, pruned_loss=0.04701, over 1423973.93 frames.], batch size: 16, lr: 5.89e-04
+2022-04-29 04:13:25,128 INFO [train.py:763] (2/8) Epoch 12, batch 2750, loss[loss=0.2016, simple_loss=0.3089, pruned_loss=0.0471, over 7108.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2812, pruned_loss=0.0468, over 1421937.58 frames.], batch size: 21, lr: 5.89e-04
+2022-04-29 04:14:30,844 INFO [train.py:763] (2/8) Epoch 12, batch 2800, loss[loss=0.1501, simple_loss=0.2451, pruned_loss=0.02753, over 7140.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2817, pruned_loss=0.04667, over 1422305.94 frames.], batch size: 17, lr: 5.89e-04
+2022-04-29 04:15:37,559 INFO [train.py:763] (2/8) Epoch 12, batch 2850, loss[loss=0.1802, simple_loss=0.272, pruned_loss=0.04423, over 7386.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2823, pruned_loss=0.04665, over 1428237.98 frames.], batch size: 23, lr: 5.88e-04
+2022-04-29 04:16:43,201 INFO [train.py:763] (2/8) Epoch 12, batch 2900, loss[loss=0.1651, simple_loss=0.261, pruned_loss=0.03459, over 7352.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2835, pruned_loss=0.04707, over 1425503.67 frames.], batch size: 19, lr: 5.88e-04
+2022-04-29 04:17:49,200 INFO [train.py:763] (2/8) Epoch 12, batch 2950, loss[loss=0.1778, simple_loss=0.2808, pruned_loss=0.03734, over 7113.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2818, pruned_loss=0.04632, over 1427186.87 frames.], batch size: 21, lr: 5.88e-04
+2022-04-29 04:18:54,865 INFO [train.py:763] (2/8) Epoch 12, batch 3000, loss[loss=0.1432, simple_loss=0.2326, pruned_loss=0.02687, over 7282.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2814, pruned_loss=0.04595, over 1427823.43 frames.], batch size: 17, lr: 5.88e-04
+2022-04-29 04:18:54,866 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 04:19:10,345 INFO [train.py:792] (2/8) Epoch 12, validation: loss=0.1673, simple_loss=0.27, pruned_loss=0.03225, over 698248.00 frames.
+2022-04-29 04:20:16,203 INFO [train.py:763] (2/8) Epoch 12, batch 3050, loss[loss=0.1635, simple_loss=0.2537, pruned_loss=0.03669, over 7138.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2808, pruned_loss=0.04578, over 1428154.87 frames.], batch size: 17, lr: 5.87e-04
+2022-04-29 04:21:32,106 INFO [train.py:763] (2/8) Epoch 12, batch 3100, loss[loss=0.175, simple_loss=0.2737, pruned_loss=0.03815, over 7118.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2799, pruned_loss=0.04551, over 1427665.20 frames.], batch size: 21, lr: 5.87e-04
+2022-04-29 04:22:37,467 INFO [train.py:763] (2/8) Epoch 12, batch 3150, loss[loss=0.1988, simple_loss=0.288, pruned_loss=0.05483, over 7307.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2807, pruned_loss=0.04553, over 1425103.30 frames.], batch size: 25, lr: 5.87e-04
+2022-04-29 04:23:52,374 INFO [train.py:763] (2/8) Epoch 12, batch 3200, loss[loss=0.2474, simple_loss=0.3191, pruned_loss=0.08784, over 5092.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2812, pruned_loss=0.04553, over 1426342.39 frames.], batch size: 52, lr: 5.87e-04
+2022-04-29 04:25:17,143 INFO [train.py:763] (2/8) Epoch 12, batch 3250, loss[loss=0.1663, simple_loss=0.2423, pruned_loss=0.04514, over 7263.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2807, pruned_loss=0.04553, over 1428325.22 frames.], batch size: 17, lr: 5.86e-04
+2022-04-29 04:26:23,033 INFO [train.py:763] (2/8) Epoch 12, batch 3300, loss[loss=0.1711, simple_loss=0.2717, pruned_loss=0.03524, over 7322.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2801, pruned_loss=0.04524, over 1428128.70 frames.], batch size: 20, lr: 5.86e-04
+2022-04-29 04:27:37,934 INFO [train.py:763] (2/8) Epoch 12, batch 3350, loss[loss=0.1666, simple_loss=0.2449, pruned_loss=0.04415, over 7429.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2803, pruned_loss=0.04572, over 1421078.29 frames.], batch size: 17, lr: 5.86e-04
+2022-04-29 04:29:03,557 INFO [train.py:763] (2/8) Epoch 12, batch 3400, loss[loss=0.1827, simple_loss=0.2957, pruned_loss=0.03488, over 7380.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2808, pruned_loss=0.04594, over 1424636.80 frames.], batch size: 23, lr: 5.86e-04
+2022-04-29 04:30:18,593 INFO [train.py:763] (2/8) Epoch 12, batch 3450, loss[loss=0.1777, simple_loss=0.2563, pruned_loss=0.04955, over 7419.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2819, pruned_loss=0.04692, over 1413793.92 frames.], batch size: 18, lr: 5.85e-04
+2022-04-29 04:31:24,818 INFO [train.py:763] (2/8) Epoch 12, batch 3500, loss[loss=0.193, simple_loss=0.3006, pruned_loss=0.04267, over 6982.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2822, pruned_loss=0.04678, over 1416553.39 frames.], batch size: 32, lr: 5.85e-04
+2022-04-29 04:32:31,883 INFO [train.py:763] (2/8) Epoch 12, batch 3550, loss[loss=0.1553, simple_loss=0.2467, pruned_loss=0.03194, over 6981.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2823, pruned_loss=0.04696, over 1421849.95 frames.], batch size: 16, lr: 5.85e-04
+2022-04-29 04:33:38,540 INFO [train.py:763] (2/8) Epoch 12, batch 3600, loss[loss=0.1718, simple_loss=0.2588, pruned_loss=0.0424, over 7283.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2818, pruned_loss=0.04656, over 1421205.82 frames.], batch size: 18, lr: 5.85e-04
+2022-04-29 04:34:44,018 INFO [train.py:763] (2/8) Epoch 12, batch 3650, loss[loss=0.2083, simple_loss=0.2998, pruned_loss=0.05838, over 7421.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2823, pruned_loss=0.04654, over 1423902.38 frames.], batch size: 21, lr: 5.84e-04
+2022-04-29 04:35:49,777 INFO [train.py:763] (2/8) Epoch 12, batch 3700, loss[loss=0.1864, simple_loss=0.2752, pruned_loss=0.04879, over 7247.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2813, pruned_loss=0.04627, over 1424734.87 frames.], batch size: 19, lr: 5.84e-04
+2022-04-29 04:36:55,379 INFO [train.py:763] (2/8) Epoch 12, batch 3750, loss[loss=0.217, simple_loss=0.312, pruned_loss=0.06104, over 7414.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2812, pruned_loss=0.04596, over 1425466.42 frames.], batch size: 21, lr: 5.84e-04
+2022-04-29 04:38:01,434 INFO [train.py:763] (2/8) Epoch 12, batch 3800, loss[loss=0.175, simple_loss=0.2763, pruned_loss=0.03682, over 7046.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2812, pruned_loss=0.04569, over 1429779.15 frames.], batch size: 28, lr: 5.84e-04
+2022-04-29 04:39:06,787 INFO [train.py:763] (2/8) Epoch 12, batch 3850, loss[loss=0.2178, simple_loss=0.3088, pruned_loss=0.06336, over 7198.00 frames.], tot_loss[loss=0.187, simple_loss=0.282, pruned_loss=0.04599, over 1427220.31 frames.], batch size: 22, lr: 5.83e-04
+2022-04-29 04:40:13,128 INFO [train.py:763] (2/8) Epoch 12, batch 3900, loss[loss=0.2117, simple_loss=0.314, pruned_loss=0.05468, over 7278.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2817, pruned_loss=0.04592, over 1425418.71 frames.], batch size: 24, lr: 5.83e-04
+2022-04-29 04:41:18,535 INFO [train.py:763] (2/8) Epoch 12, batch 3950, loss[loss=0.1911, simple_loss=0.2899, pruned_loss=0.04616, over 7205.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2811, pruned_loss=0.04536, over 1424670.70 frames.], batch size: 23, lr: 5.83e-04
+2022-04-29 04:42:24,200 INFO [train.py:763] (2/8) Epoch 12, batch 4000, loss[loss=0.1415, simple_loss=0.2311, pruned_loss=0.026, over 7134.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2813, pruned_loss=0.04553, over 1424086.76 frames.], batch size: 17, lr: 5.83e-04
+2022-04-29 04:43:29,488 INFO [train.py:763] (2/8) Epoch 12, batch 4050, loss[loss=0.1947, simple_loss=0.3066, pruned_loss=0.04135, over 7242.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2806, pruned_loss=0.0451, over 1425428.38 frames.], batch size: 20, lr: 5.82e-04
+2022-04-29 04:44:35,686 INFO [train.py:763] (2/8) Epoch 12, batch 4100, loss[loss=0.1969, simple_loss=0.2972, pruned_loss=0.04824, over 7150.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2791, pruned_loss=0.04481, over 1425162.29 frames.], batch size: 20, lr: 5.82e-04
+2022-04-29 04:45:41,161 INFO [train.py:763] (2/8) Epoch 12, batch 4150, loss[loss=0.1812, simple_loss=0.2724, pruned_loss=0.04502, over 7443.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2801, pruned_loss=0.04512, over 1419498.25 frames.], batch size: 20, lr: 5.82e-04
+2022-04-29 04:46:48,353 INFO [train.py:763] (2/8) Epoch 12, batch 4200, loss[loss=0.1769, simple_loss=0.2773, pruned_loss=0.03826, over 7143.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2796, pruned_loss=0.04528, over 1422237.90 frames.], batch size: 20, lr: 5.82e-04
+2022-04-29 04:47:54,426 INFO [train.py:763] (2/8) Epoch 12, batch 4250, loss[loss=0.199, simple_loss=0.299, pruned_loss=0.04953, over 7209.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2796, pruned_loss=0.04534, over 1419563.09 frames.], batch size: 26, lr: 5.81e-04
+2022-04-29 04:49:00,802 INFO [train.py:763] (2/8) Epoch 12, batch 4300, loss[loss=0.158, simple_loss=0.2528, pruned_loss=0.03165, over 7442.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2802, pruned_loss=0.04554, over 1417489.24 frames.], batch size: 20, lr: 5.81e-04
+2022-04-29 04:50:06,806 INFO [train.py:763] (2/8) Epoch 12, batch 4350, loss[loss=0.1473, simple_loss=0.2318, pruned_loss=0.03135, over 7011.00 frames.], tot_loss[loss=0.185, simple_loss=0.2796, pruned_loss=0.04522, over 1411571.26 frames.], batch size: 16, lr: 5.81e-04
+2022-04-29 04:51:13,413 INFO [train.py:763] (2/8) Epoch 12, batch 4400, loss[loss=0.1981, simple_loss=0.2983, pruned_loss=0.04891, over 5108.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2782, pruned_loss=0.04445, over 1410012.42 frames.], batch size: 52, lr: 5.81e-04
+2022-04-29 04:52:19,269 INFO [train.py:763] (2/8) Epoch 12, batch 4450, loss[loss=0.2178, simple_loss=0.3151, pruned_loss=0.06027, over 7288.00 frames.], tot_loss[loss=0.1833, simple_loss=0.278, pruned_loss=0.04437, over 1407617.89 frames.], batch size: 24, lr: 5.81e-04
+2022-04-29 04:53:25,176 INFO [train.py:763] (2/8) Epoch 12, batch 4500, loss[loss=0.1855, simple_loss=0.289, pruned_loss=0.04101, over 7417.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2806, pruned_loss=0.04623, over 1388241.37 frames.], batch size: 21, lr: 5.80e-04
+2022-04-29 04:54:31,133 INFO [train.py:763] (2/8) Epoch 12, batch 4550, loss[loss=0.2031, simple_loss=0.2901, pruned_loss=0.05804, over 5184.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2833, pruned_loss=0.04774, over 1354761.46 frames.], batch size: 52, lr: 5.80e-04
+2022-04-29 04:56:09,892 INFO [train.py:763] (2/8) Epoch 13, batch 0, loss[loss=0.1879, simple_loss=0.2815, pruned_loss=0.04719, over 7359.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2815, pruned_loss=0.04719, over 7359.00 frames.], batch size: 23, lr: 5.61e-04
+2022-04-29 04:57:15,970 INFO [train.py:763] (2/8) Epoch 13, batch 50, loss[loss=0.1936, simple_loss=0.2775, pruned_loss=0.05485, over 7107.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2726, pruned_loss=0.04125, over 322232.28 frames.], batch size: 21, lr: 5.61e-04
+2022-04-29 04:58:22,265 INFO [train.py:763] (2/8) Epoch 13, batch 100, loss[loss=0.2436, simple_loss=0.3318, pruned_loss=0.07767, over 7144.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2765, pruned_loss=0.04232, over 572561.33 frames.], batch size: 20, lr: 5.61e-04
+2022-04-29 04:59:28,139 INFO [train.py:763] (2/8) Epoch 13, batch 150, loss[loss=0.1764, simple_loss=0.2614, pruned_loss=0.04569, over 7024.00 frames.], tot_loss[loss=0.1809, simple_loss=0.277, pruned_loss=0.04238, over 763119.08 frames.], batch size: 16, lr: 5.61e-04
+2022-04-29 05:00:33,583 INFO [train.py:763] (2/8) Epoch 13, batch 200, loss[loss=0.1825, simple_loss=0.2907, pruned_loss=0.03718, over 7200.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2787, pruned_loss=0.04321, over 910467.32 frames.], batch size: 22, lr: 5.60e-04
+2022-04-29 05:01:39,399 INFO [train.py:763] (2/8) Epoch 13, batch 250, loss[loss=0.2063, simple_loss=0.3048, pruned_loss=0.05392, over 7216.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2791, pruned_loss=0.04351, over 1026607.16 frames.], batch size: 22, lr: 5.60e-04
+2022-04-29 05:02:44,820 INFO [train.py:763] (2/8) Epoch 13, batch 300, loss[loss=0.1559, simple_loss=0.2647, pruned_loss=0.02358, over 7414.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2808, pruned_loss=0.04417, over 1112570.18 frames.], batch size: 21, lr: 5.60e-04
+2022-04-29 05:03:50,334 INFO [train.py:763] (2/8) Epoch 13, batch 350, loss[loss=0.163, simple_loss=0.258, pruned_loss=0.03402, over 7434.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2789, pruned_loss=0.04397, over 1180874.57 frames.], batch size: 20, lr: 5.60e-04
+2022-04-29 05:04:55,867 INFO [train.py:763] (2/8) Epoch 13, batch 400, loss[loss=0.1973, simple_loss=0.3004, pruned_loss=0.04703, over 7096.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2785, pruned_loss=0.04383, over 1230502.21 frames.], batch size: 28, lr: 5.59e-04
+2022-04-29 05:06:01,966 INFO [train.py:763] (2/8) Epoch 13, batch 450, loss[loss=0.1956, simple_loss=0.2951, pruned_loss=0.04808, over 6226.00 frames.], tot_loss[loss=0.184, simple_loss=0.2798, pruned_loss=0.04411, over 1272386.66 frames.], batch size: 38, lr: 5.59e-04
+2022-04-29 05:07:07,982 INFO [train.py:763] (2/8) Epoch 13, batch 500, loss[loss=0.1999, simple_loss=0.2963, pruned_loss=0.05179, over 7143.00 frames.], tot_loss[loss=0.185, simple_loss=0.2803, pruned_loss=0.04488, over 1300243.72 frames.], batch size: 28, lr: 5.59e-04
+2022-04-29 05:08:13,587 INFO [train.py:763] (2/8) Epoch 13, batch 550, loss[loss=0.1813, simple_loss=0.2944, pruned_loss=0.03414, over 6717.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2805, pruned_loss=0.04502, over 1326291.24 frames.], batch size: 38, lr: 5.59e-04
+2022-04-29 05:09:19,615 INFO [train.py:763] (2/8) Epoch 13, batch 600, loss[loss=0.1836, simple_loss=0.2931, pruned_loss=0.03706, over 7316.00 frames.], tot_loss[loss=0.1839, simple_loss=0.279, pruned_loss=0.04442, over 1348628.16 frames.], batch size: 21, lr: 5.59e-04
+2022-04-29 05:10:25,761 INFO [train.py:763] (2/8) Epoch 13, batch 650, loss[loss=0.1854, simple_loss=0.2761, pruned_loss=0.04733, over 7063.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2792, pruned_loss=0.04453, over 1360574.13 frames.], batch size: 18, lr: 5.58e-04
+2022-04-29 05:11:32,547 INFO [train.py:763] (2/8) Epoch 13, batch 700, loss[loss=0.141, simple_loss=0.2363, pruned_loss=0.02288, over 7299.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2797, pruned_loss=0.04461, over 1375741.90 frames.], batch size: 18, lr: 5.58e-04
+2022-04-29 05:12:37,743 INFO [train.py:763] (2/8) Epoch 13, batch 750, loss[loss=0.2041, simple_loss=0.2965, pruned_loss=0.05587, over 7213.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2794, pruned_loss=0.04466, over 1382573.60 frames.], batch size: 23, lr: 5.58e-04
+2022-04-29 05:13:44,374 INFO [train.py:763] (2/8) Epoch 13, batch 800, loss[loss=0.209, simple_loss=0.3104, pruned_loss=0.05378, over 7307.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2801, pruned_loss=0.04471, over 1391893.47 frames.], batch size: 25, lr: 5.58e-04
+2022-04-29 05:14:50,889 INFO [train.py:763] (2/8) Epoch 13, batch 850, loss[loss=0.1698, simple_loss=0.2815, pruned_loss=0.02909, over 7226.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2791, pruned_loss=0.04374, over 1399944.75 frames.], batch size: 21, lr: 5.57e-04
+2022-04-29 05:15:57,546 INFO [train.py:763] (2/8) Epoch 13, batch 900, loss[loss=0.168, simple_loss=0.2685, pruned_loss=0.03377, over 7161.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2791, pruned_loss=0.0441, over 1402642.47 frames.], batch size: 18, lr: 5.57e-04
+2022-04-29 05:17:04,244 INFO [train.py:763] (2/8) Epoch 13, batch 950, loss[loss=0.187, simple_loss=0.2843, pruned_loss=0.0449, over 7228.00 frames.], tot_loss[loss=0.184, simple_loss=0.2794, pruned_loss=0.04429, over 1403615.11 frames.], batch size: 21, lr: 5.57e-04
+2022-04-29 05:18:11,091 INFO [train.py:763] (2/8) Epoch 13, batch 1000, loss[loss=0.2142, simple_loss=0.3194, pruned_loss=0.05445, over 7210.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2788, pruned_loss=0.04423, over 1410437.99 frames.], batch size: 22, lr: 5.57e-04
+2022-04-29 05:19:17,013 INFO [train.py:763] (2/8) Epoch 13, batch 1050, loss[loss=0.2301, simple_loss=0.3106, pruned_loss=0.07481, over 7429.00 frames.], tot_loss[loss=0.184, simple_loss=0.2789, pruned_loss=0.04451, over 1410926.15 frames.], batch size: 21, lr: 5.56e-04
+2022-04-29 05:20:22,744 INFO [train.py:763] (2/8) Epoch 13, batch 1100, loss[loss=0.2076, simple_loss=0.3026, pruned_loss=0.05629, over 6776.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2787, pruned_loss=0.04437, over 1410193.66 frames.], batch size: 31, lr: 5.56e-04
+2022-04-29 05:21:28,693 INFO [train.py:763] (2/8) Epoch 13, batch 1150, loss[loss=0.1993, simple_loss=0.2959, pruned_loss=0.05137, over 7338.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2805, pruned_loss=0.04543, over 1409973.28 frames.], batch size: 22, lr: 5.56e-04
+2022-04-29 05:22:34,606 INFO [train.py:763] (2/8) Epoch 13, batch 1200, loss[loss=0.2106, simple_loss=0.291, pruned_loss=0.0651, over 5407.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2805, pruned_loss=0.04544, over 1410336.10 frames.], batch size: 52, lr: 5.56e-04
+2022-04-29 05:23:40,297 INFO [train.py:763] (2/8) Epoch 13, batch 1250, loss[loss=0.1737, simple_loss=0.2642, pruned_loss=0.04159, over 7440.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2812, pruned_loss=0.04557, over 1414881.73 frames.], batch size: 20, lr: 5.56e-04
+2022-04-29 05:24:45,574 INFO [train.py:763] (2/8) Epoch 13, batch 1300, loss[loss=0.18, simple_loss=0.2685, pruned_loss=0.04576, over 7264.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2805, pruned_loss=0.04491, over 1418556.29 frames.], batch size: 19, lr: 5.55e-04
+2022-04-29 05:25:51,456 INFO [train.py:763] (2/8) Epoch 13, batch 1350, loss[loss=0.1767, simple_loss=0.2634, pruned_loss=0.04501, over 7275.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2799, pruned_loss=0.04483, over 1422163.03 frames.], batch size: 18, lr: 5.55e-04
+2022-04-29 05:26:57,105 INFO [train.py:763] (2/8) Epoch 13, batch 1400, loss[loss=0.161, simple_loss=0.2612, pruned_loss=0.03046, over 7162.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2805, pruned_loss=0.04507, over 1418170.48 frames.], batch size: 18, lr: 5.55e-04
+2022-04-29 05:28:02,589 INFO [train.py:763] (2/8) Epoch 13, batch 1450, loss[loss=0.1578, simple_loss=0.2422, pruned_loss=0.03671, over 7281.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2806, pruned_loss=0.04489, over 1421435.00 frames.], batch size: 17, lr: 5.55e-04
+2022-04-29 05:29:08,106 INFO [train.py:763] (2/8) Epoch 13, batch 1500, loss[loss=0.1634, simple_loss=0.2624, pruned_loss=0.03222, over 7269.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2796, pruned_loss=0.04482, over 1423869.29 frames.], batch size: 17, lr: 5.54e-04
+2022-04-29 05:30:14,043 INFO [train.py:763] (2/8) Epoch 13, batch 1550, loss[loss=0.1984, simple_loss=0.2932, pruned_loss=0.05183, over 6537.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2797, pruned_loss=0.0452, over 1418449.15 frames.], batch size: 38, lr: 5.54e-04
+2022-04-29 05:31:19,476 INFO [train.py:763] (2/8) Epoch 13, batch 1600, loss[loss=0.1837, simple_loss=0.2772, pruned_loss=0.04513, over 7402.00 frames.], tot_loss[loss=0.1852, simple_loss=0.28, pruned_loss=0.04517, over 1417311.37 frames.], batch size: 21, lr: 5.54e-04
+2022-04-29 05:32:25,606 INFO [train.py:763] (2/8) Epoch 13, batch 1650, loss[loss=0.1935, simple_loss=0.2849, pruned_loss=0.05102, over 7233.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2814, pruned_loss=0.04604, over 1419844.91 frames.], batch size: 20, lr: 5.54e-04
+2022-04-29 05:33:31,236 INFO [train.py:763] (2/8) Epoch 13, batch 1700, loss[loss=0.1985, simple_loss=0.2959, pruned_loss=0.05049, over 6612.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2814, pruned_loss=0.04563, over 1419468.38 frames.], batch size: 38, lr: 5.54e-04
+2022-04-29 05:34:36,765 INFO [train.py:763] (2/8) Epoch 13, batch 1750, loss[loss=0.1615, simple_loss=0.2488, pruned_loss=0.03713, over 7272.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2802, pruned_loss=0.04507, over 1421206.03 frames.], batch size: 17, lr: 5.53e-04
+2022-04-29 05:35:42,699 INFO [train.py:763] (2/8) Epoch 13, batch 1800, loss[loss=0.1939, simple_loss=0.2937, pruned_loss=0.04701, over 7148.00 frames.], tot_loss[loss=0.185, simple_loss=0.28, pruned_loss=0.04502, over 1425563.54 frames.], batch size: 20, lr: 5.53e-04
+2022-04-29 05:36:48,184 INFO [train.py:763] (2/8) Epoch 13, batch 1850, loss[loss=0.226, simple_loss=0.3201, pruned_loss=0.06599, over 7312.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2809, pruned_loss=0.04548, over 1425804.47 frames.], batch size: 25, lr: 5.53e-04
+2022-04-29 05:37:54,117 INFO [train.py:763] (2/8) Epoch 13, batch 1900, loss[loss=0.1908, simple_loss=0.2953, pruned_loss=0.04314, over 6617.00 frames.], tot_loss[loss=0.186, simple_loss=0.2809, pruned_loss=0.04551, over 1421276.94 frames.], batch size: 38, lr: 5.53e-04
+2022-04-29 05:39:00,688 INFO [train.py:763] (2/8) Epoch 13, batch 1950, loss[loss=0.2019, simple_loss=0.2956, pruned_loss=0.05414, over 7252.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2814, pruned_loss=0.04573, over 1422087.28 frames.], batch size: 19, lr: 5.52e-04
+2022-04-29 05:40:07,430 INFO [train.py:763] (2/8) Epoch 13, batch 2000, loss[loss=0.1698, simple_loss=0.2792, pruned_loss=0.03027, over 7345.00 frames.], tot_loss[loss=0.186, simple_loss=0.281, pruned_loss=0.04548, over 1423497.36 frames.], batch size: 22, lr: 5.52e-04
+2022-04-29 05:41:13,022 INFO [train.py:763] (2/8) Epoch 13, batch 2050, loss[loss=0.221, simple_loss=0.3103, pruned_loss=0.06588, over 7385.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2803, pruned_loss=0.04499, over 1425608.18 frames.], batch size: 23, lr: 5.52e-04
+2022-04-29 05:42:18,151 INFO [train.py:763] (2/8) Epoch 13, batch 2100, loss[loss=0.185, simple_loss=0.2915, pruned_loss=0.03929, over 7230.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2813, pruned_loss=0.04493, over 1424694.96 frames.], batch size: 20, lr: 5.52e-04
+2022-04-29 05:43:24,239 INFO [train.py:763] (2/8) Epoch 13, batch 2150, loss[loss=0.1727, simple_loss=0.2752, pruned_loss=0.03511, over 7190.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2804, pruned_loss=0.04445, over 1427616.07 frames.], batch size: 26, lr: 5.52e-04
+2022-04-29 05:44:29,756 INFO [train.py:763] (2/8) Epoch 13, batch 2200, loss[loss=0.1809, simple_loss=0.2717, pruned_loss=0.04505, over 7431.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2807, pruned_loss=0.04475, over 1426251.70 frames.], batch size: 20, lr: 5.51e-04
+2022-04-29 05:45:35,365 INFO [train.py:763] (2/8) Epoch 13, batch 2250, loss[loss=0.179, simple_loss=0.2756, pruned_loss=0.0412, over 7231.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2805, pruned_loss=0.04482, over 1427325.07 frames.], batch size: 20, lr: 5.51e-04
+2022-04-29 05:46:41,458 INFO [train.py:763] (2/8) Epoch 13, batch 2300, loss[loss=0.187, simple_loss=0.2868, pruned_loss=0.04361, over 7061.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2791, pruned_loss=0.04415, over 1427450.99 frames.], batch size: 28, lr: 5.51e-04
+2022-04-29 05:47:46,889 INFO [train.py:763] (2/8) Epoch 13, batch 2350, loss[loss=0.2351, simple_loss=0.3238, pruned_loss=0.07324, over 5340.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2795, pruned_loss=0.0442, over 1426843.86 frames.], batch size: 52, lr: 5.51e-04
+2022-04-29 05:48:52,767 INFO [train.py:763] (2/8) Epoch 13, batch 2400, loss[loss=0.1943, simple_loss=0.2762, pruned_loss=0.05618, over 7281.00 frames.], tot_loss[loss=0.183, simple_loss=0.2782, pruned_loss=0.04388, over 1428111.62 frames.], batch size: 17, lr: 5.50e-04
+2022-04-29 05:49:58,370 INFO [train.py:763] (2/8) Epoch 13, batch 2450, loss[loss=0.1909, simple_loss=0.3016, pruned_loss=0.0401, over 6767.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2777, pruned_loss=0.04359, over 1430511.90 frames.], batch size: 31, lr: 5.50e-04
+2022-04-29 05:51:03,648 INFO [train.py:763] (2/8) Epoch 13, batch 2500, loss[loss=0.1706, simple_loss=0.2573, pruned_loss=0.04195, over 7277.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2787, pruned_loss=0.04432, over 1425955.31 frames.], batch size: 17, lr: 5.50e-04
+2022-04-29 05:52:08,888 INFO [train.py:763] (2/8) Epoch 13, batch 2550, loss[loss=0.2247, simple_loss=0.3169, pruned_loss=0.06626, over 7347.00 frames.], tot_loss[loss=0.185, simple_loss=0.2799, pruned_loss=0.04501, over 1421634.45 frames.], batch size: 25, lr: 5.50e-04
+2022-04-29 05:53:14,606 INFO [train.py:763] (2/8) Epoch 13, batch 2600, loss[loss=0.1742, simple_loss=0.2818, pruned_loss=0.03334, over 7414.00 frames.], tot_loss[loss=0.185, simple_loss=0.2802, pruned_loss=0.0449, over 1418752.95 frames.], batch size: 21, lr: 5.50e-04
+2022-04-29 05:54:20,019 INFO [train.py:763] (2/8) Epoch 13, batch 2650, loss[loss=0.2172, simple_loss=0.3003, pruned_loss=0.06706, over 7120.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2804, pruned_loss=0.04459, over 1416748.15 frames.], batch size: 21, lr: 5.49e-04
+2022-04-29 05:55:25,825 INFO [train.py:763] (2/8) Epoch 13, batch 2700, loss[loss=0.2011, simple_loss=0.281, pruned_loss=0.06057, over 6999.00 frames.], tot_loss[loss=0.1843, simple_loss=0.28, pruned_loss=0.04436, over 1421402.40 frames.], batch size: 16, lr: 5.49e-04
+2022-04-29 05:56:31,323 INFO [train.py:763] (2/8) Epoch 13, batch 2750, loss[loss=0.1913, simple_loss=0.2902, pruned_loss=0.04622, over 7272.00 frames.], tot_loss[loss=0.184, simple_loss=0.2796, pruned_loss=0.04423, over 1426455.55 frames.], batch size: 24, lr: 5.49e-04
+2022-04-29 05:57:36,852 INFO [train.py:763] (2/8) Epoch 13, batch 2800, loss[loss=0.1632, simple_loss=0.2467, pruned_loss=0.03982, over 7139.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2791, pruned_loss=0.04404, over 1425386.16 frames.], batch size: 17, lr: 5.49e-04
+2022-04-29 05:58:42,726 INFO [train.py:763] (2/8) Epoch 13, batch 2850, loss[loss=0.1985, simple_loss=0.3044, pruned_loss=0.04634, over 7407.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2788, pruned_loss=0.04391, over 1426374.35 frames.], batch size: 21, lr: 5.48e-04
+2022-04-29 05:59:48,434 INFO [train.py:763] (2/8) Epoch 13, batch 2900, loss[loss=0.1928, simple_loss=0.303, pruned_loss=0.04134, over 7115.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2802, pruned_loss=0.04448, over 1427635.18 frames.], batch size: 21, lr: 5.48e-04
+2022-04-29 06:00:53,878 INFO [train.py:763] (2/8) Epoch 13, batch 2950, loss[loss=0.22, simple_loss=0.3051, pruned_loss=0.06746, over 7207.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2801, pruned_loss=0.04438, over 1429142.80 frames.], batch size: 23, lr: 5.48e-04
+2022-04-29 06:01:59,744 INFO [train.py:763] (2/8) Epoch 13, batch 3000, loss[loss=0.1914, simple_loss=0.2924, pruned_loss=0.04524, over 7296.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2792, pruned_loss=0.04431, over 1429901.25 frames.], batch size: 24, lr: 5.48e-04
+2022-04-29 06:01:59,745 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 06:02:15,158 INFO [train.py:792] (2/8) Epoch 13, validation: loss=0.1677, simple_loss=0.2714, pruned_loss=0.03198, over 698248.00 frames.
+2022-04-29 06:03:21,969 INFO [train.py:763] (2/8) Epoch 13, batch 3050, loss[loss=0.1796, simple_loss=0.2622, pruned_loss=0.04849, over 7295.00 frames.], tot_loss[loss=0.184, simple_loss=0.2793, pruned_loss=0.04429, over 1429716.97 frames.], batch size: 17, lr: 5.48e-04
+2022-04-29 06:04:29,180 INFO [train.py:763] (2/8) Epoch 13, batch 3100, loss[loss=0.1926, simple_loss=0.294, pruned_loss=0.04566, over 7214.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2792, pruned_loss=0.04397, over 1430919.47 frames.], batch size: 23, lr: 5.47e-04
+2022-04-29 06:05:35,702 INFO [train.py:763] (2/8) Epoch 13, batch 3150, loss[loss=0.2467, simple_loss=0.3222, pruned_loss=0.08561, over 5226.00 frames.], tot_loss[loss=0.183, simple_loss=0.2786, pruned_loss=0.04374, over 1429922.56 frames.], batch size: 52, lr: 5.47e-04
+2022-04-29 06:06:41,343 INFO [train.py:763] (2/8) Epoch 13, batch 3200, loss[loss=0.1845, simple_loss=0.2837, pruned_loss=0.04266, over 7342.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2783, pruned_loss=0.04361, over 1429790.23 frames.], batch size: 22, lr: 5.47e-04
+2022-04-29 06:07:46,882 INFO [train.py:763] (2/8) Epoch 13, batch 3250, loss[loss=0.2043, simple_loss=0.3018, pruned_loss=0.05341, over 7217.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2788, pruned_loss=0.04398, over 1426729.56 frames.], batch size: 26, lr: 5.47e-04
+2022-04-29 06:08:52,445 INFO [train.py:763] (2/8) Epoch 13, batch 3300, loss[loss=0.1684, simple_loss=0.2672, pruned_loss=0.03478, over 7166.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2791, pruned_loss=0.04394, over 1423225.25 frames.], batch size: 18, lr: 5.46e-04
+2022-04-29 06:09:57,826 INFO [train.py:763] (2/8) Epoch 13, batch 3350, loss[loss=0.1659, simple_loss=0.2656, pruned_loss=0.03311, over 7418.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2792, pruned_loss=0.04378, over 1425475.34 frames.], batch size: 18, lr: 5.46e-04
+2022-04-29 06:11:03,347 INFO [train.py:763] (2/8) Epoch 13, batch 3400, loss[loss=0.1786, simple_loss=0.2681, pruned_loss=0.0445, over 7167.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2786, pruned_loss=0.04348, over 1426661.71 frames.], batch size: 18, lr: 5.46e-04
+2022-04-29 06:12:10,256 INFO [train.py:763] (2/8) Epoch 13, batch 3450, loss[loss=0.1976, simple_loss=0.2986, pruned_loss=0.04834, over 7429.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2787, pruned_loss=0.04347, over 1426072.53 frames.], batch size: 22, lr: 5.46e-04
+2022-04-29 06:13:16,581 INFO [train.py:763] (2/8) Epoch 13, batch 3500, loss[loss=0.1726, simple_loss=0.2749, pruned_loss=0.03517, over 7340.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2785, pruned_loss=0.04368, over 1427698.98 frames.], batch size: 22, lr: 5.46e-04
+2022-04-29 06:14:22,078 INFO [train.py:763] (2/8) Epoch 13, batch 3550, loss[loss=0.1823, simple_loss=0.2953, pruned_loss=0.03465, over 7316.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2795, pruned_loss=0.04409, over 1427928.35 frames.], batch size: 21, lr: 5.45e-04
+2022-04-29 06:15:27,776 INFO [train.py:763] (2/8) Epoch 13, batch 3600, loss[loss=0.1682, simple_loss=0.2642, pruned_loss=0.03607, over 7359.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2787, pruned_loss=0.04406, over 1430882.44 frames.], batch size: 19, lr: 5.45e-04
+2022-04-29 06:16:33,705 INFO [train.py:763] (2/8) Epoch 13, batch 3650, loss[loss=0.186, simple_loss=0.2868, pruned_loss=0.04263, over 7239.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2789, pruned_loss=0.04396, over 1430302.11 frames.], batch size: 20, lr: 5.45e-04
+2022-04-29 06:17:39,180 INFO [train.py:763] (2/8) Epoch 13, batch 3700, loss[loss=0.2382, simple_loss=0.3333, pruned_loss=0.07155, over 7280.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2796, pruned_loss=0.0441, over 1422070.03 frames.], batch size: 24, lr: 5.45e-04
+2022-04-29 06:18:44,834 INFO [train.py:763] (2/8) Epoch 13, batch 3750, loss[loss=0.2268, simple_loss=0.3218, pruned_loss=0.06591, over 4963.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2807, pruned_loss=0.04457, over 1420578.76 frames.], batch size: 52, lr: 5.45e-04
+2022-04-29 06:19:51,468 INFO [train.py:763] (2/8) Epoch 13, batch 3800, loss[loss=0.1586, simple_loss=0.2418, pruned_loss=0.03769, over 6989.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2809, pruned_loss=0.04465, over 1420110.45 frames.], batch size: 16, lr: 5.44e-04
+2022-04-29 06:20:57,069 INFO [train.py:763] (2/8) Epoch 13, batch 3850, loss[loss=0.1921, simple_loss=0.2869, pruned_loss=0.04867, over 7198.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2808, pruned_loss=0.04463, over 1421434.54 frames.], batch size: 22, lr: 5.44e-04
+2022-04-29 06:22:02,331 INFO [train.py:763] (2/8) Epoch 13, batch 3900, loss[loss=0.1973, simple_loss=0.2998, pruned_loss=0.0474, over 7327.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2815, pruned_loss=0.04508, over 1423601.40 frames.], batch size: 21, lr: 5.44e-04
+2022-04-29 06:23:08,127 INFO [train.py:763] (2/8) Epoch 13, batch 3950, loss[loss=0.2584, simple_loss=0.329, pruned_loss=0.0939, over 4813.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2798, pruned_loss=0.04447, over 1421306.13 frames.], batch size: 53, lr: 5.44e-04
+2022-04-29 06:24:13,268 INFO [train.py:763] (2/8) Epoch 13, batch 4000, loss[loss=0.2025, simple_loss=0.3023, pruned_loss=0.05136, over 7351.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2806, pruned_loss=0.04473, over 1422626.40 frames.], batch size: 22, lr: 5.43e-04
+2022-04-29 06:25:19,010 INFO [train.py:763] (2/8) Epoch 13, batch 4050, loss[loss=0.1527, simple_loss=0.2419, pruned_loss=0.03173, over 7214.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2789, pruned_loss=0.04411, over 1423739.13 frames.], batch size: 16, lr: 5.43e-04
+2022-04-29 06:26:24,352 INFO [train.py:763] (2/8) Epoch 13, batch 4100, loss[loss=0.2053, simple_loss=0.3021, pruned_loss=0.05429, over 6625.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2787, pruned_loss=0.04419, over 1420861.08 frames.], batch size: 31, lr: 5.43e-04
+2022-04-29 06:27:29,931 INFO [train.py:763] (2/8) Epoch 13, batch 4150, loss[loss=0.1666, simple_loss=0.2626, pruned_loss=0.03527, over 7214.00 frames.], tot_loss[loss=0.182, simple_loss=0.2774, pruned_loss=0.04335, over 1420703.64 frames.], batch size: 21, lr: 5.43e-04
+2022-04-29 06:28:36,034 INFO [train.py:763] (2/8) Epoch 13, batch 4200, loss[loss=0.1664, simple_loss=0.252, pruned_loss=0.04045, over 7277.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2763, pruned_loss=0.04318, over 1421933.59 frames.], batch size: 17, lr: 5.43e-04
+2022-04-29 06:29:41,275 INFO [train.py:763] (2/8) Epoch 13, batch 4250, loss[loss=0.2146, simple_loss=0.3063, pruned_loss=0.06148, over 6461.00 frames.], tot_loss[loss=0.182, simple_loss=0.2774, pruned_loss=0.04326, over 1415900.94 frames.], batch size: 38, lr: 5.42e-04
+2022-04-29 06:30:47,743 INFO [train.py:763] (2/8) Epoch 13, batch 4300, loss[loss=0.1921, simple_loss=0.2989, pruned_loss=0.04263, over 7223.00 frames.], tot_loss[loss=0.1825, simple_loss=0.278, pruned_loss=0.04352, over 1412167.12 frames.], batch size: 21, lr: 5.42e-04
+2022-04-29 06:31:53,158 INFO [train.py:763] (2/8) Epoch 13, batch 4350, loss[loss=0.1494, simple_loss=0.2417, pruned_loss=0.02853, over 6767.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2781, pruned_loss=0.04389, over 1408258.66 frames.], batch size: 15, lr: 5.42e-04
+2022-04-29 06:33:10,014 INFO [train.py:763] (2/8) Epoch 13, batch 4400, loss[loss=0.1786, simple_loss=0.2859, pruned_loss=0.03563, over 7136.00 frames.], tot_loss[loss=0.183, simple_loss=0.2782, pruned_loss=0.04394, over 1401119.05 frames.], batch size: 20, lr: 5.42e-04
+2022-04-29 06:34:14,929 INFO [train.py:763] (2/8) Epoch 13, batch 4450, loss[loss=0.2118, simple_loss=0.2896, pruned_loss=0.06698, over 4942.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2796, pruned_loss=0.04464, over 1391381.48 frames.], batch size: 52, lr: 5.42e-04
+2022-04-29 06:35:30,492 INFO [train.py:763] (2/8) Epoch 13, batch 4500, loss[loss=0.1976, simple_loss=0.2829, pruned_loss=0.05618, over 5188.00 frames.], tot_loss[loss=0.1851, simple_loss=0.28, pruned_loss=0.04507, over 1376518.43 frames.], batch size: 52, lr: 5.41e-04
+2022-04-29 06:36:35,405 INFO [train.py:763] (2/8) Epoch 13, batch 4550, loss[loss=0.2035, simple_loss=0.2989, pruned_loss=0.05408, over 6704.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2802, pruned_loss=0.04516, over 1366841.90 frames.], batch size: 31, lr: 5.41e-04
+2022-04-29 06:38:13,962 INFO [train.py:763] (2/8) Epoch 14, batch 0, loss[loss=0.1976, simple_loss=0.2865, pruned_loss=0.05438, over 7087.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2865, pruned_loss=0.05438, over 7087.00 frames.], batch size: 28, lr: 5.25e-04
+2022-04-29 06:39:20,733 INFO [train.py:763] (2/8) Epoch 14, batch 50, loss[loss=0.2697, simple_loss=0.3466, pruned_loss=0.09639, over 4911.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2791, pruned_loss=0.04326, over 321677.96 frames.], batch size: 52, lr: 5.24e-04
+2022-04-29 06:40:45,782 INFO [train.py:763] (2/8) Epoch 14, batch 100, loss[loss=0.1561, simple_loss=0.2579, pruned_loss=0.02709, over 7162.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2777, pruned_loss=0.04226, over 568556.34 frames.], batch size: 18, lr: 5.24e-04
+2022-04-29 06:41:59,830 INFO [train.py:763] (2/8) Epoch 14, batch 150, loss[loss=0.1817, simple_loss=0.2878, pruned_loss=0.03776, over 7124.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2804, pruned_loss=0.04294, over 758755.42 frames.], batch size: 21, lr: 5.24e-04
+2022-04-29 06:43:06,512 INFO [train.py:763] (2/8) Epoch 14, batch 200, loss[loss=0.1795, simple_loss=0.2747, pruned_loss=0.04216, over 7332.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2808, pruned_loss=0.04346, over 902853.43 frames.], batch size: 20, lr: 5.24e-04
+2022-04-29 06:44:23,222 INFO [train.py:763] (2/8) Epoch 14, batch 250, loss[loss=0.1955, simple_loss=0.2975, pruned_loss=0.04677, over 6620.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2797, pruned_loss=0.04327, over 1019477.10 frames.], batch size: 38, lr: 5.24e-04
+2022-04-29 06:45:48,390 INFO [train.py:763] (2/8) Epoch 14, batch 300, loss[loss=0.1524, simple_loss=0.2388, pruned_loss=0.03298, over 7136.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2791, pruned_loss=0.04323, over 1109973.89 frames.], batch size: 17, lr: 5.23e-04
+2022-04-29 06:46:55,900 INFO [train.py:763] (2/8) Epoch 14, batch 350, loss[loss=0.1538, simple_loss=0.2463, pruned_loss=0.03064, over 6819.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2785, pruned_loss=0.04347, over 1171804.18 frames.], batch size: 15, lr: 5.23e-04
+2022-04-29 06:48:03,000 INFO [train.py:763] (2/8) Epoch 14, batch 400, loss[loss=0.1777, simple_loss=0.2874, pruned_loss=0.03398, over 7149.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2786, pruned_loss=0.04348, over 1226591.31 frames.], batch size: 20, lr: 5.23e-04
+2022-04-29 06:49:01,684 INFO [train.py:763] (2/8) Epoch 14, batch 450, loss[loss=0.193, simple_loss=0.2748, pruned_loss=0.05561, over 7162.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2777, pruned_loss=0.04296, over 1270973.17 frames.], batch size: 19, lr: 5.23e-04
+2022-04-29 06:50:05,437 INFO [train.py:763] (2/8) Epoch 14, batch 500, loss[loss=0.1574, simple_loss=0.2534, pruned_loss=0.03072, over 7418.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2776, pruned_loss=0.04243, over 1302686.02 frames.], batch size: 20, lr: 5.23e-04
+2022-04-29 06:51:07,458 INFO [train.py:763] (2/8) Epoch 14, batch 550, loss[loss=0.1472, simple_loss=0.2399, pruned_loss=0.02724, over 7275.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2774, pruned_loss=0.04253, over 1331948.12 frames.], batch size: 18, lr: 5.22e-04
+2022-04-29 06:52:12,670 INFO [train.py:763] (2/8) Epoch 14, batch 600, loss[loss=0.1835, simple_loss=0.2858, pruned_loss=0.04061, over 7236.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2766, pruned_loss=0.04239, over 1354976.46 frames.], batch size: 20, lr: 5.22e-04
+2022-04-29 06:53:18,166 INFO [train.py:763] (2/8) Epoch 14, batch 650, loss[loss=0.1977, simple_loss=0.2996, pruned_loss=0.04787, over 7334.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2774, pruned_loss=0.04254, over 1369346.35 frames.], batch size: 22, lr: 5.22e-04
+2022-04-29 06:54:23,429 INFO [train.py:763] (2/8) Epoch 14, batch 700, loss[loss=0.1974, simple_loss=0.2812, pruned_loss=0.05684, over 7335.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2784, pruned_loss=0.04292, over 1382265.54 frames.], batch size: 20, lr: 5.22e-04
+2022-04-29 06:55:28,864 INFO [train.py:763] (2/8) Epoch 14, batch 750, loss[loss=0.1882, simple_loss=0.2883, pruned_loss=0.04406, over 7345.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2782, pruned_loss=0.04313, over 1389548.23 frames.], batch size: 22, lr: 5.22e-04
+2022-04-29 06:56:34,176 INFO [train.py:763] (2/8) Epoch 14, batch 800, loss[loss=0.1878, simple_loss=0.2801, pruned_loss=0.04774, over 7327.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2784, pruned_loss=0.04313, over 1397993.96 frames.], batch size: 22, lr: 5.21e-04
+2022-04-29 06:57:40,705 INFO [train.py:763] (2/8) Epoch 14, batch 850, loss[loss=0.2043, simple_loss=0.2877, pruned_loss=0.06047, over 7129.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2791, pruned_loss=0.04371, over 1400909.72 frames.], batch size: 17, lr: 5.21e-04
+2022-04-29 06:58:46,052 INFO [train.py:763] (2/8) Epoch 14, batch 900, loss[loss=0.1655, simple_loss=0.2679, pruned_loss=0.03154, over 7260.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2781, pruned_loss=0.04334, over 1396048.95 frames.], batch size: 19, lr: 5.21e-04
+2022-04-29 06:59:51,291 INFO [train.py:763] (2/8) Epoch 14, batch 950, loss[loss=0.1662, simple_loss=0.2761, pruned_loss=0.02812, over 7336.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2791, pruned_loss=0.04368, over 1405135.21 frames.], batch size: 22, lr: 5.21e-04
+2022-04-29 07:00:56,951 INFO [train.py:763] (2/8) Epoch 14, batch 1000, loss[loss=0.2024, simple_loss=0.3024, pruned_loss=0.05117, over 7091.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2796, pruned_loss=0.04393, over 1406228.67 frames.], batch size: 28, lr: 5.21e-04
+2022-04-29 07:02:02,195 INFO [train.py:763] (2/8) Epoch 14, batch 1050, loss[loss=0.158, simple_loss=0.2484, pruned_loss=0.0338, over 7271.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2784, pruned_loss=0.0434, over 1412236.41 frames.], batch size: 18, lr: 5.20e-04
+2022-04-29 07:03:07,567 INFO [train.py:763] (2/8) Epoch 14, batch 1100, loss[loss=0.1707, simple_loss=0.2633, pruned_loss=0.03907, over 7270.00 frames.], tot_loss[loss=0.183, simple_loss=0.2782, pruned_loss=0.04388, over 1416098.69 frames.], batch size: 17, lr: 5.20e-04
+2022-04-29 07:04:13,186 INFO [train.py:763] (2/8) Epoch 14, batch 1150, loss[loss=0.2003, simple_loss=0.3042, pruned_loss=0.04815, over 7418.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2784, pruned_loss=0.04388, over 1421528.87 frames.], batch size: 21, lr: 5.20e-04
+2022-04-29 07:05:18,946 INFO [train.py:763] (2/8) Epoch 14, batch 1200, loss[loss=0.1697, simple_loss=0.2703, pruned_loss=0.03455, over 7424.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2777, pruned_loss=0.04362, over 1423497.68 frames.], batch size: 20, lr: 5.20e-04
+2022-04-29 07:06:24,244 INFO [train.py:763] (2/8) Epoch 14, batch 1250, loss[loss=0.1808, simple_loss=0.2756, pruned_loss=0.04303, over 7351.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2785, pruned_loss=0.04365, over 1426290.84 frames.], batch size: 19, lr: 5.20e-04
+2022-04-29 07:07:29,932 INFO [train.py:763] (2/8) Epoch 14, batch 1300, loss[loss=0.1839, simple_loss=0.2863, pruned_loss=0.0408, over 6380.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2777, pruned_loss=0.0432, over 1420257.36 frames.], batch size: 38, lr: 5.19e-04
+2022-04-29 07:08:35,853 INFO [train.py:763] (2/8) Epoch 14, batch 1350, loss[loss=0.1438, simple_loss=0.235, pruned_loss=0.0263, over 6980.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2785, pruned_loss=0.04337, over 1421704.78 frames.], batch size: 16, lr: 5.19e-04
+2022-04-29 07:09:40,885 INFO [train.py:763] (2/8) Epoch 14, batch 1400, loss[loss=0.2011, simple_loss=0.2962, pruned_loss=0.05303, over 7313.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2786, pruned_loss=0.04332, over 1421245.32 frames.], batch size: 24, lr: 5.19e-04
+2022-04-29 07:10:46,112 INFO [train.py:763] (2/8) Epoch 14, batch 1450, loss[loss=0.209, simple_loss=0.3145, pruned_loss=0.05173, over 7369.00 frames.], tot_loss[loss=0.1829, simple_loss=0.279, pruned_loss=0.04343, over 1419028.71 frames.], batch size: 23, lr: 5.19e-04
+2022-04-29 07:11:52,454 INFO [train.py:763] (2/8) Epoch 14, batch 1500, loss[loss=0.1713, simple_loss=0.2755, pruned_loss=0.03356, over 7134.00 frames.], tot_loss[loss=0.1829, simple_loss=0.279, pruned_loss=0.04339, over 1412830.26 frames.], batch size: 20, lr: 5.19e-04
+2022-04-29 07:12:59,674 INFO [train.py:763] (2/8) Epoch 14, batch 1550, loss[loss=0.1548, simple_loss=0.2655, pruned_loss=0.02204, over 7118.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2776, pruned_loss=0.04262, over 1417461.50 frames.], batch size: 21, lr: 5.18e-04
+2022-04-29 07:14:06,935 INFO [train.py:763] (2/8) Epoch 14, batch 1600, loss[loss=0.1709, simple_loss=0.2697, pruned_loss=0.03601, over 7407.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2773, pruned_loss=0.04268, over 1419122.82 frames.], batch size: 21, lr: 5.18e-04
+2022-04-29 07:15:13,437 INFO [train.py:763] (2/8) Epoch 14, batch 1650, loss[loss=0.2073, simple_loss=0.3048, pruned_loss=0.05492, over 7187.00 frames.], tot_loss[loss=0.181, simple_loss=0.2773, pruned_loss=0.04232, over 1423977.15 frames.], batch size: 23, lr: 5.18e-04
+2022-04-29 07:16:19,623 INFO [train.py:763] (2/8) Epoch 14, batch 1700, loss[loss=0.1819, simple_loss=0.273, pruned_loss=0.04538, over 7307.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2764, pruned_loss=0.04235, over 1427499.73 frames.], batch size: 25, lr: 5.18e-04
+2022-04-29 07:17:25,759 INFO [train.py:763] (2/8) Epoch 14, batch 1750, loss[loss=0.1986, simple_loss=0.3031, pruned_loss=0.04703, over 7101.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2767, pruned_loss=0.04234, over 1430440.03 frames.], batch size: 28, lr: 5.18e-04
+2022-04-29 07:18:30,995 INFO [train.py:763] (2/8) Epoch 14, batch 1800, loss[loss=0.1361, simple_loss=0.2271, pruned_loss=0.02251, over 7272.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2764, pruned_loss=0.04211, over 1427742.95 frames.], batch size: 17, lr: 5.17e-04
+2022-04-29 07:19:36,651 INFO [train.py:763] (2/8) Epoch 14, batch 1850, loss[loss=0.1983, simple_loss=0.2803, pruned_loss=0.05815, over 7160.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2773, pruned_loss=0.04272, over 1431610.21 frames.], batch size: 18, lr: 5.17e-04
+2022-04-29 07:20:42,275 INFO [train.py:763] (2/8) Epoch 14, batch 1900, loss[loss=0.1937, simple_loss=0.2945, pruned_loss=0.04643, over 7108.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2774, pruned_loss=0.0431, over 1431387.84 frames.], batch size: 21, lr: 5.17e-04
+2022-04-29 07:21:47,861 INFO [train.py:763] (2/8) Epoch 14, batch 1950, loss[loss=0.194, simple_loss=0.2907, pruned_loss=0.04863, over 7262.00 frames.], tot_loss[loss=0.181, simple_loss=0.2768, pruned_loss=0.0426, over 1431576.90 frames.], batch size: 18, lr: 5.17e-04
+2022-04-29 07:22:53,273 INFO [train.py:763] (2/8) Epoch 14, batch 2000, loss[loss=0.1849, simple_loss=0.2813, pruned_loss=0.04423, over 6574.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2773, pruned_loss=0.04303, over 1427536.86 frames.], batch size: 37, lr: 5.17e-04
+2022-04-29 07:23:58,399 INFO [train.py:763] (2/8) Epoch 14, batch 2050, loss[loss=0.1764, simple_loss=0.2755, pruned_loss=0.03861, over 7301.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2785, pruned_loss=0.04317, over 1429311.32 frames.], batch size: 25, lr: 5.16e-04
+2022-04-29 07:25:03,739 INFO [train.py:763] (2/8) Epoch 14, batch 2100, loss[loss=0.132, simple_loss=0.2188, pruned_loss=0.02256, over 7403.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2773, pruned_loss=0.04299, over 1423076.85 frames.], batch size: 18, lr: 5.16e-04
+2022-04-29 07:26:09,017 INFO [train.py:763] (2/8) Epoch 14, batch 2150, loss[loss=0.194, simple_loss=0.2948, pruned_loss=0.04658, over 7201.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2769, pruned_loss=0.04291, over 1421096.84 frames.], batch size: 22, lr: 5.16e-04
+2022-04-29 07:27:14,549 INFO [train.py:763] (2/8) Epoch 14, batch 2200, loss[loss=0.1793, simple_loss=0.2793, pruned_loss=0.03964, over 7435.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2779, pruned_loss=0.04344, over 1420887.62 frames.], batch size: 20, lr: 5.16e-04
+2022-04-29 07:28:19,749 INFO [train.py:763] (2/8) Epoch 14, batch 2250, loss[loss=0.1696, simple_loss=0.269, pruned_loss=0.03507, over 7148.00 frames.], tot_loss[loss=0.1824, simple_loss=0.278, pruned_loss=0.0434, over 1422452.97 frames.], batch size: 28, lr: 5.16e-04
+2022-04-29 07:29:24,984 INFO [train.py:763] (2/8) Epoch 14, batch 2300, loss[loss=0.1598, simple_loss=0.2455, pruned_loss=0.03708, over 6786.00 frames.], tot_loss[loss=0.1812, simple_loss=0.277, pruned_loss=0.04267, over 1422359.28 frames.], batch size: 15, lr: 5.15e-04
+2022-04-29 07:30:30,165 INFO [train.py:763] (2/8) Epoch 14, batch 2350, loss[loss=0.1586, simple_loss=0.2484, pruned_loss=0.03434, over 7412.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2768, pruned_loss=0.04242, over 1424663.54 frames.], batch size: 18, lr: 5.15e-04
+2022-04-29 07:31:35,491 INFO [train.py:763] (2/8) Epoch 14, batch 2400, loss[loss=0.155, simple_loss=0.2472, pruned_loss=0.03139, over 7411.00 frames.], tot_loss[loss=0.182, simple_loss=0.278, pruned_loss=0.04296, over 1421775.21 frames.], batch size: 18, lr: 5.15e-04
+2022-04-29 07:32:40,928 INFO [train.py:763] (2/8) Epoch 14, batch 2450, loss[loss=0.1704, simple_loss=0.2688, pruned_loss=0.03597, over 7401.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2771, pruned_loss=0.04237, over 1422338.64 frames.], batch size: 21, lr: 5.15e-04
+2022-04-29 07:33:46,233 INFO [train.py:763] (2/8) Epoch 14, batch 2500, loss[loss=0.1954, simple_loss=0.2927, pruned_loss=0.04905, over 7323.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2786, pruned_loss=0.04307, over 1423449.44 frames.], batch size: 21, lr: 5.15e-04
+2022-04-29 07:34:51,429 INFO [train.py:763] (2/8) Epoch 14, batch 2550, loss[loss=0.1702, simple_loss=0.2556, pruned_loss=0.04238, over 7158.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2791, pruned_loss=0.0435, over 1426345.73 frames.], batch size: 18, lr: 5.14e-04
+2022-04-29 07:35:56,545 INFO [train.py:763] (2/8) Epoch 14, batch 2600, loss[loss=0.1731, simple_loss=0.2766, pruned_loss=0.0348, over 7208.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2794, pruned_loss=0.0436, over 1421414.05 frames.], batch size: 23, lr: 5.14e-04
+2022-04-29 07:37:01,618 INFO [train.py:763] (2/8) Epoch 14, batch 2650, loss[loss=0.2056, simple_loss=0.2907, pruned_loss=0.06027, over 7276.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2794, pruned_loss=0.04387, over 1421413.17 frames.], batch size: 25, lr: 5.14e-04
+2022-04-29 07:38:06,934 INFO [train.py:763] (2/8) Epoch 14, batch 2700, loss[loss=0.1882, simple_loss=0.2945, pruned_loss=0.04098, over 7321.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2794, pruned_loss=0.04343, over 1423835.24 frames.], batch size: 21, lr: 5.14e-04
+2022-04-29 07:39:12,132 INFO [train.py:763] (2/8) Epoch 14, batch 2750, loss[loss=0.1838, simple_loss=0.2858, pruned_loss=0.04089, over 7278.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2787, pruned_loss=0.04327, over 1424290.29 frames.], batch size: 24, lr: 5.14e-04
+2022-04-29 07:40:17,442 INFO [train.py:763] (2/8) Epoch 14, batch 2800, loss[loss=0.1781, simple_loss=0.2841, pruned_loss=0.036, over 7138.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2787, pruned_loss=0.04301, over 1427079.56 frames.], batch size: 20, lr: 5.14e-04
+2022-04-29 07:41:22,758 INFO [train.py:763] (2/8) Epoch 14, batch 2850, loss[loss=0.1776, simple_loss=0.2677, pruned_loss=0.04371, over 6807.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2784, pruned_loss=0.04287, over 1427425.89 frames.], batch size: 15, lr: 5.13e-04
+2022-04-29 07:42:28,523 INFO [train.py:763] (2/8) Epoch 14, batch 2900, loss[loss=0.2002, simple_loss=0.2979, pruned_loss=0.05129, over 7358.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2786, pruned_loss=0.04297, over 1423801.16 frames.], batch size: 23, lr: 5.13e-04
+2022-04-29 07:43:34,053 INFO [train.py:763] (2/8) Epoch 14, batch 2950, loss[loss=0.1741, simple_loss=0.2777, pruned_loss=0.03526, over 7434.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2786, pruned_loss=0.04256, over 1425448.30 frames.], batch size: 20, lr: 5.13e-04
+2022-04-29 07:44:39,579 INFO [train.py:763] (2/8) Epoch 14, batch 3000, loss[loss=0.1873, simple_loss=0.282, pruned_loss=0.04631, over 7153.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2782, pruned_loss=0.04271, over 1422672.96 frames.], batch size: 19, lr: 5.13e-04
+2022-04-29 07:44:39,580 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 07:44:54,980 INFO [train.py:792] (2/8) Epoch 14, validation: loss=0.1687, simple_loss=0.2708, pruned_loss=0.03331, over 698248.00 frames.
+2022-04-29 07:46:00,328 INFO [train.py:763] (2/8) Epoch 14, batch 3050, loss[loss=0.152, simple_loss=0.2497, pruned_loss=0.02717, over 7265.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2782, pruned_loss=0.04295, over 1426264.40 frames.], batch size: 16, lr: 5.13e-04
+2022-04-29 07:47:05,873 INFO [train.py:763] (2/8) Epoch 14, batch 3100, loss[loss=0.1791, simple_loss=0.2811, pruned_loss=0.03851, over 7336.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2784, pruned_loss=0.04311, over 1422583.98 frames.], batch size: 20, lr: 5.12e-04
+2022-04-29 07:48:12,211 INFO [train.py:763] (2/8) Epoch 14, batch 3150, loss[loss=0.1878, simple_loss=0.2737, pruned_loss=0.051, over 7288.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2778, pruned_loss=0.04319, over 1427725.38 frames.], batch size: 17, lr: 5.12e-04
+2022-04-29 07:49:18,808 INFO [train.py:763] (2/8) Epoch 14, batch 3200, loss[loss=0.182, simple_loss=0.2724, pruned_loss=0.04581, over 7082.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2771, pruned_loss=0.04316, over 1428094.30 frames.], batch size: 28, lr: 5.12e-04
+2022-04-29 07:50:24,259 INFO [train.py:763] (2/8) Epoch 14, batch 3250, loss[loss=0.1868, simple_loss=0.2809, pruned_loss=0.04637, over 7055.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2763, pruned_loss=0.04293, over 1428293.15 frames.], batch size: 18, lr: 5.12e-04
+2022-04-29 07:51:29,736 INFO [train.py:763] (2/8) Epoch 14, batch 3300, loss[loss=0.1814, simple_loss=0.2676, pruned_loss=0.04762, over 7289.00 frames.], tot_loss[loss=0.1796, simple_loss=0.275, pruned_loss=0.04209, over 1426897.53 frames.], batch size: 17, lr: 5.12e-04
+2022-04-29 07:52:35,055 INFO [train.py:763] (2/8) Epoch 14, batch 3350, loss[loss=0.189, simple_loss=0.2862, pruned_loss=0.04588, over 7187.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2761, pruned_loss=0.04236, over 1426341.08 frames.], batch size: 23, lr: 5.11e-04
+2022-04-29 07:53:40,777 INFO [train.py:763] (2/8) Epoch 14, batch 3400, loss[loss=0.1806, simple_loss=0.2823, pruned_loss=0.03949, over 7220.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2771, pruned_loss=0.04254, over 1423213.25 frames.], batch size: 21, lr: 5.11e-04
+2022-04-29 07:54:45,990 INFO [train.py:763] (2/8) Epoch 14, batch 3450, loss[loss=0.1775, simple_loss=0.2841, pruned_loss=0.03546, over 7051.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2782, pruned_loss=0.04313, over 1420057.58 frames.], batch size: 28, lr: 5.11e-04
+2022-04-29 07:55:51,601 INFO [train.py:763] (2/8) Epoch 14, batch 3500, loss[loss=0.213, simple_loss=0.3103, pruned_loss=0.05785, over 7118.00 frames.], tot_loss[loss=0.1811, simple_loss=0.277, pruned_loss=0.04256, over 1425459.11 frames.], batch size: 26, lr: 5.11e-04
+2022-04-29 07:56:57,020 INFO [train.py:763] (2/8) Epoch 14, batch 3550, loss[loss=0.1781, simple_loss=0.2672, pruned_loss=0.04449, over 7243.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2777, pruned_loss=0.04296, over 1426953.14 frames.], batch size: 20, lr: 5.11e-04
+2022-04-29 07:58:03,505 INFO [train.py:763] (2/8) Epoch 14, batch 3600, loss[loss=0.1896, simple_loss=0.2772, pruned_loss=0.051, over 7317.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2777, pruned_loss=0.04302, over 1423483.18 frames.], batch size: 21, lr: 5.11e-04
+2022-04-29 07:59:08,915 INFO [train.py:763] (2/8) Epoch 14, batch 3650, loss[loss=0.1712, simple_loss=0.2789, pruned_loss=0.03174, over 7261.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2773, pruned_loss=0.04253, over 1424592.64 frames.], batch size: 19, lr: 5.10e-04
+2022-04-29 08:00:14,234 INFO [train.py:763] (2/8) Epoch 14, batch 3700, loss[loss=0.1687, simple_loss=0.2684, pruned_loss=0.03451, over 7430.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2776, pruned_loss=0.04236, over 1421985.46 frames.], batch size: 20, lr: 5.10e-04
+2022-04-29 08:01:19,992 INFO [train.py:763] (2/8) Epoch 14, batch 3750, loss[loss=0.2174, simple_loss=0.3053, pruned_loss=0.06473, over 5410.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2777, pruned_loss=0.04287, over 1424655.47 frames.], batch size: 52, lr: 5.10e-04
+2022-04-29 08:02:27,029 INFO [train.py:763] (2/8) Epoch 14, batch 3800, loss[loss=0.1669, simple_loss=0.2576, pruned_loss=0.03807, over 7450.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2781, pruned_loss=0.04266, over 1426557.83 frames.], batch size: 19, lr: 5.10e-04
+2022-04-29 08:03:33,820 INFO [train.py:763] (2/8) Epoch 14, batch 3850, loss[loss=0.1917, simple_loss=0.2991, pruned_loss=0.0422, over 7242.00 frames.], tot_loss[loss=0.182, simple_loss=0.2784, pruned_loss=0.04275, over 1428748.73 frames.], batch size: 20, lr: 5.10e-04
+2022-04-29 08:04:40,264 INFO [train.py:763] (2/8) Epoch 14, batch 3900, loss[loss=0.1916, simple_loss=0.2779, pruned_loss=0.0526, over 7257.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2778, pruned_loss=0.04234, over 1426204.40 frames.], batch size: 19, lr: 5.09e-04
+2022-04-29 08:05:46,497 INFO [train.py:763] (2/8) Epoch 14, batch 3950, loss[loss=0.1642, simple_loss=0.2587, pruned_loss=0.03486, over 7359.00 frames.], tot_loss[loss=0.181, simple_loss=0.2772, pruned_loss=0.04245, over 1423016.17 frames.], batch size: 19, lr: 5.09e-04
+2022-04-29 08:06:52,809 INFO [train.py:763] (2/8) Epoch 14, batch 4000, loss[loss=0.1871, simple_loss=0.2937, pruned_loss=0.04021, over 7229.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2776, pruned_loss=0.04266, over 1422894.16 frames.], batch size: 21, lr: 5.09e-04
+2022-04-29 08:07:57,991 INFO [train.py:763] (2/8) Epoch 14, batch 4050, loss[loss=0.1907, simple_loss=0.2917, pruned_loss=0.04487, over 7223.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2777, pruned_loss=0.04271, over 1427107.73 frames.], batch size: 21, lr: 5.09e-04
+2022-04-29 08:09:03,250 INFO [train.py:763] (2/8) Epoch 14, batch 4100, loss[loss=0.2079, simple_loss=0.3159, pruned_loss=0.04994, over 7209.00 frames.], tot_loss[loss=0.182, simple_loss=0.278, pruned_loss=0.04302, over 1418965.44 frames.], batch size: 23, lr: 5.09e-04
+2022-04-29 08:10:08,496 INFO [train.py:763] (2/8) Epoch 14, batch 4150, loss[loss=0.2302, simple_loss=0.3219, pruned_loss=0.06921, over 4745.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2778, pruned_loss=0.04292, over 1412386.53 frames.], batch size: 53, lr: 5.08e-04
+2022-04-29 08:11:13,730 INFO [train.py:763] (2/8) Epoch 14, batch 4200, loss[loss=0.1836, simple_loss=0.282, pruned_loss=0.04261, over 7228.00 frames.], tot_loss[loss=0.181, simple_loss=0.2766, pruned_loss=0.04267, over 1410147.31 frames.], batch size: 20, lr: 5.08e-04
+2022-04-29 08:12:19,793 INFO [train.py:763] (2/8) Epoch 14, batch 4250, loss[loss=0.1616, simple_loss=0.2547, pruned_loss=0.03424, over 7073.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2757, pruned_loss=0.04226, over 1408176.45 frames.], batch size: 18, lr: 5.08e-04
+2022-04-29 08:13:25,927 INFO [train.py:763] (2/8) Epoch 14, batch 4300, loss[loss=0.156, simple_loss=0.2432, pruned_loss=0.03436, over 7209.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2756, pruned_loss=0.04199, over 1404044.69 frames.], batch size: 16, lr: 5.08e-04
+2022-04-29 08:14:30,944 INFO [train.py:763] (2/8) Epoch 14, batch 4350, loss[loss=0.1759, simple_loss=0.2788, pruned_loss=0.03652, over 7327.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2766, pruned_loss=0.0424, over 1408215.88 frames.], batch size: 21, lr: 5.08e-04
+2022-04-29 08:15:37,006 INFO [train.py:763] (2/8) Epoch 14, batch 4400, loss[loss=0.1555, simple_loss=0.2563, pruned_loss=0.02739, over 7146.00 frames.], tot_loss[loss=0.18, simple_loss=0.2759, pruned_loss=0.04209, over 1410483.51 frames.], batch size: 19, lr: 5.08e-04
+2022-04-29 08:16:42,685 INFO [train.py:763] (2/8) Epoch 14, batch 4450, loss[loss=0.1525, simple_loss=0.2454, pruned_loss=0.02978, over 7157.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2747, pruned_loss=0.04207, over 1402951.21 frames.], batch size: 18, lr: 5.07e-04
+2022-04-29 08:17:47,609 INFO [train.py:763] (2/8) Epoch 14, batch 4500, loss[loss=0.169, simple_loss=0.2696, pruned_loss=0.03416, over 7458.00 frames.], tot_loss[loss=0.18, simple_loss=0.2754, pruned_loss=0.04229, over 1394192.48 frames.], batch size: 19, lr: 5.07e-04
+2022-04-29 08:18:51,942 INFO [train.py:763] (2/8) Epoch 14, batch 4550, loss[loss=0.2126, simple_loss=0.3064, pruned_loss=0.05941, over 4697.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2768, pruned_loss=0.0433, over 1367536.07 frames.], batch size: 52, lr: 5.07e-04
+2022-04-29 08:20:20,831 INFO [train.py:763] (2/8) Epoch 15, batch 0, loss[loss=0.1972, simple_loss=0.2946, pruned_loss=0.04987, over 7301.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2946, pruned_loss=0.04987, over 7301.00 frames.], batch size: 24, lr: 4.92e-04
+2022-04-29 08:21:27,543 INFO [train.py:763] (2/8) Epoch 15, batch 50, loss[loss=0.1692, simple_loss=0.2626, pruned_loss=0.03784, over 7398.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2804, pruned_loss=0.04295, over 320675.39 frames.], batch size: 18, lr: 4.92e-04
+2022-04-29 08:22:33,673 INFO [train.py:763] (2/8) Epoch 15, batch 100, loss[loss=0.1825, simple_loss=0.2839, pruned_loss=0.04054, over 7330.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2782, pruned_loss=0.04256, over 564019.73 frames.], batch size: 20, lr: 4.92e-04
+2022-04-29 08:23:40,359 INFO [train.py:763] (2/8) Epoch 15, batch 150, loss[loss=0.1899, simple_loss=0.2907, pruned_loss=0.04451, over 7149.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2783, pruned_loss=0.04275, over 753819.71 frames.], batch size: 20, lr: 4.92e-04
+2022-04-29 08:24:46,766 INFO [train.py:763] (2/8) Epoch 15, batch 200, loss[loss=0.1866, simple_loss=0.2906, pruned_loss=0.0413, over 7108.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2771, pruned_loss=0.04239, over 898172.81 frames.], batch size: 21, lr: 4.91e-04
+2022-04-29 08:25:52,224 INFO [train.py:763] (2/8) Epoch 15, batch 250, loss[loss=0.1576, simple_loss=0.2584, pruned_loss=0.02835, over 7156.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2767, pruned_loss=0.04252, over 1015032.48 frames.], batch size: 19, lr: 4.91e-04
+2022-04-29 08:26:57,837 INFO [train.py:763] (2/8) Epoch 15, batch 300, loss[loss=0.1708, simple_loss=0.2709, pruned_loss=0.03533, over 7155.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2759, pruned_loss=0.0424, over 1108662.47 frames.], batch size: 19, lr: 4.91e-04
+2022-04-29 08:28:03,218 INFO [train.py:763] (2/8) Epoch 15, batch 350, loss[loss=0.1535, simple_loss=0.2496, pruned_loss=0.02868, over 7278.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2759, pruned_loss=0.04191, over 1179680.48 frames.], batch size: 18, lr: 4.91e-04
+2022-04-29 08:29:08,688 INFO [train.py:763] (2/8) Epoch 15, batch 400, loss[loss=0.1685, simple_loss=0.2619, pruned_loss=0.03755, over 7258.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2776, pruned_loss=0.04238, over 1234509.69 frames.], batch size: 19, lr: 4.91e-04
+2022-04-29 08:30:14,238 INFO [train.py:763] (2/8) Epoch 15, batch 450, loss[loss=0.1773, simple_loss=0.2793, pruned_loss=0.03766, over 7423.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2773, pruned_loss=0.04225, over 1281383.33 frames.], batch size: 20, lr: 4.91e-04
+2022-04-29 08:31:19,780 INFO [train.py:763] (2/8) Epoch 15, batch 500, loss[loss=0.2123, simple_loss=0.3114, pruned_loss=0.05661, over 7178.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2774, pruned_loss=0.04208, over 1318084.59 frames.], batch size: 23, lr: 4.90e-04
+2022-04-29 08:32:25,944 INFO [train.py:763] (2/8) Epoch 15, batch 550, loss[loss=0.1721, simple_loss=0.2658, pruned_loss=0.03918, over 7288.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2761, pruned_loss=0.04171, over 1345311.67 frames.], batch size: 18, lr: 4.90e-04
+2022-04-29 08:33:31,107 INFO [train.py:763] (2/8) Epoch 15, batch 600, loss[loss=0.1776, simple_loss=0.2773, pruned_loss=0.03896, over 7163.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2759, pruned_loss=0.04112, over 1360517.10 frames.], batch size: 19, lr: 4.90e-04
+2022-04-29 08:34:36,397 INFO [train.py:763] (2/8) Epoch 15, batch 650, loss[loss=0.2147, simple_loss=0.307, pruned_loss=0.06117, over 6361.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2762, pruned_loss=0.04143, over 1372884.00 frames.], batch size: 38, lr: 4.90e-04
+2022-04-29 08:35:42,057 INFO [train.py:763] (2/8) Epoch 15, batch 700, loss[loss=0.1765, simple_loss=0.2872, pruned_loss=0.03292, over 6974.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2762, pruned_loss=0.04134, over 1385751.85 frames.], batch size: 28, lr: 4.90e-04
+2022-04-29 08:36:47,191 INFO [train.py:763] (2/8) Epoch 15, batch 750, loss[loss=0.1854, simple_loss=0.2839, pruned_loss=0.04344, over 7154.00 frames.], tot_loss[loss=0.179, simple_loss=0.2757, pruned_loss=0.04111, over 1394426.28 frames.], batch size: 19, lr: 4.89e-04
+2022-04-29 08:37:53,214 INFO [train.py:763] (2/8) Epoch 15, batch 800, loss[loss=0.1856, simple_loss=0.2885, pruned_loss=0.04134, over 7248.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2757, pruned_loss=0.04108, over 1401717.72 frames.], batch size: 19, lr: 4.89e-04
+2022-04-29 08:39:00,102 INFO [train.py:763] (2/8) Epoch 15, batch 850, loss[loss=0.1821, simple_loss=0.2779, pruned_loss=0.0431, over 7149.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2762, pruned_loss=0.04126, over 1403426.55 frames.], batch size: 20, lr: 4.89e-04
+2022-04-29 08:40:05,801 INFO [train.py:763] (2/8) Epoch 15, batch 900, loss[loss=0.1742, simple_loss=0.2757, pruned_loss=0.03635, over 7371.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2771, pruned_loss=0.04207, over 1402726.92 frames.], batch size: 19, lr: 4.89e-04
+2022-04-29 08:41:11,036 INFO [train.py:763] (2/8) Epoch 15, batch 950, loss[loss=0.1819, simple_loss=0.2823, pruned_loss=0.04073, over 7441.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2767, pruned_loss=0.04195, over 1406109.96 frames.], batch size: 20, lr: 4.89e-04
+2022-04-29 08:42:16,441 INFO [train.py:763] (2/8) Epoch 15, batch 1000, loss[loss=0.1855, simple_loss=0.2864, pruned_loss=0.04227, over 7296.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2759, pruned_loss=0.04166, over 1412514.91 frames.], batch size: 25, lr: 4.89e-04
+2022-04-29 08:43:21,668 INFO [train.py:763] (2/8) Epoch 15, batch 1050, loss[loss=0.1696, simple_loss=0.2659, pruned_loss=0.0366, over 7324.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2759, pruned_loss=0.04182, over 1417802.78 frames.], batch size: 20, lr: 4.88e-04
+2022-04-29 08:44:28,811 INFO [train.py:763] (2/8) Epoch 15, batch 1100, loss[loss=0.1404, simple_loss=0.2366, pruned_loss=0.02212, over 7354.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2755, pruned_loss=0.04154, over 1420237.21 frames.], batch size: 19, lr: 4.88e-04
+2022-04-29 08:45:35,099 INFO [train.py:763] (2/8) Epoch 15, batch 1150, loss[loss=0.1834, simple_loss=0.2783, pruned_loss=0.04422, over 4807.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2744, pruned_loss=0.04101, over 1420717.81 frames.], batch size: 52, lr: 4.88e-04
+2022-04-29 08:46:40,371 INFO [train.py:763] (2/8) Epoch 15, batch 1200, loss[loss=0.1712, simple_loss=0.2744, pruned_loss=0.03393, over 7109.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2753, pruned_loss=0.04161, over 1419308.50 frames.], batch size: 21, lr: 4.88e-04
+2022-04-29 08:47:45,858 INFO [train.py:763] (2/8) Epoch 15, batch 1250, loss[loss=0.167, simple_loss=0.2493, pruned_loss=0.04235, over 6736.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2747, pruned_loss=0.04154, over 1418983.15 frames.], batch size: 15, lr: 4.88e-04
+2022-04-29 08:48:51,147 INFO [train.py:763] (2/8) Epoch 15, batch 1300, loss[loss=0.2109, simple_loss=0.3001, pruned_loss=0.06086, over 7196.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2757, pruned_loss=0.04181, over 1425620.76 frames.], batch size: 22, lr: 4.88e-04
+2022-04-29 08:49:56,769 INFO [train.py:763] (2/8) Epoch 15, batch 1350, loss[loss=0.1716, simple_loss=0.2572, pruned_loss=0.04303, over 7159.00 frames.], tot_loss[loss=0.1804, simple_loss=0.276, pruned_loss=0.04236, over 1418966.32 frames.], batch size: 19, lr: 4.87e-04
+2022-04-29 08:51:13,197 INFO [train.py:763] (2/8) Epoch 15, batch 1400, loss[loss=0.1736, simple_loss=0.2819, pruned_loss=0.03266, over 7335.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2769, pruned_loss=0.04237, over 1416909.26 frames.], batch size: 22, lr: 4.87e-04
+2022-04-29 08:52:20,207 INFO [train.py:763] (2/8) Epoch 15, batch 1450, loss[loss=0.2082, simple_loss=0.3055, pruned_loss=0.0554, over 7398.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2765, pruned_loss=0.042, over 1422869.84 frames.], batch size: 21, lr: 4.87e-04
+2022-04-29 08:53:25,683 INFO [train.py:763] (2/8) Epoch 15, batch 1500, loss[loss=0.195, simple_loss=0.2892, pruned_loss=0.05036, over 7192.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2765, pruned_loss=0.04188, over 1422869.74 frames.], batch size: 23, lr: 4.87e-04
+2022-04-29 08:54:40,088 INFO [train.py:763] (2/8) Epoch 15, batch 1550, loss[loss=0.1453, simple_loss=0.2394, pruned_loss=0.02565, over 6807.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2762, pruned_loss=0.04206, over 1421282.51 frames.], batch size: 15, lr: 4.87e-04
+2022-04-29 08:56:03,994 INFO [train.py:763] (2/8) Epoch 15, batch 1600, loss[loss=0.1476, simple_loss=0.2388, pruned_loss=0.02819, over 6788.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2764, pruned_loss=0.0421, over 1423631.22 frames.], batch size: 15, lr: 4.87e-04
+2022-04-29 08:57:19,958 INFO [train.py:763] (2/8) Epoch 15, batch 1650, loss[loss=0.2022, simple_loss=0.309, pruned_loss=0.04768, over 7140.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2761, pruned_loss=0.04212, over 1424571.42 frames.], batch size: 20, lr: 4.86e-04
+2022-04-29 08:58:25,679 INFO [train.py:763] (2/8) Epoch 15, batch 1700, loss[loss=0.183, simple_loss=0.2791, pruned_loss=0.04348, over 7407.00 frames.], tot_loss[loss=0.179, simple_loss=0.2753, pruned_loss=0.04134, over 1424955.56 frames.], batch size: 18, lr: 4.86e-04
+2022-04-29 08:59:40,114 INFO [train.py:763] (2/8) Epoch 15, batch 1750, loss[loss=0.2032, simple_loss=0.3, pruned_loss=0.05325, over 7380.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2759, pruned_loss=0.0418, over 1424431.72 frames.], batch size: 23, lr: 4.86e-04
+2022-04-29 09:00:47,093 INFO [train.py:763] (2/8) Epoch 15, batch 1800, loss[loss=0.162, simple_loss=0.2678, pruned_loss=0.02806, over 7360.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2761, pruned_loss=0.04209, over 1422802.82 frames.], batch size: 19, lr: 4.86e-04
+2022-04-29 09:02:11,301 INFO [train.py:763] (2/8) Epoch 15, batch 1850, loss[loss=0.1865, simple_loss=0.2991, pruned_loss=0.0369, over 7147.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2762, pruned_loss=0.04215, over 1425348.96 frames.], batch size: 20, lr: 4.86e-04
+2022-04-29 09:03:16,746 INFO [train.py:763] (2/8) Epoch 15, batch 1900, loss[loss=0.1915, simple_loss=0.298, pruned_loss=0.04249, over 7319.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2752, pruned_loss=0.04168, over 1429028.28 frames.], batch size: 25, lr: 4.86e-04
+2022-04-29 09:04:23,830 INFO [train.py:763] (2/8) Epoch 15, batch 1950, loss[loss=0.1786, simple_loss=0.2775, pruned_loss=0.03983, over 7195.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2766, pruned_loss=0.04232, over 1429860.08 frames.], batch size: 23, lr: 4.85e-04
+2022-04-29 09:05:29,695 INFO [train.py:763] (2/8) Epoch 15, batch 2000, loss[loss=0.2218, simple_loss=0.3148, pruned_loss=0.06442, over 5295.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2775, pruned_loss=0.04258, over 1424162.86 frames.], batch size: 52, lr: 4.85e-04
+2022-04-29 09:06:36,277 INFO [train.py:763] (2/8) Epoch 15, batch 2050, loss[loss=0.182, simple_loss=0.2843, pruned_loss=0.03989, over 6078.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2778, pruned_loss=0.0428, over 1422607.11 frames.], batch size: 37, lr: 4.85e-04
+2022-04-29 09:07:41,963 INFO [train.py:763] (2/8) Epoch 15, batch 2100, loss[loss=0.1761, simple_loss=0.2811, pruned_loss=0.03556, over 7123.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2782, pruned_loss=0.04277, over 1423277.71 frames.], batch size: 21, lr: 4.85e-04
+2022-04-29 09:08:48,742 INFO [train.py:763] (2/8) Epoch 15, batch 2150, loss[loss=0.1684, simple_loss=0.2609, pruned_loss=0.038, over 7258.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2785, pruned_loss=0.0424, over 1418127.13 frames.], batch size: 19, lr: 4.85e-04
+2022-04-29 09:09:53,837 INFO [train.py:763] (2/8) Epoch 15, batch 2200, loss[loss=0.2035, simple_loss=0.2984, pruned_loss=0.05425, over 7193.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2774, pruned_loss=0.04214, over 1415399.21 frames.], batch size: 22, lr: 4.84e-04
+2022-04-29 09:10:59,454 INFO [train.py:763] (2/8) Epoch 15, batch 2250, loss[loss=0.1606, simple_loss=0.2631, pruned_loss=0.0291, over 7422.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2759, pruned_loss=0.04137, over 1417102.31 frames.], batch size: 21, lr: 4.84e-04
+2022-04-29 09:12:05,739 INFO [train.py:763] (2/8) Epoch 15, batch 2300, loss[loss=0.1803, simple_loss=0.2838, pruned_loss=0.03836, over 7198.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2764, pruned_loss=0.04144, over 1419107.15 frames.], batch size: 23, lr: 4.84e-04
+2022-04-29 09:13:13,273 INFO [train.py:763] (2/8) Epoch 15, batch 2350, loss[loss=0.1905, simple_loss=0.2901, pruned_loss=0.04545, over 7276.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2758, pruned_loss=0.04126, over 1421647.54 frames.], batch size: 25, lr: 4.84e-04
+2022-04-29 09:14:19,338 INFO [train.py:763] (2/8) Epoch 15, batch 2400, loss[loss=0.2046, simple_loss=0.3078, pruned_loss=0.0507, over 7293.00 frames.], tot_loss[loss=0.1788, simple_loss=0.275, pruned_loss=0.04129, over 1425195.73 frames.], batch size: 25, lr: 4.84e-04
+2022-04-29 09:15:24,432 INFO [train.py:763] (2/8) Epoch 15, batch 2450, loss[loss=0.1973, simple_loss=0.2882, pruned_loss=0.05318, over 6806.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2759, pruned_loss=0.04155, over 1424134.59 frames.], batch size: 31, lr: 4.84e-04
+2022-04-29 09:16:31,163 INFO [train.py:763] (2/8) Epoch 15, batch 2500, loss[loss=0.1844, simple_loss=0.2846, pruned_loss=0.04212, over 7215.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2746, pruned_loss=0.04089, over 1428000.14 frames.], batch size: 21, lr: 4.83e-04
+2022-04-29 09:17:37,362 INFO [train.py:763] (2/8) Epoch 15, batch 2550, loss[loss=0.1853, simple_loss=0.2813, pruned_loss=0.04464, over 7148.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2747, pruned_loss=0.0413, over 1424591.27 frames.], batch size: 20, lr: 4.83e-04
+2022-04-29 09:18:44,499 INFO [train.py:763] (2/8) Epoch 15, batch 2600, loss[loss=0.1516, simple_loss=0.2561, pruned_loss=0.02354, over 7358.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2744, pruned_loss=0.04132, over 1423345.20 frames.], batch size: 19, lr: 4.83e-04
+2022-04-29 09:19:51,207 INFO [train.py:763] (2/8) Epoch 15, batch 2650, loss[loss=0.1793, simple_loss=0.283, pruned_loss=0.03784, over 7386.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2744, pruned_loss=0.04122, over 1424062.89 frames.], batch size: 23, lr: 4.83e-04
+2022-04-29 09:20:56,491 INFO [train.py:763] (2/8) Epoch 15, batch 2700, loss[loss=0.1894, simple_loss=0.2912, pruned_loss=0.04385, over 7196.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2754, pruned_loss=0.04156, over 1421459.84 frames.], batch size: 26, lr: 4.83e-04
+2022-04-29 09:22:02,815 INFO [train.py:763] (2/8) Epoch 15, batch 2750, loss[loss=0.1638, simple_loss=0.2485, pruned_loss=0.03961, over 7277.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2757, pruned_loss=0.04161, over 1424980.07 frames.], batch size: 18, lr: 4.83e-04
+2022-04-29 09:23:10,084 INFO [train.py:763] (2/8) Epoch 15, batch 2800, loss[loss=0.1966, simple_loss=0.2909, pruned_loss=0.05122, over 7214.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2762, pruned_loss=0.04152, over 1427227.09 frames.], batch size: 21, lr: 4.82e-04
+2022-04-29 09:24:17,263 INFO [train.py:763] (2/8) Epoch 15, batch 2850, loss[loss=0.1693, simple_loss=0.2601, pruned_loss=0.03929, over 7172.00 frames.], tot_loss[loss=0.18, simple_loss=0.2765, pruned_loss=0.04176, over 1425310.54 frames.], batch size: 18, lr: 4.82e-04
+2022-04-29 09:25:24,198 INFO [train.py:763] (2/8) Epoch 15, batch 2900, loss[loss=0.1587, simple_loss=0.2539, pruned_loss=0.03176, over 7174.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2766, pruned_loss=0.04188, over 1428129.22 frames.], batch size: 18, lr: 4.82e-04
+2022-04-29 09:26:29,781 INFO [train.py:763] (2/8) Epoch 15, batch 2950, loss[loss=0.1815, simple_loss=0.2861, pruned_loss=0.03847, over 7347.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2763, pruned_loss=0.04141, over 1424576.40 frames.], batch size: 22, lr: 4.82e-04
+2022-04-29 09:27:35,042 INFO [train.py:763] (2/8) Epoch 15, batch 3000, loss[loss=0.1442, simple_loss=0.2523, pruned_loss=0.01801, over 7419.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2758, pruned_loss=0.04127, over 1428695.81 frames.], batch size: 21, lr: 4.82e-04
+2022-04-29 09:27:35,043 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 09:27:50,494 INFO [train.py:792] (2/8) Epoch 15, validation: loss=0.1668, simple_loss=0.2684, pruned_loss=0.03254, over 698248.00 frames.
+2022-04-29 09:28:57,619 INFO [train.py:763] (2/8) Epoch 15, batch 3050, loss[loss=0.1649, simple_loss=0.2479, pruned_loss=0.04092, over 7415.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2754, pruned_loss=0.04147, over 1427110.84 frames.], batch size: 18, lr: 4.82e-04
+2022-04-29 09:30:04,538 INFO [train.py:763] (2/8) Epoch 15, batch 3100, loss[loss=0.2135, simple_loss=0.308, pruned_loss=0.05953, over 7205.00 frames.], tot_loss[loss=0.179, simple_loss=0.2754, pruned_loss=0.04126, over 1427288.03 frames.], batch size: 23, lr: 4.81e-04
+2022-04-29 09:31:11,564 INFO [train.py:763] (2/8) Epoch 15, batch 3150, loss[loss=0.1467, simple_loss=0.2364, pruned_loss=0.02848, over 7153.00 frames.], tot_loss[loss=0.179, simple_loss=0.2755, pruned_loss=0.04125, over 1424376.79 frames.], batch size: 18, lr: 4.81e-04
+2022-04-29 09:32:29,188 INFO [train.py:763] (2/8) Epoch 15, batch 3200, loss[loss=0.1684, simple_loss=0.2806, pruned_loss=0.02813, over 7276.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2768, pruned_loss=0.04168, over 1423734.38 frames.], batch size: 24, lr: 4.81e-04
+2022-04-29 09:33:36,691 INFO [train.py:763] (2/8) Epoch 15, batch 3250, loss[loss=0.1962, simple_loss=0.3006, pruned_loss=0.04588, over 7321.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2752, pruned_loss=0.04093, over 1424644.05 frames.], batch size: 21, lr: 4.81e-04
+2022-04-29 09:34:43,457 INFO [train.py:763] (2/8) Epoch 15, batch 3300, loss[loss=0.2002, simple_loss=0.2946, pruned_loss=0.05289, over 7280.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2765, pruned_loss=0.04107, over 1428831.99 frames.], batch size: 25, lr: 4.81e-04
+2022-04-29 09:35:50,323 INFO [train.py:763] (2/8) Epoch 15, batch 3350, loss[loss=0.1722, simple_loss=0.2709, pruned_loss=0.03676, over 7234.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2768, pruned_loss=0.04144, over 1430949.48 frames.], batch size: 20, lr: 4.81e-04
+2022-04-29 09:36:57,528 INFO [train.py:763] (2/8) Epoch 15, batch 3400, loss[loss=0.1752, simple_loss=0.2785, pruned_loss=0.03592, over 7066.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2774, pruned_loss=0.04211, over 1428205.80 frames.], batch size: 28, lr: 4.80e-04
+2022-04-29 09:38:05,022 INFO [train.py:763] (2/8) Epoch 15, batch 3450, loss[loss=0.1655, simple_loss=0.2625, pruned_loss=0.03428, over 7369.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2764, pruned_loss=0.04173, over 1429815.65 frames.], batch size: 19, lr: 4.80e-04
+2022-04-29 09:39:11,456 INFO [train.py:763] (2/8) Epoch 15, batch 3500, loss[loss=0.183, simple_loss=0.2899, pruned_loss=0.03802, over 7320.00 frames.], tot_loss[loss=0.1799, simple_loss=0.276, pruned_loss=0.04193, over 1428183.36 frames.], batch size: 21, lr: 4.80e-04
+2022-04-29 09:40:16,433 INFO [train.py:763] (2/8) Epoch 15, batch 3550, loss[loss=0.225, simple_loss=0.3126, pruned_loss=0.06874, over 7217.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2766, pruned_loss=0.04231, over 1424523.45 frames.], batch size: 26, lr: 4.80e-04
+2022-04-29 09:41:21,618 INFO [train.py:763] (2/8) Epoch 15, batch 3600, loss[loss=0.209, simple_loss=0.3086, pruned_loss=0.05469, over 7315.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2771, pruned_loss=0.04202, over 1426147.57 frames.], batch size: 21, lr: 4.80e-04
+2022-04-29 09:42:26,931 INFO [train.py:763] (2/8) Epoch 15, batch 3650, loss[loss=0.1744, simple_loss=0.2605, pruned_loss=0.04411, over 7289.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2766, pruned_loss=0.04173, over 1426406.98 frames.], batch size: 18, lr: 4.80e-04
+2022-04-29 09:43:33,154 INFO [train.py:763] (2/8) Epoch 15, batch 3700, loss[loss=0.1503, simple_loss=0.238, pruned_loss=0.03124, over 6791.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2761, pruned_loss=0.04151, over 1423154.23 frames.], batch size: 15, lr: 4.79e-04
+2022-04-29 09:44:39,836 INFO [train.py:763] (2/8) Epoch 15, batch 3750, loss[loss=0.1807, simple_loss=0.2771, pruned_loss=0.0422, over 7280.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2759, pruned_loss=0.0414, over 1420469.36 frames.], batch size: 25, lr: 4.79e-04
+2022-04-29 09:45:46,799 INFO [train.py:763] (2/8) Epoch 15, batch 3800, loss[loss=0.1531, simple_loss=0.2406, pruned_loss=0.03278, over 7151.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2769, pruned_loss=0.04167, over 1424550.54 frames.], batch size: 17, lr: 4.79e-04
+2022-04-29 09:46:53,781 INFO [train.py:763] (2/8) Epoch 15, batch 3850, loss[loss=0.1695, simple_loss=0.2532, pruned_loss=0.04285, over 7262.00 frames.], tot_loss[loss=0.18, simple_loss=0.2768, pruned_loss=0.04158, over 1420739.67 frames.], batch size: 18, lr: 4.79e-04
+2022-04-29 09:48:00,483 INFO [train.py:763] (2/8) Epoch 15, batch 3900, loss[loss=0.1724, simple_loss=0.2827, pruned_loss=0.031, over 7226.00 frames.], tot_loss[loss=0.1801, simple_loss=0.277, pruned_loss=0.0416, over 1422942.54 frames.], batch size: 21, lr: 4.79e-04
+2022-04-29 09:49:06,577 INFO [train.py:763] (2/8) Epoch 15, batch 3950, loss[loss=0.179, simple_loss=0.286, pruned_loss=0.03602, over 7239.00 frames.], tot_loss[loss=0.1802, simple_loss=0.277, pruned_loss=0.04167, over 1421812.19 frames.], batch size: 20, lr: 4.79e-04
+2022-04-29 09:50:13,627 INFO [train.py:763] (2/8) Epoch 15, batch 4000, loss[loss=0.2011, simple_loss=0.2965, pruned_loss=0.05288, over 7318.00 frames.], tot_loss[loss=0.18, simple_loss=0.2767, pruned_loss=0.04169, over 1419310.48 frames.], batch size: 21, lr: 4.79e-04
+2022-04-29 09:51:19,313 INFO [train.py:763] (2/8) Epoch 15, batch 4050, loss[loss=0.1626, simple_loss=0.2501, pruned_loss=0.03761, over 7171.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2765, pruned_loss=0.04168, over 1417409.17 frames.], batch size: 18, lr: 4.78e-04
+2022-04-29 09:52:24,920 INFO [train.py:763] (2/8) Epoch 15, batch 4100, loss[loss=0.158, simple_loss=0.2537, pruned_loss=0.03119, over 7164.00 frames.], tot_loss[loss=0.1795, simple_loss=0.276, pruned_loss=0.0415, over 1423747.25 frames.], batch size: 18, lr: 4.78e-04
+2022-04-29 09:53:30,115 INFO [train.py:763] (2/8) Epoch 15, batch 4150, loss[loss=0.1948, simple_loss=0.2931, pruned_loss=0.04827, over 7079.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2758, pruned_loss=0.04138, over 1418609.94 frames.], batch size: 28, lr: 4.78e-04
+2022-04-29 09:54:36,326 INFO [train.py:763] (2/8) Epoch 15, batch 4200, loss[loss=0.1517, simple_loss=0.2504, pruned_loss=0.02649, over 7013.00 frames.], tot_loss[loss=0.179, simple_loss=0.2756, pruned_loss=0.04114, over 1418265.77 frames.], batch size: 16, lr: 4.78e-04
+2022-04-29 09:55:43,464 INFO [train.py:763] (2/8) Epoch 15, batch 4250, loss[loss=0.1621, simple_loss=0.2573, pruned_loss=0.03343, over 7166.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2747, pruned_loss=0.04101, over 1417342.21 frames.], batch size: 18, lr: 4.78e-04
+2022-04-29 09:56:48,657 INFO [train.py:763] (2/8) Epoch 15, batch 4300, loss[loss=0.1753, simple_loss=0.2734, pruned_loss=0.03863, over 6850.00 frames.], tot_loss[loss=0.178, simple_loss=0.2744, pruned_loss=0.04082, over 1412427.45 frames.], batch size: 31, lr: 4.78e-04
+2022-04-29 09:57:53,918 INFO [train.py:763] (2/8) Epoch 15, batch 4350, loss[loss=0.1518, simple_loss=0.2536, pruned_loss=0.02504, over 7167.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2738, pruned_loss=0.03996, over 1415530.56 frames.], batch size: 18, lr: 4.77e-04
+2022-04-29 09:59:00,569 INFO [train.py:763] (2/8) Epoch 15, batch 4400, loss[loss=0.1825, simple_loss=0.2878, pruned_loss=0.03861, over 7119.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2745, pruned_loss=0.04003, over 1415532.30 frames.], batch size: 21, lr: 4.77e-04
+2022-04-29 10:00:06,757 INFO [train.py:763] (2/8) Epoch 15, batch 4450, loss[loss=0.2366, simple_loss=0.3351, pruned_loss=0.06904, over 7194.00 frames.], tot_loss[loss=0.178, simple_loss=0.2749, pruned_loss=0.04051, over 1409891.40 frames.], batch size: 22, lr: 4.77e-04
+2022-04-29 10:01:11,550 INFO [train.py:763] (2/8) Epoch 15, batch 4500, loss[loss=0.1472, simple_loss=0.2409, pruned_loss=0.02674, over 7148.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2745, pruned_loss=0.04039, over 1400341.46 frames.], batch size: 17, lr: 4.77e-04
+2022-04-29 10:02:15,681 INFO [train.py:763] (2/8) Epoch 15, batch 4550, loss[loss=0.2077, simple_loss=0.292, pruned_loss=0.06173, over 4680.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2777, pruned_loss=0.0427, over 1350091.25 frames.], batch size: 52, lr: 4.77e-04
+2022-04-29 10:03:53,496 INFO [train.py:763] (2/8) Epoch 16, batch 0, loss[loss=0.1526, simple_loss=0.2571, pruned_loss=0.02403, over 7116.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2571, pruned_loss=0.02403, over 7116.00 frames.], batch size: 21, lr: 4.63e-04
+2022-04-29 10:04:59,092 INFO [train.py:763] (2/8) Epoch 16, batch 50, loss[loss=0.1776, simple_loss=0.2752, pruned_loss=0.03998, over 7313.00 frames.], tot_loss[loss=0.1815, simple_loss=0.277, pruned_loss=0.04303, over 317438.75 frames.], batch size: 21, lr: 4.63e-04
+2022-04-29 10:06:04,339 INFO [train.py:763] (2/8) Epoch 16, batch 100, loss[loss=0.1733, simple_loss=0.2778, pruned_loss=0.03442, over 7143.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2763, pruned_loss=0.04262, over 559593.43 frames.], batch size: 20, lr: 4.63e-04
+2022-04-29 10:07:09,680 INFO [train.py:763] (2/8) Epoch 16, batch 150, loss[loss=0.1458, simple_loss=0.232, pruned_loss=0.02987, over 7000.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2755, pruned_loss=0.04171, over 747646.01 frames.], batch size: 16, lr: 4.63e-04
+2022-04-29 10:08:15,061 INFO [train.py:763] (2/8) Epoch 16, batch 200, loss[loss=0.1783, simple_loss=0.2729, pruned_loss=0.04187, over 7141.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2775, pruned_loss=0.04187, over 897060.46 frames.], batch size: 17, lr: 4.63e-04
+2022-04-29 10:09:20,553 INFO [train.py:763] (2/8) Epoch 16, batch 250, loss[loss=0.1623, simple_loss=0.2566, pruned_loss=0.03401, over 7255.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2769, pruned_loss=0.04147, over 1016374.34 frames.], batch size: 19, lr: 4.63e-04
+2022-04-29 10:10:25,846 INFO [train.py:763] (2/8) Epoch 16, batch 300, loss[loss=0.1857, simple_loss=0.2595, pruned_loss=0.05595, over 7072.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2768, pruned_loss=0.04168, over 1102024.85 frames.], batch size: 18, lr: 4.62e-04
+2022-04-29 10:11:32,019 INFO [train.py:763] (2/8) Epoch 16, batch 350, loss[loss=0.1733, simple_loss=0.2576, pruned_loss=0.04444, over 7244.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2757, pruned_loss=0.04195, over 1172174.12 frames.], batch size: 16, lr: 4.62e-04
+2022-04-29 10:12:37,985 INFO [train.py:763] (2/8) Epoch 16, batch 400, loss[loss=0.2247, simple_loss=0.326, pruned_loss=0.06174, over 4832.00 frames.], tot_loss[loss=0.1796, simple_loss=0.276, pruned_loss=0.04162, over 1227514.04 frames.], batch size: 53, lr: 4.62e-04
+2022-04-29 10:13:43,444 INFO [train.py:763] (2/8) Epoch 16, batch 450, loss[loss=0.1484, simple_loss=0.2355, pruned_loss=0.03063, over 7360.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2759, pruned_loss=0.04098, over 1267851.29 frames.], batch size: 19, lr: 4.62e-04
+2022-04-29 10:14:49,053 INFO [train.py:763] (2/8) Epoch 16, batch 500, loss[loss=0.1515, simple_loss=0.2357, pruned_loss=0.03369, over 7169.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2749, pruned_loss=0.04078, over 1301304.81 frames.], batch size: 18, lr: 4.62e-04
+2022-04-29 10:15:54,719 INFO [train.py:763] (2/8) Epoch 16, batch 550, loss[loss=0.1492, simple_loss=0.2375, pruned_loss=0.03043, over 7130.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2746, pruned_loss=0.04084, over 1327300.78 frames.], batch size: 17, lr: 4.62e-04
+2022-04-29 10:17:00,202 INFO [train.py:763] (2/8) Epoch 16, batch 600, loss[loss=0.1934, simple_loss=0.3024, pruned_loss=0.04223, over 7044.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2759, pruned_loss=0.04138, over 1342252.18 frames.], batch size: 28, lr: 4.62e-04
+2022-04-29 10:18:05,529 INFO [train.py:763] (2/8) Epoch 16, batch 650, loss[loss=0.1569, simple_loss=0.2511, pruned_loss=0.03132, over 7334.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2758, pruned_loss=0.04132, over 1360608.53 frames.], batch size: 20, lr: 4.61e-04
+2022-04-29 10:19:10,728 INFO [train.py:763] (2/8) Epoch 16, batch 700, loss[loss=0.201, simple_loss=0.2923, pruned_loss=0.05483, over 7269.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2772, pruned_loss=0.0419, over 1367264.55 frames.], batch size: 19, lr: 4.61e-04
+2022-04-29 10:20:16,739 INFO [train.py:763] (2/8) Epoch 16, batch 750, loss[loss=0.2136, simple_loss=0.3015, pruned_loss=0.06291, over 7137.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2773, pruned_loss=0.04209, over 1376173.34 frames.], batch size: 20, lr: 4.61e-04
+2022-04-29 10:21:21,856 INFO [train.py:763] (2/8) Epoch 16, batch 800, loss[loss=0.1629, simple_loss=0.2576, pruned_loss=0.03412, over 7154.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2763, pruned_loss=0.0412, over 1387008.35 frames.], batch size: 19, lr: 4.61e-04
+2022-04-29 10:22:27,306 INFO [train.py:763] (2/8) Epoch 16, batch 850, loss[loss=0.1785, simple_loss=0.2754, pruned_loss=0.04085, over 6353.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2753, pruned_loss=0.04112, over 1396027.11 frames.], batch size: 38, lr: 4.61e-04
+2022-04-29 10:23:32,963 INFO [train.py:763] (2/8) Epoch 16, batch 900, loss[loss=0.1693, simple_loss=0.2671, pruned_loss=0.0357, over 7326.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2758, pruned_loss=0.04095, over 1407498.22 frames.], batch size: 20, lr: 4.61e-04
+2022-04-29 10:24:38,445 INFO [train.py:763] (2/8) Epoch 16, batch 950, loss[loss=0.16, simple_loss=0.2503, pruned_loss=0.0349, over 7148.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2747, pruned_loss=0.04034, over 1412734.74 frames.], batch size: 17, lr: 4.60e-04
+2022-04-29 10:25:44,697 INFO [train.py:763] (2/8) Epoch 16, batch 1000, loss[loss=0.1953, simple_loss=0.3026, pruned_loss=0.04401, over 7114.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2754, pruned_loss=0.04049, over 1416831.00 frames.], batch size: 21, lr: 4.60e-04
+2022-04-29 10:26:51,174 INFO [train.py:763] (2/8) Epoch 16, batch 1050, loss[loss=0.1849, simple_loss=0.2959, pruned_loss=0.03697, over 7330.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2747, pruned_loss=0.04031, over 1420732.65 frames.], batch size: 22, lr: 4.60e-04
+2022-04-29 10:27:57,452 INFO [train.py:763] (2/8) Epoch 16, batch 1100, loss[loss=0.1708, simple_loss=0.2734, pruned_loss=0.03412, over 7289.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2749, pruned_loss=0.04009, over 1421048.43 frames.], batch size: 24, lr: 4.60e-04
+2022-04-29 10:29:02,472 INFO [train.py:763] (2/8) Epoch 16, batch 1150, loss[loss=0.2015, simple_loss=0.3006, pruned_loss=0.05127, over 7308.00 frames.], tot_loss[loss=0.1784, simple_loss=0.276, pruned_loss=0.04038, over 1422597.18 frames.], batch size: 24, lr: 4.60e-04
+2022-04-29 10:30:08,049 INFO [train.py:763] (2/8) Epoch 16, batch 1200, loss[loss=0.2286, simple_loss=0.3211, pruned_loss=0.06807, over 7316.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2761, pruned_loss=0.04106, over 1419964.64 frames.], batch size: 25, lr: 4.60e-04
+2022-04-29 10:31:13,266 INFO [train.py:763] (2/8) Epoch 16, batch 1250, loss[loss=0.1743, simple_loss=0.2623, pruned_loss=0.04315, over 7269.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2759, pruned_loss=0.0412, over 1415119.45 frames.], batch size: 18, lr: 4.60e-04
+2022-04-29 10:32:19,085 INFO [train.py:763] (2/8) Epoch 16, batch 1300, loss[loss=0.1856, simple_loss=0.2884, pruned_loss=0.04135, over 7339.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2752, pruned_loss=0.0413, over 1413155.95 frames.], batch size: 22, lr: 4.59e-04
+2022-04-29 10:33:25,808 INFO [train.py:763] (2/8) Epoch 16, batch 1350, loss[loss=0.1528, simple_loss=0.2484, pruned_loss=0.0286, over 6993.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2752, pruned_loss=0.04103, over 1418291.25 frames.], batch size: 16, lr: 4.59e-04
+2022-04-29 10:34:32,887 INFO [train.py:763] (2/8) Epoch 16, batch 1400, loss[loss=0.1699, simple_loss=0.2677, pruned_loss=0.03607, over 7151.00 frames.], tot_loss[loss=0.177, simple_loss=0.2733, pruned_loss=0.04029, over 1420101.40 frames.], batch size: 20, lr: 4.59e-04
+2022-04-29 10:35:38,351 INFO [train.py:763] (2/8) Epoch 16, batch 1450, loss[loss=0.1842, simple_loss=0.2839, pruned_loss=0.04223, over 7328.00 frames.], tot_loss[loss=0.177, simple_loss=0.2735, pruned_loss=0.04023, over 1420051.90 frames.], batch size: 22, lr: 4.59e-04
+2022-04-29 10:36:43,996 INFO [train.py:763] (2/8) Epoch 16, batch 1500, loss[loss=0.1779, simple_loss=0.2732, pruned_loss=0.04132, over 7256.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2723, pruned_loss=0.03996, over 1425467.71 frames.], batch size: 19, lr: 4.59e-04
+2022-04-29 10:37:49,276 INFO [train.py:763] (2/8) Epoch 16, batch 1550, loss[loss=0.1558, simple_loss=0.2563, pruned_loss=0.02762, over 7219.00 frames.], tot_loss[loss=0.176, simple_loss=0.2724, pruned_loss=0.03979, over 1422775.39 frames.], batch size: 21, lr: 4.59e-04
+2022-04-29 10:38:55,267 INFO [train.py:763] (2/8) Epoch 16, batch 1600, loss[loss=0.1877, simple_loss=0.2918, pruned_loss=0.04179, over 7431.00 frames.], tot_loss[loss=0.1756, simple_loss=0.272, pruned_loss=0.03956, over 1427103.10 frames.], batch size: 20, lr: 4.58e-04
+2022-04-29 10:40:00,453 INFO [train.py:763] (2/8) Epoch 16, batch 1650, loss[loss=0.1855, simple_loss=0.2868, pruned_loss=0.04208, over 7414.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2732, pruned_loss=0.0397, over 1429337.47 frames.], batch size: 21, lr: 4.58e-04
+2022-04-29 10:41:05,541 INFO [train.py:763] (2/8) Epoch 16, batch 1700, loss[loss=0.2403, simple_loss=0.3243, pruned_loss=0.07815, over 5036.00 frames.], tot_loss[loss=0.1771, simple_loss=0.274, pruned_loss=0.0401, over 1423395.02 frames.], batch size: 52, lr: 4.58e-04
+2022-04-29 10:42:10,599 INFO [train.py:763] (2/8) Epoch 16, batch 1750, loss[loss=0.1851, simple_loss=0.2905, pruned_loss=0.03982, over 7373.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2746, pruned_loss=0.04017, over 1414455.36 frames.], batch size: 23, lr: 4.58e-04
+2022-04-29 10:43:15,522 INFO [train.py:763] (2/8) Epoch 16, batch 1800, loss[loss=0.1823, simple_loss=0.2854, pruned_loss=0.03956, over 7185.00 frames.], tot_loss[loss=0.1766, simple_loss=0.274, pruned_loss=0.03958, over 1415740.72 frames.], batch size: 23, lr: 4.58e-04
+2022-04-29 10:44:20,683 INFO [train.py:763] (2/8) Epoch 16, batch 1850, loss[loss=0.1895, simple_loss=0.2901, pruned_loss=0.04447, over 6486.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2741, pruned_loss=0.04005, over 1417298.61 frames.], batch size: 38, lr: 4.58e-04
+2022-04-29 10:45:26,185 INFO [train.py:763] (2/8) Epoch 16, batch 1900, loss[loss=0.1767, simple_loss=0.2769, pruned_loss=0.03827, over 7427.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2749, pruned_loss=0.04026, over 1421605.98 frames.], batch size: 20, lr: 4.58e-04
+2022-04-29 10:46:31,345 INFO [train.py:763] (2/8) Epoch 16, batch 1950, loss[loss=0.1796, simple_loss=0.2788, pruned_loss=0.04022, over 7304.00 frames.], tot_loss[loss=0.1779, simple_loss=0.275, pruned_loss=0.04041, over 1424002.49 frames.], batch size: 21, lr: 4.57e-04
+2022-04-29 10:47:36,624 INFO [train.py:763] (2/8) Epoch 16, batch 2000, loss[loss=0.1668, simple_loss=0.262, pruned_loss=0.03577, over 7265.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2753, pruned_loss=0.04056, over 1425392.59 frames.], batch size: 19, lr: 4.57e-04
+2022-04-29 10:48:44,155 INFO [train.py:763] (2/8) Epoch 16, batch 2050, loss[loss=0.1723, simple_loss=0.2613, pruned_loss=0.04164, over 7412.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2737, pruned_loss=0.04009, over 1428963.28 frames.], batch size: 18, lr: 4.57e-04
+2022-04-29 10:49:51,119 INFO [train.py:763] (2/8) Epoch 16, batch 2100, loss[loss=0.1644, simple_loss=0.2656, pruned_loss=0.03162, over 7415.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2734, pruned_loss=0.03983, over 1429292.65 frames.], batch size: 21, lr: 4.57e-04
+2022-04-29 10:50:57,992 INFO [train.py:763] (2/8) Epoch 16, batch 2150, loss[loss=0.1683, simple_loss=0.2577, pruned_loss=0.03948, over 7349.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2736, pruned_loss=0.04038, over 1425907.75 frames.], batch size: 19, lr: 4.57e-04
+2022-04-29 10:52:04,702 INFO [train.py:763] (2/8) Epoch 16, batch 2200, loss[loss=0.1902, simple_loss=0.2968, pruned_loss=0.0418, over 7349.00 frames.], tot_loss[loss=0.177, simple_loss=0.2737, pruned_loss=0.04011, over 1423137.26 frames.], batch size: 22, lr: 4.57e-04
+2022-04-29 10:53:10,673 INFO [train.py:763] (2/8) Epoch 16, batch 2250, loss[loss=0.1768, simple_loss=0.2743, pruned_loss=0.03968, over 7413.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2754, pruned_loss=0.04104, over 1425124.55 frames.], batch size: 21, lr: 4.56e-04
+2022-04-29 10:54:16,232 INFO [train.py:763] (2/8) Epoch 16, batch 2300, loss[loss=0.1714, simple_loss=0.2759, pruned_loss=0.03348, over 7322.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2747, pruned_loss=0.04033, over 1423564.73 frames.], batch size: 24, lr: 4.56e-04
+2022-04-29 10:55:22,547 INFO [train.py:763] (2/8) Epoch 16, batch 2350, loss[loss=0.1683, simple_loss=0.2677, pruned_loss=0.03447, over 7378.00 frames.], tot_loss[loss=0.1773, simple_loss=0.274, pruned_loss=0.04034, over 1426752.22 frames.], batch size: 23, lr: 4.56e-04
+2022-04-29 10:56:28,585 INFO [train.py:763] (2/8) Epoch 16, batch 2400, loss[loss=0.1539, simple_loss=0.2383, pruned_loss=0.03476, over 6995.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2733, pruned_loss=0.03977, over 1424448.31 frames.], batch size: 16, lr: 4.56e-04
+2022-04-29 10:57:34,905 INFO [train.py:763] (2/8) Epoch 16, batch 2450, loss[loss=0.1884, simple_loss=0.2955, pruned_loss=0.0406, over 7338.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2725, pruned_loss=0.0397, over 1423965.84 frames.], batch size: 22, lr: 4.56e-04
+2022-04-29 10:58:41,491 INFO [train.py:763] (2/8) Epoch 16, batch 2500, loss[loss=0.1935, simple_loss=0.304, pruned_loss=0.04151, over 7224.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2722, pruned_loss=0.03968, over 1423345.37 frames.], batch size: 21, lr: 4.56e-04
+2022-04-29 10:59:48,420 INFO [train.py:763] (2/8) Epoch 16, batch 2550, loss[loss=0.1762, simple_loss=0.2727, pruned_loss=0.03978, over 7217.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2727, pruned_loss=0.0399, over 1417605.18 frames.], batch size: 21, lr: 4.56e-04
+2022-04-29 11:00:54,057 INFO [train.py:763] (2/8) Epoch 16, batch 2600, loss[loss=0.1806, simple_loss=0.2738, pruned_loss=0.04369, over 6948.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2739, pruned_loss=0.0403, over 1420595.95 frames.], batch size: 28, lr: 4.55e-04
+2022-04-29 11:01:59,322 INFO [train.py:763] (2/8) Epoch 16, batch 2650, loss[loss=0.1525, simple_loss=0.2527, pruned_loss=0.02614, over 7355.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2737, pruned_loss=0.03999, over 1419125.73 frames.], batch size: 19, lr: 4.55e-04
+2022-04-29 11:03:04,679 INFO [train.py:763] (2/8) Epoch 16, batch 2700, loss[loss=0.1971, simple_loss=0.2988, pruned_loss=0.04773, over 7332.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2724, pruned_loss=0.03962, over 1422287.98 frames.], batch size: 22, lr: 4.55e-04
+2022-04-29 11:04:10,088 INFO [train.py:763] (2/8) Epoch 16, batch 2750, loss[loss=0.1866, simple_loss=0.2955, pruned_loss=0.03883, over 7164.00 frames.], tot_loss[loss=0.1765, simple_loss=0.273, pruned_loss=0.03995, over 1422533.26 frames.], batch size: 19, lr: 4.55e-04
+2022-04-29 11:05:15,586 INFO [train.py:763] (2/8) Epoch 16, batch 2800, loss[loss=0.2262, simple_loss=0.3161, pruned_loss=0.06818, over 4864.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2726, pruned_loss=0.03988, over 1421975.50 frames.], batch size: 52, lr: 4.55e-04
+2022-04-29 11:06:20,604 INFO [train.py:763] (2/8) Epoch 16, batch 2850, loss[loss=0.1577, simple_loss=0.2722, pruned_loss=0.02156, over 7306.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2735, pruned_loss=0.04041, over 1421998.75 frames.], batch size: 21, lr: 4.55e-04
+2022-04-29 11:07:35,850 INFO [train.py:763] (2/8) Epoch 16, batch 2900, loss[loss=0.1679, simple_loss=0.2759, pruned_loss=0.02991, over 7235.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2745, pruned_loss=0.04099, over 1417835.16 frames.], batch size: 20, lr: 4.55e-04
+2022-04-29 11:08:42,368 INFO [train.py:763] (2/8) Epoch 16, batch 2950, loss[loss=0.1577, simple_loss=0.251, pruned_loss=0.03218, over 7280.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2752, pruned_loss=0.04074, over 1418087.63 frames.], batch size: 18, lr: 4.54e-04
+2022-04-29 11:09:49,124 INFO [train.py:763] (2/8) Epoch 16, batch 3000, loss[loss=0.1659, simple_loss=0.2677, pruned_loss=0.03204, over 7142.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2747, pruned_loss=0.04016, over 1423669.04 frames.], batch size: 20, lr: 4.54e-04
+2022-04-29 11:09:49,125 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 11:10:05,042 INFO [train.py:792] (2/8) Epoch 16, validation: loss=0.1677, simple_loss=0.2693, pruned_loss=0.03309, over 698248.00 frames.
+2022-04-29 11:11:10,307 INFO [train.py:763] (2/8) Epoch 16, batch 3050, loss[loss=0.1746, simple_loss=0.2658, pruned_loss=0.04165, over 6492.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2756, pruned_loss=0.04085, over 1423443.36 frames.], batch size: 38, lr: 4.54e-04
+2022-04-29 11:12:42,598 INFO [train.py:763] (2/8) Epoch 16, batch 3100, loss[loss=0.184, simple_loss=0.2836, pruned_loss=0.04222, over 7299.00 frames.], tot_loss[loss=0.179, simple_loss=0.2757, pruned_loss=0.04111, over 1420437.57 frames.], batch size: 25, lr: 4.54e-04
+2022-04-29 11:13:48,018 INFO [train.py:763] (2/8) Epoch 16, batch 3150, loss[loss=0.1687, simple_loss=0.2705, pruned_loss=0.03344, over 7329.00 frames.], tot_loss[loss=0.178, simple_loss=0.2746, pruned_loss=0.04067, over 1419333.08 frames.], batch size: 20, lr: 4.54e-04
+2022-04-29 11:15:03,457 INFO [train.py:763] (2/8) Epoch 16, batch 3200, loss[loss=0.1638, simple_loss=0.262, pruned_loss=0.0328, over 7357.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2758, pruned_loss=0.0414, over 1418805.60 frames.], batch size: 19, lr: 4.54e-04
+2022-04-29 11:16:27,095 INFO [train.py:763] (2/8) Epoch 16, batch 3250, loss[loss=0.1592, simple_loss=0.2509, pruned_loss=0.03373, over 7062.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2749, pruned_loss=0.04093, over 1424343.53 frames.], batch size: 18, lr: 4.54e-04
+2022-04-29 11:17:32,419 INFO [train.py:763] (2/8) Epoch 16, batch 3300, loss[loss=0.1937, simple_loss=0.2923, pruned_loss=0.0476, over 7159.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2758, pruned_loss=0.04129, over 1424738.86 frames.], batch size: 19, lr: 4.53e-04
+2022-04-29 11:18:47,352 INFO [train.py:763] (2/8) Epoch 16, batch 3350, loss[loss=0.1882, simple_loss=0.2896, pruned_loss=0.04346, over 7341.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2762, pruned_loss=0.04124, over 1426113.29 frames.], batch size: 22, lr: 4.53e-04
+2022-04-29 11:19:53,999 INFO [train.py:763] (2/8) Epoch 16, batch 3400, loss[loss=0.1714, simple_loss=0.2806, pruned_loss=0.03107, over 7133.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2758, pruned_loss=0.04097, over 1423142.72 frames.], batch size: 20, lr: 4.53e-04
+2022-04-29 11:21:00,494 INFO [train.py:763] (2/8) Epoch 16, batch 3450, loss[loss=0.1752, simple_loss=0.2812, pruned_loss=0.03455, over 7336.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2751, pruned_loss=0.04104, over 1424140.05 frames.], batch size: 20, lr: 4.53e-04
+2022-04-29 11:22:05,834 INFO [train.py:763] (2/8) Epoch 16, batch 3500, loss[loss=0.1724, simple_loss=0.2793, pruned_loss=0.03281, over 7220.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2747, pruned_loss=0.04086, over 1423739.96 frames.], batch size: 22, lr: 4.53e-04
+2022-04-29 11:23:10,997 INFO [train.py:763] (2/8) Epoch 16, batch 3550, loss[loss=0.1644, simple_loss=0.2654, pruned_loss=0.03174, over 7109.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2756, pruned_loss=0.04114, over 1426263.79 frames.], batch size: 21, lr: 4.53e-04
+2022-04-29 11:24:16,263 INFO [train.py:763] (2/8) Epoch 16, batch 3600, loss[loss=0.1533, simple_loss=0.2474, pruned_loss=0.0296, over 7282.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2759, pruned_loss=0.04087, over 1427288.85 frames.], batch size: 18, lr: 4.52e-04
+2022-04-29 11:25:21,851 INFO [train.py:763] (2/8) Epoch 16, batch 3650, loss[loss=0.1831, simple_loss=0.2768, pruned_loss=0.04465, over 7319.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2745, pruned_loss=0.04019, over 1430772.00 frames.], batch size: 21, lr: 4.52e-04
+2022-04-29 11:26:27,133 INFO [train.py:763] (2/8) Epoch 16, batch 3700, loss[loss=0.1791, simple_loss=0.2846, pruned_loss=0.03682, over 7141.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2739, pruned_loss=0.0399, over 1430429.40 frames.], batch size: 20, lr: 4.52e-04
+2022-04-29 11:27:34,284 INFO [train.py:763] (2/8) Epoch 16, batch 3750, loss[loss=0.1865, simple_loss=0.2948, pruned_loss=0.03908, over 6290.00 frames.], tot_loss[loss=0.177, simple_loss=0.2742, pruned_loss=0.03991, over 1427950.01 frames.], batch size: 37, lr: 4.52e-04
+2022-04-29 11:28:40,551 INFO [train.py:763] (2/8) Epoch 16, batch 3800, loss[loss=0.1708, simple_loss=0.2762, pruned_loss=0.0327, over 6404.00 frames.], tot_loss[loss=0.1775, simple_loss=0.275, pruned_loss=0.03997, over 1426248.66 frames.], batch size: 38, lr: 4.52e-04
+2022-04-29 11:29:46,869 INFO [train.py:763] (2/8) Epoch 16, batch 3850, loss[loss=0.1408, simple_loss=0.2363, pruned_loss=0.02264, over 6989.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2745, pruned_loss=0.03955, over 1426033.22 frames.], batch size: 16, lr: 4.52e-04
+2022-04-29 11:30:53,554 INFO [train.py:763] (2/8) Epoch 16, batch 3900, loss[loss=0.1739, simple_loss=0.2795, pruned_loss=0.03422, over 7204.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2727, pruned_loss=0.03904, over 1428141.53 frames.], batch size: 22, lr: 4.52e-04
+2022-04-29 11:32:00,328 INFO [train.py:763] (2/8) Epoch 16, batch 3950, loss[loss=0.1632, simple_loss=0.2718, pruned_loss=0.02732, over 7197.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2735, pruned_loss=0.03917, over 1427428.60 frames.], batch size: 23, lr: 4.51e-04
+2022-04-29 11:33:05,767 INFO [train.py:763] (2/8) Epoch 16, batch 4000, loss[loss=0.1501, simple_loss=0.2509, pruned_loss=0.02463, over 7277.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2736, pruned_loss=0.03974, over 1428343.25 frames.], batch size: 18, lr: 4.51e-04
+2022-04-29 11:34:12,297 INFO [train.py:763] (2/8) Epoch 16, batch 4050, loss[loss=0.2203, simple_loss=0.3156, pruned_loss=0.06247, over 6742.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2737, pruned_loss=0.04004, over 1425344.57 frames.], batch size: 31, lr: 4.51e-04
+2022-04-29 11:35:18,249 INFO [train.py:763] (2/8) Epoch 16, batch 4100, loss[loss=0.1763, simple_loss=0.2832, pruned_loss=0.03463, over 6524.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2755, pruned_loss=0.04065, over 1424596.30 frames.], batch size: 38, lr: 4.51e-04
+2022-04-29 11:36:24,672 INFO [train.py:763] (2/8) Epoch 16, batch 4150, loss[loss=0.1847, simple_loss=0.2673, pruned_loss=0.05108, over 7136.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2734, pruned_loss=0.04018, over 1423766.77 frames.], batch size: 17, lr: 4.51e-04
+2022-04-29 11:37:30,198 INFO [train.py:763] (2/8) Epoch 16, batch 4200, loss[loss=0.1964, simple_loss=0.3003, pruned_loss=0.04622, over 7111.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2741, pruned_loss=0.04029, over 1422954.14 frames.], batch size: 26, lr: 4.51e-04
+2022-04-29 11:38:36,626 INFO [train.py:763] (2/8) Epoch 16, batch 4250, loss[loss=0.1781, simple_loss=0.2681, pruned_loss=0.04405, over 7274.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2746, pruned_loss=0.04036, over 1424548.97 frames.], batch size: 18, lr: 4.51e-04
+2022-04-29 11:39:43,731 INFO [train.py:763] (2/8) Epoch 16, batch 4300, loss[loss=0.1874, simple_loss=0.2827, pruned_loss=0.04604, over 7065.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2735, pruned_loss=0.04014, over 1422464.06 frames.], batch size: 18, lr: 4.50e-04
+2022-04-29 11:40:49,810 INFO [train.py:763] (2/8) Epoch 16, batch 4350, loss[loss=0.1503, simple_loss=0.2275, pruned_loss=0.03653, over 7163.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2736, pruned_loss=0.04004, over 1421371.19 frames.], batch size: 18, lr: 4.50e-04
+2022-04-29 11:41:55,137 INFO [train.py:763] (2/8) Epoch 16, batch 4400, loss[loss=0.199, simple_loss=0.2984, pruned_loss=0.04977, over 7212.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2734, pruned_loss=0.03985, over 1420020.56 frames.], batch size: 21, lr: 4.50e-04
+2022-04-29 11:43:00,288 INFO [train.py:763] (2/8) Epoch 16, batch 4450, loss[loss=0.1453, simple_loss=0.2383, pruned_loss=0.02618, over 7130.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2744, pruned_loss=0.04038, over 1415675.70 frames.], batch size: 17, lr: 4.50e-04
+2022-04-29 11:44:06,062 INFO [train.py:763] (2/8) Epoch 16, batch 4500, loss[loss=0.1715, simple_loss=0.2751, pruned_loss=0.03396, over 7224.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2732, pruned_loss=0.04027, over 1415029.46 frames.], batch size: 20, lr: 4.50e-04
+2022-04-29 11:45:13,645 INFO [train.py:763] (2/8) Epoch 16, batch 4550, loss[loss=0.2011, simple_loss=0.276, pruned_loss=0.06308, over 5241.00 frames.], tot_loss[loss=0.178, simple_loss=0.273, pruned_loss=0.04147, over 1379540.37 frames.], batch size: 52, lr: 4.50e-04
+2022-04-29 11:46:42,219 INFO [train.py:763] (2/8) Epoch 17, batch 0, loss[loss=0.1809, simple_loss=0.2762, pruned_loss=0.04278, over 7226.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2762, pruned_loss=0.04278, over 7226.00 frames.], batch size: 20, lr: 4.38e-04
+2022-04-29 11:47:48,724 INFO [train.py:763] (2/8) Epoch 17, batch 50, loss[loss=0.1688, simple_loss=0.2466, pruned_loss=0.04546, over 7014.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2677, pruned_loss=0.03835, over 323157.02 frames.], batch size: 16, lr: 4.38e-04
+2022-04-29 11:48:54,533 INFO [train.py:763] (2/8) Epoch 17, batch 100, loss[loss=0.1549, simple_loss=0.2486, pruned_loss=0.03061, over 7169.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2704, pruned_loss=0.03889, over 564958.53 frames.], batch size: 18, lr: 4.37e-04
+2022-04-29 11:50:00,284 INFO [train.py:763] (2/8) Epoch 17, batch 150, loss[loss=0.1857, simple_loss=0.285, pruned_loss=0.04324, over 7145.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2717, pruned_loss=0.0397, over 752529.79 frames.], batch size: 20, lr: 4.37e-04
+2022-04-29 11:51:07,233 INFO [train.py:763] (2/8) Epoch 17, batch 200, loss[loss=0.1617, simple_loss=0.2533, pruned_loss=0.03507, over 7172.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2721, pruned_loss=0.03914, over 903886.72 frames.], batch size: 18, lr: 4.37e-04
+2022-04-29 11:52:14,160 INFO [train.py:763] (2/8) Epoch 17, batch 250, loss[loss=0.1851, simple_loss=0.2869, pruned_loss=0.04165, over 6804.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2732, pruned_loss=0.03892, over 1021183.46 frames.], batch size: 31, lr: 4.37e-04
+2022-04-29 11:53:19,797 INFO [train.py:763] (2/8) Epoch 17, batch 300, loss[loss=0.1729, simple_loss=0.2649, pruned_loss=0.04042, over 7144.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2731, pruned_loss=0.03927, over 1105324.06 frames.], batch size: 28, lr: 4.37e-04
+2022-04-29 11:54:25,511 INFO [train.py:763] (2/8) Epoch 17, batch 350, loss[loss=0.1648, simple_loss=0.2714, pruned_loss=0.02913, over 7325.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2726, pruned_loss=0.03907, over 1172598.27 frames.], batch size: 22, lr: 4.37e-04
+2022-04-29 11:55:31,571 INFO [train.py:763] (2/8) Epoch 17, batch 400, loss[loss=0.1584, simple_loss=0.2419, pruned_loss=0.03741, over 7225.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2737, pruned_loss=0.03936, over 1232944.55 frames.], batch size: 16, lr: 4.37e-04
+2022-04-29 11:56:37,247 INFO [train.py:763] (2/8) Epoch 17, batch 450, loss[loss=0.198, simple_loss=0.2917, pruned_loss=0.05217, over 7216.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2747, pruned_loss=0.0397, over 1276297.22 frames.], batch size: 22, lr: 4.36e-04
+2022-04-29 11:57:42,947 INFO [train.py:763] (2/8) Epoch 17, batch 500, loss[loss=0.166, simple_loss=0.2756, pruned_loss=0.02824, over 7334.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2743, pruned_loss=0.03976, over 1312572.12 frames.], batch size: 22, lr: 4.36e-04
+2022-04-29 11:58:48,658 INFO [train.py:763] (2/8) Epoch 17, batch 550, loss[loss=0.1675, simple_loss=0.2633, pruned_loss=0.0358, over 7145.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2736, pruned_loss=0.03964, over 1339233.73 frames.], batch size: 17, lr: 4.36e-04
+2022-04-29 11:59:54,494 INFO [train.py:763] (2/8) Epoch 17, batch 600, loss[loss=0.1794, simple_loss=0.2849, pruned_loss=0.03692, over 6190.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2753, pruned_loss=0.04026, over 1356916.63 frames.], batch size: 37, lr: 4.36e-04
+2022-04-29 12:01:00,139 INFO [train.py:763] (2/8) Epoch 17, batch 650, loss[loss=0.2391, simple_loss=0.3271, pruned_loss=0.07556, over 5158.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2756, pruned_loss=0.04036, over 1369457.60 frames.], batch size: 53, lr: 4.36e-04
+2022-04-29 12:02:07,658 INFO [train.py:763] (2/8) Epoch 17, batch 700, loss[loss=0.1782, simple_loss=0.2821, pruned_loss=0.03713, over 7321.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2756, pruned_loss=0.04055, over 1380902.45 frames.], batch size: 21, lr: 4.36e-04
+2022-04-29 12:03:15,580 INFO [train.py:763] (2/8) Epoch 17, batch 750, loss[loss=0.1448, simple_loss=0.2355, pruned_loss=0.02702, over 7397.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2738, pruned_loss=0.03982, over 1391251.87 frames.], batch size: 18, lr: 4.36e-04
+2022-04-29 12:04:22,595 INFO [train.py:763] (2/8) Epoch 17, batch 800, loss[loss=0.2182, simple_loss=0.3095, pruned_loss=0.06346, over 7321.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2734, pruned_loss=0.0397, over 1403046.62 frames.], batch size: 21, lr: 4.36e-04
+2022-04-29 12:05:28,618 INFO [train.py:763] (2/8) Epoch 17, batch 850, loss[loss=0.173, simple_loss=0.2816, pruned_loss=0.03218, over 7414.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2726, pruned_loss=0.0394, over 1406545.02 frames.], batch size: 21, lr: 4.35e-04
+2022-04-29 12:06:34,118 INFO [train.py:763] (2/8) Epoch 17, batch 900, loss[loss=0.2053, simple_loss=0.3032, pruned_loss=0.05375, over 7202.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2742, pruned_loss=0.04015, over 1406757.20 frames.], batch size: 22, lr: 4.35e-04
+2022-04-29 12:07:40,031 INFO [train.py:763] (2/8) Epoch 17, batch 950, loss[loss=0.1537, simple_loss=0.2446, pruned_loss=0.03135, over 7253.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2742, pruned_loss=0.04013, over 1410181.68 frames.], batch size: 19, lr: 4.35e-04
+2022-04-29 12:08:46,271 INFO [train.py:763] (2/8) Epoch 17, batch 1000, loss[loss=0.1819, simple_loss=0.2826, pruned_loss=0.04065, over 7294.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2738, pruned_loss=0.03941, over 1415818.46 frames.], batch size: 24, lr: 4.35e-04
+2022-04-29 12:09:52,066 INFO [train.py:763] (2/8) Epoch 17, batch 1050, loss[loss=0.1822, simple_loss=0.2607, pruned_loss=0.05186, over 7277.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2727, pruned_loss=0.03904, over 1418093.66 frames.], batch size: 17, lr: 4.35e-04
+2022-04-29 12:10:57,967 INFO [train.py:763] (2/8) Epoch 17, batch 1100, loss[loss=0.1907, simple_loss=0.2861, pruned_loss=0.04764, over 7313.00 frames.], tot_loss[loss=0.176, simple_loss=0.2732, pruned_loss=0.03938, over 1421480.97 frames.], batch size: 25, lr: 4.35e-04
+2022-04-29 12:12:04,943 INFO [train.py:763] (2/8) Epoch 17, batch 1150, loss[loss=0.1933, simple_loss=0.2912, pruned_loss=0.04771, over 7394.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2726, pruned_loss=0.03937, over 1419256.48 frames.], batch size: 23, lr: 4.35e-04
+2022-04-29 12:13:12,219 INFO [train.py:763] (2/8) Epoch 17, batch 1200, loss[loss=0.1541, simple_loss=0.2503, pruned_loss=0.02894, over 7281.00 frames.], tot_loss[loss=0.175, simple_loss=0.272, pruned_loss=0.03898, over 1417277.55 frames.], batch size: 18, lr: 4.34e-04
+2022-04-29 12:14:19,343 INFO [train.py:763] (2/8) Epoch 17, batch 1250, loss[loss=0.1965, simple_loss=0.293, pruned_loss=0.04999, over 7408.00 frames.], tot_loss[loss=0.175, simple_loss=0.2718, pruned_loss=0.0391, over 1419005.08 frames.], batch size: 21, lr: 4.34e-04
+2022-04-29 12:15:25,172 INFO [train.py:763] (2/8) Epoch 17, batch 1300, loss[loss=0.1785, simple_loss=0.279, pruned_loss=0.03901, over 7157.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2718, pruned_loss=0.03899, over 1420111.03 frames.], batch size: 26, lr: 4.34e-04
+2022-04-29 12:16:30,494 INFO [train.py:763] (2/8) Epoch 17, batch 1350, loss[loss=0.1492, simple_loss=0.2297, pruned_loss=0.0343, over 6993.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2722, pruned_loss=0.03916, over 1422595.52 frames.], batch size: 16, lr: 4.34e-04
+2022-04-29 12:17:36,045 INFO [train.py:763] (2/8) Epoch 17, batch 1400, loss[loss=0.172, simple_loss=0.2802, pruned_loss=0.03192, over 7112.00 frames.], tot_loss[loss=0.176, simple_loss=0.2733, pruned_loss=0.03932, over 1423892.90 frames.], batch size: 21, lr: 4.34e-04
+2022-04-29 12:18:41,486 INFO [train.py:763] (2/8) Epoch 17, batch 1450, loss[loss=0.168, simple_loss=0.2691, pruned_loss=0.03345, over 7148.00 frames.], tot_loss[loss=0.176, simple_loss=0.2735, pruned_loss=0.03929, over 1421995.40 frames.], batch size: 20, lr: 4.34e-04
+2022-04-29 12:19:47,537 INFO [train.py:763] (2/8) Epoch 17, batch 1500, loss[loss=0.1761, simple_loss=0.2879, pruned_loss=0.03212, over 7303.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2733, pruned_loss=0.03912, over 1413569.72 frames.], batch size: 25, lr: 4.34e-04
+2022-04-29 12:20:53,495 INFO [train.py:763] (2/8) Epoch 17, batch 1550, loss[loss=0.1698, simple_loss=0.264, pruned_loss=0.03781, over 7152.00 frames.], tot_loss[loss=0.1755, simple_loss=0.273, pruned_loss=0.03899, over 1420839.25 frames.], batch size: 19, lr: 4.33e-04
+2022-04-29 12:21:59,194 INFO [train.py:763] (2/8) Epoch 17, batch 1600, loss[loss=0.1687, simple_loss=0.2683, pruned_loss=0.03455, over 7424.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2731, pruned_loss=0.03899, over 1421584.56 frames.], batch size: 20, lr: 4.33e-04
+2022-04-29 12:23:04,502 INFO [train.py:763] (2/8) Epoch 17, batch 1650, loss[loss=0.1426, simple_loss=0.2375, pruned_loss=0.02382, over 7276.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2731, pruned_loss=0.03895, over 1420860.01 frames.], batch size: 17, lr: 4.33e-04
+2022-04-29 12:24:09,897 INFO [train.py:763] (2/8) Epoch 17, batch 1700, loss[loss=0.1612, simple_loss=0.2596, pruned_loss=0.03137, over 7352.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2731, pruned_loss=0.03886, over 1423749.28 frames.], batch size: 19, lr: 4.33e-04
+2022-04-29 12:25:15,252 INFO [train.py:763] (2/8) Epoch 17, batch 1750, loss[loss=0.1787, simple_loss=0.2783, pruned_loss=0.03951, over 7315.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2723, pruned_loss=0.03854, over 1425084.93 frames.], batch size: 21, lr: 4.33e-04
+2022-04-29 12:26:20,535 INFO [train.py:763] (2/8) Epoch 17, batch 1800, loss[loss=0.175, simple_loss=0.2818, pruned_loss=0.03409, over 7231.00 frames.], tot_loss[loss=0.174, simple_loss=0.2716, pruned_loss=0.03818, over 1428911.66 frames.], batch size: 20, lr: 4.33e-04
+2022-04-29 12:27:26,283 INFO [train.py:763] (2/8) Epoch 17, batch 1850, loss[loss=0.2283, simple_loss=0.3118, pruned_loss=0.07239, over 4783.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2713, pruned_loss=0.03877, over 1426245.83 frames.], batch size: 52, lr: 4.33e-04
+2022-04-29 12:28:31,338 INFO [train.py:763] (2/8) Epoch 17, batch 1900, loss[loss=0.1692, simple_loss=0.2742, pruned_loss=0.03208, over 7314.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2725, pruned_loss=0.03926, over 1426948.10 frames.], batch size: 21, lr: 4.33e-04
+2022-04-29 12:29:36,730 INFO [train.py:763] (2/8) Epoch 17, batch 1950, loss[loss=0.1956, simple_loss=0.2966, pruned_loss=0.0473, over 7326.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2733, pruned_loss=0.03986, over 1424068.33 frames.], batch size: 21, lr: 4.32e-04
+2022-04-29 12:30:42,615 INFO [train.py:763] (2/8) Epoch 17, batch 2000, loss[loss=0.2049, simple_loss=0.2922, pruned_loss=0.05878, over 4777.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2726, pruned_loss=0.03995, over 1423887.60 frames.], batch size: 52, lr: 4.32e-04
+2022-04-29 12:31:59,161 INFO [train.py:763] (2/8) Epoch 17, batch 2050, loss[loss=0.1674, simple_loss=0.2763, pruned_loss=0.02926, over 7102.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2722, pruned_loss=0.03959, over 1420243.14 frames.], batch size: 21, lr: 4.32e-04
+2022-04-29 12:33:04,641 INFO [train.py:763] (2/8) Epoch 17, batch 2100, loss[loss=0.1986, simple_loss=0.3091, pruned_loss=0.0441, over 6702.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2724, pruned_loss=0.03965, over 1415756.94 frames.], batch size: 31, lr: 4.32e-04
+2022-04-29 12:34:11,525 INFO [train.py:763] (2/8) Epoch 17, batch 2150, loss[loss=0.1802, simple_loss=0.2898, pruned_loss=0.0353, over 7221.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2725, pruned_loss=0.03938, over 1417508.44 frames.], batch size: 21, lr: 4.32e-04
+2022-04-29 12:35:18,267 INFO [train.py:763] (2/8) Epoch 17, batch 2200, loss[loss=0.1874, simple_loss=0.2641, pruned_loss=0.05536, over 7209.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2721, pruned_loss=0.03952, over 1420224.39 frames.], batch size: 16, lr: 4.32e-04
+2022-04-29 12:36:23,939 INFO [train.py:763] (2/8) Epoch 17, batch 2250, loss[loss=0.1475, simple_loss=0.2383, pruned_loss=0.02837, over 7010.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2715, pruned_loss=0.03935, over 1423876.00 frames.], batch size: 16, lr: 4.32e-04
+2022-04-29 12:37:31,402 INFO [train.py:763] (2/8) Epoch 17, batch 2300, loss[loss=0.1606, simple_loss=0.2674, pruned_loss=0.02692, over 7151.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2734, pruned_loss=0.03994, over 1425905.00 frames.], batch size: 20, lr: 4.31e-04
+2022-04-29 12:38:38,621 INFO [train.py:763] (2/8) Epoch 17, batch 2350, loss[loss=0.1885, simple_loss=0.2888, pruned_loss=0.04412, over 7170.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2729, pruned_loss=0.03984, over 1425595.62 frames.], batch size: 26, lr: 4.31e-04
+2022-04-29 12:39:44,061 INFO [train.py:763] (2/8) Epoch 17, batch 2400, loss[loss=0.2455, simple_loss=0.3436, pruned_loss=0.07365, over 6500.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2734, pruned_loss=0.03981, over 1425022.90 frames.], batch size: 38, lr: 4.31e-04
+2022-04-29 12:40:49,288 INFO [train.py:763] (2/8) Epoch 17, batch 2450, loss[loss=0.1509, simple_loss=0.2509, pruned_loss=0.02544, over 7152.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2725, pruned_loss=0.03927, over 1426248.64 frames.], batch size: 19, lr: 4.31e-04
+2022-04-29 12:41:54,332 INFO [train.py:763] (2/8) Epoch 17, batch 2500, loss[loss=0.1792, simple_loss=0.2903, pruned_loss=0.03405, over 7110.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2747, pruned_loss=0.04036, over 1418978.08 frames.], batch size: 21, lr: 4.31e-04
+2022-04-29 12:42:59,724 INFO [train.py:763] (2/8) Epoch 17, batch 2550, loss[loss=0.1764, simple_loss=0.278, pruned_loss=0.03739, over 7313.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2738, pruned_loss=0.04026, over 1419734.55 frames.], batch size: 21, lr: 4.31e-04
+2022-04-29 12:44:04,851 INFO [train.py:763] (2/8) Epoch 17, batch 2600, loss[loss=0.1544, simple_loss=0.2447, pruned_loss=0.03203, over 7209.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2743, pruned_loss=0.04057, over 1418854.75 frames.], batch size: 16, lr: 4.31e-04
+2022-04-29 12:45:10,698 INFO [train.py:763] (2/8) Epoch 17, batch 2650, loss[loss=0.1814, simple_loss=0.2825, pruned_loss=0.04019, over 7351.00 frames.], tot_loss[loss=0.1773, simple_loss=0.274, pruned_loss=0.04032, over 1420660.70 frames.], batch size: 19, lr: 4.31e-04
+2022-04-29 12:46:17,005 INFO [train.py:763] (2/8) Epoch 17, batch 2700, loss[loss=0.1502, simple_loss=0.2403, pruned_loss=0.03003, over 7291.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2722, pruned_loss=0.03977, over 1420168.96 frames.], batch size: 18, lr: 4.30e-04
+2022-04-29 12:47:22,077 INFO [train.py:763] (2/8) Epoch 17, batch 2750, loss[loss=0.1802, simple_loss=0.2789, pruned_loss=0.04078, over 7150.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2722, pruned_loss=0.03964, over 1418173.03 frames.], batch size: 20, lr: 4.30e-04
+2022-04-29 12:48:28,856 INFO [train.py:763] (2/8) Epoch 17, batch 2800, loss[loss=0.1618, simple_loss=0.2675, pruned_loss=0.02804, over 7327.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2719, pruned_loss=0.03928, over 1417659.40 frames.], batch size: 21, lr: 4.30e-04
+2022-04-29 12:49:34,422 INFO [train.py:763] (2/8) Epoch 17, batch 2850, loss[loss=0.1841, simple_loss=0.2837, pruned_loss=0.04223, over 7321.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2726, pruned_loss=0.03922, over 1420794.11 frames.], batch size: 25, lr: 4.30e-04
+2022-04-29 12:50:39,886 INFO [train.py:763] (2/8) Epoch 17, batch 2900, loss[loss=0.1901, simple_loss=0.2857, pruned_loss=0.04725, over 7188.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2736, pruned_loss=0.03999, over 1423287.62 frames.], batch size: 22, lr: 4.30e-04
+2022-04-29 12:51:46,362 INFO [train.py:763] (2/8) Epoch 17, batch 2950, loss[loss=0.2041, simple_loss=0.2958, pruned_loss=0.05622, over 6463.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2732, pruned_loss=0.03965, over 1419956.45 frames.], batch size: 37, lr: 4.30e-04
+2022-04-29 12:52:52,634 INFO [train.py:763] (2/8) Epoch 17, batch 3000, loss[loss=0.1915, simple_loss=0.2871, pruned_loss=0.04796, over 7296.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2739, pruned_loss=0.03946, over 1418194.02 frames.], batch size: 25, lr: 4.30e-04
+2022-04-29 12:52:52,635 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 12:53:07,981 INFO [train.py:792] (2/8) Epoch 17, validation: loss=0.167, simple_loss=0.268, pruned_loss=0.03296, over 698248.00 frames.
+2022-04-29 12:54:13,314 INFO [train.py:763] (2/8) Epoch 17, batch 3050, loss[loss=0.1904, simple_loss=0.3011, pruned_loss=0.03985, over 7123.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2736, pruned_loss=0.03925, over 1417558.35 frames.], batch size: 21, lr: 4.29e-04
+2022-04-29 12:55:18,433 INFO [train.py:763] (2/8) Epoch 17, batch 3100, loss[loss=0.1661, simple_loss=0.2732, pruned_loss=0.02955, over 7239.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2734, pruned_loss=0.03898, over 1418709.25 frames.], batch size: 20, lr: 4.29e-04
+2022-04-29 12:56:23,979 INFO [train.py:763] (2/8) Epoch 17, batch 3150, loss[loss=0.1793, simple_loss=0.2758, pruned_loss=0.04137, over 7269.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2729, pruned_loss=0.03878, over 1421113.45 frames.], batch size: 19, lr: 4.29e-04
+2022-04-29 12:57:29,296 INFO [train.py:763] (2/8) Epoch 17, batch 3200, loss[loss=0.1926, simple_loss=0.2925, pruned_loss=0.04638, over 6796.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2728, pruned_loss=0.03913, over 1419383.23 frames.], batch size: 31, lr: 4.29e-04
+2022-04-29 12:58:34,629 INFO [train.py:763] (2/8) Epoch 17, batch 3250, loss[loss=0.2045, simple_loss=0.2937, pruned_loss=0.05762, over 7377.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2728, pruned_loss=0.03936, over 1422287.46 frames.], batch size: 23, lr: 4.29e-04
+2022-04-29 12:59:42,205 INFO [train.py:763] (2/8) Epoch 17, batch 3300, loss[loss=0.1461, simple_loss=0.2432, pruned_loss=0.02454, over 7161.00 frames.], tot_loss[loss=0.1747, simple_loss=0.272, pruned_loss=0.0387, over 1426827.25 frames.], batch size: 18, lr: 4.29e-04
+2022-04-29 13:00:47,851 INFO [train.py:763] (2/8) Epoch 17, batch 3350, loss[loss=0.1453, simple_loss=0.2465, pruned_loss=0.02208, over 7435.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2724, pruned_loss=0.03891, over 1427001.15 frames.], batch size: 18, lr: 4.29e-04
+2022-04-29 13:01:54,343 INFO [train.py:763] (2/8) Epoch 17, batch 3400, loss[loss=0.1965, simple_loss=0.2931, pruned_loss=0.05002, over 7380.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2729, pruned_loss=0.03894, over 1430079.74 frames.], batch size: 23, lr: 4.29e-04
+2022-04-29 13:02:59,882 INFO [train.py:763] (2/8) Epoch 17, batch 3450, loss[loss=0.1735, simple_loss=0.2607, pruned_loss=0.04321, over 7409.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2734, pruned_loss=0.03904, over 1430679.34 frames.], batch size: 18, lr: 4.28e-04
+2022-04-29 13:04:05,571 INFO [train.py:763] (2/8) Epoch 17, batch 3500, loss[loss=0.2, simple_loss=0.2897, pruned_loss=0.05518, over 6449.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2727, pruned_loss=0.03916, over 1433112.89 frames.], batch size: 38, lr: 4.28e-04
+2022-04-29 13:05:11,601 INFO [train.py:763] (2/8) Epoch 17, batch 3550, loss[loss=0.1819, simple_loss=0.2756, pruned_loss=0.0441, over 7196.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2722, pruned_loss=0.03899, over 1431217.20 frames.], batch size: 23, lr: 4.28e-04
+2022-04-29 13:06:17,355 INFO [train.py:763] (2/8) Epoch 17, batch 3600, loss[loss=0.1942, simple_loss=0.2848, pruned_loss=0.0518, over 7222.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2719, pruned_loss=0.03896, over 1432344.91 frames.], batch size: 21, lr: 4.28e-04
+2022-04-29 13:07:22,978 INFO [train.py:763] (2/8) Epoch 17, batch 3650, loss[loss=0.1824, simple_loss=0.2894, pruned_loss=0.03777, over 7327.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2723, pruned_loss=0.03909, over 1423229.96 frames.], batch size: 22, lr: 4.28e-04
+2022-04-29 13:08:28,136 INFO [train.py:763] (2/8) Epoch 17, batch 3700, loss[loss=0.1787, simple_loss=0.2682, pruned_loss=0.04463, over 7010.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2735, pruned_loss=0.03929, over 1424510.16 frames.], batch size: 16, lr: 4.28e-04
+2022-04-29 13:09:33,324 INFO [train.py:763] (2/8) Epoch 17, batch 3750, loss[loss=0.1674, simple_loss=0.2669, pruned_loss=0.03395, over 7282.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2741, pruned_loss=0.0393, over 1426906.38 frames.], batch size: 25, lr: 4.28e-04
+2022-04-29 13:10:39,692 INFO [train.py:763] (2/8) Epoch 17, batch 3800, loss[loss=0.1765, simple_loss=0.2708, pruned_loss=0.04108, over 7354.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2728, pruned_loss=0.03889, over 1427134.54 frames.], batch size: 19, lr: 4.28e-04
+2022-04-29 13:11:45,015 INFO [train.py:763] (2/8) Epoch 17, batch 3850, loss[loss=0.1574, simple_loss=0.2504, pruned_loss=0.03219, over 7417.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2724, pruned_loss=0.0389, over 1426377.50 frames.], batch size: 18, lr: 4.27e-04
+2022-04-29 13:12:50,423 INFO [train.py:763] (2/8) Epoch 17, batch 3900, loss[loss=0.1945, simple_loss=0.2947, pruned_loss=0.04714, over 7127.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2724, pruned_loss=0.03913, over 1422291.12 frames.], batch size: 21, lr: 4.27e-04
+2022-04-29 13:13:55,777 INFO [train.py:763] (2/8) Epoch 17, batch 3950, loss[loss=0.2053, simple_loss=0.3041, pruned_loss=0.05328, over 7035.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2718, pruned_loss=0.03929, over 1423797.25 frames.], batch size: 28, lr: 4.27e-04
+2022-04-29 13:15:01,123 INFO [train.py:763] (2/8) Epoch 17, batch 4000, loss[loss=0.1683, simple_loss=0.2621, pruned_loss=0.03729, over 6869.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2719, pruned_loss=0.03919, over 1424305.76 frames.], batch size: 15, lr: 4.27e-04
+2022-04-29 13:16:06,979 INFO [train.py:763] (2/8) Epoch 17, batch 4050, loss[loss=0.1699, simple_loss=0.27, pruned_loss=0.03488, over 7121.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2723, pruned_loss=0.03934, over 1427401.70 frames.], batch size: 28, lr: 4.27e-04
+2022-04-29 13:17:12,349 INFO [train.py:763] (2/8) Epoch 17, batch 4100, loss[loss=0.1967, simple_loss=0.3042, pruned_loss=0.04463, over 7153.00 frames.], tot_loss[loss=0.1761, simple_loss=0.273, pruned_loss=0.0396, over 1424163.96 frames.], batch size: 20, lr: 4.27e-04
+2022-04-29 13:18:18,021 INFO [train.py:763] (2/8) Epoch 17, batch 4150, loss[loss=0.1874, simple_loss=0.2821, pruned_loss=0.0463, over 7322.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2724, pruned_loss=0.03929, over 1422682.83 frames.], batch size: 20, lr: 4.27e-04
+2022-04-29 13:19:24,061 INFO [train.py:763] (2/8) Epoch 17, batch 4200, loss[loss=0.1598, simple_loss=0.254, pruned_loss=0.03286, over 7000.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2702, pruned_loss=0.03861, over 1421936.64 frames.], batch size: 16, lr: 4.26e-04
+2022-04-29 13:20:29,201 INFO [train.py:763] (2/8) Epoch 17, batch 4250, loss[loss=0.1801, simple_loss=0.272, pruned_loss=0.04412, over 6772.00 frames.], tot_loss[loss=0.174, simple_loss=0.2703, pruned_loss=0.03887, over 1417017.55 frames.], batch size: 31, lr: 4.26e-04
+2022-04-29 13:21:35,158 INFO [train.py:763] (2/8) Epoch 17, batch 4300, loss[loss=0.1353, simple_loss=0.2271, pruned_loss=0.02178, over 7001.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2702, pruned_loss=0.03904, over 1417973.12 frames.], batch size: 16, lr: 4.26e-04
+2022-04-29 13:22:49,722 INFO [train.py:763] (2/8) Epoch 17, batch 4350, loss[loss=0.1802, simple_loss=0.281, pruned_loss=0.03965, over 7213.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2714, pruned_loss=0.0396, over 1405205.20 frames.], batch size: 21, lr: 4.26e-04
+2022-04-29 13:23:54,550 INFO [train.py:763] (2/8) Epoch 17, batch 4400, loss[loss=0.1451, simple_loss=0.2458, pruned_loss=0.02216, over 7062.00 frames.], tot_loss[loss=0.176, simple_loss=0.2724, pruned_loss=0.03976, over 1399842.65 frames.], batch size: 18, lr: 4.26e-04
+2022-04-29 13:24:59,615 INFO [train.py:763] (2/8) Epoch 17, batch 4450, loss[loss=0.1974, simple_loss=0.2957, pruned_loss=0.04962, over 6295.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2736, pruned_loss=0.04017, over 1391279.46 frames.], batch size: 37, lr: 4.26e-04
+2022-04-29 13:26:04,072 INFO [train.py:763] (2/8) Epoch 17, batch 4500, loss[loss=0.1672, simple_loss=0.2536, pruned_loss=0.04037, over 7003.00 frames.], tot_loss[loss=0.177, simple_loss=0.274, pruned_loss=0.04001, over 1378750.09 frames.], batch size: 16, lr: 4.26e-04
+2022-04-29 13:27:09,433 INFO [train.py:763] (2/8) Epoch 17, batch 4550, loss[loss=0.1663, simple_loss=0.2569, pruned_loss=0.03784, over 7164.00 frames.], tot_loss[loss=0.177, simple_loss=0.2739, pruned_loss=0.04006, over 1369296.13 frames.], batch size: 19, lr: 4.26e-04
+2022-04-29 13:29:06,464 INFO [train.py:763] (2/8) Epoch 18, batch 0, loss[loss=0.2041, simple_loss=0.3032, pruned_loss=0.05252, over 7342.00 frames.], tot_loss[loss=0.2041, simple_loss=0.3032, pruned_loss=0.05252, over 7342.00 frames.], batch size: 25, lr: 4.15e-04
+2022-04-29 13:30:22,085 INFO [train.py:763] (2/8) Epoch 18, batch 50, loss[loss=0.2194, simple_loss=0.3244, pruned_loss=0.05716, over 7343.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2717, pruned_loss=0.03772, over 325511.65 frames.], batch size: 22, lr: 4.15e-04
+2022-04-29 13:31:37,247 INFO [train.py:763] (2/8) Epoch 18, batch 100, loss[loss=0.1783, simple_loss=0.2882, pruned_loss=0.03424, over 7351.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2715, pruned_loss=0.03695, over 575055.33 frames.], batch size: 22, lr: 4.14e-04
+2022-04-29 13:32:51,550 INFO [train.py:763] (2/8) Epoch 18, batch 150, loss[loss=0.1907, simple_loss=0.3009, pruned_loss=0.04022, over 7215.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2695, pruned_loss=0.03683, over 764280.61 frames.], batch size: 21, lr: 4.14e-04
+2022-04-29 13:33:57,482 INFO [train.py:763] (2/8) Epoch 18, batch 200, loss[loss=0.1636, simple_loss=0.248, pruned_loss=0.03959, over 7278.00 frames.], tot_loss[loss=0.1738, simple_loss=0.271, pruned_loss=0.03829, over 910036.48 frames.], batch size: 17, lr: 4.14e-04
+2022-04-29 13:35:11,767 INFO [train.py:763] (2/8) Epoch 18, batch 250, loss[loss=0.1573, simple_loss=0.2559, pruned_loss=0.02932, over 6782.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2711, pruned_loss=0.03808, over 1026173.14 frames.], batch size: 31, lr: 4.14e-04
+2022-04-29 13:36:17,270 INFO [train.py:763] (2/8) Epoch 18, batch 300, loss[loss=0.1624, simple_loss=0.2566, pruned_loss=0.03408, over 7236.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2702, pruned_loss=0.03739, over 1116512.87 frames.], batch size: 20, lr: 4.14e-04
+2022-04-29 13:37:24,205 INFO [train.py:763] (2/8) Epoch 18, batch 350, loss[loss=0.1905, simple_loss=0.2892, pruned_loss=0.04593, over 6730.00 frames.], tot_loss[loss=0.172, simple_loss=0.2698, pruned_loss=0.03707, over 1182405.32 frames.], batch size: 31, lr: 4.14e-04
+2022-04-29 13:38:31,272 INFO [train.py:763] (2/8) Epoch 18, batch 400, loss[loss=0.1753, simple_loss=0.2698, pruned_loss=0.04037, over 7061.00 frames.], tot_loss[loss=0.1735, simple_loss=0.271, pruned_loss=0.038, over 1233499.48 frames.], batch size: 18, lr: 4.14e-04
+2022-04-29 13:39:38,716 INFO [train.py:763] (2/8) Epoch 18, batch 450, loss[loss=0.1738, simple_loss=0.2787, pruned_loss=0.03447, over 7330.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2715, pruned_loss=0.03808, over 1275134.84 frames.], batch size: 22, lr: 4.14e-04
+2022-04-29 13:40:45,464 INFO [train.py:763] (2/8) Epoch 18, batch 500, loss[loss=0.1487, simple_loss=0.2404, pruned_loss=0.02844, over 7147.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2719, pruned_loss=0.03832, over 1305898.06 frames.], batch size: 17, lr: 4.13e-04
+2022-04-29 13:41:52,278 INFO [train.py:763] (2/8) Epoch 18, batch 550, loss[loss=0.1625, simple_loss=0.2425, pruned_loss=0.04127, over 7304.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2713, pruned_loss=0.03778, over 1335990.11 frames.], batch size: 17, lr: 4.13e-04
+2022-04-29 13:42:57,720 INFO [train.py:763] (2/8) Epoch 18, batch 600, loss[loss=0.1539, simple_loss=0.2441, pruned_loss=0.03186, over 7276.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2717, pruned_loss=0.03849, over 1356347.57 frames.], batch size: 18, lr: 4.13e-04
+2022-04-29 13:44:04,376 INFO [train.py:763] (2/8) Epoch 18, batch 650, loss[loss=0.1702, simple_loss=0.2678, pruned_loss=0.03635, over 7122.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2708, pruned_loss=0.03793, over 1375682.47 frames.], batch size: 21, lr: 4.13e-04
+2022-04-29 13:45:09,471 INFO [train.py:763] (2/8) Epoch 18, batch 700, loss[loss=0.209, simple_loss=0.2955, pruned_loss=0.06124, over 5195.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2724, pruned_loss=0.03844, over 1385615.62 frames.], batch size: 52, lr: 4.13e-04
+2022-04-29 13:46:15,213 INFO [train.py:763] (2/8) Epoch 18, batch 750, loss[loss=0.1702, simple_loss=0.2683, pruned_loss=0.03607, over 7161.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2727, pruned_loss=0.03884, over 1393710.00 frames.], batch size: 19, lr: 4.13e-04
+2022-04-29 13:47:20,150 INFO [train.py:763] (2/8) Epoch 18, batch 800, loss[loss=0.1686, simple_loss=0.2814, pruned_loss=0.02788, over 6927.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2726, pruned_loss=0.03846, over 1397047.03 frames.], batch size: 32, lr: 4.13e-04
+2022-04-29 13:48:26,401 INFO [train.py:763] (2/8) Epoch 18, batch 850, loss[loss=0.1657, simple_loss=0.259, pruned_loss=0.03621, over 7057.00 frames.], tot_loss[loss=0.175, simple_loss=0.273, pruned_loss=0.03852, over 1403907.19 frames.], batch size: 18, lr: 4.13e-04
+2022-04-29 13:49:33,104 INFO [train.py:763] (2/8) Epoch 18, batch 900, loss[loss=0.1707, simple_loss=0.2624, pruned_loss=0.03953, over 7230.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2732, pruned_loss=0.03855, over 1410479.36 frames.], batch size: 16, lr: 4.12e-04
+2022-04-29 13:50:38,403 INFO [train.py:763] (2/8) Epoch 18, batch 950, loss[loss=0.1836, simple_loss=0.2873, pruned_loss=0.03996, over 7382.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2723, pruned_loss=0.0383, over 1413187.99 frames.], batch size: 23, lr: 4.12e-04
+2022-04-29 13:51:45,512 INFO [train.py:763] (2/8) Epoch 18, batch 1000, loss[loss=0.1713, simple_loss=0.2682, pruned_loss=0.03721, over 7148.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2724, pruned_loss=0.0385, over 1419792.54 frames.], batch size: 20, lr: 4.12e-04
+2022-04-29 13:52:52,988 INFO [train.py:763] (2/8) Epoch 18, batch 1050, loss[loss=0.1887, simple_loss=0.2937, pruned_loss=0.04187, over 7270.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2724, pruned_loss=0.03866, over 1418695.31 frames.], batch size: 25, lr: 4.12e-04
+2022-04-29 13:53:58,528 INFO [train.py:763] (2/8) Epoch 18, batch 1100, loss[loss=0.1884, simple_loss=0.2846, pruned_loss=0.04613, over 7322.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2718, pruned_loss=0.03842, over 1418935.27 frames.], batch size: 20, lr: 4.12e-04
+2022-04-29 13:55:03,935 INFO [train.py:763] (2/8) Epoch 18, batch 1150, loss[loss=0.1956, simple_loss=0.3, pruned_loss=0.04557, over 7287.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2723, pruned_loss=0.03845, over 1419517.27 frames.], batch size: 24, lr: 4.12e-04
+2022-04-29 13:56:09,831 INFO [train.py:763] (2/8) Epoch 18, batch 1200, loss[loss=0.2097, simple_loss=0.2967, pruned_loss=0.06134, over 5112.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2718, pruned_loss=0.03851, over 1414038.98 frames.], batch size: 52, lr: 4.12e-04
+2022-04-29 13:57:15,049 INFO [train.py:763] (2/8) Epoch 18, batch 1250, loss[loss=0.1725, simple_loss=0.2753, pruned_loss=0.03487, over 7123.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2721, pruned_loss=0.03847, over 1415233.38 frames.], batch size: 21, lr: 4.12e-04
+2022-04-29 13:58:20,081 INFO [train.py:763] (2/8) Epoch 18, batch 1300, loss[loss=0.1532, simple_loss=0.2517, pruned_loss=0.02734, over 7163.00 frames.], tot_loss[loss=0.175, simple_loss=0.273, pruned_loss=0.03856, over 1414956.93 frames.], batch size: 19, lr: 4.12e-04
+2022-04-29 13:59:25,397 INFO [train.py:763] (2/8) Epoch 18, batch 1350, loss[loss=0.1923, simple_loss=0.2812, pruned_loss=0.05172, over 7012.00 frames.], tot_loss[loss=0.176, simple_loss=0.2737, pruned_loss=0.03909, over 1412817.12 frames.], batch size: 28, lr: 4.11e-04
+2022-04-29 14:00:32,445 INFO [train.py:763] (2/8) Epoch 18, batch 1400, loss[loss=0.1539, simple_loss=0.2484, pruned_loss=0.02972, over 7070.00 frames.], tot_loss[loss=0.1744, simple_loss=0.272, pruned_loss=0.03839, over 1411288.16 frames.], batch size: 18, lr: 4.11e-04
+2022-04-29 14:01:39,693 INFO [train.py:763] (2/8) Epoch 18, batch 1450, loss[loss=0.1948, simple_loss=0.2981, pruned_loss=0.04576, over 7310.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2712, pruned_loss=0.03805, over 1418103.65 frames.], batch size: 21, lr: 4.11e-04
+2022-04-29 14:02:45,980 INFO [train.py:763] (2/8) Epoch 18, batch 1500, loss[loss=0.1468, simple_loss=0.2433, pruned_loss=0.02512, over 7261.00 frames.], tot_loss[loss=0.1738, simple_loss=0.272, pruned_loss=0.03784, over 1421813.54 frames.], batch size: 19, lr: 4.11e-04
+2022-04-29 14:03:53,117 INFO [train.py:763] (2/8) Epoch 18, batch 1550, loss[loss=0.1857, simple_loss=0.2865, pruned_loss=0.04241, over 7408.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2719, pruned_loss=0.03791, over 1424889.87 frames.], batch size: 21, lr: 4.11e-04
+2022-04-29 14:04:58,305 INFO [train.py:763] (2/8) Epoch 18, batch 1600, loss[loss=0.203, simple_loss=0.2992, pruned_loss=0.0534, over 7224.00 frames.], tot_loss[loss=0.1732, simple_loss=0.271, pruned_loss=0.03768, over 1423714.82 frames.], batch size: 22, lr: 4.11e-04
+2022-04-29 14:06:03,946 INFO [train.py:763] (2/8) Epoch 18, batch 1650, loss[loss=0.1585, simple_loss=0.2514, pruned_loss=0.03286, over 7166.00 frames.], tot_loss[loss=0.1733, simple_loss=0.271, pruned_loss=0.03777, over 1423068.75 frames.], batch size: 18, lr: 4.11e-04
+2022-04-29 14:07:10,553 INFO [train.py:763] (2/8) Epoch 18, batch 1700, loss[loss=0.1815, simple_loss=0.2702, pruned_loss=0.04642, over 7166.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2707, pruned_loss=0.03773, over 1423567.17 frames.], batch size: 18, lr: 4.11e-04
+2022-04-29 14:08:17,581 INFO [train.py:763] (2/8) Epoch 18, batch 1750, loss[loss=0.1843, simple_loss=0.286, pruned_loss=0.04127, over 7148.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2724, pruned_loss=0.03843, over 1415291.85 frames.], batch size: 20, lr: 4.10e-04
+2022-04-29 14:09:24,693 INFO [train.py:763] (2/8) Epoch 18, batch 1800, loss[loss=0.1657, simple_loss=0.263, pruned_loss=0.0342, over 7254.00 frames.], tot_loss[loss=0.175, simple_loss=0.273, pruned_loss=0.03846, over 1416743.65 frames.], batch size: 19, lr: 4.10e-04
+2022-04-29 14:10:32,223 INFO [train.py:763] (2/8) Epoch 18, batch 1850, loss[loss=0.1846, simple_loss=0.2921, pruned_loss=0.03854, over 7289.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2729, pruned_loss=0.03851, over 1422456.87 frames.], batch size: 24, lr: 4.10e-04
+2022-04-29 14:11:39,559 INFO [train.py:763] (2/8) Epoch 18, batch 1900, loss[loss=0.1733, simple_loss=0.2734, pruned_loss=0.03662, over 7139.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2723, pruned_loss=0.03853, over 1420441.35 frames.], batch size: 28, lr: 4.10e-04
+2022-04-29 14:12:46,670 INFO [train.py:763] (2/8) Epoch 18, batch 1950, loss[loss=0.1353, simple_loss=0.2302, pruned_loss=0.02024, over 7008.00 frames.], tot_loss[loss=0.175, simple_loss=0.2726, pruned_loss=0.03875, over 1420700.95 frames.], batch size: 16, lr: 4.10e-04
+2022-04-29 14:13:51,988 INFO [train.py:763] (2/8) Epoch 18, batch 2000, loss[loss=0.1777, simple_loss=0.2828, pruned_loss=0.03632, over 7143.00 frames.], tot_loss[loss=0.175, simple_loss=0.2723, pruned_loss=0.03888, over 1423990.08 frames.], batch size: 20, lr: 4.10e-04
+2022-04-29 14:14:57,422 INFO [train.py:763] (2/8) Epoch 18, batch 2050, loss[loss=0.2008, simple_loss=0.2969, pruned_loss=0.05235, over 7329.00 frames.], tot_loss[loss=0.1747, simple_loss=0.272, pruned_loss=0.03872, over 1424388.62 frames.], batch size: 25, lr: 4.10e-04
+2022-04-29 14:16:02,568 INFO [train.py:763] (2/8) Epoch 18, batch 2100, loss[loss=0.1681, simple_loss=0.27, pruned_loss=0.03304, over 7156.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2717, pruned_loss=0.03804, over 1425093.94 frames.], batch size: 19, lr: 4.10e-04
+2022-04-29 14:17:08,132 INFO [train.py:763] (2/8) Epoch 18, batch 2150, loss[loss=0.1721, simple_loss=0.279, pruned_loss=0.03264, over 7210.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2707, pruned_loss=0.03778, over 1421280.84 frames.], batch size: 21, lr: 4.09e-04
+2022-04-29 14:18:13,396 INFO [train.py:763] (2/8) Epoch 18, batch 2200, loss[loss=0.1923, simple_loss=0.2916, pruned_loss=0.04645, over 7117.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2705, pruned_loss=0.03752, over 1425476.61 frames.], batch size: 21, lr: 4.09e-04
+2022-04-29 14:19:18,571 INFO [train.py:763] (2/8) Epoch 18, batch 2250, loss[loss=0.164, simple_loss=0.2644, pruned_loss=0.03185, over 6551.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2704, pruned_loss=0.03765, over 1424676.21 frames.], batch size: 38, lr: 4.09e-04
+2022-04-29 14:20:23,885 INFO [train.py:763] (2/8) Epoch 18, batch 2300, loss[loss=0.1963, simple_loss=0.2941, pruned_loss=0.04921, over 7370.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2708, pruned_loss=0.03768, over 1426087.03 frames.], batch size: 23, lr: 4.09e-04
+2022-04-29 14:21:28,905 INFO [train.py:763] (2/8) Epoch 18, batch 2350, loss[loss=0.1518, simple_loss=0.2442, pruned_loss=0.02973, over 7294.00 frames.], tot_loss[loss=0.1734, simple_loss=0.271, pruned_loss=0.03791, over 1422747.02 frames.], batch size: 17, lr: 4.09e-04
+2022-04-29 14:22:34,035 INFO [train.py:763] (2/8) Epoch 18, batch 2400, loss[loss=0.1804, simple_loss=0.288, pruned_loss=0.03639, over 7153.00 frames.], tot_loss[loss=0.174, simple_loss=0.2712, pruned_loss=0.0384, over 1419207.81 frames.], batch size: 20, lr: 4.09e-04
+2022-04-29 14:23:41,075 INFO [train.py:763] (2/8) Epoch 18, batch 2450, loss[loss=0.2102, simple_loss=0.3096, pruned_loss=0.05537, over 7145.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2713, pruned_loss=0.03804, over 1421080.48 frames.], batch size: 20, lr: 4.09e-04
+2022-04-29 14:24:46,854 INFO [train.py:763] (2/8) Epoch 18, batch 2500, loss[loss=0.1824, simple_loss=0.2879, pruned_loss=0.03849, over 7143.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2706, pruned_loss=0.03816, over 1419915.55 frames.], batch size: 26, lr: 4.09e-04
+2022-04-29 14:25:51,850 INFO [train.py:763] (2/8) Epoch 18, batch 2550, loss[loss=0.2132, simple_loss=0.3085, pruned_loss=0.05897, over 7280.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2712, pruned_loss=0.03879, over 1419737.47 frames.], batch size: 24, lr: 4.08e-04
+2022-04-29 14:26:57,009 INFO [train.py:763] (2/8) Epoch 18, batch 2600, loss[loss=0.171, simple_loss=0.2622, pruned_loss=0.03992, over 6995.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2714, pruned_loss=0.03854, over 1423785.82 frames.], batch size: 16, lr: 4.08e-04
+2022-04-29 14:28:02,329 INFO [train.py:763] (2/8) Epoch 18, batch 2650, loss[loss=0.1793, simple_loss=0.2803, pruned_loss=0.0392, over 7289.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2723, pruned_loss=0.03877, over 1425675.73 frames.], batch size: 24, lr: 4.08e-04
+2022-04-29 14:29:08,093 INFO [train.py:763] (2/8) Epoch 18, batch 2700, loss[loss=0.2338, simple_loss=0.3305, pruned_loss=0.06853, over 7290.00 frames.], tot_loss[loss=0.1735, simple_loss=0.271, pruned_loss=0.03802, over 1428980.98 frames.], batch size: 25, lr: 4.08e-04
+2022-04-29 14:30:14,901 INFO [train.py:763] (2/8) Epoch 18, batch 2750, loss[loss=0.1686, simple_loss=0.2765, pruned_loss=0.03036, over 7407.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2722, pruned_loss=0.03823, over 1429141.06 frames.], batch size: 21, lr: 4.08e-04
+2022-04-29 14:31:21,336 INFO [train.py:763] (2/8) Epoch 18, batch 2800, loss[loss=0.2039, simple_loss=0.2873, pruned_loss=0.06026, over 7061.00 frames.], tot_loss[loss=0.174, simple_loss=0.272, pruned_loss=0.03803, over 1429976.47 frames.], batch size: 18, lr: 4.08e-04
+2022-04-29 14:32:26,505 INFO [train.py:763] (2/8) Epoch 18, batch 2850, loss[loss=0.1778, simple_loss=0.2716, pruned_loss=0.04199, over 7142.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2724, pruned_loss=0.03826, over 1426065.81 frames.], batch size: 19, lr: 4.08e-04
+2022-04-29 14:33:31,778 INFO [train.py:763] (2/8) Epoch 18, batch 2900, loss[loss=0.1921, simple_loss=0.2881, pruned_loss=0.04808, over 7178.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2718, pruned_loss=0.03825, over 1423781.72 frames.], batch size: 26, lr: 4.08e-04
+2022-04-29 14:34:37,290 INFO [train.py:763] (2/8) Epoch 18, batch 2950, loss[loss=0.1382, simple_loss=0.2287, pruned_loss=0.0239, over 7280.00 frames.], tot_loss[loss=0.1742, simple_loss=0.272, pruned_loss=0.03822, over 1429421.47 frames.], batch size: 17, lr: 4.08e-04
+2022-04-29 14:35:43,261 INFO [train.py:763] (2/8) Epoch 18, batch 3000, loss[loss=0.2122, simple_loss=0.2988, pruned_loss=0.06286, over 4890.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2714, pruned_loss=0.03804, over 1428840.00 frames.], batch size: 52, lr: 4.07e-04
+2022-04-29 14:35:43,262 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 14:35:58,560 INFO [train.py:792] (2/8) Epoch 18, validation: loss=0.1668, simple_loss=0.2671, pruned_loss=0.03324, over 698248.00 frames.
+2022-04-29 14:37:05,447 INFO [train.py:763] (2/8) Epoch 18, batch 3050, loss[loss=0.183, simple_loss=0.2762, pruned_loss=0.04491, over 7213.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2712, pruned_loss=0.03797, over 1430614.81 frames.], batch size: 23, lr: 4.07e-04
+2022-04-29 14:38:12,643 INFO [train.py:763] (2/8) Epoch 18, batch 3100, loss[loss=0.1827, simple_loss=0.2887, pruned_loss=0.03835, over 6243.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2718, pruned_loss=0.03816, over 1431611.59 frames.], batch size: 37, lr: 4.07e-04
+2022-04-29 14:39:19,389 INFO [train.py:763] (2/8) Epoch 18, batch 3150, loss[loss=0.1555, simple_loss=0.2512, pruned_loss=0.02989, over 7286.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2731, pruned_loss=0.0389, over 1428791.60 frames.], batch size: 18, lr: 4.07e-04
+2022-04-29 14:40:26,375 INFO [train.py:763] (2/8) Epoch 18, batch 3200, loss[loss=0.1583, simple_loss=0.2616, pruned_loss=0.02752, over 7151.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2731, pruned_loss=0.03866, over 1427342.59 frames.], batch size: 19, lr: 4.07e-04
+2022-04-29 14:41:32,517 INFO [train.py:763] (2/8) Epoch 18, batch 3250, loss[loss=0.1468, simple_loss=0.2321, pruned_loss=0.0308, over 7366.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2732, pruned_loss=0.03853, over 1424801.71 frames.], batch size: 19, lr: 4.07e-04
+2022-04-29 14:42:37,738 INFO [train.py:763] (2/8) Epoch 18, batch 3300, loss[loss=0.1818, simple_loss=0.2819, pruned_loss=0.04086, over 6417.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2733, pruned_loss=0.03844, over 1425419.13 frames.], batch size: 37, lr: 4.07e-04
+2022-04-29 14:43:43,234 INFO [train.py:763] (2/8) Epoch 18, batch 3350, loss[loss=0.2046, simple_loss=0.3079, pruned_loss=0.05063, over 7131.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2722, pruned_loss=0.03803, over 1424857.28 frames.], batch size: 21, lr: 4.07e-04
+2022-04-29 14:44:48,481 INFO [train.py:763] (2/8) Epoch 18, batch 3400, loss[loss=0.1776, simple_loss=0.2675, pruned_loss=0.04383, over 7284.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2719, pruned_loss=0.038, over 1425799.58 frames.], batch size: 18, lr: 4.06e-04
+2022-04-29 14:45:53,979 INFO [train.py:763] (2/8) Epoch 18, batch 3450, loss[loss=0.1666, simple_loss=0.2596, pruned_loss=0.03677, over 7360.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2715, pruned_loss=0.03836, over 1420854.92 frames.], batch size: 19, lr: 4.06e-04
+2022-04-29 14:46:59,195 INFO [train.py:763] (2/8) Epoch 18, batch 3500, loss[loss=0.1672, simple_loss=0.2636, pruned_loss=0.03536, over 7286.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2713, pruned_loss=0.03797, over 1423763.78 frames.], batch size: 18, lr: 4.06e-04
+2022-04-29 14:48:04,602 INFO [train.py:763] (2/8) Epoch 18, batch 3550, loss[loss=0.1446, simple_loss=0.2357, pruned_loss=0.02675, over 7131.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2711, pruned_loss=0.03805, over 1423353.20 frames.], batch size: 17, lr: 4.06e-04
+2022-04-29 14:49:09,816 INFO [train.py:763] (2/8) Epoch 18, batch 3600, loss[loss=0.1924, simple_loss=0.2819, pruned_loss=0.05148, over 7191.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2717, pruned_loss=0.03823, over 1420699.59 frames.], batch size: 23, lr: 4.06e-04
+2022-04-29 14:50:14,978 INFO [train.py:763] (2/8) Epoch 18, batch 3650, loss[loss=0.1643, simple_loss=0.2665, pruned_loss=0.03101, over 7334.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2723, pruned_loss=0.03818, over 1414891.64 frames.], batch size: 20, lr: 4.06e-04
+2022-04-29 14:51:20,198 INFO [train.py:763] (2/8) Epoch 18, batch 3700, loss[loss=0.1757, simple_loss=0.2733, pruned_loss=0.03908, over 7412.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2728, pruned_loss=0.03869, over 1416993.26 frames.], batch size: 21, lr: 4.06e-04
+2022-04-29 14:52:25,581 INFO [train.py:763] (2/8) Epoch 18, batch 3750, loss[loss=0.1772, simple_loss=0.2779, pruned_loss=0.03825, over 7382.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2729, pruned_loss=0.03903, over 1413683.45 frames.], batch size: 23, lr: 4.06e-04
+2022-04-29 14:53:30,892 INFO [train.py:763] (2/8) Epoch 18, batch 3800, loss[loss=0.1662, simple_loss=0.2607, pruned_loss=0.03588, over 7373.00 frames.], tot_loss[loss=0.1754, simple_loss=0.273, pruned_loss=0.03888, over 1419070.34 frames.], batch size: 19, lr: 4.06e-04
+2022-04-29 14:54:36,410 INFO [train.py:763] (2/8) Epoch 18, batch 3850, loss[loss=0.159, simple_loss=0.2537, pruned_loss=0.03216, over 7155.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2726, pruned_loss=0.03896, over 1416842.65 frames.], batch size: 18, lr: 4.05e-04
+2022-04-29 14:55:41,212 INFO [train.py:763] (2/8) Epoch 18, batch 3900, loss[loss=0.1979, simple_loss=0.2881, pruned_loss=0.05388, over 7116.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2732, pruned_loss=0.03892, over 1414437.17 frames.], batch size: 21, lr: 4.05e-04
+2022-04-29 14:56:46,298 INFO [train.py:763] (2/8) Epoch 18, batch 3950, loss[loss=0.1896, simple_loss=0.272, pruned_loss=0.05366, over 7172.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2733, pruned_loss=0.03894, over 1416444.47 frames.], batch size: 18, lr: 4.05e-04
+2022-04-29 14:57:51,525 INFO [train.py:763] (2/8) Epoch 18, batch 4000, loss[loss=0.1632, simple_loss=0.2689, pruned_loss=0.02873, over 4927.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2729, pruned_loss=0.03864, over 1417699.94 frames.], batch size: 52, lr: 4.05e-04
+2022-04-29 14:58:57,190 INFO [train.py:763] (2/8) Epoch 18, batch 4050, loss[loss=0.1471, simple_loss=0.2287, pruned_loss=0.03276, over 6798.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2729, pruned_loss=0.0391, over 1415001.97 frames.], batch size: 15, lr: 4.05e-04
+2022-04-29 15:00:03,349 INFO [train.py:763] (2/8) Epoch 18, batch 4100, loss[loss=0.1982, simple_loss=0.2716, pruned_loss=0.06243, over 5136.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2738, pruned_loss=0.03951, over 1415395.90 frames.], batch size: 52, lr: 4.05e-04
+2022-04-29 15:01:09,075 INFO [train.py:763] (2/8) Epoch 18, batch 4150, loss[loss=0.1834, simple_loss=0.287, pruned_loss=0.03997, over 7390.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2728, pruned_loss=0.03911, over 1420408.88 frames.], batch size: 23, lr: 4.05e-04
+2022-04-29 15:02:16,178 INFO [train.py:763] (2/8) Epoch 18, batch 4200, loss[loss=0.1791, simple_loss=0.274, pruned_loss=0.04212, over 7206.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2725, pruned_loss=0.03911, over 1419161.36 frames.], batch size: 23, lr: 4.05e-04
+2022-04-29 15:03:23,608 INFO [train.py:763] (2/8) Epoch 18, batch 4250, loss[loss=0.1356, simple_loss=0.2251, pruned_loss=0.02299, over 6823.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2712, pruned_loss=0.03845, over 1419116.38 frames.], batch size: 15, lr: 4.04e-04
+2022-04-29 15:04:28,929 INFO [train.py:763] (2/8) Epoch 18, batch 4300, loss[loss=0.1985, simple_loss=0.3008, pruned_loss=0.04811, over 7135.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2708, pruned_loss=0.03817, over 1418361.24 frames.], batch size: 26, lr: 4.04e-04
+2022-04-29 15:05:35,077 INFO [train.py:763] (2/8) Epoch 18, batch 4350, loss[loss=0.165, simple_loss=0.2656, pruned_loss=0.03216, over 7168.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2708, pruned_loss=0.03803, over 1416808.49 frames.], batch size: 18, lr: 4.04e-04
+2022-04-29 15:06:42,524 INFO [train.py:763] (2/8) Epoch 18, batch 4400, loss[loss=0.2098, simple_loss=0.3018, pruned_loss=0.05891, over 6314.00 frames.], tot_loss[loss=0.174, simple_loss=0.2712, pruned_loss=0.03842, over 1413418.96 frames.], batch size: 38, lr: 4.04e-04
+2022-04-29 15:07:48,909 INFO [train.py:763] (2/8) Epoch 18, batch 4450, loss[loss=0.1563, simple_loss=0.2477, pruned_loss=0.03245, over 6820.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2707, pruned_loss=0.03852, over 1407449.88 frames.], batch size: 15, lr: 4.04e-04
+2022-04-29 15:08:55,422 INFO [train.py:763] (2/8) Epoch 18, batch 4500, loss[loss=0.1861, simple_loss=0.2968, pruned_loss=0.03768, over 7151.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2718, pruned_loss=0.03888, over 1393594.58 frames.], batch size: 20, lr: 4.04e-04
+2022-04-29 15:10:01,679 INFO [train.py:763] (2/8) Epoch 18, batch 4550, loss[loss=0.1714, simple_loss=0.2678, pruned_loss=0.03751, over 6543.00 frames.], tot_loss[loss=0.175, simple_loss=0.2713, pruned_loss=0.03934, over 1365691.32 frames.], batch size: 38, lr: 4.04e-04
+2022-04-29 15:11:30,592 INFO [train.py:763] (2/8) Epoch 19, batch 0, loss[loss=0.17, simple_loss=0.2719, pruned_loss=0.03404, over 7343.00 frames.], tot_loss[loss=0.17, simple_loss=0.2719, pruned_loss=0.03404, over 7343.00 frames.], batch size: 19, lr: 3.94e-04
+2022-04-29 15:12:36,737 INFO [train.py:763] (2/8) Epoch 19, batch 50, loss[loss=0.1392, simple_loss=0.2416, pruned_loss=0.01843, over 7272.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2736, pruned_loss=0.03851, over 320731.24 frames.], batch size: 18, lr: 3.94e-04
+2022-04-29 15:13:42,677 INFO [train.py:763] (2/8) Epoch 19, batch 100, loss[loss=0.2111, simple_loss=0.2969, pruned_loss=0.06268, over 5071.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2715, pruned_loss=0.03758, over 565507.96 frames.], batch size: 52, lr: 3.94e-04
+2022-04-29 15:14:48,876 INFO [train.py:763] (2/8) Epoch 19, batch 150, loss[loss=0.1714, simple_loss=0.2864, pruned_loss=0.02827, over 7311.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2732, pruned_loss=0.03755, over 755650.97 frames.], batch size: 21, lr: 3.94e-04
+2022-04-29 15:15:54,339 INFO [train.py:763] (2/8) Epoch 19, batch 200, loss[loss=0.1619, simple_loss=0.2638, pruned_loss=0.03003, over 7337.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2725, pruned_loss=0.03706, over 902379.85 frames.], batch size: 22, lr: 3.93e-04
+2022-04-29 15:17:00,297 INFO [train.py:763] (2/8) Epoch 19, batch 250, loss[loss=0.1929, simple_loss=0.2942, pruned_loss=0.04581, over 7342.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2713, pruned_loss=0.03715, over 1021558.96 frames.], batch size: 22, lr: 3.93e-04
+2022-04-29 15:18:06,647 INFO [train.py:763] (2/8) Epoch 19, batch 300, loss[loss=0.1668, simple_loss=0.2671, pruned_loss=0.0332, over 7197.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2718, pruned_loss=0.03716, over 1111343.10 frames.], batch size: 23, lr: 3.93e-04
+2022-04-29 15:19:12,751 INFO [train.py:763] (2/8) Epoch 19, batch 350, loss[loss=0.1823, simple_loss=0.2795, pruned_loss=0.04253, over 7149.00 frames.], tot_loss[loss=0.1732, simple_loss=0.272, pruned_loss=0.03717, over 1184135.47 frames.], batch size: 20, lr: 3.93e-04
+2022-04-29 15:20:18,120 INFO [train.py:763] (2/8) Epoch 19, batch 400, loss[loss=0.1973, simple_loss=0.2942, pruned_loss=0.05014, over 7144.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2732, pruned_loss=0.03764, over 1237299.54 frames.], batch size: 20, lr: 3.93e-04
+2022-04-29 15:21:23,454 INFO [train.py:763] (2/8) Epoch 19, batch 450, loss[loss=0.1907, simple_loss=0.2999, pruned_loss=0.04077, over 7380.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2735, pruned_loss=0.03782, over 1273659.39 frames.], batch size: 23, lr: 3.93e-04
+2022-04-29 15:22:28,663 INFO [train.py:763] (2/8) Epoch 19, batch 500, loss[loss=0.1744, simple_loss=0.2698, pruned_loss=0.03947, over 7225.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2735, pruned_loss=0.03785, over 1305776.87 frames.], batch size: 21, lr: 3.93e-04
+2022-04-29 15:23:34,242 INFO [train.py:763] (2/8) Epoch 19, batch 550, loss[loss=0.1609, simple_loss=0.2714, pruned_loss=0.02523, over 6729.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2727, pruned_loss=0.03744, over 1332488.24 frames.], batch size: 31, lr: 3.93e-04
+2022-04-29 15:24:40,466 INFO [train.py:763] (2/8) Epoch 19, batch 600, loss[loss=0.1318, simple_loss=0.2276, pruned_loss=0.01798, over 7152.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2706, pruned_loss=0.03683, over 1355296.20 frames.], batch size: 18, lr: 3.93e-04
+2022-04-29 15:25:45,940 INFO [train.py:763] (2/8) Epoch 19, batch 650, loss[loss=0.1985, simple_loss=0.2919, pruned_loss=0.05249, over 7154.00 frames.], tot_loss[loss=0.1724, simple_loss=0.271, pruned_loss=0.03689, over 1369991.73 frames.], batch size: 18, lr: 3.92e-04
+2022-04-29 15:26:51,168 INFO [train.py:763] (2/8) Epoch 19, batch 700, loss[loss=0.1713, simple_loss=0.2646, pruned_loss=0.03901, over 7233.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2719, pruned_loss=0.03689, over 1384029.40 frames.], batch size: 20, lr: 3.92e-04
+2022-04-29 15:27:56,781 INFO [train.py:763] (2/8) Epoch 19, batch 750, loss[loss=0.2103, simple_loss=0.3127, pruned_loss=0.05401, over 7317.00 frames.], tot_loss[loss=0.173, simple_loss=0.2717, pruned_loss=0.03713, over 1394471.22 frames.], batch size: 25, lr: 3.92e-04
+2022-04-29 15:29:03,455 INFO [train.py:763] (2/8) Epoch 19, batch 800, loss[loss=0.17, simple_loss=0.2533, pruned_loss=0.04335, over 7404.00 frames.], tot_loss[loss=0.1725, simple_loss=0.271, pruned_loss=0.03701, over 1403860.48 frames.], batch size: 18, lr: 3.92e-04
+2022-04-29 15:30:19,513 INFO [train.py:763] (2/8) Epoch 19, batch 850, loss[loss=0.193, simple_loss=0.2912, pruned_loss=0.04744, over 7070.00 frames.], tot_loss[loss=0.172, simple_loss=0.2705, pruned_loss=0.03678, over 1411158.67 frames.], batch size: 28, lr: 3.92e-04
+2022-04-29 15:31:25,287 INFO [train.py:763] (2/8) Epoch 19, batch 900, loss[loss=0.1811, simple_loss=0.2715, pruned_loss=0.04534, over 7359.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2704, pruned_loss=0.03727, over 1415756.34 frames.], batch size: 19, lr: 3.92e-04
+2022-04-29 15:32:30,745 INFO [train.py:763] (2/8) Epoch 19, batch 950, loss[loss=0.1679, simple_loss=0.2722, pruned_loss=0.03181, over 7244.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2712, pruned_loss=0.03756, over 1419117.04 frames.], batch size: 20, lr: 3.92e-04
+2022-04-29 15:33:36,031 INFO [train.py:763] (2/8) Epoch 19, batch 1000, loss[loss=0.1985, simple_loss=0.2997, pruned_loss=0.0487, over 7288.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2717, pruned_loss=0.03746, over 1420416.94 frames.], batch size: 24, lr: 3.92e-04
+2022-04-29 15:34:41,367 INFO [train.py:763] (2/8) Epoch 19, batch 1050, loss[loss=0.1964, simple_loss=0.2962, pruned_loss=0.04837, over 7196.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2711, pruned_loss=0.0372, over 1420291.90 frames.], batch size: 22, lr: 3.92e-04
+2022-04-29 15:35:47,009 INFO [train.py:763] (2/8) Epoch 19, batch 1100, loss[loss=0.193, simple_loss=0.2942, pruned_loss=0.04587, over 7193.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2709, pruned_loss=0.03728, over 1415604.70 frames.], batch size: 22, lr: 3.91e-04
+2022-04-29 15:36:52,332 INFO [train.py:763] (2/8) Epoch 19, batch 1150, loss[loss=0.1921, simple_loss=0.2914, pruned_loss=0.04638, over 7301.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2714, pruned_loss=0.03752, over 1419702.12 frames.], batch size: 24, lr: 3.91e-04
+2022-04-29 15:38:08,753 INFO [train.py:763] (2/8) Epoch 19, batch 1200, loss[loss=0.1791, simple_loss=0.2829, pruned_loss=0.03769, over 7319.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2702, pruned_loss=0.03697, over 1424963.94 frames.], batch size: 22, lr: 3.91e-04
+2022-04-29 15:39:14,188 INFO [train.py:763] (2/8) Epoch 19, batch 1250, loss[loss=0.1339, simple_loss=0.2215, pruned_loss=0.02317, over 7135.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2703, pruned_loss=0.037, over 1425272.85 frames.], batch size: 17, lr: 3.91e-04
+2022-04-29 15:40:19,872 INFO [train.py:763] (2/8) Epoch 19, batch 1300, loss[loss=0.1726, simple_loss=0.2747, pruned_loss=0.03528, over 7120.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2707, pruned_loss=0.03724, over 1427257.33 frames.], batch size: 21, lr: 3.91e-04
+2022-04-29 15:41:25,077 INFO [train.py:763] (2/8) Epoch 19, batch 1350, loss[loss=0.1685, simple_loss=0.2612, pruned_loss=0.03797, over 7196.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2715, pruned_loss=0.03748, over 1428410.62 frames.], batch size: 22, lr: 3.91e-04
+2022-04-29 15:42:30,860 INFO [train.py:763] (2/8) Epoch 19, batch 1400, loss[loss=0.1576, simple_loss=0.2567, pruned_loss=0.02921, over 7163.00 frames.], tot_loss[loss=0.173, simple_loss=0.2712, pruned_loss=0.03742, over 1430097.93 frames.], batch size: 26, lr: 3.91e-04
+2022-04-29 15:43:46,243 INFO [train.py:763] (2/8) Epoch 19, batch 1450, loss[loss=0.1931, simple_loss=0.2896, pruned_loss=0.04834, over 7196.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2717, pruned_loss=0.03773, over 1428467.82 frames.], batch size: 26, lr: 3.91e-04
+2022-04-29 15:45:09,718 INFO [train.py:763] (2/8) Epoch 19, batch 1500, loss[loss=0.2054, simple_loss=0.2972, pruned_loss=0.05682, over 7386.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2733, pruned_loss=0.03862, over 1426719.82 frames.], batch size: 23, lr: 3.91e-04
+2022-04-29 15:46:15,425 INFO [train.py:763] (2/8) Epoch 19, batch 1550, loss[loss=0.1653, simple_loss=0.2668, pruned_loss=0.03192, over 7423.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2723, pruned_loss=0.03814, over 1428681.69 frames.], batch size: 20, lr: 3.91e-04
+2022-04-29 15:47:30,074 INFO [train.py:763] (2/8) Epoch 19, batch 1600, loss[loss=0.1624, simple_loss=0.2739, pruned_loss=0.02548, over 7331.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2723, pruned_loss=0.03794, over 1423555.86 frames.], batch size: 22, lr: 3.90e-04
+2022-04-29 15:48:53,933 INFO [train.py:763] (2/8) Epoch 19, batch 1650, loss[loss=0.1628, simple_loss=0.2666, pruned_loss=0.02948, over 7185.00 frames.], tot_loss[loss=0.174, simple_loss=0.2723, pruned_loss=0.03787, over 1420481.63 frames.], batch size: 23, lr: 3.90e-04
+2022-04-29 15:50:08,825 INFO [train.py:763] (2/8) Epoch 19, batch 1700, loss[loss=0.1482, simple_loss=0.2415, pruned_loss=0.02749, over 7160.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2718, pruned_loss=0.03818, over 1420345.42 frames.], batch size: 19, lr: 3.90e-04
+2022-04-29 15:51:14,399 INFO [train.py:763] (2/8) Epoch 19, batch 1750, loss[loss=0.1542, simple_loss=0.2589, pruned_loss=0.02477, over 7326.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2716, pruned_loss=0.03798, over 1425965.59 frames.], batch size: 22, lr: 3.90e-04
+2022-04-29 15:52:19,997 INFO [train.py:763] (2/8) Epoch 19, batch 1800, loss[loss=0.1729, simple_loss=0.2765, pruned_loss=0.03467, over 7301.00 frames.], tot_loss[loss=0.173, simple_loss=0.2712, pruned_loss=0.03743, over 1424807.72 frames.], batch size: 25, lr: 3.90e-04
+2022-04-29 15:53:25,555 INFO [train.py:763] (2/8) Epoch 19, batch 1850, loss[loss=0.1604, simple_loss=0.2544, pruned_loss=0.03318, over 7082.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2713, pruned_loss=0.0375, over 1428348.35 frames.], batch size: 18, lr: 3.90e-04
+2022-04-29 15:54:30,869 INFO [train.py:763] (2/8) Epoch 19, batch 1900, loss[loss=0.1713, simple_loss=0.2718, pruned_loss=0.03545, over 7233.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2712, pruned_loss=0.03727, over 1428879.53 frames.], batch size: 20, lr: 3.90e-04
+2022-04-29 15:55:38,243 INFO [train.py:763] (2/8) Epoch 19, batch 1950, loss[loss=0.1861, simple_loss=0.2817, pruned_loss=0.0452, over 6303.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2699, pruned_loss=0.03715, over 1428785.46 frames.], batch size: 37, lr: 3.90e-04
+2022-04-29 15:56:45,556 INFO [train.py:763] (2/8) Epoch 19, batch 2000, loss[loss=0.1659, simple_loss=0.2738, pruned_loss=0.02903, over 7236.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2689, pruned_loss=0.03687, over 1429462.61 frames.], batch size: 20, lr: 3.90e-04
+2022-04-29 15:57:52,835 INFO [train.py:763] (2/8) Epoch 19, batch 2050, loss[loss=0.1582, simple_loss=0.2655, pruned_loss=0.02542, over 7218.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2682, pruned_loss=0.03683, over 1428974.84 frames.], batch size: 21, lr: 3.89e-04
+2022-04-29 15:58:58,690 INFO [train.py:763] (2/8) Epoch 19, batch 2100, loss[loss=0.1625, simple_loss=0.2682, pruned_loss=0.0284, over 7443.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2677, pruned_loss=0.03628, over 1431711.57 frames.], batch size: 20, lr: 3.89e-04
+2022-04-29 16:00:05,503 INFO [train.py:763] (2/8) Epoch 19, batch 2150, loss[loss=0.1743, simple_loss=0.283, pruned_loss=0.03278, over 7218.00 frames.], tot_loss[loss=0.1726, simple_loss=0.27, pruned_loss=0.03762, over 1425151.61 frames.], batch size: 22, lr: 3.89e-04
+2022-04-29 16:01:11,301 INFO [train.py:763] (2/8) Epoch 19, batch 2200, loss[loss=0.1606, simple_loss=0.2534, pruned_loss=0.03394, over 6817.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2697, pruned_loss=0.03764, over 1420709.60 frames.], batch size: 15, lr: 3.89e-04
+2022-04-29 16:02:17,294 INFO [train.py:763] (2/8) Epoch 19, batch 2250, loss[loss=0.2017, simple_loss=0.2982, pruned_loss=0.05257, over 7151.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2698, pruned_loss=0.03799, over 1422868.58 frames.], batch size: 20, lr: 3.89e-04
+2022-04-29 16:03:23,074 INFO [train.py:763] (2/8) Epoch 19, batch 2300, loss[loss=0.1912, simple_loss=0.2905, pruned_loss=0.04592, over 7372.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2704, pruned_loss=0.03814, over 1423065.67 frames.], batch size: 23, lr: 3.89e-04
+2022-04-29 16:04:28,766 INFO [train.py:763] (2/8) Epoch 19, batch 2350, loss[loss=0.1772, simple_loss=0.278, pruned_loss=0.03815, over 7316.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2708, pruned_loss=0.03802, over 1421827.63 frames.], batch size: 21, lr: 3.89e-04
+2022-04-29 16:05:34,122 INFO [train.py:763] (2/8) Epoch 19, batch 2400, loss[loss=0.1615, simple_loss=0.2651, pruned_loss=0.02891, over 7425.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2699, pruned_loss=0.03759, over 1423717.61 frames.], batch size: 20, lr: 3.89e-04
+2022-04-29 16:06:39,695 INFO [train.py:763] (2/8) Epoch 19, batch 2450, loss[loss=0.1774, simple_loss=0.2794, pruned_loss=0.03764, over 7102.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2692, pruned_loss=0.03725, over 1426730.03 frames.], batch size: 28, lr: 3.89e-04
+2022-04-29 16:07:45,460 INFO [train.py:763] (2/8) Epoch 19, batch 2500, loss[loss=0.178, simple_loss=0.2707, pruned_loss=0.04265, over 7166.00 frames.], tot_loss[loss=0.1718, simple_loss=0.269, pruned_loss=0.03734, over 1425006.86 frames.], batch size: 26, lr: 3.88e-04
+2022-04-29 16:08:50,993 INFO [train.py:763] (2/8) Epoch 19, batch 2550, loss[loss=0.1745, simple_loss=0.2631, pruned_loss=0.04298, over 7328.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2684, pruned_loss=0.03718, over 1424053.18 frames.], batch size: 20, lr: 3.88e-04
+2022-04-29 16:09:56,807 INFO [train.py:763] (2/8) Epoch 19, batch 2600, loss[loss=0.1872, simple_loss=0.2855, pruned_loss=0.0445, over 6785.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2695, pruned_loss=0.03765, over 1424818.55 frames.], batch size: 31, lr: 3.88e-04
+2022-04-29 16:11:03,363 INFO [train.py:763] (2/8) Epoch 19, batch 2650, loss[loss=0.1575, simple_loss=0.255, pruned_loss=0.02997, over 6987.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2691, pruned_loss=0.03751, over 1426052.91 frames.], batch size: 16, lr: 3.88e-04
+2022-04-29 16:12:10,009 INFO [train.py:763] (2/8) Epoch 19, batch 2700, loss[loss=0.1838, simple_loss=0.2702, pruned_loss=0.04865, over 7385.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2691, pruned_loss=0.03752, over 1427405.50 frames.], batch size: 23, lr: 3.88e-04
+2022-04-29 16:13:17,136 INFO [train.py:763] (2/8) Epoch 19, batch 2750, loss[loss=0.1782, simple_loss=0.2852, pruned_loss=0.03567, over 7224.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2696, pruned_loss=0.03734, over 1425682.19 frames.], batch size: 23, lr: 3.88e-04
+2022-04-29 16:14:22,704 INFO [train.py:763] (2/8) Epoch 19, batch 2800, loss[loss=0.1572, simple_loss=0.2456, pruned_loss=0.03435, over 7171.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2703, pruned_loss=0.0372, over 1429452.77 frames.], batch size: 18, lr: 3.88e-04
+2022-04-29 16:15:28,759 INFO [train.py:763] (2/8) Epoch 19, batch 2850, loss[loss=0.185, simple_loss=0.2907, pruned_loss=0.03967, over 7408.00 frames.], tot_loss[loss=0.1723, simple_loss=0.27, pruned_loss=0.03725, over 1431183.34 frames.], batch size: 21, lr: 3.88e-04
+2022-04-29 16:16:34,844 INFO [train.py:763] (2/8) Epoch 19, batch 2900, loss[loss=0.1689, simple_loss=0.2753, pruned_loss=0.0313, over 7171.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2698, pruned_loss=0.0372, over 1426320.48 frames.], batch size: 26, lr: 3.88e-04
+2022-04-29 16:17:40,407 INFO [train.py:763] (2/8) Epoch 19, batch 2950, loss[loss=0.1596, simple_loss=0.2651, pruned_loss=0.02707, over 7240.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2707, pruned_loss=0.03725, over 1430445.77 frames.], batch size: 20, lr: 3.87e-04
+2022-04-29 16:18:45,954 INFO [train.py:763] (2/8) Epoch 19, batch 3000, loss[loss=0.2288, simple_loss=0.3314, pruned_loss=0.06315, over 7386.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2715, pruned_loss=0.0376, over 1429904.35 frames.], batch size: 23, lr: 3.87e-04
+2022-04-29 16:18:45,954 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 16:19:01,554 INFO [train.py:792] (2/8) Epoch 19, validation: loss=0.1668, simple_loss=0.2663, pruned_loss=0.03363, over 698248.00 frames.
+2022-04-29 16:20:06,918 INFO [train.py:763] (2/8) Epoch 19, batch 3050, loss[loss=0.1774, simple_loss=0.2762, pruned_loss=0.0393, over 7161.00 frames.], tot_loss[loss=0.1731, simple_loss=0.271, pruned_loss=0.03763, over 1431513.88 frames.], batch size: 19, lr: 3.87e-04
+2022-04-29 16:21:12,180 INFO [train.py:763] (2/8) Epoch 19, batch 3100, loss[loss=0.1814, simple_loss=0.2778, pruned_loss=0.04255, over 7118.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2715, pruned_loss=0.03748, over 1430462.99 frames.], batch size: 21, lr: 3.87e-04
+2022-04-29 16:22:17,530 INFO [train.py:763] (2/8) Epoch 19, batch 3150, loss[loss=0.1347, simple_loss=0.2287, pruned_loss=0.02032, over 7259.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2708, pruned_loss=0.03707, over 1431466.42 frames.], batch size: 18, lr: 3.87e-04
+2022-04-29 16:23:23,019 INFO [train.py:763] (2/8) Epoch 19, batch 3200, loss[loss=0.1825, simple_loss=0.2855, pruned_loss=0.03969, over 6739.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2694, pruned_loss=0.03669, over 1431032.98 frames.], batch size: 31, lr: 3.87e-04
+2022-04-29 16:24:28,064 INFO [train.py:763] (2/8) Epoch 19, batch 3250, loss[loss=0.1671, simple_loss=0.2637, pruned_loss=0.03522, over 7063.00 frames.], tot_loss[loss=0.1717, simple_loss=0.27, pruned_loss=0.0367, over 1427874.01 frames.], batch size: 18, lr: 3.87e-04
+2022-04-29 16:25:34,717 INFO [train.py:763] (2/8) Epoch 19, batch 3300, loss[loss=0.1445, simple_loss=0.2365, pruned_loss=0.02625, over 7135.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2701, pruned_loss=0.03683, over 1426188.71 frames.], batch size: 17, lr: 3.87e-04
+2022-04-29 16:26:41,781 INFO [train.py:763] (2/8) Epoch 19, batch 3350, loss[loss=0.1693, simple_loss=0.2761, pruned_loss=0.03128, over 7142.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2702, pruned_loss=0.03711, over 1426362.51 frames.], batch size: 20, lr: 3.87e-04
+2022-04-29 16:27:47,540 INFO [train.py:763] (2/8) Epoch 19, batch 3400, loss[loss=0.1495, simple_loss=0.2464, pruned_loss=0.0263, over 7272.00 frames.], tot_loss[loss=0.1718, simple_loss=0.27, pruned_loss=0.03682, over 1425569.40 frames.], batch size: 17, lr: 3.87e-04
+2022-04-29 16:28:53,013 INFO [train.py:763] (2/8) Epoch 19, batch 3450, loss[loss=0.1732, simple_loss=0.2753, pruned_loss=0.03555, over 7229.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2705, pruned_loss=0.03728, over 1424390.08 frames.], batch size: 20, lr: 3.86e-04
+2022-04-29 16:29:58,520 INFO [train.py:763] (2/8) Epoch 19, batch 3500, loss[loss=0.1877, simple_loss=0.2828, pruned_loss=0.04632, over 7251.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2697, pruned_loss=0.03682, over 1423753.72 frames.], batch size: 19, lr: 3.86e-04
+2022-04-29 16:31:03,657 INFO [train.py:763] (2/8) Epoch 19, batch 3550, loss[loss=0.1813, simple_loss=0.2797, pruned_loss=0.04151, over 7119.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2704, pruned_loss=0.03708, over 1426492.39 frames.], batch size: 21, lr: 3.86e-04
+2022-04-29 16:32:09,188 INFO [train.py:763] (2/8) Epoch 19, batch 3600, loss[loss=0.1718, simple_loss=0.2709, pruned_loss=0.03639, over 7204.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2703, pruned_loss=0.03723, over 1429520.13 frames.], batch size: 23, lr: 3.86e-04
+2022-04-29 16:33:15,435 INFO [train.py:763] (2/8) Epoch 19, batch 3650, loss[loss=0.1794, simple_loss=0.2728, pruned_loss=0.04298, over 7320.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2703, pruned_loss=0.03703, over 1429558.38 frames.], batch size: 21, lr: 3.86e-04
+2022-04-29 16:34:21,093 INFO [train.py:763] (2/8) Epoch 19, batch 3700, loss[loss=0.1569, simple_loss=0.2415, pruned_loss=0.03616, over 7160.00 frames.], tot_loss[loss=0.172, simple_loss=0.2701, pruned_loss=0.03695, over 1431764.41 frames.], batch size: 18, lr: 3.86e-04
+2022-04-29 16:35:26,768 INFO [train.py:763] (2/8) Epoch 19, batch 3750, loss[loss=0.197, simple_loss=0.3008, pruned_loss=0.04662, over 7100.00 frames.], tot_loss[loss=0.1721, simple_loss=0.27, pruned_loss=0.03713, over 1426751.08 frames.], batch size: 28, lr: 3.86e-04
+2022-04-29 16:36:32,304 INFO [train.py:763] (2/8) Epoch 19, batch 3800, loss[loss=0.1793, simple_loss=0.271, pruned_loss=0.04378, over 7332.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2699, pruned_loss=0.03732, over 1421405.73 frames.], batch size: 20, lr: 3.86e-04
+2022-04-29 16:37:37,904 INFO [train.py:763] (2/8) Epoch 19, batch 3850, loss[loss=0.1541, simple_loss=0.2503, pruned_loss=0.02895, over 7269.00 frames.], tot_loss[loss=0.172, simple_loss=0.2699, pruned_loss=0.03711, over 1419352.27 frames.], batch size: 17, lr: 3.86e-04
+2022-04-29 16:38:44,163 INFO [train.py:763] (2/8) Epoch 19, batch 3900, loss[loss=0.1598, simple_loss=0.2627, pruned_loss=0.02849, over 7106.00 frames.], tot_loss[loss=0.172, simple_loss=0.2702, pruned_loss=0.03691, over 1416535.90 frames.], batch size: 21, lr: 3.85e-04
+2022-04-29 16:39:50,746 INFO [train.py:763] (2/8) Epoch 19, batch 3950, loss[loss=0.1484, simple_loss=0.2463, pruned_loss=0.02524, over 7328.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2699, pruned_loss=0.03712, over 1411390.25 frames.], batch size: 20, lr: 3.85e-04
+2022-04-29 16:40:57,110 INFO [train.py:763] (2/8) Epoch 19, batch 4000, loss[loss=0.155, simple_loss=0.2493, pruned_loss=0.03035, over 7159.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2697, pruned_loss=0.03737, over 1409021.47 frames.], batch size: 18, lr: 3.85e-04
+2022-04-29 16:42:03,324 INFO [train.py:763] (2/8) Epoch 19, batch 4050, loss[loss=0.179, simple_loss=0.2801, pruned_loss=0.03901, over 7325.00 frames.], tot_loss[loss=0.1725, simple_loss=0.27, pruned_loss=0.03752, over 1406633.73 frames.], batch size: 20, lr: 3.85e-04
+2022-04-29 16:43:09,189 INFO [train.py:763] (2/8) Epoch 19, batch 4100, loss[loss=0.1722, simple_loss=0.2738, pruned_loss=0.03527, over 7283.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2685, pruned_loss=0.03683, over 1407046.77 frames.], batch size: 18, lr: 3.85e-04
+2022-04-29 16:44:14,858 INFO [train.py:763] (2/8) Epoch 19, batch 4150, loss[loss=0.1674, simple_loss=0.256, pruned_loss=0.03941, over 7066.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2673, pruned_loss=0.03654, over 1410867.33 frames.], batch size: 18, lr: 3.85e-04
+2022-04-29 16:45:20,202 INFO [train.py:763] (2/8) Epoch 19, batch 4200, loss[loss=0.1725, simple_loss=0.263, pruned_loss=0.04104, over 7198.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2686, pruned_loss=0.03724, over 1404931.70 frames.], batch size: 16, lr: 3.85e-04
+2022-04-29 16:46:26,000 INFO [train.py:763] (2/8) Epoch 19, batch 4250, loss[loss=0.1914, simple_loss=0.298, pruned_loss=0.04241, over 7210.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2679, pruned_loss=0.03699, over 1403370.72 frames.], batch size: 23, lr: 3.85e-04
+2022-04-29 16:47:31,497 INFO [train.py:763] (2/8) Epoch 19, batch 4300, loss[loss=0.1752, simple_loss=0.2766, pruned_loss=0.03689, over 7230.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2689, pruned_loss=0.03732, over 1400879.59 frames.], batch size: 21, lr: 3.85e-04
+2022-04-29 16:48:37,206 INFO [train.py:763] (2/8) Epoch 19, batch 4350, loss[loss=0.2035, simple_loss=0.2968, pruned_loss=0.05511, over 5259.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2676, pruned_loss=0.03691, over 1404183.64 frames.], batch size: 52, lr: 3.84e-04
+2022-04-29 16:49:42,591 INFO [train.py:763] (2/8) Epoch 19, batch 4400, loss[loss=0.222, simple_loss=0.3094, pruned_loss=0.06735, over 7162.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2685, pruned_loss=0.03755, over 1399642.35 frames.], batch size: 19, lr: 3.84e-04
+2022-04-29 16:50:47,786 INFO [train.py:763] (2/8) Epoch 19, batch 4450, loss[loss=0.1409, simple_loss=0.2322, pruned_loss=0.02474, over 6805.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2685, pruned_loss=0.03748, over 1389279.94 frames.], batch size: 15, lr: 3.84e-04
+2022-04-29 16:51:52,272 INFO [train.py:763] (2/8) Epoch 19, batch 4500, loss[loss=0.1944, simple_loss=0.2932, pruned_loss=0.04776, over 7198.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2699, pruned_loss=0.03791, over 1382226.63 frames.], batch size: 23, lr: 3.84e-04
+2022-04-29 16:52:57,054 INFO [train.py:763] (2/8) Epoch 19, batch 4550, loss[loss=0.1895, simple_loss=0.2892, pruned_loss=0.04492, over 6440.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2729, pruned_loss=0.03993, over 1338652.39 frames.], batch size: 38, lr: 3.84e-04
+2022-04-29 16:54:25,842 INFO [train.py:763] (2/8) Epoch 20, batch 0, loss[loss=0.1907, simple_loss=0.2687, pruned_loss=0.05633, over 6981.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2687, pruned_loss=0.05633, over 6981.00 frames.], batch size: 16, lr: 3.75e-04
+2022-04-29 16:55:32,591 INFO [train.py:763] (2/8) Epoch 20, batch 50, loss[loss=0.2095, simple_loss=0.3058, pruned_loss=0.05655, over 6452.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2744, pruned_loss=0.03927, over 323056.04 frames.], batch size: 37, lr: 3.75e-04
+2022-04-29 16:56:38,000 INFO [train.py:763] (2/8) Epoch 20, batch 100, loss[loss=0.1799, simple_loss=0.2607, pruned_loss=0.04953, over 7250.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2736, pruned_loss=0.03851, over 567426.72 frames.], batch size: 16, lr: 3.75e-04
+2022-04-29 16:57:44,560 INFO [train.py:763] (2/8) Epoch 20, batch 150, loss[loss=0.16, simple_loss=0.2593, pruned_loss=0.03036, over 7156.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2703, pruned_loss=0.03636, over 755990.98 frames.], batch size: 18, lr: 3.75e-04
+2022-04-29 16:58:49,749 INFO [train.py:763] (2/8) Epoch 20, batch 200, loss[loss=0.1698, simple_loss=0.2751, pruned_loss=0.03224, over 6787.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2708, pruned_loss=0.03669, over 900868.19 frames.], batch size: 31, lr: 3.75e-04
+2022-04-29 16:59:55,577 INFO [train.py:763] (2/8) Epoch 20, batch 250, loss[loss=0.1724, simple_loss=0.271, pruned_loss=0.03691, over 7161.00 frames.], tot_loss[loss=0.1717, simple_loss=0.27, pruned_loss=0.03671, over 1012139.89 frames.], batch size: 19, lr: 3.75e-04
+2022-04-29 17:01:00,761 INFO [train.py:763] (2/8) Epoch 20, batch 300, loss[loss=0.1457, simple_loss=0.2418, pruned_loss=0.0248, over 7286.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2702, pruned_loss=0.03667, over 1101552.24 frames.], batch size: 18, lr: 3.75e-04
+2022-04-29 17:02:05,605 INFO [train.py:763] (2/8) Epoch 20, batch 350, loss[loss=0.1406, simple_loss=0.2411, pruned_loss=0.0201, over 7263.00 frames.], tot_loss[loss=0.1712, simple_loss=0.27, pruned_loss=0.03616, over 1170182.21 frames.], batch size: 19, lr: 3.74e-04
+2022-04-29 17:03:10,955 INFO [train.py:763] (2/8) Epoch 20, batch 400, loss[loss=0.175, simple_loss=0.2764, pruned_loss=0.03677, over 7063.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2701, pruned_loss=0.03628, over 1230009.85 frames.], batch size: 18, lr: 3.74e-04
+2022-04-29 17:04:16,932 INFO [train.py:763] (2/8) Epoch 20, batch 450, loss[loss=0.1767, simple_loss=0.2767, pruned_loss=0.03839, over 7056.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2702, pruned_loss=0.03643, over 1273257.60 frames.], batch size: 18, lr: 3.74e-04
+2022-04-29 17:05:22,372 INFO [train.py:763] (2/8) Epoch 20, batch 500, loss[loss=0.1915, simple_loss=0.2829, pruned_loss=0.05004, over 7068.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2702, pruned_loss=0.03657, over 1312121.07 frames.], batch size: 28, lr: 3.74e-04
+2022-04-29 17:06:27,713 INFO [train.py:763] (2/8) Epoch 20, batch 550, loss[loss=0.1603, simple_loss=0.2391, pruned_loss=0.04068, over 7179.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2689, pruned_loss=0.03623, over 1337865.91 frames.], batch size: 16, lr: 3.74e-04
+2022-04-29 17:07:34,453 INFO [train.py:763] (2/8) Epoch 20, batch 600, loss[loss=0.185, simple_loss=0.2953, pruned_loss=0.03735, over 7201.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2698, pruned_loss=0.03645, over 1355731.41 frames.], batch size: 22, lr: 3.74e-04
+2022-04-29 17:08:41,617 INFO [train.py:763] (2/8) Epoch 20, batch 650, loss[loss=0.1468, simple_loss=0.2421, pruned_loss=0.02575, over 7121.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2686, pruned_loss=0.03626, over 1370629.84 frames.], batch size: 17, lr: 3.74e-04
+2022-04-29 17:09:47,491 INFO [train.py:763] (2/8) Epoch 20, batch 700, loss[loss=0.1746, simple_loss=0.2802, pruned_loss=0.03456, over 7232.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2694, pruned_loss=0.03643, over 1380313.21 frames.], batch size: 20, lr: 3.74e-04
+2022-04-29 17:10:53,616 INFO [train.py:763] (2/8) Epoch 20, batch 750, loss[loss=0.1573, simple_loss=0.2464, pruned_loss=0.03413, over 7411.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2698, pruned_loss=0.03692, over 1385421.36 frames.], batch size: 18, lr: 3.74e-04
+2022-04-29 17:11:58,915 INFO [train.py:763] (2/8) Epoch 20, batch 800, loss[loss=0.1601, simple_loss=0.2633, pruned_loss=0.02842, over 7233.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2697, pruned_loss=0.03693, over 1384509.20 frames.], batch size: 20, lr: 3.73e-04
+2022-04-29 17:13:05,455 INFO [train.py:763] (2/8) Epoch 20, batch 850, loss[loss=0.1801, simple_loss=0.2785, pruned_loss=0.04082, over 7316.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2691, pruned_loss=0.03702, over 1390316.10 frames.], batch size: 25, lr: 3.73e-04
+2022-04-29 17:14:10,904 INFO [train.py:763] (2/8) Epoch 20, batch 900, loss[loss=0.1731, simple_loss=0.2728, pruned_loss=0.03672, over 7227.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2687, pruned_loss=0.03686, over 1399755.85 frames.], batch size: 20, lr: 3.73e-04
+2022-04-29 17:15:15,944 INFO [train.py:763] (2/8) Epoch 20, batch 950, loss[loss=0.1613, simple_loss=0.2643, pruned_loss=0.02912, over 7326.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2694, pruned_loss=0.03689, over 1405739.93 frames.], batch size: 22, lr: 3.73e-04
+2022-04-29 17:16:21,948 INFO [train.py:763] (2/8) Epoch 20, batch 1000, loss[loss=0.2015, simple_loss=0.2988, pruned_loss=0.05206, over 7199.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2706, pruned_loss=0.03752, over 1405071.15 frames.], batch size: 23, lr: 3.73e-04
+2022-04-29 17:17:26,875 INFO [train.py:763] (2/8) Epoch 20, batch 1050, loss[loss=0.1807, simple_loss=0.2847, pruned_loss=0.03839, over 7410.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2713, pruned_loss=0.03751, over 1406235.61 frames.], batch size: 21, lr: 3.73e-04
+2022-04-29 17:18:32,318 INFO [train.py:763] (2/8) Epoch 20, batch 1100, loss[loss=0.1469, simple_loss=0.2457, pruned_loss=0.02402, over 6879.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2695, pruned_loss=0.03697, over 1407483.85 frames.], batch size: 15, lr: 3.73e-04
+2022-04-29 17:19:37,612 INFO [train.py:763] (2/8) Epoch 20, batch 1150, loss[loss=0.1583, simple_loss=0.2476, pruned_loss=0.03443, over 7286.00 frames.], tot_loss[loss=0.1714, simple_loss=0.269, pruned_loss=0.03686, over 1413213.01 frames.], batch size: 24, lr: 3.73e-04
+2022-04-29 17:20:42,596 INFO [train.py:763] (2/8) Epoch 20, batch 1200, loss[loss=0.1375, simple_loss=0.2329, pruned_loss=0.02111, over 7276.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2699, pruned_loss=0.03676, over 1415172.63 frames.], batch size: 18, lr: 3.73e-04
+2022-04-29 17:21:47,929 INFO [train.py:763] (2/8) Epoch 20, batch 1250, loss[loss=0.1911, simple_loss=0.2932, pruned_loss=0.04452, over 7301.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2691, pruned_loss=0.0364, over 1417322.13 frames.], batch size: 24, lr: 3.73e-04
+2022-04-29 17:22:53,223 INFO [train.py:763] (2/8) Epoch 20, batch 1300, loss[loss=0.1463, simple_loss=0.2495, pruned_loss=0.02155, over 7068.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2681, pruned_loss=0.03634, over 1415974.18 frames.], batch size: 18, lr: 3.72e-04
+2022-04-29 17:23:59,017 INFO [train.py:763] (2/8) Epoch 20, batch 1350, loss[loss=0.1834, simple_loss=0.2948, pruned_loss=0.03601, over 7336.00 frames.], tot_loss[loss=0.17, simple_loss=0.2675, pruned_loss=0.03623, over 1422997.42 frames.], batch size: 22, lr: 3.72e-04
+2022-04-29 17:25:04,571 INFO [train.py:763] (2/8) Epoch 20, batch 1400, loss[loss=0.191, simple_loss=0.2887, pruned_loss=0.04668, over 7370.00 frames.], tot_loss[loss=0.1705, simple_loss=0.268, pruned_loss=0.03647, over 1425628.27 frames.], batch size: 23, lr: 3.72e-04
+2022-04-29 17:26:11,035 INFO [train.py:763] (2/8) Epoch 20, batch 1450, loss[loss=0.1844, simple_loss=0.2819, pruned_loss=0.04343, over 4835.00 frames.], tot_loss[loss=0.17, simple_loss=0.2674, pruned_loss=0.03633, over 1419744.26 frames.], batch size: 52, lr: 3.72e-04
+2022-04-29 17:27:17,681 INFO [train.py:763] (2/8) Epoch 20, batch 1500, loss[loss=0.1766, simple_loss=0.2829, pruned_loss=0.03518, over 7325.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2682, pruned_loss=0.0362, over 1417865.09 frames.], batch size: 22, lr: 3.72e-04
+2022-04-29 17:28:24,674 INFO [train.py:763] (2/8) Epoch 20, batch 1550, loss[loss=0.1769, simple_loss=0.2674, pruned_loss=0.04326, over 6957.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2689, pruned_loss=0.03664, over 1420128.30 frames.], batch size: 32, lr: 3.72e-04
+2022-04-29 17:29:31,790 INFO [train.py:763] (2/8) Epoch 20, batch 1600, loss[loss=0.1696, simple_loss=0.2696, pruned_loss=0.03477, over 7321.00 frames.], tot_loss[loss=0.1707, simple_loss=0.269, pruned_loss=0.03623, over 1421054.31 frames.], batch size: 22, lr: 3.72e-04
+2022-04-29 17:30:38,859 INFO [train.py:763] (2/8) Epoch 20, batch 1650, loss[loss=0.1712, simple_loss=0.2803, pruned_loss=0.03102, over 7342.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2698, pruned_loss=0.03679, over 1421949.14 frames.], batch size: 20, lr: 3.72e-04
+2022-04-29 17:31:46,135 INFO [train.py:763] (2/8) Epoch 20, batch 1700, loss[loss=0.1922, simple_loss=0.2968, pruned_loss=0.04378, over 7345.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2684, pruned_loss=0.03616, over 1421915.06 frames.], batch size: 22, lr: 3.72e-04
+2022-04-29 17:32:52,729 INFO [train.py:763] (2/8) Epoch 20, batch 1750, loss[loss=0.1198, simple_loss=0.2204, pruned_loss=0.009591, over 7416.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2691, pruned_loss=0.0365, over 1422631.30 frames.], batch size: 18, lr: 3.72e-04
+2022-04-29 17:33:59,654 INFO [train.py:763] (2/8) Epoch 20, batch 1800, loss[loss=0.1835, simple_loss=0.2865, pruned_loss=0.04022, over 7210.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2693, pruned_loss=0.03661, over 1424154.79 frames.], batch size: 23, lr: 3.71e-04
+2022-04-29 17:35:06,941 INFO [train.py:763] (2/8) Epoch 20, batch 1850, loss[loss=0.1254, simple_loss=0.209, pruned_loss=0.02092, over 7416.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2696, pruned_loss=0.03715, over 1423024.48 frames.], batch size: 18, lr: 3.71e-04
+2022-04-29 17:36:12,556 INFO [train.py:763] (2/8) Epoch 20, batch 1900, loss[loss=0.1586, simple_loss=0.2518, pruned_loss=0.03271, over 7162.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2689, pruned_loss=0.03674, over 1424559.58 frames.], batch size: 19, lr: 3.71e-04
+2022-04-29 17:37:18,015 INFO [train.py:763] (2/8) Epoch 20, batch 1950, loss[loss=0.1605, simple_loss=0.2647, pruned_loss=0.02818, over 7261.00 frames.], tot_loss[loss=0.171, simple_loss=0.2689, pruned_loss=0.03653, over 1428130.20 frames.], batch size: 19, lr: 3.71e-04
+2022-04-29 17:38:24,300 INFO [train.py:763] (2/8) Epoch 20, batch 2000, loss[loss=0.1644, simple_loss=0.2647, pruned_loss=0.03205, over 6821.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2681, pruned_loss=0.03618, over 1424705.33 frames.], batch size: 31, lr: 3.71e-04
+2022-04-29 17:39:29,412 INFO [train.py:763] (2/8) Epoch 20, batch 2050, loss[loss=0.1549, simple_loss=0.2506, pruned_loss=0.02958, over 7219.00 frames.], tot_loss[loss=0.171, simple_loss=0.2685, pruned_loss=0.03676, over 1424297.22 frames.], batch size: 21, lr: 3.71e-04
+2022-04-29 17:40:35,599 INFO [train.py:763] (2/8) Epoch 20, batch 2100, loss[loss=0.1628, simple_loss=0.2567, pruned_loss=0.03441, over 7062.00 frames.], tot_loss[loss=0.171, simple_loss=0.2687, pruned_loss=0.03663, over 1422885.62 frames.], batch size: 18, lr: 3.71e-04
+2022-04-29 17:41:42,814 INFO [train.py:763] (2/8) Epoch 20, batch 2150, loss[loss=0.1619, simple_loss=0.2471, pruned_loss=0.03831, over 7180.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2693, pruned_loss=0.03667, over 1422243.23 frames.], batch size: 16, lr: 3.71e-04
+2022-04-29 17:42:48,991 INFO [train.py:763] (2/8) Epoch 20, batch 2200, loss[loss=0.1768, simple_loss=0.2795, pruned_loss=0.037, over 7202.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2686, pruned_loss=0.03626, over 1424606.98 frames.], batch size: 22, lr: 3.71e-04
+2022-04-29 17:43:54,360 INFO [train.py:763] (2/8) Epoch 20, batch 2250, loss[loss=0.2129, simple_loss=0.3158, pruned_loss=0.05505, over 7207.00 frames.], tot_loss[loss=0.1713, simple_loss=0.269, pruned_loss=0.03676, over 1425298.59 frames.], batch size: 22, lr: 3.71e-04
+2022-04-29 17:45:01,605 INFO [train.py:763] (2/8) Epoch 20, batch 2300, loss[loss=0.2182, simple_loss=0.2955, pruned_loss=0.07048, over 5290.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2681, pruned_loss=0.03649, over 1423005.05 frames.], batch size: 53, lr: 3.71e-04
+2022-04-29 17:46:08,266 INFO [train.py:763] (2/8) Epoch 20, batch 2350, loss[loss=0.1715, simple_loss=0.2695, pruned_loss=0.03679, over 7291.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2694, pruned_loss=0.03672, over 1418258.31 frames.], batch size: 24, lr: 3.70e-04
+2022-04-29 17:47:15,535 INFO [train.py:763] (2/8) Epoch 20, batch 2400, loss[loss=0.1659, simple_loss=0.2671, pruned_loss=0.03234, over 7209.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2693, pruned_loss=0.03655, over 1420666.53 frames.], batch size: 23, lr: 3.70e-04
+2022-04-29 17:48:22,378 INFO [train.py:763] (2/8) Epoch 20, batch 2450, loss[loss=0.167, simple_loss=0.2616, pruned_loss=0.03622, over 7155.00 frames.], tot_loss[loss=0.17, simple_loss=0.2683, pruned_loss=0.03584, over 1421229.66 frames.], batch size: 19, lr: 3.70e-04
+2022-04-29 17:49:29,422 INFO [train.py:763] (2/8) Epoch 20, batch 2500, loss[loss=0.1682, simple_loss=0.2688, pruned_loss=0.03382, over 7415.00 frames.], tot_loss[loss=0.171, simple_loss=0.2691, pruned_loss=0.03645, over 1422669.56 frames.], batch size: 21, lr: 3.70e-04
+2022-04-29 17:50:36,098 INFO [train.py:763] (2/8) Epoch 20, batch 2550, loss[loss=0.2135, simple_loss=0.3005, pruned_loss=0.06325, over 5015.00 frames.], tot_loss[loss=0.172, simple_loss=0.2701, pruned_loss=0.03697, over 1420181.81 frames.], batch size: 53, lr: 3.70e-04
+2022-04-29 17:51:41,443 INFO [train.py:763] (2/8) Epoch 20, batch 2600, loss[loss=0.1686, simple_loss=0.26, pruned_loss=0.03865, over 7060.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2704, pruned_loss=0.03703, over 1421727.16 frames.], batch size: 18, lr: 3.70e-04
+2022-04-29 17:52:58,237 INFO [train.py:763] (2/8) Epoch 20, batch 2650, loss[loss=0.1664, simple_loss=0.2632, pruned_loss=0.03485, over 7334.00 frames.], tot_loss[loss=0.1732, simple_loss=0.271, pruned_loss=0.03769, over 1417789.63 frames.], batch size: 20, lr: 3.70e-04
+2022-04-29 17:54:04,060 INFO [train.py:763] (2/8) Epoch 20, batch 2700, loss[loss=0.1459, simple_loss=0.238, pruned_loss=0.02686, over 7424.00 frames.], tot_loss[loss=0.173, simple_loss=0.2709, pruned_loss=0.03753, over 1421093.34 frames.], batch size: 18, lr: 3.70e-04
+2022-04-29 17:55:10,584 INFO [train.py:763] (2/8) Epoch 20, batch 2750, loss[loss=0.1516, simple_loss=0.2532, pruned_loss=0.02498, over 7169.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2709, pruned_loss=0.03744, over 1421689.53 frames.], batch size: 18, lr: 3.70e-04
+2022-04-29 17:56:15,900 INFO [train.py:763] (2/8) Epoch 20, batch 2800, loss[loss=0.1835, simple_loss=0.2957, pruned_loss=0.03568, over 7375.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2705, pruned_loss=0.03703, over 1425342.53 frames.], batch size: 23, lr: 3.70e-04
+2022-04-29 17:57:21,234 INFO [train.py:763] (2/8) Epoch 20, batch 2850, loss[loss=0.1869, simple_loss=0.2828, pruned_loss=0.04547, over 7198.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2698, pruned_loss=0.03678, over 1420609.43 frames.], batch size: 23, lr: 3.69e-04
+2022-04-29 17:58:26,456 INFO [train.py:763] (2/8) Epoch 20, batch 2900, loss[loss=0.2001, simple_loss=0.3013, pruned_loss=0.04946, over 7096.00 frames.], tot_loss[loss=0.172, simple_loss=0.2701, pruned_loss=0.03697, over 1416867.94 frames.], batch size: 28, lr: 3.69e-04
+2022-04-29 17:59:31,727 INFO [train.py:763] (2/8) Epoch 20, batch 2950, loss[loss=0.1657, simple_loss=0.2614, pruned_loss=0.03497, over 7351.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2696, pruned_loss=0.03656, over 1415784.54 frames.], batch size: 19, lr: 3.69e-04
+2022-04-29 18:01:03,483 INFO [train.py:763] (2/8) Epoch 20, batch 3000, loss[loss=0.1726, simple_loss=0.2728, pruned_loss=0.03626, over 6631.00 frames.], tot_loss[loss=0.1717, simple_loss=0.27, pruned_loss=0.03673, over 1415022.14 frames.], batch size: 31, lr: 3.69e-04
+2022-04-29 18:01:03,484 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 18:01:18,758 INFO [train.py:792] (2/8) Epoch 20, validation: loss=0.1672, simple_loss=0.2663, pruned_loss=0.03407, over 698248.00 frames.
+2022-04-29 18:02:33,642 INFO [train.py:763] (2/8) Epoch 20, batch 3050, loss[loss=0.1491, simple_loss=0.2406, pruned_loss=0.02876, over 7271.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2699, pruned_loss=0.03671, over 1415372.11 frames.], batch size: 18, lr: 3.69e-04
+2022-04-29 18:03:49,732 INFO [train.py:763] (2/8) Epoch 20, batch 3100, loss[loss=0.1949, simple_loss=0.2866, pruned_loss=0.05157, over 7380.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2703, pruned_loss=0.03712, over 1414163.55 frames.], batch size: 23, lr: 3.69e-04
+2022-04-29 18:05:13,899 INFO [train.py:763] (2/8) Epoch 20, batch 3150, loss[loss=0.2005, simple_loss=0.3044, pruned_loss=0.04829, over 7303.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2703, pruned_loss=0.03734, over 1418589.30 frames.], batch size: 24, lr: 3.69e-04
+2022-04-29 18:06:18,920 INFO [train.py:763] (2/8) Epoch 20, batch 3200, loss[loss=0.2025, simple_loss=0.2985, pruned_loss=0.05329, over 7319.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2711, pruned_loss=0.03761, over 1422818.27 frames.], batch size: 21, lr: 3.69e-04
+2022-04-29 18:07:24,048 INFO [train.py:763] (2/8) Epoch 20, batch 3250, loss[loss=0.1584, simple_loss=0.25, pruned_loss=0.03341, over 7068.00 frames.], tot_loss[loss=0.173, simple_loss=0.271, pruned_loss=0.0375, over 1421804.25 frames.], batch size: 18, lr: 3.69e-04
+2022-04-29 18:08:29,709 INFO [train.py:763] (2/8) Epoch 20, batch 3300, loss[loss=0.1606, simple_loss=0.2578, pruned_loss=0.03168, over 7144.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2709, pruned_loss=0.03742, over 1423586.48 frames.], batch size: 17, lr: 3.69e-04
+2022-04-29 18:09:35,969 INFO [train.py:763] (2/8) Epoch 20, batch 3350, loss[loss=0.1601, simple_loss=0.2616, pruned_loss=0.02925, over 7233.00 frames.], tot_loss[loss=0.173, simple_loss=0.2708, pruned_loss=0.03758, over 1419981.16 frames.], batch size: 20, lr: 3.68e-04
+2022-04-29 18:10:42,808 INFO [train.py:763] (2/8) Epoch 20, batch 3400, loss[loss=0.182, simple_loss=0.2813, pruned_loss=0.04134, over 6497.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2705, pruned_loss=0.0375, over 1416427.21 frames.], batch size: 38, lr: 3.68e-04
+2022-04-29 18:11:49,525 INFO [train.py:763] (2/8) Epoch 20, batch 3450, loss[loss=0.1689, simple_loss=0.2873, pruned_loss=0.02524, over 7320.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2703, pruned_loss=0.03703, over 1415058.41 frames.], batch size: 21, lr: 3.68e-04
+2022-04-29 18:12:54,736 INFO [train.py:763] (2/8) Epoch 20, batch 3500, loss[loss=0.1623, simple_loss=0.2669, pruned_loss=0.02878, over 7033.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2705, pruned_loss=0.03702, over 1410666.89 frames.], batch size: 28, lr: 3.68e-04
+2022-04-29 18:14:00,241 INFO [train.py:763] (2/8) Epoch 20, batch 3550, loss[loss=0.1687, simple_loss=0.2425, pruned_loss=0.04742, over 7278.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2693, pruned_loss=0.03662, over 1414487.56 frames.], batch size: 17, lr: 3.68e-04
+2022-04-29 18:15:05,499 INFO [train.py:763] (2/8) Epoch 20, batch 3600, loss[loss=0.1763, simple_loss=0.2786, pruned_loss=0.03701, over 7379.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2705, pruned_loss=0.03714, over 1411661.26 frames.], batch size: 23, lr: 3.68e-04
+2022-04-29 18:16:10,758 INFO [train.py:763] (2/8) Epoch 20, batch 3650, loss[loss=0.1787, simple_loss=0.281, pruned_loss=0.03815, over 7138.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2708, pruned_loss=0.03717, over 1412788.34 frames.], batch size: 26, lr: 3.68e-04
+2022-04-29 18:17:15,965 INFO [train.py:763] (2/8) Epoch 20, batch 3700, loss[loss=0.1719, simple_loss=0.2716, pruned_loss=0.03605, over 7315.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2707, pruned_loss=0.03656, over 1413387.85 frames.], batch size: 21, lr: 3.68e-04
+2022-04-29 18:18:22,129 INFO [train.py:763] (2/8) Epoch 20, batch 3750, loss[loss=0.1817, simple_loss=0.2774, pruned_loss=0.04297, over 7287.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2696, pruned_loss=0.03633, over 1417109.76 frames.], batch size: 25, lr: 3.68e-04
+2022-04-29 18:19:27,280 INFO [train.py:763] (2/8) Epoch 20, batch 3800, loss[loss=0.1927, simple_loss=0.2914, pruned_loss=0.04704, over 7196.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2692, pruned_loss=0.03585, over 1417512.32 frames.], batch size: 26, lr: 3.68e-04
+2022-04-29 18:20:33,278 INFO [train.py:763] (2/8) Epoch 20, batch 3850, loss[loss=0.1577, simple_loss=0.2702, pruned_loss=0.02263, over 7329.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2694, pruned_loss=0.0355, over 1418210.64 frames.], batch size: 20, lr: 3.68e-04
+2022-04-29 18:21:38,665 INFO [train.py:763] (2/8) Epoch 20, batch 3900, loss[loss=0.1671, simple_loss=0.2577, pruned_loss=0.03822, over 7244.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2694, pruned_loss=0.03543, over 1421605.57 frames.], batch size: 19, lr: 3.67e-04
+2022-04-29 18:22:44,409 INFO [train.py:763] (2/8) Epoch 20, batch 3950, loss[loss=0.1481, simple_loss=0.2397, pruned_loss=0.02821, over 7399.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2704, pruned_loss=0.03591, over 1416566.79 frames.], batch size: 18, lr: 3.67e-04
+2022-04-29 18:23:51,280 INFO [train.py:763] (2/8) Epoch 20, batch 4000, loss[loss=0.1592, simple_loss=0.2464, pruned_loss=0.03598, over 7359.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2705, pruned_loss=0.03606, over 1421209.93 frames.], batch size: 19, lr: 3.67e-04
+2022-04-29 18:24:58,612 INFO [train.py:763] (2/8) Epoch 20, batch 4050, loss[loss=0.2382, simple_loss=0.3262, pruned_loss=0.07514, over 5472.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2696, pruned_loss=0.03572, over 1419143.91 frames.], batch size: 54, lr: 3.67e-04
+2022-04-29 18:26:05,421 INFO [train.py:763] (2/8) Epoch 20, batch 4100, loss[loss=0.1677, simple_loss=0.2722, pruned_loss=0.03156, over 7216.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2705, pruned_loss=0.03624, over 1411650.88 frames.], batch size: 21, lr: 3.67e-04
+2022-04-29 18:27:10,990 INFO [train.py:763] (2/8) Epoch 20, batch 4150, loss[loss=0.1732, simple_loss=0.2822, pruned_loss=0.03211, over 7071.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2712, pruned_loss=0.03657, over 1412555.47 frames.], batch size: 18, lr: 3.67e-04
+2022-04-29 18:28:16,323 INFO [train.py:763] (2/8) Epoch 20, batch 4200, loss[loss=0.1517, simple_loss=0.2615, pruned_loss=0.02096, over 6674.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2715, pruned_loss=0.03653, over 1411638.43 frames.], batch size: 31, lr: 3.67e-04
+2022-04-29 18:29:32,304 INFO [train.py:763] (2/8) Epoch 20, batch 4250, loss[loss=0.1753, simple_loss=0.2813, pruned_loss=0.03466, over 7227.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2693, pruned_loss=0.03556, over 1416211.12 frames.], batch size: 21, lr: 3.67e-04
+2022-04-29 18:30:38,988 INFO [train.py:763] (2/8) Epoch 20, batch 4300, loss[loss=0.1622, simple_loss=0.27, pruned_loss=0.02718, over 7289.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2687, pruned_loss=0.03554, over 1416603.75 frames.], batch size: 24, lr: 3.67e-04
+2022-04-29 18:31:45,006 INFO [train.py:763] (2/8) Epoch 20, batch 4350, loss[loss=0.1641, simple_loss=0.2677, pruned_loss=0.03029, over 7224.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2682, pruned_loss=0.03525, over 1417038.39 frames.], batch size: 21, lr: 3.67e-04
+2022-04-29 18:32:52,212 INFO [train.py:763] (2/8) Epoch 20, batch 4400, loss[loss=0.1765, simple_loss=0.2713, pruned_loss=0.04084, over 7163.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2688, pruned_loss=0.0357, over 1415743.24 frames.], batch size: 18, lr: 3.66e-04
+2022-04-29 18:33:58,453 INFO [train.py:763] (2/8) Epoch 20, batch 4450, loss[loss=0.169, simple_loss=0.2515, pruned_loss=0.04322, over 7421.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2686, pruned_loss=0.03593, over 1408495.72 frames.], batch size: 17, lr: 3.66e-04
+2022-04-29 18:35:05,721 INFO [train.py:763] (2/8) Epoch 20, batch 4500, loss[loss=0.1693, simple_loss=0.2525, pruned_loss=0.04301, over 7014.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2687, pruned_loss=0.03582, over 1410335.99 frames.], batch size: 16, lr: 3.66e-04
+2022-04-29 18:36:13,268 INFO [train.py:763] (2/8) Epoch 20, batch 4550, loss[loss=0.1769, simple_loss=0.2692, pruned_loss=0.04233, over 4868.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2683, pruned_loss=0.03603, over 1394290.35 frames.], batch size: 52, lr: 3.66e-04
+2022-04-29 18:37:42,386 INFO [train.py:763] (2/8) Epoch 21, batch 0, loss[loss=0.1937, simple_loss=0.2984, pruned_loss=0.04453, over 7293.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2984, pruned_loss=0.04453, over 7293.00 frames.], batch size: 25, lr: 3.58e-04
+2022-04-29 18:38:48,205 INFO [train.py:763] (2/8) Epoch 21, batch 50, loss[loss=0.1686, simple_loss=0.265, pruned_loss=0.03613, over 7144.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2699, pruned_loss=0.03677, over 318718.45 frames.], batch size: 18, lr: 3.58e-04
+2022-04-29 18:39:53,569 INFO [train.py:763] (2/8) Epoch 21, batch 100, loss[loss=0.165, simple_loss=0.2613, pruned_loss=0.03432, over 7117.00 frames.], tot_loss[loss=0.1705, simple_loss=0.269, pruned_loss=0.03602, over 563949.99 frames.], batch size: 21, lr: 3.58e-04
+2022-04-29 18:41:00,339 INFO [train.py:763] (2/8) Epoch 21, batch 150, loss[loss=0.1494, simple_loss=0.2562, pruned_loss=0.02136, over 7325.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2689, pruned_loss=0.03535, over 754010.75 frames.], batch size: 21, lr: 3.58e-04
+2022-04-29 18:42:07,755 INFO [train.py:763] (2/8) Epoch 21, batch 200, loss[loss=0.1779, simple_loss=0.2827, pruned_loss=0.03654, over 7328.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2698, pruned_loss=0.03604, over 901696.41 frames.], batch size: 22, lr: 3.58e-04
+2022-04-29 18:43:14,297 INFO [train.py:763] (2/8) Epoch 21, batch 250, loss[loss=0.1538, simple_loss=0.2506, pruned_loss=0.02847, over 7251.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2697, pruned_loss=0.03601, over 1015037.87 frames.], batch size: 19, lr: 3.57e-04
+2022-04-29 18:44:19,570 INFO [train.py:763] (2/8) Epoch 21, batch 300, loss[loss=0.1774, simple_loss=0.2714, pruned_loss=0.04172, over 7232.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2694, pruned_loss=0.03581, over 1107665.66 frames.], batch size: 20, lr: 3.57e-04
+2022-04-29 18:45:25,080 INFO [train.py:763] (2/8) Epoch 21, batch 350, loss[loss=0.1689, simple_loss=0.2725, pruned_loss=0.03262, over 7147.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2686, pruned_loss=0.03557, over 1179177.12 frames.], batch size: 19, lr: 3.57e-04
+2022-04-29 18:46:30,616 INFO [train.py:763] (2/8) Epoch 21, batch 400, loss[loss=0.1868, simple_loss=0.2953, pruned_loss=0.03914, over 7219.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2689, pruned_loss=0.03561, over 1231931.19 frames.], batch size: 21, lr: 3.57e-04
+2022-04-29 18:47:36,039 INFO [train.py:763] (2/8) Epoch 21, batch 450, loss[loss=0.2034, simple_loss=0.301, pruned_loss=0.05289, over 4911.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2685, pruned_loss=0.03537, over 1274373.67 frames.], batch size: 52, lr: 3.57e-04
+2022-04-29 18:48:41,846 INFO [train.py:763] (2/8) Epoch 21, batch 500, loss[loss=0.1897, simple_loss=0.2942, pruned_loss=0.04262, over 7310.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2698, pruned_loss=0.03555, over 1309731.07 frames.], batch size: 25, lr: 3.57e-04
+2022-04-29 18:49:47,433 INFO [train.py:763] (2/8) Epoch 21, batch 550, loss[loss=0.1463, simple_loss=0.2499, pruned_loss=0.0214, over 7439.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2703, pruned_loss=0.03544, over 1332852.60 frames.], batch size: 20, lr: 3.57e-04
+2022-04-29 18:50:53,638 INFO [train.py:763] (2/8) Epoch 21, batch 600, loss[loss=0.1827, simple_loss=0.2837, pruned_loss=0.04089, over 7320.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2682, pruned_loss=0.0352, over 1354020.71 frames.], batch size: 22, lr: 3.57e-04
+2022-04-29 18:51:58,876 INFO [train.py:763] (2/8) Epoch 21, batch 650, loss[loss=0.1616, simple_loss=0.268, pruned_loss=0.02763, over 7328.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2691, pruned_loss=0.03542, over 1369357.43 frames.], batch size: 22, lr: 3.57e-04
+2022-04-29 18:53:04,510 INFO [train.py:763] (2/8) Epoch 21, batch 700, loss[loss=0.1851, simple_loss=0.2831, pruned_loss=0.0436, over 7286.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2685, pruned_loss=0.03546, over 1377795.80 frames.], batch size: 25, lr: 3.57e-04
+2022-04-29 18:54:10,367 INFO [train.py:763] (2/8) Epoch 21, batch 750, loss[loss=0.2003, simple_loss=0.2918, pruned_loss=0.05444, over 7158.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2679, pruned_loss=0.03564, over 1386069.31 frames.], batch size: 18, lr: 3.57e-04
+2022-04-29 18:55:16,596 INFO [train.py:763] (2/8) Epoch 21, batch 800, loss[loss=0.1872, simple_loss=0.2863, pruned_loss=0.04404, over 7274.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2688, pruned_loss=0.03585, over 1398392.31 frames.], batch size: 25, lr: 3.56e-04
+2022-04-29 18:56:22,302 INFO [train.py:763] (2/8) Epoch 21, batch 850, loss[loss=0.1754, simple_loss=0.2688, pruned_loss=0.041, over 7404.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2681, pruned_loss=0.03534, over 1404072.90 frames.], batch size: 18, lr: 3.56e-04
+2022-04-29 18:57:27,449 INFO [train.py:763] (2/8) Epoch 21, batch 900, loss[loss=0.1575, simple_loss=0.2486, pruned_loss=0.03321, over 6370.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2677, pruned_loss=0.03535, over 1407566.78 frames.], batch size: 37, lr: 3.56e-04
+2022-04-29 18:58:32,833 INFO [train.py:763] (2/8) Epoch 21, batch 950, loss[loss=0.1499, simple_loss=0.2324, pruned_loss=0.03371, over 7281.00 frames.], tot_loss[loss=0.169, simple_loss=0.2675, pruned_loss=0.03526, over 1410039.67 frames.], batch size: 18, lr: 3.56e-04
+2022-04-29 18:59:38,147 INFO [train.py:763] (2/8) Epoch 21, batch 1000, loss[loss=0.1688, simple_loss=0.2617, pruned_loss=0.03791, over 7172.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2694, pruned_loss=0.03598, over 1410518.03 frames.], batch size: 19, lr: 3.56e-04
+2022-04-29 19:00:44,770 INFO [train.py:763] (2/8) Epoch 21, batch 1050, loss[loss=0.1759, simple_loss=0.2781, pruned_loss=0.03683, over 7325.00 frames.], tot_loss[loss=0.17, simple_loss=0.2686, pruned_loss=0.03568, over 1414489.65 frames.], batch size: 22, lr: 3.56e-04
+2022-04-29 19:01:50,752 INFO [train.py:763] (2/8) Epoch 21, batch 1100, loss[loss=0.1752, simple_loss=0.2775, pruned_loss=0.03643, over 6380.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2685, pruned_loss=0.03589, over 1418205.44 frames.], batch size: 38, lr: 3.56e-04
+2022-04-29 19:02:56,399 INFO [train.py:763] (2/8) Epoch 21, batch 1150, loss[loss=0.1475, simple_loss=0.2402, pruned_loss=0.02736, over 7262.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2681, pruned_loss=0.03559, over 1419852.36 frames.], batch size: 19, lr: 3.56e-04
+2022-04-29 19:04:02,096 INFO [train.py:763] (2/8) Epoch 21, batch 1200, loss[loss=0.1739, simple_loss=0.2753, pruned_loss=0.03628, over 7306.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2676, pruned_loss=0.03576, over 1420664.98 frames.], batch size: 25, lr: 3.56e-04
+2022-04-29 19:05:07,720 INFO [train.py:763] (2/8) Epoch 21, batch 1250, loss[loss=0.1529, simple_loss=0.2338, pruned_loss=0.03603, over 7018.00 frames.], tot_loss[loss=0.1691, simple_loss=0.267, pruned_loss=0.03559, over 1420523.47 frames.], batch size: 16, lr: 3.56e-04
+2022-04-29 19:06:13,269 INFO [train.py:763] (2/8) Epoch 21, batch 1300, loss[loss=0.16, simple_loss=0.2648, pruned_loss=0.02756, over 7156.00 frames.], tot_loss[loss=0.1692, simple_loss=0.267, pruned_loss=0.03573, over 1418862.39 frames.], batch size: 19, lr: 3.56e-04
+2022-04-29 19:07:19,445 INFO [train.py:763] (2/8) Epoch 21, batch 1350, loss[loss=0.1598, simple_loss=0.2622, pruned_loss=0.02869, over 7413.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2671, pruned_loss=0.03602, over 1423257.66 frames.], batch size: 21, lr: 3.55e-04
+2022-04-29 19:08:24,892 INFO [train.py:763] (2/8) Epoch 21, batch 1400, loss[loss=0.1862, simple_loss=0.2903, pruned_loss=0.04105, over 7211.00 frames.], tot_loss[loss=0.169, simple_loss=0.2663, pruned_loss=0.03585, over 1420040.88 frames.], batch size: 22, lr: 3.55e-04
+2022-04-29 19:09:30,407 INFO [train.py:763] (2/8) Epoch 21, batch 1450, loss[loss=0.1655, simple_loss=0.2627, pruned_loss=0.03412, over 7424.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2669, pruned_loss=0.03599, over 1424361.07 frames.], batch size: 20, lr: 3.55e-04
+2022-04-29 19:10:36,215 INFO [train.py:763] (2/8) Epoch 21, batch 1500, loss[loss=0.1586, simple_loss=0.2565, pruned_loss=0.03037, over 7231.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2672, pruned_loss=0.03606, over 1426303.82 frames.], batch size: 20, lr: 3.55e-04
+2022-04-29 19:11:42,020 INFO [train.py:763] (2/8) Epoch 21, batch 1550, loss[loss=0.1753, simple_loss=0.2784, pruned_loss=0.03611, over 7235.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2672, pruned_loss=0.03585, over 1428926.03 frames.], batch size: 20, lr: 3.55e-04
+2022-04-29 19:12:47,945 INFO [train.py:763] (2/8) Epoch 21, batch 1600, loss[loss=0.162, simple_loss=0.2479, pruned_loss=0.03811, over 7243.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2669, pruned_loss=0.03562, over 1430368.49 frames.], batch size: 16, lr: 3.55e-04
+2022-04-29 19:13:54,881 INFO [train.py:763] (2/8) Epoch 21, batch 1650, loss[loss=0.1725, simple_loss=0.283, pruned_loss=0.03101, over 6692.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2677, pruned_loss=0.03572, over 1432060.42 frames.], batch size: 31, lr: 3.55e-04
+2022-04-29 19:15:01,796 INFO [train.py:763] (2/8) Epoch 21, batch 1700, loss[loss=0.1728, simple_loss=0.2829, pruned_loss=0.03138, over 7338.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2664, pruned_loss=0.035, over 1434602.52 frames.], batch size: 22, lr: 3.55e-04
+2022-04-29 19:16:08,175 INFO [train.py:763] (2/8) Epoch 21, batch 1750, loss[loss=0.1852, simple_loss=0.2826, pruned_loss=0.0439, over 7231.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2672, pruned_loss=0.03503, over 1433352.59 frames.], batch size: 20, lr: 3.55e-04
+2022-04-29 19:17:14,195 INFO [train.py:763] (2/8) Epoch 21, batch 1800, loss[loss=0.1604, simple_loss=0.2413, pruned_loss=0.03975, over 7292.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2661, pruned_loss=0.03507, over 1429813.03 frames.], batch size: 17, lr: 3.55e-04
+2022-04-29 19:18:19,472 INFO [train.py:763] (2/8) Epoch 21, batch 1850, loss[loss=0.1688, simple_loss=0.2779, pruned_loss=0.02986, over 6429.00 frames.], tot_loss[loss=0.168, simple_loss=0.2659, pruned_loss=0.03499, over 1426163.41 frames.], batch size: 37, lr: 3.55e-04
+2022-04-29 19:19:25,202 INFO [train.py:763] (2/8) Epoch 21, batch 1900, loss[loss=0.2098, simple_loss=0.2945, pruned_loss=0.06255, over 4908.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2665, pruned_loss=0.03528, over 1424437.60 frames.], batch size: 54, lr: 3.54e-04
+2022-04-29 19:20:31,904 INFO [train.py:763] (2/8) Epoch 21, batch 1950, loss[loss=0.1773, simple_loss=0.265, pruned_loss=0.04477, over 7268.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2668, pruned_loss=0.03539, over 1425141.68 frames.], batch size: 17, lr: 3.54e-04
+2022-04-29 19:21:37,657 INFO [train.py:763] (2/8) Epoch 21, batch 2000, loss[loss=0.1868, simple_loss=0.2871, pruned_loss=0.04329, over 7329.00 frames.], tot_loss[loss=0.169, simple_loss=0.2673, pruned_loss=0.03532, over 1427775.82 frames.], batch size: 20, lr: 3.54e-04
+2022-04-29 19:22:44,040 INFO [train.py:763] (2/8) Epoch 21, batch 2050, loss[loss=0.1703, simple_loss=0.2633, pruned_loss=0.03867, over 7271.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2687, pruned_loss=0.03606, over 1428756.73 frames.], batch size: 17, lr: 3.54e-04
+2022-04-29 19:23:50,501 INFO [train.py:763] (2/8) Epoch 21, batch 2100, loss[loss=0.1387, simple_loss=0.236, pruned_loss=0.0207, over 7425.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2688, pruned_loss=0.0361, over 1427609.02 frames.], batch size: 18, lr: 3.54e-04
+2022-04-29 19:24:56,266 INFO [train.py:763] (2/8) Epoch 21, batch 2150, loss[loss=0.1576, simple_loss=0.2523, pruned_loss=0.03142, over 7161.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2684, pruned_loss=0.03609, over 1423559.87 frames.], batch size: 18, lr: 3.54e-04
+2022-04-29 19:26:02,247 INFO [train.py:763] (2/8) Epoch 21, batch 2200, loss[loss=0.1715, simple_loss=0.2828, pruned_loss=0.03012, over 7124.00 frames.], tot_loss[loss=0.1699, simple_loss=0.268, pruned_loss=0.03584, over 1426782.48 frames.], batch size: 21, lr: 3.54e-04
+2022-04-29 19:27:08,590 INFO [train.py:763] (2/8) Epoch 21, batch 2250, loss[loss=0.1495, simple_loss=0.2373, pruned_loss=0.03089, over 7259.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2684, pruned_loss=0.03586, over 1424279.73 frames.], batch size: 16, lr: 3.54e-04
+2022-04-29 19:28:14,980 INFO [train.py:763] (2/8) Epoch 21, batch 2300, loss[loss=0.2277, simple_loss=0.3079, pruned_loss=0.0737, over 5149.00 frames.], tot_loss[loss=0.171, simple_loss=0.2694, pruned_loss=0.03634, over 1425288.58 frames.], batch size: 52, lr: 3.54e-04
+2022-04-29 19:29:21,489 INFO [train.py:763] (2/8) Epoch 21, batch 2350, loss[loss=0.1695, simple_loss=0.2764, pruned_loss=0.03126, over 6503.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2686, pruned_loss=0.03596, over 1427846.38 frames.], batch size: 38, lr: 3.54e-04
+2022-04-29 19:30:28,260 INFO [train.py:763] (2/8) Epoch 21, batch 2400, loss[loss=0.1508, simple_loss=0.244, pruned_loss=0.0288, over 7146.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2682, pruned_loss=0.03643, over 1426924.79 frames.], batch size: 17, lr: 3.54e-04
+2022-04-29 19:31:33,880 INFO [train.py:763] (2/8) Epoch 21, batch 2450, loss[loss=0.1498, simple_loss=0.2467, pruned_loss=0.02642, over 7270.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2681, pruned_loss=0.03646, over 1425011.38 frames.], batch size: 17, lr: 3.54e-04
+2022-04-29 19:32:39,516 INFO [train.py:763] (2/8) Epoch 21, batch 2500, loss[loss=0.16, simple_loss=0.2596, pruned_loss=0.03022, over 7417.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2679, pruned_loss=0.0364, over 1422401.23 frames.], batch size: 21, lr: 3.53e-04
+2022-04-29 19:33:46,124 INFO [train.py:763] (2/8) Epoch 21, batch 2550, loss[loss=0.1753, simple_loss=0.2628, pruned_loss=0.04391, over 7451.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2681, pruned_loss=0.03633, over 1421200.60 frames.], batch size: 19, lr: 3.53e-04
+2022-04-29 19:34:52,129 INFO [train.py:763] (2/8) Epoch 21, batch 2600, loss[loss=0.1695, simple_loss=0.2728, pruned_loss=0.0331, over 7154.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2696, pruned_loss=0.03674, over 1418060.97 frames.], batch size: 19, lr: 3.53e-04
+2022-04-29 19:35:58,114 INFO [train.py:763] (2/8) Epoch 21, batch 2650, loss[loss=0.1658, simple_loss=0.2555, pruned_loss=0.03805, over 7255.00 frames.], tot_loss[loss=0.1703, simple_loss=0.268, pruned_loss=0.03629, over 1422244.49 frames.], batch size: 19, lr: 3.53e-04
+2022-04-29 19:37:03,414 INFO [train.py:763] (2/8) Epoch 21, batch 2700, loss[loss=0.1565, simple_loss=0.2414, pruned_loss=0.03577, over 7159.00 frames.], tot_loss[loss=0.1702, simple_loss=0.268, pruned_loss=0.03619, over 1420592.66 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:38:08,435 INFO [train.py:763] (2/8) Epoch 21, batch 2750, loss[loss=0.1416, simple_loss=0.2429, pruned_loss=0.02012, over 7062.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2676, pruned_loss=0.03573, over 1420027.71 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:39:13,883 INFO [train.py:763] (2/8) Epoch 21, batch 2800, loss[loss=0.1617, simple_loss=0.2603, pruned_loss=0.03157, over 7273.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2669, pruned_loss=0.03516, over 1420764.36 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:40:19,365 INFO [train.py:763] (2/8) Epoch 21, batch 2850, loss[loss=0.1596, simple_loss=0.2608, pruned_loss=0.02918, over 7156.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2669, pruned_loss=0.03544, over 1418727.74 frames.], batch size: 19, lr: 3.53e-04
+2022-04-29 19:41:24,552 INFO [train.py:763] (2/8) Epoch 21, batch 2900, loss[loss=0.1791, simple_loss=0.2703, pruned_loss=0.04393, over 7154.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2672, pruned_loss=0.03513, over 1421594.08 frames.], batch size: 19, lr: 3.53e-04
+2022-04-29 19:42:30,253 INFO [train.py:763] (2/8) Epoch 21, batch 2950, loss[loss=0.1786, simple_loss=0.2748, pruned_loss=0.04115, over 7402.00 frames.], tot_loss[loss=0.169, simple_loss=0.267, pruned_loss=0.03545, over 1421525.00 frames.], batch size: 21, lr: 3.53e-04
+2022-04-29 19:43:36,680 INFO [train.py:763] (2/8) Epoch 21, batch 3000, loss[loss=0.1566, simple_loss=0.2526, pruned_loss=0.0303, over 7169.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2676, pruned_loss=0.03546, over 1425663.16 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:43:36,682 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 19:43:52,055 INFO [train.py:792] (2/8) Epoch 21, validation: loss=0.1676, simple_loss=0.2672, pruned_loss=0.03398, over 698248.00 frames.
+2022-04-29 19:44:57,936 INFO [train.py:763] (2/8) Epoch 21, batch 3050, loss[loss=0.1842, simple_loss=0.2767, pruned_loss=0.04584, over 7148.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2677, pruned_loss=0.03576, over 1427380.28 frames.], batch size: 28, lr: 3.52e-04
+2022-04-29 19:46:03,952 INFO [train.py:763] (2/8) Epoch 21, batch 3100, loss[loss=0.1824, simple_loss=0.278, pruned_loss=0.04346, over 5072.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2676, pruned_loss=0.03605, over 1427359.63 frames.], batch size: 52, lr: 3.52e-04
+2022-04-29 19:47:10,165 INFO [train.py:763] (2/8) Epoch 21, batch 3150, loss[loss=0.1763, simple_loss=0.2805, pruned_loss=0.03605, over 7419.00 frames.], tot_loss[loss=0.1691, simple_loss=0.267, pruned_loss=0.03565, over 1424607.92 frames.], batch size: 21, lr: 3.52e-04
+2022-04-29 19:48:15,882 INFO [train.py:763] (2/8) Epoch 21, batch 3200, loss[loss=0.1535, simple_loss=0.2514, pruned_loss=0.02784, over 7066.00 frames.], tot_loss[loss=0.169, simple_loss=0.2669, pruned_loss=0.0356, over 1426367.67 frames.], batch size: 18, lr: 3.52e-04
+2022-04-29 19:49:21,825 INFO [train.py:763] (2/8) Epoch 21, batch 3250, loss[loss=0.1369, simple_loss=0.2247, pruned_loss=0.02454, over 6997.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2672, pruned_loss=0.0358, over 1427690.04 frames.], batch size: 16, lr: 3.52e-04
+2022-04-29 19:50:27,762 INFO [train.py:763] (2/8) Epoch 21, batch 3300, loss[loss=0.1877, simple_loss=0.2738, pruned_loss=0.05084, over 7426.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2688, pruned_loss=0.03603, over 1429765.59 frames.], batch size: 20, lr: 3.52e-04
+2022-04-29 19:51:34,059 INFO [train.py:763] (2/8) Epoch 21, batch 3350, loss[loss=0.1465, simple_loss=0.2401, pruned_loss=0.02647, over 7360.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2688, pruned_loss=0.03598, over 1428920.28 frames.], batch size: 19, lr: 3.52e-04
+2022-04-29 19:52:40,197 INFO [train.py:763] (2/8) Epoch 21, batch 3400, loss[loss=0.1604, simple_loss=0.2552, pruned_loss=0.03285, over 7149.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2692, pruned_loss=0.03629, over 1426254.52 frames.], batch size: 17, lr: 3.52e-04
+2022-04-29 19:53:45,690 INFO [train.py:763] (2/8) Epoch 21, batch 3450, loss[loss=0.1615, simple_loss=0.2693, pruned_loss=0.02689, over 7343.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2694, pruned_loss=0.03636, over 1427781.63 frames.], batch size: 22, lr: 3.52e-04
+2022-04-29 19:54:51,958 INFO [train.py:763] (2/8) Epoch 21, batch 3500, loss[loss=0.1785, simple_loss=0.2804, pruned_loss=0.0383, over 7330.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2701, pruned_loss=0.0365, over 1429729.19 frames.], batch size: 22, lr: 3.52e-04
+2022-04-29 19:55:58,075 INFO [train.py:763] (2/8) Epoch 21, batch 3550, loss[loss=0.1792, simple_loss=0.2857, pruned_loss=0.03628, over 6887.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2711, pruned_loss=0.03682, over 1428020.13 frames.], batch size: 31, lr: 3.52e-04
+2022-04-29 19:57:04,812 INFO [train.py:763] (2/8) Epoch 21, batch 3600, loss[loss=0.1492, simple_loss=0.2361, pruned_loss=0.03111, over 7282.00 frames.], tot_loss[loss=0.172, simple_loss=0.2704, pruned_loss=0.03681, over 1422186.25 frames.], batch size: 17, lr: 3.51e-04
+2022-04-29 19:58:10,360 INFO [train.py:763] (2/8) Epoch 21, batch 3650, loss[loss=0.1823, simple_loss=0.2831, pruned_loss=0.04073, over 7369.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2699, pruned_loss=0.03669, over 1424622.07 frames.], batch size: 23, lr: 3.51e-04
+2022-04-29 19:59:15,681 INFO [train.py:763] (2/8) Epoch 21, batch 3700, loss[loss=0.1733, simple_loss=0.2644, pruned_loss=0.04106, over 7233.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2695, pruned_loss=0.03632, over 1426327.51 frames.], batch size: 21, lr: 3.51e-04
+2022-04-29 20:00:21,228 INFO [train.py:763] (2/8) Epoch 21, batch 3750, loss[loss=0.1627, simple_loss=0.2477, pruned_loss=0.03882, over 6992.00 frames.], tot_loss[loss=0.171, simple_loss=0.2696, pruned_loss=0.03617, over 1429908.59 frames.], batch size: 16, lr: 3.51e-04
+2022-04-29 20:01:26,919 INFO [train.py:763] (2/8) Epoch 21, batch 3800, loss[loss=0.2018, simple_loss=0.2897, pruned_loss=0.05702, over 5177.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2688, pruned_loss=0.0361, over 1424362.36 frames.], batch size: 52, lr: 3.51e-04
+2022-04-29 20:02:32,209 INFO [train.py:763] (2/8) Epoch 21, batch 3850, loss[loss=0.1922, simple_loss=0.2905, pruned_loss=0.04693, over 7236.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2691, pruned_loss=0.03603, over 1426256.40 frames.], batch size: 20, lr: 3.51e-04
+2022-04-29 20:03:37,824 INFO [train.py:763] (2/8) Epoch 21, batch 3900, loss[loss=0.1682, simple_loss=0.2699, pruned_loss=0.03328, over 6247.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2683, pruned_loss=0.03576, over 1426993.34 frames.], batch size: 37, lr: 3.51e-04
+2022-04-29 20:04:43,328 INFO [train.py:763] (2/8) Epoch 21, batch 3950, loss[loss=0.1391, simple_loss=0.2252, pruned_loss=0.02652, over 7291.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2675, pruned_loss=0.03552, over 1425603.47 frames.], batch size: 17, lr: 3.51e-04
+2022-04-29 20:05:50,730 INFO [train.py:763] (2/8) Epoch 21, batch 4000, loss[loss=0.1756, simple_loss=0.277, pruned_loss=0.03714, over 7320.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2682, pruned_loss=0.03568, over 1425373.95 frames.], batch size: 21, lr: 3.51e-04
+2022-04-29 20:06:57,083 INFO [train.py:763] (2/8) Epoch 21, batch 4050, loss[loss=0.152, simple_loss=0.249, pruned_loss=0.02746, over 7352.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2679, pruned_loss=0.03527, over 1423233.16 frames.], batch size: 19, lr: 3.51e-04
+2022-04-29 20:08:02,544 INFO [train.py:763] (2/8) Epoch 21, batch 4100, loss[loss=0.1728, simple_loss=0.2709, pruned_loss=0.03735, over 7328.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2682, pruned_loss=0.03541, over 1424132.47 frames.], batch size: 20, lr: 3.51e-04
+2022-04-29 20:09:08,411 INFO [train.py:763] (2/8) Epoch 21, batch 4150, loss[loss=0.149, simple_loss=0.2465, pruned_loss=0.02574, over 7057.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2678, pruned_loss=0.03531, over 1420068.59 frames.], batch size: 18, lr: 3.51e-04
+2022-04-29 20:10:23,427 INFO [train.py:763] (2/8) Epoch 21, batch 4200, loss[loss=0.1846, simple_loss=0.2834, pruned_loss=0.04288, over 7144.00 frames.], tot_loss[loss=0.17, simple_loss=0.2687, pruned_loss=0.03559, over 1415795.74 frames.], batch size: 20, lr: 3.50e-04
+2022-04-29 20:11:28,554 INFO [train.py:763] (2/8) Epoch 21, batch 4250, loss[loss=0.1862, simple_loss=0.283, pruned_loss=0.04467, over 6751.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2691, pruned_loss=0.03586, over 1408985.67 frames.], batch size: 31, lr: 3.50e-04
+2022-04-29 20:12:34,517 INFO [train.py:763] (2/8) Epoch 21, batch 4300, loss[loss=0.1664, simple_loss=0.2697, pruned_loss=0.03158, over 7290.00 frames.], tot_loss[loss=0.1699, simple_loss=0.269, pruned_loss=0.03538, over 1410871.84 frames.], batch size: 24, lr: 3.50e-04
+2022-04-29 20:13:40,097 INFO [train.py:763] (2/8) Epoch 21, batch 4350, loss[loss=0.1688, simple_loss=0.2751, pruned_loss=0.03122, over 7332.00 frames.], tot_loss[loss=0.1698, simple_loss=0.269, pruned_loss=0.03531, over 1408085.87 frames.], batch size: 22, lr: 3.50e-04
+2022-04-29 20:14:45,316 INFO [train.py:763] (2/8) Epoch 21, batch 4400, loss[loss=0.1505, simple_loss=0.2582, pruned_loss=0.02136, over 7115.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2693, pruned_loss=0.03549, over 1402614.84 frames.], batch size: 21, lr: 3.50e-04
+2022-04-29 20:15:50,786 INFO [train.py:763] (2/8) Epoch 21, batch 4450, loss[loss=0.156, simple_loss=0.2592, pruned_loss=0.02635, over 7330.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2702, pruned_loss=0.036, over 1399099.71 frames.], batch size: 22, lr: 3.50e-04
+2022-04-29 20:17:22,856 INFO [train.py:763] (2/8) Epoch 21, batch 4500, loss[loss=0.1746, simple_loss=0.2829, pruned_loss=0.03317, over 7070.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2718, pruned_loss=0.03731, over 1388281.83 frames.], batch size: 28, lr: 3.50e-04
+2022-04-29 20:18:27,308 INFO [train.py:763] (2/8) Epoch 21, batch 4550, loss[loss=0.2089, simple_loss=0.302, pruned_loss=0.0579, over 5144.00 frames.], tot_loss[loss=0.1756, simple_loss=0.274, pruned_loss=0.03861, over 1345959.36 frames.], batch size: 52, lr: 3.50e-04
+2022-04-29 20:20:15,476 INFO [train.py:763] (2/8) Epoch 22, batch 0, loss[loss=0.1599, simple_loss=0.2464, pruned_loss=0.03669, over 6785.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2464, pruned_loss=0.03669, over 6785.00 frames.], batch size: 15, lr: 3.42e-04
+2022-04-29 20:21:30,523 INFO [train.py:763] (2/8) Epoch 22, batch 50, loss[loss=0.1789, simple_loss=0.2697, pruned_loss=0.04404, over 7153.00 frames.], tot_loss[loss=0.1682, simple_loss=0.265, pruned_loss=0.03576, over 319404.32 frames.], batch size: 19, lr: 3.42e-04
+2022-04-29 20:22:35,940 INFO [train.py:763] (2/8) Epoch 22, batch 100, loss[loss=0.1516, simple_loss=0.2395, pruned_loss=0.0319, over 7275.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2674, pruned_loss=0.03564, over 566472.78 frames.], batch size: 18, lr: 3.42e-04
+2022-04-29 20:23:41,419 INFO [train.py:763] (2/8) Epoch 22, batch 150, loss[loss=0.148, simple_loss=0.2496, pruned_loss=0.02316, over 7301.00 frames.], tot_loss[loss=0.1697, simple_loss=0.269, pruned_loss=0.03515, over 754125.23 frames.], batch size: 24, lr: 3.42e-04
+2022-04-29 20:24:46,880 INFO [train.py:763] (2/8) Epoch 22, batch 200, loss[loss=0.1679, simple_loss=0.2658, pruned_loss=0.03505, over 6234.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2686, pruned_loss=0.0355, over 901963.27 frames.], batch size: 38, lr: 3.42e-04
+2022-04-29 20:25:52,440 INFO [train.py:763] (2/8) Epoch 22, batch 250, loss[loss=0.1877, simple_loss=0.2921, pruned_loss=0.04163, over 7197.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2679, pruned_loss=0.03493, over 1017584.02 frames.], batch size: 23, lr: 3.42e-04
+2022-04-29 20:26:58,031 INFO [train.py:763] (2/8) Epoch 22, batch 300, loss[loss=0.1574, simple_loss=0.2552, pruned_loss=0.02984, over 7157.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2669, pruned_loss=0.03459, over 1103154.98 frames.], batch size: 19, lr: 3.42e-04
+2022-04-29 20:28:05,351 INFO [train.py:763] (2/8) Epoch 22, batch 350, loss[loss=0.1781, simple_loss=0.2791, pruned_loss=0.03858, over 7337.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2659, pruned_loss=0.03426, over 1177903.52 frames.], batch size: 22, lr: 3.42e-04
+2022-04-29 20:29:12,803 INFO [train.py:763] (2/8) Epoch 22, batch 400, loss[loss=0.2155, simple_loss=0.3106, pruned_loss=0.06019, over 7204.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2659, pruned_loss=0.0345, over 1230886.07 frames.], batch size: 23, lr: 3.42e-04
+2022-04-29 20:30:18,161 INFO [train.py:763] (2/8) Epoch 22, batch 450, loss[loss=0.1986, simple_loss=0.2956, pruned_loss=0.0508, over 7277.00 frames.], tot_loss[loss=0.1686, simple_loss=0.267, pruned_loss=0.03506, over 1271896.42 frames.], batch size: 24, lr: 3.42e-04
+2022-04-29 20:31:24,302 INFO [train.py:763] (2/8) Epoch 22, batch 500, loss[loss=0.1404, simple_loss=0.2298, pruned_loss=0.02552, over 6839.00 frames.], tot_loss[loss=0.1687, simple_loss=0.267, pruned_loss=0.03518, over 1306762.45 frames.], batch size: 15, lr: 3.41e-04
+2022-04-29 20:32:31,783 INFO [train.py:763] (2/8) Epoch 22, batch 550, loss[loss=0.1791, simple_loss=0.2806, pruned_loss=0.03877, over 7290.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2667, pruned_loss=0.03512, over 1337227.38 frames.], batch size: 24, lr: 3.41e-04
+2022-04-29 20:33:39,036 INFO [train.py:763] (2/8) Epoch 22, batch 600, loss[loss=0.1541, simple_loss=0.2599, pruned_loss=0.02418, over 7129.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2677, pruned_loss=0.03538, over 1359348.15 frames.], batch size: 21, lr: 3.41e-04
+2022-04-29 20:34:44,741 INFO [train.py:763] (2/8) Epoch 22, batch 650, loss[loss=0.1578, simple_loss=0.2545, pruned_loss=0.03056, over 6809.00 frames.], tot_loss[loss=0.169, simple_loss=0.2677, pruned_loss=0.03517, over 1374507.12 frames.], batch size: 31, lr: 3.41e-04
+2022-04-29 20:35:51,881 INFO [train.py:763] (2/8) Epoch 22, batch 700, loss[loss=0.1919, simple_loss=0.2844, pruned_loss=0.04966, over 5162.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2679, pruned_loss=0.03536, over 1380531.55 frames.], batch size: 52, lr: 3.41e-04
+2022-04-29 20:36:59,159 INFO [train.py:763] (2/8) Epoch 22, batch 750, loss[loss=0.1647, simple_loss=0.2655, pruned_loss=0.03194, over 7210.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2674, pruned_loss=0.03506, over 1391783.88 frames.], batch size: 23, lr: 3.41e-04
+2022-04-29 20:38:05,930 INFO [train.py:763] (2/8) Epoch 22, batch 800, loss[loss=0.1641, simple_loss=0.2659, pruned_loss=0.0312, over 7362.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2674, pruned_loss=0.03471, over 1395401.53 frames.], batch size: 19, lr: 3.41e-04
+2022-04-29 20:39:11,693 INFO [train.py:763] (2/8) Epoch 22, batch 850, loss[loss=0.1658, simple_loss=0.2617, pruned_loss=0.03496, over 7427.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2677, pruned_loss=0.03482, over 1403942.74 frames.], batch size: 20, lr: 3.41e-04
+2022-04-29 20:40:16,909 INFO [train.py:763] (2/8) Epoch 22, batch 900, loss[loss=0.1497, simple_loss=0.2584, pruned_loss=0.02046, over 7163.00 frames.], tot_loss[loss=0.169, simple_loss=0.2679, pruned_loss=0.03504, over 1408107.86 frames.], batch size: 19, lr: 3.41e-04
+2022-04-29 20:41:22,119 INFO [train.py:763] (2/8) Epoch 22, batch 950, loss[loss=0.1686, simple_loss=0.2729, pruned_loss=0.0321, over 7140.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2684, pruned_loss=0.03535, over 1410449.13 frames.], batch size: 28, lr: 3.41e-04
+2022-04-29 20:42:27,342 INFO [train.py:763] (2/8) Epoch 22, batch 1000, loss[loss=0.1623, simple_loss=0.2652, pruned_loss=0.02971, over 7351.00 frames.], tot_loss[loss=0.1699, simple_loss=0.269, pruned_loss=0.03536, over 1417638.49 frames.], batch size: 19, lr: 3.41e-04
+2022-04-29 20:43:32,803 INFO [train.py:763] (2/8) Epoch 22, batch 1050, loss[loss=0.1727, simple_loss=0.2808, pruned_loss=0.03229, over 5005.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2689, pruned_loss=0.0358, over 1418269.47 frames.], batch size: 52, lr: 3.41e-04
+2022-04-29 20:44:37,786 INFO [train.py:763] (2/8) Epoch 22, batch 1100, loss[loss=0.1616, simple_loss=0.255, pruned_loss=0.03404, over 7274.00 frames.], tot_loss[loss=0.171, simple_loss=0.27, pruned_loss=0.03605, over 1418700.63 frames.], batch size: 17, lr: 3.40e-04
+2022-04-29 20:45:43,152 INFO [train.py:763] (2/8) Epoch 22, batch 1150, loss[loss=0.1727, simple_loss=0.271, pruned_loss=0.03723, over 7433.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2706, pruned_loss=0.03626, over 1422120.79 frames.], batch size: 20, lr: 3.40e-04
+2022-04-29 20:46:49,109 INFO [train.py:763] (2/8) Epoch 22, batch 1200, loss[loss=0.1663, simple_loss=0.263, pruned_loss=0.03478, over 7288.00 frames.], tot_loss[loss=0.171, simple_loss=0.2698, pruned_loss=0.03609, over 1421216.27 frames.], batch size: 18, lr: 3.40e-04
+2022-04-29 20:47:55,634 INFO [train.py:763] (2/8) Epoch 22, batch 1250, loss[loss=0.1443, simple_loss=0.2315, pruned_loss=0.02855, over 6777.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2683, pruned_loss=0.03553, over 1424183.81 frames.], batch size: 15, lr: 3.40e-04
+2022-04-29 20:49:00,847 INFO [train.py:763] (2/8) Epoch 22, batch 1300, loss[loss=0.1868, simple_loss=0.2889, pruned_loss=0.04237, over 7189.00 frames.], tot_loss[loss=0.1691, simple_loss=0.268, pruned_loss=0.0351, over 1426416.53 frames.], batch size: 23, lr: 3.40e-04
+2022-04-29 20:50:07,452 INFO [train.py:763] (2/8) Epoch 22, batch 1350, loss[loss=0.1453, simple_loss=0.2393, pruned_loss=0.02562, over 7280.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2671, pruned_loss=0.03499, over 1427510.63 frames.], batch size: 18, lr: 3.40e-04
+2022-04-29 20:51:13,803 INFO [train.py:763] (2/8) Epoch 22, batch 1400, loss[loss=0.158, simple_loss=0.2638, pruned_loss=0.02607, over 7123.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2676, pruned_loss=0.03502, over 1427398.65 frames.], batch size: 21, lr: 3.40e-04
+2022-04-29 20:52:19,582 INFO [train.py:763] (2/8) Epoch 22, batch 1450, loss[loss=0.1448, simple_loss=0.2338, pruned_loss=0.02796, over 7417.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2675, pruned_loss=0.03497, over 1421483.01 frames.], batch size: 18, lr: 3.40e-04
+2022-04-29 20:53:25,449 INFO [train.py:763] (2/8) Epoch 22, batch 1500, loss[loss=0.1829, simple_loss=0.2864, pruned_loss=0.0397, over 7061.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2666, pruned_loss=0.03505, over 1423914.38 frames.], batch size: 28, lr: 3.40e-04
+2022-04-29 20:54:31,377 INFO [train.py:763] (2/8) Epoch 22, batch 1550, loss[loss=0.1517, simple_loss=0.2529, pruned_loss=0.02522, over 7359.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2672, pruned_loss=0.03507, over 1414959.33 frames.], batch size: 19, lr: 3.40e-04
+2022-04-29 20:55:37,829 INFO [train.py:763] (2/8) Epoch 22, batch 1600, loss[loss=0.1846, simple_loss=0.2926, pruned_loss=0.03833, over 7217.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2684, pruned_loss=0.03563, over 1413325.35 frames.], batch size: 21, lr: 3.40e-04
+2022-04-29 20:56:43,432 INFO [train.py:763] (2/8) Epoch 22, batch 1650, loss[loss=0.1899, simple_loss=0.294, pruned_loss=0.04295, over 7366.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2687, pruned_loss=0.03579, over 1415641.98 frames.], batch size: 23, lr: 3.40e-04
+2022-04-29 20:57:48,937 INFO [train.py:763] (2/8) Epoch 22, batch 1700, loss[loss=0.15, simple_loss=0.2454, pruned_loss=0.0273, over 7406.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2679, pruned_loss=0.03542, over 1416419.14 frames.], batch size: 18, lr: 3.39e-04
+2022-04-29 20:58:54,069 INFO [train.py:763] (2/8) Epoch 22, batch 1750, loss[loss=0.1986, simple_loss=0.294, pruned_loss=0.05165, over 7153.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2682, pruned_loss=0.03545, over 1415043.62 frames.], batch size: 26, lr: 3.39e-04
+2022-04-29 20:59:59,906 INFO [train.py:763] (2/8) Epoch 22, batch 1800, loss[loss=0.2139, simple_loss=0.3095, pruned_loss=0.0592, over 5175.00 frames.], tot_loss[loss=0.17, simple_loss=0.2685, pruned_loss=0.03574, over 1413189.17 frames.], batch size: 53, lr: 3.39e-04
+2022-04-29 21:01:05,539 INFO [train.py:763] (2/8) Epoch 22, batch 1850, loss[loss=0.167, simple_loss=0.2727, pruned_loss=0.03064, over 7433.00 frames.], tot_loss[loss=0.169, simple_loss=0.2677, pruned_loss=0.03515, over 1417862.67 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:02:10,913 INFO [train.py:763] (2/8) Epoch 22, batch 1900, loss[loss=0.1768, simple_loss=0.2837, pruned_loss=0.03495, over 7137.00 frames.], tot_loss[loss=0.1684, simple_loss=0.267, pruned_loss=0.03488, over 1420735.69 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:03:17,151 INFO [train.py:763] (2/8) Epoch 22, batch 1950, loss[loss=0.1876, simple_loss=0.3021, pruned_loss=0.03658, over 7141.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2679, pruned_loss=0.03531, over 1417683.81 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:04:22,496 INFO [train.py:763] (2/8) Epoch 22, batch 2000, loss[loss=0.178, simple_loss=0.2727, pruned_loss=0.04163, over 7258.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2686, pruned_loss=0.03551, over 1420549.93 frames.], batch size: 19, lr: 3.39e-04
+2022-04-29 21:05:28,497 INFO [train.py:763] (2/8) Epoch 22, batch 2050, loss[loss=0.178, simple_loss=0.273, pruned_loss=0.04149, over 7243.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2681, pruned_loss=0.03537, over 1425160.39 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:06:35,596 INFO [train.py:763] (2/8) Epoch 22, batch 2100, loss[loss=0.1851, simple_loss=0.2823, pruned_loss=0.0439, over 7207.00 frames.], tot_loss[loss=0.169, simple_loss=0.2675, pruned_loss=0.03528, over 1420720.54 frames.], batch size: 23, lr: 3.39e-04
+2022-04-29 21:07:42,145 INFO [train.py:763] (2/8) Epoch 22, batch 2150, loss[loss=0.158, simple_loss=0.2591, pruned_loss=0.02846, over 7158.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2674, pruned_loss=0.03519, over 1421349.19 frames.], batch size: 19, lr: 3.39e-04
+2022-04-29 21:08:47,295 INFO [train.py:763] (2/8) Epoch 22, batch 2200, loss[loss=0.1456, simple_loss=0.2437, pruned_loss=0.0237, over 7145.00 frames.], tot_loss[loss=0.169, simple_loss=0.2675, pruned_loss=0.03522, over 1416607.23 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:09:53,558 INFO [train.py:763] (2/8) Epoch 22, batch 2250, loss[loss=0.1631, simple_loss=0.259, pruned_loss=0.03365, over 7163.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2675, pruned_loss=0.03514, over 1413544.24 frames.], batch size: 19, lr: 3.39e-04
+2022-04-29 21:11:00,712 INFO [train.py:763] (2/8) Epoch 22, batch 2300, loss[loss=0.1789, simple_loss=0.2814, pruned_loss=0.03826, over 7316.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2668, pruned_loss=0.03514, over 1414332.06 frames.], batch size: 21, lr: 3.38e-04
+2022-04-29 21:12:07,636 INFO [train.py:763] (2/8) Epoch 22, batch 2350, loss[loss=0.1685, simple_loss=0.2757, pruned_loss=0.0306, over 7321.00 frames.], tot_loss[loss=0.168, simple_loss=0.2666, pruned_loss=0.03468, over 1416112.11 frames.], batch size: 22, lr: 3.38e-04
+2022-04-29 21:13:14,355 INFO [train.py:763] (2/8) Epoch 22, batch 2400, loss[loss=0.1839, simple_loss=0.2813, pruned_loss=0.04326, over 7305.00 frames.], tot_loss[loss=0.1685, simple_loss=0.267, pruned_loss=0.03502, over 1419237.13 frames.], batch size: 24, lr: 3.38e-04
+2022-04-29 21:14:19,599 INFO [train.py:763] (2/8) Epoch 22, batch 2450, loss[loss=0.1843, simple_loss=0.2796, pruned_loss=0.04452, over 7213.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2686, pruned_loss=0.03553, over 1422894.20 frames.], batch size: 22, lr: 3.38e-04
+2022-04-29 21:15:24,877 INFO [train.py:763] (2/8) Epoch 22, batch 2500, loss[loss=0.1665, simple_loss=0.2707, pruned_loss=0.0311, over 6491.00 frames.], tot_loss[loss=0.169, simple_loss=0.2676, pruned_loss=0.03525, over 1420438.91 frames.], batch size: 38, lr: 3.38e-04
+2022-04-29 21:16:30,043 INFO [train.py:763] (2/8) Epoch 22, batch 2550, loss[loss=0.1979, simple_loss=0.2963, pruned_loss=0.04974, over 7378.00 frames.], tot_loss[loss=0.169, simple_loss=0.2674, pruned_loss=0.03528, over 1421060.50 frames.], batch size: 23, lr: 3.38e-04
+2022-04-29 21:17:35,648 INFO [train.py:763] (2/8) Epoch 22, batch 2600, loss[loss=0.1682, simple_loss=0.2793, pruned_loss=0.02862, over 7339.00 frames.], tot_loss[loss=0.169, simple_loss=0.2673, pruned_loss=0.0353, over 1425275.48 frames.], batch size: 22, lr: 3.38e-04
+2022-04-29 21:18:41,154 INFO [train.py:763] (2/8) Epoch 22, batch 2650, loss[loss=0.1781, simple_loss=0.2831, pruned_loss=0.03653, over 7270.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2667, pruned_loss=0.0354, over 1423037.82 frames.], batch size: 25, lr: 3.38e-04
+2022-04-29 21:19:46,640 INFO [train.py:763] (2/8) Epoch 22, batch 2700, loss[loss=0.1877, simple_loss=0.2931, pruned_loss=0.04118, over 7161.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2676, pruned_loss=0.03585, over 1422205.52 frames.], batch size: 19, lr: 3.38e-04
+2022-04-29 21:20:54,005 INFO [train.py:763] (2/8) Epoch 22, batch 2750, loss[loss=0.1546, simple_loss=0.2447, pruned_loss=0.03223, over 7164.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2669, pruned_loss=0.03574, over 1420089.46 frames.], batch size: 18, lr: 3.38e-04
+2022-04-29 21:22:00,021 INFO [train.py:763] (2/8) Epoch 22, batch 2800, loss[loss=0.1647, simple_loss=0.2541, pruned_loss=0.03762, over 7156.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2675, pruned_loss=0.03614, over 1419449.28 frames.], batch size: 18, lr: 3.38e-04
+2022-04-29 21:23:05,435 INFO [train.py:763] (2/8) Epoch 22, batch 2850, loss[loss=0.1847, simple_loss=0.2884, pruned_loss=0.04049, over 7046.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2675, pruned_loss=0.03578, over 1421495.08 frames.], batch size: 28, lr: 3.38e-04
+2022-04-29 21:24:10,662 INFO [train.py:763] (2/8) Epoch 22, batch 2900, loss[loss=0.1732, simple_loss=0.2791, pruned_loss=0.03368, over 7308.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2683, pruned_loss=0.03596, over 1423138.14 frames.], batch size: 25, lr: 3.37e-04
+2022-04-29 21:25:15,969 INFO [train.py:763] (2/8) Epoch 22, batch 2950, loss[loss=0.1986, simple_loss=0.294, pruned_loss=0.05162, over 7198.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2685, pruned_loss=0.03592, over 1423923.69 frames.], batch size: 22, lr: 3.37e-04
+2022-04-29 21:26:20,971 INFO [train.py:763] (2/8) Epoch 22, batch 3000, loss[loss=0.138, simple_loss=0.2282, pruned_loss=0.02388, over 6995.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2688, pruned_loss=0.03591, over 1423487.89 frames.], batch size: 16, lr: 3.37e-04
+2022-04-29 21:26:20,972 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 21:26:36,379 INFO [train.py:792] (2/8) Epoch 22, validation: loss=0.1681, simple_loss=0.2667, pruned_loss=0.03474, over 698248.00 frames.
+2022-04-29 21:27:41,666 INFO [train.py:763] (2/8) Epoch 22, batch 3050, loss[loss=0.1602, simple_loss=0.2528, pruned_loss=0.03377, over 7154.00 frames.], tot_loss[loss=0.17, simple_loss=0.2686, pruned_loss=0.03567, over 1426413.72 frames.], batch size: 19, lr: 3.37e-04
+2022-04-29 21:28:58,459 INFO [train.py:763] (2/8) Epoch 22, batch 3100, loss[loss=0.1436, simple_loss=0.2481, pruned_loss=0.01952, over 7236.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2674, pruned_loss=0.03522, over 1425103.66 frames.], batch size: 20, lr: 3.37e-04
+2022-04-29 21:30:03,939 INFO [train.py:763] (2/8) Epoch 22, batch 3150, loss[loss=0.1772, simple_loss=0.2738, pruned_loss=0.04029, over 7329.00 frames.], tot_loss[loss=0.169, simple_loss=0.2674, pruned_loss=0.03531, over 1426475.76 frames.], batch size: 20, lr: 3.37e-04
+2022-04-29 21:31:09,274 INFO [train.py:763] (2/8) Epoch 22, batch 3200, loss[loss=0.1684, simple_loss=0.2742, pruned_loss=0.03131, over 7110.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2675, pruned_loss=0.03547, over 1427271.09 frames.], batch size: 21, lr: 3.37e-04
+2022-04-29 21:32:14,547 INFO [train.py:763] (2/8) Epoch 22, batch 3250, loss[loss=0.1633, simple_loss=0.266, pruned_loss=0.03026, over 6288.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2682, pruned_loss=0.03574, over 1422098.91 frames.], batch size: 37, lr: 3.37e-04
+2022-04-29 21:33:19,826 INFO [train.py:763] (2/8) Epoch 22, batch 3300, loss[loss=0.2099, simple_loss=0.3048, pruned_loss=0.05746, over 7276.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2689, pruned_loss=0.0357, over 1422421.86 frames.], batch size: 24, lr: 3.37e-04
+2022-04-29 21:34:25,355 INFO [train.py:763] (2/8) Epoch 22, batch 3350, loss[loss=0.1814, simple_loss=0.2865, pruned_loss=0.03818, over 7187.00 frames.], tot_loss[loss=0.169, simple_loss=0.2676, pruned_loss=0.03517, over 1426865.41 frames.], batch size: 26, lr: 3.37e-04
+2022-04-29 21:35:30,549 INFO [train.py:763] (2/8) Epoch 22, batch 3400, loss[loss=0.152, simple_loss=0.253, pruned_loss=0.02553, over 7149.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2676, pruned_loss=0.03536, over 1428021.22 frames.], batch size: 19, lr: 3.37e-04
+2022-04-29 21:36:36,027 INFO [train.py:763] (2/8) Epoch 22, batch 3450, loss[loss=0.1391, simple_loss=0.2229, pruned_loss=0.02762, over 6752.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2664, pruned_loss=0.035, over 1429316.05 frames.], batch size: 15, lr: 3.37e-04
+2022-04-29 21:37:41,466 INFO [train.py:763] (2/8) Epoch 22, batch 3500, loss[loss=0.1717, simple_loss=0.2615, pruned_loss=0.04097, over 6798.00 frames.], tot_loss[loss=0.1687, simple_loss=0.267, pruned_loss=0.03521, over 1430253.27 frames.], batch size: 15, lr: 3.37e-04
+2022-04-29 21:38:46,760 INFO [train.py:763] (2/8) Epoch 22, batch 3550, loss[loss=0.1609, simple_loss=0.2529, pruned_loss=0.03448, over 7411.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2664, pruned_loss=0.03511, over 1429452.25 frames.], batch size: 18, lr: 3.36e-04
+2022-04-29 21:39:52,001 INFO [train.py:763] (2/8) Epoch 22, batch 3600, loss[loss=0.1527, simple_loss=0.2446, pruned_loss=0.03036, over 7286.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2672, pruned_loss=0.035, over 1430891.92 frames.], batch size: 17, lr: 3.36e-04
+2022-04-29 21:40:57,414 INFO [train.py:763] (2/8) Epoch 22, batch 3650, loss[loss=0.1784, simple_loss=0.2911, pruned_loss=0.03283, over 6503.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2663, pruned_loss=0.03435, over 1431014.07 frames.], batch size: 38, lr: 3.36e-04
+2022-04-29 21:42:03,750 INFO [train.py:763] (2/8) Epoch 22, batch 3700, loss[loss=0.1585, simple_loss=0.2565, pruned_loss=0.03024, over 7153.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2669, pruned_loss=0.03431, over 1430014.31 frames.], batch size: 19, lr: 3.36e-04
+2022-04-29 21:43:09,189 INFO [train.py:763] (2/8) Epoch 22, batch 3750, loss[loss=0.1375, simple_loss=0.2248, pruned_loss=0.02516, over 7279.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2676, pruned_loss=0.03465, over 1427368.14 frames.], batch size: 17, lr: 3.36e-04
+2022-04-29 21:44:14,437 INFO [train.py:763] (2/8) Epoch 22, batch 3800, loss[loss=0.1911, simple_loss=0.2972, pruned_loss=0.04251, over 7388.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2678, pruned_loss=0.03469, over 1428912.41 frames.], batch size: 23, lr: 3.36e-04
+2022-04-29 21:45:19,888 INFO [train.py:763] (2/8) Epoch 22, batch 3850, loss[loss=0.1809, simple_loss=0.2786, pruned_loss=0.04156, over 7030.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2677, pruned_loss=0.0346, over 1429280.42 frames.], batch size: 28, lr: 3.36e-04
+2022-04-29 21:46:26,370 INFO [train.py:763] (2/8) Epoch 22, batch 3900, loss[loss=0.1917, simple_loss=0.2947, pruned_loss=0.04436, over 7117.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2673, pruned_loss=0.03478, over 1429671.96 frames.], batch size: 21, lr: 3.36e-04
+2022-04-29 21:47:31,490 INFO [train.py:763] (2/8) Epoch 22, batch 3950, loss[loss=0.1508, simple_loss=0.249, pruned_loss=0.02635, over 7168.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2673, pruned_loss=0.03472, over 1428988.95 frames.], batch size: 19, lr: 3.36e-04
+2022-04-29 21:48:36,595 INFO [train.py:763] (2/8) Epoch 22, batch 4000, loss[loss=0.1351, simple_loss=0.2315, pruned_loss=0.01931, over 7305.00 frames.], tot_loss[loss=0.168, simple_loss=0.2665, pruned_loss=0.03474, over 1426053.65 frames.], batch size: 17, lr: 3.36e-04
+2022-04-29 21:49:42,508 INFO [train.py:763] (2/8) Epoch 22, batch 4050, loss[loss=0.1546, simple_loss=0.2417, pruned_loss=0.03372, over 6832.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2671, pruned_loss=0.0351, over 1420772.99 frames.], batch size: 15, lr: 3.36e-04
+2022-04-29 21:50:49,120 INFO [train.py:763] (2/8) Epoch 22, batch 4100, loss[loss=0.157, simple_loss=0.2466, pruned_loss=0.03368, over 7258.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2664, pruned_loss=0.03493, over 1418228.41 frames.], batch size: 16, lr: 3.36e-04
+2022-04-29 21:51:54,122 INFO [train.py:763] (2/8) Epoch 22, batch 4150, loss[loss=0.1612, simple_loss=0.2669, pruned_loss=0.02776, over 7333.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2672, pruned_loss=0.03481, over 1417600.08 frames.], batch size: 21, lr: 3.35e-04
+2022-04-29 21:52:59,298 INFO [train.py:763] (2/8) Epoch 22, batch 4200, loss[loss=0.1493, simple_loss=0.2316, pruned_loss=0.03346, over 7012.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2672, pruned_loss=0.03464, over 1421964.91 frames.], batch size: 16, lr: 3.35e-04
+2022-04-29 21:54:05,489 INFO [train.py:763] (2/8) Epoch 22, batch 4250, loss[loss=0.1568, simple_loss=0.266, pruned_loss=0.02379, over 7229.00 frames.], tot_loss[loss=0.1691, simple_loss=0.268, pruned_loss=0.0351, over 1423194.96 frames.], batch size: 20, lr: 3.35e-04
+2022-04-29 21:55:12,484 INFO [train.py:763] (2/8) Epoch 22, batch 4300, loss[loss=0.1437, simple_loss=0.234, pruned_loss=0.02667, over 7161.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2667, pruned_loss=0.03486, over 1419607.44 frames.], batch size: 18, lr: 3.35e-04
+2022-04-29 21:56:19,737 INFO [train.py:763] (2/8) Epoch 22, batch 4350, loss[loss=0.1684, simple_loss=0.2582, pruned_loss=0.03926, over 7229.00 frames.], tot_loss[loss=0.168, simple_loss=0.2661, pruned_loss=0.03497, over 1421072.10 frames.], batch size: 16, lr: 3.35e-04
+2022-04-29 21:57:26,787 INFO [train.py:763] (2/8) Epoch 22, batch 4400, loss[loss=0.1728, simple_loss=0.2696, pruned_loss=0.03803, over 7060.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2658, pruned_loss=0.03499, over 1418707.36 frames.], batch size: 18, lr: 3.35e-04
+2022-04-29 21:58:31,942 INFO [train.py:763] (2/8) Epoch 22, batch 4450, loss[loss=0.2132, simple_loss=0.2976, pruned_loss=0.06438, over 5295.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2661, pruned_loss=0.03504, over 1412574.48 frames.], batch size: 52, lr: 3.35e-04
+2022-04-29 21:59:36,916 INFO [train.py:763] (2/8) Epoch 22, batch 4500, loss[loss=0.1448, simple_loss=0.2509, pruned_loss=0.01937, over 7061.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2663, pruned_loss=0.03492, over 1411558.02 frames.], batch size: 18, lr: 3.35e-04
+2022-04-29 22:00:41,210 INFO [train.py:763] (2/8) Epoch 22, batch 4550, loss[loss=0.1784, simple_loss=0.281, pruned_loss=0.03789, over 4980.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2697, pruned_loss=0.03692, over 1355308.35 frames.], batch size: 54, lr: 3.35e-04
+2022-04-29 22:02:00,630 INFO [train.py:763] (2/8) Epoch 23, batch 0, loss[loss=0.1399, simple_loss=0.222, pruned_loss=0.02885, over 7213.00 frames.], tot_loss[loss=0.1399, simple_loss=0.222, pruned_loss=0.02885, over 7213.00 frames.], batch size: 16, lr: 3.28e-04
+2022-04-29 22:03:02,940 INFO [train.py:763] (2/8) Epoch 23, batch 50, loss[loss=0.1452, simple_loss=0.2399, pruned_loss=0.02529, over 7281.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2653, pruned_loss=0.03328, over 316688.48 frames.], batch size: 17, lr: 3.28e-04
+2022-04-29 22:04:05,006 INFO [train.py:763] (2/8) Epoch 23, batch 100, loss[loss=0.153, simple_loss=0.2536, pruned_loss=0.02622, over 7328.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2672, pruned_loss=0.03367, over 567303.75 frames.], batch size: 20, lr: 3.28e-04
+2022-04-29 22:05:10,553 INFO [train.py:763] (2/8) Epoch 23, batch 150, loss[loss=0.1787, simple_loss=0.2829, pruned_loss=0.0373, over 7385.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2678, pruned_loss=0.03432, over 753121.77 frames.], batch size: 23, lr: 3.28e-04
+2022-04-29 22:06:15,908 INFO [train.py:763] (2/8) Epoch 23, batch 200, loss[loss=0.1956, simple_loss=0.2954, pruned_loss=0.04794, over 7183.00 frames.], tot_loss[loss=0.1675, simple_loss=0.267, pruned_loss=0.03404, over 903577.58 frames.], batch size: 22, lr: 3.28e-04
+2022-04-29 22:07:21,260 INFO [train.py:763] (2/8) Epoch 23, batch 250, loss[loss=0.1627, simple_loss=0.2647, pruned_loss=0.03034, over 7414.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2655, pruned_loss=0.0335, over 1015400.79 frames.], batch size: 21, lr: 3.28e-04
+2022-04-29 22:08:27,016 INFO [train.py:763] (2/8) Epoch 23, batch 300, loss[loss=0.1884, simple_loss=0.2802, pruned_loss=0.04834, over 7149.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2658, pruned_loss=0.03402, over 1106750.30 frames.], batch size: 20, lr: 3.27e-04
+2022-04-29 22:09:32,878 INFO [train.py:763] (2/8) Epoch 23, batch 350, loss[loss=0.1609, simple_loss=0.2673, pruned_loss=0.02729, over 7296.00 frames.], tot_loss[loss=0.167, simple_loss=0.2661, pruned_loss=0.03396, over 1178572.97 frames.], batch size: 25, lr: 3.27e-04
+2022-04-29 22:10:38,043 INFO [train.py:763] (2/8) Epoch 23, batch 400, loss[loss=0.1736, simple_loss=0.2755, pruned_loss=0.03582, over 7304.00 frames.], tot_loss[loss=0.1672, simple_loss=0.266, pruned_loss=0.03424, over 1228791.22 frames.], batch size: 24, lr: 3.27e-04
+2022-04-29 22:11:43,823 INFO [train.py:763] (2/8) Epoch 23, batch 450, loss[loss=0.158, simple_loss=0.2667, pruned_loss=0.02466, over 7142.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2657, pruned_loss=0.03366, over 1274822.67 frames.], batch size: 20, lr: 3.27e-04
+2022-04-29 22:12:49,133 INFO [train.py:763] (2/8) Epoch 23, batch 500, loss[loss=0.1668, simple_loss=0.2596, pruned_loss=0.03699, over 7365.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2655, pruned_loss=0.0338, over 1307296.79 frames.], batch size: 19, lr: 3.27e-04
+2022-04-29 22:13:54,750 INFO [train.py:763] (2/8) Epoch 23, batch 550, loss[loss=0.1843, simple_loss=0.286, pruned_loss=0.04125, over 7210.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2656, pruned_loss=0.03361, over 1335671.81 frames.], batch size: 22, lr: 3.27e-04
+2022-04-29 22:15:00,599 INFO [train.py:763] (2/8) Epoch 23, batch 600, loss[loss=0.1704, simple_loss=0.2528, pruned_loss=0.04397, over 7367.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2654, pruned_loss=0.03397, over 1354616.50 frames.], batch size: 19, lr: 3.27e-04
+2022-04-29 22:16:06,052 INFO [train.py:763] (2/8) Epoch 23, batch 650, loss[loss=0.1577, simple_loss=0.2551, pruned_loss=0.0302, over 7364.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2651, pruned_loss=0.03406, over 1364926.96 frames.], batch size: 19, lr: 3.27e-04
+2022-04-29 22:17:12,008 INFO [train.py:763] (2/8) Epoch 23, batch 700, loss[loss=0.1866, simple_loss=0.2927, pruned_loss=0.04026, over 7191.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2643, pruned_loss=0.03392, over 1382254.89 frames.], batch size: 26, lr: 3.27e-04
+2022-04-29 22:18:17,838 INFO [train.py:763] (2/8) Epoch 23, batch 750, loss[loss=0.1367, simple_loss=0.2198, pruned_loss=0.02684, over 7001.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2661, pruned_loss=0.03442, over 1393097.12 frames.], batch size: 16, lr: 3.27e-04
+2022-04-29 22:19:23,430 INFO [train.py:763] (2/8) Epoch 23, batch 800, loss[loss=0.1721, simple_loss=0.2674, pruned_loss=0.03838, over 7260.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2659, pruned_loss=0.03425, over 1399670.95 frames.], batch size: 19, lr: 3.27e-04
+2022-04-29 22:20:28,941 INFO [train.py:763] (2/8) Epoch 23, batch 850, loss[loss=0.1697, simple_loss=0.2715, pruned_loss=0.03394, over 6857.00 frames.], tot_loss[loss=0.167, simple_loss=0.2658, pruned_loss=0.03408, over 1406127.94 frames.], batch size: 32, lr: 3.27e-04
+2022-04-29 22:21:34,328 INFO [train.py:763] (2/8) Epoch 23, batch 900, loss[loss=0.1587, simple_loss=0.2564, pruned_loss=0.03046, over 7431.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2652, pruned_loss=0.03405, over 1412347.64 frames.], batch size: 20, lr: 3.27e-04
+2022-04-29 22:22:49,566 INFO [train.py:763] (2/8) Epoch 23, batch 950, loss[loss=0.1613, simple_loss=0.2699, pruned_loss=0.02639, over 6610.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2648, pruned_loss=0.03398, over 1417572.86 frames.], batch size: 38, lr: 3.26e-04
+2022-04-29 22:23:55,236 INFO [train.py:763] (2/8) Epoch 23, batch 1000, loss[loss=0.1861, simple_loss=0.2863, pruned_loss=0.04292, over 7317.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2653, pruned_loss=0.03424, over 1419716.38 frames.], batch size: 21, lr: 3.26e-04
+2022-04-29 22:25:00,701 INFO [train.py:763] (2/8) Epoch 23, batch 1050, loss[loss=0.1574, simple_loss=0.2606, pruned_loss=0.02711, over 7233.00 frames.], tot_loss[loss=0.167, simple_loss=0.2655, pruned_loss=0.03423, over 1413301.12 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:26:07,025 INFO [train.py:763] (2/8) Epoch 23, batch 1100, loss[loss=0.1732, simple_loss=0.2818, pruned_loss=0.03233, over 7153.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2657, pruned_loss=0.03456, over 1412730.93 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:27:12,597 INFO [train.py:763] (2/8) Epoch 23, batch 1150, loss[loss=0.1703, simple_loss=0.2796, pruned_loss=0.0305, over 6336.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2655, pruned_loss=0.03449, over 1415719.88 frames.], batch size: 38, lr: 3.26e-04
+2022-04-29 22:28:17,831 INFO [train.py:763] (2/8) Epoch 23, batch 1200, loss[loss=0.1483, simple_loss=0.2416, pruned_loss=0.02753, over 7161.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2651, pruned_loss=0.03423, over 1418430.36 frames.], batch size: 18, lr: 3.26e-04
+2022-04-29 22:29:23,306 INFO [train.py:763] (2/8) Epoch 23, batch 1250, loss[loss=0.1493, simple_loss=0.2509, pruned_loss=0.02387, over 7333.00 frames.], tot_loss[loss=0.167, simple_loss=0.265, pruned_loss=0.03447, over 1418471.27 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:30:28,891 INFO [train.py:763] (2/8) Epoch 23, batch 1300, loss[loss=0.1731, simple_loss=0.2734, pruned_loss=0.0364, over 6899.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2654, pruned_loss=0.03462, over 1419583.92 frames.], batch size: 31, lr: 3.26e-04
+2022-04-29 22:31:51,692 INFO [train.py:763] (2/8) Epoch 23, batch 1350, loss[loss=0.1496, simple_loss=0.2395, pruned_loss=0.02984, over 7402.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2663, pruned_loss=0.03495, over 1425509.91 frames.], batch size: 18, lr: 3.26e-04
+2022-04-29 22:32:57,242 INFO [train.py:763] (2/8) Epoch 23, batch 1400, loss[loss=0.2025, simple_loss=0.2962, pruned_loss=0.05446, over 7196.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2666, pruned_loss=0.03509, over 1424461.86 frames.], batch size: 26, lr: 3.26e-04
+2022-04-29 22:34:20,486 INFO [train.py:763] (2/8) Epoch 23, batch 1450, loss[loss=0.1857, simple_loss=0.283, pruned_loss=0.04418, over 7149.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2668, pruned_loss=0.03497, over 1422088.89 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:35:53,261 INFO [train.py:763] (2/8) Epoch 23, batch 1500, loss[loss=0.1492, simple_loss=0.2504, pruned_loss=0.02398, over 7146.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2659, pruned_loss=0.03464, over 1420980.41 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:36:59,418 INFO [train.py:763] (2/8) Epoch 23, batch 1550, loss[loss=0.1945, simple_loss=0.3039, pruned_loss=0.04257, over 6741.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2657, pruned_loss=0.03449, over 1421066.24 frames.], batch size: 31, lr: 3.26e-04
+2022-04-29 22:38:04,561 INFO [train.py:763] (2/8) Epoch 23, batch 1600, loss[loss=0.1633, simple_loss=0.2566, pruned_loss=0.03495, over 7331.00 frames.], tot_loss[loss=0.168, simple_loss=0.2664, pruned_loss=0.03477, over 1423172.45 frames.], batch size: 20, lr: 3.25e-04
+2022-04-29 22:39:10,551 INFO [train.py:763] (2/8) Epoch 23, batch 1650, loss[loss=0.131, simple_loss=0.2181, pruned_loss=0.02195, over 6784.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2666, pruned_loss=0.03454, over 1415175.22 frames.], batch size: 15, lr: 3.25e-04
+2022-04-29 22:40:17,825 INFO [train.py:763] (2/8) Epoch 23, batch 1700, loss[loss=0.1715, simple_loss=0.2882, pruned_loss=0.02744, over 7311.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2665, pruned_loss=0.03466, over 1418565.86 frames.], batch size: 21, lr: 3.25e-04
+2022-04-29 22:41:24,852 INFO [train.py:763] (2/8) Epoch 23, batch 1750, loss[loss=0.1353, simple_loss=0.2209, pruned_loss=0.02487, over 7068.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2669, pruned_loss=0.03479, over 1420023.48 frames.], batch size: 18, lr: 3.25e-04
+2022-04-29 22:42:30,369 INFO [train.py:763] (2/8) Epoch 23, batch 1800, loss[loss=0.1617, simple_loss=0.2742, pruned_loss=0.02461, over 7344.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2671, pruned_loss=0.0347, over 1420302.83 frames.], batch size: 22, lr: 3.25e-04
+2022-04-29 22:43:35,679 INFO [train.py:763] (2/8) Epoch 23, batch 1850, loss[loss=0.1465, simple_loss=0.2482, pruned_loss=0.02238, over 7278.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2673, pruned_loss=0.03489, over 1424311.33 frames.], batch size: 24, lr: 3.25e-04
+2022-04-29 22:44:41,101 INFO [train.py:763] (2/8) Epoch 23, batch 1900, loss[loss=0.1763, simple_loss=0.2792, pruned_loss=0.03676, over 7080.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2667, pruned_loss=0.0346, over 1422002.75 frames.], batch size: 28, lr: 3.25e-04
+2022-04-29 22:45:46,545 INFO [train.py:763] (2/8) Epoch 23, batch 1950, loss[loss=0.1611, simple_loss=0.2716, pruned_loss=0.0253, over 7116.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2669, pruned_loss=0.03472, over 1423798.45 frames.], batch size: 21, lr: 3.25e-04
+2022-04-29 22:46:52,055 INFO [train.py:763] (2/8) Epoch 23, batch 2000, loss[loss=0.2, simple_loss=0.2824, pruned_loss=0.05882, over 5255.00 frames.], tot_loss[loss=0.1692, simple_loss=0.268, pruned_loss=0.03522, over 1422255.74 frames.], batch size: 53, lr: 3.25e-04
+2022-04-29 22:47:58,952 INFO [train.py:763] (2/8) Epoch 23, batch 2050, loss[loss=0.1648, simple_loss=0.2651, pruned_loss=0.03226, over 7417.00 frames.], tot_loss[loss=0.169, simple_loss=0.2678, pruned_loss=0.0351, over 1421709.92 frames.], batch size: 20, lr: 3.25e-04
+2022-04-29 22:49:05,147 INFO [train.py:763] (2/8) Epoch 23, batch 2100, loss[loss=0.1554, simple_loss=0.2567, pruned_loss=0.027, over 6991.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2672, pruned_loss=0.03484, over 1422387.35 frames.], batch size: 16, lr: 3.25e-04
+2022-04-29 22:50:10,652 INFO [train.py:763] (2/8) Epoch 23, batch 2150, loss[loss=0.1863, simple_loss=0.2814, pruned_loss=0.04566, over 4938.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2665, pruned_loss=0.03447, over 1419929.97 frames.], batch size: 53, lr: 3.25e-04
+2022-04-29 22:51:16,163 INFO [train.py:763] (2/8) Epoch 23, batch 2200, loss[loss=0.1639, simple_loss=0.252, pruned_loss=0.03789, over 7139.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2664, pruned_loss=0.03451, over 1419216.16 frames.], batch size: 17, lr: 3.25e-04
+2022-04-29 22:52:21,330 INFO [train.py:763] (2/8) Epoch 23, batch 2250, loss[loss=0.1709, simple_loss=0.2795, pruned_loss=0.03112, over 7302.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2677, pruned_loss=0.03488, over 1410152.55 frames.], batch size: 25, lr: 3.24e-04
+2022-04-29 22:53:28,269 INFO [train.py:763] (2/8) Epoch 23, batch 2300, loss[loss=0.1395, simple_loss=0.222, pruned_loss=0.02857, over 7280.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2664, pruned_loss=0.03455, over 1417424.12 frames.], batch size: 17, lr: 3.24e-04
+2022-04-29 22:54:34,463 INFO [train.py:763] (2/8) Epoch 23, batch 2350, loss[loss=0.1583, simple_loss=0.2694, pruned_loss=0.02363, over 7331.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2673, pruned_loss=0.03473, over 1418279.25 frames.], batch size: 22, lr: 3.24e-04
+2022-04-29 22:55:39,709 INFO [train.py:763] (2/8) Epoch 23, batch 2400, loss[loss=0.1327, simple_loss=0.2285, pruned_loss=0.01848, over 7203.00 frames.], tot_loss[loss=0.1689, simple_loss=0.268, pruned_loss=0.03495, over 1421549.90 frames.], batch size: 16, lr: 3.24e-04
+2022-04-29 22:56:45,971 INFO [train.py:763] (2/8) Epoch 23, batch 2450, loss[loss=0.1683, simple_loss=0.2679, pruned_loss=0.03436, over 7238.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2676, pruned_loss=0.0347, over 1418401.18 frames.], batch size: 20, lr: 3.24e-04
+2022-04-29 22:57:51,397 INFO [train.py:763] (2/8) Epoch 23, batch 2500, loss[loss=0.1731, simple_loss=0.2756, pruned_loss=0.03532, over 7313.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2667, pruned_loss=0.03435, over 1418896.82 frames.], batch size: 21, lr: 3.24e-04
+2022-04-29 22:58:56,884 INFO [train.py:763] (2/8) Epoch 23, batch 2550, loss[loss=0.1845, simple_loss=0.2805, pruned_loss=0.04429, over 5078.00 frames.], tot_loss[loss=0.1682, simple_loss=0.267, pruned_loss=0.03465, over 1413659.60 frames.], batch size: 52, lr: 3.24e-04
+2022-04-29 23:00:02,918 INFO [train.py:763] (2/8) Epoch 23, batch 2600, loss[loss=0.1607, simple_loss=0.2555, pruned_loss=0.03296, over 7292.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2675, pruned_loss=0.03464, over 1416560.83 frames.], batch size: 18, lr: 3.24e-04
+2022-04-29 23:01:08,566 INFO [train.py:763] (2/8) Epoch 23, batch 2650, loss[loss=0.1925, simple_loss=0.3022, pruned_loss=0.04142, over 7314.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2669, pruned_loss=0.03441, over 1416778.19 frames.], batch size: 21, lr: 3.24e-04
+2022-04-29 23:02:14,020 INFO [train.py:763] (2/8) Epoch 23, batch 2700, loss[loss=0.1727, simple_loss=0.2835, pruned_loss=0.03099, over 7350.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2669, pruned_loss=0.03437, over 1421674.85 frames.], batch size: 22, lr: 3.24e-04
+2022-04-29 23:03:19,897 INFO [train.py:763] (2/8) Epoch 23, batch 2750, loss[loss=0.1839, simple_loss=0.2875, pruned_loss=0.04012, over 7403.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2657, pruned_loss=0.03361, over 1424955.65 frames.], batch size: 21, lr: 3.24e-04
+2022-04-29 23:04:25,094 INFO [train.py:763] (2/8) Epoch 23, batch 2800, loss[loss=0.1572, simple_loss=0.254, pruned_loss=0.03019, over 7224.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2661, pruned_loss=0.03383, over 1421733.72 frames.], batch size: 20, lr: 3.24e-04
+2022-04-29 23:05:30,272 INFO [train.py:763] (2/8) Epoch 23, batch 2850, loss[loss=0.1498, simple_loss=0.2427, pruned_loss=0.02847, over 7351.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2672, pruned_loss=0.03421, over 1422706.14 frames.], batch size: 19, lr: 3.24e-04
+2022-04-29 23:06:35,471 INFO [train.py:763] (2/8) Epoch 23, batch 2900, loss[loss=0.1747, simple_loss=0.2726, pruned_loss=0.03839, over 7288.00 frames.], tot_loss[loss=0.1683, simple_loss=0.268, pruned_loss=0.03431, over 1422363.26 frames.], batch size: 25, lr: 3.24e-04
+2022-04-29 23:07:40,683 INFO [train.py:763] (2/8) Epoch 23, batch 2950, loss[loss=0.1557, simple_loss=0.2386, pruned_loss=0.03634, over 7270.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2673, pruned_loss=0.03423, over 1425810.97 frames.], batch size: 17, lr: 3.23e-04
+2022-04-29 23:08:45,890 INFO [train.py:763] (2/8) Epoch 23, batch 3000, loss[loss=0.1639, simple_loss=0.2614, pruned_loss=0.03325, over 7113.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2672, pruned_loss=0.0346, over 1421733.58 frames.], batch size: 21, lr: 3.23e-04
+2022-04-29 23:08:45,891 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-29 23:09:01,229 INFO [train.py:792] (2/8) Epoch 23, validation: loss=0.1683, simple_loss=0.2665, pruned_loss=0.03509, over 698248.00 frames.
+2022-04-29 23:10:07,036 INFO [train.py:763] (2/8) Epoch 23, batch 3050, loss[loss=0.1714, simple_loss=0.2674, pruned_loss=0.03764, over 7265.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2677, pruned_loss=0.03457, over 1417276.86 frames.], batch size: 18, lr: 3.23e-04
+2022-04-29 23:11:12,527 INFO [train.py:763] (2/8) Epoch 23, batch 3100, loss[loss=0.1794, simple_loss=0.2789, pruned_loss=0.03993, over 6765.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2663, pruned_loss=0.0342, over 1420938.71 frames.], batch size: 31, lr: 3.23e-04
+2022-04-29 23:12:19,057 INFO [train.py:763] (2/8) Epoch 23, batch 3150, loss[loss=0.1408, simple_loss=0.2226, pruned_loss=0.0295, over 6993.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2657, pruned_loss=0.03409, over 1422718.56 frames.], batch size: 16, lr: 3.23e-04
+2022-04-29 23:13:26,790 INFO [train.py:763] (2/8) Epoch 23, batch 3200, loss[loss=0.1595, simple_loss=0.2608, pruned_loss=0.02911, over 7314.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2661, pruned_loss=0.0345, over 1426934.26 frames.], batch size: 21, lr: 3.23e-04
+2022-04-29 23:14:33,552 INFO [train.py:763] (2/8) Epoch 23, batch 3250, loss[loss=0.1368, simple_loss=0.2301, pruned_loss=0.02174, over 7168.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2656, pruned_loss=0.0343, over 1428326.21 frames.], batch size: 18, lr: 3.23e-04
+2022-04-29 23:15:38,816 INFO [train.py:763] (2/8) Epoch 23, batch 3300, loss[loss=0.1943, simple_loss=0.2936, pruned_loss=0.04754, over 7307.00 frames.], tot_loss[loss=0.1672, simple_loss=0.266, pruned_loss=0.03415, over 1428296.89 frames.], batch size: 24, lr: 3.23e-04
+2022-04-29 23:16:45,585 INFO [train.py:763] (2/8) Epoch 23, batch 3350, loss[loss=0.1662, simple_loss=0.2717, pruned_loss=0.03036, over 7282.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2665, pruned_loss=0.03463, over 1424563.44 frames.], batch size: 24, lr: 3.23e-04
+2022-04-29 23:17:51,523 INFO [train.py:763] (2/8) Epoch 23, batch 3400, loss[loss=0.1725, simple_loss=0.2775, pruned_loss=0.03369, over 7361.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2665, pruned_loss=0.03452, over 1428592.02 frames.], batch size: 19, lr: 3.23e-04
+2022-04-29 23:18:56,725 INFO [train.py:763] (2/8) Epoch 23, batch 3450, loss[loss=0.1948, simple_loss=0.3035, pruned_loss=0.04303, over 7336.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2677, pruned_loss=0.03448, over 1423261.93 frames.], batch size: 22, lr: 3.23e-04
+2022-04-29 23:20:02,249 INFO [train.py:763] (2/8) Epoch 23, batch 3500, loss[loss=0.1491, simple_loss=0.2438, pruned_loss=0.02717, over 6813.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2669, pruned_loss=0.03438, over 1421519.22 frames.], batch size: 15, lr: 3.23e-04
+2022-04-29 23:21:08,249 INFO [train.py:763] (2/8) Epoch 23, batch 3550, loss[loss=0.187, simple_loss=0.2774, pruned_loss=0.04825, over 7126.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2661, pruned_loss=0.034, over 1423766.38 frames.], batch size: 21, lr: 3.23e-04
+2022-04-29 23:22:13,611 INFO [train.py:763] (2/8) Epoch 23, batch 3600, loss[loss=0.1542, simple_loss=0.2623, pruned_loss=0.02302, over 7081.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2669, pruned_loss=0.03434, over 1423776.32 frames.], batch size: 18, lr: 3.22e-04
+2022-04-29 23:23:18,840 INFO [train.py:763] (2/8) Epoch 23, batch 3650, loss[loss=0.1702, simple_loss=0.2678, pruned_loss=0.03634, over 7354.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2678, pruned_loss=0.03478, over 1425052.31 frames.], batch size: 19, lr: 3.22e-04
+2022-04-29 23:24:24,040 INFO [train.py:763] (2/8) Epoch 23, batch 3700, loss[loss=0.1776, simple_loss=0.2784, pruned_loss=0.03842, over 6384.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2668, pruned_loss=0.03419, over 1422405.26 frames.], batch size: 37, lr: 3.22e-04
+2022-04-29 23:25:30,841 INFO [train.py:763] (2/8) Epoch 23, batch 3750, loss[loss=0.1494, simple_loss=0.2474, pruned_loss=0.02572, over 7290.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2671, pruned_loss=0.03409, over 1423193.95 frames.], batch size: 18, lr: 3.22e-04
+2022-04-29 23:26:37,715 INFO [train.py:763] (2/8) Epoch 23, batch 3800, loss[loss=0.1394, simple_loss=0.2403, pruned_loss=0.01927, over 7442.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2657, pruned_loss=0.0336, over 1424733.70 frames.], batch size: 20, lr: 3.22e-04
+2022-04-29 23:27:43,262 INFO [train.py:763] (2/8) Epoch 23, batch 3850, loss[loss=0.191, simple_loss=0.2866, pruned_loss=0.04773, over 4317.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2659, pruned_loss=0.03431, over 1420278.74 frames.], batch size: 52, lr: 3.22e-04
+2022-04-29 23:28:48,633 INFO [train.py:763] (2/8) Epoch 23, batch 3900, loss[loss=0.1907, simple_loss=0.29, pruned_loss=0.0457, over 6690.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2656, pruned_loss=0.03402, over 1417092.24 frames.], batch size: 31, lr: 3.22e-04
+2022-04-29 23:29:53,688 INFO [train.py:763] (2/8) Epoch 23, batch 3950, loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.02999, over 7140.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2661, pruned_loss=0.03418, over 1416863.22 frames.], batch size: 17, lr: 3.22e-04
+2022-04-29 23:30:59,584 INFO [train.py:763] (2/8) Epoch 23, batch 4000, loss[loss=0.1624, simple_loss=0.2669, pruned_loss=0.02899, over 7207.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2664, pruned_loss=0.03459, over 1414793.03 frames.], batch size: 22, lr: 3.22e-04
+2022-04-29 23:32:05,445 INFO [train.py:763] (2/8) Epoch 23, batch 4050, loss[loss=0.176, simple_loss=0.2652, pruned_loss=0.04342, over 5119.00 frames.], tot_loss[loss=0.1671, simple_loss=0.266, pruned_loss=0.03413, over 1415689.21 frames.], batch size: 52, lr: 3.22e-04
+2022-04-29 23:33:10,716 INFO [train.py:763] (2/8) Epoch 23, batch 4100, loss[loss=0.1452, simple_loss=0.2414, pruned_loss=0.02451, over 7290.00 frames.], tot_loss[loss=0.167, simple_loss=0.2658, pruned_loss=0.03407, over 1416124.19 frames.], batch size: 18, lr: 3.22e-04
+2022-04-29 23:34:16,152 INFO [train.py:763] (2/8) Epoch 23, batch 4150, loss[loss=0.1656, simple_loss=0.2585, pruned_loss=0.03639, over 6991.00 frames.], tot_loss[loss=0.167, simple_loss=0.2659, pruned_loss=0.03405, over 1417888.87 frames.], batch size: 16, lr: 3.22e-04
+2022-04-29 23:35:21,251 INFO [train.py:763] (2/8) Epoch 23, batch 4200, loss[loss=0.1575, simple_loss=0.2439, pruned_loss=0.03557, over 7280.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2668, pruned_loss=0.03443, over 1418371.01 frames.], batch size: 18, lr: 3.22e-04
+2022-04-29 23:36:26,913 INFO [train.py:763] (2/8) Epoch 23, batch 4250, loss[loss=0.19, simple_loss=0.2898, pruned_loss=0.04511, over 7363.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2674, pruned_loss=0.03488, over 1415932.61 frames.], batch size: 23, lr: 3.22e-04
+2022-04-29 23:37:32,232 INFO [train.py:763] (2/8) Epoch 23, batch 4300, loss[loss=0.1541, simple_loss=0.2466, pruned_loss=0.03083, over 6741.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2668, pruned_loss=0.03489, over 1415154.84 frames.], batch size: 15, lr: 3.21e-04
+2022-04-29 23:38:37,629 INFO [train.py:763] (2/8) Epoch 23, batch 4350, loss[loss=0.1769, simple_loss=0.278, pruned_loss=0.03788, over 6788.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2677, pruned_loss=0.03531, over 1411941.58 frames.], batch size: 31, lr: 3.21e-04
+2022-04-29 23:39:43,229 INFO [train.py:763] (2/8) Epoch 23, batch 4400, loss[loss=0.18, simple_loss=0.2799, pruned_loss=0.04009, over 6535.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2685, pruned_loss=0.03561, over 1407310.87 frames.], batch size: 38, lr: 3.21e-04
+2022-04-29 23:40:48,373 INFO [train.py:763] (2/8) Epoch 23, batch 4450, loss[loss=0.2056, simple_loss=0.3001, pruned_loss=0.05555, over 6252.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2675, pruned_loss=0.03511, over 1410353.09 frames.], batch size: 37, lr: 3.21e-04
+2022-04-29 23:41:53,041 INFO [train.py:763] (2/8) Epoch 23, batch 4500, loss[loss=0.1839, simple_loss=0.2866, pruned_loss=0.04065, over 6452.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2684, pruned_loss=0.03547, over 1396911.24 frames.], batch size: 38, lr: 3.21e-04
+2022-04-29 23:42:58,309 INFO [train.py:763] (2/8) Epoch 23, batch 4550, loss[loss=0.1874, simple_loss=0.2911, pruned_loss=0.04185, over 7269.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2682, pruned_loss=0.03545, over 1384586.92 frames.], batch size: 24, lr: 3.21e-04
+2022-04-29 23:44:17,937 INFO [train.py:763] (2/8) Epoch 24, batch 0, loss[loss=0.17, simple_loss=0.2771, pruned_loss=0.0314, over 7075.00 frames.], tot_loss[loss=0.17, simple_loss=0.2771, pruned_loss=0.0314, over 7075.00 frames.], batch size: 18, lr: 3.15e-04
+2022-04-29 23:45:23,857 INFO [train.py:763] (2/8) Epoch 24, batch 50, loss[loss=0.1585, simple_loss=0.2487, pruned_loss=0.03416, over 7261.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2685, pruned_loss=0.03684, over 322394.07 frames.], batch size: 19, lr: 3.15e-04
+2022-04-29 23:46:30,361 INFO [train.py:763] (2/8) Epoch 24, batch 100, loss[loss=0.1539, simple_loss=0.2523, pruned_loss=0.02776, over 7331.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2676, pruned_loss=0.03556, over 570783.87 frames.], batch size: 20, lr: 3.15e-04
+2022-04-29 23:47:35,973 INFO [train.py:763] (2/8) Epoch 24, batch 150, loss[loss=0.1732, simple_loss=0.2726, pruned_loss=0.03685, over 7328.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2661, pruned_loss=0.03418, over 762548.90 frames.], batch size: 21, lr: 3.14e-04
+2022-04-29 23:48:41,592 INFO [train.py:763] (2/8) Epoch 24, batch 200, loss[loss=0.1704, simple_loss=0.2593, pruned_loss=0.04072, over 6762.00 frames.], tot_loss[loss=0.167, simple_loss=0.2656, pruned_loss=0.03414, over 908176.88 frames.], batch size: 15, lr: 3.14e-04
+2022-04-29 23:49:46,882 INFO [train.py:763] (2/8) Epoch 24, batch 250, loss[loss=0.1867, simple_loss=0.2878, pruned_loss=0.04274, over 7237.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2655, pruned_loss=0.03383, over 1019288.99 frames.], batch size: 20, lr: 3.14e-04
+2022-04-29 23:50:52,233 INFO [train.py:763] (2/8) Epoch 24, batch 300, loss[loss=0.1901, simple_loss=0.2838, pruned_loss=0.04821, over 7169.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2665, pruned_loss=0.03449, over 1112414.32 frames.], batch size: 19, lr: 3.14e-04
+2022-04-29 23:51:57,519 INFO [train.py:763] (2/8) Epoch 24, batch 350, loss[loss=0.1618, simple_loss=0.2683, pruned_loss=0.02762, over 7205.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2654, pruned_loss=0.03419, over 1181922.63 frames.], batch size: 23, lr: 3.14e-04
+2022-04-29 23:53:03,340 INFO [train.py:763] (2/8) Epoch 24, batch 400, loss[loss=0.1584, simple_loss=0.2602, pruned_loss=0.02832, over 7232.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2652, pruned_loss=0.03392, over 1236754.82 frames.], batch size: 20, lr: 3.14e-04
+2022-04-29 23:54:08,670 INFO [train.py:763] (2/8) Epoch 24, batch 450, loss[loss=0.1781, simple_loss=0.2836, pruned_loss=0.03628, over 7051.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2643, pruned_loss=0.03354, over 1277468.50 frames.], batch size: 28, lr: 3.14e-04
+2022-04-29 23:55:14,210 INFO [train.py:763] (2/8) Epoch 24, batch 500, loss[loss=0.1726, simple_loss=0.2519, pruned_loss=0.04661, over 7171.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2648, pruned_loss=0.0338, over 1312571.00 frames.], batch size: 18, lr: 3.14e-04
+2022-04-29 23:56:20,425 INFO [train.py:763] (2/8) Epoch 24, batch 550, loss[loss=0.1532, simple_loss=0.2507, pruned_loss=0.02787, over 7162.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2648, pruned_loss=0.03346, over 1340149.15 frames.], batch size: 18, lr: 3.14e-04
+2022-04-29 23:57:26,719 INFO [train.py:763] (2/8) Epoch 24, batch 600, loss[loss=0.1715, simple_loss=0.2779, pruned_loss=0.03258, over 7189.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2653, pruned_loss=0.03365, over 1359094.86 frames.], batch size: 23, lr: 3.14e-04
+2022-04-29 23:58:32,097 INFO [train.py:763] (2/8) Epoch 24, batch 650, loss[loss=0.1504, simple_loss=0.2433, pruned_loss=0.02881, over 7256.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2643, pruned_loss=0.03366, over 1372274.34 frames.], batch size: 17, lr: 3.14e-04
+2022-04-29 23:59:38,741 INFO [train.py:763] (2/8) Epoch 24, batch 700, loss[loss=0.1632, simple_loss=0.2517, pruned_loss=0.03732, over 6830.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2645, pruned_loss=0.03383, over 1387845.91 frames.], batch size: 15, lr: 3.14e-04
+2022-04-30 00:00:44,925 INFO [train.py:763] (2/8) Epoch 24, batch 750, loss[loss=0.1542, simple_loss=0.2578, pruned_loss=0.02534, over 7230.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2657, pruned_loss=0.03432, over 1398903.59 frames.], batch size: 20, lr: 3.14e-04
+2022-04-30 00:01:50,607 INFO [train.py:763] (2/8) Epoch 24, batch 800, loss[loss=0.1777, simple_loss=0.2708, pruned_loss=0.0423, over 7417.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2665, pruned_loss=0.03467, over 1405733.86 frames.], batch size: 21, lr: 3.14e-04
+2022-04-30 00:02:56,128 INFO [train.py:763] (2/8) Epoch 24, batch 850, loss[loss=0.1666, simple_loss=0.271, pruned_loss=0.03105, over 7323.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2663, pruned_loss=0.03437, over 1407476.06 frames.], batch size: 21, lr: 3.13e-04
+2022-04-30 00:04:01,368 INFO [train.py:763] (2/8) Epoch 24, batch 900, loss[loss=0.1725, simple_loss=0.2779, pruned_loss=0.03359, over 7256.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2672, pruned_loss=0.03482, over 1410056.82 frames.], batch size: 25, lr: 3.13e-04
+2022-04-30 00:05:07,031 INFO [train.py:763] (2/8) Epoch 24, batch 950, loss[loss=0.1873, simple_loss=0.2845, pruned_loss=0.04502, over 5339.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2671, pruned_loss=0.0347, over 1404924.95 frames.], batch size: 52, lr: 3.13e-04
+2022-04-30 00:06:12,842 INFO [train.py:763] (2/8) Epoch 24, batch 1000, loss[loss=0.2066, simple_loss=0.2985, pruned_loss=0.05736, over 7416.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2669, pruned_loss=0.0346, over 1411770.69 frames.], batch size: 21, lr: 3.13e-04
+2022-04-30 00:07:18,484 INFO [train.py:763] (2/8) Epoch 24, batch 1050, loss[loss=0.1706, simple_loss=0.2676, pruned_loss=0.03683, over 7324.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2669, pruned_loss=0.03429, over 1418587.17 frames.], batch size: 20, lr: 3.13e-04
+2022-04-30 00:08:23,983 INFO [train.py:763] (2/8) Epoch 24, batch 1100, loss[loss=0.1632, simple_loss=0.2632, pruned_loss=0.03156, over 7335.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2662, pruned_loss=0.03379, over 1421453.94 frames.], batch size: 22, lr: 3.13e-04
+2022-04-30 00:09:29,775 INFO [train.py:763] (2/8) Epoch 24, batch 1150, loss[loss=0.181, simple_loss=0.2915, pruned_loss=0.03526, over 7200.00 frames.], tot_loss[loss=0.167, simple_loss=0.2663, pruned_loss=0.03385, over 1424658.79 frames.], batch size: 23, lr: 3.13e-04
+2022-04-30 00:10:35,399 INFO [train.py:763] (2/8) Epoch 24, batch 1200, loss[loss=0.1625, simple_loss=0.2613, pruned_loss=0.0319, over 7369.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2658, pruned_loss=0.03399, over 1424241.57 frames.], batch size: 23, lr: 3.13e-04
+2022-04-30 00:11:41,670 INFO [train.py:763] (2/8) Epoch 24, batch 1250, loss[loss=0.1537, simple_loss=0.2613, pruned_loss=0.02299, over 7141.00 frames.], tot_loss[loss=0.1674, simple_loss=0.266, pruned_loss=0.03443, over 1423224.42 frames.], batch size: 20, lr: 3.13e-04
+2022-04-30 00:12:47,619 INFO [train.py:763] (2/8) Epoch 24, batch 1300, loss[loss=0.1548, simple_loss=0.2453, pruned_loss=0.03218, over 7217.00 frames.], tot_loss[loss=0.1688, simple_loss=0.267, pruned_loss=0.03527, over 1421516.49 frames.], batch size: 16, lr: 3.13e-04
+2022-04-30 00:13:53,402 INFO [train.py:763] (2/8) Epoch 24, batch 1350, loss[loss=0.1796, simple_loss=0.2783, pruned_loss=0.04042, over 6494.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2666, pruned_loss=0.03507, over 1421377.27 frames.], batch size: 38, lr: 3.13e-04
+2022-04-30 00:14:58,832 INFO [train.py:763] (2/8) Epoch 24, batch 1400, loss[loss=0.1331, simple_loss=0.2269, pruned_loss=0.01971, over 7260.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2674, pruned_loss=0.03505, over 1426283.77 frames.], batch size: 17, lr: 3.13e-04
+2022-04-30 00:16:04,288 INFO [train.py:763] (2/8) Epoch 24, batch 1450, loss[loss=0.1598, simple_loss=0.2623, pruned_loss=0.02861, over 7147.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2671, pruned_loss=0.0347, over 1421772.20 frames.], batch size: 20, lr: 3.13e-04
+2022-04-30 00:17:11,223 INFO [train.py:763] (2/8) Epoch 24, batch 1500, loss[loss=0.162, simple_loss=0.2553, pruned_loss=0.03437, over 6902.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2666, pruned_loss=0.0341, over 1420965.20 frames.], batch size: 32, lr: 3.13e-04
+2022-04-30 00:18:17,536 INFO [train.py:763] (2/8) Epoch 24, batch 1550, loss[loss=0.1632, simple_loss=0.2642, pruned_loss=0.03108, over 7276.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2673, pruned_loss=0.03455, over 1422232.46 frames.], batch size: 18, lr: 3.12e-04
+2022-04-30 00:19:23,704 INFO [train.py:763] (2/8) Epoch 24, batch 1600, loss[loss=0.1517, simple_loss=0.2395, pruned_loss=0.03202, over 6782.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2672, pruned_loss=0.03418, over 1420802.14 frames.], batch size: 15, lr: 3.12e-04
+2022-04-30 00:20:29,911 INFO [train.py:763] (2/8) Epoch 24, batch 1650, loss[loss=0.1747, simple_loss=0.283, pruned_loss=0.03319, over 7217.00 frames.], tot_loss[loss=0.1678, simple_loss=0.267, pruned_loss=0.03429, over 1421737.38 frames.], batch size: 21, lr: 3.12e-04
+2022-04-30 00:21:35,718 INFO [train.py:763] (2/8) Epoch 24, batch 1700, loss[loss=0.1542, simple_loss=0.2499, pruned_loss=0.02922, over 7347.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2662, pruned_loss=0.03425, over 1420602.46 frames.], batch size: 23, lr: 3.12e-04
+2022-04-30 00:22:40,919 INFO [train.py:763] (2/8) Epoch 24, batch 1750, loss[loss=0.1403, simple_loss=0.2308, pruned_loss=0.02486, over 7158.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2665, pruned_loss=0.03445, over 1423530.52 frames.], batch size: 17, lr: 3.12e-04
+2022-04-30 00:23:47,084 INFO [train.py:763] (2/8) Epoch 24, batch 1800, loss[loss=0.1535, simple_loss=0.236, pruned_loss=0.03551, over 6996.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2663, pruned_loss=0.03414, over 1423284.75 frames.], batch size: 16, lr: 3.12e-04
+2022-04-30 00:24:52,827 INFO [train.py:763] (2/8) Epoch 24, batch 1850, loss[loss=0.1551, simple_loss=0.2345, pruned_loss=0.03786, over 6801.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2653, pruned_loss=0.0342, over 1419748.47 frames.], batch size: 15, lr: 3.12e-04
+2022-04-30 00:26:09,444 INFO [train.py:763] (2/8) Epoch 24, batch 1900, loss[loss=0.1909, simple_loss=0.295, pruned_loss=0.04342, over 7291.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2653, pruned_loss=0.03409, over 1422087.68 frames.], batch size: 25, lr: 3.12e-04
+2022-04-30 00:27:15,221 INFO [train.py:763] (2/8) Epoch 24, batch 1950, loss[loss=0.1595, simple_loss=0.2582, pruned_loss=0.03042, over 7259.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2651, pruned_loss=0.03397, over 1424671.35 frames.], batch size: 19, lr: 3.12e-04
+2022-04-30 00:28:21,026 INFO [train.py:763] (2/8) Epoch 24, batch 2000, loss[loss=0.1571, simple_loss=0.2559, pruned_loss=0.02912, over 7150.00 frames.], tot_loss[loss=0.166, simple_loss=0.2647, pruned_loss=0.03365, over 1425132.93 frames.], batch size: 18, lr: 3.12e-04
+2022-04-30 00:29:27,103 INFO [train.py:763] (2/8) Epoch 24, batch 2050, loss[loss=0.1878, simple_loss=0.2912, pruned_loss=0.04224, over 7308.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2642, pruned_loss=0.03334, over 1428156.19 frames.], batch size: 21, lr: 3.12e-04
+2022-04-30 00:30:32,481 INFO [train.py:763] (2/8) Epoch 24, batch 2100, loss[loss=0.1426, simple_loss=0.2403, pruned_loss=0.0225, over 7264.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2638, pruned_loss=0.03299, over 1424650.70 frames.], batch size: 19, lr: 3.12e-04
+2022-04-30 00:31:37,972 INFO [train.py:763] (2/8) Epoch 24, batch 2150, loss[loss=0.15, simple_loss=0.254, pruned_loss=0.02297, over 7425.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2643, pruned_loss=0.03307, over 1423423.21 frames.], batch size: 20, lr: 3.12e-04
+2022-04-30 00:32:43,331 INFO [train.py:763] (2/8) Epoch 24, batch 2200, loss[loss=0.1854, simple_loss=0.2538, pruned_loss=0.05846, over 6742.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2631, pruned_loss=0.03303, over 1421914.82 frames.], batch size: 15, lr: 3.12e-04
+2022-04-30 00:33:49,447 INFO [train.py:763] (2/8) Epoch 24, batch 2250, loss[loss=0.1522, simple_loss=0.2465, pruned_loss=0.02896, over 7072.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2633, pruned_loss=0.03304, over 1417673.00 frames.], batch size: 18, lr: 3.12e-04
+2022-04-30 00:34:55,311 INFO [train.py:763] (2/8) Epoch 24, batch 2300, loss[loss=0.1436, simple_loss=0.2372, pruned_loss=0.02507, over 6748.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2632, pruned_loss=0.03273, over 1418643.96 frames.], batch size: 15, lr: 3.11e-04
+2022-04-30 00:36:01,133 INFO [train.py:763] (2/8) Epoch 24, batch 2350, loss[loss=0.1689, simple_loss=0.2736, pruned_loss=0.03208, over 7314.00 frames.], tot_loss[loss=0.1648, simple_loss=0.264, pruned_loss=0.03282, over 1418807.74 frames.], batch size: 21, lr: 3.11e-04
+2022-04-30 00:37:06,710 INFO [train.py:763] (2/8) Epoch 24, batch 2400, loss[loss=0.1629, simple_loss=0.2548, pruned_loss=0.03548, over 7348.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2654, pruned_loss=0.03323, over 1423208.96 frames.], batch size: 19, lr: 3.11e-04
+2022-04-30 00:38:21,816 INFO [train.py:763] (2/8) Epoch 24, batch 2450, loss[loss=0.1524, simple_loss=0.2425, pruned_loss=0.03113, over 7136.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2662, pruned_loss=0.03337, over 1422246.17 frames.], batch size: 17, lr: 3.11e-04
+2022-04-30 00:39:27,184 INFO [train.py:763] (2/8) Epoch 24, batch 2500, loss[loss=0.1707, simple_loss=0.2841, pruned_loss=0.02869, over 7403.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2653, pruned_loss=0.03329, over 1422284.84 frames.], batch size: 21, lr: 3.11e-04
+2022-04-30 00:40:32,702 INFO [train.py:763] (2/8) Epoch 24, batch 2550, loss[loss=0.1497, simple_loss=0.2426, pruned_loss=0.02839, over 7423.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2655, pruned_loss=0.03344, over 1423096.55 frames.], batch size: 20, lr: 3.11e-04
+2022-04-30 00:41:38,100 INFO [train.py:763] (2/8) Epoch 24, batch 2600, loss[loss=0.1369, simple_loss=0.2325, pruned_loss=0.02064, over 7150.00 frames.], tot_loss[loss=0.1661, simple_loss=0.265, pruned_loss=0.03354, over 1420782.91 frames.], batch size: 17, lr: 3.11e-04
+2022-04-30 00:42:43,677 INFO [train.py:763] (2/8) Epoch 24, batch 2650, loss[loss=0.1887, simple_loss=0.2896, pruned_loss=0.04392, over 7199.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2662, pruned_loss=0.034, over 1422759.31 frames.], batch size: 22, lr: 3.11e-04
+2022-04-30 00:43:49,270 INFO [train.py:763] (2/8) Epoch 24, batch 2700, loss[loss=0.1598, simple_loss=0.2672, pruned_loss=0.0262, over 7074.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2657, pruned_loss=0.03359, over 1424971.75 frames.], batch size: 18, lr: 3.11e-04
+2022-04-30 00:44:54,687 INFO [train.py:763] (2/8) Epoch 24, batch 2750, loss[loss=0.1538, simple_loss=0.2584, pruned_loss=0.02458, over 7145.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2648, pruned_loss=0.03342, over 1419881.80 frames.], batch size: 20, lr: 3.11e-04
+2022-04-30 00:46:00,207 INFO [train.py:763] (2/8) Epoch 24, batch 2800, loss[loss=0.1596, simple_loss=0.262, pruned_loss=0.02863, over 7252.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2645, pruned_loss=0.03347, over 1421245.74 frames.], batch size: 19, lr: 3.11e-04
+2022-04-30 00:47:22,974 INFO [train.py:763] (2/8) Epoch 24, batch 2850, loss[loss=0.1633, simple_loss=0.2679, pruned_loss=0.02932, over 7423.00 frames.], tot_loss[loss=0.165, simple_loss=0.2639, pruned_loss=0.03305, over 1419219.76 frames.], batch size: 20, lr: 3.11e-04
+2022-04-30 00:48:28,451 INFO [train.py:763] (2/8) Epoch 24, batch 2900, loss[loss=0.1842, simple_loss=0.2919, pruned_loss=0.03827, over 7194.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2651, pruned_loss=0.03331, over 1419656.32 frames.], batch size: 23, lr: 3.11e-04
+2022-04-30 00:49:52,261 INFO [train.py:763] (2/8) Epoch 24, batch 2950, loss[loss=0.1743, simple_loss=0.2718, pruned_loss=0.03847, over 7116.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2652, pruned_loss=0.03302, over 1425003.63 frames.], batch size: 21, lr: 3.11e-04
+2022-04-30 00:51:06,862 INFO [train.py:763] (2/8) Epoch 24, batch 3000, loss[loss=0.1824, simple_loss=0.2859, pruned_loss=0.03943, over 6896.00 frames.], tot_loss[loss=0.165, simple_loss=0.2643, pruned_loss=0.0328, over 1428406.00 frames.], batch size: 31, lr: 3.10e-04
+2022-04-30 00:51:06,863 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 00:51:22,143 INFO [train.py:792] (2/8) Epoch 24, validation: loss=0.1679, simple_loss=0.2653, pruned_loss=0.03523, over 698248.00 frames.
+2022-04-30 00:52:37,060 INFO [train.py:763] (2/8) Epoch 24, batch 3050, loss[loss=0.1687, simple_loss=0.2878, pruned_loss=0.02483, over 7113.00 frames.], tot_loss[loss=0.165, simple_loss=0.2642, pruned_loss=0.03294, over 1428593.14 frames.], batch size: 21, lr: 3.10e-04
+2022-04-30 00:53:42,760 INFO [train.py:763] (2/8) Epoch 24, batch 3100, loss[loss=0.148, simple_loss=0.2379, pruned_loss=0.02902, over 6773.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2634, pruned_loss=0.03269, over 1429522.80 frames.], batch size: 15, lr: 3.10e-04
+2022-04-30 00:54:48,068 INFO [train.py:763] (2/8) Epoch 24, batch 3150, loss[loss=0.1492, simple_loss=0.2452, pruned_loss=0.02658, over 7270.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2642, pruned_loss=0.03278, over 1431257.29 frames.], batch size: 19, lr: 3.10e-04
+2022-04-30 00:55:53,502 INFO [train.py:763] (2/8) Epoch 24, batch 3200, loss[loss=0.1589, simple_loss=0.2561, pruned_loss=0.03088, over 4982.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2638, pruned_loss=0.0327, over 1429456.04 frames.], batch size: 53, lr: 3.10e-04
+2022-04-30 00:56:59,202 INFO [train.py:763] (2/8) Epoch 24, batch 3250, loss[loss=0.19, simple_loss=0.2838, pruned_loss=0.0481, over 7239.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2642, pruned_loss=0.03318, over 1427107.17 frames.], batch size: 20, lr: 3.10e-04
+2022-04-30 00:58:05,419 INFO [train.py:763] (2/8) Epoch 24, batch 3300, loss[loss=0.1737, simple_loss=0.2494, pruned_loss=0.04902, over 7163.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2643, pruned_loss=0.03297, over 1426512.19 frames.], batch size: 19, lr: 3.10e-04
+2022-04-30 00:59:11,081 INFO [train.py:763] (2/8) Epoch 24, batch 3350, loss[loss=0.1597, simple_loss=0.2521, pruned_loss=0.03369, over 7260.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2646, pruned_loss=0.03317, over 1423608.37 frames.], batch size: 19, lr: 3.10e-04
+2022-04-30 01:00:16,803 INFO [train.py:763] (2/8) Epoch 24, batch 3400, loss[loss=0.1612, simple_loss=0.248, pruned_loss=0.03722, over 7275.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2638, pruned_loss=0.03324, over 1424838.71 frames.], batch size: 17, lr: 3.10e-04
+2022-04-30 01:01:22,327 INFO [train.py:763] (2/8) Epoch 24, batch 3450, loss[loss=0.1669, simple_loss=0.2783, pruned_loss=0.02772, over 7226.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2641, pruned_loss=0.03334, over 1421184.69 frames.], batch size: 21, lr: 3.10e-04
+2022-04-30 01:02:27,608 INFO [train.py:763] (2/8) Epoch 24, batch 3500, loss[loss=0.1501, simple_loss=0.2461, pruned_loss=0.02711, over 7128.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2642, pruned_loss=0.03369, over 1422354.30 frames.], batch size: 17, lr: 3.10e-04
+2022-04-30 01:03:33,195 INFO [train.py:763] (2/8) Epoch 24, batch 3550, loss[loss=0.1897, simple_loss=0.2934, pruned_loss=0.04297, over 7326.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2651, pruned_loss=0.03413, over 1424056.80 frames.], batch size: 20, lr: 3.10e-04
+2022-04-30 01:04:38,395 INFO [train.py:763] (2/8) Epoch 24, batch 3600, loss[loss=0.2024, simple_loss=0.2993, pruned_loss=0.05275, over 7199.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2664, pruned_loss=0.03437, over 1421904.40 frames.], batch size: 23, lr: 3.10e-04
+2022-04-30 01:05:45,314 INFO [train.py:763] (2/8) Epoch 24, batch 3650, loss[loss=0.1757, simple_loss=0.2801, pruned_loss=0.03563, over 6425.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2662, pruned_loss=0.03437, over 1417435.11 frames.], batch size: 37, lr: 3.10e-04
+2022-04-30 01:06:51,859 INFO [train.py:763] (2/8) Epoch 24, batch 3700, loss[loss=0.1623, simple_loss=0.263, pruned_loss=0.03082, over 7426.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2651, pruned_loss=0.03388, over 1420860.71 frames.], batch size: 20, lr: 3.10e-04
+2022-04-30 01:07:57,540 INFO [train.py:763] (2/8) Epoch 24, batch 3750, loss[loss=0.183, simple_loss=0.2844, pruned_loss=0.04079, over 7373.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2659, pruned_loss=0.03449, over 1423195.13 frames.], batch size: 23, lr: 3.09e-04
+2022-04-30 01:09:02,949 INFO [train.py:763] (2/8) Epoch 24, batch 3800, loss[loss=0.1873, simple_loss=0.2768, pruned_loss=0.0489, over 5281.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2656, pruned_loss=0.03435, over 1422746.92 frames.], batch size: 53, lr: 3.09e-04
+2022-04-30 01:10:08,026 INFO [train.py:763] (2/8) Epoch 24, batch 3850, loss[loss=0.1475, simple_loss=0.2455, pruned_loss=0.02476, over 7291.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2659, pruned_loss=0.03441, over 1422557.09 frames.], batch size: 18, lr: 3.09e-04
+2022-04-30 01:11:13,746 INFO [train.py:763] (2/8) Epoch 24, batch 3900, loss[loss=0.1677, simple_loss=0.2586, pruned_loss=0.03845, over 7256.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2664, pruned_loss=0.03453, over 1422339.01 frames.], batch size: 19, lr: 3.09e-04
+2022-04-30 01:12:19,226 INFO [train.py:763] (2/8) Epoch 24, batch 3950, loss[loss=0.1567, simple_loss=0.2429, pruned_loss=0.03524, over 7425.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2659, pruned_loss=0.03381, over 1424323.56 frames.], batch size: 18, lr: 3.09e-04
+2022-04-30 01:13:24,347 INFO [train.py:763] (2/8) Epoch 24, batch 4000, loss[loss=0.1706, simple_loss=0.277, pruned_loss=0.03207, over 7324.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2655, pruned_loss=0.03332, over 1423511.56 frames.], batch size: 21, lr: 3.09e-04
+2022-04-30 01:14:29,870 INFO [train.py:763] (2/8) Epoch 24, batch 4050, loss[loss=0.1684, simple_loss=0.2677, pruned_loss=0.03452, over 7428.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2656, pruned_loss=0.03352, over 1421939.15 frames.], batch size: 20, lr: 3.09e-04
+2022-04-30 01:15:36,734 INFO [train.py:763] (2/8) Epoch 24, batch 4100, loss[loss=0.1852, simple_loss=0.282, pruned_loss=0.04418, over 6588.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2659, pruned_loss=0.03369, over 1423500.89 frames.], batch size: 38, lr: 3.09e-04
+2022-04-30 01:16:43,482 INFO [train.py:763] (2/8) Epoch 24, batch 4150, loss[loss=0.1605, simple_loss=0.2596, pruned_loss=0.03074, over 7216.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2658, pruned_loss=0.03375, over 1419400.20 frames.], batch size: 21, lr: 3.09e-04
+2022-04-30 01:17:50,166 INFO [train.py:763] (2/8) Epoch 24, batch 4200, loss[loss=0.1904, simple_loss=0.2936, pruned_loss=0.04361, over 7211.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2674, pruned_loss=0.03422, over 1420808.89 frames.], batch size: 23, lr: 3.09e-04
+2022-04-30 01:18:56,565 INFO [train.py:763] (2/8) Epoch 24, batch 4250, loss[loss=0.1716, simple_loss=0.2847, pruned_loss=0.0293, over 6479.00 frames.], tot_loss[loss=0.168, simple_loss=0.2672, pruned_loss=0.0344, over 1415389.68 frames.], batch size: 38, lr: 3.09e-04
+2022-04-30 01:20:02,370 INFO [train.py:763] (2/8) Epoch 24, batch 4300, loss[loss=0.1589, simple_loss=0.2611, pruned_loss=0.02835, over 7156.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2665, pruned_loss=0.03424, over 1414617.97 frames.], batch size: 19, lr: 3.09e-04
+2022-04-30 01:21:09,409 INFO [train.py:763] (2/8) Epoch 24, batch 4350, loss[loss=0.1842, simple_loss=0.2825, pruned_loss=0.04298, over 7277.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2652, pruned_loss=0.03397, over 1415512.20 frames.], batch size: 25, lr: 3.09e-04
+2022-04-30 01:22:16,101 INFO [train.py:763] (2/8) Epoch 24, batch 4400, loss[loss=0.1834, simple_loss=0.2917, pruned_loss=0.03751, over 7281.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2664, pruned_loss=0.03411, over 1413968.72 frames.], batch size: 24, lr: 3.09e-04
+2022-04-30 01:23:21,723 INFO [train.py:763] (2/8) Epoch 24, batch 4450, loss[loss=0.1913, simple_loss=0.2882, pruned_loss=0.04715, over 7304.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2673, pruned_loss=0.03423, over 1404465.15 frames.], batch size: 25, lr: 3.09e-04
+2022-04-30 01:24:28,207 INFO [train.py:763] (2/8) Epoch 24, batch 4500, loss[loss=0.1846, simple_loss=0.2781, pruned_loss=0.04558, over 4940.00 frames.], tot_loss[loss=0.1697, simple_loss=0.269, pruned_loss=0.03517, over 1388315.15 frames.], batch size: 52, lr: 3.08e-04
+2022-04-30 01:25:32,947 INFO [train.py:763] (2/8) Epoch 24, batch 4550, loss[loss=0.1768, simple_loss=0.2776, pruned_loss=0.03796, over 5287.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2701, pruned_loss=0.0354, over 1350073.09 frames.], batch size: 55, lr: 3.08e-04
+2022-04-30 01:26:52,283 INFO [train.py:763] (2/8) Epoch 25, batch 0, loss[loss=0.1966, simple_loss=0.3019, pruned_loss=0.04567, over 7208.00 frames.], tot_loss[loss=0.1966, simple_loss=0.3019, pruned_loss=0.04567, over 7208.00 frames.], batch size: 21, lr: 3.02e-04
+2022-04-30 01:27:58,470 INFO [train.py:763] (2/8) Epoch 25, batch 50, loss[loss=0.1768, simple_loss=0.2808, pruned_loss=0.03638, over 7320.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2621, pruned_loss=0.03185, over 322871.13 frames.], batch size: 21, lr: 3.02e-04
+2022-04-30 01:29:03,628 INFO [train.py:763] (2/8) Epoch 25, batch 100, loss[loss=0.1709, simple_loss=0.2689, pruned_loss=0.03646, over 4792.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2648, pruned_loss=0.03201, over 566715.63 frames.], batch size: 52, lr: 3.02e-04
+2022-04-30 01:30:08,881 INFO [train.py:763] (2/8) Epoch 25, batch 150, loss[loss=0.1851, simple_loss=0.2671, pruned_loss=0.05152, over 7275.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2661, pruned_loss=0.03246, over 760354.77 frames.], batch size: 17, lr: 3.02e-04
+2022-04-30 01:31:14,492 INFO [train.py:763] (2/8) Epoch 25, batch 200, loss[loss=0.1784, simple_loss=0.2749, pruned_loss=0.04097, over 7390.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2643, pruned_loss=0.03219, over 907076.82 frames.], batch size: 23, lr: 3.02e-04
+2022-04-30 01:32:20,359 INFO [train.py:763] (2/8) Epoch 25, batch 250, loss[loss=0.1706, simple_loss=0.2685, pruned_loss=0.03638, over 7210.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2651, pruned_loss=0.03269, over 1019767.59 frames.], batch size: 22, lr: 3.02e-04
+2022-04-30 01:33:26,235 INFO [train.py:763] (2/8) Epoch 25, batch 300, loss[loss=0.1527, simple_loss=0.2466, pruned_loss=0.02941, over 7328.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2658, pruned_loss=0.03334, over 1106150.88 frames.], batch size: 20, lr: 3.02e-04
+2022-04-30 01:34:31,514 INFO [train.py:763] (2/8) Epoch 25, batch 350, loss[loss=0.1663, simple_loss=0.2642, pruned_loss=0.03419, over 7162.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2644, pruned_loss=0.03246, over 1175898.11 frames.], batch size: 18, lr: 3.02e-04
+2022-04-30 01:35:36,787 INFO [train.py:763] (2/8) Epoch 25, batch 400, loss[loss=0.1406, simple_loss=0.2321, pruned_loss=0.02457, over 7409.00 frames.], tot_loss[loss=0.165, simple_loss=0.2648, pruned_loss=0.0326, over 1233210.92 frames.], batch size: 18, lr: 3.02e-04
+2022-04-30 01:36:42,352 INFO [train.py:763] (2/8) Epoch 25, batch 450, loss[loss=0.1699, simple_loss=0.2793, pruned_loss=0.03025, over 7408.00 frames.], tot_loss[loss=0.1644, simple_loss=0.264, pruned_loss=0.03237, over 1273967.94 frames.], batch size: 21, lr: 3.02e-04
+2022-04-30 01:37:47,499 INFO [train.py:763] (2/8) Epoch 25, batch 500, loss[loss=0.1878, simple_loss=0.2887, pruned_loss=0.04342, over 7370.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2645, pruned_loss=0.0325, over 1302201.44 frames.], batch size: 23, lr: 3.02e-04
+2022-04-30 01:38:52,806 INFO [train.py:763] (2/8) Epoch 25, batch 550, loss[loss=0.1677, simple_loss=0.28, pruned_loss=0.02767, over 7238.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2634, pruned_loss=0.03217, over 1328582.31 frames.], batch size: 20, lr: 3.02e-04
+2022-04-30 01:39:58,984 INFO [train.py:763] (2/8) Epoch 25, batch 600, loss[loss=0.1649, simple_loss=0.2662, pruned_loss=0.03183, over 7101.00 frames.], tot_loss[loss=0.164, simple_loss=0.2636, pruned_loss=0.03218, over 1347433.07 frames.], batch size: 28, lr: 3.02e-04
+2022-04-30 01:41:04,679 INFO [train.py:763] (2/8) Epoch 25, batch 650, loss[loss=0.1663, simple_loss=0.2618, pruned_loss=0.03546, over 7333.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2629, pruned_loss=0.03239, over 1362215.33 frames.], batch size: 20, lr: 3.02e-04
+2022-04-30 01:42:10,705 INFO [train.py:763] (2/8) Epoch 25, batch 700, loss[loss=0.1537, simple_loss=0.2564, pruned_loss=0.02554, over 7143.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2633, pruned_loss=0.03248, over 1374664.21 frames.], batch size: 20, lr: 3.02e-04
+2022-04-30 01:43:16,095 INFO [train.py:763] (2/8) Epoch 25, batch 750, loss[loss=0.1623, simple_loss=0.2618, pruned_loss=0.03143, over 7429.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2638, pruned_loss=0.03249, over 1389751.77 frames.], batch size: 20, lr: 3.01e-04
+2022-04-30 01:44:20,961 INFO [train.py:763] (2/8) Epoch 25, batch 800, loss[loss=0.1677, simple_loss=0.2767, pruned_loss=0.02934, over 6772.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2641, pruned_loss=0.03269, over 1394576.95 frames.], batch size: 31, lr: 3.01e-04
+2022-04-30 01:45:26,279 INFO [train.py:763] (2/8) Epoch 25, batch 850, loss[loss=0.1663, simple_loss=0.2648, pruned_loss=0.03388, over 7112.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2647, pruned_loss=0.03249, over 1405214.06 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:46:33,098 INFO [train.py:763] (2/8) Epoch 25, batch 900, loss[loss=0.1399, simple_loss=0.2335, pruned_loss=0.02317, over 6788.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2648, pruned_loss=0.03294, over 1405620.16 frames.], batch size: 15, lr: 3.01e-04
+2022-04-30 01:47:40,152 INFO [train.py:763] (2/8) Epoch 25, batch 950, loss[loss=0.1345, simple_loss=0.2235, pruned_loss=0.02274, over 7289.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2657, pruned_loss=0.03334, over 1412288.40 frames.], batch size: 17, lr: 3.01e-04
+2022-04-30 01:48:46,805 INFO [train.py:763] (2/8) Epoch 25, batch 1000, loss[loss=0.1898, simple_loss=0.294, pruned_loss=0.04281, over 7122.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2659, pruned_loss=0.03327, over 1412041.20 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:49:52,611 INFO [train.py:763] (2/8) Epoch 25, batch 1050, loss[loss=0.181, simple_loss=0.2752, pruned_loss=0.04342, over 5180.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2665, pruned_loss=0.03349, over 1412754.81 frames.], batch size: 52, lr: 3.01e-04
+2022-04-30 01:50:59,147 INFO [train.py:763] (2/8) Epoch 25, batch 1100, loss[loss=0.1684, simple_loss=0.2695, pruned_loss=0.03367, over 7110.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2663, pruned_loss=0.03322, over 1414266.64 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:52:04,511 INFO [train.py:763] (2/8) Epoch 25, batch 1150, loss[loss=0.1928, simple_loss=0.2947, pruned_loss=0.04549, over 7378.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2663, pruned_loss=0.03348, over 1418364.92 frames.], batch size: 23, lr: 3.01e-04
+2022-04-30 01:53:10,906 INFO [train.py:763] (2/8) Epoch 25, batch 1200, loss[loss=0.1352, simple_loss=0.2321, pruned_loss=0.01912, over 7134.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2662, pruned_loss=0.03369, over 1422197.70 frames.], batch size: 17, lr: 3.01e-04
+2022-04-30 01:54:16,904 INFO [train.py:763] (2/8) Epoch 25, batch 1250, loss[loss=0.1713, simple_loss=0.2711, pruned_loss=0.03577, over 7319.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2659, pruned_loss=0.03337, over 1423883.50 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:55:23,797 INFO [train.py:763] (2/8) Epoch 25, batch 1300, loss[loss=0.139, simple_loss=0.24, pruned_loss=0.01897, over 7435.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2652, pruned_loss=0.0333, over 1427565.59 frames.], batch size: 20, lr: 3.01e-04
+2022-04-30 01:56:30,373 INFO [train.py:763] (2/8) Epoch 25, batch 1350, loss[loss=0.1606, simple_loss=0.2705, pruned_loss=0.02537, over 7331.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2654, pruned_loss=0.0334, over 1427736.73 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:57:36,862 INFO [train.py:763] (2/8) Epoch 25, batch 1400, loss[loss=0.1693, simple_loss=0.274, pruned_loss=0.03231, over 7342.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2654, pruned_loss=0.03362, over 1428021.18 frames.], batch size: 22, lr: 3.01e-04
+2022-04-30 01:58:42,267 INFO [train.py:763] (2/8) Epoch 25, batch 1450, loss[loss=0.1529, simple_loss=0.2376, pruned_loss=0.03415, over 7006.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2657, pruned_loss=0.03358, over 1429426.67 frames.], batch size: 16, lr: 3.01e-04
+2022-04-30 01:59:49,359 INFO [train.py:763] (2/8) Epoch 25, batch 1500, loss[loss=0.1542, simple_loss=0.2551, pruned_loss=0.02665, over 7216.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2647, pruned_loss=0.03337, over 1428997.46 frames.], batch size: 21, lr: 3.00e-04
+2022-04-30 02:00:55,045 INFO [train.py:763] (2/8) Epoch 25, batch 1550, loss[loss=0.1493, simple_loss=0.2395, pruned_loss=0.02959, over 7130.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2641, pruned_loss=0.03309, over 1428020.95 frames.], batch size: 17, lr: 3.00e-04
+2022-04-30 02:02:00,070 INFO [train.py:763] (2/8) Epoch 25, batch 1600, loss[loss=0.1711, simple_loss=0.2746, pruned_loss=0.03378, over 7135.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2659, pruned_loss=0.03376, over 1425355.86 frames.], batch size: 20, lr: 3.00e-04
+2022-04-30 02:03:05,632 INFO [train.py:763] (2/8) Epoch 25, batch 1650, loss[loss=0.1604, simple_loss=0.2621, pruned_loss=0.02934, over 7085.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2645, pruned_loss=0.03335, over 1426406.79 frames.], batch size: 28, lr: 3.00e-04
+2022-04-30 02:04:10,608 INFO [train.py:763] (2/8) Epoch 25, batch 1700, loss[loss=0.1921, simple_loss=0.2982, pruned_loss=0.04304, over 7315.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2652, pruned_loss=0.03331, over 1426054.24 frames.], batch size: 21, lr: 3.00e-04
+2022-04-30 02:05:15,838 INFO [train.py:763] (2/8) Epoch 25, batch 1750, loss[loss=0.141, simple_loss=0.237, pruned_loss=0.02248, over 7125.00 frames.], tot_loss[loss=0.1656, simple_loss=0.265, pruned_loss=0.03304, over 1425182.47 frames.], batch size: 17, lr: 3.00e-04
+2022-04-30 02:06:21,037 INFO [train.py:763] (2/8) Epoch 25, batch 1800, loss[loss=0.1555, simple_loss=0.2644, pruned_loss=0.02329, over 7145.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2652, pruned_loss=0.03333, over 1421500.62 frames.], batch size: 20, lr: 3.00e-04
+2022-04-30 02:07:26,295 INFO [train.py:763] (2/8) Epoch 25, batch 1850, loss[loss=0.1625, simple_loss=0.2628, pruned_loss=0.03113, over 7437.00 frames.], tot_loss[loss=0.1659, simple_loss=0.265, pruned_loss=0.03342, over 1422662.07 frames.], batch size: 20, lr: 3.00e-04
+2022-04-30 02:08:31,444 INFO [train.py:763] (2/8) Epoch 25, batch 1900, loss[loss=0.1342, simple_loss=0.2277, pruned_loss=0.0204, over 7135.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2656, pruned_loss=0.0334, over 1423252.08 frames.], batch size: 17, lr: 3.00e-04
+2022-04-30 02:09:36,776 INFO [train.py:763] (2/8) Epoch 25, batch 1950, loss[loss=0.1925, simple_loss=0.2905, pruned_loss=0.04725, over 4978.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2655, pruned_loss=0.03377, over 1420958.87 frames.], batch size: 53, lr: 3.00e-04
+2022-04-30 02:10:42,027 INFO [train.py:763] (2/8) Epoch 25, batch 2000, loss[loss=0.151, simple_loss=0.2478, pruned_loss=0.02714, over 7162.00 frames.], tot_loss[loss=0.1663, simple_loss=0.265, pruned_loss=0.03381, over 1417612.37 frames.], batch size: 19, lr: 3.00e-04
+2022-04-30 02:11:47,907 INFO [train.py:763] (2/8) Epoch 25, batch 2050, loss[loss=0.1747, simple_loss=0.2763, pruned_loss=0.03654, over 7320.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2647, pruned_loss=0.03351, over 1418625.83 frames.], batch size: 20, lr: 3.00e-04
+2022-04-30 02:12:54,271 INFO [train.py:763] (2/8) Epoch 25, batch 2100, loss[loss=0.1638, simple_loss=0.269, pruned_loss=0.02932, over 7202.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2656, pruned_loss=0.03344, over 1418246.36 frames.], batch size: 22, lr: 3.00e-04
+2022-04-30 02:13:59,520 INFO [train.py:763] (2/8) Epoch 25, batch 2150, loss[loss=0.1656, simple_loss=0.2592, pruned_loss=0.03604, over 7177.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2659, pruned_loss=0.03329, over 1420817.67 frames.], batch size: 18, lr: 3.00e-04
+2022-04-30 02:15:05,482 INFO [train.py:763] (2/8) Epoch 25, batch 2200, loss[loss=0.1892, simple_loss=0.2876, pruned_loss=0.0454, over 7002.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2656, pruned_loss=0.03305, over 1423096.86 frames.], batch size: 28, lr: 3.00e-04
+2022-04-30 02:16:11,383 INFO [train.py:763] (2/8) Epoch 25, batch 2250, loss[loss=0.178, simple_loss=0.2791, pruned_loss=0.03848, over 7376.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2649, pruned_loss=0.03278, over 1425480.33 frames.], batch size: 23, lr: 3.00e-04
+2022-04-30 02:17:16,591 INFO [train.py:763] (2/8) Epoch 25, batch 2300, loss[loss=0.1529, simple_loss=0.2474, pruned_loss=0.02919, over 7059.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2656, pruned_loss=0.03294, over 1426001.22 frames.], batch size: 18, lr: 2.99e-04
+2022-04-30 02:18:23,379 INFO [train.py:763] (2/8) Epoch 25, batch 2350, loss[loss=0.1409, simple_loss=0.2407, pruned_loss=0.02059, over 7250.00 frames.], tot_loss[loss=0.1654, simple_loss=0.265, pruned_loss=0.03289, over 1426382.96 frames.], batch size: 19, lr: 2.99e-04
+2022-04-30 02:19:30,573 INFO [train.py:763] (2/8) Epoch 25, batch 2400, loss[loss=0.1756, simple_loss=0.2743, pruned_loss=0.03843, over 7384.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2642, pruned_loss=0.03227, over 1423478.34 frames.], batch size: 23, lr: 2.99e-04
+2022-04-30 02:20:35,956 INFO [train.py:763] (2/8) Epoch 25, batch 2450, loss[loss=0.1533, simple_loss=0.2629, pruned_loss=0.02182, over 6679.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2642, pruned_loss=0.03262, over 1421728.29 frames.], batch size: 31, lr: 2.99e-04
+2022-04-30 02:21:42,821 INFO [train.py:763] (2/8) Epoch 25, batch 2500, loss[loss=0.1489, simple_loss=0.2448, pruned_loss=0.02655, over 7351.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2633, pruned_loss=0.03248, over 1423599.16 frames.], batch size: 19, lr: 2.99e-04
+2022-04-30 02:22:48,783 INFO [train.py:763] (2/8) Epoch 25, batch 2550, loss[loss=0.1596, simple_loss=0.2497, pruned_loss=0.03471, over 7418.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2633, pruned_loss=0.03285, over 1426188.00 frames.], batch size: 18, lr: 2.99e-04
+2022-04-30 02:23:56,375 INFO [train.py:763] (2/8) Epoch 25, batch 2600, loss[loss=0.1559, simple_loss=0.2514, pruned_loss=0.03015, over 7164.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2638, pruned_loss=0.03337, over 1424457.34 frames.], batch size: 19, lr: 2.99e-04
+2022-04-30 02:25:02,538 INFO [train.py:763] (2/8) Epoch 25, batch 2650, loss[loss=0.1891, simple_loss=0.3016, pruned_loss=0.03829, over 7085.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2645, pruned_loss=0.03331, over 1420293.49 frames.], batch size: 28, lr: 2.99e-04
+2022-04-30 02:26:07,755 INFO [train.py:763] (2/8) Epoch 25, batch 2700, loss[loss=0.1392, simple_loss=0.2377, pruned_loss=0.02032, over 7263.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2648, pruned_loss=0.0333, over 1420980.29 frames.], batch size: 19, lr: 2.99e-04
+2022-04-30 02:27:12,937 INFO [train.py:763] (2/8) Epoch 25, batch 2750, loss[loss=0.1805, simple_loss=0.2878, pruned_loss=0.03661, over 7311.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2661, pruned_loss=0.0341, over 1413984.55 frames.], batch size: 25, lr: 2.99e-04
+2022-04-30 02:28:19,368 INFO [train.py:763] (2/8) Epoch 25, batch 2800, loss[loss=0.1604, simple_loss=0.2594, pruned_loss=0.03069, over 7274.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2659, pruned_loss=0.03386, over 1416326.35 frames.], batch size: 18, lr: 2.99e-04
+2022-04-30 02:29:24,928 INFO [train.py:763] (2/8) Epoch 25, batch 2850, loss[loss=0.1617, simple_loss=0.2713, pruned_loss=0.02602, over 7409.00 frames.], tot_loss[loss=0.166, simple_loss=0.2646, pruned_loss=0.03368, over 1411397.12 frames.], batch size: 21, lr: 2.99e-04
+2022-04-30 02:30:30,618 INFO [train.py:763] (2/8) Epoch 25, batch 2900, loss[loss=0.1677, simple_loss=0.2839, pruned_loss=0.02571, over 7149.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2642, pruned_loss=0.0335, over 1417375.56 frames.], batch size: 20, lr: 2.99e-04
+2022-04-30 02:31:35,883 INFO [train.py:763] (2/8) Epoch 25, batch 2950, loss[loss=0.1506, simple_loss=0.252, pruned_loss=0.02457, over 7326.00 frames.], tot_loss[loss=0.166, simple_loss=0.265, pruned_loss=0.03355, over 1418522.12 frames.], batch size: 20, lr: 2.99e-04
+2022-04-30 02:32:41,159 INFO [train.py:763] (2/8) Epoch 25, batch 3000, loss[loss=0.1795, simple_loss=0.2911, pruned_loss=0.03391, over 6424.00 frames.], tot_loss[loss=0.166, simple_loss=0.2652, pruned_loss=0.03343, over 1422121.90 frames.], batch size: 38, lr: 2.99e-04
+2022-04-30 02:32:41,160 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 02:32:56,273 INFO [train.py:792] (2/8) Epoch 25, validation: loss=0.1697, simple_loss=0.2684, pruned_loss=0.03548, over 698248.00 frames.
+2022-04-30 02:34:02,072 INFO [train.py:763] (2/8) Epoch 25, batch 3050, loss[loss=0.1697, simple_loss=0.277, pruned_loss=0.03116, over 7322.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2658, pruned_loss=0.03355, over 1421458.96 frames.], batch size: 22, lr: 2.99e-04
+2022-04-30 02:35:09,270 INFO [train.py:763] (2/8) Epoch 25, batch 3100, loss[loss=0.1659, simple_loss=0.266, pruned_loss=0.03292, over 7270.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2652, pruned_loss=0.03321, over 1419287.00 frames.], batch size: 19, lr: 2.98e-04
+2022-04-30 02:36:16,359 INFO [train.py:763] (2/8) Epoch 25, batch 3150, loss[loss=0.1521, simple_loss=0.2419, pruned_loss=0.03116, over 7144.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2657, pruned_loss=0.03352, over 1417652.91 frames.], batch size: 17, lr: 2.98e-04
+2022-04-30 02:37:22,256 INFO [train.py:763] (2/8) Epoch 25, batch 3200, loss[loss=0.1566, simple_loss=0.2646, pruned_loss=0.02426, over 7153.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2655, pruned_loss=0.0334, over 1420533.13 frames.], batch size: 19, lr: 2.98e-04
+2022-04-30 02:38:29,210 INFO [train.py:763] (2/8) Epoch 25, batch 3250, loss[loss=0.1369, simple_loss=0.2295, pruned_loss=0.02219, over 7268.00 frames.], tot_loss[loss=0.1649, simple_loss=0.264, pruned_loss=0.03286, over 1423606.41 frames.], batch size: 18, lr: 2.98e-04
+2022-04-30 02:39:35,755 INFO [train.py:763] (2/8) Epoch 25, batch 3300, loss[loss=0.1598, simple_loss=0.2619, pruned_loss=0.0289, over 7167.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2645, pruned_loss=0.03323, over 1416553.01 frames.], batch size: 26, lr: 2.98e-04
+2022-04-30 02:40:42,704 INFO [train.py:763] (2/8) Epoch 25, batch 3350, loss[loss=0.1624, simple_loss=0.2767, pruned_loss=0.02401, over 7327.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2642, pruned_loss=0.03329, over 1413890.72 frames.], batch size: 21, lr: 2.98e-04
+2022-04-30 02:41:49,869 INFO [train.py:763] (2/8) Epoch 25, batch 3400, loss[loss=0.1532, simple_loss=0.2533, pruned_loss=0.02656, over 6248.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2638, pruned_loss=0.03303, over 1419799.72 frames.], batch size: 38, lr: 2.98e-04
+2022-04-30 02:42:55,391 INFO [train.py:763] (2/8) Epoch 25, batch 3450, loss[loss=0.1382, simple_loss=0.228, pruned_loss=0.02414, over 7165.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2636, pruned_loss=0.033, over 1419085.94 frames.], batch size: 18, lr: 2.98e-04
+2022-04-30 02:44:00,602 INFO [train.py:763] (2/8) Epoch 25, batch 3500, loss[loss=0.1671, simple_loss=0.2771, pruned_loss=0.0286, over 7369.00 frames.], tot_loss[loss=0.1649, simple_loss=0.264, pruned_loss=0.03284, over 1418212.52 frames.], batch size: 23, lr: 2.98e-04
+2022-04-30 02:45:06,555 INFO [train.py:763] (2/8) Epoch 25, batch 3550, loss[loss=0.1567, simple_loss=0.2615, pruned_loss=0.02591, over 7429.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2629, pruned_loss=0.03222, over 1420436.46 frames.], batch size: 21, lr: 2.98e-04
+2022-04-30 02:46:12,315 INFO [train.py:763] (2/8) Epoch 25, batch 3600, loss[loss=0.1685, simple_loss=0.2732, pruned_loss=0.0319, over 7193.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2626, pruned_loss=0.03244, over 1425047.86 frames.], batch size: 23, lr: 2.98e-04
+2022-04-30 02:47:18,086 INFO [train.py:763] (2/8) Epoch 25, batch 3650, loss[loss=0.1513, simple_loss=0.246, pruned_loss=0.02824, over 7269.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2635, pruned_loss=0.03297, over 1426597.42 frames.], batch size: 19, lr: 2.98e-04
+2022-04-30 02:48:25,753 INFO [train.py:763] (2/8) Epoch 25, batch 3700, loss[loss=0.1679, simple_loss=0.2637, pruned_loss=0.03602, over 7068.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2634, pruned_loss=0.03303, over 1424862.65 frames.], batch size: 18, lr: 2.98e-04
+2022-04-30 02:49:32,856 INFO [train.py:763] (2/8) Epoch 25, batch 3750, loss[loss=0.1906, simple_loss=0.2842, pruned_loss=0.04848, over 7157.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2637, pruned_loss=0.03305, over 1422779.41 frames.], batch size: 19, lr: 2.98e-04
+2022-04-30 02:50:38,245 INFO [train.py:763] (2/8) Epoch 25, batch 3800, loss[loss=0.1561, simple_loss=0.2531, pruned_loss=0.02954, over 6207.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2643, pruned_loss=0.03298, over 1419600.44 frames.], batch size: 37, lr: 2.98e-04
+2022-04-30 02:51:43,561 INFO [train.py:763] (2/8) Epoch 25, batch 3850, loss[loss=0.1491, simple_loss=0.2616, pruned_loss=0.01827, over 7150.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2644, pruned_loss=0.03343, over 1418323.89 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 02:52:57,809 INFO [train.py:763] (2/8) Epoch 25, batch 3900, loss[loss=0.1514, simple_loss=0.2453, pruned_loss=0.02878, over 7434.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2649, pruned_loss=0.0335, over 1420585.72 frames.], batch size: 18, lr: 2.97e-04
+2022-04-30 02:54:03,673 INFO [train.py:763] (2/8) Epoch 25, batch 3950, loss[loss=0.1693, simple_loss=0.2688, pruned_loss=0.03486, over 7239.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2647, pruned_loss=0.03337, over 1425085.91 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 02:55:09,636 INFO [train.py:763] (2/8) Epoch 25, batch 4000, loss[loss=0.1517, simple_loss=0.25, pruned_loss=0.02672, over 7421.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2648, pruned_loss=0.03317, over 1417614.10 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 02:56:14,884 INFO [train.py:763] (2/8) Epoch 25, batch 4050, loss[loss=0.1652, simple_loss=0.2627, pruned_loss=0.03379, over 7413.00 frames.], tot_loss[loss=0.1655, simple_loss=0.265, pruned_loss=0.03304, over 1419365.50 frames.], batch size: 21, lr: 2.97e-04
+2022-04-30 02:57:21,066 INFO [train.py:763] (2/8) Epoch 25, batch 4100, loss[loss=0.161, simple_loss=0.2658, pruned_loss=0.02808, over 7420.00 frames.], tot_loss[loss=0.1664, simple_loss=0.266, pruned_loss=0.03335, over 1417554.69 frames.], batch size: 21, lr: 2.97e-04
+2022-04-30 02:58:26,412 INFO [train.py:763] (2/8) Epoch 25, batch 4150, loss[loss=0.1485, simple_loss=0.2391, pruned_loss=0.02896, over 7259.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2649, pruned_loss=0.03287, over 1423043.09 frames.], batch size: 19, lr: 2.97e-04
+2022-04-30 02:59:32,217 INFO [train.py:763] (2/8) Epoch 25, batch 4200, loss[loss=0.1855, simple_loss=0.2884, pruned_loss=0.04134, over 7135.00 frames.], tot_loss[loss=0.1657, simple_loss=0.265, pruned_loss=0.03321, over 1420384.90 frames.], batch size: 28, lr: 2.97e-04
+2022-04-30 03:00:37,738 INFO [train.py:763] (2/8) Epoch 25, batch 4250, loss[loss=0.141, simple_loss=0.2355, pruned_loss=0.02324, over 7170.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2656, pruned_loss=0.03376, over 1419892.05 frames.], batch size: 18, lr: 2.97e-04
+2022-04-30 03:01:43,167 INFO [train.py:763] (2/8) Epoch 25, batch 4300, loss[loss=0.186, simple_loss=0.2907, pruned_loss=0.0407, over 7211.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2655, pruned_loss=0.03398, over 1423014.94 frames.], batch size: 26, lr: 2.97e-04
+2022-04-30 03:03:06,197 INFO [train.py:763] (2/8) Epoch 25, batch 4350, loss[loss=0.1513, simple_loss=0.252, pruned_loss=0.02528, over 7228.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2651, pruned_loss=0.03369, over 1416213.86 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 03:04:20,098 INFO [train.py:763] (2/8) Epoch 25, batch 4400, loss[loss=0.1504, simple_loss=0.2458, pruned_loss=0.02751, over 7067.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2661, pruned_loss=0.03375, over 1416145.89 frames.], batch size: 18, lr: 2.97e-04
+2022-04-30 03:05:34,207 INFO [train.py:763] (2/8) Epoch 25, batch 4450, loss[loss=0.1562, simple_loss=0.2549, pruned_loss=0.02874, over 7293.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2657, pruned_loss=0.03356, over 1414504.18 frames.], batch size: 24, lr: 2.97e-04
+2022-04-30 03:06:39,191 INFO [train.py:763] (2/8) Epoch 25, batch 4500, loss[loss=0.1501, simple_loss=0.2525, pruned_loss=0.0239, over 7324.00 frames.], tot_loss[loss=0.166, simple_loss=0.2652, pruned_loss=0.0334, over 1398918.97 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 03:08:11,348 INFO [train.py:763] (2/8) Epoch 25, batch 4550, loss[loss=0.2185, simple_loss=0.307, pruned_loss=0.06496, over 5030.00 frames.], tot_loss[loss=0.167, simple_loss=0.2659, pruned_loss=0.03404, over 1388827.07 frames.], batch size: 52, lr: 2.97e-04
+2022-04-30 03:09:39,539 INFO [train.py:763] (2/8) Epoch 26, batch 0, loss[loss=0.1693, simple_loss=0.2627, pruned_loss=0.03791, over 7152.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2627, pruned_loss=0.03791, over 7152.00 frames.], batch size: 18, lr: 2.91e-04
+2022-04-30 03:10:45,446 INFO [train.py:763] (2/8) Epoch 26, batch 50, loss[loss=0.1422, simple_loss=0.2307, pruned_loss=0.02685, over 7274.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2632, pruned_loss=0.03309, over 318724.44 frames.], batch size: 17, lr: 2.91e-04
+2022-04-30 03:11:50,708 INFO [train.py:763] (2/8) Epoch 26, batch 100, loss[loss=0.1511, simple_loss=0.2381, pruned_loss=0.03208, over 7289.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.03193, over 562978.93 frames.], batch size: 17, lr: 2.91e-04
+2022-04-30 03:12:56,047 INFO [train.py:763] (2/8) Epoch 26, batch 150, loss[loss=0.1975, simple_loss=0.2999, pruned_loss=0.04752, over 6529.00 frames.], tot_loss[loss=0.1639, simple_loss=0.264, pruned_loss=0.0319, over 751911.89 frames.], batch size: 38, lr: 2.91e-04
+2022-04-30 03:14:01,245 INFO [train.py:763] (2/8) Epoch 26, batch 200, loss[loss=0.1635, simple_loss=0.2698, pruned_loss=0.02865, over 7113.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2633, pruned_loss=0.03203, over 895307.66 frames.], batch size: 26, lr: 2.91e-04
+2022-04-30 03:15:07,039 INFO [train.py:763] (2/8) Epoch 26, batch 250, loss[loss=0.1592, simple_loss=0.27, pruned_loss=0.02422, over 6402.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2645, pruned_loss=0.03235, over 1007115.52 frames.], batch size: 38, lr: 2.91e-04
+2022-04-30 03:16:13,119 INFO [train.py:763] (2/8) Epoch 26, batch 300, loss[loss=0.1662, simple_loss=0.2768, pruned_loss=0.02774, over 6375.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2642, pruned_loss=0.03183, over 1100846.41 frames.], batch size: 37, lr: 2.91e-04
+2022-04-30 03:17:18,444 INFO [train.py:763] (2/8) Epoch 26, batch 350, loss[loss=0.1776, simple_loss=0.2907, pruned_loss=0.03227, over 6813.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2645, pruned_loss=0.03225, over 1168644.84 frames.], batch size: 31, lr: 2.91e-04
+2022-04-30 03:18:23,746 INFO [train.py:763] (2/8) Epoch 26, batch 400, loss[loss=0.1652, simple_loss=0.2733, pruned_loss=0.02852, over 7149.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2651, pruned_loss=0.03269, over 1229283.43 frames.], batch size: 20, lr: 2.91e-04
+2022-04-30 03:19:29,468 INFO [train.py:763] (2/8) Epoch 26, batch 450, loss[loss=0.1725, simple_loss=0.2769, pruned_loss=0.03405, over 7235.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2645, pruned_loss=0.03241, over 1276706.47 frames.], batch size: 20, lr: 2.91e-04
+2022-04-30 03:20:34,843 INFO [train.py:763] (2/8) Epoch 26, batch 500, loss[loss=0.1704, simple_loss=0.261, pruned_loss=0.03992, over 5239.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2639, pruned_loss=0.0323, over 1309173.91 frames.], batch size: 52, lr: 2.91e-04
+2022-04-30 03:21:40,166 INFO [train.py:763] (2/8) Epoch 26, batch 550, loss[loss=0.1712, simple_loss=0.2814, pruned_loss=0.03053, over 7200.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2644, pruned_loss=0.03248, over 1333343.76 frames.], batch size: 22, lr: 2.90e-04
+2022-04-30 03:22:45,576 INFO [train.py:763] (2/8) Epoch 26, batch 600, loss[loss=0.1688, simple_loss=0.2659, pruned_loss=0.03583, over 7259.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2642, pruned_loss=0.03234, over 1355811.49 frames.], batch size: 19, lr: 2.90e-04
+2022-04-30 03:23:51,105 INFO [train.py:763] (2/8) Epoch 26, batch 650, loss[loss=0.1517, simple_loss=0.2496, pruned_loss=0.02695, over 7277.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2639, pruned_loss=0.03235, over 1372534.08 frames.], batch size: 18, lr: 2.90e-04
+2022-04-30 03:24:56,235 INFO [train.py:763] (2/8) Epoch 26, batch 700, loss[loss=0.1677, simple_loss=0.2665, pruned_loss=0.03446, over 7119.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2647, pruned_loss=0.03242, over 1380744.05 frames.], batch size: 21, lr: 2.90e-04
+2022-04-30 03:26:12,123 INFO [train.py:763] (2/8) Epoch 26, batch 750, loss[loss=0.1699, simple_loss=0.2734, pruned_loss=0.03322, over 7142.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2647, pruned_loss=0.03243, over 1390482.55 frames.], batch size: 20, lr: 2.90e-04
+2022-04-30 03:27:17,950 INFO [train.py:763] (2/8) Epoch 26, batch 800, loss[loss=0.1625, simple_loss=0.2612, pruned_loss=0.03193, over 7240.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2644, pruned_loss=0.03239, over 1396243.34 frames.], batch size: 20, lr: 2.90e-04
+2022-04-30 03:28:23,822 INFO [train.py:763] (2/8) Epoch 26, batch 850, loss[loss=0.191, simple_loss=0.2821, pruned_loss=0.04992, over 5106.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2648, pruned_loss=0.03214, over 1398866.84 frames.], batch size: 52, lr: 2.90e-04
+2022-04-30 03:29:29,376 INFO [train.py:763] (2/8) Epoch 26, batch 900, loss[loss=0.1523, simple_loss=0.2531, pruned_loss=0.02572, over 7410.00 frames.], tot_loss[loss=0.164, simple_loss=0.264, pruned_loss=0.03198, over 1408264.86 frames.], batch size: 18, lr: 2.90e-04
+2022-04-30 03:30:35,251 INFO [train.py:763] (2/8) Epoch 26, batch 950, loss[loss=0.156, simple_loss=0.2497, pruned_loss=0.03115, over 7284.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2646, pruned_loss=0.03206, over 1409718.03 frames.], batch size: 16, lr: 2.90e-04
+2022-04-30 03:31:40,713 INFO [train.py:763] (2/8) Epoch 26, batch 1000, loss[loss=0.1911, simple_loss=0.2982, pruned_loss=0.04202, over 7305.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2649, pruned_loss=0.0324, over 1413009.71 frames.], batch size: 24, lr: 2.90e-04
+2022-04-30 03:32:46,138 INFO [train.py:763] (2/8) Epoch 26, batch 1050, loss[loss=0.1853, simple_loss=0.2881, pruned_loss=0.04126, over 7211.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2646, pruned_loss=0.03235, over 1419017.04 frames.], batch size: 23, lr: 2.90e-04
+2022-04-30 03:33:51,496 INFO [train.py:763] (2/8) Epoch 26, batch 1100, loss[loss=0.1875, simple_loss=0.2913, pruned_loss=0.0418, over 7191.00 frames.], tot_loss[loss=0.165, simple_loss=0.2647, pruned_loss=0.03272, over 1422788.39 frames.], batch size: 22, lr: 2.90e-04
+2022-04-30 03:34:56,892 INFO [train.py:763] (2/8) Epoch 26, batch 1150, loss[loss=0.1615, simple_loss=0.2545, pruned_loss=0.03428, over 7164.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2655, pruned_loss=0.03298, over 1423907.67 frames.], batch size: 19, lr: 2.90e-04
+2022-04-30 03:36:02,470 INFO [train.py:763] (2/8) Epoch 26, batch 1200, loss[loss=0.1609, simple_loss=0.2549, pruned_loss=0.03345, over 7297.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2652, pruned_loss=0.03279, over 1427451.05 frames.], batch size: 24, lr: 2.90e-04
+2022-04-30 03:37:08,326 INFO [train.py:763] (2/8) Epoch 26, batch 1250, loss[loss=0.1922, simple_loss=0.2954, pruned_loss=0.0445, over 6570.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2642, pruned_loss=0.03257, over 1426762.17 frames.], batch size: 38, lr: 2.90e-04
+2022-04-30 03:38:14,024 INFO [train.py:763] (2/8) Epoch 26, batch 1300, loss[loss=0.1717, simple_loss=0.2578, pruned_loss=0.04284, over 7285.00 frames.], tot_loss[loss=0.1647, simple_loss=0.264, pruned_loss=0.03267, over 1422566.05 frames.], batch size: 18, lr: 2.90e-04
+2022-04-30 03:39:20,365 INFO [train.py:763] (2/8) Epoch 26, batch 1350, loss[loss=0.1331, simple_loss=0.2314, pruned_loss=0.01742, over 7422.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2628, pruned_loss=0.03249, over 1426487.45 frames.], batch size: 18, lr: 2.89e-04
+2022-04-30 03:40:25,488 INFO [train.py:763] (2/8) Epoch 26, batch 1400, loss[loss=0.1949, simple_loss=0.2978, pruned_loss=0.04597, over 7197.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2631, pruned_loss=0.0328, over 1419576.50 frames.], batch size: 23, lr: 2.89e-04
+2022-04-30 03:41:30,973 INFO [train.py:763] (2/8) Epoch 26, batch 1450, loss[loss=0.1432, simple_loss=0.2446, pruned_loss=0.02093, over 7286.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2635, pruned_loss=0.03291, over 1421377.08 frames.], batch size: 18, lr: 2.89e-04
+2022-04-30 03:42:36,426 INFO [train.py:763] (2/8) Epoch 26, batch 1500, loss[loss=0.1709, simple_loss=0.2766, pruned_loss=0.03256, over 5375.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2632, pruned_loss=0.03263, over 1417960.58 frames.], batch size: 52, lr: 2.89e-04
+2022-04-30 03:43:42,570 INFO [train.py:763] (2/8) Epoch 26, batch 1550, loss[loss=0.1623, simple_loss=0.2718, pruned_loss=0.02644, over 7122.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2634, pruned_loss=0.03251, over 1420784.34 frames.], batch size: 21, lr: 2.89e-04
+2022-04-30 03:44:49,277 INFO [train.py:763] (2/8) Epoch 26, batch 1600, loss[loss=0.1493, simple_loss=0.2423, pruned_loss=0.02815, over 7259.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2623, pruned_loss=0.03244, over 1424969.44 frames.], batch size: 19, lr: 2.89e-04
+2022-04-30 03:45:54,874 INFO [train.py:763] (2/8) Epoch 26, batch 1650, loss[loss=0.2055, simple_loss=0.299, pruned_loss=0.056, over 7187.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2626, pruned_loss=0.03237, over 1429702.96 frames.], batch size: 26, lr: 2.89e-04
+2022-04-30 03:47:00,372 INFO [train.py:763] (2/8) Epoch 26, batch 1700, loss[loss=0.1697, simple_loss=0.2708, pruned_loss=0.03431, over 7344.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2628, pruned_loss=0.03216, over 1430885.17 frames.], batch size: 22, lr: 2.89e-04
+2022-04-30 03:48:06,015 INFO [train.py:763] (2/8) Epoch 26, batch 1750, loss[loss=0.1736, simple_loss=0.2819, pruned_loss=0.03265, over 7205.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2635, pruned_loss=0.0326, over 1431354.14 frames.], batch size: 26, lr: 2.89e-04
+2022-04-30 03:49:13,270 INFO [train.py:763] (2/8) Epoch 26, batch 1800, loss[loss=0.1819, simple_loss=0.2953, pruned_loss=0.03421, over 7103.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2636, pruned_loss=0.03252, over 1429903.09 frames.], batch size: 21, lr: 2.89e-04
+2022-04-30 03:50:19,933 INFO [train.py:763] (2/8) Epoch 26, batch 1850, loss[loss=0.1785, simple_loss=0.2687, pruned_loss=0.0441, over 4908.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2632, pruned_loss=0.03268, over 1429842.05 frames.], batch size: 52, lr: 2.89e-04
+2022-04-30 03:51:25,625 INFO [train.py:763] (2/8) Epoch 26, batch 1900, loss[loss=0.1781, simple_loss=0.2636, pruned_loss=0.04624, over 7347.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2625, pruned_loss=0.03253, over 1428259.36 frames.], batch size: 19, lr: 2.89e-04
+2022-04-30 03:52:30,898 INFO [train.py:763] (2/8) Epoch 26, batch 1950, loss[loss=0.1877, simple_loss=0.2845, pruned_loss=0.04546, over 6153.00 frames.], tot_loss[loss=0.1643, simple_loss=0.263, pruned_loss=0.03276, over 1424012.24 frames.], batch size: 37, lr: 2.89e-04
+2022-04-30 03:53:36,217 INFO [train.py:763] (2/8) Epoch 26, batch 2000, loss[loss=0.1644, simple_loss=0.2784, pruned_loss=0.02517, over 6687.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2623, pruned_loss=0.0322, over 1421738.85 frames.], batch size: 31, lr: 2.89e-04
+2022-04-30 03:54:41,490 INFO [train.py:763] (2/8) Epoch 26, batch 2050, loss[loss=0.1655, simple_loss=0.2725, pruned_loss=0.02919, over 7182.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2631, pruned_loss=0.03233, over 1424863.85 frames.], batch size: 26, lr: 2.89e-04
+2022-04-30 03:55:48,140 INFO [train.py:763] (2/8) Epoch 26, batch 2100, loss[loss=0.1751, simple_loss=0.2679, pruned_loss=0.04115, over 7218.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2631, pruned_loss=0.03258, over 1423553.24 frames.], batch size: 22, lr: 2.89e-04
+2022-04-30 03:56:54,314 INFO [train.py:763] (2/8) Epoch 26, batch 2150, loss[loss=0.1944, simple_loss=0.2955, pruned_loss=0.04659, over 7307.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2644, pruned_loss=0.03315, over 1427189.49 frames.], batch size: 25, lr: 2.89e-04
+2022-04-30 03:57:59,844 INFO [train.py:763] (2/8) Epoch 26, batch 2200, loss[loss=0.1743, simple_loss=0.2739, pruned_loss=0.03736, over 7230.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2647, pruned_loss=0.03303, over 1425302.92 frames.], batch size: 20, lr: 2.88e-04
+2022-04-30 03:59:06,001 INFO [train.py:763] (2/8) Epoch 26, batch 2250, loss[loss=0.1482, simple_loss=0.2334, pruned_loss=0.03152, over 6990.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2649, pruned_loss=0.0332, over 1430428.87 frames.], batch size: 16, lr: 2.88e-04
+2022-04-30 04:00:11,169 INFO [train.py:763] (2/8) Epoch 26, batch 2300, loss[loss=0.1445, simple_loss=0.2413, pruned_loss=0.02383, over 7131.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2649, pruned_loss=0.03302, over 1432532.83 frames.], batch size: 17, lr: 2.88e-04
+2022-04-30 04:01:17,204 INFO [train.py:763] (2/8) Epoch 26, batch 2350, loss[loss=0.164, simple_loss=0.2743, pruned_loss=0.02684, over 7139.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2659, pruned_loss=0.03363, over 1431624.84 frames.], batch size: 20, lr: 2.88e-04
+2022-04-30 04:02:24,605 INFO [train.py:763] (2/8) Epoch 26, batch 2400, loss[loss=0.2084, simple_loss=0.3027, pruned_loss=0.05703, over 7298.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2655, pruned_loss=0.03332, over 1433566.43 frames.], batch size: 24, lr: 2.88e-04
+2022-04-30 04:03:31,272 INFO [train.py:763] (2/8) Epoch 26, batch 2450, loss[loss=0.1703, simple_loss=0.2787, pruned_loss=0.03091, over 7228.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2655, pruned_loss=0.03303, over 1436846.43 frames.], batch size: 20, lr: 2.88e-04
+2022-04-30 04:04:36,616 INFO [train.py:763] (2/8) Epoch 26, batch 2500, loss[loss=0.1809, simple_loss=0.29, pruned_loss=0.03592, over 7211.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2655, pruned_loss=0.03307, over 1438007.09 frames.], batch size: 21, lr: 2.88e-04
+2022-04-30 04:05:41,761 INFO [train.py:763] (2/8) Epoch 26, batch 2550, loss[loss=0.1692, simple_loss=0.2779, pruned_loss=0.03022, over 6759.00 frames.], tot_loss[loss=0.1661, simple_loss=0.266, pruned_loss=0.03307, over 1434718.46 frames.], batch size: 31, lr: 2.88e-04
+2022-04-30 04:06:47,198 INFO [train.py:763] (2/8) Epoch 26, batch 2600, loss[loss=0.1603, simple_loss=0.2491, pruned_loss=0.0358, over 7226.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2658, pruned_loss=0.03317, over 1434454.88 frames.], batch size: 16, lr: 2.88e-04
+2022-04-30 04:07:52,613 INFO [train.py:763] (2/8) Epoch 26, batch 2650, loss[loss=0.1685, simple_loss=0.2682, pruned_loss=0.0344, over 7273.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2661, pruned_loss=0.03344, over 1430004.44 frames.], batch size: 24, lr: 2.88e-04
+2022-04-30 04:08:58,039 INFO [train.py:763] (2/8) Epoch 26, batch 2700, loss[loss=0.1592, simple_loss=0.2727, pruned_loss=0.02279, over 7332.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2659, pruned_loss=0.03325, over 1428603.50 frames.], batch size: 22, lr: 2.88e-04
+2022-04-30 04:10:03,922 INFO [train.py:763] (2/8) Epoch 26, batch 2750, loss[loss=0.1373, simple_loss=0.2323, pruned_loss=0.02111, over 7165.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2654, pruned_loss=0.03289, over 1427651.76 frames.], batch size: 19, lr: 2.88e-04
+2022-04-30 04:11:09,743 INFO [train.py:763] (2/8) Epoch 26, batch 2800, loss[loss=0.1761, simple_loss=0.2804, pruned_loss=0.03586, over 7296.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2646, pruned_loss=0.03247, over 1427316.79 frames.], batch size: 25, lr: 2.88e-04
+2022-04-30 04:12:16,484 INFO [train.py:763] (2/8) Epoch 26, batch 2850, loss[loss=0.1845, simple_loss=0.2792, pruned_loss=0.04492, over 7257.00 frames.], tot_loss[loss=0.165, simple_loss=0.2648, pruned_loss=0.03263, over 1427118.05 frames.], batch size: 19, lr: 2.88e-04
+2022-04-30 04:13:21,767 INFO [train.py:763] (2/8) Epoch 26, batch 2900, loss[loss=0.1736, simple_loss=0.2608, pruned_loss=0.04316, over 7157.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2655, pruned_loss=0.03372, over 1426334.70 frames.], batch size: 19, lr: 2.88e-04
+2022-04-30 04:14:26,916 INFO [train.py:763] (2/8) Epoch 26, batch 2950, loss[loss=0.1651, simple_loss=0.2669, pruned_loss=0.03166, over 7116.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2665, pruned_loss=0.03407, over 1419142.88 frames.], batch size: 21, lr: 2.88e-04
+2022-04-30 04:15:32,481 INFO [train.py:763] (2/8) Epoch 26, batch 3000, loss[loss=0.174, simple_loss=0.277, pruned_loss=0.03551, over 7407.00 frames.], tot_loss[loss=0.167, simple_loss=0.2662, pruned_loss=0.03394, over 1418361.86 frames.], batch size: 21, lr: 2.88e-04
+2022-04-30 04:15:32,482 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 04:15:47,843 INFO [train.py:792] (2/8) Epoch 26, validation: loss=0.1682, simple_loss=0.2653, pruned_loss=0.03549, over 698248.00 frames.
+2022-04-30 04:16:54,019 INFO [train.py:763] (2/8) Epoch 26, batch 3050, loss[loss=0.155, simple_loss=0.2632, pruned_loss=0.02346, over 7120.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2648, pruned_loss=0.03381, over 1410392.05 frames.], batch size: 21, lr: 2.87e-04
+2022-04-30 04:17:59,868 INFO [train.py:763] (2/8) Epoch 26, batch 3100, loss[loss=0.1588, simple_loss=0.2727, pruned_loss=0.02247, over 7325.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2653, pruned_loss=0.03371, over 1416591.35 frames.], batch size: 21, lr: 2.87e-04
+2022-04-30 04:19:05,970 INFO [train.py:763] (2/8) Epoch 26, batch 3150, loss[loss=0.1848, simple_loss=0.2778, pruned_loss=0.04586, over 7213.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2654, pruned_loss=0.03397, over 1417764.81 frames.], batch size: 22, lr: 2.87e-04
+2022-04-30 04:20:11,637 INFO [train.py:763] (2/8) Epoch 26, batch 3200, loss[loss=0.1762, simple_loss=0.2789, pruned_loss=0.03678, over 7185.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2657, pruned_loss=0.03388, over 1420088.03 frames.], batch size: 23, lr: 2.87e-04
+2022-04-30 04:21:17,156 INFO [train.py:763] (2/8) Epoch 26, batch 3250, loss[loss=0.1626, simple_loss=0.2638, pruned_loss=0.03069, over 6302.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2646, pruned_loss=0.0334, over 1420213.74 frames.], batch size: 37, lr: 2.87e-04
+2022-04-30 04:22:22,720 INFO [train.py:763] (2/8) Epoch 26, batch 3300, loss[loss=0.1719, simple_loss=0.2731, pruned_loss=0.03531, over 6827.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2647, pruned_loss=0.03353, over 1419177.05 frames.], batch size: 31, lr: 2.87e-04
+2022-04-30 04:23:27,751 INFO [train.py:763] (2/8) Epoch 26, batch 3350, loss[loss=0.1838, simple_loss=0.2868, pruned_loss=0.04039, over 7343.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2655, pruned_loss=0.03361, over 1420146.14 frames.], batch size: 22, lr: 2.87e-04
+2022-04-30 04:24:33,264 INFO [train.py:763] (2/8) Epoch 26, batch 3400, loss[loss=0.1651, simple_loss=0.2757, pruned_loss=0.02724, over 7154.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2652, pruned_loss=0.03326, over 1417710.78 frames.], batch size: 20, lr: 2.87e-04
+2022-04-30 04:25:38,624 INFO [train.py:763] (2/8) Epoch 26, batch 3450, loss[loss=0.1804, simple_loss=0.289, pruned_loss=0.03587, over 7338.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2652, pruned_loss=0.03283, over 1421378.38 frames.], batch size: 22, lr: 2.87e-04
+2022-04-30 04:26:44,096 INFO [train.py:763] (2/8) Epoch 26, batch 3500, loss[loss=0.153, simple_loss=0.2424, pruned_loss=0.03178, over 6767.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2644, pruned_loss=0.03262, over 1423417.66 frames.], batch size: 15, lr: 2.87e-04
+2022-04-30 04:27:49,683 INFO [train.py:763] (2/8) Epoch 26, batch 3550, loss[loss=0.183, simple_loss=0.2764, pruned_loss=0.0448, over 5174.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2639, pruned_loss=0.03271, over 1416514.21 frames.], batch size: 53, lr: 2.87e-04
+2022-04-30 04:28:54,781 INFO [train.py:763] (2/8) Epoch 26, batch 3600, loss[loss=0.1651, simple_loss=0.2666, pruned_loss=0.03176, over 7157.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2648, pruned_loss=0.03285, over 1413941.83 frames.], batch size: 19, lr: 2.87e-04
+2022-04-30 04:30:00,883 INFO [train.py:763] (2/8) Epoch 26, batch 3650, loss[loss=0.1407, simple_loss=0.2329, pruned_loss=0.02431, over 7077.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2648, pruned_loss=0.03306, over 1414555.69 frames.], batch size: 18, lr: 2.87e-04
+2022-04-30 04:31:07,247 INFO [train.py:763] (2/8) Epoch 26, batch 3700, loss[loss=0.1372, simple_loss=0.2369, pruned_loss=0.01879, over 7276.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2642, pruned_loss=0.03304, over 1413476.89 frames.], batch size: 18, lr: 2.87e-04
+2022-04-30 04:32:12,925 INFO [train.py:763] (2/8) Epoch 26, batch 3750, loss[loss=0.1742, simple_loss=0.2689, pruned_loss=0.03974, over 7229.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2622, pruned_loss=0.03259, over 1416857.50 frames.], batch size: 21, lr: 2.87e-04
+2022-04-30 04:33:19,994 INFO [train.py:763] (2/8) Epoch 26, batch 3800, loss[loss=0.1553, simple_loss=0.2532, pruned_loss=0.02872, over 7325.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2615, pruned_loss=0.03215, over 1420496.35 frames.], batch size: 20, lr: 2.87e-04
+2022-04-30 04:34:26,369 INFO [train.py:763] (2/8) Epoch 26, batch 3850, loss[loss=0.1455, simple_loss=0.2465, pruned_loss=0.02229, over 7407.00 frames.], tot_loss[loss=0.164, simple_loss=0.2629, pruned_loss=0.03254, over 1413746.14 frames.], batch size: 18, lr: 2.87e-04
+2022-04-30 04:35:31,741 INFO [train.py:763] (2/8) Epoch 26, batch 3900, loss[loss=0.1801, simple_loss=0.2865, pruned_loss=0.03683, over 7028.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2636, pruned_loss=0.0327, over 1414439.08 frames.], batch size: 28, lr: 2.86e-04
+2022-04-30 04:36:37,005 INFO [train.py:763] (2/8) Epoch 26, batch 3950, loss[loss=0.1648, simple_loss=0.2547, pruned_loss=0.03743, over 7366.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2639, pruned_loss=0.03254, over 1418654.64 frames.], batch size: 19, lr: 2.86e-04
+2022-04-30 04:37:42,770 INFO [train.py:763] (2/8) Epoch 26, batch 4000, loss[loss=0.1865, simple_loss=0.2871, pruned_loss=0.04298, over 7057.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2633, pruned_loss=0.03216, over 1424179.17 frames.], batch size: 28, lr: 2.86e-04
+2022-04-30 04:38:48,117 INFO [train.py:763] (2/8) Epoch 26, batch 4050, loss[loss=0.1727, simple_loss=0.271, pruned_loss=0.03724, over 7321.00 frames.], tot_loss[loss=0.1644, simple_loss=0.264, pruned_loss=0.03239, over 1424958.46 frames.], batch size: 20, lr: 2.86e-04
+2022-04-30 04:39:53,362 INFO [train.py:763] (2/8) Epoch 26, batch 4100, loss[loss=0.1732, simple_loss=0.2695, pruned_loss=0.03842, over 7322.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2633, pruned_loss=0.03224, over 1423401.96 frames.], batch size: 20, lr: 2.86e-04
+2022-04-30 04:40:58,509 INFO [train.py:763] (2/8) Epoch 26, batch 4150, loss[loss=0.1696, simple_loss=0.2751, pruned_loss=0.03198, over 7120.00 frames.], tot_loss[loss=0.164, simple_loss=0.2634, pruned_loss=0.03234, over 1420884.09 frames.], batch size: 21, lr: 2.86e-04
+2022-04-30 04:42:03,898 INFO [train.py:763] (2/8) Epoch 26, batch 4200, loss[loss=0.1595, simple_loss=0.2711, pruned_loss=0.02394, over 7335.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2627, pruned_loss=0.0322, over 1422664.93 frames.], batch size: 22, lr: 2.86e-04
+2022-04-30 04:43:08,776 INFO [train.py:763] (2/8) Epoch 26, batch 4250, loss[loss=0.1734, simple_loss=0.2679, pruned_loss=0.03949, over 7421.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2645, pruned_loss=0.03265, over 1415573.34 frames.], batch size: 21, lr: 2.86e-04
+2022-04-30 04:44:14,516 INFO [train.py:763] (2/8) Epoch 26, batch 4300, loss[loss=0.1742, simple_loss=0.2614, pruned_loss=0.04354, over 6699.00 frames.], tot_loss[loss=0.165, simple_loss=0.2642, pruned_loss=0.03289, over 1413926.11 frames.], batch size: 31, lr: 2.86e-04
+2022-04-30 04:45:19,672 INFO [train.py:763] (2/8) Epoch 26, batch 4350, loss[loss=0.159, simple_loss=0.2547, pruned_loss=0.03166, over 7002.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2649, pruned_loss=0.03313, over 1413321.13 frames.], batch size: 16, lr: 2.86e-04
+2022-04-30 04:46:24,702 INFO [train.py:763] (2/8) Epoch 26, batch 4400, loss[loss=0.1699, simple_loss=0.2659, pruned_loss=0.03689, over 6310.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2657, pruned_loss=0.03357, over 1401125.51 frames.], batch size: 37, lr: 2.86e-04
+2022-04-30 04:47:29,332 INFO [train.py:763] (2/8) Epoch 26, batch 4450, loss[loss=0.1623, simple_loss=0.2558, pruned_loss=0.03444, over 7340.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2652, pruned_loss=0.03353, over 1396871.27 frames.], batch size: 22, lr: 2.86e-04
+2022-04-30 04:48:34,526 INFO [train.py:763] (2/8) Epoch 26, batch 4500, loss[loss=0.1513, simple_loss=0.2485, pruned_loss=0.0271, over 7170.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2661, pruned_loss=0.03408, over 1387679.41 frames.], batch size: 18, lr: 2.86e-04
+2022-04-30 04:49:39,405 INFO [train.py:763] (2/8) Epoch 26, batch 4550, loss[loss=0.1573, simple_loss=0.2605, pruned_loss=0.02707, over 5023.00 frames.], tot_loss[loss=0.166, simple_loss=0.2645, pruned_loss=0.03375, over 1371166.59 frames.], batch size: 52, lr: 2.86e-04
+2022-04-30 04:51:07,359 INFO [train.py:763] (2/8) Epoch 27, batch 0, loss[loss=0.1502, simple_loss=0.2492, pruned_loss=0.02559, over 7256.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2492, pruned_loss=0.02559, over 7256.00 frames.], batch size: 19, lr: 2.81e-04
+2022-04-30 04:52:13,081 INFO [train.py:763] (2/8) Epoch 27, batch 50, loss[loss=0.1446, simple_loss=0.2471, pruned_loss=0.02109, over 7268.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2618, pruned_loss=0.03223, over 320841.12 frames.], batch size: 19, lr: 2.81e-04
+2022-04-30 04:53:19,206 INFO [train.py:763] (2/8) Epoch 27, batch 100, loss[loss=0.1521, simple_loss=0.2595, pruned_loss=0.02232, over 7140.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2622, pruned_loss=0.03138, over 564887.37 frames.], batch size: 20, lr: 2.80e-04
+2022-04-30 04:54:25,261 INFO [train.py:763] (2/8) Epoch 27, batch 150, loss[loss=0.1624, simple_loss=0.2703, pruned_loss=0.02724, over 6572.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2636, pruned_loss=0.03207, over 753307.01 frames.], batch size: 39, lr: 2.80e-04
+2022-04-30 04:55:31,373 INFO [train.py:763] (2/8) Epoch 27, batch 200, loss[loss=0.1945, simple_loss=0.2882, pruned_loss=0.05037, over 7194.00 frames.], tot_loss[loss=0.164, simple_loss=0.2632, pruned_loss=0.03241, over 899624.32 frames.], batch size: 23, lr: 2.80e-04
+2022-04-30 04:56:38,000 INFO [train.py:763] (2/8) Epoch 27, batch 250, loss[loss=0.1886, simple_loss=0.2809, pruned_loss=0.0481, over 7281.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2638, pruned_loss=0.03247, over 1015498.19 frames.], batch size: 24, lr: 2.80e-04
+2022-04-30 04:57:44,217 INFO [train.py:763] (2/8) Epoch 27, batch 300, loss[loss=0.1749, simple_loss=0.2852, pruned_loss=0.03233, over 6825.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2646, pruned_loss=0.03247, over 1105647.35 frames.], batch size: 31, lr: 2.80e-04
+2022-04-30 04:58:50,089 INFO [train.py:763] (2/8) Epoch 27, batch 350, loss[loss=0.1627, simple_loss=0.2684, pruned_loss=0.02854, over 7160.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2631, pruned_loss=0.03174, over 1177583.03 frames.], batch size: 19, lr: 2.80e-04
+2022-04-30 04:59:56,367 INFO [train.py:763] (2/8) Epoch 27, batch 400, loss[loss=0.1359, simple_loss=0.228, pruned_loss=0.02189, over 7131.00 frames.], tot_loss[loss=0.1634, simple_loss=0.263, pruned_loss=0.03183, over 1233056.37 frames.], batch size: 17, lr: 2.80e-04
+2022-04-30 05:01:02,253 INFO [train.py:763] (2/8) Epoch 27, batch 450, loss[loss=0.1797, simple_loss=0.2823, pruned_loss=0.03855, over 7318.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2639, pruned_loss=0.03201, over 1269766.77 frames.], batch size: 25, lr: 2.80e-04
+2022-04-30 05:02:08,164 INFO [train.py:763] (2/8) Epoch 27, batch 500, loss[loss=0.1494, simple_loss=0.2506, pruned_loss=0.02407, over 7327.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2637, pruned_loss=0.03198, over 1307215.41 frames.], batch size: 21, lr: 2.80e-04
+2022-04-30 05:03:14,020 INFO [train.py:763] (2/8) Epoch 27, batch 550, loss[loss=0.1594, simple_loss=0.2528, pruned_loss=0.03301, over 7074.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2634, pruned_loss=0.03206, over 1329357.92 frames.], batch size: 18, lr: 2.80e-04
+2022-04-30 05:04:19,658 INFO [train.py:763] (2/8) Epoch 27, batch 600, loss[loss=0.1344, simple_loss=0.2405, pruned_loss=0.01415, over 7330.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2629, pruned_loss=0.03175, over 1347921.46 frames.], batch size: 20, lr: 2.80e-04
+2022-04-30 05:05:24,798 INFO [train.py:763] (2/8) Epoch 27, batch 650, loss[loss=0.2051, simple_loss=0.3044, pruned_loss=0.05291, over 7148.00 frames.], tot_loss[loss=0.164, simple_loss=0.2636, pruned_loss=0.03218, over 1366295.88 frames.], batch size: 28, lr: 2.80e-04
+2022-04-30 05:06:40,257 INFO [train.py:763] (2/8) Epoch 27, batch 700, loss[loss=0.1353, simple_loss=0.2339, pruned_loss=0.01837, over 7065.00 frames.], tot_loss[loss=0.164, simple_loss=0.2635, pruned_loss=0.03228, over 1380641.25 frames.], batch size: 18, lr: 2.80e-04
+2022-04-30 05:07:46,092 INFO [train.py:763] (2/8) Epoch 27, batch 750, loss[loss=0.1529, simple_loss=0.2588, pruned_loss=0.02351, over 7221.00 frames.], tot_loss[loss=0.164, simple_loss=0.2631, pruned_loss=0.03242, over 1391742.24 frames.], batch size: 21, lr: 2.80e-04
+2022-04-30 05:08:51,492 INFO [train.py:763] (2/8) Epoch 27, batch 800, loss[loss=0.1985, simple_loss=0.2888, pruned_loss=0.05409, over 7123.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2635, pruned_loss=0.03266, over 1397375.07 frames.], batch size: 28, lr: 2.80e-04
+2022-04-30 05:09:56,915 INFO [train.py:763] (2/8) Epoch 27, batch 850, loss[loss=0.1751, simple_loss=0.2775, pruned_loss=0.03631, over 7301.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2637, pruned_loss=0.03259, over 1405338.94 frames.], batch size: 25, lr: 2.80e-04
+2022-04-30 05:11:02,104 INFO [train.py:763] (2/8) Epoch 27, batch 900, loss[loss=0.1614, simple_loss=0.2453, pruned_loss=0.0388, over 6997.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2645, pruned_loss=0.03283, over 1407253.33 frames.], batch size: 16, lr: 2.80e-04
+2022-04-30 05:12:07,290 INFO [train.py:763] (2/8) Epoch 27, batch 950, loss[loss=0.1605, simple_loss=0.255, pruned_loss=0.03293, over 7161.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2652, pruned_loss=0.03346, over 1409451.43 frames.], batch size: 18, lr: 2.80e-04
+2022-04-30 05:13:12,787 INFO [train.py:763] (2/8) Epoch 27, batch 1000, loss[loss=0.1597, simple_loss=0.2678, pruned_loss=0.02579, over 7414.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2643, pruned_loss=0.03295, over 1414932.49 frames.], batch size: 20, lr: 2.79e-04
+2022-04-30 05:14:18,813 INFO [train.py:763] (2/8) Epoch 27, batch 1050, loss[loss=0.1753, simple_loss=0.273, pruned_loss=0.03878, over 7421.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2644, pruned_loss=0.03304, over 1414965.22 frames.], batch size: 21, lr: 2.79e-04
+2022-04-30 05:15:25,039 INFO [train.py:763] (2/8) Epoch 27, batch 1100, loss[loss=0.1704, simple_loss=0.2583, pruned_loss=0.04131, over 7067.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2647, pruned_loss=0.03312, over 1414667.56 frames.], batch size: 18, lr: 2.79e-04
+2022-04-30 05:16:31,239 INFO [train.py:763] (2/8) Epoch 27, batch 1150, loss[loss=0.1674, simple_loss=0.2703, pruned_loss=0.03223, over 7197.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2627, pruned_loss=0.03255, over 1420571.17 frames.], batch size: 23, lr: 2.79e-04
+2022-04-30 05:17:47,506 INFO [train.py:763] (2/8) Epoch 27, batch 1200, loss[loss=0.1583, simple_loss=0.2485, pruned_loss=0.03402, over 7127.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2623, pruned_loss=0.03216, over 1424337.38 frames.], batch size: 17, lr: 2.79e-04
+2022-04-30 05:19:01,883 INFO [train.py:763] (2/8) Epoch 27, batch 1250, loss[loss=0.1532, simple_loss=0.2413, pruned_loss=0.03256, over 7122.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2631, pruned_loss=0.03225, over 1422650.08 frames.], batch size: 17, lr: 2.79e-04
+2022-04-30 05:20:26,018 INFO [train.py:763] (2/8) Epoch 27, batch 1300, loss[loss=0.1366, simple_loss=0.2226, pruned_loss=0.02528, over 7290.00 frames.], tot_loss[loss=0.164, simple_loss=0.2631, pruned_loss=0.03248, over 1419043.91 frames.], batch size: 18, lr: 2.79e-04
+2022-04-30 05:21:31,872 INFO [train.py:763] (2/8) Epoch 27, batch 1350, loss[loss=0.1596, simple_loss=0.2551, pruned_loss=0.03204, over 7352.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2627, pruned_loss=0.03238, over 1419105.47 frames.], batch size: 19, lr: 2.79e-04
+2022-04-30 05:22:37,300 INFO [train.py:763] (2/8) Epoch 27, batch 1400, loss[loss=0.1614, simple_loss=0.2564, pruned_loss=0.03322, over 7049.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2627, pruned_loss=0.03242, over 1418573.86 frames.], batch size: 18, lr: 2.79e-04
+2022-04-30 05:24:10,241 INFO [train.py:763] (2/8) Epoch 27, batch 1450, loss[loss=0.1576, simple_loss=0.2656, pruned_loss=0.02477, over 7337.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2616, pruned_loss=0.0321, over 1420969.24 frames.], batch size: 20, lr: 2.79e-04
+2022-04-30 05:25:16,092 INFO [train.py:763] (2/8) Epoch 27, batch 1500, loss[loss=0.1525, simple_loss=0.2581, pruned_loss=0.02347, over 7114.00 frames.], tot_loss[loss=0.164, simple_loss=0.2631, pruned_loss=0.03244, over 1422912.24 frames.], batch size: 21, lr: 2.79e-04
+2022-04-30 05:26:21,997 INFO [train.py:763] (2/8) Epoch 27, batch 1550, loss[loss=0.1476, simple_loss=0.2355, pruned_loss=0.02988, over 7166.00 frames.], tot_loss[loss=0.164, simple_loss=0.2634, pruned_loss=0.03234, over 1420326.82 frames.], batch size: 16, lr: 2.79e-04
+2022-04-30 05:27:29,036 INFO [train.py:763] (2/8) Epoch 27, batch 1600, loss[loss=0.1991, simple_loss=0.3091, pruned_loss=0.04458, over 7415.00 frames.], tot_loss[loss=0.164, simple_loss=0.2632, pruned_loss=0.03238, over 1424147.29 frames.], batch size: 21, lr: 2.79e-04
+2022-04-30 05:28:35,018 INFO [train.py:763] (2/8) Epoch 27, batch 1650, loss[loss=0.1532, simple_loss=0.2561, pruned_loss=0.02516, over 7059.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2629, pruned_loss=0.03215, over 1424223.78 frames.], batch size: 18, lr: 2.79e-04
+2022-04-30 05:29:41,339 INFO [train.py:763] (2/8) Epoch 27, batch 1700, loss[loss=0.1435, simple_loss=0.2386, pruned_loss=0.02419, over 7365.00 frames.], tot_loss[loss=0.164, simple_loss=0.2633, pruned_loss=0.03237, over 1425624.40 frames.], batch size: 19, lr: 2.79e-04
+2022-04-30 05:30:48,488 INFO [train.py:763] (2/8) Epoch 27, batch 1750, loss[loss=0.1846, simple_loss=0.2767, pruned_loss=0.04624, over 6826.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2625, pruned_loss=0.03241, over 1426852.34 frames.], batch size: 31, lr: 2.79e-04
+2022-04-30 05:31:54,569 INFO [train.py:763] (2/8) Epoch 27, batch 1800, loss[loss=0.1671, simple_loss=0.2722, pruned_loss=0.03098, over 7228.00 frames.], tot_loss[loss=0.164, simple_loss=0.2628, pruned_loss=0.03256, over 1426191.15 frames.], batch size: 20, lr: 2.79e-04
+2022-04-30 05:33:00,690 INFO [train.py:763] (2/8) Epoch 27, batch 1850, loss[loss=0.1446, simple_loss=0.2377, pruned_loss=0.02576, over 7146.00 frames.], tot_loss[loss=0.164, simple_loss=0.263, pruned_loss=0.03248, over 1429202.00 frames.], batch size: 19, lr: 2.79e-04
+2022-04-30 05:34:06,838 INFO [train.py:763] (2/8) Epoch 27, batch 1900, loss[loss=0.1394, simple_loss=0.2269, pruned_loss=0.02593, over 7282.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2629, pruned_loss=0.03215, over 1429437.85 frames.], batch size: 17, lr: 2.78e-04
+2022-04-30 05:35:13,646 INFO [train.py:763] (2/8) Epoch 27, batch 1950, loss[loss=0.2084, simple_loss=0.3015, pruned_loss=0.05768, over 6545.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2632, pruned_loss=0.03233, over 1424820.37 frames.], batch size: 38, lr: 2.78e-04
+2022-04-30 05:36:20,333 INFO [train.py:763] (2/8) Epoch 27, batch 2000, loss[loss=0.1744, simple_loss=0.2822, pruned_loss=0.03335, over 7228.00 frames.], tot_loss[loss=0.164, simple_loss=0.2634, pruned_loss=0.03228, over 1424098.04 frames.], batch size: 21, lr: 2.78e-04
+2022-04-30 05:37:26,469 INFO [train.py:763] (2/8) Epoch 27, batch 2050, loss[loss=0.1679, simple_loss=0.2653, pruned_loss=0.03529, over 7206.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2642, pruned_loss=0.03264, over 1422804.47 frames.], batch size: 23, lr: 2.78e-04
+2022-04-30 05:38:32,943 INFO [train.py:763] (2/8) Epoch 27, batch 2100, loss[loss=0.1631, simple_loss=0.2708, pruned_loss=0.02765, over 7297.00 frames.], tot_loss[loss=0.1644, simple_loss=0.264, pruned_loss=0.0324, over 1422799.35 frames.], batch size: 25, lr: 2.78e-04
+2022-04-30 05:39:38,767 INFO [train.py:763] (2/8) Epoch 27, batch 2150, loss[loss=0.1343, simple_loss=0.2222, pruned_loss=0.02323, over 7128.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2635, pruned_loss=0.03208, over 1421163.69 frames.], batch size: 17, lr: 2.78e-04
+2022-04-30 05:40:44,410 INFO [train.py:763] (2/8) Epoch 27, batch 2200, loss[loss=0.1989, simple_loss=0.2961, pruned_loss=0.05082, over 7292.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2642, pruned_loss=0.03273, over 1420541.96 frames.], batch size: 24, lr: 2.78e-04
+2022-04-30 05:41:50,156 INFO [train.py:763] (2/8) Epoch 27, batch 2250, loss[loss=0.1727, simple_loss=0.2855, pruned_loss=0.02999, over 7328.00 frames.], tot_loss[loss=0.1646, simple_loss=0.264, pruned_loss=0.03256, over 1423309.10 frames.], batch size: 22, lr: 2.78e-04
+2022-04-30 05:42:56,031 INFO [train.py:763] (2/8) Epoch 27, batch 2300, loss[loss=0.1713, simple_loss=0.273, pruned_loss=0.03479, over 7147.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2649, pruned_loss=0.03278, over 1420593.32 frames.], batch size: 20, lr: 2.78e-04
+2022-04-30 05:44:01,764 INFO [train.py:763] (2/8) Epoch 27, batch 2350, loss[loss=0.1748, simple_loss=0.2807, pruned_loss=0.03449, over 7166.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2646, pruned_loss=0.03241, over 1419274.92 frames.], batch size: 19, lr: 2.78e-04
+2022-04-30 05:45:08,042 INFO [train.py:763] (2/8) Epoch 27, batch 2400, loss[loss=0.1822, simple_loss=0.2809, pruned_loss=0.04174, over 7224.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2649, pruned_loss=0.03277, over 1423066.91 frames.], batch size: 23, lr: 2.78e-04
+2022-04-30 05:46:14,164 INFO [train.py:763] (2/8) Epoch 27, batch 2450, loss[loss=0.1827, simple_loss=0.2832, pruned_loss=0.04111, over 6245.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2636, pruned_loss=0.03229, over 1423455.58 frames.], batch size: 37, lr: 2.78e-04
+2022-04-30 05:47:19,801 INFO [train.py:763] (2/8) Epoch 27, batch 2500, loss[loss=0.1442, simple_loss=0.2344, pruned_loss=0.02704, over 6799.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2636, pruned_loss=0.033, over 1420347.28 frames.], batch size: 15, lr: 2.78e-04
+2022-04-30 05:48:25,885 INFO [train.py:763] (2/8) Epoch 27, batch 2550, loss[loss=0.1535, simple_loss=0.2487, pruned_loss=0.02917, over 7263.00 frames.], tot_loss[loss=0.165, simple_loss=0.2638, pruned_loss=0.03305, over 1421133.68 frames.], batch size: 19, lr: 2.78e-04
+2022-04-30 05:49:31,723 INFO [train.py:763] (2/8) Epoch 27, batch 2600, loss[loss=0.1734, simple_loss=0.2774, pruned_loss=0.03469, over 7236.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2635, pruned_loss=0.03272, over 1420838.17 frames.], batch size: 20, lr: 2.78e-04
+2022-04-30 05:50:37,395 INFO [train.py:763] (2/8) Epoch 27, batch 2650, loss[loss=0.146, simple_loss=0.2381, pruned_loss=0.02694, over 6996.00 frames.], tot_loss[loss=0.1647, simple_loss=0.264, pruned_loss=0.03275, over 1419986.63 frames.], batch size: 16, lr: 2.78e-04
+2022-04-30 05:51:42,951 INFO [train.py:763] (2/8) Epoch 27, batch 2700, loss[loss=0.1678, simple_loss=0.2581, pruned_loss=0.0387, over 7311.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2636, pruned_loss=0.0324, over 1421929.60 frames.], batch size: 21, lr: 2.78e-04
+2022-04-30 05:52:49,035 INFO [train.py:763] (2/8) Epoch 27, batch 2750, loss[loss=0.175, simple_loss=0.2744, pruned_loss=0.03779, over 7252.00 frames.], tot_loss[loss=0.1643, simple_loss=0.264, pruned_loss=0.03231, over 1420672.82 frames.], batch size: 19, lr: 2.78e-04
+2022-04-30 05:53:54,753 INFO [train.py:763] (2/8) Epoch 27, batch 2800, loss[loss=0.1818, simple_loss=0.2924, pruned_loss=0.03561, over 7232.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2639, pruned_loss=0.03226, over 1416183.57 frames.], batch size: 20, lr: 2.77e-04
+2022-04-30 05:55:00,517 INFO [train.py:763] (2/8) Epoch 27, batch 2850, loss[loss=0.1282, simple_loss=0.221, pruned_loss=0.01776, over 7135.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2638, pruned_loss=0.03202, over 1420300.93 frames.], batch size: 17, lr: 2.77e-04
+2022-04-30 05:56:06,155 INFO [train.py:763] (2/8) Epoch 27, batch 2900, loss[loss=0.1977, simple_loss=0.2994, pruned_loss=0.04798, over 7293.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2645, pruned_loss=0.03201, over 1419064.14 frames.], batch size: 25, lr: 2.77e-04
+2022-04-30 05:57:11,709 INFO [train.py:763] (2/8) Epoch 27, batch 2950, loss[loss=0.1962, simple_loss=0.2934, pruned_loss=0.04954, over 7193.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2643, pruned_loss=0.0323, over 1422633.59 frames.], batch size: 23, lr: 2.77e-04
+2022-04-30 05:58:18,057 INFO [train.py:763] (2/8) Epoch 27, batch 3000, loss[loss=0.1844, simple_loss=0.285, pruned_loss=0.04192, over 7074.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2654, pruned_loss=0.03262, over 1424708.75 frames.], batch size: 28, lr: 2.77e-04
+2022-04-30 05:58:18,058 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 05:58:33,166 INFO [train.py:792] (2/8) Epoch 27, validation: loss=0.1686, simple_loss=0.2648, pruned_loss=0.03621, over 698248.00 frames.
+2022-04-30 05:59:40,072 INFO [train.py:763] (2/8) Epoch 27, batch 3050, loss[loss=0.1567, simple_loss=0.2435, pruned_loss=0.035, over 7137.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2652, pruned_loss=0.03265, over 1426450.79 frames.], batch size: 17, lr: 2.77e-04
+2022-04-30 06:00:45,832 INFO [train.py:763] (2/8) Epoch 27, batch 3100, loss[loss=0.169, simple_loss=0.2691, pruned_loss=0.03445, over 7390.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2643, pruned_loss=0.03201, over 1425073.51 frames.], batch size: 23, lr: 2.77e-04
+2022-04-30 06:01:51,939 INFO [train.py:763] (2/8) Epoch 27, batch 3150, loss[loss=0.1342, simple_loss=0.2313, pruned_loss=0.01857, over 7405.00 frames.], tot_loss[loss=0.1635, simple_loss=0.263, pruned_loss=0.03193, over 1423668.36 frames.], batch size: 18, lr: 2.77e-04
+2022-04-30 06:02:58,129 INFO [train.py:763] (2/8) Epoch 27, batch 3200, loss[loss=0.1684, simple_loss=0.2744, pruned_loss=0.03125, over 7318.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2637, pruned_loss=0.03211, over 1424235.67 frames.], batch size: 21, lr: 2.77e-04
+2022-04-30 06:04:04,074 INFO [train.py:763] (2/8) Epoch 27, batch 3250, loss[loss=0.157, simple_loss=0.255, pruned_loss=0.02948, over 7171.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2632, pruned_loss=0.03211, over 1423138.87 frames.], batch size: 18, lr: 2.77e-04
+2022-04-30 06:05:10,044 INFO [train.py:763] (2/8) Epoch 27, batch 3300, loss[loss=0.1474, simple_loss=0.2346, pruned_loss=0.03004, over 7013.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2632, pruned_loss=0.0319, over 1422117.33 frames.], batch size: 16, lr: 2.77e-04
+2022-04-30 06:06:16,450 INFO [train.py:763] (2/8) Epoch 27, batch 3350, loss[loss=0.1737, simple_loss=0.269, pruned_loss=0.0392, over 7382.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2638, pruned_loss=0.03228, over 1419265.09 frames.], batch size: 23, lr: 2.77e-04
+2022-04-30 06:07:23,072 INFO [train.py:763] (2/8) Epoch 27, batch 3400, loss[loss=0.1485, simple_loss=0.2522, pruned_loss=0.02243, over 7324.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2641, pruned_loss=0.03261, over 1421513.96 frames.], batch size: 20, lr: 2.77e-04
+2022-04-30 06:08:29,072 INFO [train.py:763] (2/8) Epoch 27, batch 3450, loss[loss=0.1685, simple_loss=0.2654, pruned_loss=0.03582, over 7184.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2646, pruned_loss=0.03288, over 1422535.68 frames.], batch size: 22, lr: 2.77e-04
+2022-04-30 06:09:34,960 INFO [train.py:763] (2/8) Epoch 27, batch 3500, loss[loss=0.153, simple_loss=0.2461, pruned_loss=0.02995, over 7052.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2643, pruned_loss=0.03294, over 1422244.09 frames.], batch size: 18, lr: 2.77e-04
+2022-04-30 06:10:40,824 INFO [train.py:763] (2/8) Epoch 27, batch 3550, loss[loss=0.1703, simple_loss=0.2778, pruned_loss=0.03144, over 7334.00 frames.], tot_loss[loss=0.165, simple_loss=0.2642, pruned_loss=0.03289, over 1423045.45 frames.], batch size: 22, lr: 2.77e-04
+2022-04-30 06:11:46,445 INFO [train.py:763] (2/8) Epoch 27, batch 3600, loss[loss=0.141, simple_loss=0.2365, pruned_loss=0.02271, over 7061.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2651, pruned_loss=0.0332, over 1422162.54 frames.], batch size: 18, lr: 2.77e-04
+2022-04-30 06:12:52,023 INFO [train.py:763] (2/8) Epoch 27, batch 3650, loss[loss=0.1918, simple_loss=0.2985, pruned_loss=0.04254, over 7402.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2641, pruned_loss=0.03264, over 1423026.64 frames.], batch size: 21, lr: 2.77e-04
+2022-04-30 06:13:58,382 INFO [train.py:763] (2/8) Epoch 27, batch 3700, loss[loss=0.1568, simple_loss=0.2579, pruned_loss=0.02779, over 7431.00 frames.], tot_loss[loss=0.1642, simple_loss=0.264, pruned_loss=0.03224, over 1424003.53 frames.], batch size: 20, lr: 2.77e-04
+2022-04-30 06:15:04,061 INFO [train.py:763] (2/8) Epoch 27, batch 3750, loss[loss=0.1859, simple_loss=0.2827, pruned_loss=0.04456, over 5095.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2636, pruned_loss=0.03187, over 1420225.82 frames.], batch size: 52, lr: 2.76e-04
+2022-04-30 06:16:10,306 INFO [train.py:763] (2/8) Epoch 27, batch 3800, loss[loss=0.1475, simple_loss=0.2358, pruned_loss=0.0296, over 7292.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2634, pruned_loss=0.03194, over 1422476.79 frames.], batch size: 17, lr: 2.76e-04
+2022-04-30 06:17:16,528 INFO [train.py:763] (2/8) Epoch 27, batch 3850, loss[loss=0.1589, simple_loss=0.2586, pruned_loss=0.02964, over 7165.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2639, pruned_loss=0.03189, over 1426917.57 frames.], batch size: 19, lr: 2.76e-04
+2022-04-30 06:18:22,907 INFO [train.py:763] (2/8) Epoch 27, batch 3900, loss[loss=0.1577, simple_loss=0.2585, pruned_loss=0.02845, over 7199.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2635, pruned_loss=0.03159, over 1426047.49 frames.], batch size: 22, lr: 2.76e-04
+2022-04-30 06:19:28,539 INFO [train.py:763] (2/8) Epoch 27, batch 3950, loss[loss=0.1841, simple_loss=0.2873, pruned_loss=0.04041, over 7208.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2635, pruned_loss=0.03168, over 1426917.83 frames.], batch size: 22, lr: 2.76e-04
+2022-04-30 06:20:34,795 INFO [train.py:763] (2/8) Epoch 27, batch 4000, loss[loss=0.1722, simple_loss=0.2724, pruned_loss=0.036, over 6683.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2622, pruned_loss=0.03144, over 1423909.01 frames.], batch size: 31, lr: 2.76e-04
+2022-04-30 06:21:40,917 INFO [train.py:763] (2/8) Epoch 27, batch 4050, loss[loss=0.2, simple_loss=0.2968, pruned_loss=0.05155, over 5283.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2639, pruned_loss=0.03222, over 1417204.31 frames.], batch size: 53, lr: 2.76e-04
+2022-04-30 06:22:47,106 INFO [train.py:763] (2/8) Epoch 27, batch 4100, loss[loss=0.175, simple_loss=0.26, pruned_loss=0.04498, over 7124.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2635, pruned_loss=0.03205, over 1418907.50 frames.], batch size: 17, lr: 2.76e-04
+2022-04-30 06:24:03,943 INFO [train.py:763] (2/8) Epoch 27, batch 4150, loss[loss=0.1572, simple_loss=0.2571, pruned_loss=0.02867, over 7150.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2641, pruned_loss=0.03222, over 1423816.55 frames.], batch size: 19, lr: 2.76e-04
+2022-04-30 06:25:09,373 INFO [train.py:763] (2/8) Epoch 27, batch 4200, loss[loss=0.1794, simple_loss=0.2814, pruned_loss=0.03871, over 5257.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2652, pruned_loss=0.03264, over 1418179.25 frames.], batch size: 52, lr: 2.76e-04
+2022-04-30 06:26:15,105 INFO [train.py:763] (2/8) Epoch 27, batch 4250, loss[loss=0.1565, simple_loss=0.2498, pruned_loss=0.03163, over 7060.00 frames.], tot_loss[loss=0.1649, simple_loss=0.265, pruned_loss=0.03237, over 1415491.93 frames.], batch size: 18, lr: 2.76e-04
+2022-04-30 06:27:21,138 INFO [train.py:763] (2/8) Epoch 27, batch 4300, loss[loss=0.1629, simple_loss=0.2616, pruned_loss=0.03217, over 7121.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2644, pruned_loss=0.03205, over 1417389.50 frames.], batch size: 17, lr: 2.76e-04
+2022-04-30 06:28:27,400 INFO [train.py:763] (2/8) Epoch 27, batch 4350, loss[loss=0.15, simple_loss=0.2602, pruned_loss=0.01987, over 7223.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2643, pruned_loss=0.03198, over 1417366.27 frames.], batch size: 21, lr: 2.76e-04
+2022-04-30 06:29:33,354 INFO [train.py:763] (2/8) Epoch 27, batch 4400, loss[loss=0.2019, simple_loss=0.3023, pruned_loss=0.05076, over 6444.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2635, pruned_loss=0.032, over 1409094.11 frames.], batch size: 37, lr: 2.76e-04
+2022-04-30 06:30:39,366 INFO [train.py:763] (2/8) Epoch 27, batch 4450, loss[loss=0.1381, simple_loss=0.2216, pruned_loss=0.02734, over 6847.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2637, pruned_loss=0.03226, over 1404403.32 frames.], batch size: 15, lr: 2.76e-04
+2022-04-30 06:31:44,894 INFO [train.py:763] (2/8) Epoch 27, batch 4500, loss[loss=0.1926, simple_loss=0.2987, pruned_loss=0.04322, over 7222.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2643, pruned_loss=0.03268, over 1391227.69 frames.], batch size: 21, lr: 2.76e-04
+2022-04-30 06:32:50,033 INFO [train.py:763] (2/8) Epoch 27, batch 4550, loss[loss=0.1639, simple_loss=0.2707, pruned_loss=0.02853, over 6505.00 frames.], tot_loss[loss=0.1659, simple_loss=0.265, pruned_loss=0.03335, over 1361605.88 frames.], batch size: 38, lr: 2.76e-04
+2022-04-30 06:34:19,192 INFO [train.py:763] (2/8) Epoch 28, batch 0, loss[loss=0.1833, simple_loss=0.2959, pruned_loss=0.03537, over 7109.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2959, pruned_loss=0.03537, over 7109.00 frames.], batch size: 28, lr: 2.71e-04
+2022-04-30 06:35:24,831 INFO [train.py:763] (2/8) Epoch 28, batch 50, loss[loss=0.221, simple_loss=0.3121, pruned_loss=0.06497, over 7288.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2652, pruned_loss=0.03267, over 323180.77 frames.], batch size: 24, lr: 2.71e-04
+2022-04-30 06:36:31,684 INFO [train.py:763] (2/8) Epoch 28, batch 100, loss[loss=0.1791, simple_loss=0.2878, pruned_loss=0.03518, over 7318.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2644, pruned_loss=0.0326, over 568774.16 frames.], batch size: 21, lr: 2.71e-04
+2022-04-30 06:37:37,370 INFO [train.py:763] (2/8) Epoch 28, batch 150, loss[loss=0.1627, simple_loss=0.2635, pruned_loss=0.03093, over 7239.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2635, pruned_loss=0.03186, over 758951.03 frames.], batch size: 20, lr: 2.71e-04
+2022-04-30 06:38:43,638 INFO [train.py:763] (2/8) Epoch 28, batch 200, loss[loss=0.1543, simple_loss=0.2486, pruned_loss=0.02997, over 7063.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2622, pruned_loss=0.0312, over 908241.53 frames.], batch size: 18, lr: 2.71e-04
+2022-04-30 06:39:49,237 INFO [train.py:763] (2/8) Epoch 28, batch 250, loss[loss=0.1621, simple_loss=0.2613, pruned_loss=0.03145, over 5194.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2616, pruned_loss=0.03074, over 1019054.66 frames.], batch size: 54, lr: 2.71e-04
+2022-04-30 06:40:54,480 INFO [train.py:763] (2/8) Epoch 28, batch 300, loss[loss=0.1847, simple_loss=0.2736, pruned_loss=0.04787, over 7170.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2629, pruned_loss=0.03111, over 1108676.99 frames.], batch size: 18, lr: 2.70e-04
+2022-04-30 06:41:59,621 INFO [train.py:763] (2/8) Epoch 28, batch 350, loss[loss=0.1543, simple_loss=0.2541, pruned_loss=0.0272, over 7061.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2634, pruned_loss=0.03156, over 1180311.10 frames.], batch size: 18, lr: 2.70e-04
+2022-04-30 06:43:05,884 INFO [train.py:763] (2/8) Epoch 28, batch 400, loss[loss=0.1616, simple_loss=0.2663, pruned_loss=0.02846, over 7142.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2637, pruned_loss=0.03155, over 1236208.86 frames.], batch size: 20, lr: 2.70e-04
+2022-04-30 06:44:12,420 INFO [train.py:763] (2/8) Epoch 28, batch 450, loss[loss=0.1806, simple_loss=0.2855, pruned_loss=0.03784, over 7105.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2638, pruned_loss=0.03193, over 1282527.70 frames.], batch size: 21, lr: 2.70e-04
+2022-04-30 06:45:17,935 INFO [train.py:763] (2/8) Epoch 28, batch 500, loss[loss=0.2033, simple_loss=0.2991, pruned_loss=0.05375, over 4819.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2636, pruned_loss=0.03203, over 1309992.32 frames.], batch size: 52, lr: 2.70e-04
+2022-04-30 06:46:23,645 INFO [train.py:763] (2/8) Epoch 28, batch 550, loss[loss=0.1459, simple_loss=0.2535, pruned_loss=0.01912, over 7215.00 frames.], tot_loss[loss=0.164, simple_loss=0.2639, pruned_loss=0.03206, over 1332084.91 frames.], batch size: 21, lr: 2.70e-04
+2022-04-30 06:47:29,777 INFO [train.py:763] (2/8) Epoch 28, batch 600, loss[loss=0.141, simple_loss=0.2431, pruned_loss=0.01943, over 7262.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2632, pruned_loss=0.03217, over 1348723.86 frames.], batch size: 19, lr: 2.70e-04
+2022-04-30 06:48:35,459 INFO [train.py:763] (2/8) Epoch 28, batch 650, loss[loss=0.1665, simple_loss=0.2571, pruned_loss=0.03797, over 7060.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2623, pruned_loss=0.03232, over 1367142.59 frames.], batch size: 18, lr: 2.70e-04
+2022-04-30 06:49:42,648 INFO [train.py:763] (2/8) Epoch 28, batch 700, loss[loss=0.1896, simple_loss=0.2729, pruned_loss=0.0532, over 4910.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2628, pruned_loss=0.03253, over 1376156.13 frames.], batch size: 52, lr: 2.70e-04
+2022-04-30 06:50:48,227 INFO [train.py:763] (2/8) Epoch 28, batch 750, loss[loss=0.1679, simple_loss=0.2668, pruned_loss=0.0345, over 7429.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2624, pruned_loss=0.03213, over 1382445.03 frames.], batch size: 20, lr: 2.70e-04
+2022-04-30 06:51:53,702 INFO [train.py:763] (2/8) Epoch 28, batch 800, loss[loss=0.1579, simple_loss=0.265, pruned_loss=0.02541, over 7126.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2627, pruned_loss=0.03219, over 1388093.76 frames.], batch size: 21, lr: 2.70e-04
+2022-04-30 06:52:59,915 INFO [train.py:763] (2/8) Epoch 28, batch 850, loss[loss=0.1642, simple_loss=0.2677, pruned_loss=0.03029, over 6427.00 frames.], tot_loss[loss=0.164, simple_loss=0.2634, pruned_loss=0.0323, over 1393115.22 frames.], batch size: 37, lr: 2.70e-04
+2022-04-30 06:54:06,448 INFO [train.py:763] (2/8) Epoch 28, batch 900, loss[loss=0.178, simple_loss=0.2714, pruned_loss=0.04228, over 6720.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.03197, over 1399776.77 frames.], batch size: 31, lr: 2.70e-04
+2022-04-30 06:55:12,061 INFO [train.py:763] (2/8) Epoch 28, batch 950, loss[loss=0.1728, simple_loss=0.276, pruned_loss=0.03477, over 7187.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2629, pruned_loss=0.0318, over 1408634.03 frames.], batch size: 22, lr: 2.70e-04
+2022-04-30 06:56:17,975 INFO [train.py:763] (2/8) Epoch 28, batch 1000, loss[loss=0.1715, simple_loss=0.2661, pruned_loss=0.03846, over 6793.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2622, pruned_loss=0.03197, over 1414463.81 frames.], batch size: 15, lr: 2.70e-04
+2022-04-30 06:57:23,495 INFO [train.py:763] (2/8) Epoch 28, batch 1050, loss[loss=0.1473, simple_loss=0.2526, pruned_loss=0.02102, over 7422.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2622, pruned_loss=0.03168, over 1419553.62 frames.], batch size: 21, lr: 2.70e-04
+2022-04-30 06:58:29,246 INFO [train.py:763] (2/8) Epoch 28, batch 1100, loss[loss=0.1451, simple_loss=0.2362, pruned_loss=0.02702, over 7275.00 frames.], tot_loss[loss=0.163, simple_loss=0.2625, pruned_loss=0.0318, over 1422432.00 frames.], batch size: 17, lr: 2.70e-04
+2022-04-30 06:59:35,654 INFO [train.py:763] (2/8) Epoch 28, batch 1150, loss[loss=0.1682, simple_loss=0.2728, pruned_loss=0.03178, over 7066.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2631, pruned_loss=0.03207, over 1421773.53 frames.], batch size: 28, lr: 2.70e-04
+2022-04-30 07:00:40,809 INFO [train.py:763] (2/8) Epoch 28, batch 1200, loss[loss=0.1586, simple_loss=0.2636, pruned_loss=0.0268, over 7082.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2643, pruned_loss=0.03228, over 1424634.37 frames.], batch size: 28, lr: 2.70e-04
+2022-04-30 07:01:47,020 INFO [train.py:763] (2/8) Epoch 28, batch 1250, loss[loss=0.1757, simple_loss=0.2801, pruned_loss=0.03565, over 7198.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2639, pruned_loss=0.03265, over 1419520.39 frames.], batch size: 22, lr: 2.70e-04
+2022-04-30 07:02:52,925 INFO [train.py:763] (2/8) Epoch 28, batch 1300, loss[loss=0.1488, simple_loss=0.2559, pruned_loss=0.02083, over 7144.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2638, pruned_loss=0.03277, over 1421998.15 frames.], batch size: 20, lr: 2.69e-04
+2022-04-30 07:03:58,472 INFO [train.py:763] (2/8) Epoch 28, batch 1350, loss[loss=0.1914, simple_loss=0.2859, pruned_loss=0.04847, over 7118.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2634, pruned_loss=0.03237, over 1427035.54 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:05:04,524 INFO [train.py:763] (2/8) Epoch 28, batch 1400, loss[loss=0.1321, simple_loss=0.2239, pruned_loss=0.02019, over 7293.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2631, pruned_loss=0.03231, over 1428415.64 frames.], batch size: 17, lr: 2.69e-04
+2022-04-30 07:06:10,005 INFO [train.py:763] (2/8) Epoch 28, batch 1450, loss[loss=0.1721, simple_loss=0.274, pruned_loss=0.03513, over 7275.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2629, pruned_loss=0.03215, over 1432237.13 frames.], batch size: 24, lr: 2.69e-04
+2022-04-30 07:07:16,027 INFO [train.py:763] (2/8) Epoch 28, batch 1500, loss[loss=0.1402, simple_loss=0.2468, pruned_loss=0.01678, over 7328.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2634, pruned_loss=0.03196, over 1428321.83 frames.], batch size: 20, lr: 2.69e-04
+2022-04-30 07:08:21,692 INFO [train.py:763] (2/8) Epoch 28, batch 1550, loss[loss=0.1726, simple_loss=0.2826, pruned_loss=0.03131, over 7220.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2634, pruned_loss=0.0319, over 1430043.86 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:09:26,974 INFO [train.py:763] (2/8) Epoch 28, batch 1600, loss[loss=0.1524, simple_loss=0.2395, pruned_loss=0.03269, over 6760.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2635, pruned_loss=0.03186, over 1427731.40 frames.], batch size: 15, lr: 2.69e-04
+2022-04-30 07:10:32,954 INFO [train.py:763] (2/8) Epoch 28, batch 1650, loss[loss=0.1528, simple_loss=0.2374, pruned_loss=0.03408, over 6764.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2629, pruned_loss=0.03185, over 1429119.39 frames.], batch size: 15, lr: 2.69e-04
+2022-04-30 07:11:39,858 INFO [train.py:763] (2/8) Epoch 28, batch 1700, loss[loss=0.1612, simple_loss=0.2607, pruned_loss=0.03087, over 7262.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03128, over 1431301.84 frames.], batch size: 19, lr: 2.69e-04
+2022-04-30 07:12:45,209 INFO [train.py:763] (2/8) Epoch 28, batch 1750, loss[loss=0.1607, simple_loss=0.2605, pruned_loss=0.0304, over 7109.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2623, pruned_loss=0.03154, over 1433421.17 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:13:50,835 INFO [train.py:763] (2/8) Epoch 28, batch 1800, loss[loss=0.1585, simple_loss=0.2504, pruned_loss=0.0333, over 7425.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2625, pruned_loss=0.03192, over 1423492.47 frames.], batch size: 17, lr: 2.69e-04
+2022-04-30 07:14:56,955 INFO [train.py:763] (2/8) Epoch 28, batch 1850, loss[loss=0.1548, simple_loss=0.2479, pruned_loss=0.03083, over 7410.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2621, pruned_loss=0.0316, over 1426018.83 frames.], batch size: 18, lr: 2.69e-04
+2022-04-30 07:16:02,987 INFO [train.py:763] (2/8) Epoch 28, batch 1900, loss[loss=0.1851, simple_loss=0.2717, pruned_loss=0.04926, over 7156.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2619, pruned_loss=0.03161, over 1426045.52 frames.], batch size: 26, lr: 2.69e-04
+2022-04-30 07:17:09,675 INFO [train.py:763] (2/8) Epoch 28, batch 1950, loss[loss=0.1668, simple_loss=0.2755, pruned_loss=0.02911, over 7330.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2624, pruned_loss=0.03209, over 1427819.98 frames.], batch size: 25, lr: 2.69e-04
+2022-04-30 07:18:15,509 INFO [train.py:763] (2/8) Epoch 28, batch 2000, loss[loss=0.177, simple_loss=0.2773, pruned_loss=0.03836, over 7206.00 frames.], tot_loss[loss=0.163, simple_loss=0.2624, pruned_loss=0.03179, over 1430762.07 frames.], batch size: 23, lr: 2.69e-04
+2022-04-30 07:19:21,141 INFO [train.py:763] (2/8) Epoch 28, batch 2050, loss[loss=0.1802, simple_loss=0.2899, pruned_loss=0.03523, over 7324.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2625, pruned_loss=0.03169, over 1424047.69 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:20:26,742 INFO [train.py:763] (2/8) Epoch 28, batch 2100, loss[loss=0.1801, simple_loss=0.2968, pruned_loss=0.03171, over 7290.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.0311, over 1425347.84 frames.], batch size: 25, lr: 2.69e-04
+2022-04-30 07:21:33,840 INFO [train.py:763] (2/8) Epoch 28, batch 2150, loss[loss=0.172, simple_loss=0.2753, pruned_loss=0.03439, over 7217.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2623, pruned_loss=0.03157, over 1426169.61 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:22:48,757 INFO [train.py:763] (2/8) Epoch 28, batch 2200, loss[loss=0.1706, simple_loss=0.2761, pruned_loss=0.03252, over 7294.00 frames.], tot_loss[loss=0.163, simple_loss=0.2625, pruned_loss=0.0317, over 1420702.80 frames.], batch size: 25, lr: 2.69e-04
+2022-04-30 07:23:56,112 INFO [train.py:763] (2/8) Epoch 28, batch 2250, loss[loss=0.191, simple_loss=0.2934, pruned_loss=0.04433, over 7121.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2631, pruned_loss=0.03179, over 1425396.86 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:25:01,832 INFO [train.py:763] (2/8) Epoch 28, batch 2300, loss[loss=0.1719, simple_loss=0.2712, pruned_loss=0.03629, over 7327.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2632, pruned_loss=0.0321, over 1426866.49 frames.], batch size: 24, lr: 2.68e-04
+2022-04-30 07:26:07,546 INFO [train.py:763] (2/8) Epoch 28, batch 2350, loss[loss=0.1551, simple_loss=0.249, pruned_loss=0.03062, over 7065.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2636, pruned_loss=0.03247, over 1424483.48 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:27:14,913 INFO [train.py:763] (2/8) Epoch 28, batch 2400, loss[loss=0.1717, simple_loss=0.2695, pruned_loss=0.03698, over 7357.00 frames.], tot_loss[loss=0.164, simple_loss=0.263, pruned_loss=0.03251, over 1425554.99 frames.], batch size: 19, lr: 2.68e-04
+2022-04-30 07:28:20,435 INFO [train.py:763] (2/8) Epoch 28, batch 2450, loss[loss=0.1581, simple_loss=0.2548, pruned_loss=0.03065, over 7107.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2635, pruned_loss=0.0325, over 1417404.90 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:29:26,087 INFO [train.py:763] (2/8) Epoch 28, batch 2500, loss[loss=0.1366, simple_loss=0.2351, pruned_loss=0.01908, over 7416.00 frames.], tot_loss[loss=0.1627, simple_loss=0.262, pruned_loss=0.03166, over 1420249.54 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:30:32,238 INFO [train.py:763] (2/8) Epoch 28, batch 2550, loss[loss=0.1441, simple_loss=0.2384, pruned_loss=0.02489, over 7154.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2622, pruned_loss=0.03178, over 1417365.48 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:31:37,897 INFO [train.py:763] (2/8) Epoch 28, batch 2600, loss[loss=0.2023, simple_loss=0.2963, pruned_loss=0.05415, over 7203.00 frames.], tot_loss[loss=0.163, simple_loss=0.2621, pruned_loss=0.03198, over 1416680.79 frames.], batch size: 23, lr: 2.68e-04
+2022-04-30 07:32:43,453 INFO [train.py:763] (2/8) Epoch 28, batch 2650, loss[loss=0.1373, simple_loss=0.2372, pruned_loss=0.01867, over 7405.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2617, pruned_loss=0.03178, over 1418743.49 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:33:59,642 INFO [train.py:763] (2/8) Epoch 28, batch 2700, loss[loss=0.1725, simple_loss=0.2627, pruned_loss=0.04117, over 5062.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2613, pruned_loss=0.03163, over 1418592.93 frames.], batch size: 52, lr: 2.68e-04
+2022-04-30 07:35:13,946 INFO [train.py:763] (2/8) Epoch 28, batch 2750, loss[loss=0.1744, simple_loss=0.2701, pruned_loss=0.03931, over 7316.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2626, pruned_loss=0.03227, over 1413544.53 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:36:28,353 INFO [train.py:763] (2/8) Epoch 28, batch 2800, loss[loss=0.1758, simple_loss=0.2896, pruned_loss=0.03102, over 7335.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2628, pruned_loss=0.03189, over 1417522.15 frames.], batch size: 22, lr: 2.68e-04
+2022-04-30 07:37:44,241 INFO [train.py:763] (2/8) Epoch 28, batch 2850, loss[loss=0.1452, simple_loss=0.2378, pruned_loss=0.02627, over 7263.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2621, pruned_loss=0.03158, over 1418560.07 frames.], batch size: 19, lr: 2.68e-04
+2022-04-30 07:38:58,496 INFO [train.py:763] (2/8) Epoch 28, batch 2900, loss[loss=0.1448, simple_loss=0.2329, pruned_loss=0.02839, over 7287.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2622, pruned_loss=0.03176, over 1418030.94 frames.], batch size: 17, lr: 2.68e-04
+2022-04-30 07:40:13,605 INFO [train.py:763] (2/8) Epoch 28, batch 2950, loss[loss=0.1446, simple_loss=0.2307, pruned_loss=0.02926, over 7143.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2607, pruned_loss=0.03177, over 1417886.61 frames.], batch size: 17, lr: 2.68e-04
+2022-04-30 07:41:27,526 INFO [train.py:763] (2/8) Epoch 28, batch 3000, loss[loss=0.1609, simple_loss=0.2645, pruned_loss=0.02862, over 7236.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2621, pruned_loss=0.03202, over 1418666.28 frames.], batch size: 20, lr: 2.68e-04
+2022-04-30 07:41:27,527 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 07:41:44,121 INFO [train.py:792] (2/8) Epoch 28, validation: loss=0.1685, simple_loss=0.2656, pruned_loss=0.03573, over 698248.00 frames.
+2022-04-30 07:42:49,821 INFO [train.py:763] (2/8) Epoch 28, batch 3050, loss[loss=0.1711, simple_loss=0.2692, pruned_loss=0.03646, over 7150.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2624, pruned_loss=0.03212, over 1421553.00 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:43:55,525 INFO [train.py:763] (2/8) Epoch 28, batch 3100, loss[loss=0.14, simple_loss=0.2328, pruned_loss=0.02357, over 7272.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2616, pruned_loss=0.03206, over 1418669.30 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:45:01,626 INFO [train.py:763] (2/8) Epoch 28, batch 3150, loss[loss=0.1744, simple_loss=0.2859, pruned_loss=0.03143, over 7224.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2621, pruned_loss=0.03163, over 1422546.54 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:46:07,722 INFO [train.py:763] (2/8) Epoch 28, batch 3200, loss[loss=0.1722, simple_loss=0.2759, pruned_loss=0.03425, over 7098.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2624, pruned_loss=0.03139, over 1422170.56 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:47:14,366 INFO [train.py:763] (2/8) Epoch 28, batch 3250, loss[loss=0.1532, simple_loss=0.2447, pruned_loss=0.0308, over 7260.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2621, pruned_loss=0.03162, over 1422891.59 frames.], batch size: 16, lr: 2.67e-04
+2022-04-30 07:48:20,826 INFO [train.py:763] (2/8) Epoch 28, batch 3300, loss[loss=0.162, simple_loss=0.2642, pruned_loss=0.02988, over 7222.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2633, pruned_loss=0.03206, over 1421831.41 frames.], batch size: 21, lr: 2.67e-04
+2022-04-30 07:49:26,927 INFO [train.py:763] (2/8) Epoch 28, batch 3350, loss[loss=0.1851, simple_loss=0.2831, pruned_loss=0.04362, over 7122.00 frames.], tot_loss[loss=0.1637, simple_loss=0.263, pruned_loss=0.03214, over 1419701.18 frames.], batch size: 28, lr: 2.67e-04
+2022-04-30 07:50:33,791 INFO [train.py:763] (2/8) Epoch 28, batch 3400, loss[loss=0.1799, simple_loss=0.2763, pruned_loss=0.0417, over 7068.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2636, pruned_loss=0.03288, over 1417798.04 frames.], batch size: 18, lr: 2.67e-04
+2022-04-30 07:51:39,844 INFO [train.py:763] (2/8) Epoch 28, batch 3450, loss[loss=0.1329, simple_loss=0.23, pruned_loss=0.01793, over 7275.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2632, pruned_loss=0.03259, over 1419349.73 frames.], batch size: 17, lr: 2.67e-04
+2022-04-30 07:52:45,404 INFO [train.py:763] (2/8) Epoch 28, batch 3500, loss[loss=0.1715, simple_loss=0.2669, pruned_loss=0.03807, over 6792.00 frames.], tot_loss[loss=0.1639, simple_loss=0.263, pruned_loss=0.03236, over 1419187.52 frames.], batch size: 31, lr: 2.67e-04
+2022-04-30 07:53:50,879 INFO [train.py:763] (2/8) Epoch 28, batch 3550, loss[loss=0.145, simple_loss=0.2412, pruned_loss=0.0244, over 7298.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2625, pruned_loss=0.03255, over 1423433.57 frames.], batch size: 18, lr: 2.67e-04
+2022-04-30 07:54:56,699 INFO [train.py:763] (2/8) Epoch 28, batch 3600, loss[loss=0.1349, simple_loss=0.2332, pruned_loss=0.01826, over 6783.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2634, pruned_loss=0.03303, over 1423555.38 frames.], batch size: 15, lr: 2.67e-04
+2022-04-30 07:56:02,358 INFO [train.py:763] (2/8) Epoch 28, batch 3650, loss[loss=0.1701, simple_loss=0.2787, pruned_loss=0.03072, over 7326.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2633, pruned_loss=0.03295, over 1426614.83 frames.], batch size: 22, lr: 2.67e-04
+2022-04-30 07:57:08,116 INFO [train.py:763] (2/8) Epoch 28, batch 3700, loss[loss=0.181, simple_loss=0.2818, pruned_loss=0.04006, over 7193.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2633, pruned_loss=0.03271, over 1426360.45 frames.], batch size: 23, lr: 2.67e-04
+2022-04-30 07:58:13,559 INFO [train.py:763] (2/8) Epoch 28, batch 3750, loss[loss=0.2105, simple_loss=0.2987, pruned_loss=0.06114, over 4994.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2638, pruned_loss=0.03279, over 1425607.81 frames.], batch size: 52, lr: 2.67e-04
+2022-04-30 07:59:19,060 INFO [train.py:763] (2/8) Epoch 28, batch 3800, loss[loss=0.1879, simple_loss=0.2825, pruned_loss=0.04665, over 7435.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2635, pruned_loss=0.03252, over 1426364.28 frames.], batch size: 20, lr: 2.67e-04
+2022-04-30 08:00:24,607 INFO [train.py:763] (2/8) Epoch 28, batch 3850, loss[loss=0.1912, simple_loss=0.296, pruned_loss=0.04318, over 7390.00 frames.], tot_loss[loss=0.1645, simple_loss=0.264, pruned_loss=0.03247, over 1426951.35 frames.], batch size: 23, lr: 2.67e-04
+2022-04-30 08:01:31,041 INFO [train.py:763] (2/8) Epoch 28, batch 3900, loss[loss=0.1704, simple_loss=0.2682, pruned_loss=0.03634, over 7297.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2636, pruned_loss=0.03229, over 1429646.05 frames.], batch size: 24, lr: 2.67e-04
+2022-04-30 08:02:37,685 INFO [train.py:763] (2/8) Epoch 28, batch 3950, loss[loss=0.1537, simple_loss=0.2417, pruned_loss=0.03282, over 7412.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2645, pruned_loss=0.03207, over 1430767.47 frames.], batch size: 18, lr: 2.67e-04
+2022-04-30 08:03:44,062 INFO [train.py:763] (2/8) Epoch 28, batch 4000, loss[loss=0.1598, simple_loss=0.2682, pruned_loss=0.02569, over 7352.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2645, pruned_loss=0.03212, over 1430202.73 frames.], batch size: 22, lr: 2.67e-04
+2022-04-30 08:04:50,782 INFO [train.py:763] (2/8) Epoch 28, batch 4050, loss[loss=0.1429, simple_loss=0.2332, pruned_loss=0.0263, over 7269.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2645, pruned_loss=0.03231, over 1428909.50 frames.], batch size: 17, lr: 2.67e-04
+2022-04-30 08:05:55,977 INFO [train.py:763] (2/8) Epoch 28, batch 4100, loss[loss=0.1817, simple_loss=0.2949, pruned_loss=0.03424, over 7330.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2645, pruned_loss=0.03232, over 1429678.42 frames.], batch size: 22, lr: 2.67e-04
+2022-04-30 08:07:02,628 INFO [train.py:763] (2/8) Epoch 28, batch 4150, loss[loss=0.17, simple_loss=0.2737, pruned_loss=0.03317, over 7330.00 frames.], tot_loss[loss=0.164, simple_loss=0.2638, pruned_loss=0.03205, over 1423591.48 frames.], batch size: 21, lr: 2.67e-04
+2022-04-30 08:08:09,140 INFO [train.py:763] (2/8) Epoch 28, batch 4200, loss[loss=0.1456, simple_loss=0.2495, pruned_loss=0.02088, over 7257.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2638, pruned_loss=0.03223, over 1420132.90 frames.], batch size: 19, lr: 2.66e-04
+2022-04-30 08:09:14,664 INFO [train.py:763] (2/8) Epoch 28, batch 4250, loss[loss=0.1729, simple_loss=0.2787, pruned_loss=0.03356, over 6848.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2635, pruned_loss=0.03198, over 1421281.19 frames.], batch size: 31, lr: 2.66e-04
+2022-04-30 08:10:19,661 INFO [train.py:763] (2/8) Epoch 28, batch 4300, loss[loss=0.153, simple_loss=0.2482, pruned_loss=0.02891, over 7166.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2635, pruned_loss=0.03195, over 1417601.51 frames.], batch size: 18, lr: 2.66e-04
+2022-04-30 08:11:24,964 INFO [train.py:763] (2/8) Epoch 28, batch 4350, loss[loss=0.1463, simple_loss=0.2548, pruned_loss=0.01888, over 7322.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2629, pruned_loss=0.03188, over 1418588.49 frames.], batch size: 21, lr: 2.66e-04
+2022-04-30 08:12:30,141 INFO [train.py:763] (2/8) Epoch 28, batch 4400, loss[loss=0.179, simple_loss=0.2774, pruned_loss=0.04034, over 7280.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2635, pruned_loss=0.03244, over 1410867.24 frames.], batch size: 24, lr: 2.66e-04
+2022-04-30 08:13:35,271 INFO [train.py:763] (2/8) Epoch 28, batch 4450, loss[loss=0.148, simple_loss=0.2609, pruned_loss=0.01749, over 6464.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2638, pruned_loss=0.03258, over 1402109.20 frames.], batch size: 38, lr: 2.66e-04
+2022-04-30 08:14:40,127 INFO [train.py:763] (2/8) Epoch 28, batch 4500, loss[loss=0.1664, simple_loss=0.2645, pruned_loss=0.0342, over 7203.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2652, pruned_loss=0.03321, over 1379657.51 frames.], batch size: 22, lr: 2.66e-04
+2022-04-30 08:15:45,360 INFO [train.py:763] (2/8) Epoch 28, batch 4550, loss[loss=0.2062, simple_loss=0.2921, pruned_loss=0.06016, over 5173.00 frames.], tot_loss[loss=0.167, simple_loss=0.2663, pruned_loss=0.03381, over 1360113.02 frames.], batch size: 52, lr: 2.66e-04
+2022-04-30 08:17:05,887 INFO [train.py:763] (2/8) Epoch 29, batch 0, loss[loss=0.1543, simple_loss=0.2509, pruned_loss=0.02886, over 7331.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2509, pruned_loss=0.02886, over 7331.00 frames.], batch size: 20, lr: 2.62e-04
+2022-04-30 08:18:11,687 INFO [train.py:763] (2/8) Epoch 29, batch 50, loss[loss=0.1707, simple_loss=0.2596, pruned_loss=0.04087, over 7282.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2608, pruned_loss=0.02977, over 324231.20 frames.], batch size: 18, lr: 2.62e-04
+2022-04-30 08:19:17,257 INFO [train.py:763] (2/8) Epoch 29, batch 100, loss[loss=0.1335, simple_loss=0.2248, pruned_loss=0.02107, over 7278.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2592, pruned_loss=0.03009, over 572172.62 frames.], batch size: 17, lr: 2.62e-04
+2022-04-30 08:20:22,566 INFO [train.py:763] (2/8) Epoch 29, batch 150, loss[loss=0.188, simple_loss=0.2886, pruned_loss=0.04367, over 7309.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2605, pruned_loss=0.0314, over 749737.16 frames.], batch size: 24, lr: 2.62e-04
+2022-04-30 08:21:28,002 INFO [train.py:763] (2/8) Epoch 29, batch 200, loss[loss=0.1421, simple_loss=0.2466, pruned_loss=0.01884, over 7358.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2617, pruned_loss=0.03173, over 899945.73 frames.], batch size: 19, lr: 2.61e-04
+2022-04-30 08:22:33,077 INFO [train.py:763] (2/8) Epoch 29, batch 250, loss[loss=0.1617, simple_loss=0.2521, pruned_loss=0.0357, over 6830.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2629, pruned_loss=0.03168, over 1016239.85 frames.], batch size: 15, lr: 2.61e-04
+2022-04-30 08:23:39,495 INFO [train.py:763] (2/8) Epoch 29, batch 300, loss[loss=0.1585, simple_loss=0.2534, pruned_loss=0.03182, over 7278.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2643, pruned_loss=0.03234, over 1109003.14 frames.], batch size: 18, lr: 2.61e-04
+2022-04-30 08:24:46,636 INFO [train.py:763] (2/8) Epoch 29, batch 350, loss[loss=0.153, simple_loss=0.2526, pruned_loss=0.02674, over 7340.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2621, pruned_loss=0.03162, over 1181409.11 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:25:52,369 INFO [train.py:763] (2/8) Epoch 29, batch 400, loss[loss=0.1725, simple_loss=0.279, pruned_loss=0.03298, over 7273.00 frames.], tot_loss[loss=0.163, simple_loss=0.263, pruned_loss=0.03153, over 1237473.98 frames.], batch size: 24, lr: 2.61e-04
+2022-04-30 08:26:57,827 INFO [train.py:763] (2/8) Epoch 29, batch 450, loss[loss=0.1697, simple_loss=0.2728, pruned_loss=0.03329, over 7417.00 frames.], tot_loss[loss=0.1632, simple_loss=0.263, pruned_loss=0.03172, over 1279460.90 frames.], batch size: 21, lr: 2.61e-04
+2022-04-30 08:28:03,211 INFO [train.py:763] (2/8) Epoch 29, batch 500, loss[loss=0.1559, simple_loss=0.2483, pruned_loss=0.0317, over 7330.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2629, pruned_loss=0.03174, over 1307778.42 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:29:08,669 INFO [train.py:763] (2/8) Epoch 29, batch 550, loss[loss=0.168, simple_loss=0.2754, pruned_loss=0.03031, over 7274.00 frames.], tot_loss[loss=0.163, simple_loss=0.2629, pruned_loss=0.03154, over 1335589.53 frames.], batch size: 24, lr: 2.61e-04
+2022-04-30 08:30:14,683 INFO [train.py:763] (2/8) Epoch 29, batch 600, loss[loss=0.1517, simple_loss=0.2568, pruned_loss=0.02334, over 7205.00 frames.], tot_loss[loss=0.163, simple_loss=0.263, pruned_loss=0.03153, over 1351031.81 frames.], batch size: 22, lr: 2.61e-04
+2022-04-30 08:31:20,871 INFO [train.py:763] (2/8) Epoch 29, batch 650, loss[loss=0.1472, simple_loss=0.2439, pruned_loss=0.0252, over 7071.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2636, pruned_loss=0.03187, over 1366079.68 frames.], batch size: 18, lr: 2.61e-04
+2022-04-30 08:32:27,043 INFO [train.py:763] (2/8) Epoch 29, batch 700, loss[loss=0.1593, simple_loss=0.2559, pruned_loss=0.03134, over 7332.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2645, pruned_loss=0.03228, over 1374467.66 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:33:32,280 INFO [train.py:763] (2/8) Epoch 29, batch 750, loss[loss=0.153, simple_loss=0.2482, pruned_loss=0.02888, over 7239.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2635, pruned_loss=0.03172, over 1382045.50 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:34:37,538 INFO [train.py:763] (2/8) Epoch 29, batch 800, loss[loss=0.1727, simple_loss=0.2847, pruned_loss=0.03041, over 7339.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2632, pruned_loss=0.03171, over 1388384.21 frames.], batch size: 22, lr: 2.61e-04
+2022-04-30 08:35:43,020 INFO [train.py:763] (2/8) Epoch 29, batch 850, loss[loss=0.1616, simple_loss=0.2579, pruned_loss=0.03258, over 7060.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2614, pruned_loss=0.03112, over 1397196.60 frames.], batch size: 18, lr: 2.61e-04
+2022-04-30 08:36:48,527 INFO [train.py:763] (2/8) Epoch 29, batch 900, loss[loss=0.1663, simple_loss=0.2759, pruned_loss=0.02834, over 7227.00 frames.], tot_loss[loss=0.1624, simple_loss=0.262, pruned_loss=0.03145, over 1401427.57 frames.], batch size: 21, lr: 2.61e-04
+2022-04-30 08:37:53,908 INFO [train.py:763] (2/8) Epoch 29, batch 950, loss[loss=0.1378, simple_loss=0.2432, pruned_loss=0.01621, over 7112.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2623, pruned_loss=0.03126, over 1407713.20 frames.], batch size: 21, lr: 2.61e-04
+2022-04-30 08:38:59,971 INFO [train.py:763] (2/8) Epoch 29, batch 1000, loss[loss=0.1679, simple_loss=0.2745, pruned_loss=0.03068, over 7157.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2636, pruned_loss=0.03142, over 1411574.78 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:40:06,267 INFO [train.py:763] (2/8) Epoch 29, batch 1050, loss[loss=0.1423, simple_loss=0.2345, pruned_loss=0.02506, over 7262.00 frames.], tot_loss[loss=0.1639, simple_loss=0.264, pruned_loss=0.03186, over 1408052.58 frames.], batch size: 18, lr: 2.61e-04
+2022-04-30 08:41:11,503 INFO [train.py:763] (2/8) Epoch 29, batch 1100, loss[loss=0.1812, simple_loss=0.2755, pruned_loss=0.04351, over 7326.00 frames.], tot_loss[loss=0.165, simple_loss=0.2654, pruned_loss=0.03227, over 1417397.20 frames.], batch size: 21, lr: 2.61e-04
+2022-04-30 08:42:16,626 INFO [train.py:763] (2/8) Epoch 29, batch 1150, loss[loss=0.153, simple_loss=0.2463, pruned_loss=0.02985, over 6994.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2656, pruned_loss=0.03229, over 1418908.60 frames.], batch size: 16, lr: 2.61e-04
+2022-04-30 08:43:21,908 INFO [train.py:763] (2/8) Epoch 29, batch 1200, loss[loss=0.1591, simple_loss=0.2602, pruned_loss=0.02896, over 7166.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2646, pruned_loss=0.03162, over 1423511.34 frames.], batch size: 19, lr: 2.61e-04
+2022-04-30 08:44:27,475 INFO [train.py:763] (2/8) Epoch 29, batch 1250, loss[loss=0.161, simple_loss=0.2569, pruned_loss=0.03255, over 4927.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2639, pruned_loss=0.03178, over 1418248.13 frames.], batch size: 53, lr: 2.60e-04
+2022-04-30 08:45:34,622 INFO [train.py:763] (2/8) Epoch 29, batch 1300, loss[loss=0.1516, simple_loss=0.257, pruned_loss=0.02314, over 7347.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2631, pruned_loss=0.03126, over 1419726.74 frames.], batch size: 22, lr: 2.60e-04
+2022-04-30 08:46:42,212 INFO [train.py:763] (2/8) Epoch 29, batch 1350, loss[loss=0.1829, simple_loss=0.2856, pruned_loss=0.04009, over 6511.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2641, pruned_loss=0.03181, over 1420542.27 frames.], batch size: 38, lr: 2.60e-04
+2022-04-30 08:47:48,985 INFO [train.py:763] (2/8) Epoch 29, batch 1400, loss[loss=0.1391, simple_loss=0.2315, pruned_loss=0.02331, over 7178.00 frames.], tot_loss[loss=0.164, simple_loss=0.264, pruned_loss=0.03204, over 1420998.53 frames.], batch size: 16, lr: 2.60e-04
+2022-04-30 08:48:56,272 INFO [train.py:763] (2/8) Epoch 29, batch 1450, loss[loss=0.168, simple_loss=0.2766, pruned_loss=0.02972, over 7116.00 frames.], tot_loss[loss=0.1641, simple_loss=0.264, pruned_loss=0.03209, over 1419458.11 frames.], batch size: 21, lr: 2.60e-04
+2022-04-30 08:50:03,374 INFO [train.py:763] (2/8) Epoch 29, batch 1500, loss[loss=0.1435, simple_loss=0.2429, pruned_loss=0.02203, over 7268.00 frames.], tot_loss[loss=0.164, simple_loss=0.2637, pruned_loss=0.03219, over 1417884.24 frames.], batch size: 19, lr: 2.60e-04
+2022-04-30 08:51:09,974 INFO [train.py:763] (2/8) Epoch 29, batch 1550, loss[loss=0.1666, simple_loss=0.2722, pruned_loss=0.03048, over 7202.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2631, pruned_loss=0.03197, over 1418631.40 frames.], batch size: 23, lr: 2.60e-04
+2022-04-30 08:52:16,968 INFO [train.py:763] (2/8) Epoch 29, batch 1600, loss[loss=0.1598, simple_loss=0.2766, pruned_loss=0.02153, over 7316.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2642, pruned_loss=0.03261, over 1419949.22 frames.], batch size: 21, lr: 2.60e-04
+2022-04-30 08:53:22,971 INFO [train.py:763] (2/8) Epoch 29, batch 1650, loss[loss=0.1798, simple_loss=0.2849, pruned_loss=0.03731, over 7184.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2632, pruned_loss=0.03193, over 1423995.16 frames.], batch size: 26, lr: 2.60e-04
+2022-04-30 08:54:28,289 INFO [train.py:763] (2/8) Epoch 29, batch 1700, loss[loss=0.1332, simple_loss=0.2245, pruned_loss=0.02098, over 7148.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2632, pruned_loss=0.03185, over 1426971.31 frames.], batch size: 17, lr: 2.60e-04
+2022-04-30 08:55:35,253 INFO [train.py:763] (2/8) Epoch 29, batch 1750, loss[loss=0.1667, simple_loss=0.2774, pruned_loss=0.028, over 7150.00 frames.], tot_loss[loss=0.163, simple_loss=0.2629, pruned_loss=0.03159, over 1423045.85 frames.], batch size: 20, lr: 2.60e-04
+2022-04-30 08:56:42,193 INFO [train.py:763] (2/8) Epoch 29, batch 1800, loss[loss=0.1911, simple_loss=0.2862, pruned_loss=0.04802, over 4501.00 frames.], tot_loss[loss=0.163, simple_loss=0.2626, pruned_loss=0.03173, over 1420043.86 frames.], batch size: 52, lr: 2.60e-04
+2022-04-30 08:57:49,260 INFO [train.py:763] (2/8) Epoch 29, batch 1850, loss[loss=0.1729, simple_loss=0.2733, pruned_loss=0.03631, over 7112.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2625, pruned_loss=0.03166, over 1424366.26 frames.], batch size: 21, lr: 2.60e-04
+2022-04-30 08:58:55,864 INFO [train.py:763] (2/8) Epoch 29, batch 1900, loss[loss=0.1572, simple_loss=0.2439, pruned_loss=0.03529, over 6852.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2623, pruned_loss=0.03138, over 1426973.19 frames.], batch size: 15, lr: 2.60e-04
+2022-04-30 09:00:01,475 INFO [train.py:763] (2/8) Epoch 29, batch 1950, loss[loss=0.1502, simple_loss=0.2375, pruned_loss=0.03149, over 7270.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2624, pruned_loss=0.03129, over 1428779.99 frames.], batch size: 17, lr: 2.60e-04
+2022-04-30 09:01:06,696 INFO [train.py:763] (2/8) Epoch 29, batch 2000, loss[loss=0.1518, simple_loss=0.2588, pruned_loss=0.02236, over 7330.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2626, pruned_loss=0.0314, over 1430557.22 frames.], batch size: 22, lr: 2.60e-04
+2022-04-30 09:02:12,104 INFO [train.py:763] (2/8) Epoch 29, batch 2050, loss[loss=0.1735, simple_loss=0.2747, pruned_loss=0.03618, over 7188.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2625, pruned_loss=0.03134, over 1430760.40 frames.], batch size: 23, lr: 2.60e-04
+2022-04-30 09:03:17,244 INFO [train.py:763] (2/8) Epoch 29, batch 2100, loss[loss=0.1657, simple_loss=0.2772, pruned_loss=0.02708, over 7138.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2613, pruned_loss=0.03089, over 1430357.11 frames.], batch size: 20, lr: 2.60e-04
+2022-04-30 09:04:22,314 INFO [train.py:763] (2/8) Epoch 29, batch 2150, loss[loss=0.151, simple_loss=0.2452, pruned_loss=0.02837, over 7142.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2619, pruned_loss=0.03134, over 1428367.42 frames.], batch size: 17, lr: 2.60e-04
+2022-04-30 09:05:27,758 INFO [train.py:763] (2/8) Epoch 29, batch 2200, loss[loss=0.1722, simple_loss=0.277, pruned_loss=0.03368, over 7302.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2621, pruned_loss=0.03169, over 1423320.33 frames.], batch size: 24, lr: 2.60e-04
+2022-04-30 09:06:32,908 INFO [train.py:763] (2/8) Epoch 29, batch 2250, loss[loss=0.1807, simple_loss=0.2766, pruned_loss=0.04236, over 7154.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2628, pruned_loss=0.03205, over 1421848.49 frames.], batch size: 26, lr: 2.59e-04
+2022-04-30 09:07:38,515 INFO [train.py:763] (2/8) Epoch 29, batch 2300, loss[loss=0.1591, simple_loss=0.2623, pruned_loss=0.02797, over 7326.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2627, pruned_loss=0.03186, over 1417770.21 frames.], batch size: 20, lr: 2.59e-04
+2022-04-30 09:08:43,784 INFO [train.py:763] (2/8) Epoch 29, batch 2350, loss[loss=0.1582, simple_loss=0.2694, pruned_loss=0.0235, over 7339.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2626, pruned_loss=0.03176, over 1420430.28 frames.], batch size: 22, lr: 2.59e-04
+2022-04-30 09:09:49,526 INFO [train.py:763] (2/8) Epoch 29, batch 2400, loss[loss=0.1766, simple_loss=0.2772, pruned_loss=0.03797, over 7281.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2626, pruned_loss=0.03155, over 1422068.97 frames.], batch size: 25, lr: 2.59e-04
+2022-04-30 09:10:55,173 INFO [train.py:763] (2/8) Epoch 29, batch 2450, loss[loss=0.175, simple_loss=0.2722, pruned_loss=0.03891, over 7132.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2619, pruned_loss=0.03136, over 1426281.89 frames.], batch size: 20, lr: 2.59e-04
+2022-04-30 09:12:00,709 INFO [train.py:763] (2/8) Epoch 29, batch 2500, loss[loss=0.1592, simple_loss=0.2494, pruned_loss=0.03449, over 6793.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2609, pruned_loss=0.03122, over 1430145.16 frames.], batch size: 15, lr: 2.59e-04
+2022-04-30 09:13:06,078 INFO [train.py:763] (2/8) Epoch 29, batch 2550, loss[loss=0.1398, simple_loss=0.229, pruned_loss=0.02525, over 7412.00 frames.], tot_loss[loss=0.162, simple_loss=0.261, pruned_loss=0.03154, over 1426778.06 frames.], batch size: 18, lr: 2.59e-04
+2022-04-30 09:14:11,172 INFO [train.py:763] (2/8) Epoch 29, batch 2600, loss[loss=0.1795, simple_loss=0.2948, pruned_loss=0.03208, over 7117.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2617, pruned_loss=0.03151, over 1425490.08 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:15:16,451 INFO [train.py:763] (2/8) Epoch 29, batch 2650, loss[loss=0.1343, simple_loss=0.2285, pruned_loss=0.02005, over 7137.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2604, pruned_loss=0.03095, over 1427759.37 frames.], batch size: 17, lr: 2.59e-04
+2022-04-30 09:16:21,499 INFO [train.py:763] (2/8) Epoch 29, batch 2700, loss[loss=0.158, simple_loss=0.2598, pruned_loss=0.02814, over 7110.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2611, pruned_loss=0.0311, over 1428724.57 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:17:27,764 INFO [train.py:763] (2/8) Epoch 29, batch 2750, loss[loss=0.1463, simple_loss=0.2537, pruned_loss=0.01942, over 7240.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.03103, over 1424788.78 frames.], batch size: 20, lr: 2.59e-04
+2022-04-30 09:18:33,542 INFO [train.py:763] (2/8) Epoch 29, batch 2800, loss[loss=0.161, simple_loss=0.2626, pruned_loss=0.0297, over 7339.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2622, pruned_loss=0.03108, over 1424132.34 frames.], batch size: 22, lr: 2.59e-04
+2022-04-30 09:19:39,942 INFO [train.py:763] (2/8) Epoch 29, batch 2850, loss[loss=0.1643, simple_loss=0.2698, pruned_loss=0.02945, over 7231.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2617, pruned_loss=0.03126, over 1419204.32 frames.], batch size: 20, lr: 2.59e-04
+2022-04-30 09:20:45,377 INFO [train.py:763] (2/8) Epoch 29, batch 2900, loss[loss=0.1371, simple_loss=0.2256, pruned_loss=0.02427, over 7000.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2613, pruned_loss=0.03103, over 1422628.02 frames.], batch size: 16, lr: 2.59e-04
+2022-04-30 09:22:01,682 INFO [train.py:763] (2/8) Epoch 29, batch 2950, loss[loss=0.1838, simple_loss=0.2907, pruned_loss=0.03848, over 6296.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2605, pruned_loss=0.03066, over 1423904.35 frames.], batch size: 38, lr: 2.59e-04
+2022-04-30 09:23:07,148 INFO [train.py:763] (2/8) Epoch 29, batch 3000, loss[loss=0.17, simple_loss=0.2738, pruned_loss=0.0331, over 7117.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.03077, over 1426316.17 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:23:07,149 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 09:23:22,371 INFO [train.py:792] (2/8) Epoch 29, validation: loss=0.1693, simple_loss=0.2664, pruned_loss=0.03606, over 698248.00 frames.
+2022-04-30 09:24:27,447 INFO [train.py:763] (2/8) Epoch 29, batch 3050, loss[loss=0.1769, simple_loss=0.2775, pruned_loss=0.03812, over 7117.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03058, over 1427802.84 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:25:32,592 INFO [train.py:763] (2/8) Epoch 29, batch 3100, loss[loss=0.1578, simple_loss=0.2688, pruned_loss=0.0234, over 7418.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2612, pruned_loss=0.03051, over 1427342.00 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:26:38,419 INFO [train.py:763] (2/8) Epoch 29, batch 3150, loss[loss=0.1428, simple_loss=0.2412, pruned_loss=0.02219, over 7167.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2602, pruned_loss=0.03042, over 1422340.56 frames.], batch size: 18, lr: 2.59e-04
+2022-04-30 09:27:44,831 INFO [train.py:763] (2/8) Epoch 29, batch 3200, loss[loss=0.1447, simple_loss=0.2484, pruned_loss=0.02043, over 7264.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2597, pruned_loss=0.03049, over 1425799.79 frames.], batch size: 19, lr: 2.59e-04
+2022-04-30 09:28:51,938 INFO [train.py:763] (2/8) Epoch 29, batch 3250, loss[loss=0.1749, simple_loss=0.2845, pruned_loss=0.03259, over 7093.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2599, pruned_loss=0.03082, over 1421639.65 frames.], batch size: 28, lr: 2.59e-04
+2022-04-30 09:29:57,729 INFO [train.py:763] (2/8) Epoch 29, batch 3300, loss[loss=0.1671, simple_loss=0.278, pruned_loss=0.0281, over 7336.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2607, pruned_loss=0.03104, over 1424402.94 frames.], batch size: 20, lr: 2.58e-04
+2022-04-30 09:31:03,712 INFO [train.py:763] (2/8) Epoch 29, batch 3350, loss[loss=0.148, simple_loss=0.242, pruned_loss=0.02702, over 7289.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2602, pruned_loss=0.03099, over 1428252.70 frames.], batch size: 17, lr: 2.58e-04
+2022-04-30 09:32:09,338 INFO [train.py:763] (2/8) Epoch 29, batch 3400, loss[loss=0.1654, simple_loss=0.2583, pruned_loss=0.03627, over 4711.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2601, pruned_loss=0.03082, over 1424382.71 frames.], batch size: 52, lr: 2.58e-04
+2022-04-30 09:33:15,077 INFO [train.py:763] (2/8) Epoch 29, batch 3450, loss[loss=0.1878, simple_loss=0.2907, pruned_loss=0.04251, over 7284.00 frames.], tot_loss[loss=0.162, simple_loss=0.2607, pruned_loss=0.03165, over 1421211.55 frames.], batch size: 24, lr: 2.58e-04
+2022-04-30 09:34:21,146 INFO [train.py:763] (2/8) Epoch 29, batch 3500, loss[loss=0.224, simple_loss=0.3211, pruned_loss=0.06344, over 7190.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2614, pruned_loss=0.03194, over 1423675.99 frames.], batch size: 26, lr: 2.58e-04
+2022-04-30 09:35:26,533 INFO [train.py:763] (2/8) Epoch 29, batch 3550, loss[loss=0.1558, simple_loss=0.25, pruned_loss=0.03083, over 7162.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2609, pruned_loss=0.03209, over 1423013.43 frames.], batch size: 18, lr: 2.58e-04
+2022-04-30 09:36:32,236 INFO [train.py:763] (2/8) Epoch 29, batch 3600, loss[loss=0.1454, simple_loss=0.243, pruned_loss=0.02391, over 7246.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2612, pruned_loss=0.03211, over 1427501.04 frames.], batch size: 19, lr: 2.58e-04
+2022-04-30 09:37:46,876 INFO [train.py:763] (2/8) Epoch 29, batch 3650, loss[loss=0.1712, simple_loss=0.2816, pruned_loss=0.03038, over 6836.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2625, pruned_loss=0.03211, over 1429251.47 frames.], batch size: 31, lr: 2.58e-04
+2022-04-30 09:38:52,210 INFO [train.py:763] (2/8) Epoch 29, batch 3700, loss[loss=0.1422, simple_loss=0.238, pruned_loss=0.02324, over 7274.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2618, pruned_loss=0.03164, over 1429397.55 frames.], batch size: 17, lr: 2.58e-04
+2022-04-30 09:39:59,118 INFO [train.py:763] (2/8) Epoch 29, batch 3750, loss[loss=0.1767, simple_loss=0.2904, pruned_loss=0.03156, over 7005.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2623, pruned_loss=0.03153, over 1432097.38 frames.], batch size: 28, lr: 2.58e-04
+2022-04-30 09:41:05,831 INFO [train.py:763] (2/8) Epoch 29, batch 3800, loss[loss=0.1667, simple_loss=0.2702, pruned_loss=0.03161, over 7225.00 frames.], tot_loss[loss=0.163, simple_loss=0.263, pruned_loss=0.0315, over 1424237.99 frames.], batch size: 22, lr: 2.58e-04
+2022-04-30 09:42:11,176 INFO [train.py:763] (2/8) Epoch 29, batch 3850, loss[loss=0.1478, simple_loss=0.238, pruned_loss=0.02879, over 6761.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2625, pruned_loss=0.03114, over 1424713.71 frames.], batch size: 15, lr: 2.58e-04
+2022-04-30 09:43:16,812 INFO [train.py:763] (2/8) Epoch 29, batch 3900, loss[loss=0.1359, simple_loss=0.2288, pruned_loss=0.02148, over 7139.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2626, pruned_loss=0.03131, over 1425010.04 frames.], batch size: 17, lr: 2.58e-04
+2022-04-30 09:44:22,546 INFO [train.py:763] (2/8) Epoch 29, batch 3950, loss[loss=0.1878, simple_loss=0.2786, pruned_loss=0.04848, over 7383.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2636, pruned_loss=0.03164, over 1419351.82 frames.], batch size: 23, lr: 2.58e-04
+2022-04-30 09:45:27,971 INFO [train.py:763] (2/8) Epoch 29, batch 4000, loss[loss=0.1627, simple_loss=0.265, pruned_loss=0.03018, over 7274.00 frames.], tot_loss[loss=0.1649, simple_loss=0.265, pruned_loss=0.03238, over 1417488.82 frames.], batch size: 25, lr: 2.58e-04
+2022-04-30 09:46:33,247 INFO [train.py:763] (2/8) Epoch 29, batch 4050, loss[loss=0.1905, simple_loss=0.2799, pruned_loss=0.05052, over 7077.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2643, pruned_loss=0.03228, over 1417873.80 frames.], batch size: 28, lr: 2.58e-04
+2022-04-30 09:47:39,262 INFO [train.py:763] (2/8) Epoch 29, batch 4100, loss[loss=0.188, simple_loss=0.2973, pruned_loss=0.03932, over 7328.00 frames.], tot_loss[loss=0.1641, simple_loss=0.264, pruned_loss=0.03212, over 1420565.46 frames.], batch size: 21, lr: 2.58e-04
+2022-04-30 09:48:45,604 INFO [train.py:763] (2/8) Epoch 29, batch 4150, loss[loss=0.1506, simple_loss=0.2543, pruned_loss=0.02348, over 7211.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2629, pruned_loss=0.03177, over 1421972.31 frames.], batch size: 21, lr: 2.58e-04
+2022-04-30 09:50:00,120 INFO [train.py:763] (2/8) Epoch 29, batch 4200, loss[loss=0.1659, simple_loss=0.264, pruned_loss=0.03386, over 7432.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2632, pruned_loss=0.03178, over 1422709.46 frames.], batch size: 20, lr: 2.58e-04
+2022-04-30 09:51:13,962 INFO [train.py:763] (2/8) Epoch 29, batch 4250, loss[loss=0.1672, simple_loss=0.2729, pruned_loss=0.03078, over 7368.00 frames.], tot_loss[loss=0.1641, simple_loss=0.264, pruned_loss=0.03207, over 1417988.96 frames.], batch size: 23, lr: 2.58e-04
+2022-04-30 09:52:28,881 INFO [train.py:763] (2/8) Epoch 29, batch 4300, loss[loss=0.1321, simple_loss=0.2229, pruned_loss=0.02068, over 7281.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2626, pruned_loss=0.0316, over 1421621.92 frames.], batch size: 17, lr: 2.58e-04
+2022-04-30 09:53:43,986 INFO [train.py:763] (2/8) Epoch 29, batch 4350, loss[loss=0.1633, simple_loss=0.2656, pruned_loss=0.03048, over 7233.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2621, pruned_loss=0.0315, over 1423659.51 frames.], batch size: 20, lr: 2.58e-04
+2022-04-30 09:54:58,495 INFO [train.py:763] (2/8) Epoch 29, batch 4400, loss[loss=0.1385, simple_loss=0.2442, pruned_loss=0.01635, over 7223.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.03117, over 1419432.78 frames.], batch size: 20, lr: 2.57e-04
+2022-04-30 09:56:12,784 INFO [train.py:763] (2/8) Epoch 29, batch 4450, loss[loss=0.1688, simple_loss=0.2688, pruned_loss=0.0344, over 6503.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.03111, over 1414624.78 frames.], batch size: 38, lr: 2.57e-04
+2022-04-30 09:57:17,980 INFO [train.py:763] (2/8) Epoch 29, batch 4500, loss[loss=0.2158, simple_loss=0.3045, pruned_loss=0.06353, over 5036.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.03193, over 1400027.53 frames.], batch size: 53, lr: 2.57e-04
+2022-04-30 09:58:32,302 INFO [train.py:763] (2/8) Epoch 29, batch 4550, loss[loss=0.1643, simple_loss=0.2622, pruned_loss=0.0332, over 5029.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2659, pruned_loss=0.03299, over 1359254.35 frames.], batch size: 52, lr: 2.57e-04
+2022-04-30 10:00:01,317 INFO [train.py:763] (2/8) Epoch 30, batch 0, loss[loss=0.1444, simple_loss=0.2496, pruned_loss=0.01961, over 7319.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2496, pruned_loss=0.01961, over 7319.00 frames.], batch size: 20, lr: 2.53e-04
+2022-04-30 10:01:06,991 INFO [train.py:763] (2/8) Epoch 30, batch 50, loss[loss=0.1573, simple_loss=0.2595, pruned_loss=0.0276, over 7265.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2598, pruned_loss=0.03058, over 316765.69 frames.], batch size: 19, lr: 2.53e-04
+2022-04-30 10:02:12,182 INFO [train.py:763] (2/8) Epoch 30, batch 100, loss[loss=0.1774, simple_loss=0.2803, pruned_loss=0.03723, over 7390.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2626, pruned_loss=0.03147, over 561456.41 frames.], batch size: 23, lr: 2.53e-04
+2022-04-30 10:03:17,803 INFO [train.py:763] (2/8) Epoch 30, batch 150, loss[loss=0.1714, simple_loss=0.2695, pruned_loss=0.03663, over 7201.00 frames.], tot_loss[loss=0.1608, simple_loss=0.26, pruned_loss=0.03084, over 756472.64 frames.], batch size: 22, lr: 2.53e-04
+2022-04-30 10:04:23,869 INFO [train.py:763] (2/8) Epoch 30, batch 200, loss[loss=0.1658, simple_loss=0.2672, pruned_loss=0.03222, over 4773.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2586, pruned_loss=0.03039, over 900851.27 frames.], batch size: 52, lr: 2.53e-04
+2022-04-30 10:05:29,993 INFO [train.py:763] (2/8) Epoch 30, batch 250, loss[loss=0.1792, simple_loss=0.2853, pruned_loss=0.03656, over 7292.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2621, pruned_loss=0.03115, over 1015024.73 frames.], batch size: 25, lr: 2.53e-04
+2022-04-30 10:06:35,953 INFO [train.py:763] (2/8) Epoch 30, batch 300, loss[loss=0.1459, simple_loss=0.2536, pruned_loss=0.01913, over 7314.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2626, pruned_loss=0.03134, over 1106300.91 frames.], batch size: 21, lr: 2.53e-04
+2022-04-30 10:07:41,449 INFO [train.py:763] (2/8) Epoch 30, batch 350, loss[loss=0.1604, simple_loss=0.2552, pruned_loss=0.03279, over 7170.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2628, pruned_loss=0.03116, over 1173217.35 frames.], batch size: 18, lr: 2.53e-04
+2022-04-30 10:08:46,853 INFO [train.py:763] (2/8) Epoch 30, batch 400, loss[loss=0.1746, simple_loss=0.2748, pruned_loss=0.03719, over 7218.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2627, pruned_loss=0.03171, over 1224329.17 frames.], batch size: 21, lr: 2.53e-04
+2022-04-30 10:09:52,318 INFO [train.py:763] (2/8) Epoch 30, batch 450, loss[loss=0.199, simple_loss=0.3015, pruned_loss=0.04821, over 7180.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2633, pruned_loss=0.03182, over 1265431.73 frames.], batch size: 26, lr: 2.53e-04
+2022-04-30 10:10:57,855 INFO [train.py:763] (2/8) Epoch 30, batch 500, loss[loss=0.1412, simple_loss=0.2314, pruned_loss=0.0255, over 7282.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2626, pruned_loss=0.03157, over 1300270.14 frames.], batch size: 17, lr: 2.53e-04
+2022-04-30 10:12:03,589 INFO [train.py:763] (2/8) Epoch 30, batch 550, loss[loss=0.1605, simple_loss=0.2663, pruned_loss=0.02734, over 7423.00 frames.], tot_loss[loss=0.163, simple_loss=0.2628, pruned_loss=0.03161, over 1327672.16 frames.], batch size: 21, lr: 2.53e-04
+2022-04-30 10:13:09,438 INFO [train.py:763] (2/8) Epoch 30, batch 600, loss[loss=0.1372, simple_loss=0.2311, pruned_loss=0.02164, over 7062.00 frames.], tot_loss[loss=0.164, simple_loss=0.264, pruned_loss=0.03204, over 1346904.16 frames.], batch size: 18, lr: 2.53e-04
+2022-04-30 10:14:15,860 INFO [train.py:763] (2/8) Epoch 30, batch 650, loss[loss=0.1695, simple_loss=0.2715, pruned_loss=0.03377, over 7140.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.03189, over 1368187.88 frames.], batch size: 20, lr: 2.53e-04
+2022-04-30 10:15:21,892 INFO [train.py:763] (2/8) Epoch 30, batch 700, loss[loss=0.162, simple_loss=0.2535, pruned_loss=0.03524, over 7219.00 frames.], tot_loss[loss=0.1633, simple_loss=0.263, pruned_loss=0.03181, over 1378440.26 frames.], batch size: 16, lr: 2.52e-04
+2022-04-30 10:16:28,668 INFO [train.py:763] (2/8) Epoch 30, batch 750, loss[loss=0.1543, simple_loss=0.2556, pruned_loss=0.02649, over 7240.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2629, pruned_loss=0.03191, over 1386342.53 frames.], batch size: 20, lr: 2.52e-04
+2022-04-30 10:17:34,224 INFO [train.py:763] (2/8) Epoch 30, batch 800, loss[loss=0.1619, simple_loss=0.2587, pruned_loss=0.03252, over 7326.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2623, pruned_loss=0.03167, over 1394437.38 frames.], batch size: 20, lr: 2.52e-04
+2022-04-30 10:18:39,957 INFO [train.py:763] (2/8) Epoch 30, batch 850, loss[loss=0.1774, simple_loss=0.2755, pruned_loss=0.0397, over 7426.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2614, pruned_loss=0.03147, over 1398615.20 frames.], batch size: 20, lr: 2.52e-04
+2022-04-30 10:19:45,737 INFO [train.py:763] (2/8) Epoch 30, batch 900, loss[loss=0.1515, simple_loss=0.2402, pruned_loss=0.03143, over 7215.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2613, pruned_loss=0.03109, over 1403967.02 frames.], batch size: 16, lr: 2.52e-04
+2022-04-30 10:20:52,494 INFO [train.py:763] (2/8) Epoch 30, batch 950, loss[loss=0.1683, simple_loss=0.2767, pruned_loss=0.03, over 7107.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2613, pruned_loss=0.03107, over 1405285.96 frames.], batch size: 28, lr: 2.52e-04
+2022-04-30 10:21:58,498 INFO [train.py:763] (2/8) Epoch 30, batch 1000, loss[loss=0.1527, simple_loss=0.2594, pruned_loss=0.02293, over 7336.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2609, pruned_loss=0.03087, over 1408546.86 frames.], batch size: 22, lr: 2.52e-04
+2022-04-30 10:23:03,970 INFO [train.py:763] (2/8) Epoch 30, batch 1050, loss[loss=0.1751, simple_loss=0.2744, pruned_loss=0.03787, over 7029.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2617, pruned_loss=0.03123, over 1410492.41 frames.], batch size: 28, lr: 2.52e-04
+2022-04-30 10:24:09,735 INFO [train.py:763] (2/8) Epoch 30, batch 1100, loss[loss=0.1634, simple_loss=0.2718, pruned_loss=0.02752, over 7062.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.03116, over 1414969.68 frames.], batch size: 18, lr: 2.52e-04
+2022-04-30 10:25:15,757 INFO [train.py:763] (2/8) Epoch 30, batch 1150, loss[loss=0.1607, simple_loss=0.2472, pruned_loss=0.03713, over 7062.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2615, pruned_loss=0.03154, over 1416700.89 frames.], batch size: 18, lr: 2.52e-04
+2022-04-30 10:26:21,661 INFO [train.py:763] (2/8) Epoch 30, batch 1200, loss[loss=0.2041, simple_loss=0.3005, pruned_loss=0.05385, over 7193.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2616, pruned_loss=0.03152, over 1418303.88 frames.], batch size: 22, lr: 2.52e-04
+2022-04-30 10:27:27,463 INFO [train.py:763] (2/8) Epoch 30, batch 1250, loss[loss=0.1615, simple_loss=0.2497, pruned_loss=0.03662, over 7413.00 frames.], tot_loss[loss=0.1626, simple_loss=0.262, pruned_loss=0.03159, over 1417266.09 frames.], batch size: 18, lr: 2.52e-04
+2022-04-30 10:28:33,934 INFO [train.py:763] (2/8) Epoch 30, batch 1300, loss[loss=0.1772, simple_loss=0.273, pruned_loss=0.04072, over 7121.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2621, pruned_loss=0.03177, over 1417305.31 frames.], batch size: 26, lr: 2.52e-04
+2022-04-30 10:29:40,213 INFO [train.py:763] (2/8) Epoch 30, batch 1350, loss[loss=0.1678, simple_loss=0.2497, pruned_loss=0.04299, over 7138.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2631, pruned_loss=0.03174, over 1414700.41 frames.], batch size: 17, lr: 2.52e-04
+2022-04-30 10:30:45,700 INFO [train.py:763] (2/8) Epoch 30, batch 1400, loss[loss=0.1866, simple_loss=0.2888, pruned_loss=0.04221, over 7327.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2631, pruned_loss=0.03176, over 1419319.33 frames.], batch size: 22, lr: 2.52e-04
+2022-04-30 10:31:51,066 INFO [train.py:763] (2/8) Epoch 30, batch 1450, loss[loss=0.1524, simple_loss=0.26, pruned_loss=0.02245, over 7144.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2628, pruned_loss=0.03151, over 1419465.10 frames.], batch size: 20, lr: 2.52e-04
+2022-04-30 10:32:56,514 INFO [train.py:763] (2/8) Epoch 30, batch 1500, loss[loss=0.1765, simple_loss=0.2866, pruned_loss=0.03315, over 7305.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2636, pruned_loss=0.03146, over 1425525.75 frames.], batch size: 25, lr: 2.52e-04
+2022-04-30 10:34:02,178 INFO [train.py:763] (2/8) Epoch 30, batch 1550, loss[loss=0.162, simple_loss=0.2683, pruned_loss=0.02784, over 7304.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2624, pruned_loss=0.03121, over 1426495.45 frames.], batch size: 25, lr: 2.52e-04
+2022-04-30 10:35:07,677 INFO [train.py:763] (2/8) Epoch 30, batch 1600, loss[loss=0.1587, simple_loss=0.2567, pruned_loss=0.03033, over 7256.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2613, pruned_loss=0.03097, over 1427468.88 frames.], batch size: 19, lr: 2.52e-04
+2022-04-30 10:36:13,948 INFO [train.py:763] (2/8) Epoch 30, batch 1650, loss[loss=0.1451, simple_loss=0.2522, pruned_loss=0.01905, over 7123.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2612, pruned_loss=0.03088, over 1427769.29 frames.], batch size: 21, lr: 2.52e-04
+2022-04-30 10:37:20,413 INFO [train.py:763] (2/8) Epoch 30, batch 1700, loss[loss=0.1714, simple_loss=0.272, pruned_loss=0.03539, over 7301.00 frames.], tot_loss[loss=0.1606, simple_loss=0.26, pruned_loss=0.03056, over 1424835.51 frames.], batch size: 24, lr: 2.52e-04
+2022-04-30 10:38:27,154 INFO [train.py:763] (2/8) Epoch 30, batch 1750, loss[loss=0.1791, simple_loss=0.2857, pruned_loss=0.03629, over 7379.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2613, pruned_loss=0.03084, over 1427433.53 frames.], batch size: 23, lr: 2.52e-04
+2022-04-30 10:39:33,029 INFO [train.py:763] (2/8) Epoch 30, batch 1800, loss[loss=0.1517, simple_loss=0.2541, pruned_loss=0.02462, over 7448.00 frames.], tot_loss[loss=0.1616, simple_loss=0.261, pruned_loss=0.03109, over 1422668.46 frames.], batch size: 20, lr: 2.51e-04
+2022-04-30 10:40:38,991 INFO [train.py:763] (2/8) Epoch 30, batch 1850, loss[loss=0.1747, simple_loss=0.2631, pruned_loss=0.04317, over 7152.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2607, pruned_loss=0.03093, over 1421495.40 frames.], batch size: 17, lr: 2.51e-04
+2022-04-30 10:41:45,825 INFO [train.py:763] (2/8) Epoch 30, batch 1900, loss[loss=0.1574, simple_loss=0.2635, pruned_loss=0.02564, over 7321.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2606, pruned_loss=0.0309, over 1425558.80 frames.], batch size: 20, lr: 2.51e-04
+2022-04-30 10:42:51,808 INFO [train.py:763] (2/8) Epoch 30, batch 1950, loss[loss=0.1703, simple_loss=0.2673, pruned_loss=0.0366, over 7401.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2607, pruned_loss=0.03061, over 1425523.13 frames.], batch size: 23, lr: 2.51e-04
+2022-04-30 10:43:59,473 INFO [train.py:763] (2/8) Epoch 30, batch 2000, loss[loss=0.1621, simple_loss=0.269, pruned_loss=0.02764, over 7165.00 frames.], tot_loss[loss=0.16, simple_loss=0.2593, pruned_loss=0.03036, over 1427170.05 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:45:05,769 INFO [train.py:763] (2/8) Epoch 30, batch 2050, loss[loss=0.2036, simple_loss=0.2996, pruned_loss=0.0538, over 7220.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2592, pruned_loss=0.03056, over 1424757.01 frames.], batch size: 22, lr: 2.51e-04
+2022-04-30 10:46:11,290 INFO [train.py:763] (2/8) Epoch 30, batch 2100, loss[loss=0.1546, simple_loss=0.2562, pruned_loss=0.02653, over 7162.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2595, pruned_loss=0.03059, over 1423311.59 frames.], batch size: 19, lr: 2.51e-04
+2022-04-30 10:47:17,300 INFO [train.py:763] (2/8) Epoch 30, batch 2150, loss[loss=0.155, simple_loss=0.246, pruned_loss=0.03204, over 7152.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2592, pruned_loss=0.03033, over 1426828.08 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:48:22,845 INFO [train.py:763] (2/8) Epoch 30, batch 2200, loss[loss=0.1456, simple_loss=0.2437, pruned_loss=0.02379, over 7055.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2604, pruned_loss=0.03073, over 1428626.69 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:49:28,453 INFO [train.py:763] (2/8) Epoch 30, batch 2250, loss[loss=0.1676, simple_loss=0.2755, pruned_loss=0.02988, over 7209.00 frames.], tot_loss[loss=0.1615, simple_loss=0.261, pruned_loss=0.03106, over 1427707.16 frames.], batch size: 23, lr: 2.51e-04
+2022-04-30 10:50:34,513 INFO [train.py:763] (2/8) Epoch 30, batch 2300, loss[loss=0.1428, simple_loss=0.2395, pruned_loss=0.02306, over 7255.00 frames.], tot_loss[loss=0.162, simple_loss=0.2614, pruned_loss=0.03127, over 1429548.64 frames.], batch size: 19, lr: 2.51e-04
+2022-04-30 10:51:40,501 INFO [train.py:763] (2/8) Epoch 30, batch 2350, loss[loss=0.1329, simple_loss=0.226, pruned_loss=0.01989, over 7446.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2614, pruned_loss=0.03138, over 1429800.32 frames.], batch size: 19, lr: 2.51e-04
+2022-04-30 10:52:46,202 INFO [train.py:763] (2/8) Epoch 30, batch 2400, loss[loss=0.1577, simple_loss=0.2569, pruned_loss=0.02927, over 7217.00 frames.], tot_loss[loss=0.1626, simple_loss=0.262, pruned_loss=0.03157, over 1428036.50 frames.], batch size: 21, lr: 2.51e-04
+2022-04-30 10:53:51,751 INFO [train.py:763] (2/8) Epoch 30, batch 2450, loss[loss=0.1526, simple_loss=0.2572, pruned_loss=0.024, over 7228.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2627, pruned_loss=0.03182, over 1424280.55 frames.], batch size: 21, lr: 2.51e-04
+2022-04-30 10:54:57,031 INFO [train.py:763] (2/8) Epoch 30, batch 2500, loss[loss=0.1475, simple_loss=0.2532, pruned_loss=0.02091, over 7333.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2618, pruned_loss=0.03147, over 1427150.84 frames.], batch size: 22, lr: 2.51e-04
+2022-04-30 10:56:03,556 INFO [train.py:763] (2/8) Epoch 30, batch 2550, loss[loss=0.1491, simple_loss=0.2477, pruned_loss=0.02519, over 7206.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2612, pruned_loss=0.03132, over 1428750.34 frames.], batch size: 23, lr: 2.51e-04
+2022-04-30 10:57:09,405 INFO [train.py:763] (2/8) Epoch 30, batch 2600, loss[loss=0.1421, simple_loss=0.2462, pruned_loss=0.01899, over 7418.00 frames.], tot_loss[loss=0.1626, simple_loss=0.262, pruned_loss=0.03166, over 1427847.28 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:58:15,102 INFO [train.py:763] (2/8) Epoch 30, batch 2650, loss[loss=0.1701, simple_loss=0.2814, pruned_loss=0.02942, over 7416.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2618, pruned_loss=0.03139, over 1424166.83 frames.], batch size: 21, lr: 2.51e-04
+2022-04-30 10:59:20,428 INFO [train.py:763] (2/8) Epoch 30, batch 2700, loss[loss=0.1737, simple_loss=0.2785, pruned_loss=0.03448, over 7282.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2619, pruned_loss=0.03138, over 1417736.28 frames.], batch size: 25, lr: 2.51e-04
+2022-04-30 11:00:26,174 INFO [train.py:763] (2/8) Epoch 30, batch 2750, loss[loss=0.1549, simple_loss=0.265, pruned_loss=0.02242, over 7146.00 frames.], tot_loss[loss=0.162, simple_loss=0.2614, pruned_loss=0.03129, over 1418847.21 frames.], batch size: 20, lr: 2.51e-04
+2022-04-30 11:01:31,733 INFO [train.py:763] (2/8) Epoch 30, batch 2800, loss[loss=0.1761, simple_loss=0.2698, pruned_loss=0.04122, over 7173.00 frames.], tot_loss[loss=0.162, simple_loss=0.2615, pruned_loss=0.03119, over 1421556.17 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 11:02:36,835 INFO [train.py:763] (2/8) Epoch 30, batch 2850, loss[loss=0.1699, simple_loss=0.2753, pruned_loss=0.03228, over 7201.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2621, pruned_loss=0.03118, over 1420360.39 frames.], batch size: 22, lr: 2.51e-04
+2022-04-30 11:03:42,110 INFO [train.py:763] (2/8) Epoch 30, batch 2900, loss[loss=0.1571, simple_loss=0.2596, pruned_loss=0.02726, over 7112.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2625, pruned_loss=0.03144, over 1424223.92 frames.], batch size: 21, lr: 2.51e-04
+2022-04-30 11:04:47,457 INFO [train.py:763] (2/8) Epoch 30, batch 2950, loss[loss=0.1483, simple_loss=0.2451, pruned_loss=0.0258, over 7268.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2614, pruned_loss=0.03101, over 1423389.14 frames.], batch size: 19, lr: 2.50e-04
+2022-04-30 11:05:53,064 INFO [train.py:763] (2/8) Epoch 30, batch 3000, loss[loss=0.1864, simple_loss=0.2696, pruned_loss=0.05157, over 7329.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2608, pruned_loss=0.03094, over 1423142.24 frames.], batch size: 20, lr: 2.50e-04
+2022-04-30 11:05:53,065 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 11:06:08,153 INFO [train.py:792] (2/8) Epoch 30, validation: loss=0.1701, simple_loss=0.2661, pruned_loss=0.03704, over 698248.00 frames.
+2022-04-30 11:07:13,671 INFO [train.py:763] (2/8) Epoch 30, batch 3050, loss[loss=0.1564, simple_loss=0.2553, pruned_loss=0.02873, over 7009.00 frames.], tot_loss[loss=0.162, simple_loss=0.2616, pruned_loss=0.03119, over 1422579.77 frames.], batch size: 16, lr: 2.50e-04
+2022-04-30 11:08:19,230 INFO [train.py:763] (2/8) Epoch 30, batch 3100, loss[loss=0.173, simple_loss=0.2777, pruned_loss=0.03414, over 7290.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.03073, over 1426013.98 frames.], batch size: 25, lr: 2.50e-04
+2022-04-30 11:09:24,924 INFO [train.py:763] (2/8) Epoch 30, batch 3150, loss[loss=0.1256, simple_loss=0.2138, pruned_loss=0.01869, over 6999.00 frames.], tot_loss[loss=0.1615, simple_loss=0.261, pruned_loss=0.03097, over 1424307.45 frames.], batch size: 16, lr: 2.50e-04
+2022-04-30 11:10:31,192 INFO [train.py:763] (2/8) Epoch 30, batch 3200, loss[loss=0.1733, simple_loss=0.2689, pruned_loss=0.03889, over 7208.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2603, pruned_loss=0.03063, over 1416643.84 frames.], batch size: 23, lr: 2.50e-04
+2022-04-30 11:11:37,934 INFO [train.py:763] (2/8) Epoch 30, batch 3250, loss[loss=0.1675, simple_loss=0.2734, pruned_loss=0.03079, over 7145.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2614, pruned_loss=0.03043, over 1415698.17 frames.], batch size: 20, lr: 2.50e-04
+2022-04-30 11:12:45,385 INFO [train.py:763] (2/8) Epoch 30, batch 3300, loss[loss=0.1392, simple_loss=0.2319, pruned_loss=0.02322, over 7286.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2611, pruned_loss=0.03076, over 1422076.38 frames.], batch size: 17, lr: 2.50e-04
+2022-04-30 11:13:51,983 INFO [train.py:763] (2/8) Epoch 30, batch 3350, loss[loss=0.1568, simple_loss=0.2586, pruned_loss=0.02753, over 7223.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2606, pruned_loss=0.03052, over 1421631.52 frames.], batch size: 21, lr: 2.50e-04
+2022-04-30 11:14:57,139 INFO [train.py:763] (2/8) Epoch 30, batch 3400, loss[loss=0.1845, simple_loss=0.2845, pruned_loss=0.04224, over 7292.00 frames.], tot_loss[loss=0.161, simple_loss=0.2609, pruned_loss=0.03052, over 1421280.73 frames.], batch size: 25, lr: 2.50e-04
+2022-04-30 11:16:02,378 INFO [train.py:763] (2/8) Epoch 30, batch 3450, loss[loss=0.146, simple_loss=0.2569, pruned_loss=0.01753, over 6628.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2608, pruned_loss=0.03034, over 1425751.92 frames.], batch size: 38, lr: 2.50e-04
+2022-04-30 11:17:08,604 INFO [train.py:763] (2/8) Epoch 30, batch 3500, loss[loss=0.1815, simple_loss=0.2852, pruned_loss=0.03888, over 7375.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2609, pruned_loss=0.03037, over 1426728.84 frames.], batch size: 23, lr: 2.50e-04
+2022-04-30 11:18:14,697 INFO [train.py:763] (2/8) Epoch 30, batch 3550, loss[loss=0.1516, simple_loss=0.2481, pruned_loss=0.0276, over 7428.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03081, over 1428312.90 frames.], batch size: 20, lr: 2.50e-04
+2022-04-30 11:19:20,434 INFO [train.py:763] (2/8) Epoch 30, batch 3600, loss[loss=0.1754, simple_loss=0.2736, pruned_loss=0.03861, over 7296.00 frames.], tot_loss[loss=0.1629, simple_loss=0.263, pruned_loss=0.03138, over 1422966.50 frames.], batch size: 24, lr: 2.50e-04
+2022-04-30 11:20:25,885 INFO [train.py:763] (2/8) Epoch 30, batch 3650, loss[loss=0.1373, simple_loss=0.227, pruned_loss=0.02385, over 7153.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2623, pruned_loss=0.03108, over 1421831.83 frames.], batch size: 17, lr: 2.50e-04
+2022-04-30 11:21:32,102 INFO [train.py:763] (2/8) Epoch 30, batch 3700, loss[loss=0.1302, simple_loss=0.2179, pruned_loss=0.02128, over 7283.00 frames.], tot_loss[loss=0.1613, simple_loss=0.261, pruned_loss=0.03075, over 1424096.65 frames.], batch size: 17, lr: 2.50e-04
+2022-04-30 11:22:38,024 INFO [train.py:763] (2/8) Epoch 30, batch 3750, loss[loss=0.147, simple_loss=0.251, pruned_loss=0.02147, over 7253.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2613, pruned_loss=0.03112, over 1422162.14 frames.], batch size: 19, lr: 2.50e-04
+2022-04-30 11:23:45,243 INFO [train.py:763] (2/8) Epoch 30, batch 3800, loss[loss=0.144, simple_loss=0.2485, pruned_loss=0.01977, over 7268.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2614, pruned_loss=0.03094, over 1425033.17 frames.], batch size: 18, lr: 2.50e-04
+2022-04-30 11:24:50,557 INFO [train.py:763] (2/8) Epoch 30, batch 3850, loss[loss=0.1522, simple_loss=0.2517, pruned_loss=0.0263, over 7067.00 frames.], tot_loss[loss=0.162, simple_loss=0.262, pruned_loss=0.03098, over 1424057.21 frames.], batch size: 18, lr: 2.50e-04
+2022-04-30 11:25:56,094 INFO [train.py:763] (2/8) Epoch 30, batch 3900, loss[loss=0.1864, simple_loss=0.2784, pruned_loss=0.04724, over 7295.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03062, over 1428210.26 frames.], batch size: 24, lr: 2.50e-04
+2022-04-30 11:27:01,583 INFO [train.py:763] (2/8) Epoch 30, batch 3950, loss[loss=0.1668, simple_loss=0.2678, pruned_loss=0.03292, over 7360.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.03057, over 1428443.50 frames.], batch size: 19, lr: 2.50e-04
+2022-04-30 11:28:06,969 INFO [train.py:763] (2/8) Epoch 30, batch 4000, loss[loss=0.1345, simple_loss=0.2327, pruned_loss=0.01816, over 7155.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2617, pruned_loss=0.03104, over 1426098.81 frames.], batch size: 18, lr: 2.50e-04
+2022-04-30 11:29:11,955 INFO [train.py:763] (2/8) Epoch 30, batch 4050, loss[loss=0.1907, simple_loss=0.2848, pruned_loss=0.04827, over 7287.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2618, pruned_loss=0.031, over 1425108.12 frames.], batch size: 24, lr: 2.49e-04
+2022-04-30 11:30:18,166 INFO [train.py:763] (2/8) Epoch 30, batch 4100, loss[loss=0.1745, simple_loss=0.2768, pruned_loss=0.03613, over 7164.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2623, pruned_loss=0.0313, over 1426712.97 frames.], batch size: 19, lr: 2.49e-04
+2022-04-30 11:31:24,157 INFO [train.py:763] (2/8) Epoch 30, batch 4150, loss[loss=0.1555, simple_loss=0.2643, pruned_loss=0.0234, over 7432.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2618, pruned_loss=0.03061, over 1428462.69 frames.], batch size: 22, lr: 2.49e-04
+2022-04-30 11:32:29,728 INFO [train.py:763] (2/8) Epoch 30, batch 4200, loss[loss=0.1541, simple_loss=0.2415, pruned_loss=0.03331, over 6766.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2611, pruned_loss=0.03038, over 1430789.93 frames.], batch size: 15, lr: 2.49e-04
+2022-04-30 11:33:35,005 INFO [train.py:763] (2/8) Epoch 30, batch 4250, loss[loss=0.1777, simple_loss=0.2714, pruned_loss=0.04202, over 7162.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2619, pruned_loss=0.03057, over 1426996.69 frames.], batch size: 26, lr: 2.49e-04
+2022-04-30 11:34:41,232 INFO [train.py:763] (2/8) Epoch 30, batch 4300, loss[loss=0.1646, simple_loss=0.2584, pruned_loss=0.0354, over 7286.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2617, pruned_loss=0.03037, over 1429788.16 frames.], batch size: 24, lr: 2.49e-04
+2022-04-30 11:35:46,139 INFO [train.py:763] (2/8) Epoch 30, batch 4350, loss[loss=0.1777, simple_loss=0.2775, pruned_loss=0.03896, over 7129.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2616, pruned_loss=0.03039, over 1421267.91 frames.], batch size: 21, lr: 2.49e-04
+2022-04-30 11:36:51,028 INFO [train.py:763] (2/8) Epoch 30, batch 4400, loss[loss=0.1958, simple_loss=0.2995, pruned_loss=0.04603, over 7108.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2615, pruned_loss=0.0305, over 1410452.45 frames.], batch size: 21, lr: 2.49e-04
+2022-04-30 11:37:56,305 INFO [train.py:763] (2/8) Epoch 30, batch 4450, loss[loss=0.1848, simple_loss=0.2789, pruned_loss=0.04537, over 6416.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2614, pruned_loss=0.03053, over 1409235.17 frames.], batch size: 37, lr: 2.49e-04
+2022-04-30 11:39:02,206 INFO [train.py:763] (2/8) Epoch 30, batch 4500, loss[loss=0.1586, simple_loss=0.2652, pruned_loss=0.02603, over 6261.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2628, pruned_loss=0.03117, over 1385373.77 frames.], batch size: 37, lr: 2.49e-04
+2022-04-30 11:40:07,225 INFO [train.py:763] (2/8) Epoch 30, batch 4550, loss[loss=0.1739, simple_loss=0.2786, pruned_loss=0.03463, over 5254.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2642, pruned_loss=0.03216, over 1356619.58 frames.], batch size: 52, lr: 2.49e-04
+2022-04-30 11:41:35,690 INFO [train.py:763] (2/8) Epoch 31, batch 0, loss[loss=0.1811, simple_loss=0.2771, pruned_loss=0.04255, over 4774.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2771, pruned_loss=0.04255, over 4774.00 frames.], batch size: 52, lr: 2.45e-04
+2022-04-30 11:42:41,155 INFO [train.py:763] (2/8) Epoch 31, batch 50, loss[loss=0.1819, simple_loss=0.2876, pruned_loss=0.03807, over 6432.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2686, pruned_loss=0.03243, over 319624.26 frames.], batch size: 38, lr: 2.45e-04
+2022-04-30 11:43:46,468 INFO [train.py:763] (2/8) Epoch 31, batch 100, loss[loss=0.158, simple_loss=0.2686, pruned_loss=0.02367, over 7272.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2638, pruned_loss=0.03095, over 566236.45 frames.], batch size: 25, lr: 2.45e-04
+2022-04-30 11:44:52,568 INFO [train.py:763] (2/8) Epoch 31, batch 150, loss[loss=0.1734, simple_loss=0.2737, pruned_loss=0.03655, over 7166.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2621, pruned_loss=0.03047, over 757485.28 frames.], batch size: 26, lr: 2.45e-04
+2022-04-30 11:45:58,813 INFO [train.py:763] (2/8) Epoch 31, batch 200, loss[loss=0.1203, simple_loss=0.2101, pruned_loss=0.01529, over 7002.00 frames.], tot_loss[loss=0.1599, simple_loss=0.26, pruned_loss=0.02988, over 902586.94 frames.], batch size: 16, lr: 2.45e-04
+2022-04-30 11:47:04,080 INFO [train.py:763] (2/8) Epoch 31, batch 250, loss[loss=0.1673, simple_loss=0.2747, pruned_loss=0.02996, over 7296.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.03018, over 1022794.49 frames.], batch size: 24, lr: 2.45e-04
+2022-04-30 11:48:09,432 INFO [train.py:763] (2/8) Epoch 31, batch 300, loss[loss=0.1975, simple_loss=0.2994, pruned_loss=0.04779, over 7270.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2618, pruned_loss=0.03081, over 1113845.55 frames.], batch size: 24, lr: 2.45e-04
+2022-04-30 11:49:14,693 INFO [train.py:763] (2/8) Epoch 31, batch 350, loss[loss=0.155, simple_loss=0.2616, pruned_loss=0.02418, over 7110.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2616, pruned_loss=0.03076, over 1181933.72 frames.], batch size: 28, lr: 2.45e-04
+2022-04-30 11:50:20,233 INFO [train.py:763] (2/8) Epoch 31, batch 400, loss[loss=0.1687, simple_loss=0.2748, pruned_loss=0.03127, over 7147.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2619, pruned_loss=0.0307, over 1236961.12 frames.], batch size: 26, lr: 2.45e-04
+2022-04-30 11:51:25,625 INFO [train.py:763] (2/8) Epoch 31, batch 450, loss[loss=0.173, simple_loss=0.2783, pruned_loss=0.03382, over 7301.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2613, pruned_loss=0.03032, over 1277168.42 frames.], batch size: 21, lr: 2.45e-04
+2022-04-30 11:52:41,060 INFO [train.py:763] (2/8) Epoch 31, batch 500, loss[loss=0.1484, simple_loss=0.2543, pruned_loss=0.02122, over 7328.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2606, pruned_loss=0.02984, over 1312764.64 frames.], batch size: 22, lr: 2.45e-04
+2022-04-30 11:53:47,760 INFO [train.py:763] (2/8) Epoch 31, batch 550, loss[loss=0.1668, simple_loss=0.2716, pruned_loss=0.031, over 7346.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2607, pruned_loss=0.02993, over 1340618.02 frames.], batch size: 22, lr: 2.45e-04
+2022-04-30 11:54:53,974 INFO [train.py:763] (2/8) Epoch 31, batch 600, loss[loss=0.138, simple_loss=0.2336, pruned_loss=0.02121, over 7131.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2607, pruned_loss=0.03023, over 1363145.78 frames.], batch size: 17, lr: 2.45e-04
+2022-04-30 11:55:59,907 INFO [train.py:763] (2/8) Epoch 31, batch 650, loss[loss=0.168, simple_loss=0.2549, pruned_loss=0.04054, over 7004.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03024, over 1378669.05 frames.], batch size: 16, lr: 2.45e-04
+2022-04-30 11:57:06,460 INFO [train.py:763] (2/8) Epoch 31, batch 700, loss[loss=0.1983, simple_loss=0.2974, pruned_loss=0.0496, over 7206.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2617, pruned_loss=0.03074, over 1387745.50 frames.], batch size: 23, lr: 2.45e-04
+2022-04-30 11:58:13,267 INFO [train.py:763] (2/8) Epoch 31, batch 750, loss[loss=0.1605, simple_loss=0.2642, pruned_loss=0.0284, over 7122.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2615, pruned_loss=0.0303, over 1395754.60 frames.], batch size: 21, lr: 2.44e-04
+2022-04-30 11:59:18,734 INFO [train.py:763] (2/8) Epoch 31, batch 800, loss[loss=0.1424, simple_loss=0.2369, pruned_loss=0.02391, over 7272.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2609, pruned_loss=0.03027, over 1400948.58 frames.], batch size: 18, lr: 2.44e-04
+2022-04-30 12:00:24,034 INFO [train.py:763] (2/8) Epoch 31, batch 850, loss[loss=0.1745, simple_loss=0.2902, pruned_loss=0.02943, over 7271.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2615, pruned_loss=0.03047, over 1408621.29 frames.], batch size: 25, lr: 2.44e-04
+2022-04-30 12:01:28,728 INFO [train.py:763] (2/8) Epoch 31, batch 900, loss[loss=0.1696, simple_loss=0.277, pruned_loss=0.03113, over 7330.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2629, pruned_loss=0.03083, over 1411350.48 frames.], batch size: 22, lr: 2.44e-04
+2022-04-30 12:02:34,057 INFO [train.py:763] (2/8) Epoch 31, batch 950, loss[loss=0.1371, simple_loss=0.2346, pruned_loss=0.01975, over 6808.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2614, pruned_loss=0.03073, over 1412774.33 frames.], batch size: 15, lr: 2.44e-04
+2022-04-30 12:03:39,302 INFO [train.py:763] (2/8) Epoch 31, batch 1000, loss[loss=0.1453, simple_loss=0.2435, pruned_loss=0.0235, over 7430.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03026, over 1416180.90 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:04:53,737 INFO [train.py:763] (2/8) Epoch 31, batch 1050, loss[loss=0.1442, simple_loss=0.2431, pruned_loss=0.02265, over 7240.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2599, pruned_loss=0.02999, over 1420443.85 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:05:59,153 INFO [train.py:763] (2/8) Epoch 31, batch 1100, loss[loss=0.1765, simple_loss=0.2868, pruned_loss=0.03312, over 7194.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2601, pruned_loss=0.03029, over 1418882.15 frames.], batch size: 22, lr: 2.44e-04
+2022-04-30 12:07:23,560 INFO [train.py:763] (2/8) Epoch 31, batch 1150, loss[loss=0.1396, simple_loss=0.2346, pruned_loss=0.02231, over 7132.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2611, pruned_loss=0.03056, over 1422783.97 frames.], batch size: 17, lr: 2.44e-04
+2022-04-30 12:08:30,097 INFO [train.py:763] (2/8) Epoch 31, batch 1200, loss[loss=0.1612, simple_loss=0.27, pruned_loss=0.02621, over 7422.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2601, pruned_loss=0.0306, over 1424951.69 frames.], batch size: 21, lr: 2.44e-04
+2022-04-30 12:09:54,552 INFO [train.py:763] (2/8) Epoch 31, batch 1250, loss[loss=0.1616, simple_loss=0.2666, pruned_loss=0.02825, over 7205.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2604, pruned_loss=0.03097, over 1417590.01 frames.], batch size: 23, lr: 2.44e-04
+2022-04-30 12:11:00,224 INFO [train.py:763] (2/8) Epoch 31, batch 1300, loss[loss=0.1715, simple_loss=0.2813, pruned_loss=0.03089, over 7145.00 frames.], tot_loss[loss=0.1617, simple_loss=0.261, pruned_loss=0.03122, over 1423507.51 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:12:14,866 INFO [train.py:763] (2/8) Epoch 31, batch 1350, loss[loss=0.1651, simple_loss=0.269, pruned_loss=0.0306, over 7329.00 frames.], tot_loss[loss=0.161, simple_loss=0.2605, pruned_loss=0.03076, over 1422017.84 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:13:22,475 INFO [train.py:763] (2/8) Epoch 31, batch 1400, loss[loss=0.1619, simple_loss=0.2733, pruned_loss=0.02526, over 7238.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2594, pruned_loss=0.03012, over 1422519.14 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:14:38,779 INFO [train.py:763] (2/8) Epoch 31, batch 1450, loss[loss=0.1584, simple_loss=0.2603, pruned_loss=0.02823, over 7325.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2607, pruned_loss=0.03032, over 1424042.58 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:15:46,109 INFO [train.py:763] (2/8) Epoch 31, batch 1500, loss[loss=0.1832, simple_loss=0.2791, pruned_loss=0.04368, over 4722.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.0304, over 1422186.01 frames.], batch size: 53, lr: 2.44e-04
+2022-04-30 12:16:51,626 INFO [train.py:763] (2/8) Epoch 31, batch 1550, loss[loss=0.1359, simple_loss=0.2305, pruned_loss=0.02065, over 7409.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2607, pruned_loss=0.03036, over 1421476.03 frames.], batch size: 18, lr: 2.44e-04
+2022-04-30 12:17:56,937 INFO [train.py:763] (2/8) Epoch 31, batch 1600, loss[loss=0.1711, simple_loss=0.2695, pruned_loss=0.03638, over 7200.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2602, pruned_loss=0.03009, over 1417651.44 frames.], batch size: 23, lr: 2.44e-04
+2022-04-30 12:19:02,302 INFO [train.py:763] (2/8) Epoch 31, batch 1650, loss[loss=0.1682, simple_loss=0.2665, pruned_loss=0.03494, over 7421.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2616, pruned_loss=0.03049, over 1416786.07 frames.], batch size: 21, lr: 2.44e-04
+2022-04-30 12:20:07,948 INFO [train.py:763] (2/8) Epoch 31, batch 1700, loss[loss=0.1567, simple_loss=0.2575, pruned_loss=0.02793, over 7112.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2619, pruned_loss=0.03062, over 1412313.15 frames.], batch size: 21, lr: 2.44e-04
+2022-04-30 12:21:14,749 INFO [train.py:763] (2/8) Epoch 31, batch 1750, loss[loss=0.2026, simple_loss=0.2932, pruned_loss=0.05602, over 5304.00 frames.], tot_loss[loss=0.162, simple_loss=0.2622, pruned_loss=0.03092, over 1410969.71 frames.], batch size: 53, lr: 2.44e-04
+2022-04-30 12:22:33,258 INFO [train.py:763] (2/8) Epoch 31, batch 1800, loss[loss=0.1884, simple_loss=0.2942, pruned_loss=0.04129, over 7226.00 frames.], tot_loss[loss=0.163, simple_loss=0.2635, pruned_loss=0.03126, over 1411989.51 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:23:40,149 INFO [train.py:763] (2/8) Epoch 31, batch 1850, loss[loss=0.156, simple_loss=0.2515, pruned_loss=0.03029, over 7000.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2636, pruned_loss=0.03132, over 1405988.09 frames.], batch size: 16, lr: 2.44e-04
+2022-04-30 12:24:46,001 INFO [train.py:763] (2/8) Epoch 31, batch 1900, loss[loss=0.1716, simple_loss=0.2716, pruned_loss=0.03582, over 7364.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2626, pruned_loss=0.03138, over 1412177.20 frames.], batch size: 19, lr: 2.44e-04
+2022-04-30 12:25:51,347 INFO [train.py:763] (2/8) Epoch 31, batch 1950, loss[loss=0.1578, simple_loss=0.2689, pruned_loss=0.02338, over 7361.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2623, pruned_loss=0.03116, over 1418672.98 frames.], batch size: 19, lr: 2.43e-04
+2022-04-30 12:26:56,755 INFO [train.py:763] (2/8) Epoch 31, batch 2000, loss[loss=0.126, simple_loss=0.2131, pruned_loss=0.01939, over 7286.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2618, pruned_loss=0.0308, over 1420654.20 frames.], batch size: 18, lr: 2.43e-04
+2022-04-30 12:28:01,916 INFO [train.py:763] (2/8) Epoch 31, batch 2050, loss[loss=0.1491, simple_loss=0.2524, pruned_loss=0.02289, over 7145.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2616, pruned_loss=0.03088, over 1416709.69 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:29:07,871 INFO [train.py:763] (2/8) Epoch 31, batch 2100, loss[loss=0.1385, simple_loss=0.2243, pruned_loss=0.02633, over 6818.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2626, pruned_loss=0.03084, over 1417102.22 frames.], batch size: 15, lr: 2.43e-04
+2022-04-30 12:30:13,150 INFO [train.py:763] (2/8) Epoch 31, batch 2150, loss[loss=0.1577, simple_loss=0.2647, pruned_loss=0.02538, over 7219.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2629, pruned_loss=0.03097, over 1420821.55 frames.], batch size: 21, lr: 2.43e-04
+2022-04-30 12:31:18,645 INFO [train.py:763] (2/8) Epoch 31, batch 2200, loss[loss=0.1767, simple_loss=0.2872, pruned_loss=0.0331, over 7191.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2614, pruned_loss=0.03064, over 1423666.22 frames.], batch size: 26, lr: 2.43e-04
+2022-04-30 12:32:23,983 INFO [train.py:763] (2/8) Epoch 31, batch 2250, loss[loss=0.1418, simple_loss=0.2375, pruned_loss=0.02302, over 7067.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2615, pruned_loss=0.03075, over 1424864.15 frames.], batch size: 18, lr: 2.43e-04
+2022-04-30 12:33:30,742 INFO [train.py:763] (2/8) Epoch 31, batch 2300, loss[loss=0.1909, simple_loss=0.2876, pruned_loss=0.04706, over 7338.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2614, pruned_loss=0.03105, over 1422190.37 frames.], batch size: 22, lr: 2.43e-04
+2022-04-30 12:34:36,633 INFO [train.py:763] (2/8) Epoch 31, batch 2350, loss[loss=0.1391, simple_loss=0.2305, pruned_loss=0.02387, over 7277.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.03107, over 1425589.65 frames.], batch size: 17, lr: 2.43e-04
+2022-04-30 12:35:41,753 INFO [train.py:763] (2/8) Epoch 31, batch 2400, loss[loss=0.1604, simple_loss=0.2562, pruned_loss=0.03228, over 7321.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2619, pruned_loss=0.03098, over 1420924.41 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:36:47,279 INFO [train.py:763] (2/8) Epoch 31, batch 2450, loss[loss=0.1754, simple_loss=0.274, pruned_loss=0.03845, over 7208.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2616, pruned_loss=0.03092, over 1423163.03 frames.], batch size: 26, lr: 2.43e-04
+2022-04-30 12:37:52,777 INFO [train.py:763] (2/8) Epoch 31, batch 2500, loss[loss=0.1237, simple_loss=0.2102, pruned_loss=0.0186, over 7271.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2618, pruned_loss=0.03096, over 1424887.47 frames.], batch size: 17, lr: 2.43e-04
+2022-04-30 12:38:58,015 INFO [train.py:763] (2/8) Epoch 31, batch 2550, loss[loss=0.1426, simple_loss=0.2428, pruned_loss=0.02121, over 7341.00 frames.], tot_loss[loss=0.162, simple_loss=0.2618, pruned_loss=0.03107, over 1421973.62 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:40:03,276 INFO [train.py:763] (2/8) Epoch 31, batch 2600, loss[loss=0.145, simple_loss=0.2251, pruned_loss=0.03246, over 7144.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.03078, over 1420796.26 frames.], batch size: 17, lr: 2.43e-04
+2022-04-30 12:41:08,490 INFO [train.py:763] (2/8) Epoch 31, batch 2650, loss[loss=0.191, simple_loss=0.2894, pruned_loss=0.04627, over 7127.00 frames.], tot_loss[loss=0.1613, simple_loss=0.261, pruned_loss=0.03077, over 1423407.54 frames.], batch size: 26, lr: 2.43e-04
+2022-04-30 12:42:15,309 INFO [train.py:763] (2/8) Epoch 31, batch 2700, loss[loss=0.1504, simple_loss=0.2587, pruned_loss=0.02108, over 7320.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2608, pruned_loss=0.03083, over 1422684.62 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:43:20,587 INFO [train.py:763] (2/8) Epoch 31, batch 2750, loss[loss=0.1667, simple_loss=0.2702, pruned_loss=0.03159, over 7039.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2609, pruned_loss=0.03085, over 1424818.65 frames.], batch size: 28, lr: 2.43e-04
+2022-04-30 12:44:27,118 INFO [train.py:763] (2/8) Epoch 31, batch 2800, loss[loss=0.148, simple_loss=0.2382, pruned_loss=0.02894, over 7405.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2599, pruned_loss=0.03068, over 1424147.90 frames.], batch size: 18, lr: 2.43e-04
+2022-04-30 12:45:34,092 INFO [train.py:763] (2/8) Epoch 31, batch 2850, loss[loss=0.1621, simple_loss=0.2617, pruned_loss=0.03123, over 6490.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2598, pruned_loss=0.03058, over 1421207.88 frames.], batch size: 37, lr: 2.43e-04
+2022-04-30 12:46:39,725 INFO [train.py:763] (2/8) Epoch 31, batch 2900, loss[loss=0.1707, simple_loss=0.2778, pruned_loss=0.03174, over 7230.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2607, pruned_loss=0.0304, over 1424810.03 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:47:44,743 INFO [train.py:763] (2/8) Epoch 31, batch 2950, loss[loss=0.1658, simple_loss=0.2727, pruned_loss=0.02945, over 7203.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2616, pruned_loss=0.03079, over 1417212.69 frames.], batch size: 23, lr: 2.43e-04
+2022-04-30 12:48:50,663 INFO [train.py:763] (2/8) Epoch 31, batch 3000, loss[loss=0.1633, simple_loss=0.2644, pruned_loss=0.03114, over 7426.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2618, pruned_loss=0.03068, over 1418568.17 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:48:50,664 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 12:49:05,873 INFO [train.py:792] (2/8) Epoch 31, validation: loss=0.1686, simple_loss=0.2652, pruned_loss=0.03603, over 698248.00 frames.
+2022-04-30 12:50:12,205 INFO [train.py:763] (2/8) Epoch 31, batch 3050, loss[loss=0.1635, simple_loss=0.2614, pruned_loss=0.03277, over 7294.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2621, pruned_loss=0.03091, over 1422523.45 frames.], batch size: 25, lr: 2.43e-04
+2022-04-30 12:51:18,202 INFO [train.py:763] (2/8) Epoch 31, batch 3100, loss[loss=0.1613, simple_loss=0.2693, pruned_loss=0.02665, over 7074.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2621, pruned_loss=0.03072, over 1425909.11 frames.], batch size: 28, lr: 2.42e-04
+2022-04-30 12:52:23,636 INFO [train.py:763] (2/8) Epoch 31, batch 3150, loss[loss=0.1459, simple_loss=0.239, pruned_loss=0.02644, over 7269.00 frames.], tot_loss[loss=0.1619, simple_loss=0.262, pruned_loss=0.03092, over 1423788.97 frames.], batch size: 17, lr: 2.42e-04
+2022-04-30 12:53:29,082 INFO [train.py:763] (2/8) Epoch 31, batch 3200, loss[loss=0.192, simple_loss=0.2894, pruned_loss=0.04732, over 7114.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2632, pruned_loss=0.0313, over 1426731.14 frames.], batch size: 21, lr: 2.42e-04
+2022-04-30 12:54:36,150 INFO [train.py:763] (2/8) Epoch 31, batch 3250, loss[loss=0.1563, simple_loss=0.261, pruned_loss=0.02584, over 7341.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2628, pruned_loss=0.03118, over 1427234.63 frames.], batch size: 22, lr: 2.42e-04
+2022-04-30 12:55:42,934 INFO [train.py:763] (2/8) Epoch 31, batch 3300, loss[loss=0.1491, simple_loss=0.24, pruned_loss=0.02911, over 7437.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2618, pruned_loss=0.03093, over 1424252.40 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 12:56:50,141 INFO [train.py:763] (2/8) Epoch 31, batch 3350, loss[loss=0.1768, simple_loss=0.2855, pruned_loss=0.03408, over 7307.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2598, pruned_loss=0.03046, over 1425464.32 frames.], batch size: 21, lr: 2.42e-04
+2022-04-30 12:57:56,830 INFO [train.py:763] (2/8) Epoch 31, batch 3400, loss[loss=0.1531, simple_loss=0.2688, pruned_loss=0.01873, over 7336.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2613, pruned_loss=0.03087, over 1422369.51 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 12:59:03,243 INFO [train.py:763] (2/8) Epoch 31, batch 3450, loss[loss=0.1808, simple_loss=0.2813, pruned_loss=0.04016, over 7189.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2626, pruned_loss=0.03084, over 1425445.78 frames.], batch size: 22, lr: 2.42e-04
+2022-04-30 13:00:08,920 INFO [train.py:763] (2/8) Epoch 31, batch 3500, loss[loss=0.166, simple_loss=0.2611, pruned_loss=0.03542, over 7302.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2628, pruned_loss=0.03101, over 1428323.68 frames.], batch size: 24, lr: 2.42e-04
+2022-04-30 13:01:14,840 INFO [train.py:763] (2/8) Epoch 31, batch 3550, loss[loss=0.1759, simple_loss=0.2742, pruned_loss=0.03877, over 7372.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2621, pruned_loss=0.03086, over 1431559.56 frames.], batch size: 23, lr: 2.42e-04
+2022-04-30 13:02:21,335 INFO [train.py:763] (2/8) Epoch 31, batch 3600, loss[loss=0.1786, simple_loss=0.2906, pruned_loss=0.03328, over 6480.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2615, pruned_loss=0.03103, over 1429475.41 frames.], batch size: 37, lr: 2.42e-04
+2022-04-30 13:03:26,534 INFO [train.py:763] (2/8) Epoch 31, batch 3650, loss[loss=0.1589, simple_loss=0.266, pruned_loss=0.02594, over 7240.00 frames.], tot_loss[loss=0.1621, simple_loss=0.262, pruned_loss=0.03108, over 1429086.87 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 13:04:32,085 INFO [train.py:763] (2/8) Epoch 31, batch 3700, loss[loss=0.1429, simple_loss=0.2344, pruned_loss=0.02572, over 7137.00 frames.], tot_loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.03064, over 1430704.95 frames.], batch size: 17, lr: 2.42e-04
+2022-04-30 13:05:36,812 INFO [train.py:763] (2/8) Epoch 31, batch 3750, loss[loss=0.198, simple_loss=0.2951, pruned_loss=0.05047, over 7197.00 frames.], tot_loss[loss=0.161, simple_loss=0.2609, pruned_loss=0.03059, over 1426201.62 frames.], batch size: 23, lr: 2.42e-04
+2022-04-30 13:06:42,584 INFO [train.py:763] (2/8) Epoch 31, batch 3800, loss[loss=0.1515, simple_loss=0.2578, pruned_loss=0.02263, over 7368.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2608, pruned_loss=0.03067, over 1427071.01 frames.], batch size: 23, lr: 2.42e-04
+2022-04-30 13:07:47,975 INFO [train.py:763] (2/8) Epoch 31, batch 3850, loss[loss=0.1593, simple_loss=0.2578, pruned_loss=0.03041, over 7429.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2599, pruned_loss=0.03019, over 1428826.86 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 13:08:53,255 INFO [train.py:763] (2/8) Epoch 31, batch 3900, loss[loss=0.1482, simple_loss=0.2456, pruned_loss=0.02541, over 7156.00 frames.], tot_loss[loss=0.16, simple_loss=0.2599, pruned_loss=0.03, over 1430147.65 frames.], batch size: 18, lr: 2.42e-04
+2022-04-30 13:09:58,647 INFO [train.py:763] (2/8) Epoch 31, batch 3950, loss[loss=0.1597, simple_loss=0.2663, pruned_loss=0.02654, over 7227.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2603, pruned_loss=0.03028, over 1424157.56 frames.], batch size: 21, lr: 2.42e-04
+2022-04-30 13:11:04,246 INFO [train.py:763] (2/8) Epoch 31, batch 4000, loss[loss=0.1513, simple_loss=0.2354, pruned_loss=0.03364, over 7411.00 frames.], tot_loss[loss=0.161, simple_loss=0.2605, pruned_loss=0.0307, over 1421389.12 frames.], batch size: 18, lr: 2.42e-04
+2022-04-30 13:12:09,630 INFO [train.py:763] (2/8) Epoch 31, batch 4050, loss[loss=0.1883, simple_loss=0.2945, pruned_loss=0.04101, over 7386.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2608, pruned_loss=0.03088, over 1419789.50 frames.], batch size: 23, lr: 2.42e-04
+2022-04-30 13:13:15,758 INFO [train.py:763] (2/8) Epoch 31, batch 4100, loss[loss=0.1754, simple_loss=0.281, pruned_loss=0.03493, over 7199.00 frames.], tot_loss[loss=0.162, simple_loss=0.2615, pruned_loss=0.03125, over 1417566.09 frames.], batch size: 22, lr: 2.42e-04
+2022-04-30 13:14:21,772 INFO [train.py:763] (2/8) Epoch 31, batch 4150, loss[loss=0.1789, simple_loss=0.2931, pruned_loss=0.0324, over 7222.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2616, pruned_loss=0.03124, over 1421002.70 frames.], batch size: 21, lr: 2.42e-04
+2022-04-30 13:15:28,691 INFO [train.py:763] (2/8) Epoch 31, batch 4200, loss[loss=0.1711, simple_loss=0.2685, pruned_loss=0.03682, over 7336.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2607, pruned_loss=0.03145, over 1421126.32 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 13:16:35,570 INFO [train.py:763] (2/8) Epoch 31, batch 4250, loss[loss=0.1764, simple_loss=0.273, pruned_loss=0.0399, over 7259.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2609, pruned_loss=0.03139, over 1419572.24 frames.], batch size: 19, lr: 2.42e-04
+2022-04-30 13:17:40,849 INFO [train.py:763] (2/8) Epoch 31, batch 4300, loss[loss=0.1572, simple_loss=0.255, pruned_loss=0.02969, over 7428.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2597, pruned_loss=0.03061, over 1419588.23 frames.], batch size: 18, lr: 2.42e-04
+2022-04-30 13:18:46,140 INFO [train.py:763] (2/8) Epoch 31, batch 4350, loss[loss=0.1336, simple_loss=0.2214, pruned_loss=0.02289, over 7169.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2609, pruned_loss=0.03105, over 1420425.45 frames.], batch size: 18, lr: 2.41e-04
+2022-04-30 13:19:51,340 INFO [train.py:763] (2/8) Epoch 31, batch 4400, loss[loss=0.193, simple_loss=0.2966, pruned_loss=0.0447, over 7288.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2622, pruned_loss=0.03167, over 1406747.23 frames.], batch size: 25, lr: 2.41e-04
+2022-04-30 13:20:56,963 INFO [train.py:763] (2/8) Epoch 31, batch 4450, loss[loss=0.1447, simple_loss=0.2324, pruned_loss=0.02848, over 6835.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2631, pruned_loss=0.03209, over 1404039.53 frames.], batch size: 15, lr: 2.41e-04
+2022-04-30 13:22:02,212 INFO [train.py:763] (2/8) Epoch 31, batch 4500, loss[loss=0.1661, simple_loss=0.2729, pruned_loss=0.02965, over 6795.00 frames.], tot_loss[loss=0.1636, simple_loss=0.263, pruned_loss=0.03206, over 1394502.29 frames.], batch size: 31, lr: 2.41e-04
+2022-04-30 13:23:07,075 INFO [train.py:763] (2/8) Epoch 31, batch 4550, loss[loss=0.2038, simple_loss=0.3024, pruned_loss=0.05257, over 5167.00 frames.], tot_loss[loss=0.164, simple_loss=0.2627, pruned_loss=0.03269, over 1358569.99 frames.], batch size: 54, lr: 2.41e-04
+2022-04-30 13:24:35,146 INFO [train.py:763] (2/8) Epoch 32, batch 0, loss[loss=0.1665, simple_loss=0.2744, pruned_loss=0.02929, over 6871.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2744, pruned_loss=0.02929, over 6871.00 frames.], batch size: 31, lr: 2.38e-04
+2022-04-30 13:25:38,915 INFO [train.py:763] (2/8) Epoch 32, batch 50, loss[loss=0.2183, simple_loss=0.2988, pruned_loss=0.06893, over 5013.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2639, pruned_loss=0.0309, over 313497.66 frames.], batch size: 52, lr: 2.38e-04
+2022-04-30 13:26:41,351 INFO [train.py:763] (2/8) Epoch 32, batch 100, loss[loss=0.1503, simple_loss=0.2581, pruned_loss=0.02132, over 6540.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2633, pruned_loss=0.03103, over 558179.63 frames.], batch size: 38, lr: 2.38e-04
+2022-04-30 13:27:47,089 INFO [train.py:763] (2/8) Epoch 32, batch 150, loss[loss=0.1673, simple_loss=0.2719, pruned_loss=0.03132, over 7184.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2631, pruned_loss=0.03037, over 750538.30 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:28:52,457 INFO [train.py:763] (2/8) Epoch 32, batch 200, loss[loss=0.1365, simple_loss=0.2195, pruned_loss=0.02675, over 7000.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2622, pruned_loss=0.03046, over 893545.44 frames.], batch size: 16, lr: 2.37e-04
+2022-04-30 13:29:57,591 INFO [train.py:763] (2/8) Epoch 32, batch 250, loss[loss=0.1607, simple_loss=0.2612, pruned_loss=0.03013, over 7234.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2621, pruned_loss=0.0307, over 1009224.06 frames.], batch size: 20, lr: 2.37e-04
+2022-04-30 13:31:03,084 INFO [train.py:763] (2/8) Epoch 32, batch 300, loss[loss=0.1649, simple_loss=0.2745, pruned_loss=0.02768, over 6654.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2631, pruned_loss=0.03091, over 1092546.83 frames.], batch size: 31, lr: 2.37e-04
+2022-04-30 13:32:10,109 INFO [train.py:763] (2/8) Epoch 32, batch 350, loss[loss=0.1515, simple_loss=0.2416, pruned_loss=0.03072, over 7415.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2641, pruned_loss=0.03122, over 1162626.46 frames.], batch size: 18, lr: 2.37e-04
+2022-04-30 13:33:15,975 INFO [train.py:763] (2/8) Epoch 32, batch 400, loss[loss=0.1655, simple_loss=0.2719, pruned_loss=0.02952, over 7433.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2628, pruned_loss=0.03094, over 1219765.86 frames.], batch size: 20, lr: 2.37e-04
+2022-04-30 13:34:21,563 INFO [train.py:763] (2/8) Epoch 32, batch 450, loss[loss=0.161, simple_loss=0.2708, pruned_loss=0.02556, over 6650.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2616, pruned_loss=0.0307, over 1262157.13 frames.], batch size: 31, lr: 2.37e-04
+2022-04-30 13:35:26,871 INFO [train.py:763] (2/8) Epoch 32, batch 500, loss[loss=0.1667, simple_loss=0.268, pruned_loss=0.03269, over 7195.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2623, pruned_loss=0.03094, over 1300574.42 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:36:32,823 INFO [train.py:763] (2/8) Epoch 32, batch 550, loss[loss=0.1665, simple_loss=0.2718, pruned_loss=0.03058, over 7308.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2632, pruned_loss=0.03106, over 1328637.50 frames.], batch size: 21, lr: 2.37e-04
+2022-04-30 13:37:38,140 INFO [train.py:763] (2/8) Epoch 32, batch 600, loss[loss=0.159, simple_loss=0.2681, pruned_loss=0.02492, over 7308.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2632, pruned_loss=0.03106, over 1346537.95 frames.], batch size: 24, lr: 2.37e-04
+2022-04-30 13:38:43,399 INFO [train.py:763] (2/8) Epoch 32, batch 650, loss[loss=0.1722, simple_loss=0.2818, pruned_loss=0.03133, over 7153.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2625, pruned_loss=0.03055, over 1363592.43 frames.], batch size: 26, lr: 2.37e-04
+2022-04-30 13:39:48,618 INFO [train.py:763] (2/8) Epoch 32, batch 700, loss[loss=0.1584, simple_loss=0.2496, pruned_loss=0.03361, over 7120.00 frames.], tot_loss[loss=0.162, simple_loss=0.2625, pruned_loss=0.03072, over 1375048.58 frames.], batch size: 17, lr: 2.37e-04
+2022-04-30 13:40:55,072 INFO [train.py:763] (2/8) Epoch 32, batch 750, loss[loss=0.1773, simple_loss=0.2884, pruned_loss=0.03312, over 7218.00 frames.], tot_loss[loss=0.1625, simple_loss=0.263, pruned_loss=0.03102, over 1380507.64 frames.], batch size: 21, lr: 2.37e-04
+2022-04-30 13:42:02,248 INFO [train.py:763] (2/8) Epoch 32, batch 800, loss[loss=0.1431, simple_loss=0.2388, pruned_loss=0.02369, over 7437.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2619, pruned_loss=0.03089, over 1391701.98 frames.], batch size: 20, lr: 2.37e-04
+2022-04-30 13:43:08,535 INFO [train.py:763] (2/8) Epoch 32, batch 850, loss[loss=0.1778, simple_loss=0.2817, pruned_loss=0.03701, over 7383.00 frames.], tot_loss[loss=0.162, simple_loss=0.2621, pruned_loss=0.03099, over 1399176.14 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:44:14,302 INFO [train.py:763] (2/8) Epoch 32, batch 900, loss[loss=0.1709, simple_loss=0.271, pruned_loss=0.03537, over 7192.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2604, pruned_loss=0.0304, over 1408807.22 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:45:21,093 INFO [train.py:763] (2/8) Epoch 32, batch 950, loss[loss=0.1523, simple_loss=0.2658, pruned_loss=0.01945, over 7436.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03005, over 1412891.14 frames.], batch size: 20, lr: 2.37e-04
+2022-04-30 13:46:27,365 INFO [train.py:763] (2/8) Epoch 32, batch 1000, loss[loss=0.1528, simple_loss=0.259, pruned_loss=0.02326, over 7197.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2597, pruned_loss=0.03006, over 1412972.13 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:47:33,310 INFO [train.py:763] (2/8) Epoch 32, batch 1050, loss[loss=0.1607, simple_loss=0.2608, pruned_loss=0.03037, over 7086.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2601, pruned_loss=0.03011, over 1411926.03 frames.], batch size: 28, lr: 2.37e-04
+2022-04-30 13:48:38,616 INFO [train.py:763] (2/8) Epoch 32, batch 1100, loss[loss=0.1803, simple_loss=0.2865, pruned_loss=0.03701, over 7281.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2601, pruned_loss=0.03033, over 1417075.56 frames.], batch size: 24, lr: 2.37e-04
+2022-04-30 13:49:45,239 INFO [train.py:763] (2/8) Epoch 32, batch 1150, loss[loss=0.1608, simple_loss=0.2673, pruned_loss=0.02709, over 7217.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2604, pruned_loss=0.03028, over 1418074.76 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:50:50,720 INFO [train.py:763] (2/8) Epoch 32, batch 1200, loss[loss=0.1603, simple_loss=0.2661, pruned_loss=0.02724, over 7163.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2612, pruned_loss=0.03051, over 1421123.07 frames.], batch size: 26, lr: 2.37e-04
+2022-04-30 13:51:56,746 INFO [train.py:763] (2/8) Epoch 32, batch 1250, loss[loss=0.1776, simple_loss=0.2754, pruned_loss=0.03986, over 6629.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2621, pruned_loss=0.03107, over 1420099.89 frames.], batch size: 38, lr: 2.37e-04
+2022-04-30 13:53:02,499 INFO [train.py:763] (2/8) Epoch 32, batch 1300, loss[loss=0.1588, simple_loss=0.2685, pruned_loss=0.02452, over 7214.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2623, pruned_loss=0.03157, over 1420913.56 frames.], batch size: 21, lr: 2.37e-04
+2022-04-30 13:54:10,198 INFO [train.py:763] (2/8) Epoch 32, batch 1350, loss[loss=0.1376, simple_loss=0.2271, pruned_loss=0.02399, over 7279.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2621, pruned_loss=0.03175, over 1420469.84 frames.], batch size: 17, lr: 2.37e-04
+2022-04-30 13:55:17,148 INFO [train.py:763] (2/8) Epoch 32, batch 1400, loss[loss=0.1824, simple_loss=0.2913, pruned_loss=0.03679, over 7150.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2613, pruned_loss=0.03123, over 1421780.28 frames.], batch size: 20, lr: 2.36e-04
+2022-04-30 13:56:22,418 INFO [train.py:763] (2/8) Epoch 32, batch 1450, loss[loss=0.17, simple_loss=0.274, pruned_loss=0.03299, over 6824.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2615, pruned_loss=0.03136, over 1424679.73 frames.], batch size: 31, lr: 2.36e-04
+2022-04-30 13:57:27,824 INFO [train.py:763] (2/8) Epoch 32, batch 1500, loss[loss=0.2065, simple_loss=0.3072, pruned_loss=0.05289, over 4784.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2619, pruned_loss=0.0316, over 1421798.44 frames.], batch size: 52, lr: 2.36e-04
+2022-04-30 13:58:33,076 INFO [train.py:763] (2/8) Epoch 32, batch 1550, loss[loss=0.1651, simple_loss=0.267, pruned_loss=0.03161, over 7210.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2625, pruned_loss=0.03169, over 1418485.11 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 13:59:38,324 INFO [train.py:763] (2/8) Epoch 32, batch 1600, loss[loss=0.1555, simple_loss=0.262, pruned_loss=0.02455, over 7416.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2622, pruned_loss=0.03138, over 1420068.88 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 14:00:43,684 INFO [train.py:763] (2/8) Epoch 32, batch 1650, loss[loss=0.1702, simple_loss=0.2758, pruned_loss=0.03224, over 7215.00 frames.], tot_loss[loss=0.1622, simple_loss=0.262, pruned_loss=0.03123, over 1421042.16 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 14:01:48,786 INFO [train.py:763] (2/8) Epoch 32, batch 1700, loss[loss=0.1913, simple_loss=0.2947, pruned_loss=0.04395, over 7298.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2624, pruned_loss=0.03106, over 1422825.26 frames.], batch size: 24, lr: 2.36e-04
+2022-04-30 14:02:54,182 INFO [train.py:763] (2/8) Epoch 32, batch 1750, loss[loss=0.1755, simple_loss=0.2727, pruned_loss=0.03916, over 7056.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2636, pruned_loss=0.03157, over 1415548.18 frames.], batch size: 28, lr: 2.36e-04
+2022-04-30 14:03:59,639 INFO [train.py:763] (2/8) Epoch 32, batch 1800, loss[loss=0.1493, simple_loss=0.2458, pruned_loss=0.0264, over 7262.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2629, pruned_loss=0.03094, over 1419134.73 frames.], batch size: 19, lr: 2.36e-04
+2022-04-30 14:05:06,114 INFO [train.py:763] (2/8) Epoch 32, batch 1850, loss[loss=0.1742, simple_loss=0.2736, pruned_loss=0.03742, over 7315.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2622, pruned_loss=0.03023, over 1422099.41 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 14:06:21,241 INFO [train.py:763] (2/8) Epoch 32, batch 1900, loss[loss=0.1625, simple_loss=0.2676, pruned_loss=0.02872, over 7380.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2621, pruned_loss=0.03008, over 1424706.54 frames.], batch size: 23, lr: 2.36e-04
+2022-04-30 14:07:26,669 INFO [train.py:763] (2/8) Epoch 32, batch 1950, loss[loss=0.17, simple_loss=0.2752, pruned_loss=0.03234, over 7301.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2625, pruned_loss=0.03063, over 1423676.11 frames.], batch size: 24, lr: 2.36e-04
+2022-04-30 14:08:33,677 INFO [train.py:763] (2/8) Epoch 32, batch 2000, loss[loss=0.1619, simple_loss=0.2599, pruned_loss=0.03196, over 6134.00 frames.], tot_loss[loss=0.162, simple_loss=0.2622, pruned_loss=0.03092, over 1425439.70 frames.], batch size: 37, lr: 2.36e-04
+2022-04-30 14:09:39,826 INFO [train.py:763] (2/8) Epoch 32, batch 2050, loss[loss=0.1602, simple_loss=0.2505, pruned_loss=0.03496, over 7170.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2619, pruned_loss=0.03064, over 1425477.60 frames.], batch size: 18, lr: 2.36e-04
+2022-04-30 14:10:45,529 INFO [train.py:763] (2/8) Epoch 32, batch 2100, loss[loss=0.1492, simple_loss=0.2494, pruned_loss=0.02446, over 7154.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2616, pruned_loss=0.03046, over 1427394.91 frames.], batch size: 19, lr: 2.36e-04
+2022-04-30 14:11:52,553 INFO [train.py:763] (2/8) Epoch 32, batch 2150, loss[loss=0.1436, simple_loss=0.2389, pruned_loss=0.02414, over 7419.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2615, pruned_loss=0.03075, over 1428711.91 frames.], batch size: 18, lr: 2.36e-04
+2022-04-30 14:12:58,732 INFO [train.py:763] (2/8) Epoch 32, batch 2200, loss[loss=0.1738, simple_loss=0.2673, pruned_loss=0.04019, over 4745.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2617, pruned_loss=0.03102, over 1421922.39 frames.], batch size: 52, lr: 2.36e-04
+2022-04-30 14:14:05,698 INFO [train.py:763] (2/8) Epoch 32, batch 2250, loss[loss=0.1776, simple_loss=0.2789, pruned_loss=0.03814, over 7213.00 frames.], tot_loss[loss=0.1625, simple_loss=0.262, pruned_loss=0.03153, over 1419373.57 frames.], batch size: 26, lr: 2.36e-04
+2022-04-30 14:15:12,721 INFO [train.py:763] (2/8) Epoch 32, batch 2300, loss[loss=0.1721, simple_loss=0.2806, pruned_loss=0.03181, over 7213.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2612, pruned_loss=0.03146, over 1418228.11 frames.], batch size: 22, lr: 2.36e-04
+2022-04-30 14:16:18,544 INFO [train.py:763] (2/8) Epoch 32, batch 2350, loss[loss=0.1626, simple_loss=0.2471, pruned_loss=0.03905, over 7201.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2603, pruned_loss=0.03118, over 1422080.55 frames.], batch size: 16, lr: 2.36e-04
+2022-04-30 14:17:25,995 INFO [train.py:763] (2/8) Epoch 32, batch 2400, loss[loss=0.1487, simple_loss=0.2517, pruned_loss=0.02291, over 7441.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2602, pruned_loss=0.03106, over 1423603.91 frames.], batch size: 20, lr: 2.36e-04
+2022-04-30 14:18:32,875 INFO [train.py:763] (2/8) Epoch 32, batch 2450, loss[loss=0.1503, simple_loss=0.2615, pruned_loss=0.0196, over 7247.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2602, pruned_loss=0.03068, over 1426021.74 frames.], batch size: 19, lr: 2.36e-04
+2022-04-30 14:19:38,451 INFO [train.py:763] (2/8) Epoch 32, batch 2500, loss[loss=0.1705, simple_loss=0.2791, pruned_loss=0.03102, over 7319.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2601, pruned_loss=0.03053, over 1428024.53 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 14:20:45,067 INFO [train.py:763] (2/8) Epoch 32, batch 2550, loss[loss=0.174, simple_loss=0.267, pruned_loss=0.04048, over 7394.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2596, pruned_loss=0.03096, over 1428001.43 frames.], batch size: 23, lr: 2.36e-04
+2022-04-30 14:21:59,920 INFO [train.py:763] (2/8) Epoch 32, batch 2600, loss[loss=0.1664, simple_loss=0.2763, pruned_loss=0.02828, over 7188.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2598, pruned_loss=0.03082, over 1428209.30 frames.], batch size: 23, lr: 2.36e-04
+2022-04-30 14:23:23,008 INFO [train.py:763] (2/8) Epoch 32, batch 2650, loss[loss=0.1556, simple_loss=0.2479, pruned_loss=0.03161, over 7196.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2599, pruned_loss=0.03067, over 1423208.56 frames.], batch size: 16, lr: 2.35e-04
+2022-04-30 14:24:36,935 INFO [train.py:763] (2/8) Epoch 32, batch 2700, loss[loss=0.1622, simple_loss=0.2654, pruned_loss=0.02949, over 7424.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2599, pruned_loss=0.03027, over 1424994.68 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:25:51,352 INFO [train.py:763] (2/8) Epoch 32, batch 2750, loss[loss=0.1466, simple_loss=0.241, pruned_loss=0.02606, over 7268.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03038, over 1425930.00 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:26:57,659 INFO [train.py:763] (2/8) Epoch 32, batch 2800, loss[loss=0.1867, simple_loss=0.2876, pruned_loss=0.04291, over 7206.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2597, pruned_loss=0.03035, over 1424325.62 frames.], batch size: 23, lr: 2.35e-04
+2022-04-30 14:28:12,041 INFO [train.py:763] (2/8) Epoch 32, batch 2850, loss[loss=0.1863, simple_loss=0.2849, pruned_loss=0.04387, over 7323.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2593, pruned_loss=0.03016, over 1426019.42 frames.], batch size: 21, lr: 2.35e-04
+2022-04-30 14:29:27,080 INFO [train.py:763] (2/8) Epoch 32, batch 2900, loss[loss=0.1693, simple_loss=0.2831, pruned_loss=0.02773, over 7273.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2601, pruned_loss=0.03017, over 1424940.52 frames.], batch size: 25, lr: 2.35e-04
+2022-04-30 14:30:33,971 INFO [train.py:763] (2/8) Epoch 32, batch 2950, loss[loss=0.1428, simple_loss=0.243, pruned_loss=0.02129, over 7435.00 frames.], tot_loss[loss=0.1607, simple_loss=0.261, pruned_loss=0.03024, over 1426997.13 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:31:40,117 INFO [train.py:763] (2/8) Epoch 32, batch 3000, loss[loss=0.1458, simple_loss=0.2415, pruned_loss=0.02506, over 7061.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.0302, over 1426716.73 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:31:40,118 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 14:31:55,318 INFO [train.py:792] (2/8) Epoch 32, validation: loss=0.1696, simple_loss=0.2645, pruned_loss=0.0374, over 698248.00 frames.
+2022-04-30 14:33:01,763 INFO [train.py:763] (2/8) Epoch 32, batch 3050, loss[loss=0.1777, simple_loss=0.2829, pruned_loss=0.03622, over 6433.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2599, pruned_loss=0.02991, over 1424074.41 frames.], batch size: 38, lr: 2.35e-04
+2022-04-30 14:34:07,504 INFO [train.py:763] (2/8) Epoch 32, batch 3100, loss[loss=0.1891, simple_loss=0.2903, pruned_loss=0.04392, over 7384.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2595, pruned_loss=0.02964, over 1425055.86 frames.], batch size: 23, lr: 2.35e-04
+2022-04-30 14:35:13,883 INFO [train.py:763] (2/8) Epoch 32, batch 3150, loss[loss=0.167, simple_loss=0.2633, pruned_loss=0.03532, over 7061.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2593, pruned_loss=0.02991, over 1422313.96 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:36:20,353 INFO [train.py:763] (2/8) Epoch 32, batch 3200, loss[loss=0.157, simple_loss=0.2359, pruned_loss=0.03902, over 7181.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2596, pruned_loss=0.03004, over 1422990.51 frames.], batch size: 16, lr: 2.35e-04
+2022-04-30 14:37:25,784 INFO [train.py:763] (2/8) Epoch 32, batch 3250, loss[loss=0.1444, simple_loss=0.2486, pruned_loss=0.02005, over 7283.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2599, pruned_loss=0.03033, over 1421343.45 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:38:31,354 INFO [train.py:763] (2/8) Epoch 32, batch 3300, loss[loss=0.1672, simple_loss=0.2753, pruned_loss=0.02953, over 7242.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2588, pruned_loss=0.02946, over 1426106.56 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:39:37,081 INFO [train.py:763] (2/8) Epoch 32, batch 3350, loss[loss=0.1775, simple_loss=0.2895, pruned_loss=0.03279, over 7310.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2591, pruned_loss=0.02953, over 1429101.63 frames.], batch size: 21, lr: 2.35e-04
+2022-04-30 14:40:43,410 INFO [train.py:763] (2/8) Epoch 32, batch 3400, loss[loss=0.1484, simple_loss=0.2466, pruned_loss=0.0251, over 7273.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2584, pruned_loss=0.02938, over 1428770.28 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:41:50,115 INFO [train.py:763] (2/8) Epoch 32, batch 3450, loss[loss=0.1411, simple_loss=0.2482, pruned_loss=0.01698, over 7340.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2595, pruned_loss=0.02974, over 1432951.62 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:42:56,321 INFO [train.py:763] (2/8) Epoch 32, batch 3500, loss[loss=0.196, simple_loss=0.2866, pruned_loss=0.05276, over 7376.00 frames.], tot_loss[loss=0.161, simple_loss=0.2607, pruned_loss=0.03063, over 1428823.98 frames.], batch size: 23, lr: 2.35e-04
+2022-04-30 14:44:01,644 INFO [train.py:763] (2/8) Epoch 32, batch 3550, loss[loss=0.1555, simple_loss=0.2355, pruned_loss=0.03778, over 7414.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2611, pruned_loss=0.03093, over 1426969.24 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:45:06,992 INFO [train.py:763] (2/8) Epoch 32, batch 3600, loss[loss=0.1558, simple_loss=0.2553, pruned_loss=0.02809, over 7327.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2614, pruned_loss=0.03096, over 1424074.97 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:46:12,674 INFO [train.py:763] (2/8) Epoch 32, batch 3650, loss[loss=0.1438, simple_loss=0.2495, pruned_loss=0.01902, over 7337.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2606, pruned_loss=0.03078, over 1424017.81 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:47:18,398 INFO [train.py:763] (2/8) Epoch 32, batch 3700, loss[loss=0.1483, simple_loss=0.2406, pruned_loss=0.02799, over 7281.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2617, pruned_loss=0.0307, over 1426986.62 frames.], batch size: 17, lr: 2.35e-04
+2022-04-30 14:48:25,075 INFO [train.py:763] (2/8) Epoch 32, batch 3750, loss[loss=0.1773, simple_loss=0.2894, pruned_loss=0.03264, over 7230.00 frames.], tot_loss[loss=0.161, simple_loss=0.2613, pruned_loss=0.03034, over 1427062.00 frames.], batch size: 21, lr: 2.35e-04
+2022-04-30 14:49:30,588 INFO [train.py:763] (2/8) Epoch 32, batch 3800, loss[loss=0.1914, simple_loss=0.2883, pruned_loss=0.04731, over 7200.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2606, pruned_loss=0.03053, over 1427784.21 frames.], batch size: 23, lr: 2.35e-04
+2022-04-30 14:50:35,837 INFO [train.py:763] (2/8) Epoch 32, batch 3850, loss[loss=0.1542, simple_loss=0.2649, pruned_loss=0.0217, over 7320.00 frames.], tot_loss[loss=0.161, simple_loss=0.2611, pruned_loss=0.03052, over 1427988.27 frames.], batch size: 21, lr: 2.35e-04
+2022-04-30 14:51:41,189 INFO [train.py:763] (2/8) Epoch 32, batch 3900, loss[loss=0.1506, simple_loss=0.2413, pruned_loss=0.02993, over 6730.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2624, pruned_loss=0.03087, over 1428592.61 frames.], batch size: 15, lr: 2.35e-04
+2022-04-30 14:52:46,604 INFO [train.py:763] (2/8) Epoch 32, batch 3950, loss[loss=0.1575, simple_loss=0.2492, pruned_loss=0.03294, over 7401.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2628, pruned_loss=0.03105, over 1430830.04 frames.], batch size: 18, lr: 2.34e-04
+2022-04-30 14:53:52,264 INFO [train.py:763] (2/8) Epoch 32, batch 4000, loss[loss=0.1629, simple_loss=0.2796, pruned_loss=0.02309, over 6175.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2611, pruned_loss=0.03064, over 1431257.99 frames.], batch size: 37, lr: 2.34e-04
+2022-04-30 14:54:57,657 INFO [train.py:763] (2/8) Epoch 32, batch 4050, loss[loss=0.1621, simple_loss=0.2479, pruned_loss=0.03815, over 7285.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2611, pruned_loss=0.03091, over 1427308.43 frames.], batch size: 18, lr: 2.34e-04
+2022-04-30 14:56:02,791 INFO [train.py:763] (2/8) Epoch 32, batch 4100, loss[loss=0.162, simple_loss=0.2593, pruned_loss=0.03239, over 7178.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2599, pruned_loss=0.03065, over 1420631.55 frames.], batch size: 26, lr: 2.34e-04
+2022-04-30 14:57:08,458 INFO [train.py:763] (2/8) Epoch 32, batch 4150, loss[loss=0.1579, simple_loss=0.251, pruned_loss=0.03243, over 7204.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2595, pruned_loss=0.03016, over 1420790.46 frames.], batch size: 16, lr: 2.34e-04
+2022-04-30 14:58:14,263 INFO [train.py:763] (2/8) Epoch 32, batch 4200, loss[loss=0.1508, simple_loss=0.2559, pruned_loss=0.02289, over 7261.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2594, pruned_loss=0.02961, over 1419420.26 frames.], batch size: 19, lr: 2.34e-04
+2022-04-30 14:59:19,678 INFO [train.py:763] (2/8) Epoch 32, batch 4250, loss[loss=0.1526, simple_loss=0.2556, pruned_loss=0.02477, over 7442.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2591, pruned_loss=0.02934, over 1420306.01 frames.], batch size: 20, lr: 2.34e-04
+2022-04-30 15:00:26,349 INFO [train.py:763] (2/8) Epoch 32, batch 4300, loss[loss=0.1664, simple_loss=0.2739, pruned_loss=0.02943, over 6680.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2595, pruned_loss=0.02928, over 1419254.32 frames.], batch size: 31, lr: 2.34e-04
+2022-04-30 15:01:32,991 INFO [train.py:763] (2/8) Epoch 32, batch 4350, loss[loss=0.1633, simple_loss=0.2692, pruned_loss=0.02874, over 7224.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2596, pruned_loss=0.02959, over 1415334.99 frames.], batch size: 21, lr: 2.34e-04
+2022-04-30 15:02:38,275 INFO [train.py:763] (2/8) Epoch 32, batch 4400, loss[loss=0.1704, simple_loss=0.2725, pruned_loss=0.03417, over 7140.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02957, over 1414062.77 frames.], batch size: 20, lr: 2.34e-04
+2022-04-30 15:03:43,362 INFO [train.py:763] (2/8) Epoch 32, batch 4450, loss[loss=0.1965, simple_loss=0.3023, pruned_loss=0.04536, over 7342.00 frames.], tot_loss[loss=0.16, simple_loss=0.2605, pruned_loss=0.02976, over 1407536.31 frames.], batch size: 22, lr: 2.34e-04
+2022-04-30 15:04:48,250 INFO [train.py:763] (2/8) Epoch 32, batch 4500, loss[loss=0.1631, simple_loss=0.2649, pruned_loss=0.03071, over 7142.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2618, pruned_loss=0.0303, over 1397662.58 frames.], batch size: 20, lr: 2.34e-04
+2022-04-30 15:05:53,070 INFO [train.py:763] (2/8) Epoch 32, batch 4550, loss[loss=0.1757, simple_loss=0.2622, pruned_loss=0.04458, over 5156.00 frames.], tot_loss[loss=0.162, simple_loss=0.2624, pruned_loss=0.03084, over 1376537.87 frames.], batch size: 52, lr: 2.34e-04
+2022-04-30 15:07:21,082 INFO [train.py:763] (2/8) Epoch 33, batch 0, loss[loss=0.1587, simple_loss=0.2612, pruned_loss=0.0281, over 7434.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2612, pruned_loss=0.0281, over 7434.00 frames.], batch size: 20, lr: 2.31e-04
+2022-04-30 15:08:26,671 INFO [train.py:763] (2/8) Epoch 33, batch 50, loss[loss=0.1716, simple_loss=0.2782, pruned_loss=0.03255, over 7089.00 frames.], tot_loss[loss=0.1589, simple_loss=0.258, pruned_loss=0.02991, over 324890.94 frames.], batch size: 28, lr: 2.30e-04
+2022-04-30 15:09:31,880 INFO [train.py:763] (2/8) Epoch 33, batch 100, loss[loss=0.1575, simple_loss=0.2644, pruned_loss=0.02531, over 7111.00 frames.], tot_loss[loss=0.1602, simple_loss=0.261, pruned_loss=0.02973, over 566088.06 frames.], batch size: 21, lr: 2.30e-04
+2022-04-30 15:10:37,372 INFO [train.py:763] (2/8) Epoch 33, batch 150, loss[loss=0.1371, simple_loss=0.2387, pruned_loss=0.01776, over 7061.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2585, pruned_loss=0.02898, over 755574.10 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:11:42,895 INFO [train.py:763] (2/8) Epoch 33, batch 200, loss[loss=0.1325, simple_loss=0.231, pruned_loss=0.01706, over 7273.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2579, pruned_loss=0.02881, over 905361.18 frames.], batch size: 17, lr: 2.30e-04
+2022-04-30 15:12:48,572 INFO [train.py:763] (2/8) Epoch 33, batch 250, loss[loss=0.219, simple_loss=0.2971, pruned_loss=0.07052, over 4880.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2581, pruned_loss=0.02953, over 1011263.90 frames.], batch size: 52, lr: 2.30e-04
+2022-04-30 15:13:55,816 INFO [train.py:763] (2/8) Epoch 33, batch 300, loss[loss=0.1594, simple_loss=0.2677, pruned_loss=0.02562, over 7384.00 frames.], tot_loss[loss=0.1594, simple_loss=0.259, pruned_loss=0.02986, over 1101543.64 frames.], batch size: 23, lr: 2.30e-04
+2022-04-30 15:15:01,945 INFO [train.py:763] (2/8) Epoch 33, batch 350, loss[loss=0.1411, simple_loss=0.2325, pruned_loss=0.02484, over 7124.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2607, pruned_loss=0.0301, over 1166644.33 frames.], batch size: 17, lr: 2.30e-04
+2022-04-30 15:16:08,892 INFO [train.py:763] (2/8) Epoch 33, batch 400, loss[loss=0.174, simple_loss=0.2775, pruned_loss=0.03525, over 7413.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2592, pruned_loss=0.02963, over 1227976.45 frames.], batch size: 21, lr: 2.30e-04
+2022-04-30 15:17:14,696 INFO [train.py:763] (2/8) Epoch 33, batch 450, loss[loss=0.1478, simple_loss=0.2456, pruned_loss=0.02495, over 7396.00 frames.], tot_loss[loss=0.16, simple_loss=0.2601, pruned_loss=0.02991, over 1272747.21 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:18:21,052 INFO [train.py:763] (2/8) Epoch 33, batch 500, loss[loss=0.1646, simple_loss=0.2681, pruned_loss=0.03052, over 7296.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2604, pruned_loss=0.03015, over 1305798.69 frames.], batch size: 24, lr: 2.30e-04
+2022-04-30 15:19:26,287 INFO [train.py:763] (2/8) Epoch 33, batch 550, loss[loss=0.1718, simple_loss=0.2732, pruned_loss=0.03519, over 6360.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2608, pruned_loss=0.0305, over 1329539.04 frames.], batch size: 37, lr: 2.30e-04
+2022-04-30 15:20:43,083 INFO [train.py:763] (2/8) Epoch 33, batch 600, loss[loss=0.169, simple_loss=0.272, pruned_loss=0.033, over 7290.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2614, pruned_loss=0.03063, over 1351610.91 frames.], batch size: 25, lr: 2.30e-04
+2022-04-30 15:21:48,328 INFO [train.py:763] (2/8) Epoch 33, batch 650, loss[loss=0.1339, simple_loss=0.2317, pruned_loss=0.01799, over 7161.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2617, pruned_loss=0.03056, over 1370105.13 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:22:53,610 INFO [train.py:763] (2/8) Epoch 33, batch 700, loss[loss=0.1741, simple_loss=0.2597, pruned_loss=0.04426, over 7130.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2606, pruned_loss=0.03056, over 1377116.82 frames.], batch size: 17, lr: 2.30e-04
+2022-04-30 15:23:58,782 INFO [train.py:763] (2/8) Epoch 33, batch 750, loss[loss=0.1601, simple_loss=0.263, pruned_loss=0.02863, over 7226.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2618, pruned_loss=0.03081, over 1388829.93 frames.], batch size: 23, lr: 2.30e-04
+2022-04-30 15:25:05,619 INFO [train.py:763] (2/8) Epoch 33, batch 800, loss[loss=0.1535, simple_loss=0.2562, pruned_loss=0.02534, over 7280.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2621, pruned_loss=0.03059, over 1394709.58 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:26:11,923 INFO [train.py:763] (2/8) Epoch 33, batch 850, loss[loss=0.146, simple_loss=0.2556, pruned_loss=0.01823, over 6479.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2613, pruned_loss=0.03013, over 1403906.36 frames.], batch size: 37, lr: 2.30e-04
+2022-04-30 15:27:17,419 INFO [train.py:763] (2/8) Epoch 33, batch 900, loss[loss=0.207, simple_loss=0.2974, pruned_loss=0.05824, over 5060.00 frames.], tot_loss[loss=0.16, simple_loss=0.2601, pruned_loss=0.02993, over 1408911.97 frames.], batch size: 53, lr: 2.30e-04
+2022-04-30 15:28:22,821 INFO [train.py:763] (2/8) Epoch 33, batch 950, loss[loss=0.1703, simple_loss=0.2664, pruned_loss=0.03705, over 7274.00 frames.], tot_loss[loss=0.16, simple_loss=0.2601, pruned_loss=0.03, over 1408178.48 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:29:28,252 INFO [train.py:763] (2/8) Epoch 33, batch 1000, loss[loss=0.1541, simple_loss=0.2554, pruned_loss=0.02642, over 7428.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2598, pruned_loss=0.0298, over 1409686.22 frames.], batch size: 20, lr: 2.30e-04
+2022-04-30 15:30:33,668 INFO [train.py:763] (2/8) Epoch 33, batch 1050, loss[loss=0.1655, simple_loss=0.269, pruned_loss=0.031, over 7166.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2607, pruned_loss=0.02985, over 1415868.59 frames.], batch size: 19, lr: 2.30e-04
+2022-04-30 15:31:40,466 INFO [train.py:763] (2/8) Epoch 33, batch 1100, loss[loss=0.1831, simple_loss=0.2837, pruned_loss=0.04128, over 6501.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2612, pruned_loss=0.03015, over 1413825.84 frames.], batch size: 37, lr: 2.30e-04
+2022-04-30 15:32:45,925 INFO [train.py:763] (2/8) Epoch 33, batch 1150, loss[loss=0.1528, simple_loss=0.2499, pruned_loss=0.02787, over 7419.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2611, pruned_loss=0.02982, over 1416833.09 frames.], batch size: 20, lr: 2.30e-04
+2022-04-30 15:33:51,341 INFO [train.py:763] (2/8) Epoch 33, batch 1200, loss[loss=0.1757, simple_loss=0.2772, pruned_loss=0.03711, over 7189.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2608, pruned_loss=0.02989, over 1420816.60 frames.], batch size: 23, lr: 2.30e-04
+2022-04-30 15:34:56,631 INFO [train.py:763] (2/8) Epoch 33, batch 1250, loss[loss=0.1767, simple_loss=0.286, pruned_loss=0.03371, over 7346.00 frames.], tot_loss[loss=0.1596, simple_loss=0.26, pruned_loss=0.0296, over 1418082.09 frames.], batch size: 22, lr: 2.30e-04
+2022-04-30 15:36:02,615 INFO [train.py:763] (2/8) Epoch 33, batch 1300, loss[loss=0.1904, simple_loss=0.2904, pruned_loss=0.04523, over 7140.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2592, pruned_loss=0.02987, over 1417975.84 frames.], batch size: 26, lr: 2.30e-04
+2022-04-30 15:37:09,762 INFO [train.py:763] (2/8) Epoch 33, batch 1350, loss[loss=0.1715, simple_loss=0.2732, pruned_loss=0.03494, over 7222.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2589, pruned_loss=0.02996, over 1418842.90 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 15:38:16,824 INFO [train.py:763] (2/8) Epoch 33, batch 1400, loss[loss=0.1599, simple_loss=0.2658, pruned_loss=0.02698, over 7258.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2585, pruned_loss=0.02987, over 1422180.39 frames.], batch size: 19, lr: 2.29e-04
+2022-04-30 15:39:22,841 INFO [train.py:763] (2/8) Epoch 33, batch 1450, loss[loss=0.1513, simple_loss=0.2636, pruned_loss=0.01945, over 7410.00 frames.], tot_loss[loss=0.1583, simple_loss=0.258, pruned_loss=0.0293, over 1425819.71 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 15:40:28,336 INFO [train.py:763] (2/8) Epoch 33, batch 1500, loss[loss=0.2014, simple_loss=0.2992, pruned_loss=0.05182, over 7396.00 frames.], tot_loss[loss=0.1593, simple_loss=0.259, pruned_loss=0.02977, over 1424592.74 frames.], batch size: 23, lr: 2.29e-04
+2022-04-30 15:41:33,823 INFO [train.py:763] (2/8) Epoch 33, batch 1550, loss[loss=0.1701, simple_loss=0.2787, pruned_loss=0.03075, over 7272.00 frames.], tot_loss[loss=0.16, simple_loss=0.2599, pruned_loss=0.03011, over 1421690.74 frames.], batch size: 24, lr: 2.29e-04
+2022-04-30 15:42:39,065 INFO [train.py:763] (2/8) Epoch 33, batch 1600, loss[loss=0.1628, simple_loss=0.2586, pruned_loss=0.0335, over 7323.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2597, pruned_loss=0.03028, over 1422898.68 frames.], batch size: 20, lr: 2.29e-04
+2022-04-30 15:43:46,167 INFO [train.py:763] (2/8) Epoch 33, batch 1650, loss[loss=0.1859, simple_loss=0.293, pruned_loss=0.03943, over 7200.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03024, over 1422694.75 frames.], batch size: 22, lr: 2.29e-04
+2022-04-30 15:44:53,521 INFO [train.py:763] (2/8) Epoch 33, batch 1700, loss[loss=0.1834, simple_loss=0.29, pruned_loss=0.03842, over 7371.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2608, pruned_loss=0.03051, over 1426409.71 frames.], batch size: 23, lr: 2.29e-04
+2022-04-30 15:46:00,129 INFO [train.py:763] (2/8) Epoch 33, batch 1750, loss[loss=0.1678, simple_loss=0.2627, pruned_loss=0.03645, over 7050.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2615, pruned_loss=0.03094, over 1421520.34 frames.], batch size: 28, lr: 2.29e-04
+2022-04-30 15:47:05,292 INFO [train.py:763] (2/8) Epoch 33, batch 1800, loss[loss=0.1491, simple_loss=0.2381, pruned_loss=0.03004, over 7283.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03035, over 1422962.74 frames.], batch size: 17, lr: 2.29e-04
+2022-04-30 15:48:11,895 INFO [train.py:763] (2/8) Epoch 33, batch 1850, loss[loss=0.1574, simple_loss=0.2598, pruned_loss=0.02754, over 7324.00 frames.], tot_loss[loss=0.1606, simple_loss=0.26, pruned_loss=0.03059, over 1414850.03 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 15:49:17,340 INFO [train.py:763] (2/8) Epoch 33, batch 1900, loss[loss=0.1648, simple_loss=0.2699, pruned_loss=0.02987, over 6745.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2601, pruned_loss=0.03048, over 1410521.82 frames.], batch size: 31, lr: 2.29e-04
+2022-04-30 15:50:23,824 INFO [train.py:763] (2/8) Epoch 33, batch 1950, loss[loss=0.1546, simple_loss=0.2461, pruned_loss=0.03158, over 7017.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2604, pruned_loss=0.03045, over 1416750.31 frames.], batch size: 16, lr: 2.29e-04
+2022-04-30 15:51:31,072 INFO [train.py:763] (2/8) Epoch 33, batch 2000, loss[loss=0.1492, simple_loss=0.2403, pruned_loss=0.02906, over 7405.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2604, pruned_loss=0.03025, over 1422362.95 frames.], batch size: 18, lr: 2.29e-04
+2022-04-30 15:52:37,439 INFO [train.py:763] (2/8) Epoch 33, batch 2050, loss[loss=0.1825, simple_loss=0.2906, pruned_loss=0.03719, over 7135.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2601, pruned_loss=0.03025, over 1421632.15 frames.], batch size: 26, lr: 2.29e-04
+2022-04-30 15:53:42,707 INFO [train.py:763] (2/8) Epoch 33, batch 2100, loss[loss=0.16, simple_loss=0.2666, pruned_loss=0.02672, over 7221.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2604, pruned_loss=0.03003, over 1424048.22 frames.], batch size: 23, lr: 2.29e-04
+2022-04-30 15:54:47,940 INFO [train.py:763] (2/8) Epoch 33, batch 2150, loss[loss=0.1848, simple_loss=0.2874, pruned_loss=0.04109, over 7259.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2596, pruned_loss=0.03012, over 1423844.74 frames.], batch size: 24, lr: 2.29e-04
+2022-04-30 15:55:53,178 INFO [train.py:763] (2/8) Epoch 33, batch 2200, loss[loss=0.1511, simple_loss=0.256, pruned_loss=0.02307, over 7319.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.0302, over 1426721.94 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 15:56:58,871 INFO [train.py:763] (2/8) Epoch 33, batch 2250, loss[loss=0.1671, simple_loss=0.2567, pruned_loss=0.03878, over 7257.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2613, pruned_loss=0.03064, over 1422921.79 frames.], batch size: 18, lr: 2.29e-04
+2022-04-30 15:58:05,268 INFO [train.py:763] (2/8) Epoch 33, batch 2300, loss[loss=0.1646, simple_loss=0.2693, pruned_loss=0.02992, over 7153.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2623, pruned_loss=0.03073, over 1424043.52 frames.], batch size: 19, lr: 2.29e-04
+2022-04-30 15:59:10,705 INFO [train.py:763] (2/8) Epoch 33, batch 2350, loss[loss=0.156, simple_loss=0.2566, pruned_loss=0.02768, over 7148.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2613, pruned_loss=0.03043, over 1424629.71 frames.], batch size: 19, lr: 2.29e-04
+2022-04-30 16:00:16,787 INFO [train.py:763] (2/8) Epoch 33, batch 2400, loss[loss=0.1558, simple_loss=0.2679, pruned_loss=0.02188, over 7368.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2602, pruned_loss=0.03004, over 1426594.86 frames.], batch size: 23, lr: 2.29e-04
+2022-04-30 16:01:22,889 INFO [train.py:763] (2/8) Epoch 33, batch 2450, loss[loss=0.1656, simple_loss=0.2773, pruned_loss=0.02696, over 7217.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2613, pruned_loss=0.03008, over 1420568.98 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 16:02:28,044 INFO [train.py:763] (2/8) Epoch 33, batch 2500, loss[loss=0.1435, simple_loss=0.233, pruned_loss=0.02695, over 6978.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2616, pruned_loss=0.03013, over 1418926.71 frames.], batch size: 16, lr: 2.29e-04
+2022-04-30 16:03:33,221 INFO [train.py:763] (2/8) Epoch 33, batch 2550, loss[loss=0.1997, simple_loss=0.298, pruned_loss=0.0507, over 7344.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2611, pruned_loss=0.03025, over 1420937.50 frames.], batch size: 22, lr: 2.29e-04
+2022-04-30 16:04:38,850 INFO [train.py:763] (2/8) Epoch 33, batch 2600, loss[loss=0.1417, simple_loss=0.24, pruned_loss=0.0217, over 7060.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2618, pruned_loss=0.0305, over 1420555.95 frames.], batch size: 18, lr: 2.29e-04
+2022-04-30 16:05:45,686 INFO [train.py:763] (2/8) Epoch 33, batch 2650, loss[loss=0.1558, simple_loss=0.2637, pruned_loss=0.02397, over 7335.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2606, pruned_loss=0.03016, over 1421015.30 frames.], batch size: 22, lr: 2.29e-04
+2022-04-30 16:06:52,532 INFO [train.py:763] (2/8) Epoch 33, batch 2700, loss[loss=0.1269, simple_loss=0.2202, pruned_loss=0.01685, over 7286.00 frames.], tot_loss[loss=0.161, simple_loss=0.2611, pruned_loss=0.03047, over 1425702.25 frames.], batch size: 18, lr: 2.28e-04
+2022-04-30 16:07:59,669 INFO [train.py:763] (2/8) Epoch 33, batch 2750, loss[loss=0.1633, simple_loss=0.2646, pruned_loss=0.03095, over 7323.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2609, pruned_loss=0.0304, over 1424901.01 frames.], batch size: 21, lr: 2.28e-04
+2022-04-30 16:09:06,751 INFO [train.py:763] (2/8) Epoch 33, batch 2800, loss[loss=0.1501, simple_loss=0.2457, pruned_loss=0.02729, over 7422.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2608, pruned_loss=0.03048, over 1429978.77 frames.], batch size: 18, lr: 2.28e-04
+2022-04-30 16:10:13,294 INFO [train.py:763] (2/8) Epoch 33, batch 2850, loss[loss=0.1417, simple_loss=0.2498, pruned_loss=0.01681, over 7222.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2606, pruned_loss=0.03053, over 1430798.46 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:11:18,327 INFO [train.py:763] (2/8) Epoch 33, batch 2900, loss[loss=0.1701, simple_loss=0.2766, pruned_loss=0.03176, over 7147.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2611, pruned_loss=0.03072, over 1427200.24 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:12:24,333 INFO [train.py:763] (2/8) Epoch 33, batch 2950, loss[loss=0.1556, simple_loss=0.2672, pruned_loss=0.02201, over 7144.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2607, pruned_loss=0.03055, over 1426739.64 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:13:31,368 INFO [train.py:763] (2/8) Epoch 33, batch 3000, loss[loss=0.1546, simple_loss=0.2523, pruned_loss=0.02847, over 7365.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.03057, over 1427141.57 frames.], batch size: 19, lr: 2.28e-04
+2022-04-30 16:13:31,369 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 16:13:46,765 INFO [train.py:792] (2/8) Epoch 33, validation: loss=0.1701, simple_loss=0.2653, pruned_loss=0.03746, over 698248.00 frames.
+2022-04-30 16:14:51,744 INFO [train.py:763] (2/8) Epoch 33, batch 3050, loss[loss=0.145, simple_loss=0.2474, pruned_loss=0.02127, over 7358.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2614, pruned_loss=0.03037, over 1427599.30 frames.], batch size: 19, lr: 2.28e-04
+2022-04-30 16:15:58,062 INFO [train.py:763] (2/8) Epoch 33, batch 3100, loss[loss=0.1411, simple_loss=0.2337, pruned_loss=0.0242, over 7213.00 frames.], tot_loss[loss=0.161, simple_loss=0.2612, pruned_loss=0.03037, over 1429883.11 frames.], batch size: 16, lr: 2.28e-04
+2022-04-30 16:17:04,953 INFO [train.py:763] (2/8) Epoch 33, batch 3150, loss[loss=0.1645, simple_loss=0.2451, pruned_loss=0.04192, over 7277.00 frames.], tot_loss[loss=0.16, simple_loss=0.26, pruned_loss=0.02998, over 1429542.19 frames.], batch size: 17, lr: 2.28e-04
+2022-04-30 16:18:11,842 INFO [train.py:763] (2/8) Epoch 33, batch 3200, loss[loss=0.1827, simple_loss=0.2838, pruned_loss=0.04079, over 5018.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2602, pruned_loss=0.03036, over 1425436.64 frames.], batch size: 53, lr: 2.28e-04
+2022-04-30 16:19:17,470 INFO [train.py:763] (2/8) Epoch 33, batch 3250, loss[loss=0.1482, simple_loss=0.2373, pruned_loss=0.02949, over 7145.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2595, pruned_loss=0.03008, over 1422459.77 frames.], batch size: 17, lr: 2.28e-04
+2022-04-30 16:20:22,897 INFO [train.py:763] (2/8) Epoch 33, batch 3300, loss[loss=0.1692, simple_loss=0.2731, pruned_loss=0.03263, over 7020.00 frames.], tot_loss[loss=0.1602, simple_loss=0.26, pruned_loss=0.03026, over 1419553.14 frames.], batch size: 28, lr: 2.28e-04
+2022-04-30 16:21:28,691 INFO [train.py:763] (2/8) Epoch 33, batch 3350, loss[loss=0.1606, simple_loss=0.2732, pruned_loss=0.024, over 7140.00 frames.], tot_loss[loss=0.1596, simple_loss=0.259, pruned_loss=0.03006, over 1422033.59 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:22:44,378 INFO [train.py:763] (2/8) Epoch 33, batch 3400, loss[loss=0.1605, simple_loss=0.2592, pruned_loss=0.03096, over 7200.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2599, pruned_loss=0.03019, over 1422154.12 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:23:50,288 INFO [train.py:763] (2/8) Epoch 33, batch 3450, loss[loss=0.1446, simple_loss=0.2357, pruned_loss=0.0268, over 6993.00 frames.], tot_loss[loss=0.16, simple_loss=0.2598, pruned_loss=0.03006, over 1427647.43 frames.], batch size: 16, lr: 2.28e-04
+2022-04-30 16:24:55,490 INFO [train.py:763] (2/8) Epoch 33, batch 3500, loss[loss=0.1685, simple_loss=0.2659, pruned_loss=0.03554, over 7200.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2609, pruned_loss=0.02986, over 1429178.03 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:26:01,142 INFO [train.py:763] (2/8) Epoch 33, batch 3550, loss[loss=0.1398, simple_loss=0.2332, pruned_loss=0.02323, over 7277.00 frames.], tot_loss[loss=0.1603, simple_loss=0.261, pruned_loss=0.02974, over 1430393.62 frames.], batch size: 17, lr: 2.28e-04
+2022-04-30 16:27:06,624 INFO [train.py:763] (2/8) Epoch 33, batch 3600, loss[loss=0.1612, simple_loss=0.2696, pruned_loss=0.02634, over 7333.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2619, pruned_loss=0.03034, over 1432303.40 frames.], batch size: 21, lr: 2.28e-04
+2022-04-30 16:28:13,474 INFO [train.py:763] (2/8) Epoch 33, batch 3650, loss[loss=0.1652, simple_loss=0.2714, pruned_loss=0.02952, over 6183.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2618, pruned_loss=0.03049, over 1427291.93 frames.], batch size: 37, lr: 2.28e-04
+2022-04-30 16:29:20,521 INFO [train.py:763] (2/8) Epoch 33, batch 3700, loss[loss=0.1922, simple_loss=0.2983, pruned_loss=0.04303, over 7235.00 frames.], tot_loss[loss=0.1609, simple_loss=0.261, pruned_loss=0.03037, over 1422691.41 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:30:26,037 INFO [train.py:763] (2/8) Epoch 33, batch 3750, loss[loss=0.1685, simple_loss=0.2676, pruned_loss=0.03471, over 7314.00 frames.], tot_loss[loss=0.1599, simple_loss=0.26, pruned_loss=0.02997, over 1419575.31 frames.], batch size: 24, lr: 2.28e-04
+2022-04-30 16:31:31,698 INFO [train.py:763] (2/8) Epoch 33, batch 3800, loss[loss=0.1679, simple_loss=0.2747, pruned_loss=0.03054, over 7149.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02958, over 1424209.15 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:32:38,578 INFO [train.py:763] (2/8) Epoch 33, batch 3850, loss[loss=0.1838, simple_loss=0.2814, pruned_loss=0.04311, over 7178.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2601, pruned_loss=0.03, over 1426390.60 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:33:45,458 INFO [train.py:763] (2/8) Epoch 33, batch 3900, loss[loss=0.1831, simple_loss=0.2883, pruned_loss=0.03899, over 7193.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2605, pruned_loss=0.03015, over 1425230.93 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:34:52,419 INFO [train.py:763] (2/8) Epoch 33, batch 3950, loss[loss=0.1485, simple_loss=0.2559, pruned_loss=0.02057, over 7324.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2608, pruned_loss=0.02998, over 1422519.53 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:35:59,189 INFO [train.py:763] (2/8) Epoch 33, batch 4000, loss[loss=0.137, simple_loss=0.2301, pruned_loss=0.02198, over 7058.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2607, pruned_loss=0.02977, over 1423098.37 frames.], batch size: 18, lr: 2.28e-04
+2022-04-30 16:37:13,141 INFO [train.py:763] (2/8) Epoch 33, batch 4050, loss[loss=0.1556, simple_loss=0.2662, pruned_loss=0.02249, over 7169.00 frames.], tot_loss[loss=0.1605, simple_loss=0.261, pruned_loss=0.02995, over 1418177.48 frames.], batch size: 26, lr: 2.27e-04
+2022-04-30 16:38:27,099 INFO [train.py:763] (2/8) Epoch 33, batch 4100, loss[loss=0.1795, simple_loss=0.2851, pruned_loss=0.03699, over 6291.00 frames.], tot_loss[loss=0.1612, simple_loss=0.262, pruned_loss=0.03025, over 1418735.09 frames.], batch size: 37, lr: 2.27e-04
+2022-04-30 16:39:41,391 INFO [train.py:763] (2/8) Epoch 33, batch 4150, loss[loss=0.1251, simple_loss=0.2202, pruned_loss=0.01503, over 7405.00 frames.], tot_loss[loss=0.16, simple_loss=0.2605, pruned_loss=0.02975, over 1418075.31 frames.], batch size: 18, lr: 2.27e-04
+2022-04-30 16:40:55,328 INFO [train.py:763] (2/8) Epoch 33, batch 4200, loss[loss=0.1432, simple_loss=0.2455, pruned_loss=0.02045, over 7233.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2606, pruned_loss=0.03001, over 1420451.82 frames.], batch size: 20, lr: 2.27e-04
+2022-04-30 16:42:02,046 INFO [train.py:763] (2/8) Epoch 33, batch 4250, loss[loss=0.1315, simple_loss=0.2235, pruned_loss=0.01971, over 7129.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2606, pruned_loss=0.02983, over 1420106.33 frames.], batch size: 17, lr: 2.27e-04
+2022-04-30 16:43:17,915 INFO [train.py:763] (2/8) Epoch 33, batch 4300, loss[loss=0.1343, simple_loss=0.2282, pruned_loss=0.02018, over 6999.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2608, pruned_loss=0.02987, over 1422009.96 frames.], batch size: 16, lr: 2.27e-04
+2022-04-30 16:44:24,668 INFO [train.py:763] (2/8) Epoch 33, batch 4350, loss[loss=0.1499, simple_loss=0.2376, pruned_loss=0.03108, over 7223.00 frames.], tot_loss[loss=0.161, simple_loss=0.2613, pruned_loss=0.03042, over 1417771.20 frames.], batch size: 16, lr: 2.27e-04
+2022-04-30 16:45:48,491 INFO [train.py:763] (2/8) Epoch 33, batch 4400, loss[loss=0.1404, simple_loss=0.2319, pruned_loss=0.0245, over 7165.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03061, over 1418824.17 frames.], batch size: 18, lr: 2.27e-04
+2022-04-30 16:46:53,552 INFO [train.py:763] (2/8) Epoch 33, batch 4450, loss[loss=0.1736, simple_loss=0.2743, pruned_loss=0.03647, over 7195.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2624, pruned_loss=0.03086, over 1401653.29 frames.], batch size: 23, lr: 2.27e-04
+2022-04-30 16:48:00,199 INFO [train.py:763] (2/8) Epoch 33, batch 4500, loss[loss=0.1929, simple_loss=0.2784, pruned_loss=0.05377, over 5073.00 frames.], tot_loss[loss=0.162, simple_loss=0.2623, pruned_loss=0.03087, over 1391484.09 frames.], batch size: 52, lr: 2.27e-04
+2022-04-30 16:49:05,828 INFO [train.py:763] (2/8) Epoch 33, batch 4550, loss[loss=0.2189, simple_loss=0.3146, pruned_loss=0.06161, over 5064.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2639, pruned_loss=0.03146, over 1350358.38 frames.], batch size: 52, lr: 2.27e-04
+2022-04-30 16:50:25,383 INFO [train.py:763] (2/8) Epoch 34, batch 0, loss[loss=0.1724, simple_loss=0.2729, pruned_loss=0.03598, over 7229.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2729, pruned_loss=0.03598, over 7229.00 frames.], batch size: 20, lr: 2.24e-04
+2022-04-30 16:51:31,602 INFO [train.py:763] (2/8) Epoch 34, batch 50, loss[loss=0.1748, simple_loss=0.2802, pruned_loss=0.0347, over 7302.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2654, pruned_loss=0.0322, over 318300.69 frames.], batch size: 24, lr: 2.24e-04
+2022-04-30 16:52:37,601 INFO [train.py:763] (2/8) Epoch 34, batch 100, loss[loss=0.205, simple_loss=0.2976, pruned_loss=0.05618, over 7215.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2623, pruned_loss=0.02996, over 568543.11 frames.], batch size: 26, lr: 2.24e-04
+2022-04-30 16:53:43,308 INFO [train.py:763] (2/8) Epoch 34, batch 150, loss[loss=0.1933, simple_loss=0.2907, pruned_loss=0.04797, over 7384.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2623, pruned_loss=0.03009, over 760779.42 frames.], batch size: 23, lr: 2.24e-04
+2022-04-30 16:54:49,440 INFO [train.py:763] (2/8) Epoch 34, batch 200, loss[loss=0.1368, simple_loss=0.239, pruned_loss=0.01731, over 7081.00 frames.], tot_loss[loss=0.1597, simple_loss=0.26, pruned_loss=0.02969, over 909532.18 frames.], batch size: 18, lr: 2.24e-04
+2022-04-30 16:55:56,553 INFO [train.py:763] (2/8) Epoch 34, batch 250, loss[loss=0.1481, simple_loss=0.2531, pruned_loss=0.02153, over 7226.00 frames.], tot_loss[loss=0.1597, simple_loss=0.26, pruned_loss=0.02965, over 1027065.00 frames.], batch size: 20, lr: 2.24e-04
+2022-04-30 16:57:03,052 INFO [train.py:763] (2/8) Epoch 34, batch 300, loss[loss=0.1223, simple_loss=0.2242, pruned_loss=0.01018, over 7159.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2591, pruned_loss=0.02893, over 1113656.15 frames.], batch size: 19, lr: 2.24e-04
+2022-04-30 16:58:08,935 INFO [train.py:763] (2/8) Epoch 34, batch 350, loss[loss=0.1675, simple_loss=0.2731, pruned_loss=0.03096, over 7202.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2585, pruned_loss=0.02894, over 1185257.94 frames.], batch size: 23, lr: 2.24e-04
+2022-04-30 16:59:14,456 INFO [train.py:763] (2/8) Epoch 34, batch 400, loss[loss=0.1443, simple_loss=0.2533, pruned_loss=0.01766, over 7317.00 frames.], tot_loss[loss=0.159, simple_loss=0.2591, pruned_loss=0.02947, over 1239601.69 frames.], batch size: 20, lr: 2.24e-04
+2022-04-30 17:00:20,015 INFO [train.py:763] (2/8) Epoch 34, batch 450, loss[loss=0.1862, simple_loss=0.2782, pruned_loss=0.04707, over 6789.00 frames.], tot_loss[loss=0.1591, simple_loss=0.259, pruned_loss=0.02963, over 1284507.33 frames.], batch size: 31, lr: 2.24e-04
+2022-04-30 17:01:26,959 INFO [train.py:763] (2/8) Epoch 34, batch 500, loss[loss=0.1564, simple_loss=0.2625, pruned_loss=0.02515, over 7333.00 frames.], tot_loss[loss=0.159, simple_loss=0.2589, pruned_loss=0.02948, over 1313890.91 frames.], batch size: 20, lr: 2.23e-04
+2022-04-30 17:02:32,701 INFO [train.py:763] (2/8) Epoch 34, batch 550, loss[loss=0.1466, simple_loss=0.2337, pruned_loss=0.02972, over 7057.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2586, pruned_loss=0.02976, over 1334675.71 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:03:38,760 INFO [train.py:763] (2/8) Epoch 34, batch 600, loss[loss=0.1563, simple_loss=0.2648, pruned_loss=0.02395, over 7336.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2596, pruned_loss=0.02985, over 1353574.00 frames.], batch size: 22, lr: 2.23e-04
+2022-04-30 17:04:44,664 INFO [train.py:763] (2/8) Epoch 34, batch 650, loss[loss=0.14, simple_loss=0.2373, pruned_loss=0.02131, over 7166.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2601, pruned_loss=0.02984, over 1372517.44 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:05:50,784 INFO [train.py:763] (2/8) Epoch 34, batch 700, loss[loss=0.1531, simple_loss=0.2461, pruned_loss=0.03003, over 7280.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2593, pruned_loss=0.02976, over 1386508.96 frames.], batch size: 17, lr: 2.23e-04
+2022-04-30 17:06:58,021 INFO [train.py:763] (2/8) Epoch 34, batch 750, loss[loss=0.1442, simple_loss=0.2342, pruned_loss=0.02709, over 7249.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2582, pruned_loss=0.02938, over 1392659.38 frames.], batch size: 19, lr: 2.23e-04
+2022-04-30 17:08:04,367 INFO [train.py:763] (2/8) Epoch 34, batch 800, loss[loss=0.1542, simple_loss=0.2632, pruned_loss=0.02257, over 7224.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2592, pruned_loss=0.02966, over 1401654.32 frames.], batch size: 21, lr: 2.23e-04
+2022-04-30 17:09:09,693 INFO [train.py:763] (2/8) Epoch 34, batch 850, loss[loss=0.1682, simple_loss=0.2748, pruned_loss=0.03082, over 7287.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2596, pruned_loss=0.02913, over 1402708.60 frames.], batch size: 24, lr: 2.23e-04
+2022-04-30 17:10:15,221 INFO [train.py:763] (2/8) Epoch 34, batch 900, loss[loss=0.2005, simple_loss=0.2894, pruned_loss=0.05575, over 4928.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2596, pruned_loss=0.02908, over 1406655.88 frames.], batch size: 52, lr: 2.23e-04
+2022-04-30 17:11:21,163 INFO [train.py:763] (2/8) Epoch 34, batch 950, loss[loss=0.1659, simple_loss=0.2666, pruned_loss=0.03264, over 7266.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2593, pruned_loss=0.02901, over 1410194.23 frames.], batch size: 19, lr: 2.23e-04
+2022-04-30 17:12:27,410 INFO [train.py:763] (2/8) Epoch 34, batch 1000, loss[loss=0.1676, simple_loss=0.272, pruned_loss=0.03158, over 7021.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2596, pruned_loss=0.02933, over 1412130.31 frames.], batch size: 32, lr: 2.23e-04
+2022-04-30 17:13:34,597 INFO [train.py:763] (2/8) Epoch 34, batch 1050, loss[loss=0.195, simple_loss=0.3001, pruned_loss=0.04493, over 7413.00 frames.], tot_loss[loss=0.1585, simple_loss=0.259, pruned_loss=0.02902, over 1417030.31 frames.], batch size: 21, lr: 2.23e-04
+2022-04-30 17:14:40,033 INFO [train.py:763] (2/8) Epoch 34, batch 1100, loss[loss=0.1329, simple_loss=0.2308, pruned_loss=0.01747, over 7355.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2581, pruned_loss=0.02879, over 1420715.83 frames.], batch size: 19, lr: 2.23e-04
+2022-04-30 17:15:45,148 INFO [train.py:763] (2/8) Epoch 34, batch 1150, loss[loss=0.1664, simple_loss=0.2632, pruned_loss=0.03478, over 7206.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2589, pruned_loss=0.029, over 1423339.74 frames.], batch size: 23, lr: 2.23e-04
+2022-04-30 17:16:50,470 INFO [train.py:763] (2/8) Epoch 34, batch 1200, loss[loss=0.1514, simple_loss=0.2464, pruned_loss=0.02821, over 7273.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2589, pruned_loss=0.02869, over 1426787.41 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:17:56,079 INFO [train.py:763] (2/8) Epoch 34, batch 1250, loss[loss=0.1578, simple_loss=0.2729, pruned_loss=0.02136, over 7334.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2591, pruned_loss=0.02888, over 1424387.92 frames.], batch size: 22, lr: 2.23e-04
+2022-04-30 17:19:02,071 INFO [train.py:763] (2/8) Epoch 34, batch 1300, loss[loss=0.1598, simple_loss=0.2651, pruned_loss=0.02725, over 7171.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2601, pruned_loss=0.02985, over 1419946.14 frames.], batch size: 28, lr: 2.23e-04
+2022-04-30 17:20:07,318 INFO [train.py:763] (2/8) Epoch 34, batch 1350, loss[loss=0.1761, simple_loss=0.2832, pruned_loss=0.03452, over 7014.00 frames.], tot_loss[loss=0.16, simple_loss=0.2602, pruned_loss=0.02993, over 1422203.74 frames.], batch size: 28, lr: 2.23e-04
+2022-04-30 17:21:12,461 INFO [train.py:763] (2/8) Epoch 34, batch 1400, loss[loss=0.1541, simple_loss=0.2619, pruned_loss=0.0232, over 7340.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.03018, over 1419933.02 frames.], batch size: 20, lr: 2.23e-04
+2022-04-30 17:22:17,953 INFO [train.py:763] (2/8) Epoch 34, batch 1450, loss[loss=0.1725, simple_loss=0.2735, pruned_loss=0.03578, over 7250.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2609, pruned_loss=0.03034, over 1418615.25 frames.], batch size: 19, lr: 2.23e-04
+2022-04-30 17:23:24,433 INFO [train.py:763] (2/8) Epoch 34, batch 1500, loss[loss=0.1289, simple_loss=0.2211, pruned_loss=0.01835, over 7147.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03015, over 1420019.95 frames.], batch size: 17, lr: 2.23e-04
+2022-04-30 17:24:29,696 INFO [train.py:763] (2/8) Epoch 34, batch 1550, loss[loss=0.1943, simple_loss=0.3017, pruned_loss=0.04348, over 7225.00 frames.], tot_loss[loss=0.161, simple_loss=0.2612, pruned_loss=0.03036, over 1420169.17 frames.], batch size: 21, lr: 2.23e-04
+2022-04-30 17:25:36,475 INFO [train.py:763] (2/8) Epoch 34, batch 1600, loss[loss=0.1726, simple_loss=0.2713, pruned_loss=0.03689, over 7128.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2607, pruned_loss=0.03031, over 1421861.56 frames.], batch size: 28, lr: 2.23e-04
+2022-04-30 17:26:43,357 INFO [train.py:763] (2/8) Epoch 34, batch 1650, loss[loss=0.1291, simple_loss=0.2175, pruned_loss=0.02039, over 7418.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2598, pruned_loss=0.02968, over 1427166.21 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:27:48,832 INFO [train.py:763] (2/8) Epoch 34, batch 1700, loss[loss=0.179, simple_loss=0.2733, pruned_loss=0.04238, over 5051.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2595, pruned_loss=0.02974, over 1426481.06 frames.], batch size: 52, lr: 2.23e-04
+2022-04-30 17:28:54,320 INFO [train.py:763] (2/8) Epoch 34, batch 1750, loss[loss=0.1547, simple_loss=0.2496, pruned_loss=0.02992, over 7156.00 frames.], tot_loss[loss=0.1593, simple_loss=0.259, pruned_loss=0.0298, over 1426829.40 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:29:59,723 INFO [train.py:763] (2/8) Epoch 34, batch 1800, loss[loss=0.173, simple_loss=0.2792, pruned_loss=0.03337, over 7279.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2581, pruned_loss=0.02932, over 1430726.53 frames.], batch size: 25, lr: 2.23e-04
+2022-04-30 17:31:04,979 INFO [train.py:763] (2/8) Epoch 34, batch 1850, loss[loss=0.1562, simple_loss=0.2505, pruned_loss=0.03097, over 7070.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2585, pruned_loss=0.0295, over 1426865.54 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:32:10,316 INFO [train.py:763] (2/8) Epoch 34, batch 1900, loss[loss=0.1561, simple_loss=0.2571, pruned_loss=0.02751, over 7381.00 frames.], tot_loss[loss=0.159, simple_loss=0.2588, pruned_loss=0.02958, over 1426328.00 frames.], batch size: 23, lr: 2.22e-04
+2022-04-30 17:33:15,839 INFO [train.py:763] (2/8) Epoch 34, batch 1950, loss[loss=0.1411, simple_loss=0.242, pruned_loss=0.02012, over 7166.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2595, pruned_loss=0.02974, over 1424913.94 frames.], batch size: 18, lr: 2.22e-04
+2022-04-30 17:34:22,078 INFO [train.py:763] (2/8) Epoch 34, batch 2000, loss[loss=0.1647, simple_loss=0.2683, pruned_loss=0.03055, over 6440.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2597, pruned_loss=0.02998, over 1420427.57 frames.], batch size: 38, lr: 2.22e-04
+2022-04-30 17:35:27,873 INFO [train.py:763] (2/8) Epoch 34, batch 2050, loss[loss=0.1463, simple_loss=0.2512, pruned_loss=0.02069, over 7123.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03009, over 1422075.07 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:36:33,091 INFO [train.py:763] (2/8) Epoch 34, batch 2100, loss[loss=0.173, simple_loss=0.2686, pruned_loss=0.03872, over 7412.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2609, pruned_loss=0.03025, over 1424918.40 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:37:40,124 INFO [train.py:763] (2/8) Epoch 34, batch 2150, loss[loss=0.1617, simple_loss=0.2717, pruned_loss=0.02587, over 6455.00 frames.], tot_loss[loss=0.16, simple_loss=0.2607, pruned_loss=0.02963, over 1428657.38 frames.], batch size: 38, lr: 2.22e-04
+2022-04-30 17:38:46,193 INFO [train.py:763] (2/8) Epoch 34, batch 2200, loss[loss=0.1466, simple_loss=0.2471, pruned_loss=0.02307, over 7421.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2604, pruned_loss=0.02971, over 1424733.26 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 17:39:51,382 INFO [train.py:763] (2/8) Epoch 34, batch 2250, loss[loss=0.1496, simple_loss=0.2431, pruned_loss=0.02807, over 7290.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2608, pruned_loss=0.02986, over 1422550.99 frames.], batch size: 18, lr: 2.22e-04
+2022-04-30 17:40:56,556 INFO [train.py:763] (2/8) Epoch 34, batch 2300, loss[loss=0.1539, simple_loss=0.2552, pruned_loss=0.02632, over 7166.00 frames.], tot_loss[loss=0.16, simple_loss=0.2603, pruned_loss=0.02986, over 1418990.54 frames.], batch size: 26, lr: 2.22e-04
+2022-04-30 17:42:01,777 INFO [train.py:763] (2/8) Epoch 34, batch 2350, loss[loss=0.2073, simple_loss=0.3091, pruned_loss=0.05277, over 7061.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2601, pruned_loss=0.02962, over 1417872.76 frames.], batch size: 28, lr: 2.22e-04
+2022-04-30 17:43:08,012 INFO [train.py:763] (2/8) Epoch 34, batch 2400, loss[loss=0.1487, simple_loss=0.2357, pruned_loss=0.03091, over 6980.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2604, pruned_loss=0.02999, over 1423000.36 frames.], batch size: 16, lr: 2.22e-04
+2022-04-30 17:44:15,062 INFO [train.py:763] (2/8) Epoch 34, batch 2450, loss[loss=0.1594, simple_loss=0.2575, pruned_loss=0.0307, over 7438.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2594, pruned_loss=0.02948, over 1422328.82 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 17:45:22,379 INFO [train.py:763] (2/8) Epoch 34, batch 2500, loss[loss=0.1654, simple_loss=0.2688, pruned_loss=0.03102, over 6417.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2592, pruned_loss=0.02963, over 1424250.45 frames.], batch size: 38, lr: 2.22e-04
+2022-04-30 17:46:28,712 INFO [train.py:763] (2/8) Epoch 34, batch 2550, loss[loss=0.1666, simple_loss=0.2745, pruned_loss=0.02938, over 7117.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2595, pruned_loss=0.02981, over 1424008.85 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:47:35,754 INFO [train.py:763] (2/8) Epoch 34, batch 2600, loss[loss=0.1618, simple_loss=0.2639, pruned_loss=0.02987, over 7194.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2588, pruned_loss=0.02943, over 1423021.87 frames.], batch size: 22, lr: 2.22e-04
+2022-04-30 17:48:40,937 INFO [train.py:763] (2/8) Epoch 34, batch 2650, loss[loss=0.2005, simple_loss=0.2901, pruned_loss=0.05543, over 7196.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2591, pruned_loss=0.02981, over 1422283.38 frames.], batch size: 23, lr: 2.22e-04
+2022-04-30 17:49:46,278 INFO [train.py:763] (2/8) Epoch 34, batch 2700, loss[loss=0.1527, simple_loss=0.261, pruned_loss=0.02224, over 7132.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2587, pruned_loss=0.02939, over 1424552.81 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:50:51,541 INFO [train.py:763] (2/8) Epoch 34, batch 2750, loss[loss=0.1487, simple_loss=0.2471, pruned_loss=0.02516, over 7311.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2593, pruned_loss=0.02984, over 1424985.67 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:51:57,727 INFO [train.py:763] (2/8) Epoch 34, batch 2800, loss[loss=0.1435, simple_loss=0.2395, pruned_loss=0.02373, over 7319.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2596, pruned_loss=0.03025, over 1425501.43 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 17:53:04,496 INFO [train.py:763] (2/8) Epoch 34, batch 2850, loss[loss=0.1675, simple_loss=0.2581, pruned_loss=0.0385, over 7167.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2597, pruned_loss=0.02984, over 1423254.07 frames.], batch size: 19, lr: 2.22e-04
+2022-04-30 17:54:11,622 INFO [train.py:763] (2/8) Epoch 34, batch 2900, loss[loss=0.1595, simple_loss=0.2644, pruned_loss=0.02729, over 6297.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2598, pruned_loss=0.02971, over 1422756.83 frames.], batch size: 37, lr: 2.22e-04
+2022-04-30 17:55:17,491 INFO [train.py:763] (2/8) Epoch 34, batch 2950, loss[loss=0.1513, simple_loss=0.2454, pruned_loss=0.02855, over 7192.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2601, pruned_loss=0.02962, over 1416160.32 frames.], batch size: 16, lr: 2.22e-04
+2022-04-30 17:56:22,954 INFO [train.py:763] (2/8) Epoch 34, batch 3000, loss[loss=0.1678, simple_loss=0.2717, pruned_loss=0.03192, over 7380.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02957, over 1420346.09 frames.], batch size: 23, lr: 2.22e-04
+2022-04-30 17:56:22,954 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 17:56:38,271 INFO [train.py:792] (2/8) Epoch 34, validation: loss=0.1686, simple_loss=0.2638, pruned_loss=0.03669, over 698248.00 frames.
+2022-04-30 17:57:44,334 INFO [train.py:763] (2/8) Epoch 34, batch 3050, loss[loss=0.1528, simple_loss=0.2569, pruned_loss=0.02436, over 7241.00 frames.], tot_loss[loss=0.159, simple_loss=0.2592, pruned_loss=0.02943, over 1423474.23 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 17:58:51,168 INFO [train.py:763] (2/8) Epoch 34, batch 3100, loss[loss=0.1724, simple_loss=0.2756, pruned_loss=0.03465, over 7367.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2595, pruned_loss=0.02935, over 1419888.02 frames.], batch size: 23, lr: 2.22e-04
+2022-04-30 17:59:56,666 INFO [train.py:763] (2/8) Epoch 34, batch 3150, loss[loss=0.1706, simple_loss=0.2675, pruned_loss=0.03691, over 7216.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2583, pruned_loss=0.0292, over 1422241.33 frames.], batch size: 22, lr: 2.22e-04
+2022-04-30 18:01:02,257 INFO [train.py:763] (2/8) Epoch 34, batch 3200, loss[loss=0.1505, simple_loss=0.2576, pruned_loss=0.02172, over 7191.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2583, pruned_loss=0.02868, over 1426872.47 frames.], batch size: 22, lr: 2.22e-04
+2022-04-30 18:02:09,377 INFO [train.py:763] (2/8) Epoch 34, batch 3250, loss[loss=0.168, simple_loss=0.2563, pruned_loss=0.0398, over 7443.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2584, pruned_loss=0.0286, over 1426322.29 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 18:03:15,758 INFO [train.py:763] (2/8) Epoch 34, batch 3300, loss[loss=0.1371, simple_loss=0.2324, pruned_loss=0.0209, over 7435.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2591, pruned_loss=0.02864, over 1427238.31 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 18:04:21,123 INFO [train.py:763] (2/8) Epoch 34, batch 3350, loss[loss=0.167, simple_loss=0.2721, pruned_loss=0.03091, over 7427.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2594, pruned_loss=0.02876, over 1430522.47 frames.], batch size: 20, lr: 2.21e-04
+2022-04-30 18:05:26,505 INFO [train.py:763] (2/8) Epoch 34, batch 3400, loss[loss=0.1471, simple_loss=0.2508, pruned_loss=0.02166, over 7267.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2594, pruned_loss=0.02906, over 1427234.31 frames.], batch size: 18, lr: 2.21e-04
+2022-04-30 18:06:31,933 INFO [train.py:763] (2/8) Epoch 34, batch 3450, loss[loss=0.1457, simple_loss=0.2357, pruned_loss=0.02785, over 7010.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2602, pruned_loss=0.02947, over 1430074.12 frames.], batch size: 16, lr: 2.21e-04
+2022-04-30 18:07:37,451 INFO [train.py:763] (2/8) Epoch 34, batch 3500, loss[loss=0.1469, simple_loss=0.2587, pruned_loss=0.01752, over 7330.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2599, pruned_loss=0.02951, over 1428589.96 frames.], batch size: 22, lr: 2.21e-04
+2022-04-30 18:08:42,508 INFO [train.py:763] (2/8) Epoch 34, batch 3550, loss[loss=0.1803, simple_loss=0.2817, pruned_loss=0.03947, over 6807.00 frames.], tot_loss[loss=0.1597, simple_loss=0.26, pruned_loss=0.02971, over 1421594.21 frames.], batch size: 31, lr: 2.21e-04
+2022-04-30 18:09:48,189 INFO [train.py:763] (2/8) Epoch 34, batch 3600, loss[loss=0.1843, simple_loss=0.2782, pruned_loss=0.04518, over 7210.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2598, pruned_loss=0.03003, over 1419959.87 frames.], batch size: 22, lr: 2.21e-04
+2022-04-30 18:10:55,324 INFO [train.py:763] (2/8) Epoch 34, batch 3650, loss[loss=0.1658, simple_loss=0.2741, pruned_loss=0.02876, over 7289.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2601, pruned_loss=0.03002, over 1421089.83 frames.], batch size: 25, lr: 2.21e-04
+2022-04-30 18:12:01,491 INFO [train.py:763] (2/8) Epoch 34, batch 3700, loss[loss=0.1519, simple_loss=0.2552, pruned_loss=0.02429, over 6497.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2596, pruned_loss=0.02963, over 1420451.60 frames.], batch size: 38, lr: 2.21e-04
+2022-04-30 18:13:06,699 INFO [train.py:763] (2/8) Epoch 34, batch 3750, loss[loss=0.1969, simple_loss=0.2939, pruned_loss=0.04994, over 5245.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2599, pruned_loss=0.02948, over 1418013.09 frames.], batch size: 53, lr: 2.21e-04
+2022-04-30 18:14:11,982 INFO [train.py:763] (2/8) Epoch 34, batch 3800, loss[loss=0.167, simple_loss=0.2722, pruned_loss=0.0309, over 6667.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2599, pruned_loss=0.02964, over 1418653.51 frames.], batch size: 31, lr: 2.21e-04
+2022-04-30 18:15:17,333 INFO [train.py:763] (2/8) Epoch 34, batch 3850, loss[loss=0.1483, simple_loss=0.2469, pruned_loss=0.02483, over 7290.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2594, pruned_loss=0.02981, over 1421728.21 frames.], batch size: 24, lr: 2.21e-04
+2022-04-30 18:16:23,809 INFO [train.py:763] (2/8) Epoch 34, batch 3900, loss[loss=0.1407, simple_loss=0.2308, pruned_loss=0.02527, over 7221.00 frames.], tot_loss[loss=0.1601, simple_loss=0.26, pruned_loss=0.03005, over 1418433.74 frames.], batch size: 16, lr: 2.21e-04
+2022-04-30 18:17:30,966 INFO [train.py:763] (2/8) Epoch 34, batch 3950, loss[loss=0.1684, simple_loss=0.2594, pruned_loss=0.03872, over 7130.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2596, pruned_loss=0.02981, over 1418495.25 frames.], batch size: 17, lr: 2.21e-04
+2022-04-30 18:18:37,950 INFO [train.py:763] (2/8) Epoch 34, batch 4000, loss[loss=0.1658, simple_loss=0.2512, pruned_loss=0.04021, over 7013.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2597, pruned_loss=0.02984, over 1418562.29 frames.], batch size: 16, lr: 2.21e-04
+2022-04-30 18:19:54,710 INFO [train.py:763] (2/8) Epoch 34, batch 4050, loss[loss=0.1473, simple_loss=0.2565, pruned_loss=0.01902, over 6413.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2599, pruned_loss=0.02957, over 1422194.47 frames.], batch size: 38, lr: 2.21e-04
+2022-04-30 18:21:01,770 INFO [train.py:763] (2/8) Epoch 34, batch 4100, loss[loss=0.1493, simple_loss=0.2576, pruned_loss=0.02052, over 7225.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2602, pruned_loss=0.02963, over 1427251.18 frames.], batch size: 21, lr: 2.21e-04
+2022-04-30 18:22:08,648 INFO [train.py:763] (2/8) Epoch 34, batch 4150, loss[loss=0.1571, simple_loss=0.2622, pruned_loss=0.02599, over 7315.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2598, pruned_loss=0.02991, over 1425757.36 frames.], batch size: 21, lr: 2.21e-04
+2022-04-30 18:23:15,038 INFO [train.py:763] (2/8) Epoch 34, batch 4200, loss[loss=0.1622, simple_loss=0.2671, pruned_loss=0.02863, over 7328.00 frames.], tot_loss[loss=0.16, simple_loss=0.2602, pruned_loss=0.02991, over 1423807.55 frames.], batch size: 21, lr: 2.21e-04
+2022-04-30 18:24:20,536 INFO [train.py:763] (2/8) Epoch 34, batch 4250, loss[loss=0.1444, simple_loss=0.2368, pruned_loss=0.02596, over 7298.00 frames.], tot_loss[loss=0.1591, simple_loss=0.259, pruned_loss=0.02964, over 1427776.30 frames.], batch size: 17, lr: 2.21e-04
+2022-04-30 18:25:25,960 INFO [train.py:763] (2/8) Epoch 34, batch 4300, loss[loss=0.1655, simple_loss=0.2633, pruned_loss=0.03381, over 7174.00 frames.], tot_loss[loss=0.1584, simple_loss=0.258, pruned_loss=0.02945, over 1418796.69 frames.], batch size: 26, lr: 2.21e-04
+2022-04-30 18:26:32,708 INFO [train.py:763] (2/8) Epoch 34, batch 4350, loss[loss=0.1648, simple_loss=0.2611, pruned_loss=0.03429, over 7295.00 frames.], tot_loss[loss=0.1596, simple_loss=0.259, pruned_loss=0.03013, over 1414621.61 frames.], batch size: 24, lr: 2.21e-04
+2022-04-30 18:27:38,203 INFO [train.py:763] (2/8) Epoch 34, batch 4400, loss[loss=0.141, simple_loss=0.2378, pruned_loss=0.0221, over 7165.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2601, pruned_loss=0.0301, over 1410293.31 frames.], batch size: 19, lr: 2.21e-04
+2022-04-30 18:28:42,655 INFO [train.py:763] (2/8) Epoch 34, batch 4450, loss[loss=0.1658, simple_loss=0.2693, pruned_loss=0.03111, over 6829.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2604, pruned_loss=0.03024, over 1395132.78 frames.], batch size: 32, lr: 2.21e-04
+2022-04-30 18:29:47,242 INFO [train.py:763] (2/8) Epoch 34, batch 4500, loss[loss=0.1697, simple_loss=0.2769, pruned_loss=0.03128, over 7169.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03044, over 1381791.88 frames.], batch size: 26, lr: 2.21e-04
+2022-04-30 18:30:51,772 INFO [train.py:763] (2/8) Epoch 34, batch 4550, loss[loss=0.1758, simple_loss=0.2656, pruned_loss=0.04301, over 4908.00 frames.], tot_loss[loss=0.1636, simple_loss=0.263, pruned_loss=0.03208, over 1356421.82 frames.], batch size: 54, lr: 2.21e-04
+2022-04-30 18:32:11,384 INFO [train.py:763] (2/8) Epoch 35, batch 0, loss[loss=0.1723, simple_loss=0.2733, pruned_loss=0.03562, over 7316.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2733, pruned_loss=0.03562, over 7316.00 frames.], batch size: 20, lr: 2.18e-04
+2022-04-30 18:33:17,372 INFO [train.py:763] (2/8) Epoch 35, batch 50, loss[loss=0.1749, simple_loss=0.2783, pruned_loss=0.0358, over 7427.00 frames.], tot_loss[loss=0.16, simple_loss=0.2605, pruned_loss=0.02977, over 316908.40 frames.], batch size: 20, lr: 2.18e-04
+2022-04-30 18:34:22,741 INFO [train.py:763] (2/8) Epoch 35, batch 100, loss[loss=0.1855, simple_loss=0.2797, pruned_loss=0.04564, over 5028.00 frames.], tot_loss[loss=0.158, simple_loss=0.2581, pruned_loss=0.02895, over 562481.39 frames.], batch size: 53, lr: 2.17e-04
+2022-04-30 18:35:28,400 INFO [train.py:763] (2/8) Epoch 35, batch 150, loss[loss=0.1692, simple_loss=0.2734, pruned_loss=0.03255, over 7232.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2592, pruned_loss=0.02911, over 751868.63 frames.], batch size: 20, lr: 2.17e-04
+2022-04-30 18:36:34,084 INFO [train.py:763] (2/8) Epoch 35, batch 200, loss[loss=0.159, simple_loss=0.26, pruned_loss=0.02898, over 7318.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2596, pruned_loss=0.02906, over 901552.48 frames.], batch size: 21, lr: 2.17e-04
+2022-04-30 18:37:50,840 INFO [train.py:763] (2/8) Epoch 35, batch 250, loss[loss=0.1553, simple_loss=0.2582, pruned_loss=0.02622, over 7167.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2597, pruned_loss=0.02931, over 1020860.43 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 18:38:58,239 INFO [train.py:763] (2/8) Epoch 35, batch 300, loss[loss=0.1916, simple_loss=0.2812, pruned_loss=0.05101, over 7180.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2594, pruned_loss=0.02919, over 1105053.90 frames.], batch size: 26, lr: 2.17e-04
+2022-04-30 18:40:05,542 INFO [train.py:763] (2/8) Epoch 35, batch 350, loss[loss=0.1437, simple_loss=0.2393, pruned_loss=0.02401, over 6698.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2596, pruned_loss=0.02898, over 1174316.28 frames.], batch size: 31, lr: 2.17e-04
+2022-04-30 18:41:12,762 INFO [train.py:763] (2/8) Epoch 35, batch 400, loss[loss=0.1772, simple_loss=0.2713, pruned_loss=0.04153, over 7199.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2597, pruned_loss=0.02899, over 1230315.23 frames.], batch size: 22, lr: 2.17e-04
+2022-04-30 18:42:19,864 INFO [train.py:763] (2/8) Epoch 35, batch 450, loss[loss=0.1684, simple_loss=0.2689, pruned_loss=0.03389, over 7187.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2603, pruned_loss=0.02941, over 1278194.20 frames.], batch size: 26, lr: 2.17e-04
+2022-04-30 18:43:25,152 INFO [train.py:763] (2/8) Epoch 35, batch 500, loss[loss=0.1873, simple_loss=0.293, pruned_loss=0.04079, over 7204.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2611, pruned_loss=0.02962, over 1310242.41 frames.], batch size: 23, lr: 2.17e-04
+2022-04-30 18:44:30,965 INFO [train.py:763] (2/8) Epoch 35, batch 550, loss[loss=0.1741, simple_loss=0.2775, pruned_loss=0.0354, over 7428.00 frames.], tot_loss[loss=0.1602, simple_loss=0.261, pruned_loss=0.0297, over 1336759.64 frames.], batch size: 20, lr: 2.17e-04
+2022-04-30 18:45:37,224 INFO [train.py:763] (2/8) Epoch 35, batch 600, loss[loss=0.1677, simple_loss=0.2696, pruned_loss=0.03284, over 7210.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2593, pruned_loss=0.02929, over 1359436.77 frames.], batch size: 23, lr: 2.17e-04
+2022-04-30 18:46:44,897 INFO [train.py:763] (2/8) Epoch 35, batch 650, loss[loss=0.1449, simple_loss=0.2503, pruned_loss=0.01978, over 7149.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2585, pruned_loss=0.0291, over 1373800.13 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 18:47:52,732 INFO [train.py:763] (2/8) Epoch 35, batch 700, loss[loss=0.1414, simple_loss=0.2403, pruned_loss=0.02123, over 7260.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2584, pruned_loss=0.02936, over 1385139.39 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 18:48:58,269 INFO [train.py:763] (2/8) Epoch 35, batch 750, loss[loss=0.181, simple_loss=0.2762, pruned_loss=0.04291, over 7320.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2587, pruned_loss=0.02947, over 1384364.55 frames.], batch size: 20, lr: 2.17e-04
+2022-04-30 18:50:03,731 INFO [train.py:763] (2/8) Epoch 35, batch 800, loss[loss=0.175, simple_loss=0.279, pruned_loss=0.03547, over 7429.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02954, over 1392460.28 frames.], batch size: 21, lr: 2.17e-04
+2022-04-30 18:51:09,199 INFO [train.py:763] (2/8) Epoch 35, batch 850, loss[loss=0.1608, simple_loss=0.2683, pruned_loss=0.02669, over 7213.00 frames.], tot_loss[loss=0.159, simple_loss=0.2595, pruned_loss=0.02926, over 1394406.07 frames.], batch size: 21, lr: 2.17e-04
+2022-04-30 18:52:23,427 INFO [train.py:763] (2/8) Epoch 35, batch 900, loss[loss=0.1468, simple_loss=0.2483, pruned_loss=0.02263, over 6760.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2596, pruned_loss=0.02925, over 1401453.52 frames.], batch size: 31, lr: 2.17e-04
+2022-04-30 18:53:37,764 INFO [train.py:763] (2/8) Epoch 35, batch 950, loss[loss=0.1472, simple_loss=0.2437, pruned_loss=0.02538, over 7019.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2602, pruned_loss=0.02941, over 1405085.82 frames.], batch size: 16, lr: 2.17e-04
+2022-04-30 18:54:42,874 INFO [train.py:763] (2/8) Epoch 35, batch 1000, loss[loss=0.1535, simple_loss=0.2423, pruned_loss=0.03234, over 7275.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2598, pruned_loss=0.02893, over 1406528.21 frames.], batch size: 17, lr: 2.17e-04
+2022-04-30 18:55:57,239 INFO [train.py:763] (2/8) Epoch 35, batch 1050, loss[loss=0.1217, simple_loss=0.2191, pruned_loss=0.01218, over 7353.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2593, pruned_loss=0.02878, over 1407569.39 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 18:57:20,297 INFO [train.py:763] (2/8) Epoch 35, batch 1100, loss[loss=0.1736, simple_loss=0.2691, pruned_loss=0.03909, over 7211.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2596, pruned_loss=0.02942, over 1407820.34 frames.], batch size: 22, lr: 2.17e-04
+2022-04-30 18:58:25,984 INFO [train.py:763] (2/8) Epoch 35, batch 1150, loss[loss=0.1731, simple_loss=0.28, pruned_loss=0.03309, over 7277.00 frames.], tot_loss[loss=0.1589, simple_loss=0.259, pruned_loss=0.0294, over 1413367.47 frames.], batch size: 24, lr: 2.17e-04
+2022-04-30 18:59:32,074 INFO [train.py:763] (2/8) Epoch 35, batch 1200, loss[loss=0.1601, simple_loss=0.2562, pruned_loss=0.03203, over 7282.00 frames.], tot_loss[loss=0.1607, simple_loss=0.261, pruned_loss=0.03025, over 1408542.03 frames.], batch size: 17, lr: 2.17e-04
+2022-04-30 19:00:55,253 INFO [train.py:763] (2/8) Epoch 35, batch 1250, loss[loss=0.1602, simple_loss=0.2512, pruned_loss=0.03456, over 6993.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2592, pruned_loss=0.02956, over 1409872.38 frames.], batch size: 16, lr: 2.17e-04
+2022-04-30 19:02:00,722 INFO [train.py:763] (2/8) Epoch 35, batch 1300, loss[loss=0.1324, simple_loss=0.2278, pruned_loss=0.01847, over 7144.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2595, pruned_loss=0.02984, over 1413781.05 frames.], batch size: 17, lr: 2.17e-04
+2022-04-30 19:03:07,764 INFO [train.py:763] (2/8) Epoch 35, batch 1350, loss[loss=0.1462, simple_loss=0.2357, pruned_loss=0.02834, over 7271.00 frames.], tot_loss[loss=0.1592, simple_loss=0.259, pruned_loss=0.02969, over 1418763.60 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 19:04:12,911 INFO [train.py:763] (2/8) Epoch 35, batch 1400, loss[loss=0.1311, simple_loss=0.2241, pruned_loss=0.01907, over 6987.00 frames.], tot_loss[loss=0.16, simple_loss=0.2598, pruned_loss=0.03006, over 1417345.31 frames.], batch size: 16, lr: 2.17e-04
+2022-04-30 19:05:18,833 INFO [train.py:763] (2/8) Epoch 35, batch 1450, loss[loss=0.1522, simple_loss=0.2433, pruned_loss=0.03054, over 7238.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2598, pruned_loss=0.02981, over 1414769.15 frames.], batch size: 16, lr: 2.17e-04
+2022-04-30 19:06:24,725 INFO [train.py:763] (2/8) Epoch 35, batch 1500, loss[loss=0.1508, simple_loss=0.253, pruned_loss=0.02432, over 7322.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2603, pruned_loss=0.02962, over 1419434.46 frames.], batch size: 21, lr: 2.17e-04
+2022-04-30 19:07:30,577 INFO [train.py:763] (2/8) Epoch 35, batch 1550, loss[loss=0.1529, simple_loss=0.2614, pruned_loss=0.02225, over 7239.00 frames.], tot_loss[loss=0.1592, simple_loss=0.26, pruned_loss=0.02917, over 1420960.64 frames.], batch size: 20, lr: 2.17e-04
+2022-04-30 19:08:36,015 INFO [train.py:763] (2/8) Epoch 35, batch 1600, loss[loss=0.2133, simple_loss=0.3106, pruned_loss=0.05796, over 7376.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2595, pruned_loss=0.02913, over 1420761.95 frames.], batch size: 23, lr: 2.16e-04
+2022-04-30 19:09:42,622 INFO [train.py:763] (2/8) Epoch 35, batch 1650, loss[loss=0.1635, simple_loss=0.2742, pruned_loss=0.0264, over 7180.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2599, pruned_loss=0.02928, over 1421841.45 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:10:49,563 INFO [train.py:763] (2/8) Epoch 35, batch 1700, loss[loss=0.1663, simple_loss=0.276, pruned_loss=0.02826, over 7296.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2606, pruned_loss=0.02954, over 1424147.67 frames.], batch size: 25, lr: 2.16e-04
+2022-04-30 19:11:56,502 INFO [train.py:763] (2/8) Epoch 35, batch 1750, loss[loss=0.1493, simple_loss=0.2412, pruned_loss=0.02872, over 7278.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2608, pruned_loss=0.02969, over 1420124.15 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:13:03,547 INFO [train.py:763] (2/8) Epoch 35, batch 1800, loss[loss=0.1755, simple_loss=0.2762, pruned_loss=0.03738, over 7181.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2609, pruned_loss=0.02979, over 1422235.45 frames.], batch size: 23, lr: 2.16e-04
+2022-04-30 19:14:09,378 INFO [train.py:763] (2/8) Epoch 35, batch 1850, loss[loss=0.1591, simple_loss=0.2618, pruned_loss=0.02821, over 7113.00 frames.], tot_loss[loss=0.159, simple_loss=0.2598, pruned_loss=0.02911, over 1424748.12 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:15:15,149 INFO [train.py:763] (2/8) Epoch 35, batch 1900, loss[loss=0.1694, simple_loss=0.2755, pruned_loss=0.03165, over 6695.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2595, pruned_loss=0.02891, over 1424680.29 frames.], batch size: 31, lr: 2.16e-04
+2022-04-30 19:16:21,438 INFO [train.py:763] (2/8) Epoch 35, batch 1950, loss[loss=0.1534, simple_loss=0.2578, pruned_loss=0.02447, over 7236.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2594, pruned_loss=0.02915, over 1422693.79 frames.], batch size: 20, lr: 2.16e-04
+2022-04-30 19:17:27,459 INFO [train.py:763] (2/8) Epoch 35, batch 2000, loss[loss=0.1753, simple_loss=0.2646, pruned_loss=0.04299, over 7001.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2604, pruned_loss=0.0295, over 1420122.57 frames.], batch size: 16, lr: 2.16e-04
+2022-04-30 19:18:34,496 INFO [train.py:763] (2/8) Epoch 35, batch 2050, loss[loss=0.1812, simple_loss=0.2854, pruned_loss=0.03849, over 7319.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2608, pruned_loss=0.02975, over 1425112.84 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:19:40,350 INFO [train.py:763] (2/8) Epoch 35, batch 2100, loss[loss=0.1643, simple_loss=0.2678, pruned_loss=0.03041, over 7419.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2596, pruned_loss=0.02914, over 1423463.80 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:20:47,325 INFO [train.py:763] (2/8) Epoch 35, batch 2150, loss[loss=0.147, simple_loss=0.2438, pruned_loss=0.02508, over 7253.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2585, pruned_loss=0.02893, over 1425755.92 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:21:54,060 INFO [train.py:763] (2/8) Epoch 35, batch 2200, loss[loss=0.1357, simple_loss=0.2277, pruned_loss=0.02189, over 7412.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2583, pruned_loss=0.02889, over 1425072.45 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:23:01,260 INFO [train.py:763] (2/8) Epoch 35, batch 2250, loss[loss=0.1697, simple_loss=0.2783, pruned_loss=0.03055, over 7343.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2594, pruned_loss=0.0292, over 1421038.08 frames.], batch size: 22, lr: 2.16e-04
+2022-04-30 19:24:07,984 INFO [train.py:763] (2/8) Epoch 35, batch 2300, loss[loss=0.1364, simple_loss=0.2319, pruned_loss=0.02043, over 7132.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2585, pruned_loss=0.02898, over 1424564.04 frames.], batch size: 17, lr: 2.16e-04
+2022-04-30 19:25:12,947 INFO [train.py:763] (2/8) Epoch 35, batch 2350, loss[loss=0.1925, simple_loss=0.2858, pruned_loss=0.0496, over 5341.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2596, pruned_loss=0.02932, over 1423544.32 frames.], batch size: 52, lr: 2.16e-04
+2022-04-30 19:26:18,887 INFO [train.py:763] (2/8) Epoch 35, batch 2400, loss[loss=0.1486, simple_loss=0.2416, pruned_loss=0.02783, over 7410.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2587, pruned_loss=0.02886, over 1426195.56 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:27:24,045 INFO [train.py:763] (2/8) Epoch 35, batch 2450, loss[loss=0.1582, simple_loss=0.2457, pruned_loss=0.03541, over 7166.00 frames.], tot_loss[loss=0.1585, simple_loss=0.259, pruned_loss=0.02906, over 1422316.67 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:28:30,197 INFO [train.py:763] (2/8) Epoch 35, batch 2500, loss[loss=0.1675, simple_loss=0.2748, pruned_loss=0.03009, over 7141.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2586, pruned_loss=0.02886, over 1425782.84 frames.], batch size: 20, lr: 2.16e-04
+2022-04-30 19:29:36,781 INFO [train.py:763] (2/8) Epoch 35, batch 2550, loss[loss=0.1575, simple_loss=0.2604, pruned_loss=0.02728, over 7359.00 frames.], tot_loss[loss=0.159, simple_loss=0.2595, pruned_loss=0.02927, over 1423146.26 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:30:41,922 INFO [train.py:763] (2/8) Epoch 35, batch 2600, loss[loss=0.1482, simple_loss=0.2536, pruned_loss=0.0214, over 7152.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2591, pruned_loss=0.02897, over 1423968.89 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:31:47,693 INFO [train.py:763] (2/8) Epoch 35, batch 2650, loss[loss=0.201, simple_loss=0.3006, pruned_loss=0.05072, over 5026.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2599, pruned_loss=0.02935, over 1422196.18 frames.], batch size: 52, lr: 2.16e-04
+2022-04-30 19:32:53,212 INFO [train.py:763] (2/8) Epoch 35, batch 2700, loss[loss=0.1665, simple_loss=0.2678, pruned_loss=0.03259, over 7316.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2593, pruned_loss=0.02919, over 1423269.00 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:33:59,267 INFO [train.py:763] (2/8) Epoch 35, batch 2750, loss[loss=0.1702, simple_loss=0.2742, pruned_loss=0.03312, over 7102.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2598, pruned_loss=0.0293, over 1425744.48 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:35:05,455 INFO [train.py:763] (2/8) Epoch 35, batch 2800, loss[loss=0.178, simple_loss=0.2733, pruned_loss=0.04135, over 7208.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2584, pruned_loss=0.02925, over 1426792.38 frames.], batch size: 22, lr: 2.16e-04
+2022-04-30 19:36:12,138 INFO [train.py:763] (2/8) Epoch 35, batch 2850, loss[loss=0.1538, simple_loss=0.2407, pruned_loss=0.03338, over 7274.00 frames.], tot_loss[loss=0.158, simple_loss=0.2579, pruned_loss=0.02907, over 1427556.94 frames.], batch size: 17, lr: 2.16e-04
+2022-04-30 19:37:18,074 INFO [train.py:763] (2/8) Epoch 35, batch 2900, loss[loss=0.1587, simple_loss=0.2645, pruned_loss=0.02645, over 7248.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2573, pruned_loss=0.02897, over 1426981.48 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:38:23,358 INFO [train.py:763] (2/8) Epoch 35, batch 2950, loss[loss=0.135, simple_loss=0.2338, pruned_loss=0.01813, over 7163.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2584, pruned_loss=0.02909, over 1424886.52 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:39:28,869 INFO [train.py:763] (2/8) Epoch 35, batch 3000, loss[loss=0.1647, simple_loss=0.2625, pruned_loss=0.03345, over 7171.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2602, pruned_loss=0.02996, over 1421888.67 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:39:28,870 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 19:39:43,929 INFO [train.py:792] (2/8) Epoch 35, validation: loss=0.1681, simple_loss=0.2634, pruned_loss=0.03644, over 698248.00 frames.
+2022-04-30 19:40:49,414 INFO [train.py:763] (2/8) Epoch 35, batch 3050, loss[loss=0.1748, simple_loss=0.296, pruned_loss=0.0268, over 7318.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2605, pruned_loss=0.02999, over 1424563.51 frames.], batch size: 24, lr: 2.16e-04
+2022-04-30 19:41:55,471 INFO [train.py:763] (2/8) Epoch 35, batch 3100, loss[loss=0.2119, simple_loss=0.3036, pruned_loss=0.06011, over 7312.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2612, pruned_loss=0.03028, over 1428912.29 frames.], batch size: 25, lr: 2.15e-04
+2022-04-30 19:43:02,574 INFO [train.py:763] (2/8) Epoch 35, batch 3150, loss[loss=0.1872, simple_loss=0.2844, pruned_loss=0.04504, over 7354.00 frames.], tot_loss[loss=0.1607, simple_loss=0.261, pruned_loss=0.03016, over 1427309.15 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 19:44:09,424 INFO [train.py:763] (2/8) Epoch 35, batch 3200, loss[loss=0.133, simple_loss=0.2252, pruned_loss=0.02045, over 7141.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2609, pruned_loss=0.03034, over 1421835.74 frames.], batch size: 17, lr: 2.15e-04
+2022-04-30 19:45:15,565 INFO [train.py:763] (2/8) Epoch 35, batch 3250, loss[loss=0.1843, simple_loss=0.2816, pruned_loss=0.04353, over 5223.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03027, over 1419749.55 frames.], batch size: 52, lr: 2.15e-04
+2022-04-30 19:46:21,010 INFO [train.py:763] (2/8) Epoch 35, batch 3300, loss[loss=0.1734, simple_loss=0.2769, pruned_loss=0.03491, over 7203.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03025, over 1423134.20 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 19:47:26,297 INFO [train.py:763] (2/8) Epoch 35, batch 3350, loss[loss=0.1716, simple_loss=0.2748, pruned_loss=0.03422, over 7202.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2604, pruned_loss=0.03021, over 1427587.56 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 19:48:32,219 INFO [train.py:763] (2/8) Epoch 35, batch 3400, loss[loss=0.1442, simple_loss=0.2408, pruned_loss=0.02378, over 7252.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2594, pruned_loss=0.02999, over 1425806.36 frames.], batch size: 19, lr: 2.15e-04
+2022-04-30 19:49:37,615 INFO [train.py:763] (2/8) Epoch 35, batch 3450, loss[loss=0.1552, simple_loss=0.2387, pruned_loss=0.03586, over 7250.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2597, pruned_loss=0.03001, over 1423215.21 frames.], batch size: 17, lr: 2.15e-04
+2022-04-30 19:50:43,215 INFO [train.py:763] (2/8) Epoch 35, batch 3500, loss[loss=0.1731, simple_loss=0.2834, pruned_loss=0.03143, over 7412.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2592, pruned_loss=0.02975, over 1420463.86 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 19:51:48,954 INFO [train.py:763] (2/8) Epoch 35, batch 3550, loss[loss=0.1702, simple_loss=0.2763, pruned_loss=0.03201, over 7093.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2599, pruned_loss=0.03023, over 1423829.25 frames.], batch size: 28, lr: 2.15e-04
+2022-04-30 19:52:54,515 INFO [train.py:763] (2/8) Epoch 35, batch 3600, loss[loss=0.2066, simple_loss=0.2919, pruned_loss=0.0606, over 7293.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2605, pruned_loss=0.03034, over 1421478.69 frames.], batch size: 25, lr: 2.15e-04
+2022-04-30 19:54:00,479 INFO [train.py:763] (2/8) Epoch 35, batch 3650, loss[loss=0.1697, simple_loss=0.273, pruned_loss=0.03319, over 7285.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.03047, over 1423266.42 frames.], batch size: 24, lr: 2.15e-04
+2022-04-30 19:55:05,852 INFO [train.py:763] (2/8) Epoch 35, batch 3700, loss[loss=0.1523, simple_loss=0.2624, pruned_loss=0.02117, over 7105.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2605, pruned_loss=0.0304, over 1426170.28 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 19:56:11,426 INFO [train.py:763] (2/8) Epoch 35, batch 3750, loss[loss=0.1795, simple_loss=0.2878, pruned_loss=0.03557, over 7330.00 frames.], tot_loss[loss=0.161, simple_loss=0.2609, pruned_loss=0.03053, over 1424924.80 frames.], batch size: 22, lr: 2.15e-04
+2022-04-30 19:57:16,643 INFO [train.py:763] (2/8) Epoch 35, batch 3800, loss[loss=0.1552, simple_loss=0.2489, pruned_loss=0.03075, over 7348.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2614, pruned_loss=0.0306, over 1427422.31 frames.], batch size: 19, lr: 2.15e-04
+2022-04-30 19:58:21,844 INFO [train.py:763] (2/8) Epoch 35, batch 3850, loss[loss=0.1441, simple_loss=0.2403, pruned_loss=0.02394, over 7011.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2608, pruned_loss=0.03046, over 1422987.59 frames.], batch size: 16, lr: 2.15e-04
+2022-04-30 19:59:27,365 INFO [train.py:763] (2/8) Epoch 35, batch 3900, loss[loss=0.1732, simple_loss=0.2687, pruned_loss=0.03884, over 7193.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2601, pruned_loss=0.03019, over 1425432.97 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 20:00:33,648 INFO [train.py:763] (2/8) Epoch 35, batch 3950, loss[loss=0.1448, simple_loss=0.2531, pruned_loss=0.01823, over 6675.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.03017, over 1423259.12 frames.], batch size: 31, lr: 2.15e-04
+2022-04-30 20:01:41,040 INFO [train.py:763] (2/8) Epoch 35, batch 4000, loss[loss=0.1786, simple_loss=0.2796, pruned_loss=0.03879, over 7081.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2614, pruned_loss=0.03023, over 1423388.22 frames.], batch size: 28, lr: 2.15e-04
+2022-04-30 20:02:46,169 INFO [train.py:763] (2/8) Epoch 35, batch 4050, loss[loss=0.1648, simple_loss=0.2691, pruned_loss=0.03024, over 7222.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2612, pruned_loss=0.02987, over 1427087.35 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 20:03:51,643 INFO [train.py:763] (2/8) Epoch 35, batch 4100, loss[loss=0.1425, simple_loss=0.2333, pruned_loss=0.0259, over 7105.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2611, pruned_loss=0.02983, over 1426583.15 frames.], batch size: 17, lr: 2.15e-04
+2022-04-30 20:04:57,462 INFO [train.py:763] (2/8) Epoch 35, batch 4150, loss[loss=0.1797, simple_loss=0.2939, pruned_loss=0.03278, over 7207.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2605, pruned_loss=0.02996, over 1419263.82 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 20:06:03,148 INFO [train.py:763] (2/8) Epoch 35, batch 4200, loss[loss=0.1429, simple_loss=0.2438, pruned_loss=0.02101, over 7234.00 frames.], tot_loss[loss=0.16, simple_loss=0.2601, pruned_loss=0.02995, over 1417820.85 frames.], batch size: 20, lr: 2.15e-04
+2022-04-30 20:07:09,098 INFO [train.py:763] (2/8) Epoch 35, batch 4250, loss[loss=0.1642, simple_loss=0.2711, pruned_loss=0.02867, over 7210.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2592, pruned_loss=0.02976, over 1416557.41 frames.], batch size: 22, lr: 2.15e-04
+2022-04-30 20:08:14,294 INFO [train.py:763] (2/8) Epoch 35, batch 4300, loss[loss=0.1586, simple_loss=0.2698, pruned_loss=0.0237, over 7202.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2585, pruned_loss=0.02931, over 1412221.34 frames.], batch size: 22, lr: 2.15e-04
+2022-04-30 20:09:20,404 INFO [train.py:763] (2/8) Epoch 35, batch 4350, loss[loss=0.1639, simple_loss=0.2641, pruned_loss=0.03182, over 7423.00 frames.], tot_loss[loss=0.1585, simple_loss=0.258, pruned_loss=0.02946, over 1411650.86 frames.], batch size: 20, lr: 2.15e-04
+2022-04-30 20:10:26,455 INFO [train.py:763] (2/8) Epoch 35, batch 4400, loss[loss=0.1608, simple_loss=0.2613, pruned_loss=0.03011, over 7348.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2578, pruned_loss=0.02897, over 1416189.70 frames.], batch size: 19, lr: 2.15e-04
+2022-04-30 20:11:33,063 INFO [train.py:763] (2/8) Epoch 35, batch 4450, loss[loss=0.1759, simple_loss=0.2849, pruned_loss=0.03351, over 7217.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2571, pruned_loss=0.02873, over 1406242.21 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 20:12:39,698 INFO [train.py:763] (2/8) Epoch 35, batch 4500, loss[loss=0.1553, simple_loss=0.2616, pruned_loss=0.02448, over 7229.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2568, pruned_loss=0.02895, over 1394879.93 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 20:13:46,212 INFO [train.py:763] (2/8) Epoch 35, batch 4550, loss[loss=0.1593, simple_loss=0.2555, pruned_loss=0.03153, over 7247.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2579, pruned_loss=0.02992, over 1358056.91 frames.], batch size: 19, lr: 2.15e-04
+2022-04-30 20:15:13,844 INFO [train.py:763] (2/8) Epoch 36, batch 0, loss[loss=0.1603, simple_loss=0.259, pruned_loss=0.03082, over 7331.00 frames.], tot_loss[loss=0.1603, simple_loss=0.259, pruned_loss=0.03082, over 7331.00 frames.], batch size: 22, lr: 2.12e-04
+2022-04-30 20:16:19,177 INFO [train.py:763] (2/8) Epoch 36, batch 50, loss[loss=0.1281, simple_loss=0.2285, pruned_loss=0.01391, over 7067.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2591, pruned_loss=0.02939, over 322284.82 frames.], batch size: 18, lr: 2.12e-04
+2022-04-30 20:17:24,378 INFO [train.py:763] (2/8) Epoch 36, batch 100, loss[loss=0.1415, simple_loss=0.2454, pruned_loss=0.01879, over 7328.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2605, pruned_loss=0.02982, over 567244.84 frames.], batch size: 20, lr: 2.12e-04
+2022-04-30 20:18:29,495 INFO [train.py:763] (2/8) Epoch 36, batch 150, loss[loss=0.1619, simple_loss=0.2669, pruned_loss=0.02846, over 7077.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2606, pruned_loss=0.02923, over 754997.03 frames.], batch size: 28, lr: 2.11e-04
+2022-04-30 20:19:34,472 INFO [train.py:763] (2/8) Epoch 36, batch 200, loss[loss=0.1633, simple_loss=0.2759, pruned_loss=0.02538, over 7319.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2622, pruned_loss=0.02996, over 906404.01 frames.], batch size: 21, lr: 2.11e-04
+2022-04-30 20:20:39,729 INFO [train.py:763] (2/8) Epoch 36, batch 250, loss[loss=0.1526, simple_loss=0.2474, pruned_loss=0.02887, over 7255.00 frames.], tot_loss[loss=0.1599, simple_loss=0.261, pruned_loss=0.0294, over 1018027.53 frames.], batch size: 19, lr: 2.11e-04
+2022-04-30 20:21:45,223 INFO [train.py:763] (2/8) Epoch 36, batch 300, loss[loss=0.1803, simple_loss=0.2845, pruned_loss=0.03804, over 7333.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2611, pruned_loss=0.02971, over 1104636.60 frames.], batch size: 22, lr: 2.11e-04
+2022-04-30 20:22:50,515 INFO [train.py:763] (2/8) Epoch 36, batch 350, loss[loss=0.1547, simple_loss=0.2533, pruned_loss=0.02811, over 7162.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2608, pruned_loss=0.02993, over 1173808.68 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:23:55,932 INFO [train.py:763] (2/8) Epoch 36, batch 400, loss[loss=0.1577, simple_loss=0.2651, pruned_loss=0.02516, over 7235.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2599, pruned_loss=0.0296, over 1233468.99 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:25:01,046 INFO [train.py:763] (2/8) Epoch 36, batch 450, loss[loss=0.1618, simple_loss=0.2695, pruned_loss=0.02709, over 7154.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2602, pruned_loss=0.02933, over 1277825.87 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:26:07,074 INFO [train.py:763] (2/8) Epoch 36, batch 500, loss[loss=0.1531, simple_loss=0.2547, pruned_loss=0.02573, over 7242.00 frames.], tot_loss[loss=0.16, simple_loss=0.2605, pruned_loss=0.02972, over 1307404.17 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:27:14,405 INFO [train.py:763] (2/8) Epoch 36, batch 550, loss[loss=0.1319, simple_loss=0.228, pruned_loss=0.01787, over 7065.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2606, pruned_loss=0.02977, over 1324154.29 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:28:22,076 INFO [train.py:763] (2/8) Epoch 36, batch 600, loss[loss=0.1461, simple_loss=0.2458, pruned_loss=0.02323, over 7415.00 frames.], tot_loss[loss=0.1589, simple_loss=0.259, pruned_loss=0.02935, over 1348834.06 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:29:29,896 INFO [train.py:763] (2/8) Epoch 36, batch 650, loss[loss=0.1528, simple_loss=0.239, pruned_loss=0.03331, over 7130.00 frames.], tot_loss[loss=0.158, simple_loss=0.2578, pruned_loss=0.0291, over 1369114.92 frames.], batch size: 17, lr: 2.11e-04
+2022-04-30 20:30:35,967 INFO [train.py:763] (2/8) Epoch 36, batch 700, loss[loss=0.1513, simple_loss=0.2544, pruned_loss=0.02415, over 7229.00 frames.], tot_loss[loss=0.1581, simple_loss=0.258, pruned_loss=0.0291, over 1381428.33 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:31:41,361 INFO [train.py:763] (2/8) Epoch 36, batch 750, loss[loss=0.1512, simple_loss=0.2464, pruned_loss=0.028, over 7168.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2581, pruned_loss=0.02899, over 1390713.46 frames.], batch size: 19, lr: 2.11e-04
+2022-04-30 20:32:47,561 INFO [train.py:763] (2/8) Epoch 36, batch 800, loss[loss=0.1487, simple_loss=0.2436, pruned_loss=0.02693, over 7418.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2583, pruned_loss=0.02902, over 1400772.15 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:33:53,515 INFO [train.py:763] (2/8) Epoch 36, batch 850, loss[loss=0.1708, simple_loss=0.2519, pruned_loss=0.04483, over 7259.00 frames.], tot_loss[loss=0.159, simple_loss=0.2593, pruned_loss=0.02938, over 1400201.90 frames.], batch size: 19, lr: 2.11e-04
+2022-04-30 20:34:59,124 INFO [train.py:763] (2/8) Epoch 36, batch 900, loss[loss=0.1493, simple_loss=0.2414, pruned_loss=0.02861, over 7063.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2587, pruned_loss=0.02909, over 1408186.33 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:36:04,435 INFO [train.py:763] (2/8) Epoch 36, batch 950, loss[loss=0.1414, simple_loss=0.2312, pruned_loss=0.0258, over 7280.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2588, pruned_loss=0.02932, over 1411540.92 frames.], batch size: 17, lr: 2.11e-04
+2022-04-30 20:37:09,727 INFO [train.py:763] (2/8) Epoch 36, batch 1000, loss[loss=0.1735, simple_loss=0.2714, pruned_loss=0.03783, over 6733.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.02923, over 1413946.84 frames.], batch size: 31, lr: 2.11e-04
+2022-04-30 20:38:15,270 INFO [train.py:763] (2/8) Epoch 36, batch 1050, loss[loss=0.1701, simple_loss=0.2635, pruned_loss=0.03834, over 7369.00 frames.], tot_loss[loss=0.1583, simple_loss=0.258, pruned_loss=0.02932, over 1418219.17 frames.], batch size: 23, lr: 2.11e-04
+2022-04-30 20:39:20,503 INFO [train.py:763] (2/8) Epoch 36, batch 1100, loss[loss=0.1478, simple_loss=0.2472, pruned_loss=0.02421, over 7226.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2569, pruned_loss=0.02876, over 1418811.26 frames.], batch size: 21, lr: 2.11e-04
+2022-04-30 20:40:26,421 INFO [train.py:763] (2/8) Epoch 36, batch 1150, loss[loss=0.1594, simple_loss=0.2609, pruned_loss=0.02896, over 4947.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2568, pruned_loss=0.02876, over 1417276.48 frames.], batch size: 52, lr: 2.11e-04
+2022-04-30 20:41:32,752 INFO [train.py:763] (2/8) Epoch 36, batch 1200, loss[loss=0.1492, simple_loss=0.2553, pruned_loss=0.02158, over 7137.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2591, pruned_loss=0.0292, over 1419623.76 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:42:37,807 INFO [train.py:763] (2/8) Epoch 36, batch 1250, loss[loss=0.1836, simple_loss=0.2773, pruned_loss=0.04494, over 7197.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2598, pruned_loss=0.02892, over 1419482.03 frames.], batch size: 22, lr: 2.11e-04
+2022-04-30 20:43:42,980 INFO [train.py:763] (2/8) Epoch 36, batch 1300, loss[loss=0.1392, simple_loss=0.2348, pruned_loss=0.02175, over 7135.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2597, pruned_loss=0.02897, over 1421477.66 frames.], batch size: 17, lr: 2.11e-04
+2022-04-30 20:44:48,208 INFO [train.py:763] (2/8) Epoch 36, batch 1350, loss[loss=0.1508, simple_loss=0.2517, pruned_loss=0.02498, over 7067.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2599, pruned_loss=0.02912, over 1417772.84 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:45:54,979 INFO [train.py:763] (2/8) Epoch 36, batch 1400, loss[loss=0.1507, simple_loss=0.2413, pruned_loss=0.03001, over 6998.00 frames.], tot_loss[loss=0.159, simple_loss=0.2595, pruned_loss=0.02925, over 1417202.77 frames.], batch size: 16, lr: 2.11e-04
+2022-04-30 20:47:00,115 INFO [train.py:763] (2/8) Epoch 36, batch 1450, loss[loss=0.1749, simple_loss=0.2798, pruned_loss=0.03504, over 7285.00 frames.], tot_loss[loss=0.159, simple_loss=0.2598, pruned_loss=0.02914, over 1419383.77 frames.], batch size: 24, lr: 2.11e-04
+2022-04-30 20:48:05,222 INFO [train.py:763] (2/8) Epoch 36, batch 1500, loss[loss=0.1807, simple_loss=0.2906, pruned_loss=0.0354, over 7263.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2604, pruned_loss=0.02945, over 1415601.09 frames.], batch size: 24, lr: 2.11e-04
+2022-04-30 20:49:10,948 INFO [train.py:763] (2/8) Epoch 36, batch 1550, loss[loss=0.1724, simple_loss=0.2686, pruned_loss=0.03815, over 6767.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2602, pruned_loss=0.02973, over 1411407.52 frames.], batch size: 31, lr: 2.11e-04
+2022-04-30 20:50:16,846 INFO [train.py:763] (2/8) Epoch 36, batch 1600, loss[loss=0.1698, simple_loss=0.2706, pruned_loss=0.03451, over 7374.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2586, pruned_loss=0.02917, over 1412752.02 frames.], batch size: 23, lr: 2.11e-04
+2022-04-30 20:51:24,010 INFO [train.py:763] (2/8) Epoch 36, batch 1650, loss[loss=0.1692, simple_loss=0.2872, pruned_loss=0.02559, over 7202.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2585, pruned_loss=0.02882, over 1415518.61 frames.], batch size: 22, lr: 2.11e-04
+2022-04-30 20:52:38,228 INFO [train.py:763] (2/8) Epoch 36, batch 1700, loss[loss=0.1557, simple_loss=0.2605, pruned_loss=0.02551, over 7156.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2594, pruned_loss=0.02916, over 1414229.29 frames.], batch size: 19, lr: 2.11e-04
+2022-04-30 20:53:43,581 INFO [train.py:763] (2/8) Epoch 36, batch 1750, loss[loss=0.1642, simple_loss=0.2604, pruned_loss=0.03396, over 7356.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2593, pruned_loss=0.0295, over 1407490.92 frames.], batch size: 19, lr: 2.10e-04
+2022-04-30 20:54:48,731 INFO [train.py:763] (2/8) Epoch 36, batch 1800, loss[loss=0.1802, simple_loss=0.2857, pruned_loss=0.03735, over 7302.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2601, pruned_loss=0.02952, over 1409301.87 frames.], batch size: 24, lr: 2.10e-04
+2022-04-30 20:55:54,034 INFO [train.py:763] (2/8) Epoch 36, batch 1850, loss[loss=0.152, simple_loss=0.2503, pruned_loss=0.02681, over 7247.00 frames.], tot_loss[loss=0.159, simple_loss=0.2595, pruned_loss=0.02926, over 1410578.48 frames.], batch size: 19, lr: 2.10e-04
+2022-04-30 20:56:59,657 INFO [train.py:763] (2/8) Epoch 36, batch 1900, loss[loss=0.172, simple_loss=0.2718, pruned_loss=0.0361, over 6808.00 frames.], tot_loss[loss=0.16, simple_loss=0.2605, pruned_loss=0.02975, over 1416217.34 frames.], batch size: 31, lr: 2.10e-04
+2022-04-30 20:58:07,232 INFO [train.py:763] (2/8) Epoch 36, batch 1950, loss[loss=0.1609, simple_loss=0.2733, pruned_loss=0.02431, over 7224.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2599, pruned_loss=0.02964, over 1419731.93 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 20:59:14,629 INFO [train.py:763] (2/8) Epoch 36, batch 2000, loss[loss=0.171, simple_loss=0.2784, pruned_loss=0.03178, over 7405.00 frames.], tot_loss[loss=0.1597, simple_loss=0.26, pruned_loss=0.02968, over 1416581.56 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 21:00:22,192 INFO [train.py:763] (2/8) Epoch 36, batch 2050, loss[loss=0.1668, simple_loss=0.2758, pruned_loss=0.02887, over 7243.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2598, pruned_loss=0.02951, over 1420473.87 frames.], batch size: 20, lr: 2.10e-04
+2022-04-30 21:01:28,529 INFO [train.py:763] (2/8) Epoch 36, batch 2100, loss[loss=0.1601, simple_loss=0.2677, pruned_loss=0.02626, over 7144.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2591, pruned_loss=0.02941, over 1420920.25 frames.], batch size: 20, lr: 2.10e-04
+2022-04-30 21:02:35,085 INFO [train.py:763] (2/8) Epoch 36, batch 2150, loss[loss=0.157, simple_loss=0.2647, pruned_loss=0.02465, over 7412.00 frames.], tot_loss[loss=0.1591, simple_loss=0.259, pruned_loss=0.02955, over 1418795.77 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 21:03:42,381 INFO [train.py:763] (2/8) Epoch 36, batch 2200, loss[loss=0.1512, simple_loss=0.2561, pruned_loss=0.0232, over 7252.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2579, pruned_loss=0.02896, over 1420930.13 frames.], batch size: 19, lr: 2.10e-04
+2022-04-30 21:04:49,050 INFO [train.py:763] (2/8) Epoch 36, batch 2250, loss[loss=0.1623, simple_loss=0.2654, pruned_loss=0.02956, over 7141.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2591, pruned_loss=0.02939, over 1421338.91 frames.], batch size: 20, lr: 2.10e-04
+2022-04-30 21:05:54,010 INFO [train.py:763] (2/8) Epoch 36, batch 2300, loss[loss=0.17, simple_loss=0.2802, pruned_loss=0.02991, over 7201.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2592, pruned_loss=0.02909, over 1419774.42 frames.], batch size: 23, lr: 2.10e-04
+2022-04-30 21:06:59,111 INFO [train.py:763] (2/8) Epoch 36, batch 2350, loss[loss=0.1234, simple_loss=0.2131, pruned_loss=0.01689, over 7284.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2596, pruned_loss=0.02926, over 1413395.86 frames.], batch size: 17, lr: 2.10e-04
+2022-04-30 21:08:06,478 INFO [train.py:763] (2/8) Epoch 36, batch 2400, loss[loss=0.195, simple_loss=0.2943, pruned_loss=0.04783, over 7318.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2593, pruned_loss=0.02913, over 1419472.28 frames.], batch size: 25, lr: 2.10e-04
+2022-04-30 21:09:12,589 INFO [train.py:763] (2/8) Epoch 36, batch 2450, loss[loss=0.1508, simple_loss=0.2519, pruned_loss=0.02481, over 7145.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2588, pruned_loss=0.02914, over 1424762.10 frames.], batch size: 26, lr: 2.10e-04
+2022-04-30 21:10:36,028 INFO [train.py:763] (2/8) Epoch 36, batch 2500, loss[loss=0.134, simple_loss=0.232, pruned_loss=0.01803, over 7161.00 frames.], tot_loss[loss=0.1582, simple_loss=0.258, pruned_loss=0.02925, over 1427659.56 frames.], batch size: 19, lr: 2.10e-04
+2022-04-30 21:11:41,252 INFO [train.py:763] (2/8) Epoch 36, batch 2550, loss[loss=0.1812, simple_loss=0.2839, pruned_loss=0.03923, over 7290.00 frames.], tot_loss[loss=0.158, simple_loss=0.2578, pruned_loss=0.02913, over 1427961.69 frames.], batch size: 24, lr: 2.10e-04
+2022-04-30 21:12:55,221 INFO [train.py:763] (2/8) Epoch 36, batch 2600, loss[loss=0.1261, simple_loss=0.2212, pruned_loss=0.01553, over 7223.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2583, pruned_loss=0.0291, over 1425275.13 frames.], batch size: 16, lr: 2.10e-04
+2022-04-30 21:14:18,380 INFO [train.py:763] (2/8) Epoch 36, batch 2650, loss[loss=0.1872, simple_loss=0.2905, pruned_loss=0.04194, over 7206.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2591, pruned_loss=0.02952, over 1428325.28 frames.], batch size: 22, lr: 2.10e-04
+2022-04-30 21:15:32,419 INFO [train.py:763] (2/8) Epoch 36, batch 2700, loss[loss=0.155, simple_loss=0.268, pruned_loss=0.02099, over 6473.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2588, pruned_loss=0.02937, over 1424276.53 frames.], batch size: 38, lr: 2.10e-04
+2022-04-30 21:16:46,237 INFO [train.py:763] (2/8) Epoch 36, batch 2750, loss[loss=0.1767, simple_loss=0.2754, pruned_loss=0.03906, over 5115.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2589, pruned_loss=0.02909, over 1425226.29 frames.], batch size: 52, lr: 2.10e-04
+2022-04-30 21:17:52,032 INFO [train.py:763] (2/8) Epoch 36, batch 2800, loss[loss=0.1459, simple_loss=0.2433, pruned_loss=0.0242, over 7278.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2585, pruned_loss=0.0291, over 1429508.95 frames.], batch size: 18, lr: 2.10e-04
+2022-04-30 21:19:07,512 INFO [train.py:763] (2/8) Epoch 36, batch 2850, loss[loss=0.1625, simple_loss=0.2794, pruned_loss=0.02277, over 6360.00 frames.], tot_loss[loss=0.1588, simple_loss=0.259, pruned_loss=0.0293, over 1427133.80 frames.], batch size: 37, lr: 2.10e-04
+2022-04-30 21:20:12,991 INFO [train.py:763] (2/8) Epoch 36, batch 2900, loss[loss=0.153, simple_loss=0.2382, pruned_loss=0.03391, over 6980.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2589, pruned_loss=0.02923, over 1427374.69 frames.], batch size: 16, lr: 2.10e-04
+2022-04-30 21:21:20,750 INFO [train.py:763] (2/8) Epoch 36, batch 2950, loss[loss=0.1516, simple_loss=0.2548, pruned_loss=0.02419, over 7429.00 frames.], tot_loss[loss=0.159, simple_loss=0.259, pruned_loss=0.02949, over 1423386.94 frames.], batch size: 20, lr: 2.10e-04
+2022-04-30 21:22:27,896 INFO [train.py:763] (2/8) Epoch 36, batch 3000, loss[loss=0.1537, simple_loss=0.2568, pruned_loss=0.02535, over 7219.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2596, pruned_loss=0.0298, over 1419886.09 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 21:22:27,897 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 21:22:43,066 INFO [train.py:792] (2/8) Epoch 36, validation: loss=0.1683, simple_loss=0.2628, pruned_loss=0.03692, over 698248.00 frames.
+2022-04-30 21:23:48,278 INFO [train.py:763] (2/8) Epoch 36, batch 3050, loss[loss=0.1392, simple_loss=0.2277, pruned_loss=0.02534, over 6783.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2602, pruned_loss=0.02998, over 1418326.74 frames.], batch size: 15, lr: 2.10e-04
+2022-04-30 21:24:54,038 INFO [train.py:763] (2/8) Epoch 36, batch 3100, loss[loss=0.1628, simple_loss=0.2558, pruned_loss=0.03486, over 7063.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2602, pruned_loss=0.02981, over 1416971.15 frames.], batch size: 18, lr: 2.10e-04
+2022-04-30 21:26:01,265 INFO [train.py:763] (2/8) Epoch 36, batch 3150, loss[loss=0.1223, simple_loss=0.2117, pruned_loss=0.0165, over 7004.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2594, pruned_loss=0.02958, over 1416484.89 frames.], batch size: 16, lr: 2.10e-04
+2022-04-30 21:27:07,745 INFO [train.py:763] (2/8) Epoch 36, batch 3200, loss[loss=0.1578, simple_loss=0.2596, pruned_loss=0.028, over 5046.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2592, pruned_loss=0.02949, over 1417686.64 frames.], batch size: 52, lr: 2.10e-04
+2022-04-30 21:28:14,746 INFO [train.py:763] (2/8) Epoch 36, batch 3250, loss[loss=0.1577, simple_loss=0.2598, pruned_loss=0.02787, over 7210.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2589, pruned_loss=0.02922, over 1417649.10 frames.], batch size: 22, lr: 2.10e-04
+2022-04-30 21:29:20,182 INFO [train.py:763] (2/8) Epoch 36, batch 3300, loss[loss=0.1783, simple_loss=0.2827, pruned_loss=0.03696, over 7411.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2596, pruned_loss=0.02941, over 1415340.07 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 21:30:25,143 INFO [train.py:763] (2/8) Epoch 36, batch 3350, loss[loss=0.1657, simple_loss=0.2713, pruned_loss=0.0301, over 7395.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2604, pruned_loss=0.02968, over 1410829.89 frames.], batch size: 23, lr: 2.09e-04
+2022-04-30 21:31:31,783 INFO [train.py:763] (2/8) Epoch 36, batch 3400, loss[loss=0.1296, simple_loss=0.2169, pruned_loss=0.02108, over 7150.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2598, pruned_loss=0.02988, over 1415826.31 frames.], batch size: 17, lr: 2.09e-04
+2022-04-30 21:32:37,217 INFO [train.py:763] (2/8) Epoch 36, batch 3450, loss[loss=0.1515, simple_loss=0.2404, pruned_loss=0.03128, over 7286.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2588, pruned_loss=0.02953, over 1419137.51 frames.], batch size: 17, lr: 2.09e-04
+2022-04-30 21:33:42,447 INFO [train.py:763] (2/8) Epoch 36, batch 3500, loss[loss=0.1378, simple_loss=0.2385, pruned_loss=0.0186, over 7361.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2592, pruned_loss=0.02954, over 1416984.47 frames.], batch size: 19, lr: 2.09e-04
+2022-04-30 21:34:47,626 INFO [train.py:763] (2/8) Epoch 36, batch 3550, loss[loss=0.1651, simple_loss=0.2538, pruned_loss=0.03822, over 7230.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2588, pruned_loss=0.02939, over 1414341.88 frames.], batch size: 16, lr: 2.09e-04
+2022-04-30 21:35:54,816 INFO [train.py:763] (2/8) Epoch 36, batch 3600, loss[loss=0.1506, simple_loss=0.2423, pruned_loss=0.02948, over 6992.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2579, pruned_loss=0.0293, over 1420720.26 frames.], batch size: 16, lr: 2.09e-04
+2022-04-30 21:37:01,772 INFO [train.py:763] (2/8) Epoch 36, batch 3650, loss[loss=0.1509, simple_loss=0.2595, pruned_loss=0.02119, over 7154.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2579, pruned_loss=0.02923, over 1423132.66 frames.], batch size: 19, lr: 2.09e-04
+2022-04-30 21:38:08,982 INFO [train.py:763] (2/8) Epoch 36, batch 3700, loss[loss=0.1496, simple_loss=0.2561, pruned_loss=0.02155, over 7232.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2575, pruned_loss=0.02921, over 1426687.22 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:39:14,212 INFO [train.py:763] (2/8) Epoch 36, batch 3750, loss[loss=0.1535, simple_loss=0.2594, pruned_loss=0.02384, over 7289.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2588, pruned_loss=0.02926, over 1423691.82 frames.], batch size: 24, lr: 2.09e-04
+2022-04-30 21:40:19,601 INFO [train.py:763] (2/8) Epoch 36, batch 3800, loss[loss=0.1323, simple_loss=0.2263, pruned_loss=0.01918, over 7283.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2583, pruned_loss=0.0291, over 1425198.46 frames.], batch size: 17, lr: 2.09e-04
+2022-04-30 21:41:25,002 INFO [train.py:763] (2/8) Epoch 36, batch 3850, loss[loss=0.1836, simple_loss=0.2909, pruned_loss=0.03816, over 5298.00 frames.], tot_loss[loss=0.159, simple_loss=0.259, pruned_loss=0.02952, over 1424145.90 frames.], batch size: 53, lr: 2.09e-04
+2022-04-30 21:42:30,254 INFO [train.py:763] (2/8) Epoch 36, batch 3900, loss[loss=0.1372, simple_loss=0.2362, pruned_loss=0.01911, over 7329.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2587, pruned_loss=0.02936, over 1425716.41 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:43:35,821 INFO [train.py:763] (2/8) Epoch 36, batch 3950, loss[loss=0.1386, simple_loss=0.2358, pruned_loss=0.02066, over 7258.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2584, pruned_loss=0.02943, over 1426876.87 frames.], batch size: 18, lr: 2.09e-04
+2022-04-30 21:44:41,516 INFO [train.py:763] (2/8) Epoch 36, batch 4000, loss[loss=0.1461, simple_loss=0.2436, pruned_loss=0.02433, over 7160.00 frames.], tot_loss[loss=0.158, simple_loss=0.258, pruned_loss=0.02902, over 1428731.40 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:45:48,398 INFO [train.py:763] (2/8) Epoch 36, batch 4050, loss[loss=0.1712, simple_loss=0.2711, pruned_loss=0.03562, over 7153.00 frames.], tot_loss[loss=0.158, simple_loss=0.2577, pruned_loss=0.02913, over 1427122.52 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:46:54,628 INFO [train.py:763] (2/8) Epoch 36, batch 4100, loss[loss=0.1755, simple_loss=0.269, pruned_loss=0.04103, over 7314.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2587, pruned_loss=0.0294, over 1424286.13 frames.], batch size: 25, lr: 2.09e-04
+2022-04-30 21:48:00,279 INFO [train.py:763] (2/8) Epoch 36, batch 4150, loss[loss=0.1643, simple_loss=0.2696, pruned_loss=0.02945, over 7198.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2581, pruned_loss=0.02903, over 1426328.83 frames.], batch size: 21, lr: 2.09e-04
+2022-04-30 21:49:06,723 INFO [train.py:763] (2/8) Epoch 36, batch 4200, loss[loss=0.1816, simple_loss=0.2847, pruned_loss=0.03925, over 7342.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2579, pruned_loss=0.02866, over 1428408.44 frames.], batch size: 22, lr: 2.09e-04
+2022-04-30 21:50:13,176 INFO [train.py:763] (2/8) Epoch 36, batch 4250, loss[loss=0.1527, simple_loss=0.2542, pruned_loss=0.02567, over 7207.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2581, pruned_loss=0.02885, over 1430736.26 frames.], batch size: 22, lr: 2.09e-04
+2022-04-30 21:51:18,746 INFO [train.py:763] (2/8) Epoch 36, batch 4300, loss[loss=0.1492, simple_loss=0.252, pruned_loss=0.02325, over 7327.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2585, pruned_loss=0.02909, over 1424825.00 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:52:24,303 INFO [train.py:763] (2/8) Epoch 36, batch 4350, loss[loss=0.1651, simple_loss=0.2686, pruned_loss=0.03082, over 7342.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.02924, over 1429536.28 frames.], batch size: 22, lr: 2.09e-04
+2022-04-30 21:53:30,946 INFO [train.py:763] (2/8) Epoch 36, batch 4400, loss[loss=0.1552, simple_loss=0.2721, pruned_loss=0.0191, over 7334.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2597, pruned_loss=0.02932, over 1421989.27 frames.], batch size: 22, lr: 2.09e-04
+2022-04-30 21:54:38,266 INFO [train.py:763] (2/8) Epoch 36, batch 4450, loss[loss=0.1617, simple_loss=0.247, pruned_loss=0.03816, over 7411.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2603, pruned_loss=0.0296, over 1420491.40 frames.], batch size: 18, lr: 2.09e-04
+2022-04-30 21:55:43,444 INFO [train.py:763] (2/8) Epoch 36, batch 4500, loss[loss=0.1326, simple_loss=0.2335, pruned_loss=0.01588, over 7279.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2594, pruned_loss=0.02956, over 1414805.53 frames.], batch size: 18, lr: 2.09e-04
+2022-04-30 21:56:47,987 INFO [train.py:763] (2/8) Epoch 36, batch 4550, loss[loss=0.177, simple_loss=0.2806, pruned_loss=0.03667, over 6481.00 frames.], tot_loss[loss=0.1604, simple_loss=0.261, pruned_loss=0.02995, over 1391786.82 frames.], batch size: 38, lr: 2.09e-04
+2022-04-30 21:58:07,227 INFO [train.py:763] (2/8) Epoch 37, batch 0, loss[loss=0.1448, simple_loss=0.2454, pruned_loss=0.02208, over 7367.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2454, pruned_loss=0.02208, over 7367.00 frames.], batch size: 19, lr: 2.06e-04
+2022-04-30 21:59:13,878 INFO [train.py:763] (2/8) Epoch 37, batch 50, loss[loss=0.1491, simple_loss=0.2503, pruned_loss=0.02395, over 6476.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2546, pruned_loss=0.02675, over 323267.18 frames.], batch size: 38, lr: 2.06e-04
+2022-04-30 22:00:20,508 INFO [train.py:763] (2/8) Epoch 37, batch 100, loss[loss=0.1432, simple_loss=0.2429, pruned_loss=0.02174, over 7269.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2591, pruned_loss=0.02834, over 561274.37 frames.], batch size: 19, lr: 2.06e-04
+2022-04-30 22:01:27,285 INFO [train.py:763] (2/8) Epoch 37, batch 150, loss[loss=0.2115, simple_loss=0.3123, pruned_loss=0.05534, over 7381.00 frames.], tot_loss[loss=0.159, simple_loss=0.2602, pruned_loss=0.02892, over 749800.07 frames.], batch size: 23, lr: 2.06e-04
+2022-04-30 22:02:34,203 INFO [train.py:763] (2/8) Epoch 37, batch 200, loss[loss=0.1508, simple_loss=0.2545, pruned_loss=0.02354, over 7415.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2593, pruned_loss=0.02892, over 897762.97 frames.], batch size: 21, lr: 2.06e-04
+2022-04-30 22:03:39,674 INFO [train.py:763] (2/8) Epoch 37, batch 250, loss[loss=0.1283, simple_loss=0.2318, pruned_loss=0.01243, over 7350.00 frames.], tot_loss[loss=0.1576, simple_loss=0.258, pruned_loss=0.02859, over 1015783.10 frames.], batch size: 19, lr: 2.06e-04
+2022-04-30 22:04:45,242 INFO [train.py:763] (2/8) Epoch 37, batch 300, loss[loss=0.1827, simple_loss=0.288, pruned_loss=0.03875, over 7230.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02935, over 1105609.01 frames.], batch size: 20, lr: 2.06e-04
+2022-04-30 22:05:51,660 INFO [train.py:763] (2/8) Epoch 37, batch 350, loss[loss=0.1538, simple_loss=0.2508, pruned_loss=0.02839, over 7261.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2592, pruned_loss=0.0292, over 1173079.96 frames.], batch size: 19, lr: 2.06e-04
+2022-04-30 22:06:57,559 INFO [train.py:763] (2/8) Epoch 37, batch 400, loss[loss=0.1327, simple_loss=0.2221, pruned_loss=0.02159, over 7298.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2587, pruned_loss=0.02879, over 1233270.02 frames.], batch size: 17, lr: 2.06e-04
+2022-04-30 22:08:03,012 INFO [train.py:763] (2/8) Epoch 37, batch 450, loss[loss=0.1672, simple_loss=0.2704, pruned_loss=0.03205, over 7110.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2587, pruned_loss=0.0289, over 1276342.58 frames.], batch size: 21, lr: 2.06e-04
+2022-04-30 22:09:09,224 INFO [train.py:763] (2/8) Epoch 37, batch 500, loss[loss=0.138, simple_loss=0.2347, pruned_loss=0.02058, over 7278.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2578, pruned_loss=0.02869, over 1312184.45 frames.], batch size: 18, lr: 2.06e-04
+2022-04-30 22:10:16,154 INFO [train.py:763] (2/8) Epoch 37, batch 550, loss[loss=0.1487, simple_loss=0.2573, pruned_loss=0.02007, over 7326.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2576, pruned_loss=0.02887, over 1336109.53 frames.], batch size: 20, lr: 2.06e-04
+2022-04-30 22:11:22,960 INFO [train.py:763] (2/8) Epoch 37, batch 600, loss[loss=0.178, simple_loss=0.2825, pruned_loss=0.03681, over 7372.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2587, pruned_loss=0.0291, over 1357843.81 frames.], batch size: 23, lr: 2.06e-04
+2022-04-30 22:12:30,633 INFO [train.py:763] (2/8) Epoch 37, batch 650, loss[loss=0.1581, simple_loss=0.2649, pruned_loss=0.02564, over 7318.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2588, pruned_loss=0.029, over 1373973.65 frames.], batch size: 22, lr: 2.06e-04
+2022-04-30 22:13:38,152 INFO [train.py:763] (2/8) Epoch 37, batch 700, loss[loss=0.1386, simple_loss=0.2388, pruned_loss=0.01921, over 7159.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2589, pruned_loss=0.02901, over 1386267.99 frames.], batch size: 18, lr: 2.06e-04
+2022-04-30 22:14:45,733 INFO [train.py:763] (2/8) Epoch 37, batch 750, loss[loss=0.1716, simple_loss=0.2728, pruned_loss=0.03516, over 7366.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2592, pruned_loss=0.02924, over 1400602.40 frames.], batch size: 23, lr: 2.05e-04
+2022-04-30 22:15:51,453 INFO [train.py:763] (2/8) Epoch 37, batch 800, loss[loss=0.1525, simple_loss=0.2472, pruned_loss=0.02896, over 7412.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2599, pruned_loss=0.02943, over 1408567.81 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:16:56,736 INFO [train.py:763] (2/8) Epoch 37, batch 850, loss[loss=0.1544, simple_loss=0.257, pruned_loss=0.02589, over 7356.00 frames.], tot_loss[loss=0.159, simple_loss=0.2599, pruned_loss=0.02905, over 1411593.03 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:18:02,417 INFO [train.py:763] (2/8) Epoch 37, batch 900, loss[loss=0.184, simple_loss=0.2802, pruned_loss=0.04389, over 7313.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2597, pruned_loss=0.02928, over 1413878.92 frames.], batch size: 24, lr: 2.05e-04
+2022-04-30 22:19:07,693 INFO [train.py:763] (2/8) Epoch 37, batch 950, loss[loss=0.153, simple_loss=0.2546, pruned_loss=0.02567, over 7254.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2601, pruned_loss=0.02921, over 1419440.05 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:20:12,873 INFO [train.py:763] (2/8) Epoch 37, batch 1000, loss[loss=0.1591, simple_loss=0.2596, pruned_loss=0.02937, over 7200.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2601, pruned_loss=0.02906, over 1422048.45 frames.], batch size: 22, lr: 2.05e-04
+2022-04-30 22:21:18,156 INFO [train.py:763] (2/8) Epoch 37, batch 1050, loss[loss=0.1519, simple_loss=0.2596, pruned_loss=0.02207, over 7329.00 frames.], tot_loss[loss=0.159, simple_loss=0.2601, pruned_loss=0.02892, over 1423406.70 frames.], batch size: 20, lr: 2.05e-04
+2022-04-30 22:22:25,731 INFO [train.py:763] (2/8) Epoch 37, batch 1100, loss[loss=0.1259, simple_loss=0.2146, pruned_loss=0.01863, over 6851.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2597, pruned_loss=0.02855, over 1426628.98 frames.], batch size: 15, lr: 2.05e-04
+2022-04-30 22:23:31,640 INFO [train.py:763] (2/8) Epoch 37, batch 1150, loss[loss=0.1301, simple_loss=0.224, pruned_loss=0.01812, over 7266.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2593, pruned_loss=0.02843, over 1422754.16 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:24:36,964 INFO [train.py:763] (2/8) Epoch 37, batch 1200, loss[loss=0.1477, simple_loss=0.2526, pruned_loss=0.02143, over 7221.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2596, pruned_loss=0.02875, over 1424840.43 frames.], batch size: 26, lr: 2.05e-04
+2022-04-30 22:25:43,864 INFO [train.py:763] (2/8) Epoch 37, batch 1250, loss[loss=0.144, simple_loss=0.2503, pruned_loss=0.01887, over 6547.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2602, pruned_loss=0.02915, over 1428194.26 frames.], batch size: 37, lr: 2.05e-04
+2022-04-30 22:26:50,669 INFO [train.py:763] (2/8) Epoch 37, batch 1300, loss[loss=0.1444, simple_loss=0.2368, pruned_loss=0.02602, over 7270.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2607, pruned_loss=0.02931, over 1427920.30 frames.], batch size: 17, lr: 2.05e-04
+2022-04-30 22:27:56,058 INFO [train.py:763] (2/8) Epoch 37, batch 1350, loss[loss=0.1645, simple_loss=0.2708, pruned_loss=0.02903, over 7111.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2591, pruned_loss=0.02892, over 1422213.06 frames.], batch size: 21, lr: 2.05e-04
+2022-04-30 22:29:02,055 INFO [train.py:763] (2/8) Epoch 37, batch 1400, loss[loss=0.1686, simple_loss=0.2744, pruned_loss=0.03141, over 7299.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2585, pruned_loss=0.02906, over 1421564.13 frames.], batch size: 24, lr: 2.05e-04
+2022-04-30 22:30:07,326 INFO [train.py:763] (2/8) Epoch 37, batch 1450, loss[loss=0.1601, simple_loss=0.2825, pruned_loss=0.01891, over 7206.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.02946, over 1425732.83 frames.], batch size: 22, lr: 2.05e-04
+2022-04-30 22:31:13,218 INFO [train.py:763] (2/8) Epoch 37, batch 1500, loss[loss=0.1625, simple_loss=0.259, pruned_loss=0.033, over 7285.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2589, pruned_loss=0.02935, over 1426368.45 frames.], batch size: 25, lr: 2.05e-04
+2022-04-30 22:32:18,519 INFO [train.py:763] (2/8) Epoch 37, batch 1550, loss[loss=0.1564, simple_loss=0.2581, pruned_loss=0.02736, over 7241.00 frames.], tot_loss[loss=0.159, simple_loss=0.2592, pruned_loss=0.02944, over 1423783.26 frames.], batch size: 20, lr: 2.05e-04
+2022-04-30 22:33:23,881 INFO [train.py:763] (2/8) Epoch 37, batch 1600, loss[loss=0.1369, simple_loss=0.238, pruned_loss=0.01793, over 7260.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2598, pruned_loss=0.02965, over 1426311.83 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:34:29,218 INFO [train.py:763] (2/8) Epoch 37, batch 1650, loss[loss=0.1556, simple_loss=0.2603, pruned_loss=0.02549, over 7135.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2596, pruned_loss=0.0295, over 1425726.24 frames.], batch size: 28, lr: 2.05e-04
+2022-04-30 22:35:34,590 INFO [train.py:763] (2/8) Epoch 37, batch 1700, loss[loss=0.1429, simple_loss=0.2499, pruned_loss=0.01795, over 7166.00 frames.], tot_loss[loss=0.1587, simple_loss=0.259, pruned_loss=0.02927, over 1425618.05 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:36:40,243 INFO [train.py:763] (2/8) Epoch 37, batch 1750, loss[loss=0.1735, simple_loss=0.264, pruned_loss=0.04154, over 5126.00 frames.], tot_loss[loss=0.159, simple_loss=0.2593, pruned_loss=0.02932, over 1423197.74 frames.], batch size: 52, lr: 2.05e-04
+2022-04-30 22:37:45,567 INFO [train.py:763] (2/8) Epoch 37, batch 1800, loss[loss=0.1875, simple_loss=0.2922, pruned_loss=0.0414, over 7334.00 frames.], tot_loss[loss=0.1578, simple_loss=0.258, pruned_loss=0.02875, over 1419657.18 frames.], batch size: 20, lr: 2.05e-04
+2022-04-30 22:38:50,827 INFO [train.py:763] (2/8) Epoch 37, batch 1850, loss[loss=0.1585, simple_loss=0.2632, pruned_loss=0.02687, over 7274.00 frames.], tot_loss[loss=0.1578, simple_loss=0.258, pruned_loss=0.02883, over 1421572.27 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:39:57,178 INFO [train.py:763] (2/8) Epoch 37, batch 1900, loss[loss=0.1575, simple_loss=0.2453, pruned_loss=0.03482, over 6792.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2589, pruned_loss=0.02897, over 1424389.12 frames.], batch size: 15, lr: 2.05e-04
+2022-04-30 22:41:04,597 INFO [train.py:763] (2/8) Epoch 37, batch 1950, loss[loss=0.1835, simple_loss=0.2755, pruned_loss=0.04578, over 7243.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2595, pruned_loss=0.02912, over 1426870.02 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:42:12,272 INFO [train.py:763] (2/8) Epoch 37, batch 2000, loss[loss=0.1288, simple_loss=0.2191, pruned_loss=0.01927, over 7404.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2589, pruned_loss=0.02899, over 1425587.68 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:43:17,406 INFO [train.py:763] (2/8) Epoch 37, batch 2050, loss[loss=0.1352, simple_loss=0.2364, pruned_loss=0.01695, over 7262.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2591, pruned_loss=0.02904, over 1423377.64 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:44:22,372 INFO [train.py:763] (2/8) Epoch 37, batch 2100, loss[loss=0.1727, simple_loss=0.2768, pruned_loss=0.03427, over 7156.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2601, pruned_loss=0.02949, over 1417432.45 frames.], batch size: 26, lr: 2.05e-04
+2022-04-30 22:45:27,585 INFO [train.py:763] (2/8) Epoch 37, batch 2150, loss[loss=0.1344, simple_loss=0.2402, pruned_loss=0.01424, over 7061.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2597, pruned_loss=0.02934, over 1417629.15 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:46:32,463 INFO [train.py:763] (2/8) Epoch 37, batch 2200, loss[loss=0.1386, simple_loss=0.2368, pruned_loss=0.02023, over 7065.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2605, pruned_loss=0.02922, over 1419337.65 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:47:37,561 INFO [train.py:763] (2/8) Epoch 37, batch 2250, loss[loss=0.1444, simple_loss=0.2432, pruned_loss=0.02281, over 6229.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2605, pruned_loss=0.02933, over 1417798.16 frames.], batch size: 37, lr: 2.05e-04
+2022-04-30 22:48:44,663 INFO [train.py:763] (2/8) Epoch 37, batch 2300, loss[loss=0.1451, simple_loss=0.2434, pruned_loss=0.02343, over 7068.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2598, pruned_loss=0.0289, over 1421578.62 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:49:50,006 INFO [train.py:763] (2/8) Epoch 37, batch 2350, loss[loss=0.1576, simple_loss=0.2679, pruned_loss=0.02358, over 7342.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2601, pruned_loss=0.02906, over 1419396.44 frames.], batch size: 20, lr: 2.05e-04
+2022-04-30 22:50:55,499 INFO [train.py:763] (2/8) Epoch 37, batch 2400, loss[loss=0.1405, simple_loss=0.2401, pruned_loss=0.02041, over 7424.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2591, pruned_loss=0.02889, over 1424857.00 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:52:02,203 INFO [train.py:763] (2/8) Epoch 37, batch 2450, loss[loss=0.1788, simple_loss=0.2758, pruned_loss=0.04093, over 7326.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2594, pruned_loss=0.0288, over 1427217.63 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 22:53:07,498 INFO [train.py:763] (2/8) Epoch 37, batch 2500, loss[loss=0.1443, simple_loss=0.2432, pruned_loss=0.02269, over 7169.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2592, pruned_loss=0.0291, over 1426555.90 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 22:54:13,274 INFO [train.py:763] (2/8) Epoch 37, batch 2550, loss[loss=0.1424, simple_loss=0.2359, pruned_loss=0.02449, over 7152.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2591, pruned_loss=0.02898, over 1424198.63 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 22:55:19,536 INFO [train.py:763] (2/8) Epoch 37, batch 2600, loss[loss=0.1552, simple_loss=0.2616, pruned_loss=0.02436, over 7429.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2584, pruned_loss=0.02899, over 1423289.27 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 22:56:24,703 INFO [train.py:763] (2/8) Epoch 37, batch 2650, loss[loss=0.2074, simple_loss=0.3121, pruned_loss=0.05136, over 7215.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.02921, over 1425024.71 frames.], batch size: 23, lr: 2.04e-04
+2022-04-30 22:57:30,426 INFO [train.py:763] (2/8) Epoch 37, batch 2700, loss[loss=0.1561, simple_loss=0.2592, pruned_loss=0.02652, over 7230.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2577, pruned_loss=0.02895, over 1424276.30 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 22:58:35,691 INFO [train.py:763] (2/8) Epoch 37, batch 2750, loss[loss=0.1556, simple_loss=0.2602, pruned_loss=0.02549, over 7358.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2585, pruned_loss=0.02908, over 1425377.17 frames.], batch size: 19, lr: 2.04e-04
+2022-04-30 22:59:42,055 INFO [train.py:763] (2/8) Epoch 37, batch 2800, loss[loss=0.168, simple_loss=0.2752, pruned_loss=0.03035, over 7286.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2586, pruned_loss=0.02913, over 1423682.13 frames.], batch size: 24, lr: 2.04e-04
+2022-04-30 23:00:49,139 INFO [train.py:763] (2/8) Epoch 37, batch 2850, loss[loss=0.1593, simple_loss=0.2674, pruned_loss=0.02558, over 7409.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2587, pruned_loss=0.02874, over 1424319.81 frames.], batch size: 21, lr: 2.04e-04
+2022-04-30 23:01:56,140 INFO [train.py:763] (2/8) Epoch 37, batch 2900, loss[loss=0.1385, simple_loss=0.2331, pruned_loss=0.0219, over 7146.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2583, pruned_loss=0.02858, over 1424553.15 frames.], batch size: 17, lr: 2.04e-04
+2022-04-30 23:03:03,257 INFO [train.py:763] (2/8) Epoch 37, batch 2950, loss[loss=0.1495, simple_loss=0.251, pruned_loss=0.02401, over 7431.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2587, pruned_loss=0.02852, over 1429133.06 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 23:04:10,176 INFO [train.py:763] (2/8) Epoch 37, batch 3000, loss[loss=0.17, simple_loss=0.2661, pruned_loss=0.03698, over 7204.00 frames.], tot_loss[loss=0.158, simple_loss=0.2587, pruned_loss=0.02866, over 1428994.00 frames.], batch size: 23, lr: 2.04e-04
+2022-04-30 23:04:10,177 INFO [train.py:783] (2/8) Computing validation loss
+2022-04-30 23:04:25,433 INFO [train.py:792] (2/8) Epoch 37, validation: loss=0.1692, simple_loss=0.2632, pruned_loss=0.03757, over 698248.00 frames.
+2022-04-30 23:05:32,514 INFO [train.py:763] (2/8) Epoch 37, batch 3050, loss[loss=0.1448, simple_loss=0.2391, pruned_loss=0.0253, over 7172.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2589, pruned_loss=0.02869, over 1429126.49 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 23:06:38,291 INFO [train.py:763] (2/8) Epoch 37, batch 3100, loss[loss=0.1637, simple_loss=0.27, pruned_loss=0.02868, over 7217.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2586, pruned_loss=0.02878, over 1422380.58 frames.], batch size: 22, lr: 2.04e-04
+2022-04-30 23:07:53,026 INFO [train.py:763] (2/8) Epoch 37, batch 3150, loss[loss=0.1647, simple_loss=0.2707, pruned_loss=0.02932, over 7393.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2581, pruned_loss=0.02847, over 1420115.27 frames.], batch size: 23, lr: 2.04e-04
+2022-04-30 23:08:58,933 INFO [train.py:763] (2/8) Epoch 37, batch 3200, loss[loss=0.1743, simple_loss=0.2799, pruned_loss=0.03436, over 7105.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2581, pruned_loss=0.02849, over 1424734.52 frames.], batch size: 21, lr: 2.04e-04
+2022-04-30 23:10:06,286 INFO [train.py:763] (2/8) Epoch 37, batch 3250, loss[loss=0.1328, simple_loss=0.2332, pruned_loss=0.01625, over 7281.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2575, pruned_loss=0.02819, over 1426123.51 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 23:11:13,121 INFO [train.py:763] (2/8) Epoch 37, batch 3300, loss[loss=0.1512, simple_loss=0.2563, pruned_loss=0.02302, over 7239.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2582, pruned_loss=0.02824, over 1425319.91 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:12:18,271 INFO [train.py:763] (2/8) Epoch 37, batch 3350, loss[loss=0.1624, simple_loss=0.2682, pruned_loss=0.02832, over 7195.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2593, pruned_loss=0.02873, over 1425965.36 frames.], batch size: 22, lr: 2.04e-04
+2022-04-30 23:13:23,564 INFO [train.py:763] (2/8) Epoch 37, batch 3400, loss[loss=0.1737, simple_loss=0.2768, pruned_loss=0.03534, over 6847.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2587, pruned_loss=0.02846, over 1430095.27 frames.], batch size: 31, lr: 2.04e-04
+2022-04-30 23:14:28,969 INFO [train.py:763] (2/8) Epoch 37, batch 3450, loss[loss=0.2021, simple_loss=0.2833, pruned_loss=0.06043, over 7429.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2603, pruned_loss=0.02943, over 1432243.19 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:15:34,294 INFO [train.py:763] (2/8) Epoch 37, batch 3500, loss[loss=0.1439, simple_loss=0.2477, pruned_loss=0.02009, over 7238.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2595, pruned_loss=0.0291, over 1430533.16 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:16:39,549 INFO [train.py:763] (2/8) Epoch 37, batch 3550, loss[loss=0.1628, simple_loss=0.2704, pruned_loss=0.02756, over 7146.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2604, pruned_loss=0.02898, over 1430637.60 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:17:44,637 INFO [train.py:763] (2/8) Epoch 37, batch 3600, loss[loss=0.1864, simple_loss=0.299, pruned_loss=0.03689, over 6711.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2609, pruned_loss=0.02913, over 1428565.13 frames.], batch size: 31, lr: 2.04e-04
+2022-04-30 23:18:50,216 INFO [train.py:763] (2/8) Epoch 37, batch 3650, loss[loss=0.17, simple_loss=0.2778, pruned_loss=0.03111, over 7110.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2597, pruned_loss=0.02867, over 1430989.78 frames.], batch size: 28, lr: 2.04e-04
+2022-04-30 23:19:55,911 INFO [train.py:763] (2/8) Epoch 37, batch 3700, loss[loss=0.1897, simple_loss=0.279, pruned_loss=0.0502, over 7301.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2588, pruned_loss=0.02901, over 1423332.87 frames.], batch size: 24, lr: 2.04e-04
+2022-04-30 23:21:00,945 INFO [train.py:763] (2/8) Epoch 37, batch 3750, loss[loss=0.1634, simple_loss=0.2657, pruned_loss=0.03052, over 7165.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2592, pruned_loss=0.02897, over 1418523.70 frames.], batch size: 19, lr: 2.04e-04
+2022-04-30 23:22:07,106 INFO [train.py:763] (2/8) Epoch 37, batch 3800, loss[loss=0.1863, simple_loss=0.3034, pruned_loss=0.0346, over 7370.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2589, pruned_loss=0.02897, over 1419006.06 frames.], batch size: 23, lr: 2.04e-04
+2022-04-30 23:23:12,316 INFO [train.py:763] (2/8) Epoch 37, batch 3850, loss[loss=0.1558, simple_loss=0.2644, pruned_loss=0.02357, over 7106.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2589, pruned_loss=0.02883, over 1421097.09 frames.], batch size: 21, lr: 2.04e-04
+2022-04-30 23:24:18,023 INFO [train.py:763] (2/8) Epoch 37, batch 3900, loss[loss=0.1631, simple_loss=0.266, pruned_loss=0.0301, over 7333.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2588, pruned_loss=0.02931, over 1423831.58 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:25:32,657 INFO [train.py:763] (2/8) Epoch 37, batch 3950, loss[loss=0.1611, simple_loss=0.2611, pruned_loss=0.0306, over 7202.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2584, pruned_loss=0.02893, over 1418500.82 frames.], batch size: 22, lr: 2.04e-04
+2022-04-30 23:26:37,875 INFO [train.py:763] (2/8) Epoch 37, batch 4000, loss[loss=0.143, simple_loss=0.2394, pruned_loss=0.02324, over 7168.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2578, pruned_loss=0.0285, over 1419331.44 frames.], batch size: 19, lr: 2.04e-04
+2022-04-30 23:28:01,968 INFO [train.py:763] (2/8) Epoch 37, batch 4050, loss[loss=0.1485, simple_loss=0.2363, pruned_loss=0.03037, over 7287.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2578, pruned_loss=0.02835, over 1411884.60 frames.], batch size: 17, lr: 2.04e-04
+2022-04-30 23:29:07,112 INFO [train.py:763] (2/8) Epoch 37, batch 4100, loss[loss=0.1719, simple_loss=0.2781, pruned_loss=0.03281, over 7195.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2585, pruned_loss=0.02854, over 1413578.66 frames.], batch size: 21, lr: 2.04e-04
+2022-04-30 23:30:21,705 INFO [train.py:763] (2/8) Epoch 37, batch 4150, loss[loss=0.1711, simple_loss=0.2667, pruned_loss=0.0377, over 7261.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2577, pruned_loss=0.02853, over 1413253.99 frames.], batch size: 19, lr: 2.03e-04
+2022-04-30 23:31:36,368 INFO [train.py:763] (2/8) Epoch 37, batch 4200, loss[loss=0.1763, simple_loss=0.2896, pruned_loss=0.03149, over 7297.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2574, pruned_loss=0.02813, over 1414544.22 frames.], batch size: 24, lr: 2.03e-04
+2022-04-30 23:32:51,950 INFO [train.py:763] (2/8) Epoch 37, batch 4250, loss[loss=0.1766, simple_loss=0.2764, pruned_loss=0.0384, over 7240.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2585, pruned_loss=0.02861, over 1414228.28 frames.], batch size: 20, lr: 2.03e-04
+2022-04-30 23:33:58,661 INFO [train.py:763] (2/8) Epoch 37, batch 4300, loss[loss=0.1897, simple_loss=0.2784, pruned_loss=0.05049, over 5092.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2569, pruned_loss=0.02841, over 1411061.05 frames.], batch size: 53, lr: 2.03e-04
+2022-04-30 23:35:04,833 INFO [train.py:763] (2/8) Epoch 37, batch 4350, loss[loss=0.1574, simple_loss=0.2442, pruned_loss=0.03533, over 7011.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2561, pruned_loss=0.02815, over 1412947.85 frames.], batch size: 16, lr: 2.03e-04
+2022-04-30 23:36:10,381 INFO [train.py:763] (2/8) Epoch 37, batch 4400, loss[loss=0.1433, simple_loss=0.2434, pruned_loss=0.02163, over 7208.00 frames.], tot_loss[loss=0.156, simple_loss=0.2559, pruned_loss=0.0281, over 1414060.32 frames.], batch size: 16, lr: 2.03e-04
+2022-04-30 23:37:17,175 INFO [train.py:763] (2/8) Epoch 37, batch 4450, loss[loss=0.1471, simple_loss=0.2357, pruned_loss=0.02921, over 6760.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2552, pruned_loss=0.02826, over 1406035.75 frames.], batch size: 15, lr: 2.03e-04
+2022-04-30 23:38:22,830 INFO [train.py:763] (2/8) Epoch 37, batch 4500, loss[loss=0.1592, simple_loss=0.2578, pruned_loss=0.03034, over 6465.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2552, pruned_loss=0.02844, over 1382497.22 frames.], batch size: 38, lr: 2.03e-04
+2022-04-30 23:39:28,654 INFO [train.py:763] (2/8) Epoch 37, batch 4550, loss[loss=0.1965, simple_loss=0.2757, pruned_loss=0.05868, over 5356.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2549, pruned_loss=0.02884, over 1355608.96 frames.], batch size: 52, lr: 2.03e-04
+2022-04-30 23:40:56,594 INFO [train.py:763] (2/8) Epoch 38, batch 0, loss[loss=0.1629, simple_loss=0.26, pruned_loss=0.03292, over 7262.00 frames.], tot_loss[loss=0.1629, simple_loss=0.26, pruned_loss=0.03292, over 7262.00 frames.], batch size: 19, lr: 2.01e-04
+2022-04-30 23:42:03,203 INFO [train.py:763] (2/8) Epoch 38, batch 50, loss[loss=0.1525, simple_loss=0.2574, pruned_loss=0.02383, over 7151.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2613, pruned_loss=0.02862, over 320027.53 frames.], batch size: 20, lr: 2.01e-04
+2022-04-30 23:43:10,049 INFO [train.py:763] (2/8) Epoch 38, batch 100, loss[loss=0.165, simple_loss=0.2738, pruned_loss=0.02807, over 6732.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2599, pruned_loss=0.0287, over 565135.41 frames.], batch size: 31, lr: 2.01e-04
+2022-04-30 23:44:16,789 INFO [train.py:763] (2/8) Epoch 38, batch 150, loss[loss=0.1682, simple_loss=0.268, pruned_loss=0.03416, over 7155.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2582, pruned_loss=0.02908, over 754220.07 frames.], batch size: 18, lr: 2.01e-04
+2022-04-30 23:45:22,772 INFO [train.py:763] (2/8) Epoch 38, batch 200, loss[loss=0.1405, simple_loss=0.2318, pruned_loss=0.02461, over 7428.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2599, pruned_loss=0.02958, over 900748.08 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:46:29,134 INFO [train.py:763] (2/8) Epoch 38, batch 250, loss[loss=0.1551, simple_loss=0.2659, pruned_loss=0.02212, over 6164.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2609, pruned_loss=0.03024, over 1016989.53 frames.], batch size: 37, lr: 2.00e-04
+2022-04-30 23:47:35,363 INFO [train.py:763] (2/8) Epoch 38, batch 300, loss[loss=0.1488, simple_loss=0.2388, pruned_loss=0.02939, over 7443.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2597, pruned_loss=0.02973, over 1112840.70 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:48:41,445 INFO [train.py:763] (2/8) Epoch 38, batch 350, loss[loss=0.1747, simple_loss=0.2841, pruned_loss=0.03264, over 7294.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2595, pruned_loss=0.02976, over 1179076.60 frames.], batch size: 24, lr: 2.00e-04
+2022-04-30 23:49:47,442 INFO [train.py:763] (2/8) Epoch 38, batch 400, loss[loss=0.1393, simple_loss=0.245, pruned_loss=0.01677, over 7216.00 frames.], tot_loss[loss=0.159, simple_loss=0.259, pruned_loss=0.02951, over 1229250.36 frames.], batch size: 21, lr: 2.00e-04
+2022-04-30 23:50:53,869 INFO [train.py:763] (2/8) Epoch 38, batch 450, loss[loss=0.1508, simple_loss=0.2486, pruned_loss=0.02649, over 7199.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2583, pruned_loss=0.02906, over 1274197.76 frames.], batch size: 23, lr: 2.00e-04
+2022-04-30 23:52:00,160 INFO [train.py:763] (2/8) Epoch 38, batch 500, loss[loss=0.1669, simple_loss=0.2787, pruned_loss=0.02752, over 7148.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2581, pruned_loss=0.02915, over 1302077.19 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:53:06,412 INFO [train.py:763] (2/8) Epoch 38, batch 550, loss[loss=0.1554, simple_loss=0.2636, pruned_loss=0.02357, over 7439.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2575, pruned_loss=0.02886, over 1328093.75 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:54:12,144 INFO [train.py:763] (2/8) Epoch 38, batch 600, loss[loss=0.152, simple_loss=0.2431, pruned_loss=0.03043, over 7167.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2575, pruned_loss=0.02846, over 1346218.64 frames.], batch size: 18, lr: 2.00e-04
+2022-04-30 23:55:17,886 INFO [train.py:763] (2/8) Epoch 38, batch 650, loss[loss=0.1532, simple_loss=0.2355, pruned_loss=0.03546, over 7280.00 frames.], tot_loss[loss=0.157, simple_loss=0.2576, pruned_loss=0.02821, over 1365734.53 frames.], batch size: 17, lr: 2.00e-04
+2022-04-30 23:56:23,408 INFO [train.py:763] (2/8) Epoch 38, batch 700, loss[loss=0.1554, simple_loss=0.2525, pruned_loss=0.02912, over 6797.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2571, pruned_loss=0.02828, over 1377627.78 frames.], batch size: 15, lr: 2.00e-04
+2022-04-30 23:57:28,959 INFO [train.py:763] (2/8) Epoch 38, batch 750, loss[loss=0.1797, simple_loss=0.2866, pruned_loss=0.0364, over 6273.00 frames.], tot_loss[loss=0.1558, simple_loss=0.256, pruned_loss=0.0278, over 1385927.04 frames.], batch size: 37, lr: 2.00e-04
+2022-04-30 23:58:35,116 INFO [train.py:763] (2/8) Epoch 38, batch 800, loss[loss=0.1592, simple_loss=0.2573, pruned_loss=0.03056, over 7232.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2561, pruned_loss=0.0278, over 1398884.19 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:59:41,180 INFO [train.py:763] (2/8) Epoch 38, batch 850, loss[loss=0.1716, simple_loss=0.2792, pruned_loss=0.03206, over 7015.00 frames.], tot_loss[loss=0.156, simple_loss=0.2564, pruned_loss=0.02777, over 1404868.79 frames.], batch size: 28, lr: 2.00e-04
+2022-05-01 00:00:47,047 INFO [train.py:763] (2/8) Epoch 38, batch 900, loss[loss=0.1739, simple_loss=0.2793, pruned_loss=0.03421, over 7427.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2569, pruned_loss=0.02822, over 1402914.62 frames.], batch size: 21, lr: 2.00e-04
+2022-05-01 00:01:52,974 INFO [train.py:763] (2/8) Epoch 38, batch 950, loss[loss=0.1426, simple_loss=0.2359, pruned_loss=0.02462, over 7134.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2581, pruned_loss=0.02903, over 1405113.12 frames.], batch size: 17, lr: 2.00e-04
+2022-05-01 00:02:58,567 INFO [train.py:763] (2/8) Epoch 38, batch 1000, loss[loss=0.157, simple_loss=0.2569, pruned_loss=0.02854, over 7364.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2577, pruned_loss=0.0284, over 1408480.28 frames.], batch size: 19, lr: 2.00e-04
+2022-05-01 00:04:03,994 INFO [train.py:763] (2/8) Epoch 38, batch 1050, loss[loss=0.1706, simple_loss=0.2753, pruned_loss=0.03294, over 6718.00 frames.], tot_loss[loss=0.1581, simple_loss=0.258, pruned_loss=0.02908, over 1411093.52 frames.], batch size: 31, lr: 2.00e-04
+2022-05-01 00:05:09,982 INFO [train.py:763] (2/8) Epoch 38, batch 1100, loss[loss=0.1721, simple_loss=0.2758, pruned_loss=0.03416, over 7381.00 frames.], tot_loss[loss=0.1573, simple_loss=0.257, pruned_loss=0.02886, over 1414733.26 frames.], batch size: 23, lr: 2.00e-04
+2022-05-01 00:06:15,676 INFO [train.py:763] (2/8) Epoch 38, batch 1150, loss[loss=0.1521, simple_loss=0.2493, pruned_loss=0.02749, over 7255.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2561, pruned_loss=0.0286, over 1418795.83 frames.], batch size: 18, lr: 2.00e-04
+2022-05-01 00:07:21,223 INFO [train.py:763] (2/8) Epoch 38, batch 1200, loss[loss=0.161, simple_loss=0.2592, pruned_loss=0.0314, over 6860.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2564, pruned_loss=0.02901, over 1420294.48 frames.], batch size: 31, lr: 2.00e-04
+2022-05-01 00:08:27,090 INFO [train.py:763] (2/8) Epoch 38, batch 1250, loss[loss=0.1506, simple_loss=0.2483, pruned_loss=0.02651, over 7431.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2569, pruned_loss=0.02903, over 1420304.85 frames.], batch size: 20, lr: 2.00e-04
+2022-05-01 00:09:34,183 INFO [train.py:763] (2/8) Epoch 38, batch 1300, loss[loss=0.1341, simple_loss=0.2274, pruned_loss=0.02045, over 7274.00 frames.], tot_loss[loss=0.157, simple_loss=0.2565, pruned_loss=0.02875, over 1423676.31 frames.], batch size: 17, lr: 2.00e-04
+2022-05-01 00:10:39,849 INFO [train.py:763] (2/8) Epoch 38, batch 1350, loss[loss=0.1697, simple_loss=0.2734, pruned_loss=0.033, over 7325.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2569, pruned_loss=0.02884, over 1424203.63 frames.], batch size: 20, lr: 2.00e-04
+2022-05-01 00:11:45,174 INFO [train.py:763] (2/8) Epoch 38, batch 1400, loss[loss=0.1323, simple_loss=0.2425, pruned_loss=0.01105, over 7157.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2573, pruned_loss=0.02901, over 1423669.04 frames.], batch size: 19, lr: 2.00e-04
+2022-05-01 00:12:50,401 INFO [train.py:763] (2/8) Epoch 38, batch 1450, loss[loss=0.1847, simple_loss=0.2854, pruned_loss=0.04195, over 7326.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2587, pruned_loss=0.02933, over 1423920.38 frames.], batch size: 25, lr: 2.00e-04
+2022-05-01 00:13:55,954 INFO [train.py:763] (2/8) Epoch 38, batch 1500, loss[loss=0.1591, simple_loss=0.2663, pruned_loss=0.02598, over 7117.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2578, pruned_loss=0.02889, over 1422511.09 frames.], batch size: 21, lr: 2.00e-04
+2022-05-01 00:15:03,014 INFO [train.py:763] (2/8) Epoch 38, batch 1550, loss[loss=0.1557, simple_loss=0.2619, pruned_loss=0.02478, over 7217.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2571, pruned_loss=0.02881, over 1422432.19 frames.], batch size: 22, lr: 2.00e-04
+2022-05-01 00:16:09,257 INFO [train.py:763] (2/8) Epoch 38, batch 1600, loss[loss=0.192, simple_loss=0.295, pruned_loss=0.04452, over 6774.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2573, pruned_loss=0.02894, over 1425068.17 frames.], batch size: 31, lr: 2.00e-04
+2022-05-01 00:17:15,069 INFO [train.py:763] (2/8) Epoch 38, batch 1650, loss[loss=0.172, simple_loss=0.2771, pruned_loss=0.03342, over 7221.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2573, pruned_loss=0.02842, over 1424542.31 frames.], batch size: 21, lr: 2.00e-04
+2022-05-01 00:18:31,381 INFO [train.py:763] (2/8) Epoch 38, batch 1700, loss[loss=0.1608, simple_loss=0.2625, pruned_loss=0.02957, over 7086.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2578, pruned_loss=0.02834, over 1426360.56 frames.], batch size: 28, lr: 2.00e-04
+2022-05-01 00:19:36,542 INFO [train.py:763] (2/8) Epoch 38, batch 1750, loss[loss=0.1574, simple_loss=0.2523, pruned_loss=0.03124, over 7432.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2587, pruned_loss=0.02853, over 1426266.99 frames.], batch size: 20, lr: 2.00e-04
+2022-05-01 00:20:42,261 INFO [train.py:763] (2/8) Epoch 38, batch 1800, loss[loss=0.1659, simple_loss=0.2646, pruned_loss=0.03361, over 7212.00 frames.], tot_loss[loss=0.158, simple_loss=0.2588, pruned_loss=0.02858, over 1424417.21 frames.], batch size: 23, lr: 2.00e-04
+2022-05-01 00:21:47,718 INFO [train.py:763] (2/8) Epoch 38, batch 1850, loss[loss=0.1477, simple_loss=0.2524, pruned_loss=0.0215, over 7167.00 frames.], tot_loss[loss=0.158, simple_loss=0.2585, pruned_loss=0.02879, over 1422060.58 frames.], batch size: 19, lr: 2.00e-04
+2022-05-01 00:22:54,644 INFO [train.py:763] (2/8) Epoch 38, batch 1900, loss[loss=0.1422, simple_loss=0.2535, pruned_loss=0.0154, over 7285.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2585, pruned_loss=0.0289, over 1424474.35 frames.], batch size: 18, lr: 2.00e-04
+2022-05-01 00:24:00,338 INFO [train.py:763] (2/8) Epoch 38, batch 1950, loss[loss=0.1619, simple_loss=0.2699, pruned_loss=0.02695, over 7316.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2583, pruned_loss=0.02865, over 1424309.00 frames.], batch size: 21, lr: 1.99e-04
+2022-05-01 00:25:06,437 INFO [train.py:763] (2/8) Epoch 38, batch 2000, loss[loss=0.1703, simple_loss=0.2635, pruned_loss=0.03852, over 7257.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2586, pruned_loss=0.02852, over 1423533.96 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:26:13,052 INFO [train.py:763] (2/8) Epoch 38, batch 2050, loss[loss=0.1369, simple_loss=0.2464, pruned_loss=0.01374, over 7308.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2588, pruned_loss=0.02866, over 1422054.82 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:27:18,297 INFO [train.py:763] (2/8) Epoch 38, batch 2100, loss[loss=0.14, simple_loss=0.2234, pruned_loss=0.02826, over 6794.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2574, pruned_loss=0.02807, over 1423307.87 frames.], batch size: 15, lr: 1.99e-04
+2022-05-01 00:28:25,362 INFO [train.py:763] (2/8) Epoch 38, batch 2150, loss[loss=0.1509, simple_loss=0.2561, pruned_loss=0.02283, over 7276.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2572, pruned_loss=0.02816, over 1420878.03 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:29:31,360 INFO [train.py:763] (2/8) Epoch 38, batch 2200, loss[loss=0.1446, simple_loss=0.246, pruned_loss=0.02165, over 7204.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2579, pruned_loss=0.02843, over 1421428.29 frames.], batch size: 22, lr: 1.99e-04
+2022-05-01 00:30:38,809 INFO [train.py:763] (2/8) Epoch 38, batch 2250, loss[loss=0.1592, simple_loss=0.2441, pruned_loss=0.0372, over 7142.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2567, pruned_loss=0.02846, over 1425072.66 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:31:44,021 INFO [train.py:763] (2/8) Epoch 38, batch 2300, loss[loss=0.1537, simple_loss=0.2494, pruned_loss=0.02901, over 7159.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2575, pruned_loss=0.02867, over 1424486.99 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:32:50,156 INFO [train.py:763] (2/8) Epoch 38, batch 2350, loss[loss=0.1511, simple_loss=0.2494, pruned_loss=0.02644, over 7243.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2568, pruned_loss=0.02829, over 1425925.17 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:33:55,522 INFO [train.py:763] (2/8) Epoch 38, batch 2400, loss[loss=0.1709, simple_loss=0.2805, pruned_loss=0.03065, over 7144.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2576, pruned_loss=0.02857, over 1429235.13 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:35:01,017 INFO [train.py:763] (2/8) Epoch 38, batch 2450, loss[loss=0.1423, simple_loss=0.2436, pruned_loss=0.02048, over 7414.00 frames.], tot_loss[loss=0.1568, simple_loss=0.257, pruned_loss=0.02826, over 1429782.70 frames.], batch size: 18, lr: 1.99e-04
+2022-05-01 00:36:06,993 INFO [train.py:763] (2/8) Epoch 38, batch 2500, loss[loss=0.1383, simple_loss=0.2313, pruned_loss=0.02267, over 7415.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2568, pruned_loss=0.0283, over 1428145.69 frames.], batch size: 18, lr: 1.99e-04
+2022-05-01 00:37:12,683 INFO [train.py:763] (2/8) Epoch 38, batch 2550, loss[loss=0.16, simple_loss=0.2685, pruned_loss=0.02578, over 7429.00 frames.], tot_loss[loss=0.1568, simple_loss=0.257, pruned_loss=0.02832, over 1432295.67 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:38:18,033 INFO [train.py:763] (2/8) Epoch 38, batch 2600, loss[loss=0.1744, simple_loss=0.2795, pruned_loss=0.03463, over 7176.00 frames.], tot_loss[loss=0.1575, simple_loss=0.258, pruned_loss=0.02848, over 1429915.64 frames.], batch size: 26, lr: 1.99e-04
+2022-05-01 00:39:23,360 INFO [train.py:763] (2/8) Epoch 38, batch 2650, loss[loss=0.1791, simple_loss=0.2814, pruned_loss=0.03843, over 7121.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2578, pruned_loss=0.0287, over 1431183.02 frames.], batch size: 28, lr: 1.99e-04
+2022-05-01 00:40:27,510 INFO [train.py:763] (2/8) Epoch 38, batch 2700, loss[loss=0.1846, simple_loss=0.2962, pruned_loss=0.03648, over 7287.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2572, pruned_loss=0.02824, over 1428737.95 frames.], batch size: 25, lr: 1.99e-04
+2022-05-01 00:41:33,241 INFO [train.py:763] (2/8) Epoch 38, batch 2750, loss[loss=0.1423, simple_loss=0.2428, pruned_loss=0.02091, over 7151.00 frames.], tot_loss[loss=0.157, simple_loss=0.2573, pruned_loss=0.02839, over 1428470.16 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:42:38,763 INFO [train.py:763] (2/8) Epoch 38, batch 2800, loss[loss=0.1504, simple_loss=0.2615, pruned_loss=0.01969, over 7330.00 frames.], tot_loss[loss=0.158, simple_loss=0.2584, pruned_loss=0.02879, over 1425362.15 frames.], batch size: 22, lr: 1.99e-04
+2022-05-01 00:43:44,125 INFO [train.py:763] (2/8) Epoch 38, batch 2850, loss[loss=0.1427, simple_loss=0.2495, pruned_loss=0.0179, over 6455.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2585, pruned_loss=0.02854, over 1425397.49 frames.], batch size: 38, lr: 1.99e-04
+2022-05-01 00:44:49,672 INFO [train.py:763] (2/8) Epoch 38, batch 2900, loss[loss=0.1697, simple_loss=0.2724, pruned_loss=0.03348, over 7314.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2583, pruned_loss=0.0284, over 1424526.86 frames.], batch size: 21, lr: 1.99e-04
+2022-05-01 00:45:55,138 INFO [train.py:763] (2/8) Epoch 38, batch 2950, loss[loss=0.1685, simple_loss=0.2747, pruned_loss=0.03116, over 7321.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2578, pruned_loss=0.02851, over 1427968.72 frames.], batch size: 22, lr: 1.99e-04
+2022-05-01 00:47:00,413 INFO [train.py:763] (2/8) Epoch 38, batch 3000, loss[loss=0.1643, simple_loss=0.2645, pruned_loss=0.032, over 7231.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2583, pruned_loss=0.02862, over 1428613.01 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:47:00,414 INFO [train.py:783] (2/8) Computing validation loss
+2022-05-01 00:47:15,873 INFO [train.py:792] (2/8) Epoch 38, validation: loss=0.1707, simple_loss=0.2648, pruned_loss=0.03834, over 698248.00 frames.
+2022-05-01 00:48:21,028 INFO [train.py:763] (2/8) Epoch 38, batch 3050, loss[loss=0.147, simple_loss=0.2401, pruned_loss=0.02693, over 7135.00 frames.], tot_loss[loss=0.158, simple_loss=0.2584, pruned_loss=0.0288, over 1425669.74 frames.], batch size: 17, lr: 1.99e-04
+2022-05-01 00:49:26,201 INFO [train.py:763] (2/8) Epoch 38, batch 3100, loss[loss=0.1548, simple_loss=0.2667, pruned_loss=0.02146, over 6635.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2586, pruned_loss=0.02909, over 1417821.90 frames.], batch size: 38, lr: 1.99e-04
+2022-05-01 00:50:31,504 INFO [train.py:763] (2/8) Epoch 38, batch 3150, loss[loss=0.1866, simple_loss=0.2843, pruned_loss=0.0445, over 7417.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2585, pruned_loss=0.02866, over 1422929.03 frames.], batch size: 21, lr: 1.99e-04
+2022-05-01 00:51:36,872 INFO [train.py:763] (2/8) Epoch 38, batch 3200, loss[loss=0.1454, simple_loss=0.245, pruned_loss=0.0229, over 6299.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2583, pruned_loss=0.02864, over 1423753.04 frames.], batch size: 37, lr: 1.99e-04
+2022-05-01 00:52:42,219 INFO [train.py:763] (2/8) Epoch 38, batch 3250, loss[loss=0.1777, simple_loss=0.2767, pruned_loss=0.03935, over 6284.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2591, pruned_loss=0.02869, over 1423670.73 frames.], batch size: 38, lr: 1.99e-04
+2022-05-01 00:53:47,528 INFO [train.py:763] (2/8) Epoch 38, batch 3300, loss[loss=0.1581, simple_loss=0.262, pruned_loss=0.02715, over 7162.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2583, pruned_loss=0.02838, over 1424215.30 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:54:52,911 INFO [train.py:763] (2/8) Epoch 38, batch 3350, loss[loss=0.1335, simple_loss=0.2194, pruned_loss=0.02378, over 7134.00 frames.], tot_loss[loss=0.1564, simple_loss=0.257, pruned_loss=0.02794, over 1426048.77 frames.], batch size: 17, lr: 1.99e-04
+2022-05-01 00:55:59,017 INFO [train.py:763] (2/8) Epoch 38, batch 3400, loss[loss=0.1618, simple_loss=0.2591, pruned_loss=0.03227, over 7358.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2568, pruned_loss=0.02807, over 1427646.34 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:57:06,504 INFO [train.py:763] (2/8) Epoch 38, batch 3450, loss[loss=0.1938, simple_loss=0.3087, pruned_loss=0.03951, over 7180.00 frames.], tot_loss[loss=0.1569, simple_loss=0.257, pruned_loss=0.02841, over 1420291.86 frames.], batch size: 23, lr: 1.99e-04
+2022-05-01 00:58:13,605 INFO [train.py:763] (2/8) Epoch 38, batch 3500, loss[loss=0.1415, simple_loss=0.2398, pruned_loss=0.0216, over 7159.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2579, pruned_loss=0.02892, over 1421725.76 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:59:19,211 INFO [train.py:763] (2/8) Epoch 38, batch 3550, loss[loss=0.163, simple_loss=0.2707, pruned_loss=0.02767, over 7342.00 frames.], tot_loss[loss=0.157, simple_loss=0.257, pruned_loss=0.02848, over 1424170.87 frames.], batch size: 22, lr: 1.99e-04
+2022-05-01 01:00:25,361 INFO [train.py:763] (2/8) Epoch 38, batch 3600, loss[loss=0.1294, simple_loss=0.2169, pruned_loss=0.02095, over 7286.00 frames.], tot_loss[loss=0.157, simple_loss=0.257, pruned_loss=0.02851, over 1424654.52 frames.], batch size: 18, lr: 1.99e-04
+2022-05-01 01:01:30,571 INFO [train.py:763] (2/8) Epoch 38, batch 3650, loss[loss=0.1567, simple_loss=0.2548, pruned_loss=0.02927, over 7072.00 frames.], tot_loss[loss=0.1568, simple_loss=0.257, pruned_loss=0.02834, over 1425921.88 frames.], batch size: 28, lr: 1.99e-04
+2022-05-01 01:02:35,700 INFO [train.py:763] (2/8) Epoch 38, batch 3700, loss[loss=0.155, simple_loss=0.2639, pruned_loss=0.0231, over 6701.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2573, pruned_loss=0.02855, over 1422904.74 frames.], batch size: 38, lr: 1.99e-04
+2022-05-01 01:03:41,345 INFO [train.py:763] (2/8) Epoch 38, batch 3750, loss[loss=0.1894, simple_loss=0.2815, pruned_loss=0.04867, over 7193.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2574, pruned_loss=0.02884, over 1416469.18 frames.], batch size: 23, lr: 1.98e-04
+2022-05-01 01:04:46,825 INFO [train.py:763] (2/8) Epoch 38, batch 3800, loss[loss=0.1517, simple_loss=0.2457, pruned_loss=0.0289, over 7354.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2572, pruned_loss=0.02847, over 1422943.45 frames.], batch size: 19, lr: 1.98e-04
+2022-05-01 01:05:52,022 INFO [train.py:763] (2/8) Epoch 38, batch 3850, loss[loss=0.1921, simple_loss=0.2908, pruned_loss=0.04671, over 5188.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2574, pruned_loss=0.02862, over 1419549.03 frames.], batch size: 52, lr: 1.98e-04
+2022-05-01 01:06:57,233 INFO [train.py:763] (2/8) Epoch 38, batch 3900, loss[loss=0.1795, simple_loss=0.2882, pruned_loss=0.03536, over 7147.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2578, pruned_loss=0.02882, over 1419922.25 frames.], batch size: 28, lr: 1.98e-04
+2022-05-01 01:08:02,830 INFO [train.py:763] (2/8) Epoch 38, batch 3950, loss[loss=0.1637, simple_loss=0.2675, pruned_loss=0.02998, over 7273.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2574, pruned_loss=0.02852, over 1421936.70 frames.], batch size: 25, lr: 1.98e-04
+2022-05-01 01:09:08,083 INFO [train.py:763] (2/8) Epoch 38, batch 4000, loss[loss=0.1561, simple_loss=0.25, pruned_loss=0.03112, over 6833.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2571, pruned_loss=0.0286, over 1424680.13 frames.], batch size: 31, lr: 1.98e-04
+2022-05-01 01:10:13,450 INFO [train.py:763] (2/8) Epoch 38, batch 4050, loss[loss=0.1558, simple_loss=0.2557, pruned_loss=0.02791, over 6727.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2573, pruned_loss=0.02852, over 1422892.05 frames.], batch size: 31, lr: 1.98e-04
+2022-05-01 01:11:18,886 INFO [train.py:763] (2/8) Epoch 38, batch 4100, loss[loss=0.173, simple_loss=0.2929, pruned_loss=0.02658, over 7217.00 frames.], tot_loss[loss=0.1572, simple_loss=0.257, pruned_loss=0.0287, over 1421505.57 frames.], batch size: 21, lr: 1.98e-04
+2022-05-01 01:12:24,226 INFO [train.py:763] (2/8) Epoch 38, batch 4150, loss[loss=0.1682, simple_loss=0.2788, pruned_loss=0.02875, over 7220.00 frames.], tot_loss[loss=0.157, simple_loss=0.257, pruned_loss=0.02852, over 1419262.67 frames.], batch size: 21, lr: 1.98e-04
+2022-05-01 01:13:30,533 INFO [train.py:763] (2/8) Epoch 38, batch 4200, loss[loss=0.154, simple_loss=0.2494, pruned_loss=0.02928, over 6815.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.0286, over 1418187.47 frames.], batch size: 31, lr: 1.98e-04
+2022-05-01 01:14:35,833 INFO [train.py:763] (2/8) Epoch 38, batch 4250, loss[loss=0.1605, simple_loss=0.2543, pruned_loss=0.03331, over 7141.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.02874, over 1415764.25 frames.], batch size: 17, lr: 1.98e-04
+2022-05-01 01:15:41,251 INFO [train.py:763] (2/8) Epoch 38, batch 4300, loss[loss=0.1686, simple_loss=0.2673, pruned_loss=0.03491, over 7292.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2593, pruned_loss=0.02909, over 1416674.02 frames.], batch size: 25, lr: 1.98e-04
+2022-05-01 01:16:46,654 INFO [train.py:763] (2/8) Epoch 38, batch 4350, loss[loss=0.1506, simple_loss=0.264, pruned_loss=0.01859, over 7435.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2596, pruned_loss=0.02905, over 1413495.89 frames.], batch size: 20, lr: 1.98e-04
+2022-05-01 01:17:51,726 INFO [train.py:763] (2/8) Epoch 38, batch 4400, loss[loss=0.1463, simple_loss=0.2559, pruned_loss=0.01833, over 7332.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2602, pruned_loss=0.02919, over 1410385.35 frames.], batch size: 22, lr: 1.98e-04
+2022-05-01 01:18:57,800 INFO [train.py:763] (2/8) Epoch 38, batch 4450, loss[loss=0.1264, simple_loss=0.2264, pruned_loss=0.01326, over 7006.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2612, pruned_loss=0.02962, over 1397226.94 frames.], batch size: 16, lr: 1.98e-04
+2022-05-01 01:20:03,886 INFO [train.py:763] (2/8) Epoch 38, batch 4500, loss[loss=0.1525, simple_loss=0.2442, pruned_loss=0.03042, over 7172.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2621, pruned_loss=0.03022, over 1386160.23 frames.], batch size: 18, lr: 1.98e-04
+2022-05-01 01:21:09,320 INFO [train.py:763] (2/8) Epoch 38, batch 4550, loss[loss=0.2006, simple_loss=0.3052, pruned_loss=0.04797, over 4921.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2635, pruned_loss=0.03111, over 1347700.88 frames.], batch size: 52, lr: 1.98e-04
+2022-05-01 01:22:39,304 INFO [train.py:763] (2/8) Epoch 39, batch 0, loss[loss=0.1987, simple_loss=0.3039, pruned_loss=0.04681, over 7310.00 frames.], tot_loss[loss=0.1987, simple_loss=0.3039, pruned_loss=0.04681, over 7310.00 frames.], batch size: 24, lr: 1.96e-04
+2022-05-01 01:23:44,999 INFO [train.py:763] (2/8) Epoch 39, batch 50, loss[loss=0.1161, simple_loss=0.2048, pruned_loss=0.01367, over 7305.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2622, pruned_loss=0.03038, over 316609.57 frames.], batch size: 17, lr: 1.95e-04
+2022-05-01 01:24:50,352 INFO [train.py:763] (2/8) Epoch 39, batch 100, loss[loss=0.1596, simple_loss=0.2578, pruned_loss=0.03073, over 7361.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2582, pruned_loss=0.02875, over 561328.35 frames.], batch size: 19, lr: 1.95e-04
+2022-05-01 01:25:56,216 INFO [train.py:763] (2/8) Epoch 39, batch 150, loss[loss=0.1725, simple_loss=0.2717, pruned_loss=0.03663, over 7228.00 frames.], tot_loss[loss=0.1567, simple_loss=0.256, pruned_loss=0.0287, over 753550.45 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:27:01,293 INFO [train.py:763] (2/8) Epoch 39, batch 200, loss[loss=0.1507, simple_loss=0.2459, pruned_loss=0.02768, over 7432.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2578, pruned_loss=0.02903, over 901991.11 frames.], batch size: 18, lr: 1.95e-04
+2022-05-01 01:28:06,658 INFO [train.py:763] (2/8) Epoch 39, batch 250, loss[loss=0.1675, simple_loss=0.2728, pruned_loss=0.03114, over 7442.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2581, pruned_loss=0.02862, over 1016014.12 frames.], batch size: 22, lr: 1.95e-04
+2022-05-01 01:29:11,528 INFO [train.py:763] (2/8) Epoch 39, batch 300, loss[loss=0.1645, simple_loss=0.2591, pruned_loss=0.03499, over 7265.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2571, pruned_loss=0.0284, over 1106498.55 frames.], batch size: 24, lr: 1.95e-04
+2022-05-01 01:30:16,874 INFO [train.py:763] (2/8) Epoch 39, batch 350, loss[loss=0.154, simple_loss=0.2688, pruned_loss=0.01955, over 7153.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2575, pruned_loss=0.02871, over 1171144.67 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:31:22,218 INFO [train.py:763] (2/8) Epoch 39, batch 400, loss[loss=0.1807, simple_loss=0.2814, pruned_loss=0.03995, over 7149.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2588, pruned_loss=0.02933, over 1228179.80 frames.], batch size: 26, lr: 1.95e-04
+2022-05-01 01:32:27,452 INFO [train.py:763] (2/8) Epoch 39, batch 450, loss[loss=0.1688, simple_loss=0.2756, pruned_loss=0.03104, over 7309.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2577, pruned_loss=0.02852, over 1272192.80 frames.], batch size: 25, lr: 1.95e-04
+2022-05-01 01:33:32,865 INFO [train.py:763] (2/8) Epoch 39, batch 500, loss[loss=0.1432, simple_loss=0.2498, pruned_loss=0.01826, over 7320.00 frames.], tot_loss[loss=0.157, simple_loss=0.2572, pruned_loss=0.0284, over 1305131.14 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:34:38,278 INFO [train.py:763] (2/8) Epoch 39, batch 550, loss[loss=0.1883, simple_loss=0.292, pruned_loss=0.04232, over 7235.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2562, pruned_loss=0.02827, over 1326844.83 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:35:43,496 INFO [train.py:763] (2/8) Epoch 39, batch 600, loss[loss=0.1654, simple_loss=0.2545, pruned_loss=0.03818, over 7259.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2557, pruned_loss=0.02821, over 1348411.11 frames.], batch size: 19, lr: 1.95e-04
+2022-05-01 01:36:48,735 INFO [train.py:763] (2/8) Epoch 39, batch 650, loss[loss=0.1439, simple_loss=0.2496, pruned_loss=0.01915, over 7223.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2562, pruned_loss=0.02845, over 1366782.12 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:37:53,920 INFO [train.py:763] (2/8) Epoch 39, batch 700, loss[loss=0.1482, simple_loss=0.2398, pruned_loss=0.02833, over 7268.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2567, pruned_loss=0.02858, over 1380170.39 frames.], batch size: 18, lr: 1.95e-04
+2022-05-01 01:38:59,262 INFO [train.py:763] (2/8) Epoch 39, batch 750, loss[loss=0.1489, simple_loss=0.2391, pruned_loss=0.02931, over 7360.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2564, pruned_loss=0.02825, over 1386340.76 frames.], batch size: 19, lr: 1.95e-04
+2022-05-01 01:40:04,490 INFO [train.py:763] (2/8) Epoch 39, batch 800, loss[loss=0.1607, simple_loss=0.27, pruned_loss=0.02576, over 7112.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2565, pruned_loss=0.02824, over 1395422.95 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:41:18,499 INFO [train.py:763] (2/8) Epoch 39, batch 850, loss[loss=0.1416, simple_loss=0.2366, pruned_loss=0.02335, over 7138.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2566, pruned_loss=0.02817, over 1402232.05 frames.], batch size: 17, lr: 1.95e-04
+2022-05-01 01:42:32,262 INFO [train.py:763] (2/8) Epoch 39, batch 900, loss[loss=0.1806, simple_loss=0.2866, pruned_loss=0.03731, over 7203.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2574, pruned_loss=0.0285, over 1408488.49 frames.], batch size: 23, lr: 1.95e-04
+2022-05-01 01:43:55,208 INFO [train.py:763] (2/8) Epoch 39, batch 950, loss[loss=0.18, simple_loss=0.2748, pruned_loss=0.04261, over 5030.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2578, pruned_loss=0.02856, over 1412115.52 frames.], batch size: 52, lr: 1.95e-04
+2022-05-01 01:45:01,220 INFO [train.py:763] (2/8) Epoch 39, batch 1000, loss[loss=0.1537, simple_loss=0.2568, pruned_loss=0.02533, over 7118.00 frames.], tot_loss[loss=0.158, simple_loss=0.2584, pruned_loss=0.0288, over 1411352.99 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:46:06,269 INFO [train.py:763] (2/8) Epoch 39, batch 1050, loss[loss=0.168, simple_loss=0.2742, pruned_loss=0.03089, over 7224.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2586, pruned_loss=0.02865, over 1410020.65 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:47:29,491 INFO [train.py:763] (2/8) Epoch 39, batch 1100, loss[loss=0.1391, simple_loss=0.239, pruned_loss=0.01956, over 7173.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2576, pruned_loss=0.02811, over 1408097.97 frames.], batch size: 18, lr: 1.95e-04
+2022-05-01 01:48:43,940 INFO [train.py:763] (2/8) Epoch 39, batch 1150, loss[loss=0.1479, simple_loss=0.2617, pruned_loss=0.01703, over 6691.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2567, pruned_loss=0.02784, over 1414898.55 frames.], batch size: 31, lr: 1.95e-04
+2022-05-01 01:49:48,901 INFO [train.py:763] (2/8) Epoch 39, batch 1200, loss[loss=0.1738, simple_loss=0.2698, pruned_loss=0.03891, over 6418.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2574, pruned_loss=0.02784, over 1417473.52 frames.], batch size: 38, lr: 1.95e-04
+2022-05-01 01:50:54,366 INFO [train.py:763] (2/8) Epoch 39, batch 1250, loss[loss=0.1579, simple_loss=0.258, pruned_loss=0.02886, over 7307.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2572, pruned_loss=0.02803, over 1420692.52 frames.], batch size: 25, lr: 1.95e-04
+2022-05-01 01:51:59,438 INFO [train.py:763] (2/8) Epoch 39, batch 1300, loss[loss=0.1537, simple_loss=0.2576, pruned_loss=0.02491, over 7444.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2569, pruned_loss=0.02767, over 1421409.05 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:53:04,813 INFO [train.py:763] (2/8) Epoch 39, batch 1350, loss[loss=0.1415, simple_loss=0.2515, pruned_loss=0.01581, over 6560.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2564, pruned_loss=0.02769, over 1421616.93 frames.], batch size: 37, lr: 1.95e-04
+2022-05-01 01:54:11,087 INFO [train.py:763] (2/8) Epoch 39, batch 1400, loss[loss=0.1634, simple_loss=0.2715, pruned_loss=0.02764, over 6488.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2571, pruned_loss=0.02793, over 1423023.97 frames.], batch size: 38, lr: 1.95e-04
+2022-05-01 01:55:16,350 INFO [train.py:763] (2/8) Epoch 39, batch 1450, loss[loss=0.1759, simple_loss=0.2719, pruned_loss=0.03992, over 7196.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2578, pruned_loss=0.02824, over 1424702.53 frames.], batch size: 23, lr: 1.95e-04
+2022-05-01 01:56:21,442 INFO [train.py:763] (2/8) Epoch 39, batch 1500, loss[loss=0.1423, simple_loss=0.2408, pruned_loss=0.02184, over 7124.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2579, pruned_loss=0.02828, over 1425984.89 frames.], batch size: 17, lr: 1.95e-04
+2022-05-01 01:57:28,664 INFO [train.py:763] (2/8) Epoch 39, batch 1550, loss[loss=0.1795, simple_loss=0.2721, pruned_loss=0.04348, over 7197.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2577, pruned_loss=0.02845, over 1423884.23 frames.], batch size: 23, lr: 1.95e-04
+2022-05-01 01:58:35,227 INFO [train.py:763] (2/8) Epoch 39, batch 1600, loss[loss=0.16, simple_loss=0.2631, pruned_loss=0.02848, over 7068.00 frames.], tot_loss[loss=0.1577, simple_loss=0.258, pruned_loss=0.02873, over 1426457.93 frames.], batch size: 28, lr: 1.95e-04
+2022-05-01 01:59:41,354 INFO [train.py:763] (2/8) Epoch 39, batch 1650, loss[loss=0.2064, simple_loss=0.3066, pruned_loss=0.05305, over 5343.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2583, pruned_loss=0.02858, over 1419933.00 frames.], batch size: 54, lr: 1.95e-04
+2022-05-01 02:00:47,161 INFO [train.py:763] (2/8) Epoch 39, batch 1700, loss[loss=0.1387, simple_loss=0.2332, pruned_loss=0.02207, over 7011.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2577, pruned_loss=0.02854, over 1413303.56 frames.], batch size: 16, lr: 1.95e-04
+2022-05-01 02:01:53,358 INFO [train.py:763] (2/8) Epoch 39, batch 1750, loss[loss=0.1417, simple_loss=0.2427, pruned_loss=0.0204, over 7318.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2575, pruned_loss=0.02837, over 1415270.60 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 02:02:58,279 INFO [train.py:763] (2/8) Epoch 39, batch 1800, loss[loss=0.1717, simple_loss=0.282, pruned_loss=0.03068, over 7335.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.02857, over 1417039.28 frames.], batch size: 22, lr: 1.95e-04
+2022-05-01 02:04:03,599 INFO [train.py:763] (2/8) Epoch 39, batch 1850, loss[loss=0.1546, simple_loss=0.248, pruned_loss=0.03063, over 7076.00 frames.], tot_loss[loss=0.158, simple_loss=0.2585, pruned_loss=0.02875, over 1420653.48 frames.], batch size: 18, lr: 1.95e-04
+2022-05-01 02:05:08,882 INFO [train.py:763] (2/8) Epoch 39, batch 1900, loss[loss=0.1807, simple_loss=0.2762, pruned_loss=0.04255, over 7161.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2591, pruned_loss=0.02856, over 1424950.94 frames.], batch size: 19, lr: 1.94e-04
+2022-05-01 02:06:14,308 INFO [train.py:763] (2/8) Epoch 39, batch 1950, loss[loss=0.1691, simple_loss=0.2721, pruned_loss=0.03303, over 5193.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2597, pruned_loss=0.02898, over 1419605.33 frames.], batch size: 52, lr: 1.94e-04
+2022-05-01 02:07:19,644 INFO [train.py:763] (2/8) Epoch 39, batch 2000, loss[loss=0.1537, simple_loss=0.2567, pruned_loss=0.02538, over 7064.00 frames.], tot_loss[loss=0.1582, simple_loss=0.259, pruned_loss=0.02872, over 1422778.74 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:08:24,807 INFO [train.py:763] (2/8) Epoch 39, batch 2050, loss[loss=0.1499, simple_loss=0.2568, pruned_loss=0.0215, over 7429.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2582, pruned_loss=0.02836, over 1426962.39 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:09:30,528 INFO [train.py:763] (2/8) Epoch 39, batch 2100, loss[loss=0.1488, simple_loss=0.2415, pruned_loss=0.02805, over 7405.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2573, pruned_loss=0.02791, over 1426356.04 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:10:35,926 INFO [train.py:763] (2/8) Epoch 39, batch 2150, loss[loss=0.1464, simple_loss=0.2553, pruned_loss=0.01881, over 7149.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2573, pruned_loss=0.028, over 1430397.20 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:11:43,126 INFO [train.py:763] (2/8) Epoch 39, batch 2200, loss[loss=0.1843, simple_loss=0.2808, pruned_loss=0.04388, over 7236.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2575, pruned_loss=0.0281, over 1433417.68 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:12:48,268 INFO [train.py:763] (2/8) Epoch 39, batch 2250, loss[loss=0.1873, simple_loss=0.2878, pruned_loss=0.0434, over 7199.00 frames.], tot_loss[loss=0.1573, simple_loss=0.258, pruned_loss=0.0283, over 1431697.16 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:13:53,526 INFO [train.py:763] (2/8) Epoch 39, batch 2300, loss[loss=0.1591, simple_loss=0.2593, pruned_loss=0.02949, over 7431.00 frames.], tot_loss[loss=0.157, simple_loss=0.2573, pruned_loss=0.02836, over 1428709.50 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:15:00,685 INFO [train.py:763] (2/8) Epoch 39, batch 2350, loss[loss=0.1696, simple_loss=0.2825, pruned_loss=0.0284, over 7326.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2569, pruned_loss=0.0281, over 1427358.06 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:16:07,732 INFO [train.py:763] (2/8) Epoch 39, batch 2400, loss[loss=0.1569, simple_loss=0.2581, pruned_loss=0.02788, over 7194.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2569, pruned_loss=0.02817, over 1427092.94 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:17:13,326 INFO [train.py:763] (2/8) Epoch 39, batch 2450, loss[loss=0.1722, simple_loss=0.2754, pruned_loss=0.03452, over 7061.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2583, pruned_loss=0.02839, over 1422116.89 frames.], batch size: 28, lr: 1.94e-04
+2022-05-01 02:18:19,516 INFO [train.py:763] (2/8) Epoch 39, batch 2500, loss[loss=0.1536, simple_loss=0.2524, pruned_loss=0.02746, over 7412.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2581, pruned_loss=0.02836, over 1419392.58 frames.], batch size: 21, lr: 1.94e-04
+2022-05-01 02:19:24,719 INFO [train.py:763] (2/8) Epoch 39, batch 2550, loss[loss=0.1679, simple_loss=0.2747, pruned_loss=0.03054, over 7076.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2589, pruned_loss=0.02899, over 1419751.38 frames.], batch size: 28, lr: 1.94e-04
+2022-05-01 02:20:31,561 INFO [train.py:763] (2/8) Epoch 39, batch 2600, loss[loss=0.1455, simple_loss=0.244, pruned_loss=0.02352, over 7333.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2578, pruned_loss=0.0286, over 1419324.18 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:21:37,531 INFO [train.py:763] (2/8) Epoch 39, batch 2650, loss[loss=0.146, simple_loss=0.2354, pruned_loss=0.02829, over 7162.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2577, pruned_loss=0.02883, over 1421546.52 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:22:43,384 INFO [train.py:763] (2/8) Epoch 39, batch 2700, loss[loss=0.1781, simple_loss=0.2919, pruned_loss=0.03216, over 7154.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2587, pruned_loss=0.02874, over 1422738.12 frames.], batch size: 26, lr: 1.94e-04
+2022-05-01 02:23:48,609 INFO [train.py:763] (2/8) Epoch 39, batch 2750, loss[loss=0.1577, simple_loss=0.2662, pruned_loss=0.02457, over 7305.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2583, pruned_loss=0.02834, over 1425110.62 frames.], batch size: 24, lr: 1.94e-04
+2022-05-01 02:24:53,686 INFO [train.py:763] (2/8) Epoch 39, batch 2800, loss[loss=0.168, simple_loss=0.2605, pruned_loss=0.03774, over 7461.00 frames.], tot_loss[loss=0.1581, simple_loss=0.259, pruned_loss=0.02864, over 1422494.60 frames.], batch size: 19, lr: 1.94e-04
+2022-05-01 02:25:58,653 INFO [train.py:763] (2/8) Epoch 39, batch 2850, loss[loss=0.1639, simple_loss=0.2683, pruned_loss=0.02976, over 6378.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2591, pruned_loss=0.02878, over 1420095.07 frames.], batch size: 38, lr: 1.94e-04
+2022-05-01 02:27:03,578 INFO [train.py:763] (2/8) Epoch 39, batch 2900, loss[loss=0.1438, simple_loss=0.2344, pruned_loss=0.02661, over 7066.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2581, pruned_loss=0.02834, over 1419799.14 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:28:08,497 INFO [train.py:763] (2/8) Epoch 39, batch 2950, loss[loss=0.1698, simple_loss=0.2803, pruned_loss=0.02963, over 7280.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2598, pruned_loss=0.02925, over 1418856.43 frames.], batch size: 24, lr: 1.94e-04
+2022-05-01 02:29:13,387 INFO [train.py:763] (2/8) Epoch 39, batch 3000, loss[loss=0.1554, simple_loss=0.2656, pruned_loss=0.0226, over 7338.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2604, pruned_loss=0.02942, over 1413875.45 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:29:13,388 INFO [train.py:783] (2/8) Computing validation loss
+2022-05-01 02:29:28,415 INFO [train.py:792] (2/8) Epoch 39, validation: loss=0.1688, simple_loss=0.2638, pruned_loss=0.03694, over 698248.00 frames.
+2022-05-01 02:30:33,955 INFO [train.py:763] (2/8) Epoch 39, batch 3050, loss[loss=0.1656, simple_loss=0.2773, pruned_loss=0.02699, over 7348.00 frames.], tot_loss[loss=0.1591, simple_loss=0.26, pruned_loss=0.02912, over 1415728.15 frames.], batch size: 19, lr: 1.94e-04
+2022-05-01 02:31:41,151 INFO [train.py:763] (2/8) Epoch 39, batch 3100, loss[loss=0.1546, simple_loss=0.2504, pruned_loss=0.0294, over 7186.00 frames.], tot_loss[loss=0.1588, simple_loss=0.26, pruned_loss=0.02881, over 1417947.53 frames.], batch size: 26, lr: 1.94e-04
+2022-05-01 02:32:47,800 INFO [train.py:763] (2/8) Epoch 39, batch 3150, loss[loss=0.1744, simple_loss=0.2735, pruned_loss=0.03763, over 7130.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2589, pruned_loss=0.02819, over 1421385.01 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:33:53,388 INFO [train.py:763] (2/8) Epoch 39, batch 3200, loss[loss=0.1917, simple_loss=0.2956, pruned_loss=0.04395, over 5131.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2594, pruned_loss=0.02839, over 1422291.61 frames.], batch size: 53, lr: 1.94e-04
+2022-05-01 02:34:58,486 INFO [train.py:763] (2/8) Epoch 39, batch 3250, loss[loss=0.1562, simple_loss=0.2573, pruned_loss=0.02753, over 7383.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2598, pruned_loss=0.02831, over 1420773.57 frames.], batch size: 23, lr: 1.94e-04
+2022-05-01 02:36:03,617 INFO [train.py:763] (2/8) Epoch 39, batch 3300, loss[loss=0.1728, simple_loss=0.2842, pruned_loss=0.03072, over 7119.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2592, pruned_loss=0.02815, over 1419430.25 frames.], batch size: 21, lr: 1.94e-04
+2022-05-01 02:37:08,798 INFO [train.py:763] (2/8) Epoch 39, batch 3350, loss[loss=0.1643, simple_loss=0.2794, pruned_loss=0.02463, over 7119.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2596, pruned_loss=0.02833, over 1417129.07 frames.], batch size: 21, lr: 1.94e-04
+2022-05-01 02:38:14,796 INFO [train.py:763] (2/8) Epoch 39, batch 3400, loss[loss=0.1681, simple_loss=0.2733, pruned_loss=0.03146, over 7163.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2588, pruned_loss=0.02809, over 1417984.35 frames.], batch size: 19, lr: 1.94e-04
+2022-05-01 02:39:20,469 INFO [train.py:763] (2/8) Epoch 39, batch 3450, loss[loss=0.1403, simple_loss=0.2265, pruned_loss=0.02709, over 7281.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2595, pruned_loss=0.02834, over 1416965.44 frames.], batch size: 17, lr: 1.94e-04
+2022-05-01 02:40:25,648 INFO [train.py:763] (2/8) Epoch 39, batch 3500, loss[loss=0.152, simple_loss=0.2528, pruned_loss=0.02556, over 7308.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2599, pruned_loss=0.0284, over 1418503.57 frames.], batch size: 21, lr: 1.94e-04
+2022-05-01 02:41:31,486 INFO [train.py:763] (2/8) Epoch 39, batch 3550, loss[loss=0.1527, simple_loss=0.2552, pruned_loss=0.02511, over 7060.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2584, pruned_loss=0.02809, over 1419760.45 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:42:37,764 INFO [train.py:763] (2/8) Epoch 39, batch 3600, loss[loss=0.1808, simple_loss=0.2733, pruned_loss=0.04422, over 4852.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2575, pruned_loss=0.02787, over 1416588.24 frames.], batch size: 52, lr: 1.94e-04
+2022-05-01 02:43:44,821 INFO [train.py:763] (2/8) Epoch 39, batch 3650, loss[loss=0.1823, simple_loss=0.287, pruned_loss=0.03877, over 6388.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2575, pruned_loss=0.0277, over 1418095.90 frames.], batch size: 37, lr: 1.94e-04
+2022-05-01 02:44:50,052 INFO [train.py:763] (2/8) Epoch 39, batch 3700, loss[loss=0.1578, simple_loss=0.2549, pruned_loss=0.03034, over 7132.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2589, pruned_loss=0.02859, over 1421665.74 frames.], batch size: 17, lr: 1.94e-04
+2022-05-01 02:45:55,093 INFO [train.py:763] (2/8) Epoch 39, batch 3750, loss[loss=0.1661, simple_loss=0.2568, pruned_loss=0.03772, over 7366.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2594, pruned_loss=0.02873, over 1419159.90 frames.], batch size: 19, lr: 1.93e-04
+2022-05-01 02:47:00,703 INFO [train.py:763] (2/8) Epoch 39, batch 3800, loss[loss=0.129, simple_loss=0.2168, pruned_loss=0.02063, over 6993.00 frames.], tot_loss[loss=0.1579, simple_loss=0.259, pruned_loss=0.02837, over 1423617.30 frames.], batch size: 16, lr: 1.93e-04
+2022-05-01 02:48:07,766 INFO [train.py:763] (2/8) Epoch 39, batch 3850, loss[loss=0.1815, simple_loss=0.2725, pruned_loss=0.04524, over 7418.00 frames.], tot_loss[loss=0.1569, simple_loss=0.258, pruned_loss=0.02792, over 1420839.14 frames.], batch size: 21, lr: 1.93e-04
+2022-05-01 02:49:13,628 INFO [train.py:763] (2/8) Epoch 39, batch 3900, loss[loss=0.1777, simple_loss=0.2815, pruned_loss=0.03694, over 7192.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2577, pruned_loss=0.02784, over 1421705.18 frames.], batch size: 23, lr: 1.93e-04
+2022-05-01 02:50:20,004 INFO [train.py:763] (2/8) Epoch 39, batch 3950, loss[loss=0.1458, simple_loss=0.2411, pruned_loss=0.02524, over 7064.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2583, pruned_loss=0.0285, over 1417769.92 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 02:51:25,343 INFO [train.py:763] (2/8) Epoch 39, batch 4000, loss[loss=0.147, simple_loss=0.25, pruned_loss=0.02202, over 7144.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2583, pruned_loss=0.02856, over 1417214.23 frames.], batch size: 17, lr: 1.93e-04
+2022-05-01 02:52:30,792 INFO [train.py:763] (2/8) Epoch 39, batch 4050, loss[loss=0.214, simple_loss=0.3054, pruned_loss=0.06131, over 7208.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2583, pruned_loss=0.02866, over 1421288.64 frames.], batch size: 22, lr: 1.93e-04
+2022-05-01 02:53:35,943 INFO [train.py:763] (2/8) Epoch 39, batch 4100, loss[loss=0.1619, simple_loss=0.2667, pruned_loss=0.02854, over 7227.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2586, pruned_loss=0.02877, over 1421633.76 frames.], batch size: 20, lr: 1.93e-04
+2022-05-01 02:54:41,368 INFO [train.py:763] (2/8) Epoch 39, batch 4150, loss[loss=0.1519, simple_loss=0.2515, pruned_loss=0.02611, over 7290.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.0287, over 1422921.35 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 02:55:46,807 INFO [train.py:763] (2/8) Epoch 39, batch 4200, loss[loss=0.1414, simple_loss=0.2403, pruned_loss=0.02131, over 7160.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2586, pruned_loss=0.02881, over 1424746.74 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 02:56:52,113 INFO [train.py:763] (2/8) Epoch 39, batch 4250, loss[loss=0.1422, simple_loss=0.249, pruned_loss=0.01764, over 7318.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2578, pruned_loss=0.02877, over 1420467.26 frames.], batch size: 21, lr: 1.93e-04
+2022-05-01 02:57:57,421 INFO [train.py:763] (2/8) Epoch 39, batch 4300, loss[loss=0.1597, simple_loss=0.2618, pruned_loss=0.02884, over 7154.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2576, pruned_loss=0.02859, over 1420893.01 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 02:59:02,810 INFO [train.py:763] (2/8) Epoch 39, batch 4350, loss[loss=0.1634, simple_loss=0.2635, pruned_loss=0.03161, over 7319.00 frames.], tot_loss[loss=0.157, simple_loss=0.2573, pruned_loss=0.02835, over 1422407.73 frames.], batch size: 20, lr: 1.93e-04
+2022-05-01 03:00:09,027 INFO [train.py:763] (2/8) Epoch 39, batch 4400, loss[loss=0.1466, simple_loss=0.25, pruned_loss=0.02163, over 6783.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2577, pruned_loss=0.02837, over 1422655.93 frames.], batch size: 31, lr: 1.93e-04
+2022-05-01 03:01:14,004 INFO [train.py:763] (2/8) Epoch 39, batch 4450, loss[loss=0.1397, simple_loss=0.2402, pruned_loss=0.01965, over 7152.00 frames.], tot_loss[loss=0.1588, simple_loss=0.259, pruned_loss=0.02933, over 1410269.42 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 03:02:19,218 INFO [train.py:763] (2/8) Epoch 39, batch 4500, loss[loss=0.1624, simple_loss=0.2675, pruned_loss=0.0287, over 7213.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2593, pruned_loss=0.02927, over 1403113.79 frames.], batch size: 21, lr: 1.93e-04
+2022-05-01 03:03:25,867 INFO [train.py:763] (2/8) Epoch 39, batch 4550, loss[loss=0.1439, simple_loss=0.2312, pruned_loss=0.02828, over 6771.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2558, pruned_loss=0.02884, over 1393899.65 frames.], batch size: 15, lr: 1.93e-04
+2022-05-01 03:04:15,425 INFO [train.py:971] (2/8) Done!