diff --git "a/exp/log/log-train-2022-12-09-10-39-23-7" "b/exp/log/log-train-2022-12-09-10-39-23-7"
new file mode 100644--- /dev/null
+++ "b/exp/log/log-train-2022-12-09-10-39-23-7"
@@ -0,0 +1,6042 @@
+2022-12-09 10:39:23,964 INFO [train.py:493] (7/8) Training started
+2022-12-09 10:39:23,964 INFO [train.py:494] (7/8) {'max_sent_len': 200, 'sos_id': 1, 'eos_id': 1, 'blank_id': 0, 'lr': 0.001, 'weight_decay': 1e-06, 'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 200, 'reset_interval': 2000, 'valid_interval': 1000, 'nhead': 8, 'embedding_dim': 768, 'encoder_dim': 768, 'dim_feedforward': 2048, 'dropout': 0.1, 'env_info': {'k2-version': '1.22', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '96c9a2aece2a3a7633da07740e24fa3d96f5498c', 'k2-git-date': 'Thu Nov 10 08:14:02 2022', 'lhotse-version': '1.10.0', 'torch-version': '1.12.1', 'torch-cuda-available': True, 'torch-cuda-version': '11.6', 'python-version': '3.8', 'icefall-git-branch': 'transformer_lm', 'icefall-git-sha1': '5b028fe-dirty', 'icefall-git-date': 'Thu Dec 8 23:29:10 2022', 'icefall-path': '/ceph-data4/yangxiaoyu/softwares/icefall_development/icefall_zipformer_mvq', 'k2-path': '/ceph-data4/yangxiaoyu/softwares/anaconda3/envs/k2_latest/lib/python3.8/site-packages/k2/__init__.py', 'lhotse-path': '/ceph-data4/yangxiaoyu/softwares/anaconda3/envs/k2_latest/lib/python3.8/site-packages/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-1-0307195509-567fcb96d6-kdztg', 'IP address': '10.177.22.10'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 20, 'start_epoch': 0, 'exp_dir': PosixPath('transformer_lm/exp_full_libri_16layer_maxlen200_8gpu'), 'use_fp16': False, 'batch_size': 70, 'lm_data': './transformer_lm/libri_lm_training_bpe500/sorted-lm-data-libri-lm_maxlen200.pt', 'lm_data_valid': './transformer_lm/libri_lm_training_bpe500/sorted_lm_data-test.pt', 'vocab_size': 500, 'num_layers': 16, 'tie_weights': True, 'seed': 42}
+2022-12-09 10:39:23,964 INFO [train.py:505] (7/8) Device: cuda:7
+2022-12-09 10:39:23,964 INFO [train.py:507] (7/8) About to create model
+2022-12-09 10:39:24,446 INFO [model.py:64] (7/8) Tying weights
+2022-12-09 10:39:24,448 INFO [train.py:520] (7/8) Number of model parameters: 98611638
+2022-12-09 10:39:27,368 INFO [train.py:539] (7/8) Loading LM training data from ./transformer_lm/libri_lm_training_bpe500/sorted-lm-data-libri-lm_maxlen200.pt
+2022-12-09 10:39:41,359 INFO [train.py:546] (7/8) Loading LM validation data from ./transformer_lm/libri_lm_training_bpe500/sorted_lm_data-test.pt
+2022-12-09 10:39:44,760 INFO [train.py:421] (7/8) Epoch 0, batch 0, loss[loss=77.6, over 6370.00 frames. , ppl: 5.047094899427535e+33] tot_loss[loss=77.6, over 6370.00 frames. , ppl: 5.047094899427535e+33], batch size: 70
+2022-12-09 10:39:44,762 INFO [distributed.py:995] (7/8) Reducer buckets have been rebuilt in this iteration.
+2022-12-09 10:41:21,515 INFO [train.py:421] (7/8) Epoch 0, batch 200, loss[loss=7.932, over 3990.00 frames. , ppl: 2784.107745604238] tot_loss[loss=18.52, over 525014.00 frames. , ppl: 110937223.13436946], batch size: 70
+2022-12-09 10:43:01,688 INFO [train.py:421] (7/8) Epoch 0, batch 400, loss[loss=6.704, over 1960.00 frames. , ppl: 815.2832141062848] tot_loss[loss=12.64, over 1007934.77 frames. , ppl: 309251.9440250581], batch size: 70
+2022-12-09 10:44:42,143 INFO [train.py:421] (7/8) Epoch 0, batch 600, loss[loss=6.448, over 3150.00 frames. , ppl: 631.30646030096] tot_loss[loss=10.42, over 1429496.64 frames. , ppl: 33655.349358208674], batch size: 70
+2022-12-09 10:46:22,398 INFO [train.py:421] (7/8) Epoch 0, batch 800, loss[loss=5.344, over 4690.00 frames. , ppl: 209.32905004970974] tot_loss[loss=9.103, over 1863910.32 frames. , ppl: 8986.060319090426], batch size: 70
+2022-12-09 10:48:02,281 INFO [train.py:421] (7/8) Epoch 0, batch 1000, loss[loss=5.572, over 2240.00 frames. , ppl: 262.862670737393] tot_loss[loss=8.246, over 2206384.25 frames. , ppl: 3811.6237371226894], batch size: 70
+2022-12-09 10:48:02,282 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 10:48:03,028 INFO [train.py:452] (7/8) Epoch 0, validation: loss=5.053, over 211138.00 frames. , ppl: 156.50471436114304
+2022-12-09 10:49:43,715 INFO [train.py:421] (7/8) Epoch 0, batch 1200, loss[loss=5.151, over 2310.00 frames. , ppl: 172.65469690540428] tot_loss[loss=7.707, over 2512340.94 frames. , ppl: 2223.1058633325197], batch size: 70
+2022-12-09 10:51:23,224 INFO [train.py:421] (7/8) Epoch 0, batch 1400, loss[loss=5.318, over 7350.00 frames. , ppl: 203.95267215480453] tot_loss[loss=7.231, over 2870159.60 frames. , ppl: 1381.578948374082], batch size: 70
+2022-12-09 10:53:02,876 INFO [train.py:421] (7/8) Epoch 0, batch 1600, loss[loss=4.865, over 2800.00 frames. , ppl: 129.67971268169114] tot_loss[loss=6.878, over 3095407.98 frames. , ppl: 971.0533606159347], batch size: 70
+2022-12-09 10:54:41,870 INFO [train.py:421] (7/8) Epoch 0, batch 1800, loss[loss=4.381, over 2380.00 frames. , ppl: 79.92260993918495] tot_loss[loss=6.547, over 3301985.87 frames. , ppl: 697.4229045676797], batch size: 70
+2022-12-09 10:56:19,742 INFO [train.py:421] (7/8) Epoch 0, batch 2000, loss[loss=4.396, over 5530.00 frames. , ppl: 81.11647428557997] tot_loss[loss=6.256, over 3474942.89 frames. , ppl: 521.3582857393102], batch size: 70
+2022-12-09 10:56:19,742 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 10:56:20,475 INFO [train.py:452] (7/8) Epoch 0, validation: loss=4.224, over 211138.00 frames. , ppl: 68.31401714385908
+2022-12-09 10:58:02,726 INFO [train.py:421] (7/8) Epoch 0, batch 2200, loss[loss=4.433, over 2030.00 frames. , ppl: 84.19979963082523] tot_loss[loss=6.01, over 3652937.48 frames. , ppl: 407.62430271169046], batch size: 70
+2022-12-09 10:59:45,478 INFO [train.py:421] (7/8) Epoch 0, batch 2400, loss[loss=4.234, over 3080.00 frames. , ppl: 69.0053123552178] tot_loss[loss=5.763, over 3912056.22 frames. , ppl: 318.31170373205515], batch size: 70
+2022-12-09 11:01:26,792 INFO [train.py:421] (7/8) Epoch 0, batch 2600, loss[loss=4.181, over 2590.00 frames. , ppl: 65.42274183073305] tot_loss[loss=5.559, over 4084750.59 frames. , ppl: 259.58956598565396], batch size: 70
+2022-12-09 11:03:09,419 INFO [train.py:421] (7/8) Epoch 0, batch 2800, loss[loss=3.965, over 2170.00 frames. , ppl: 52.73552243690784] tot_loss[loss=5.395, over 4166204.23 frames. , ppl: 220.23056714135063], batch size: 70
+2022-12-09 11:04:49,031 INFO [train.py:421] (7/8) Epoch 0, batch 3000, loss[loss=3.885, over 1610.00 frames. , ppl: 48.68340528745355] tot_loss[loss=5.207, over 4295865.15 frames. , ppl: 182.53692944974563], batch size: 70
+2022-12-09 11:04:49,032 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 11:04:49,779 INFO [train.py:452] (7/8) Epoch 0, validation: loss=3.608, over 211138.00 frames. , ppl: 36.89311779083857
+2022-12-09 11:06:26,630 INFO [train.py:421] (7/8) Epoch 0, batch 3200, loss[loss=3.557, over 2310.00 frames. , ppl: 35.0510771456847] tot_loss[loss=5.027, over 4391525.67 frames. , ppl: 152.46219415496242], batch size: 70
+2022-12-09 11:08:06,513 INFO [train.py:421] (7/8) Epoch 0, batch 3400, loss[loss=3.412, over 2940.00 frames. , ppl: 30.3168240053128] tot_loss[loss=4.863, over 4460047.35 frames. , ppl: 129.43407895713287], batch size: 70
+2022-12-09 11:09:49,633 INFO [train.py:421] (7/8) Epoch 0, batch 3600, loss[loss=3.424, over 1470.00 frames. , ppl: 30.69575634982492] tot_loss[loss=4.686, over 4582787.74 frames. , ppl: 108.43547130651292], batch size: 70
+2022-12-09 11:11:30,326 INFO [train.py:421] (7/8) Epoch 0, batch 3800, loss[loss=3.168, over 1120.00 frames. , ppl: 23.76899088618223] tot_loss[loss=4.536, over 4648414.62 frames. , ppl: 93.34326481175974], batch size: 70
+2022-12-09 11:13:10,826 INFO [train.py:421] (7/8) Epoch 0, batch 4000, loss[loss=3.176, over 4410.00 frames. , ppl: 23.942895376019166] tot_loss[loss=4.392, over 4720624.22 frames. , ppl: 80.79591675757334], batch size: 70
+2022-12-09 11:13:10,827 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 11:13:11,561 INFO [train.py:452] (7/8) Epoch 0, validation: loss=3.125, over 211138.00 frames. , ppl: 22.762158928396982
+2022-12-09 11:14:48,459 INFO [train.py:421] (7/8) Epoch 0, batch 4200, loss[loss=3.026, over 6790.00 frames. , ppl: 20.615347400307652] tot_loss[loss=4.257, over 4796442.66 frames. , ppl: 70.60987537937447], batch size: 70
+2022-12-09 11:16:24,328 INFO [train.py:421] (7/8) Epoch 0, batch 4400, loss[loss=3.121, over 1050.00 frames. , ppl: 22.68025235711934] tot_loss[loss=4.134, over 4865591.81 frames. , ppl: 62.40156797535721], batch size: 70
+2022-12-09 11:18:03,019 INFO [train.py:421] (7/8) Epoch 0, batch 4600, loss[loss=3.137, over 700.00 frames. , ppl: 23.039139232895117] tot_loss[loss=4.024, over 4916316.63 frames. , ppl: 55.904595095564254], batch size: 70
+2022-12-09 11:19:43,497 INFO [train.py:421] (7/8) Epoch 0, batch 4800, loss[loss=2.947, over 1540.00 frames. , ppl: 19.0557095194153] tot_loss[loss=3.921, over 4970607.40 frames. , ppl: 50.45390250541341], batch size: 70
+2022-12-09 11:21:24,000 INFO [train.py:421] (7/8) Epoch 0, batch 5000, loss[loss=3.057, over 1750.00 frames. , ppl: 21.272844678250163] tot_loss[loss=3.823, over 5049450.28 frames. , ppl: 45.75050773044563], batch size: 70
+2022-12-09 11:21:24,001 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 11:21:24,746 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.954, over 211138.00 frames. , ppl: 19.189241084043
+2022-12-09 11:23:04,385 INFO [train.py:421] (7/8) Epoch 0, batch 5200, loss[loss=3.053, over 3570.00 frames. , ppl: 21.176137923791224] tot_loss[loss=3.741, over 5077961.14 frames. , ppl: 42.130297754250584], batch size: 70
+2022-12-09 11:24:42,544 INFO [train.py:421] (7/8) Epoch 0, batch 5400, loss[loss=2.955, over 2940.00 frames. , ppl: 19.20322291302118] tot_loss[loss=3.673, over 5048142.04 frames. , ppl: 39.38325419548241], batch size: 70
+2022-12-09 11:26:20,378 INFO [train.py:421] (7/8) Epoch 0, batch 5600, loss[loss=2.955, over 840.00 frames. , ppl: 19.19650421083419] tot_loss[loss=3.599, over 5106429.94 frames. , ppl: 36.55033887197577], batch size: 70
+2022-12-09 11:28:00,841 INFO [train.py:421] (7/8) Epoch 0, batch 5800, loss[loss=2.955, over 2100.00 frames. , ppl: 19.19292037668075] tot_loss[loss=3.528, over 5175384.97 frames. , ppl: 34.06579992171034], batch size: 70
+2022-12-09 11:29:42,215 INFO [train.py:421] (7/8) Epoch 0, batch 6000, loss[loss=2.899, over 2030.00 frames. , ppl: 18.158279472855654] tot_loss[loss=3.469, over 5196782.35 frames. , ppl: 32.09986869511335], batch size: 70
+2022-12-09 11:29:42,215 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 11:29:42,974 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.875, over 211138.00 frames. , ppl: 17.725366404663895
+2022-12-09 11:31:26,510 INFO [train.py:421] (7/8) Epoch 0, batch 6200, loss[loss=2.93, over 4760.00 frames. , ppl: 18.729147444537926] tot_loss[loss=3.409, over 5272418.62 frames. , ppl: 30.243295512422076], batch size: 70
+2022-12-09 11:33:07,631 INFO [train.py:421] (7/8) Epoch 0, batch 6400, loss[loss=2.909, over 1470.00 frames. , ppl: 18.33777456994732] tot_loss[loss=3.362, over 5270074.06 frames. , ppl: 28.84267928196868], batch size: 70
+2022-12-09 11:34:47,513 INFO [train.py:421] (7/8) Epoch 0, batch 6600, loss[loss=2.842, over 1750.00 frames. , ppl: 17.148945124529703] tot_loss[loss=3.314, over 5307027.50 frames. , ppl: 27.482660818944616], batch size: 70
+2022-12-09 11:36:26,661 INFO [train.py:421] (7/8) Epoch 0, batch 6800, loss[loss=3.021, over 1680.00 frames. , ppl: 20.517818685945514] tot_loss[loss=3.269, over 5356898.79 frames. , ppl: 26.276259861399136], batch size: 70
+2022-12-09 11:38:05,182 INFO [train.py:421] (7/8) Epoch 0, batch 7000, loss[loss=2.787, over 2800.00 frames. , ppl: 16.229714408895116] tot_loss[loss=3.226, over 5392673.03 frames. , ppl: 25.190867945487565], batch size: 70
+2022-12-09 11:38:05,182 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 11:38:05,970 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.816, over 211138.00 frames. , ppl: 16.709705528719027
+2022-12-09 11:39:47,610 INFO [train.py:421] (7/8) Epoch 0, batch 7200, loss[loss=2.895, over 3150.00 frames. , ppl: 18.09098171777163] tot_loss[loss=3.19, over 5409119.05 frames. , ppl: 24.299760431333663], batch size: 70
+2022-12-09 11:41:23,911 INFO [train.py:421] (7/8) Epoch 0, batch 7400, loss[loss=2.821, over 2870.00 frames. , ppl: 16.799597098827256] tot_loss[loss=3.158, over 5417213.26 frames. , ppl: 23.51695509779911], batch size: 70
+2022-12-09 11:43:02,515 INFO [train.py:421] (7/8) Epoch 0, batch 7600, loss[loss=2.764, over 9100.00 frames. , ppl: 15.860040959407453] tot_loss[loss=3.13, over 5377512.93 frames. , ppl: 22.864888328681307], batch size: 70
+2022-12-09 11:44:44,305 INFO [train.py:421] (7/8) Epoch 0, batch 7800, loss[loss=2.858, over 2870.00 frames. , ppl: 17.434686988571848] tot_loss[loss=3.097, over 5421267.75 frames. , ppl: 22.138808234226566], batch size: 70
+2022-12-09 11:46:23,651 INFO [train.py:421] (7/8) Epoch 0, batch 8000, loss[loss=2.8, over 5670.00 frames. , ppl: 16.444270077532657] tot_loss[loss=3.072, over 5419121.44 frames. , ppl: 21.57883157878767], batch size: 70
+2022-12-09 11:46:23,652 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 11:46:24,382 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.773, over 211138.00 frames. , ppl: 16.01179093613074
+2022-12-09 11:47:58,419 INFO [train.py:421] (7/8) Epoch 0, batch 8200, loss[loss=2.721, over 4970.00 frames. , ppl: 15.20077537406777] tot_loss[loss=3.047, over 5406876.09 frames. , ppl: 21.059042495081368], batch size: 70
+2022-12-09 11:49:42,156 INFO [train.py:421] (7/8) Epoch 0, batch 8400, loss[loss=2.845, over 2380.00 frames. , ppl: 17.195726802533702] tot_loss[loss=3.024, over 5417612.88 frames. , ppl: 20.569406354221], batch size: 70
+2022-12-09 11:51:19,108 INFO [train.py:421] (7/8) Epoch 0, batch 8600, loss[loss=2.834, over 2380.00 frames. , ppl: 17.00587500303056] tot_loss[loss=3.002, over 5413904.73 frames. , ppl: 20.13099098478731], batch size: 70
+2022-12-09 11:53:00,421 INFO [train.py:421] (7/8) Epoch 0, batch 8800, loss[loss=2.984, over 700.00 frames. , ppl: 19.757339485894978] tot_loss[loss=2.984, over 5389005.84 frames. , ppl: 19.76529548289986], batch size: 70
+2022-12-09 11:54:40,009 INFO [train.py:421] (7/8) Epoch 0, batch 9000, loss[loss=2.844, over 1750.00 frames. , ppl: 17.179197750422833] tot_loss[loss=2.965, over 5382148.90 frames. , ppl: 19.39394612948737], batch size: 70
+2022-12-09 11:54:40,009 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 11:54:40,785 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.745, over 211138.00 frames. , ppl: 15.565240729798518
+2022-12-09 11:56:21,412 INFO [train.py:421] (7/8) Epoch 0, batch 9200, loss[loss=2.817, over 4270.00 frames. , ppl: 16.71833022720027] tot_loss[loss=2.945, over 5437152.01 frames. , ppl: 19.007412845826003], batch size: 70
+2022-12-09 11:58:04,178 INFO [train.py:421] (7/8) Epoch 0, batch 9400, loss[loss=2.694, over 7420.00 frames. , ppl: 14.796383479882751] tot_loss[loss=2.928, over 5456933.86 frames. , ppl: 18.68212726706809], batch size: 70
+2022-12-09 11:59:43,942 INFO [train.py:421] (7/8) Epoch 0, batch 9600, loss[loss=2.837, over 4060.00 frames. , ppl: 17.066168781044404] tot_loss[loss=2.914, over 5410295.09 frames. , ppl: 18.426799346165808], batch size: 70
+2022-12-09 12:01:21,908 INFO [train.py:421] (7/8) Epoch 0, batch 9800, loss[loss=2.743, over 2100.00 frames. , ppl: 15.525942325755686] tot_loss[loss=2.901, over 5357715.86 frames. , ppl: 18.199155687918676], batch size: 70
+2022-12-09 12:03:00,591 INFO [train.py:421] (7/8) Epoch 0, batch 10000, loss[loss=2.778, over 910.00 frames. , ppl: 16.09275451584896] tot_loss[loss=2.884, over 5419572.22 frames. , ppl: 17.889900606790484], batch size: 70
+2022-12-09 12:03:00,592 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 12:03:01,337 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.716, over 211138.00 frames. , ppl: 15.11237530515154
+2022-12-09 12:04:40,067 INFO [train.py:421] (7/8) Epoch 0, batch 10200, loss[loss=2.816, over 980.00 frames. , ppl: 16.703791211202013] tot_loss[loss=2.872, over 5409045.80 frames. , ppl: 17.67162798245074], batch size: 70
+2022-12-09 12:06:22,433 INFO [train.py:421] (7/8) Epoch 0, batch 10400, loss[loss=2.922, over 1610.00 frames. , ppl: 18.58446991330453] tot_loss[loss=2.859, over 5449642.67 frames. , ppl: 17.441662849875783], batch size: 70
+2022-12-09 12:08:01,856 INFO [train.py:421] (7/8) Epoch 0, batch 10600, loss[loss=2.745, over 3920.00 frames. , ppl: 15.56843917276625] tot_loss[loss=2.847, over 5463316.68 frames. , ppl: 17.234667349660782], batch size: 70
+2022-12-09 12:09:45,721 INFO [train.py:421] (7/8) Epoch 0, batch 10800, loss[loss=3.094, over 700.00 frames. , ppl: 22.055423249185196] tot_loss[loss=2.838, over 5424408.82 frames. , ppl: 17.080866827314757], batch size: 70
+2022-12-09 12:11:29,860 INFO [train.py:421] (7/8) Epoch 0, batch 11000, loss[loss=2.63, over 3150.00 frames. , ppl: 13.871546388908834] tot_loss[loss=2.827, over 5471674.30 frames. , ppl: 16.88633328742675], batch size: 70
+2022-12-09 12:11:29,860 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 12:11:30,607 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.692, over 211138.00 frames. , ppl: 14.756337129748474
+2022-12-09 12:13:13,813 INFO [train.py:421] (7/8) Epoch 0, batch 11200, loss[loss=2.757, over 2030.00 frames. , ppl: 15.748320286843748] tot_loss[loss=2.817, over 5439366.53 frames. , ppl: 16.730498944047802], batch size: 70
+2022-12-09 12:14:55,286 INFO [train.py:421] (7/8) Epoch 0, batch 11400, loss[loss=3.746, over 420.00 frames. , ppl: 42.3376095000564] tot_loss[loss=2.808, over 5420614.23 frames. , ppl: 16.574499961370982], batch size: 70
+2022-12-09 12:16:35,945 INFO [train.py:421] (7/8) Epoch 0, batch 11600, loss[loss=2.61, over 1610.00 frames. , ppl: 13.602747573310229] tot_loss[loss=2.798, over 5453714.46 frames. , ppl: 16.410369132447528], batch size: 70
+2022-12-09 12:18:18,170 INFO [train.py:421] (7/8) Epoch 0, batch 11800, loss[loss=2.813, over 1120.00 frames. , ppl: 16.65592746336418] tot_loss[loss=2.788, over 5514445.34 frames. , ppl: 16.25283853479427], batch size: 70
+2022-12-09 12:19:58,705 INFO [train.py:421] (7/8) Epoch 0, batch 12000, loss[loss=2.729, over 2240.00 frames. , ppl: 15.311225487861783] tot_loss[loss=2.78, over 5514781.08 frames. , ppl: 16.121033834328692], batch size: 70
+2022-12-09 12:19:58,706 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 12:19:59,461 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.67, over 211138.00 frames. , ppl: 14.443332034874045
+2022-12-09 12:21:38,235 INFO [train.py:421] (7/8) Epoch 0, batch 12200, loss[loss=2.748, over 3290.00 frames. , ppl: 15.617217302816323] tot_loss[loss=2.774, over 5484925.51 frames. , ppl: 16.023916904406136], batch size: 70
+2022-12-09 12:23:19,261 INFO [train.py:421] (7/8) Epoch 0, batch 12400, loss[loss=2.832, over 980.00 frames. , ppl: 16.972007849343527] tot_loss[loss=2.765, over 5493187.51 frames. , ppl: 15.883120764297058], batch size: 70
+2022-12-09 12:25:01,001 INFO [train.py:421] (7/8) Epoch 0, batch 12600, loss[loss=2.854, over 1470.00 frames. , ppl: 17.357681213794073] tot_loss[loss=2.758, over 5489528.61 frames. , ppl: 15.772842404829122], batch size: 70
+2022-12-09 12:26:41,331 INFO [train.py:421] (7/8) Epoch 0, batch 12800, loss[loss=2.723, over 3920.00 frames. , ppl: 15.222029566605904] tot_loss[loss=2.752, over 5492115.72 frames. , ppl: 15.670507019576098], batch size: 70
+2022-12-09 12:28:17,833 INFO [train.py:421] (7/8) Epoch 0, batch 13000, loss[loss=2.62, over 3640.00 frames. , ppl: 13.730708332095901] tot_loss[loss=2.745, over 5506778.65 frames. , ppl: 15.562791630850382], batch size: 70
+2022-12-09 12:28:17,834 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 12:28:18,579 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.655, over 211138.00 frames. , ppl: 14.220370751795132
+2022-12-09 12:29:56,775 INFO [train.py:421] (7/8) Epoch 0, batch 13200, loss[loss=2.936, over 840.00 frames. , ppl: 18.839780783223866] tot_loss[loss=2.739, over 5542152.46 frames. , ppl: 15.468885554643808], batch size: 70
+2022-12-09 12:31:35,007 INFO [train.py:421] (7/8) Epoch 0, batch 13400, loss[loss=2.598, over 2520.00 frames. , ppl: 13.430499101889675] tot_loss[loss=2.734, over 5517817.30 frames. , ppl: 15.389601585961078], batch size: 70
+2022-12-09 12:33:14,489 INFO [train.py:421] (7/8) Epoch 0, batch 13600, loss[loss=2.845, over 1190.00 frames. , ppl: 17.193172808139465] tot_loss[loss=2.729, over 5539778.90 frames. , ppl: 15.311692324943309], batch size: 70
+2022-12-09 12:34:55,727 INFO [train.py:421] (7/8) Epoch 0, batch 13800, loss[loss=2.73, over 1330.00 frames. , ppl: 15.332322990073823] tot_loss[loss=2.724, over 5524204.01 frames. , ppl: 15.237026348481619], batch size: 70
+2022-12-09 12:36:40,251 INFO [train.py:421] (7/8) Epoch 0, batch 14000, loss[loss=2.853, over 840.00 frames. , ppl: 17.335853420088714] tot_loss[loss=2.718, over 5505005.38 frames. , ppl: 15.155439992782064], batch size: 70
+2022-12-09 12:36:40,251 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 12:36:41,012 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.637, over 211138.00 frames. , ppl: 13.971456542635757
+2022-12-09 12:38:24,304 INFO [train.py:421] (7/8) Epoch 0, batch 14200, loss[loss=2.811, over 840.00 frames. , ppl: 16.63221528683199] tot_loss[loss=2.712, over 5557754.39 frames. , ppl: 15.059211966133638], batch size: 70
+2022-12-09 12:40:02,569 INFO [train.py:421] (7/8) Epoch 0, batch 14400, loss[loss=2.716, over 2100.00 frames. , ppl: 15.115100684420234] tot_loss[loss=2.709, over 5492984.85 frames. , ppl: 15.01798243558813], batch size: 70
+2022-12-09 12:41:41,074 INFO [train.py:421] (7/8) Epoch 0, batch 14600, loss[loss=2.579, over 4340.00 frames. , ppl: 13.180671024295785] tot_loss[loss=2.704, over 5503470.10 frames. , ppl: 14.94217955814274], batch size: 70
+2022-12-09 12:43:22,501 INFO [train.py:421] (7/8) Epoch 0, batch 14800, loss[loss=2.72, over 1960.00 frames. , ppl: 15.182710241539969] tot_loss[loss=2.701, over 5471276.96 frames. , ppl: 14.896863936484984], batch size: 70
+2022-12-09 12:45:00,509 INFO [train.py:421] (7/8) Epoch 0, batch 15000, loss[loss=2.901, over 770.00 frames. , ppl: 18.18765745311876] tot_loss[loss=2.697, over 5477824.83 frames. , ppl: 14.829579455982467], batch size: 70
+2022-12-09 12:45:00,510 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 12:45:01,254 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.624, over 211138.00 frames. , ppl: 13.790181361567887
+2022-12-09 12:46:44,177 INFO [train.py:421] (7/8) Epoch 0, batch 15200, loss[loss=2.944, over 910.00 frames. , ppl: 18.9992961920121] tot_loss[loss=2.693, over 5490164.89 frames. , ppl: 14.768896355132041], batch size: 70
+2022-12-09 12:48:23,217 INFO [train.py:421] (7/8) Epoch 0, batch 15400, loss[loss=2.74, over 1890.00 frames. , ppl: 15.48346136314252] tot_loss[loss=2.688, over 5558998.74 frames. , ppl: 14.69894851297477], batch size: 70
+2022-12-09 12:50:02,349 INFO [train.py:421] (7/8) Epoch 0, batch 15600, loss[loss=2.619, over 5110.00 frames. , ppl: 13.725697614109544] tot_loss[loss=2.685, over 5526666.11 frames. , ppl: 14.653327278172338], batch size: 70
+2022-12-09 12:51:41,369 INFO [train.py:421] (7/8) Epoch 0, batch 15800, loss[loss=2.674, over 1050.00 frames. , ppl: 14.491538366459704] tot_loss[loss=2.682, over 5480924.19 frames. , ppl: 14.614094791348316], batch size: 70
+2022-12-09 12:53:18,263 INFO [train.py:421] (7/8) Epoch 0, batch 16000, loss[loss=2.67, over 4620.00 frames. , ppl: 14.43464211613543] tot_loss[loss=2.678, over 5482479.65 frames. , ppl: 14.561965069051649], batch size: 70
+2022-12-09 12:53:18,263 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 12:53:18,996 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.614, over 211138.00 frames. , ppl: 13.652930714419472
+2022-12-09 12:54:59,756 INFO [train.py:421] (7/8) Epoch 0, batch 16200, loss[loss=2.595, over 9310.00 frames. , ppl: 13.390399074925963] tot_loss[loss=2.675, over 5501737.61 frames. , ppl: 14.50822509306888], batch size: 70
+2022-12-09 12:56:38,652 INFO [train.py:421] (7/8) Epoch 0, batch 16400, loss[loss=2.742, over 2660.00 frames. , ppl: 15.511221787095275] tot_loss[loss=2.671, over 5510722.09 frames. , ppl: 14.452636036234525], batch size: 70
+2022-12-09 12:58:19,165 INFO [train.py:421] (7/8) Epoch 0, batch 16600, loss[loss=2.6, over 2030.00 frames. , ppl: 13.46857069695193] tot_loss[loss=2.667, over 5523267.10 frames. , ppl: 14.397395941324698], batch size: 70
+2022-12-09 13:00:02,391 INFO [train.py:421] (7/8) Epoch 0, batch 16800, loss[loss=2.612, over 3780.00 frames. , ppl: 13.628252494877719] tot_loss[loss=2.664, over 5520627.51 frames. , ppl: 14.35252860559097], batch size: 70
+2022-12-09 13:01:41,577 INFO [train.py:421] (7/8) Epoch 0, batch 17000, loss[loss=2.523, over 4410.00 frames. , ppl: 12.468292476448605] tot_loss[loss=2.662, over 5484055.61 frames. , ppl: 14.325336990702798], batch size: 70
+2022-12-09 13:01:41,577 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 13:01:42,309 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.601, over 211138.00 frames. , ppl: 13.482567378311968
+2022-12-09 13:03:23,534 INFO [train.py:421] (7/8) Epoch 0, batch 17200, loss[loss=2.553, over 1960.00 frames. , ppl: 12.848616098113741] tot_loss[loss=2.658, over 5527603.82 frames. , ppl: 14.267970526657788], batch size: 70
+2022-12-09 13:05:01,412 INFO [train.py:421] (7/8) Epoch 0, batch 17400, loss[loss=2.722, over 1050.00 frames. , ppl: 15.20500042314003] tot_loss[loss=2.657, over 5470350.47 frames. , ppl: 14.249305727364082], batch size: 70
+2022-12-09 13:06:45,178 INFO [train.py:421] (7/8) Epoch 0, batch 17600, loss[loss=2.708, over 2590.00 frames. , ppl: 14.999098376998798] tot_loss[loss=2.652, over 5519710.99 frames. , ppl: 14.18721630322744], batch size: 70
+2022-12-09 13:08:28,801 INFO [train.py:421] (7/8) Epoch 0, batch 17800, loss[loss=2.743, over 1120.00 frames. , ppl: 15.534428850851963] tot_loss[loss=2.649, over 5546968.33 frames. , ppl: 14.141534990921024], batch size: 70
+2022-12-09 13:10:04,651 INFO [train.py:421] (7/8) Epoch 0, batch 18000, loss[loss=2.692, over 1050.00 frames. , ppl: 14.758743768059157] tot_loss[loss=2.648, over 5478268.65 frames. , ppl: 14.123372242435122], batch size: 70
+2022-12-09 13:10:04,651 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 13:10:05,409 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.595, over 211138.00 frames. , ppl: 13.393325029986839
+2022-12-09 13:11:44,553 INFO [train.py:421] (7/8) Epoch 0, batch 18200, loss[loss=2.681, over 2310.00 frames. , ppl: 14.5946400164929] tot_loss[loss=2.644, over 5500536.76 frames. , ppl: 14.074307677084994], batch size: 70
+2022-12-09 13:13:26,208 INFO [train.py:421] (7/8) Epoch 0, batch 18400, loss[loss=2.751, over 1050.00 frames. , ppl: 15.654744626143263] tot_loss[loss=2.642, over 5494479.79 frames. , ppl: 14.034980751000253], batch size: 70
+2022-12-09 13:15:03,886 INFO [train.py:421] (7/8) Epoch 0, batch 18600, loss[loss=2.706, over 1190.00 frames. , ppl: 14.974950531625172] tot_loss[loss=2.639, over 5487324.10 frames. , ppl: 13.997652151149486], batch size: 70
+2022-12-09 13:16:42,945 INFO [train.py:421] (7/8) Epoch 0, batch 18800, loss[loss=2.619, over 1470.00 frames. , ppl: 13.72394959055646] tot_loss[loss=2.636, over 5485803.06 frames. , ppl: 13.961356997162312], batch size: 70
+2022-12-09 13:18:25,095 INFO [train.py:421] (7/8) Epoch 0, batch 19000, loss[loss=2.802, over 2170.00 frames. , ppl: 16.475699219583216] tot_loss[loss=2.633, over 5480803.59 frames. , ppl: 13.919563995093178], batch size: 70
+2022-12-09 13:18:25,095 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 13:18:25,839 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.582, over 211138.00 frames. , ppl: 13.223891354355008
+2022-12-09 13:20:07,273 INFO [train.py:421] (7/8) Epoch 0, batch 19200, loss[loss=2.636, over 2450.00 frames. , ppl: 13.956076143424028] tot_loss[loss=2.632, over 5482564.98 frames. , ppl: 13.897148915976803], batch size: 70
+2022-12-09 13:21:45,762 INFO [train.py:421] (7/8) Epoch 0, batch 19400, loss[loss=2.508, over 7140.00 frames. , ppl: 12.285897411767362] tot_loss[loss=2.63, over 5445023.24 frames. , ppl: 13.874739080267872], batch size: 70
+2022-12-09 13:23:23,704 INFO [train.py:421] (7/8) Epoch 0, batch 19600, loss[loss=2.611, over 1190.00 frames. , ppl: 13.612875548100858] tot_loss[loss=2.629, over 5390305.08 frames. , ppl: 13.859312967319465], batch size: 70
+2022-12-09 13:25:02,644 INFO [train.py:421] (7/8) Epoch 0, batch 19800, loss[loss=3.324, over 560.00 frames. , ppl: 27.76142966807059] tot_loss[loss=2.627, over 5373235.06 frames. , ppl: 13.830281657919178], batch size: 70
+2022-12-09 13:26:43,266 INFO [train.py:421] (7/8) Epoch 0, batch 20000, loss[loss=2.499, over 4620.00 frames. , ppl: 12.16441987180829] tot_loss[loss=2.624, over 5398995.81 frames. , ppl: 13.79036372337249], batch size: 70
+2022-12-09 13:26:43,267 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 13:26:44,026 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.574, over 211138.00 frames. , ppl: 13.115298232215096
+2022-12-09 13:28:25,521 INFO [train.py:421] (7/8) Epoch 0, batch 20200, loss[loss=2.597, over 4620.00 frames. , ppl: 13.419153734524391] tot_loss[loss=2.622, over 5406641.32 frames. , ppl: 13.761697027251937], batch size: 70
+2022-12-09 13:30:02,452 INFO [train.py:421] (7/8) Epoch 0, batch 20400, loss[loss=2.812, over 1190.00 frames. , ppl: 16.644332682977886] tot_loss[loss=2.62, over 5422607.96 frames. , ppl: 13.731190378486236], batch size: 70
+2022-12-09 13:31:42,427 INFO [train.py:421] (7/8) Epoch 0, batch 20600, loss[loss=2.615, over 3710.00 frames. , ppl: 13.66762434555638] tot_loss[loss=2.619, over 5390146.05 frames. , ppl: 13.726761073706367], batch size: 70
+2022-12-09 13:33:22,029 INFO [train.py:421] (7/8) Epoch 0, batch 20800, loss[loss=2.55, over 2870.00 frames. , ppl: 12.801581439454754] tot_loss[loss=2.618, over 5358154.44 frames. , ppl: 13.710831855427637], batch size: 70
+2022-12-09 13:35:01,472 INFO [train.py:421] (7/8) Epoch 0, batch 21000, loss[loss=2.591, over 1050.00 frames. , ppl: 13.337609114416138] tot_loss[loss=2.616, over 5355773.68 frames. , ppl: 13.6767602639132], batch size: 70
+2022-12-09 13:35:01,473 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 13:35:02,241 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.567, over 211138.00 frames. , ppl: 13.024711781587353
+2022-12-09 13:36:41,727 INFO [train.py:421] (7/8) Epoch 0, batch 21200, loss[loss=2.663, over 1750.00 frames. , ppl: 14.345741305157429] tot_loss[loss=2.614, over 5345087.67 frames. , ppl: 13.65397905768404], batch size: 70
+2022-12-09 13:38:26,895 INFO [train.py:421] (7/8) Epoch 0, batch 21400, loss[loss=2.604, over 3010.00 frames. , ppl: 13.518790900248915] tot_loss[loss=2.611, over 5375256.34 frames. , ppl: 13.612366946964372], batch size: 70
+2022-12-09 13:40:04,867 INFO [train.py:421] (7/8) Epoch 0, batch 21600, loss[loss=2.498, over 4060.00 frames. , ppl: 12.15210382494209] tot_loss[loss=2.608, over 5428676.56 frames. , ppl: 13.572870912998429], batch size: 70
+2022-12-09 13:41:41,314 INFO [train.py:421] (7/8) Epoch 0, batch 21800, loss[loss=2.578, over 1470.00 frames. , ppl: 13.171099778398506] tot_loss[loss=2.607, over 5424944.23 frames. , ppl: 13.551812276370306], batch size: 70
+2022-12-09 13:43:22,213 INFO [train.py:421] (7/8) Epoch 0, batch 22000, loss[loss=2.6, over 3990.00 frames. , ppl: 13.459257195063122] tot_loss[loss=2.605, over 5381596.95 frames. , ppl: 13.526513360695414], batch size: 70
+2022-12-09 13:43:22,214 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 13:43:22,962 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.558, over 211138.00 frames. , ppl: 12.907422572347382
+2022-12-09 13:45:08,010 INFO [train.py:421] (7/8) Epoch 0, batch 22200, loss[loss=2.614, over 2380.00 frames. , ppl: 13.64949109758799] tot_loss[loss=2.602, over 5400136.48 frames. , ppl: 13.49328418208848], batch size: 70
+2022-12-09 13:46:46,061 INFO [train.py:421] (7/8) Epoch 0, batch 22400, loss[loss=2.689, over 1750.00 frames. , ppl: 14.718528508624443] tot_loss[loss=2.601, over 5404570.79 frames. , ppl: 13.473964552040131], batch size: 70
+2022-12-09 13:48:21,209 INFO [train.py:421] (7/8) Epoch 0, batch 22600, loss[loss=2.64, over 1820.00 frames. , ppl: 14.013420159599942] tot_loss[loss=2.599, over 5381966.36 frames. , ppl: 13.45687241366189], batch size: 70
+2022-12-09 13:50:00,273 INFO [train.py:421] (7/8) Epoch 0, batch 22800, loss[loss=2.593, over 1680.00 frames. , ppl: 13.370992520269484] tot_loss[loss=2.597, over 5408387.41 frames. , ppl: 13.424550524461138], batch size: 70
+2022-12-09 13:51:39,316 INFO [train.py:421] (7/8) Epoch 0, batch 23000, loss[loss=2.501, over 6720.00 frames. , ppl: 12.194829141337998] tot_loss[loss=2.595, over 5430146.87 frames. , ppl: 13.391728575605883], batch size: 70
+2022-12-09 13:51:39,317 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 13:51:40,059 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.55, over 211138.00 frames. , ppl: 12.811174547900729
+2022-12-09 13:53:19,960 INFO [train.py:421] (7/8) Epoch 0, batch 23200, loss[loss=2.526, over 3850.00 frames. , ppl: 12.505030919929188] tot_loss[loss=2.593, over 5416639.14 frames. , ppl: 13.367216895599872], batch size: 70
+2022-12-09 13:55:01,930 INFO [train.py:421] (7/8) Epoch 0, batch 23400, loss[loss=2.763, over 1400.00 frames. , ppl: 15.847708287716774] tot_loss[loss=2.59, over 5449424.19 frames. , ppl: 13.327323488029942], batch size: 70
+2022-12-09 13:56:43,809 INFO [train.py:421] (7/8) Epoch 0, batch 23600, loss[loss=2.81, over 840.00 frames. , ppl: 16.607150322834542] tot_loss[loss=2.588, over 5451598.96 frames. , ppl: 13.308096442474817], batch size: 70
+2022-12-09 13:58:26,277 INFO [train.py:421] (7/8) Epoch 0, batch 23800, loss[loss=2.478, over 4900.00 frames. , ppl: 11.915864876925061] tot_loss[loss=2.587, over 5484472.04 frames. , ppl: 13.284687107643363], batch size: 70
+2022-12-09 14:00:07,996 INFO [train.py:421] (7/8) Epoch 0, batch 24000, loss[loss=2.592, over 1190.00 frames. , ppl: 13.359222765991557] tot_loss[loss=2.586, over 5449271.71 frames. , ppl: 13.275868192896361], batch size: 70
+2022-12-09 14:00:07,996 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 14:00:08,746 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.543, over 211138.00 frames. , ppl: 12.713002157513388
+2022-12-09 14:01:49,804 INFO [train.py:421] (7/8) Epoch 0, batch 24200, loss[loss=2.609, over 2590.00 frames. , ppl: 13.580073755890396] tot_loss[loss=2.585, over 5433559.03 frames. , ppl: 13.26602786019001], batch size: 70
+2022-12-09 14:03:30,660 INFO [train.py:421] (7/8) Epoch 0, batch 24400, loss[loss=2.725, over 1400.00 frames. , ppl: 15.250221522566568] tot_loss[loss=2.584, over 5396716.74 frames. , ppl: 13.247698777805123], batch size: 70
+2022-12-09 14:05:11,546 INFO [train.py:421] (7/8) Epoch 0, batch 24600, loss[loss=2.518, over 3640.00 frames. , ppl: 12.409667566384792] tot_loss[loss=2.583, over 5389092.48 frames. , ppl: 13.23823324836699], batch size: 70
+2022-12-09 14:06:52,052 INFO [train.py:421] (7/8) Epoch 0, batch 24800, loss[loss=2.567, over 2660.00 frames. , ppl: 13.021893211864732] tot_loss[loss=2.582, over 5343487.29 frames. , ppl: 13.230053197164807], batch size: 70
+2022-12-09 14:08:35,025 INFO [train.py:421] (7/8) Epoch 0, batch 25000, loss[loss=2.595, over 2800.00 frames. , ppl: 13.390517006788253] tot_loss[loss=2.58, over 5402829.74 frames. , ppl: 13.20088867142495], batch size: 70
+2022-12-09 14:08:35,025 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 14:08:35,787 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.538, over 211138.00 frames. , ppl: 12.65462202047239
+2022-12-09 14:10:12,803 INFO [train.py:421] (7/8) Epoch 0, batch 25200, loss[loss=2.856, over 700.00 frames. , ppl: 17.3835170441317] tot_loss[loss=2.578, over 5416512.76 frames. , ppl: 13.17453820444136], batch size: 70
+2022-12-09 14:11:51,084 INFO [train.py:421] (7/8) Epoch 0, batch 25400, loss[loss=2.565, over 3290.00 frames. , ppl: 12.995290131070332] tot_loss[loss=2.577, over 5401067.10 frames. , ppl: 13.157366554233208], batch size: 70
+2022-12-09 14:13:29,071 INFO [train.py:421] (7/8) Epoch 0, batch 25600, loss[loss=2.547, over 5040.00 frames. , ppl: 12.763330034738106] tot_loss[loss=2.575, over 5441215.23 frames. , ppl: 13.130103690441862], batch size: 70
+2022-12-09 14:15:06,162 INFO [train.py:421] (7/8) Epoch 0, batch 25800, loss[loss=2.885, over 770.00 frames. , ppl: 17.901608137662745] tot_loss[loss=2.574, over 5414909.38 frames. , ppl: 13.118069482778589], batch size: 70
+2022-12-09 14:16:45,359 INFO [train.py:421] (7/8) Epoch 0, batch 26000, loss[loss=2.679, over 1400.00 frames. , ppl: 14.569741556256783] tot_loss[loss=2.572, over 5441860.73 frames. , ppl: 13.092000332358802], batch size: 70
+2022-12-09 14:16:45,359 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 14:16:46,124 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.534, over 211138.00 frames. , ppl: 12.606376393324691
+2022-12-09 14:18:23,650 INFO [train.py:421] (7/8) Epoch 0, batch 26200, loss[loss=2.547, over 6020.00 frames. , ppl: 12.763828681073505] tot_loss[loss=2.571, over 5440684.62 frames. , ppl: 13.07829052069656], batch size: 70
+2022-12-09 14:20:04,901 INFO [train.py:421] (7/8) Epoch 0, batch 26400, loss[loss=2.528, over 4900.00 frames. , ppl: 12.528137574322251] tot_loss[loss=2.571, over 5440270.89 frames. , ppl: 13.072376797418222], batch size: 70
+2022-12-09 14:21:42,870 INFO [train.py:421] (7/8) Epoch 0, batch 26600, loss[loss=2.415, over 5250.00 frames. , ppl: 11.19195190934413] tot_loss[loss=2.568, over 5469592.62 frames. , ppl: 13.038823354380378], batch size: 70
+2022-12-09 14:23:20,635 INFO [train.py:421] (7/8) Epoch 0, batch 26800, loss[loss=2.571, over 1330.00 frames. , ppl: 13.08011340034322] tot_loss[loss=2.568, over 5440569.37 frames. , ppl: 13.035112797413746], batch size: 70
+2022-12-09 14:25:00,577 INFO [train.py:421] (7/8) Epoch 0, batch 27000, loss[loss=2.509, over 4970.00 frames. , ppl: 12.2885631697273] tot_loss[loss=2.566, over 5450439.41 frames. , ppl: 13.019279954271173], batch size: 70
+2022-12-09 14:25:00,577 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 14:25:01,326 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.527, over 211138.00 frames. , ppl: 12.51153246345996
+2022-12-09 14:26:38,298 INFO [train.py:421] (7/8) Epoch 0, batch 27200, loss[loss=2.59, over 3290.00 frames. , ppl: 13.33478007112091] tot_loss[loss=2.565, over 5447415.68 frames. , ppl: 12.999224088247953], batch size: 70
+2022-12-09 14:28:19,675 INFO [train.py:421] (7/8) Epoch 0, batch 27400, loss[loss=2.548, over 2590.00 frames. , ppl: 12.781461292743808] tot_loss[loss=2.564, over 5425592.98 frames. , ppl: 12.984082531554094], batch size: 70
+2022-12-09 14:30:01,585 INFO [train.py:421] (7/8) Epoch 0, batch 27600, loss[loss=2.564, over 2380.00 frames. , ppl: 12.990384042204067] tot_loss[loss=2.563, over 5450651.39 frames. , ppl: 12.972265644875957], batch size: 70
+2022-12-09 14:31:41,952 INFO [train.py:421] (7/8) Epoch 0, batch 27800, loss[loss=3.031, over 630.00 frames. , ppl: 20.718334548312058] tot_loss[loss=2.562, over 5448414.23 frames. , ppl: 12.955707260451167], batch size: 70
+2022-12-09 14:33:19,871 INFO [train.py:421] (7/8) Epoch 0, batch 28000, loss[loss=2.497, over 4060.00 frames. , ppl: 12.15154262620948] tot_loss[loss=2.561, over 5441749.68 frames. , ppl: 12.948037714387151], batch size: 70
+2022-12-09 14:33:19,872 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 14:33:20,620 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.521, over 211138.00 frames. , ppl: 12.4409233226362
+2022-12-09 14:35:00,359 INFO [train.py:421] (7/8) Epoch 0, batch 28200, loss[loss=2.647, over 2310.00 frames. , ppl: 14.105823671129079] tot_loss[loss=2.558, over 5449191.34 frames. , ppl: 12.914810007827855], batch size: 70
+2022-12-09 14:36:41,344 INFO [train.py:421] (7/8) Epoch 0, batch 28400, loss[loss=2.747, over 1120.00 frames. , ppl: 15.59054849089608] tot_loss[loss=2.557, over 5457677.73 frames. , ppl: 12.898788645453639], batch size: 70
+2022-12-09 14:38:25,493 INFO [train.py:421] (7/8) Epoch 0, batch 28600, loss[loss=2.54, over 2170.00 frames. , ppl: 12.676109650323443] tot_loss[loss=2.556, over 5463176.95 frames. , ppl: 12.88740084037211], batch size: 70
+2022-12-09 14:40:02,956 INFO [train.py:421] (7/8) Epoch 0, batch 28800, loss[loss=2.665, over 1470.00 frames. , ppl: 14.371465412306122] tot_loss[loss=2.555, over 5458053.65 frames. , ppl: 12.872354644192631], batch size: 70
+2022-12-09 14:41:43,068 INFO [train.py:421] (7/8) Epoch 0, batch 29000, loss[loss=2.587, over 2730.00 frames. , ppl: 13.295784872953535] tot_loss[loss=2.554, over 5449608.18 frames. , ppl: 12.861389985948316], batch size: 70
+2022-12-09 14:41:43,068 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 14:41:43,812 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.513, over 211138.00 frames. , ppl: 12.34438956706025
+2022-12-09 14:43:21,608 INFO [train.py:421] (7/8) Epoch 0, batch 29200, loss[loss=2.587, over 1540.00 frames. , ppl: 13.292016518647877] tot_loss[loss=2.553, over 5424554.32 frames. , ppl: 12.850844390602878], batch size: 70
+2022-12-09 14:45:00,643 INFO [train.py:421] (7/8) Epoch 0, batch 29400, loss[loss=2.563, over 2240.00 frames. , ppl: 12.975967807738753] tot_loss[loss=2.553, over 5408794.55 frames. , ppl: 12.84613545154954], batch size: 70
+2022-12-09 14:46:41,806 INFO [train.py:421] (7/8) Epoch 0, batch 29600, loss[loss=2.632, over 3080.00 frames. , ppl: 13.8992051786886] tot_loss[loss=2.551, over 5435835.50 frames. , ppl: 12.8198618217222], batch size: 70
+2022-12-09 14:48:22,706 INFO [train.py:421] (7/8) Epoch 0, batch 29800, loss[loss=2.827, over 980.00 frames. , ppl: 16.896375156274566] tot_loss[loss=2.55, over 5448084.39 frames. , ppl: 12.80671180529299], batch size: 70
+2022-12-09 14:50:00,656 INFO [train.py:421] (7/8) Epoch 0, batch 30000, loss[loss=2.505, over 4340.00 frames. , ppl: 12.237701082322863] tot_loss[loss=2.549, over 5435298.30 frames. , ppl: 12.798446882608822], batch size: 70
+2022-12-09 14:50:00,657 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 14:50:01,403 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.512, over 211138.00 frames. , ppl: 12.331413290958714
+2022-12-09 14:51:44,212 INFO [train.py:421] (7/8) Epoch 0, batch 30200, loss[loss=3.121, over 560.00 frames. , ppl: 22.674068707600746] tot_loss[loss=2.549, over 5414000.37 frames. , ppl: 12.788537433183217], batch size: 70
+2022-12-09 14:53:26,920 INFO [train.py:421] (7/8) Epoch 0, batch 30400, loss[loss=2.569, over 2170.00 frames. , ppl: 13.054436323933547] tot_loss[loss=2.547, over 5433330.31 frames. , ppl: 12.771957121518556], batch size: 70
+2022-12-09 14:55:12,237 INFO [train.py:421] (7/8) Epoch 0, batch 30600, loss[loss=2.586, over 2730.00 frames. , ppl: 13.275615280070882] tot_loss[loss=2.545, over 5467939.37 frames. , ppl: 12.743656328637998], batch size: 70
+2022-12-09 14:56:52,334 INFO [train.py:421] (7/8) Epoch 0, batch 30800, loss[loss=2.526, over 3850.00 frames. , ppl: 12.505655806455675] tot_loss[loss=2.544, over 5453050.99 frames. , ppl: 12.728278174139973], batch size: 70
+2022-12-09 14:58:33,196 INFO [train.py:421] (7/8) Epoch 0, batch 31000, loss[loss=2.429, over 4130.00 frames. , ppl: 11.347699312924242] tot_loss[loss=2.543, over 5454010.49 frames. , ppl: 12.715876720560061], batch size: 70
+2022-12-09 14:58:33,196 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 14:58:33,957 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.506, over 211138.00 frames. , ppl: 12.259548686709403
+2022-12-09 15:00:11,903 INFO [train.py:421] (7/8) Epoch 0, batch 31200, loss[loss=2.635, over 1470.00 frames. , ppl: 13.940845961459154] tot_loss[loss=2.542, over 5469099.60 frames. , ppl: 12.703668947771504], batch size: 70
+2022-12-09 15:01:49,407 INFO [train.py:421] (7/8) Epoch 0, batch 31400, loss[loss=2.754, over 910.00 frames. , ppl: 15.70564188343142] tot_loss[loss=2.541, over 5463716.92 frames. , ppl: 12.693947429030114], batch size: 70
+2022-12-09 15:03:32,010 INFO [train.py:421] (7/8) Epoch 0, batch 31600, loss[loss=2.477, over 8050.00 frames. , ppl: 11.90417372960354] tot_loss[loss=2.54, over 5473729.37 frames. , ppl: 12.68020636841732], batch size: 70
+2022-12-09 15:05:12,046 INFO [train.py:421] (7/8) Epoch 0, batch 31800, loss[loss=4.182, over 350.00 frames. , ppl: 65.48238533203143] tot_loss[loss=2.538, over 5513601.70 frames. , ppl: 12.655245665949357], batch size: 70
+2022-12-09 15:06:52,420 INFO [train.py:421] (7/8) Epoch 0, batch 32000, loss[loss=2.789, over 840.00 frames. , ppl: 16.25957159956635] tot_loss[loss=2.537, over 5501825.50 frames. , ppl: 12.647107506668817], batch size: 70
+2022-12-09 15:06:52,421 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 15:06:53,178 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.502, over 211138.00 frames. , ppl: 12.211804295938897
+2022-12-09 15:08:31,773 INFO [train.py:421] (7/8) Epoch 0, batch 32200, loss[loss=2.579, over 1680.00 frames. , ppl: 13.187199096606054] tot_loss[loss=2.537, over 5454436.33 frames. , ppl: 12.6387398802628], batch size: 70
+2022-12-09 15:10:13,703 INFO [train.py:421] (7/8) Epoch 0, batch 32400, loss[loss=2.428, over 3080.00 frames. , ppl: 11.334703525423237] tot_loss[loss=2.536, over 5443399.25 frames. , ppl: 12.627024170462255], batch size: 70
+2022-12-09 15:11:52,319 INFO [train.py:421] (7/8) Epoch 0, batch 32600, loss[loss=2.567, over 2380.00 frames. , ppl: 13.028687390458533] tot_loss[loss=2.534, over 5457998.17 frames. , ppl: 12.607345128059208], batch size: 70
+2022-12-09 15:13:32,201 INFO [train.py:421] (7/8) Epoch 0, batch 32800, loss[loss=2.562, over 2450.00 frames. , ppl: 12.962584906841716] tot_loss[loss=2.534, over 5445199.24 frames. , ppl: 12.59847288210586], batch size: 70
+2022-12-09 15:15:11,964 INFO [train.py:421] (7/8) Epoch 0, batch 33000, loss[loss=2.504, over 2030.00 frames. , ppl: 12.231060394601673] tot_loss[loss=2.532, over 5463530.60 frames. , ppl: 12.576761854486673], batch size: 70
+2022-12-09 15:15:11,965 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 15:15:12,723 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.498, over 211138.00 frames. , ppl: 12.152444554503326
+2022-12-09 15:16:47,647 INFO [train.py:421] (7/8) Epoch 0, batch 33200, loss[loss=2.564, over 1750.00 frames. , ppl: 12.9940436465325] tot_loss[loss=2.532, over 5440349.64 frames. , ppl: 12.58049097439137], batch size: 70
+2022-12-09 15:18:24,716 INFO [train.py:421] (7/8) Epoch 0, batch 33400, loss[loss=2.644, over 1330.00 frames. , ppl: 14.069420536822228] tot_loss[loss=2.531, over 5427856.85 frames. , ppl: 12.571500691318656], batch size: 70
+2022-12-09 15:20:01,835 INFO [train.py:421] (7/8) Epoch 0, batch 33600, loss[loss=2.504, over 2730.00 frames. , ppl: 12.227528354037055] tot_loss[loss=2.53, over 5419719.17 frames. , ppl: 12.551482117461498], batch size: 70
+2022-12-09 15:21:40,605 INFO [train.py:421] (7/8) Epoch 0, batch 33800, loss[loss=2.593, over 1260.00 frames. , ppl: 13.373913961429478] tot_loss[loss=2.529, over 5391012.92 frames. , ppl: 12.539944069168593], batch size: 70
+2022-12-09 15:23:22,962 INFO [train.py:421] (7/8) Epoch 0, batch 34000, loss[loss=2.574, over 1400.00 frames. , ppl: 13.119952626338499] tot_loss[loss=2.528, over 5419826.69 frames. , ppl: 12.529416412292761], batch size: 70
+2022-12-09 15:23:22,963 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 15:23:23,718 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.494, over 211138.00 frames. , ppl: 12.106278320487071
+2022-12-09 15:25:05,073 INFO [train.py:421] (7/8) Epoch 0, batch 34200, loss[loss=2.401, over 5752.00 frames. , ppl: 11.03353583512941] tot_loss[loss=2.527, over 5445466.34 frames. , ppl: 12.509920822569677], batch size: 70
+2022-12-09 15:26:48,264 INFO [train.py:421] (7/8) Epoch 0, batch 34400, loss[loss=2.47, over 5810.00 frames. , ppl: 11.822568466028342] tot_loss[loss=2.525, over 5448359.12 frames. , ppl: 12.496348314132286], batch size: 70
+2022-12-09 15:28:27,300 INFO [train.py:421] (7/8) Epoch 0, batch 34600, loss[loss=2.692, over 1400.00 frames. , ppl: 14.765739082294079] tot_loss[loss=2.524, over 5454717.72 frames. , ppl: 12.479600406418962], batch size: 70
+2022-12-09 15:30:05,467 INFO [train.py:421] (7/8) Epoch 0, batch 34800, loss[loss=2.507, over 3080.00 frames. , ppl: 12.274152061308973] tot_loss[loss=2.523, over 5443275.27 frames. , ppl: 12.471318383293548], batch size: 70
+2022-12-09 15:31:45,505 INFO [train.py:421] (7/8) Epoch 0, batch 35000, loss[loss=2.58, over 2380.00 frames. , ppl: 13.20008102846404] tot_loss[loss=2.523, over 5451502.30 frames. , ppl: 12.461240469126029], batch size: 70
+2022-12-09 15:31:45,505 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 15:31:46,264 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.491, over 211138.00 frames. , ppl: 12.072202954749265
+2022-12-09 15:33:26,024 INFO [train.py:421] (7/8) Epoch 0, batch 35200, loss[loss=2.472, over 3010.00 frames. , ppl: 11.84734042065229] tot_loss[loss=2.521, over 5505721.85 frames. , ppl: 12.438689928129499], batch size: 70
+2022-12-09 15:35:05,217 INFO [train.py:421] (7/8) Epoch 0, batch 35400, loss[loss=2.377, over 2520.00 frames. , ppl: 10.777209314427614] tot_loss[loss=2.52, over 5534546.76 frames. , ppl: 12.42322394867265], batch size: 70
+2022-12-09 15:36:46,643 INFO [train.py:421] (7/8) Epoch 0, batch 35600, loss[loss=2.509, over 4690.00 frames. , ppl: 12.295521306248677] tot_loss[loss=2.519, over 5538028.47 frames. , ppl: 12.419145659540144], batch size: 70
+2022-12-09 15:38:27,733 INFO [train.py:421] (7/8) Epoch 0, batch 35800, loss[loss=2.514, over 4690.00 frames. , ppl: 12.353651973852257] tot_loss[loss=2.519, over 5495510.48 frames. , ppl: 12.41665033373937], batch size: 70
+2022-12-09 15:40:08,922 INFO [train.py:421] (7/8) Epoch 0, batch 36000, loss[loss=2.543, over 1330.00 frames. , ppl: 12.715829027673479] tot_loss[loss=2.519, over 5482967.01 frames. , ppl: 12.421983911354419], batch size: 70
+2022-12-09 15:40:08,923 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 15:40:09,682 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.487, over 211138.00 frames. , ppl: 12.026263233378076
+2022-12-09 15:41:50,312 INFO [train.py:421] (7/8) Epoch 0, batch 36200, loss[loss=2.743, over 980.00 frames. , ppl: 15.541042611243538] tot_loss[loss=2.519, over 5452203.44 frames. , ppl: 12.422340894834852], batch size: 70
+2022-12-09 15:43:29,539 INFO [train.py:421] (7/8) Epoch 0, batch 36400, loss[loss=2.649, over 1820.00 frames. , ppl: 14.146635776607534] tot_loss[loss=2.518, over 5463820.15 frames. , ppl: 12.40345448608999], batch size: 70
+2022-12-09 15:45:09,051 INFO [train.py:421] (7/8) Epoch 0, batch 36600, loss[loss=2.486, over 1260.00 frames. , ppl: 12.00910216848566] tot_loss[loss=2.517, over 5501696.96 frames. , ppl: 12.387661075248063], batch size: 70
+2022-12-09 15:46:47,617 INFO [train.py:421] (7/8) Epoch 0, batch 36800, loss[loss=2.709, over 1050.00 frames. , ppl: 15.014438079401474] tot_loss[loss=2.515, over 5519161.54 frames. , ppl: 12.367799909756757], batch size: 70
+2022-12-09 15:48:30,559 INFO [train.py:421] (7/8) Epoch 0, batch 37000, loss[loss=2.601, over 2450.00 frames. , ppl: 13.482878206424939] tot_loss[loss=2.514, over 5582792.71 frames. , ppl: 12.354866454385], batch size: 70
+2022-12-09 15:48:30,559 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 15:48:31,316 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.483, over 211138.00 frames. , ppl: 11.975344738756288
+2022-12-09 15:50:06,980 INFO [train.py:421] (7/8) Epoch 0, batch 37200, loss[loss=2.617, over 1050.00 frames. , ppl: 13.698891513740362] tot_loss[loss=2.514, over 5588306.85 frames. , ppl: 12.350909552797972], batch size: 70
+2022-12-09 15:51:48,863 INFO [train.py:421] (7/8) Epoch 0, batch 37400, loss[loss=2.561, over 3780.00 frames. , ppl: 12.946685944202766] tot_loss[loss=2.514, over 5584911.91 frames. , ppl: 12.350243456923266], batch size: 70
+2022-12-09 15:53:29,772 INFO [train.py:421] (7/8) Epoch 0, batch 37600, loss[loss=2.803, over 770.00 frames. , ppl: 16.495023564417277] tot_loss[loss=2.512, over 5597590.56 frames. , ppl: 12.33266856472808], batch size: 70
+2022-12-09 15:55:11,151 INFO [train.py:421] (7/8) Epoch 0, batch 37800, loss[loss=2.601, over 2030.00 frames. , ppl: 13.477865163616904] tot_loss[loss=2.512, over 5581647.06 frames. , ppl: 12.32406073804479], batch size: 70
+2022-12-09 15:56:53,634 INFO [train.py:421] (7/8) Epoch 0, batch 38000, loss[loss=2.573, over 1330.00 frames. , ppl: 13.10662373243876] tot_loss[loss=2.512, over 5530389.92 frames. , ppl: 12.327273671592192], batch size: 70
+2022-12-09 15:56:53,634 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 15:56:54,399 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.477, over 211138.00 frames. , ppl: 11.90581072793103
+2022-12-09 15:58:34,660 INFO [train.py:421] (7/8) Epoch 0, batch 38200, loss[loss=2.39, over 3010.00 frames. , ppl: 10.909445472898543] tot_loss[loss=2.512, over 5490800.02 frames. , ppl: 12.324668861827721], batch size: 70
+2022-12-09 16:00:16,310 INFO [train.py:421] (7/8) Epoch 0, batch 38400, loss[loss=2.438, over 4130.00 frames. , ppl: 11.446201777531478] tot_loss[loss=2.511, over 5468948.82 frames. , ppl: 12.31512223457313], batch size: 70
+2022-12-09 16:01:53,974 INFO [train.py:421] (7/8) Epoch 0, batch 38600, loss[loss=2.485, over 4900.00 frames. , ppl: 11.999780918829593] tot_loss[loss=2.51, over 5479072.80 frames. , ppl: 12.299643467257775], batch size: 70
+2022-12-09 16:03:33,412 INFO [train.py:421] (7/8) Epoch 0, batch 38800, loss[loss=2.349, over 5110.00 frames. , ppl: 10.478486407352205] tot_loss[loss=2.508, over 5475090.80 frames. , ppl: 12.283759337723836], batch size: 70
+2022-12-09 16:05:12,806 INFO [train.py:421] (7/8) Epoch 0, batch 39000, loss[loss=2.655, over 1050.00 frames. , ppl: 14.226064352023702] tot_loss[loss=2.509, over 5433653.34 frames. , ppl: 12.286852300429265], batch size: 70
+2022-12-09 16:05:12,807 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 16:05:13,565 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.476, over 211138.00 frames. , ppl: 11.897084242143393
+2022-12-09 16:06:53,444 INFO [train.py:421] (7/8) Epoch 0, batch 39200, loss[loss=2.626, over 1960.00 frames. , ppl: 13.824225067107516] tot_loss[loss=2.508, over 5414754.62 frames. , ppl: 12.275984864195888], batch size: 70
+2022-12-09 16:08:35,764 INFO [train.py:421] (7/8) Epoch 0, batch 39400, loss[loss=3.179, over 560.00 frames. , ppl: 24.0136923052226] tot_loss[loss=2.507, over 5427814.83 frames. , ppl: 12.269290710814278], batch size: 70
+2022-12-09 16:10:13,107 INFO [train.py:421] (7/8) Epoch 0, batch 39600, loss[loss=2.623, over 770.00 frames. , ppl: 13.777922390157308] tot_loss[loss=2.507, over 5415980.70 frames. , ppl: 12.267616221544317], batch size: 70
+2022-12-09 16:11:57,756 INFO [train.py:421] (7/8) Epoch 0, batch 39800, loss[loss=2.513, over 2590.00 frames. , ppl: 12.340085163655367] tot_loss[loss=2.506, over 5422670.33 frames. , ppl: 12.254504773511707], batch size: 70
+2022-12-09 16:13:37,672 INFO [train.py:421] (7/8) Epoch 0, batch 40000, loss[loss=3.001, over 700.00 frames. , ppl: 20.110715655117275] tot_loss[loss=2.505, over 5396165.66 frames. , ppl: 12.245756573247526], batch size: 70
+2022-12-09 16:13:37,672 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 16:13:38,429 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.473, over 211138.00 frames. , ppl: 11.854175758684555
+2022-12-09 16:15:17,654 INFO [train.py:421] (7/8) Epoch 0, batch 40200, loss[loss=2.516, over 3850.00 frames. , ppl: 12.382667179837316] tot_loss[loss=2.505, over 5375110.73 frames. , ppl: 12.249163424475526], batch size: 70
+2022-12-09 16:16:59,434 INFO [train.py:421] (7/8) Epoch 0, batch 40400, loss[loss=2.422, over 7210.00 frames. , ppl: 11.263596043979005] tot_loss[loss=2.504, over 5423713.83 frames. , ppl: 12.2308944757514], batch size: 70
+2022-12-09 16:18:39,717 INFO [train.py:421] (7/8) Epoch 0, batch 40600, loss[loss=2.439, over 3500.00 frames. , ppl: 11.457263365281694] tot_loss[loss=2.503, over 5429154.20 frames. , ppl: 12.220467338981921], batch size: 70
+2022-12-09 16:20:18,287 INFO [train.py:421] (7/8) Epoch 0, batch 40800, loss[loss=2.536, over 2380.00 frames. , ppl: 12.62378556966806] tot_loss[loss=2.502, over 5412762.65 frames. , ppl: 12.210657017035295], batch size: 70
+2022-12-09 16:21:58,922 INFO [train.py:421] (7/8) Epoch 0, batch 41000, loss[loss=2.741, over 910.00 frames. , ppl: 15.49793143272495] tot_loss[loss=2.502, over 5411362.43 frames. , ppl: 12.204933361748319], batch size: 70
+2022-12-09 16:21:58,923 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 16:21:59,668 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.47, over 211138.00 frames. , ppl: 11.826051100421541
+2022-12-09 16:23:39,477 INFO [train.py:421] (7/8) Epoch 0, batch 41200, loss[loss=2.521, over 1750.00 frames. , ppl: 12.437869551567509] tot_loss[loss=2.502, over 5364813.13 frames. , ppl: 12.208443233115839], batch size: 70
+2022-12-09 16:25:18,888 INFO [train.py:421] (7/8) Epoch 0, batch 41400, loss[loss=2.513, over 2520.00 frames. , ppl: 12.340928261830856] tot_loss[loss=2.501, over 5400915.88 frames. , ppl: 12.19169955662027], batch size: 70
+2022-12-09 16:26:57,210 INFO [train.py:421] (7/8) Epoch 0, batch 41600, loss[loss=2.424, over 2100.00 frames. , ppl: 11.291919473659034] tot_loss[loss=2.499, over 5428865.09 frames. , ppl: 12.173777416460489], batch size: 70
+2022-12-09 16:28:34,643 INFO [train.py:421] (7/8) Epoch 0, batch 41800, loss[loss=2.524, over 2310.00 frames. , ppl: 12.47809905625666] tot_loss[loss=2.497, over 5432110.37 frames. , ppl: 12.151583208117174], batch size: 70
+2022-12-09 16:30:16,901 INFO [train.py:421] (7/8) Epoch 0, batch 42000, loss[loss=2.51, over 2800.00 frames. , ppl: 12.303292916772275] tot_loss[loss=2.498, over 5420765.16 frames. , ppl: 12.152509547996551], batch size: 70
+2022-12-09 16:30:16,902 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 16:30:17,662 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.468, over 211138.00 frames. , ppl: 11.797221378196006
+2022-12-09 16:31:58,210 INFO [train.py:421] (7/8) Epoch 0, batch 42200, loss[loss=2.394, over 12320.00 frames. , ppl: 10.960529415303178] tot_loss[loss=2.496, over 5449490.88 frames. , ppl: 12.132280710619495], batch size: 70
+2022-12-09 16:33:38,751 INFO [train.py:421] (7/8) Epoch 0, batch 42400, loss[loss=2.434, over 1540.00 frames. , ppl: 11.40100910447809] tot_loss[loss=2.494, over 5447186.58 frames. , ppl: 12.113784628777573], batch size: 70
+2022-12-09 16:35:21,173 INFO [train.py:421] (7/8) Epoch 0, batch 42600, loss[loss=2.535, over 2310.00 frames. , ppl: 12.610235200991736] tot_loss[loss=2.495, over 5391656.70 frames. , ppl: 12.117836482356966], batch size: 70
+2022-12-09 16:37:02,071 INFO [train.py:421] (7/8) Epoch 0, batch 42800, loss[loss=2.461, over 2730.00 frames. , ppl: 11.716198567574821] tot_loss[loss=2.494, over 5389080.44 frames. , ppl: 12.106788766983122], batch size: 70
+2022-12-09 16:38:43,437 INFO [train.py:421] (7/8) Epoch 0, batch 43000, loss[loss=2.501, over 3080.00 frames. , ppl: 12.198047190380082] tot_loss[loss=2.492, over 5404309.76 frames. , ppl: 12.08720071676878], batch size: 70
+2022-12-09 16:38:43,438 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 16:38:44,197 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.462, over 211138.00 frames. , ppl: 11.728416107172176
+2022-12-09 16:40:25,946 INFO [train.py:421] (7/8) Epoch 0, batch 43200, loss[loss=2.543, over 2450.00 frames. , ppl: 12.71221037367] tot_loss[loss=2.491, over 5386281.88 frames. , ppl: 12.078807673343137], batch size: 70
+2022-12-09 16:42:04,147 INFO [train.py:421] (7/8) Epoch 0, batch 43400, loss[loss=2.63, over 1330.00 frames. , ppl: 13.870117353554214] tot_loss[loss=2.49, over 5427553.40 frames. , ppl: 12.055403282571682], batch size: 70
+2022-12-09 16:43:44,139 INFO [train.py:421] (7/8) Epoch 0, batch 43600, loss[loss=2.386, over 4480.00 frames. , ppl: 10.874262421834832] tot_loss[loss=2.488, over 5424873.05 frames. , ppl: 12.041239208362894], batch size: 70
+2022-12-09 16:45:29,465 INFO [train.py:421] (7/8) Epoch 0, batch 43800, loss[loss=2.775, over 770.00 frames. , ppl: 16.038138814357872] tot_loss[loss=2.488, over 5421216.85 frames. , ppl: 12.038808685937921], batch size: 70
+2022-12-09 16:47:12,055 INFO [train.py:421] (7/8) Epoch 0, batch 44000, loss[loss=2.647, over 2030.00 frames. , ppl: 14.108556154402361] tot_loss[loss=2.487, over 5469029.31 frames. , ppl: 12.023663664910478], batch size: 70
+2022-12-09 16:47:12,056 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 16:47:12,815 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.46, over 211138.00 frames. , ppl: 11.703982858703393
+2022-12-09 16:48:52,645 INFO [train.py:421] (7/8) Epoch 0, batch 44200, loss[loss=2.44, over 6860.00 frames. , ppl: 11.477203689384943] tot_loss[loss=2.486, over 5459711.42 frames. , ppl: 12.018092475203586], batch size: 70
+2022-12-09 16:50:32,147 INFO [train.py:421] (7/8) Epoch 0, batch 44400, loss[loss=2.902, over 630.00 frames. , ppl: 18.216413301349707] tot_loss[loss=2.486, over 5436893.41 frames. , ppl: 12.012458895260337], batch size: 70
+2022-12-09 16:52:13,145 INFO [train.py:421] (7/8) Epoch 0, batch 44600, loss[loss=2.532, over 1610.00 frames. , ppl: 12.57399851262573] tot_loss[loss=2.486, over 5448083.26 frames. , ppl: 12.00885048860255], batch size: 70
+2022-12-09 16:53:54,415 INFO [train.py:421] (7/8) Epoch 0, batch 44800, loss[loss=2.681, over 1190.00 frames. , ppl: 14.60048712173622] tot_loss[loss=2.484, over 5476323.16 frames. , ppl: 11.990670393553682], batch size: 70
+2022-12-09 16:55:31,012 INFO [train.py:421] (7/8) Epoch 0, batch 45000, loss[loss=2.431, over 1400.00 frames. , ppl: 11.370237919039367] tot_loss[loss=2.483, over 5468875.93 frames. , ppl: 11.981393429210721], batch size: 70
+2022-12-09 16:55:31,013 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 16:55:31,771 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.459, over 211138.00 frames. , ppl: 11.693083254495477
+2022-12-09 16:57:12,295 INFO [train.py:421] (7/8) Epoch 0, batch 45200, loss[loss=2.524, over 1890.00 frames. , ppl: 12.474293601211768] tot_loss[loss=2.483, over 5499832.43 frames. , ppl: 11.972813069407856], batch size: 70
+2022-12-09 16:58:52,876 INFO [train.py:421] (7/8) Epoch 0, batch 45400, loss[loss=3.281, over 560.00 frames. , ppl: 26.597890527876753] tot_loss[loss=2.483, over 5490573.69 frames. , ppl: 11.97989401307413], batch size: 70
+2022-12-09 17:00:33,544 INFO [train.py:421] (7/8) Epoch 0, batch 45600, loss[loss=2.681, over 1120.00 frames. , ppl: 14.59916656742299] tot_loss[loss=2.482, over 5508905.48 frames. , ppl: 11.966962318476893], batch size: 70
+2022-12-09 17:02:15,307 INFO [train.py:421] (7/8) Epoch 0, batch 45800, loss[loss=2.548, over 2940.00 frames. , ppl: 12.781091132670696] tot_loss[loss=2.482, over 5537566.76 frames. , ppl: 11.967319072800743], batch size: 70
+2022-12-09 17:03:53,494 INFO [train.py:421] (7/8) Epoch 0, batch 46000, loss[loss=2.547, over 2030.00 frames. , ppl: 12.774218328943352] tot_loss[loss=2.483, over 5500987.36 frames. , ppl: 11.972355594197317], batch size: 70
+2022-12-09 17:03:53,495 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 17:03:54,253 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.455, over 211138.00 frames. , ppl: 11.65209699143015
+2022-12-09 17:05:29,359 INFO [train.py:421] (7/8) Epoch 0, batch 46200, loss[loss=2.559, over 1330.00 frames. , ppl: 12.919175747910934] tot_loss[loss=2.483, over 5479685.78 frames. , ppl: 11.97183933327871], batch size: 70
+2022-12-09 17:07:09,589 INFO [train.py:421] (7/8) Epoch 0, batch 46400, loss[loss=2.807, over 770.00 frames. , ppl: 16.559268235680406] tot_loss[loss=2.482, over 5451749.12 frames. , ppl: 11.965091430571611], batch size: 70
+2022-12-09 17:08:51,915 INFO [train.py:421] (7/8) Epoch 0, batch 46600, loss[loss=2.379, over 8400.00 frames. , ppl: 10.792454053972627] tot_loss[loss=2.481, over 5493698.65 frames. , ppl: 11.949105135086171], batch size: 70
+2022-12-09 17:10:31,043 INFO [train.py:421] (7/8) Epoch 0, batch 46800, loss[loss=2.573, over 2660.00 frames. , ppl: 13.0990040276833] tot_loss[loss=2.481, over 5463013.54 frames. , ppl: 11.95112098563522], batch size: 70
+2022-12-09 17:12:09,904 INFO [train.py:421] (7/8) Epoch 0, batch 47000, loss[loss=2.715, over 770.00 frames. , ppl: 15.10425184738884] tot_loss[loss=2.481, over 5419576.31 frames. , ppl: 11.954548455535706], batch size: 70
+2022-12-09 17:12:09,904 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 17:12:10,666 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.453, over 211138.00 frames. , ppl: 11.621817980016578
+2022-12-09 17:13:49,887 INFO [train.py:421] (7/8) Epoch 0, batch 47200, loss[loss=2.505, over 2730.00 frames. , ppl: 12.237822455739684] tot_loss[loss=2.482, over 5376145.69 frames. , ppl: 11.965119073081034], batch size: 70
+2022-12-09 17:15:28,651 INFO [train.py:421] (7/8) Epoch 0, batch 47400, loss[loss=2.455, over 1960.00 frames. , ppl: 11.644816423322224] tot_loss[loss=2.481, over 5372593.90 frames. , ppl: 11.951451119832603], batch size: 70
+2022-12-09 17:17:08,453 INFO [train.py:421] (7/8) Epoch 0, batch 47600, loss[loss=2.483, over 2800.00 frames. , ppl: 11.976853352919475] tot_loss[loss=2.479, over 5432942.61 frames. , ppl: 11.931594819693814], batch size: 70
+2022-12-09 17:18:46,708 INFO [train.py:421] (7/8) Epoch 0, batch 47800, loss[loss=2.68, over 770.00 frames. , ppl: 14.58612180615309] tot_loss[loss=2.48, over 5374222.28 frames. , ppl: 11.936451882473879], batch size: 70
+2022-12-09 17:20:33,546 INFO [train.py:421] (7/8) Epoch 0, batch 48000, loss[loss=2.702, over 980.00 frames. , ppl: 14.909676375003759] tot_loss[loss=2.48, over 5390886.62 frames. , ppl: 11.936553000807645], batch size: 70
+2022-12-09 17:20:33,546 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 17:20:34,308 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.453, over 211138.00 frames. , ppl: 11.621976231748523
+2022-12-09 17:22:13,220 INFO [train.py:421] (7/8) Epoch 0, batch 48200, loss[loss=2.407, over 3080.00 frames. , ppl: 11.099133141886863] tot_loss[loss=2.478, over 5395434.59 frames. , ppl: 11.921268164661168], batch size: 70
+2022-12-09 17:23:50,816 INFO [train.py:421] (7/8) Epoch 0, batch 48400, loss[loss=2.558, over 2100.00 frames. , ppl: 12.90652777471264] tot_loss[loss=2.479, over 5378196.74 frames. , ppl: 11.92606276079309], batch size: 70
+2022-12-09 17:25:30,263 INFO [train.py:421] (7/8) Epoch 0, batch 48600, loss[loss=2.477, over 4480.00 frames. , ppl: 11.905919821842282] tot_loss[loss=2.479, over 5370975.21 frames. , ppl: 11.927273632506694], batch size: 70
+2022-12-09 17:27:09,485 INFO [train.py:421] (7/8) Epoch 0, batch 48800, loss[loss=2.442, over 7350.00 frames. , ppl: 11.500775116398762] tot_loss[loss=2.479, over 5365884.98 frames. , ppl: 11.923823503061184], batch size: 70
+2022-12-09 17:28:45,144 INFO [train.py:421] (7/8) Epoch 0, batch 49000, loss[loss=2.575, over 1190.00 frames. , ppl: 13.130557465836183] tot_loss[loss=2.478, over 5338881.03 frames. , ppl: 11.920117284919987], batch size: 70
+2022-12-09 17:28:45,144 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 17:28:45,901 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.449, over 211138.00 frames. , ppl: 11.574441333093757
+2022-12-09 17:30:31,209 INFO [train.py:421] (7/8) Epoch 0, batch 49200, loss[loss=2.455, over 2170.00 frames. , ppl: 11.647621272277796] tot_loss[loss=2.476, over 5426826.70 frames. , ppl: 11.89099785974978], batch size: 70
+2022-12-09 17:32:12,943 INFO [train.py:421] (7/8) Epoch 0, batch 49400, loss[loss=2.515, over 2450.00 frames. , ppl: 12.365004398516286] tot_loss[loss=2.475, over 5432408.97 frames. , ppl: 11.88309666295338], batch size: 70
+2022-12-09 17:33:55,713 INFO [train.py:421] (7/8) Epoch 0, batch 49600, loss[loss=2.383, over 4340.00 frames. , ppl: 10.834544509920907] tot_loss[loss=2.475, over 5439107.24 frames. , ppl: 11.881391679640782], batch size: 70
+2022-12-09 17:35:36,204 INFO [train.py:421] (7/8) Epoch 0, batch 49800, loss[loss=2.474, over 3710.00 frames. , ppl: 11.875006652423865] tot_loss[loss=2.474, over 5456355.94 frames. , ppl: 11.872433017860713], batch size: 70
+2022-12-09 17:37:18,309 INFO [train.py:421] (7/8) Epoch 0, batch 50000, loss[loss=2.822, over 630.00 frames. , ppl: 16.808086002595033] tot_loss[loss=2.474, over 5474439.19 frames. , ppl: 11.871609988726632], batch size: 70
+2022-12-09 17:37:18,310 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 17:37:19,072 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.445, over 211138.00 frames. , ppl: 11.528131384960666
+2022-12-09 17:38:55,889 INFO [train.py:421] (7/8) Epoch 0, batch 50200, loss[loss=3.067, over 560.00 frames. , ppl: 21.46730191042514] tot_loss[loss=2.474, over 5441407.97 frames. , ppl: 11.870024798538145], batch size: 70
+2022-12-09 17:40:41,945 INFO [train.py:421] (7/8) Epoch 0, batch 50400, loss[loss=2.308, over 3710.00 frames. , ppl: 10.05777324365389] tot_loss[loss=2.473, over 5428389.16 frames. , ppl: 11.861540566414304], batch size: 70
+2022-12-09 17:42:23,293 INFO [train.py:421] (7/8) Epoch 0, batch 50600, loss[loss=2.526, over 1890.00 frames. , ppl: 12.501955932243] tot_loss[loss=2.472, over 5453301.19 frames. , ppl: 11.841785750530988], batch size: 70
+2022-12-09 17:44:03,399 INFO [train.py:421] (7/8) Epoch 0, batch 50800, loss[loss=2.853, over 630.00 frames. , ppl: 17.33561493013211] tot_loss[loss=2.472, over 5438826.40 frames. , ppl: 11.84452059992568], batch size: 70
+2022-12-09 17:45:43,893 INFO [train.py:421] (7/8) Epoch 0, batch 51000, loss[loss=2.571, over 1050.00 frames. , ppl: 13.078194947697336] tot_loss[loss=2.471, over 5462671.92 frames. , ppl: 11.831321460077342], batch size: 70
+2022-12-09 17:45:43,893 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 17:45:44,651 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.442, over 211138.00 frames. , ppl: 11.496775701837747
+2022-12-09 17:47:23,524 INFO [train.py:421] (7/8) Epoch 0, batch 51200, loss[loss=2.439, over 10640.00 frames. , ppl: 11.465486332488442] tot_loss[loss=2.47, over 5484940.22 frames. , ppl: 11.817864227713352], batch size: 70
+2022-12-09 17:49:00,223 INFO [train.py:421] (7/8) Epoch 0, batch 51400, loss[loss=2.397, over 3710.00 frames. , ppl: 10.995205983874783] tot_loss[loss=2.469, over 5486554.99 frames. , ppl: 11.8095941724182], batch size: 70
+2022-12-09 17:50:40,892 INFO [train.py:421] (7/8) Epoch 0, batch 51600, loss[loss=2.466, over 1260.00 frames. , ppl: 11.778018603546126] tot_loss[loss=2.469, over 5508335.17 frames. , ppl: 11.805741466681528], batch size: 70
+2022-12-09 17:52:21,993 INFO [train.py:421] (7/8) Epoch 0, batch 51800, loss[loss=2.65, over 770.00 frames. , ppl: 14.156738290939984] tot_loss[loss=2.468, over 5492499.35 frames. , ppl: 11.80171861378324], batch size: 70
+2022-12-09 17:54:03,061 INFO [train.py:421] (7/8) Epoch 0, batch 52000, loss[loss=2.393, over 3640.00 frames. , ppl: 10.944235459636989] tot_loss[loss=2.468, over 5467116.53 frames. , ppl: 11.804137150543694], batch size: 70
+2022-12-09 17:54:03,062 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 17:54:03,822 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.441, over 211138.00 frames. , ppl: 11.488961168872661
+2022-12-09 17:55:46,384 INFO [train.py:421] (7/8) Epoch 0, batch 52200, loss[loss=2.729, over 770.00 frames. , ppl: 15.320681653409116] tot_loss[loss=2.468, over 5463179.93 frames. , ppl: 11.79900492694567], batch size: 70
+2022-12-09 17:57:27,049 INFO [train.py:421] (7/8) Epoch 0, batch 52400, loss[loss=2.553, over 1890.00 frames. , ppl: 12.851288286653304] tot_loss[loss=2.467, over 5447845.00 frames. , ppl: 11.790711465997042], batch size: 70
+2022-12-09 17:59:04,826 INFO [train.py:421] (7/8) Epoch 0, batch 52600, loss[loss=2.444, over 1330.00 frames. , ppl: 11.522533442705319] tot_loss[loss=2.465, over 5479514.63 frames. , ppl: 11.76623347165324], batch size: 70
+2022-12-09 18:00:44,984 INFO [train.py:421] (7/8) Epoch 0, batch 52800, loss[loss=2.456, over 4060.00 frames. , ppl: 11.654285009247543] tot_loss[loss=2.465, over 5453077.04 frames. , ppl: 11.763274017287015], batch size: 70
+2022-12-09 18:02:25,847 INFO [train.py:421] (7/8) Epoch 0, batch 53000, loss[loss=2.439, over 2660.00 frames. , ppl: 11.464253071056284] tot_loss[loss=2.465, over 5457107.85 frames. , ppl: 11.759072392550799], batch size: 70
+2022-12-09 18:02:25,847 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 18:02:26,589 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.439, over 211138.00 frames. , ppl: 11.45966239282214
+2022-12-09 18:04:04,858 INFO [train.py:421] (7/8) Epoch 0, batch 53200, loss[loss=2.421, over 4270.00 frames. , ppl: 11.252091365609862] tot_loss[loss=2.464, over 5478586.14 frames. , ppl: 11.749294462270347], batch size: 70
+2022-12-09 18:05:43,609 INFO [train.py:421] (7/8) Epoch 0, batch 53400, loss[loss=2.441, over 1540.00 frames. , ppl: 11.48110728504047] tot_loss[loss=2.462, over 5509722.08 frames. , ppl: 11.730406084970323], batch size: 70
+2022-12-09 18:07:22,521 INFO [train.py:421] (7/8) Epoch 0, batch 53600, loss[loss=2.423, over 10640.00 frames. , ppl: 11.278047880091385] tot_loss[loss=2.462, over 5539820.83 frames. , ppl: 11.724605413862635], batch size: 70
+2022-12-09 18:09:01,078 INFO [train.py:421] (7/8) Epoch 0, batch 53800, loss[loss=2.546, over 1680.00 frames. , ppl: 12.75295114199216] tot_loss[loss=2.461, over 5539995.77 frames. , ppl: 11.718753409397296], batch size: 70
+2022-12-09 18:10:37,936 INFO [train.py:421] (7/8) Epoch 0, batch 54000, loss[loss=3.244, over 560.00 frames. , ppl: 25.64316545641691] tot_loss[loss=2.461, over 5533996.17 frames. , ppl: 11.719142595209563], batch size: 70
+2022-12-09 18:10:37,936 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 18:10:38,696 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.437, over 211138.00 frames. , ppl: 11.437813533531314
+2022-12-09 18:12:17,930 INFO [train.py:421] (7/8) Epoch 0, batch 54200, loss[loss=2.556, over 1330.00 frames. , ppl: 12.881982602172409] tot_loss[loss=2.462, over 5517056.27 frames. , ppl: 11.724246555250131], batch size: 70
+2022-12-09 18:13:57,248 INFO [train.py:421] (7/8) Epoch 0, batch 54400, loss[loss=2.357, over 9520.00 frames. , ppl: 10.556129501166932] tot_loss[loss=2.46, over 5549158.12 frames. , ppl: 11.705274299404566], batch size: 70
+2022-12-09 18:15:38,993 INFO [train.py:421] (7/8) Epoch 0, batch 54600, loss[loss=2.537, over 1680.00 frames. , ppl: 12.640584241421776] tot_loss[loss=2.46, over 5513358.43 frames. , ppl: 11.707346932576137], batch size: 70
+2022-12-09 18:17:17,688 INFO [train.py:421] (7/8) Epoch 0, batch 54800, loss[loss=2.602, over 1120.00 frames. , ppl: 13.485261889879489] tot_loss[loss=2.459, over 5537609.02 frames. , ppl: 11.69127868001498], batch size: 70
+2022-12-09 18:18:54,918 INFO [train.py:421] (7/8) Epoch 0, batch 55000, loss[loss=2.561, over 2380.00 frames. , ppl: 12.944678054650351] tot_loss[loss=2.46, over 5500992.93 frames. , ppl: 11.69960427278868], batch size: 70
+2022-12-09 18:18:54,918 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 18:18:55,677 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.435, over 211138.00 frames. , ppl: 11.413029548583495
+2022-12-09 18:20:34,878 INFO [train.py:421] (7/8) Epoch 0, batch 55200, loss[loss=2.423, over 4550.00 frames. , ppl: 11.274807675183768] tot_loss[loss=2.458, over 5562884.52 frames. , ppl: 11.676222725155258], batch size: 70
+2022-12-09 18:22:16,319 INFO [train.py:421] (7/8) Epoch 0, batch 55400, loss[loss=2.413, over 4620.00 frames. , ppl: 11.172079897573653] tot_loss[loss=2.459, over 5510431.13 frames. , ppl: 11.690440149089959], batch size: 70
+2022-12-09 18:23:55,793 INFO [train.py:421] (7/8) Epoch 0, batch 55600, loss[loss=2.502, over 1680.00 frames. , ppl: 12.200841839142054] tot_loss[loss=2.457, over 5538135.46 frames. , ppl: 11.675427326793585], batch size: 70
+2022-12-09 18:25:34,332 INFO [train.py:421] (7/8) Epoch 0, batch 55800, loss[loss=2.58, over 1680.00 frames. , ppl: 13.196036603002122] tot_loss[loss=2.457, over 5508595.34 frames. , ppl: 11.675217091573165], batch size: 70
+2022-12-09 18:27:11,393 INFO [train.py:421] (7/8) Epoch 0, batch 56000, loss[loss=3.033, over 560.00 frames. , ppl: 20.76828354146122] tot_loss[loss=2.456, over 5522426.90 frames. , ppl: 11.66171426341101], batch size: 70
+2022-12-09 18:27:11,394 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 18:27:12,150 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.435, over 211138.00 frames. , ppl: 11.411955259320733
+2022-12-09 18:28:51,286 INFO [train.py:421] (7/8) Epoch 0, batch 56200, loss[loss=2.543, over 1470.00 frames. , ppl: 12.711636543419907] tot_loss[loss=2.456, over 5524366.48 frames. , ppl: 11.661416521765807], batch size: 70
+2022-12-09 18:30:31,871 INFO [train.py:421] (7/8) Epoch 0, batch 56400, loss[loss=2.409, over 5040.00 frames. , ppl: 11.121887438090189] tot_loss[loss=2.457, over 5508640.38 frames. , ppl: 11.664505392231137], batch size: 70
+2022-12-09 18:32:12,542 INFO [train.py:421] (7/8) Epoch 0, batch 56600, loss[loss=2.59, over 1190.00 frames. , ppl: 13.326414860982581] tot_loss[loss=2.457, over 5515445.44 frames. , ppl: 11.666053991332463], batch size: 70
+2022-12-09 18:33:53,495 INFO [train.py:421] (7/8) Epoch 0, batch 56800, loss[loss=2.506, over 2730.00 frames. , ppl: 12.255183405754948] tot_loss[loss=2.457, over 5513741.20 frames. , ppl: 11.667566335404137], batch size: 70
+2022-12-09 18:35:37,613 INFO [train.py:421] (7/8) Epoch 0, batch 57000, loss[loss=2.584, over 1050.00 frames. , ppl: 13.24566391791719] tot_loss[loss=2.456, over 5504552.59 frames. , ppl: 11.662861476889274], batch size: 70
+2022-12-09 18:35:37,614 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 18:35:38,358 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.428, over 211138.00 frames. , ppl: 11.336884940977864
+2022-12-09 18:37:20,806 INFO [train.py:421] (7/8) Epoch 0, batch 57200, loss[loss=2.524, over 1820.00 frames. , ppl: 12.477407520870283] tot_loss[loss=2.456, over 5502438.19 frames. , ppl: 11.661784198411624], batch size: 70
+2022-12-09 18:39:00,406 INFO [train.py:421] (7/8) Epoch 0, batch 57400, loss[loss=2.663, over 1050.00 frames. , ppl: 14.343779440379217] tot_loss[loss=2.457, over 5477983.45 frames. , ppl: 11.664349186893958], batch size: 70
+2022-12-09 18:40:42,489 INFO [train.py:421] (7/8) Epoch 0, batch 57600, loss[loss=2.479, over 3150.00 frames. , ppl: 11.925744500887605] tot_loss[loss=2.455, over 5499866.91 frames. , ppl: 11.649008766982735], batch size: 70
+2022-12-09 18:42:21,001 INFO [train.py:421] (7/8) Epoch 0, batch 57800, loss[loss=2.361, over 7140.00 frames. , ppl: 10.602216234979098] tot_loss[loss=2.456, over 5453481.06 frames. , ppl: 11.652567890537139], batch size: 70
+2022-12-09 18:44:01,540 INFO [train.py:421] (7/8) Epoch 0, batch 58000, loss[loss=2.953, over 560.00 frames. , ppl: 19.16112895209667] tot_loss[loss=2.456, over 5417714.20 frames. , ppl: 11.658192588082976], batch size: 70
+2022-12-09 18:44:01,541 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 18:44:02,301 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.427, over 211138.00 frames. , ppl: 11.325093455985686
+2022-12-09 18:45:45,018 INFO [train.py:421] (7/8) Epoch 0, batch 58200, loss[loss=2.426, over 4830.00 frames. , ppl: 11.31102843190782] tot_loss[loss=2.456, over 5406685.67 frames. , ppl: 11.662127429131793], batch size: 70
+2022-12-09 18:47:28,537 INFO [train.py:421] (7/8) Epoch 0, batch 58400, loss[loss=2.444, over 6860.00 frames. , ppl: 11.514201260394966] tot_loss[loss=2.455, over 5451558.72 frames. , ppl: 11.64608792659383], batch size: 70
+2022-12-09 18:49:11,539 INFO [train.py:421] (7/8) Epoch 0, batch 58600, loss[loss=2.365, over 6930.00 frames. , ppl: 10.647452023195898] tot_loss[loss=2.454, over 5472210.92 frames. , ppl: 11.632872526762602], batch size: 70
+2022-12-09 18:50:48,054 INFO [train.py:421] (7/8) Epoch 0, batch 58800, loss[loss=2.417, over 3360.00 frames. , ppl: 11.208240066901078] tot_loss[loss=2.453, over 5465744.94 frames. , ppl: 11.621548416429553], batch size: 70
+2022-12-09 18:52:28,262 INFO [train.py:421] (7/8) Epoch 0, batch 59000, loss[loss=2.642, over 840.00 frames. , ppl: 14.044046150775692] tot_loss[loss=2.453, over 5471523.84 frames. , ppl: 11.617745202149862], batch size: 70
+2022-12-09 18:52:28,263 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 18:52:29,026 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.429, over 211138.00 frames. , ppl: 11.349824230730555
+2022-12-09 18:54:09,184 INFO [train.py:421] (7/8) Epoch 0, batch 59200, loss[loss=3.59, over 420.00 frames. , ppl: 36.235522942566966] tot_loss[loss=2.453, over 5421926.80 frames. , ppl: 11.626528566288991], batch size: 70
+2022-12-09 18:55:49,441 INFO [train.py:421] (7/8) Epoch 0, batch 59400, loss[loss=2.488, over 2310.00 frames. , ppl: 12.038263056259535] tot_loss[loss=2.453, over 5404281.56 frames. , ppl: 11.626427118745669], batch size: 70
+2022-12-09 18:57:31,357 INFO [train.py:421] (7/8) Epoch 0, batch 59600, loss[loss=2.388, over 3500.00 frames. , ppl: 10.894041188766117] tot_loss[loss=2.453, over 5422222.78 frames. , ppl: 11.618424891788758], batch size: 70
+2022-12-09 18:59:09,089 INFO [train.py:421] (7/8) Epoch 0, batch 59800, loss[loss=2.629, over 1330.00 frames. , ppl: 13.859122736495985] tot_loss[loss=2.453, over 5410433.44 frames. , ppl: 11.626617041476672], batch size: 70
+2022-12-09 19:00:50,598 INFO [train.py:421] (7/8) Epoch 0, batch 60000, loss[loss=2.474, over 1610.00 frames. , ppl: 11.873643443926701] tot_loss[loss=2.452, over 5435834.97 frames. , ppl: 11.612805445078973], batch size: 70
+2022-12-09 19:00:50,599 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 19:00:51,357 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.426, over 211138.00 frames. , ppl: 11.316449249268606
+2022-12-09 19:02:33,564 INFO [train.py:421] (7/8) Epoch 0, batch 60200, loss[loss=2.36, over 6650.00 frames. , ppl: 10.594370547340324] tot_loss[loss=2.452, over 5415835.89 frames. , ppl: 11.609160646212965], batch size: 70
+2022-12-09 19:04:11,513 INFO [train.py:421] (7/8) Epoch 0, batch 60400, loss[loss=2.381, over 7280.00 frames. , ppl: 10.812538703341396] tot_loss[loss=2.451, over 5399885.26 frames. , ppl: 11.602059969429703], batch size: 70
+2022-12-09 19:05:47,683 INFO [train.py:421] (7/8) Epoch 0, batch 60600, loss[loss=2.497, over 3150.00 frames. , ppl: 12.15075725131527] tot_loss[loss=2.45, over 5404048.76 frames. , ppl: 11.592823287595124], batch size: 70
+2022-12-09 19:07:33,495 INFO [train.py:421] (7/8) Epoch 0, batch 60800, loss[loss=2.525, over 1540.00 frames. , ppl: 12.49567444253063] tot_loss[loss=2.449, over 5439405.23 frames. , ppl: 11.578943852347901], batch size: 70
+2022-12-09 19:09:14,084 INFO [train.py:421] (7/8) Epoch 0, batch 61000, loss[loss=2.299, over 11060.00 frames. , ppl: 9.96386612677259] tot_loss[loss=2.45, over 5421808.50 frames. , ppl: 11.584944356723254], batch size: 70
+2022-12-09 19:09:14,085 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 19:09:14,814 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.424, over 211138.00 frames. , ppl: 11.292349414932128
+2022-12-09 19:10:56,125 INFO [train.py:421] (7/8) Epoch 0, batch 61200, loss[loss=2.799, over 1050.00 frames. , ppl: 16.4321864763548] tot_loss[loss=2.449, over 5424701.19 frames. , ppl: 11.578096104016103], batch size: 70
+2022-12-09 19:12:36,990 INFO [train.py:421] (7/8) Epoch 0, batch 61400, loss[loss=2.552, over 1540.00 frames. , ppl: 12.827764998651974] tot_loss[loss=2.448, over 5487587.45 frames. , ppl: 11.563521362232034], batch size: 70
+2022-12-09 19:14:17,499 INFO [train.py:421] (7/8) Epoch 0, batch 61600, loss[loss=2.422, over 9100.00 frames. , ppl: 11.26507661096143] tot_loss[loss=2.447, over 5484552.86 frames. , ppl: 11.557937383393275], batch size: 70
+2022-12-09 19:16:00,806 INFO [train.py:421] (7/8) Epoch 0, batch 61800, loss[loss=2.381, over 5810.00 frames. , ppl: 10.816733736881583] tot_loss[loss=2.445, over 5553058.38 frames. , ppl: 11.534989006987827], batch size: 70
+2022-12-09 19:17:37,924 INFO [train.py:421] (7/8) Epoch 0, batch 62000, loss[loss=2.327, over 5950.00 frames. , ppl: 10.242261580852828] tot_loss[loss=2.445, over 5537597.46 frames. , ppl: 11.533211727869569], batch size: 70
+2022-12-09 19:17:37,925 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 19:17:38,663 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.422, over 211138.00 frames. , ppl: 11.26730360842701
+2022-12-09 19:19:16,403 INFO [train.py:421] (7/8) Epoch 0, batch 62200, loss[loss=2.376, over 3290.00 frames. , ppl: 10.763782357761022] tot_loss[loss=2.445, over 5501147.13 frames. , ppl: 11.536283018403413], batch size: 70
+2022-12-09 19:20:55,513 INFO [train.py:421] (7/8) Epoch 0, batch 62400, loss[loss=2.398, over 5180.00 frames. , ppl: 11.002659213089224] tot_loss[loss=2.445, over 5491916.02 frames. , ppl: 11.530944448096424], batch size: 70
+2022-12-09 19:22:38,381 INFO [train.py:421] (7/8) Epoch 0, batch 62600, loss[loss=2.409, over 3920.00 frames. , ppl: 11.119506106214486] tot_loss[loss=2.444, over 5501352.48 frames. , ppl: 11.522420902259604], batch size: 70
+2022-12-09 19:24:18,378 INFO [train.py:421] (7/8) Epoch 0, batch 62800, loss[loss=2.397, over 2870.00 frames. , ppl: 10.991942721047575] tot_loss[loss=2.444, over 5460687.30 frames. , ppl: 11.524784797151561], batch size: 70
+2022-12-09 19:25:57,775 INFO [train.py:421] (7/8) Epoch 0, batch 63000, loss[loss=2.392, over 6650.00 frames. , ppl: 10.930495399829434] tot_loss[loss=2.444, over 5499325.24 frames. , ppl: 11.518241747620127], batch size: 70
+2022-12-09 19:25:57,775 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 19:25:58,533 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.419, over 211138.00 frames. , ppl: 11.238974307884806
+2022-12-09 19:27:42,799 INFO [train.py:421] (7/8) Epoch 0, batch 63200, loss[loss=2.535, over 2170.00 frames. , ppl: 12.621210721546207] tot_loss[loss=2.443, over 5532921.86 frames. , ppl: 11.50861158892706], batch size: 70
+2022-12-09 19:29:19,323 INFO [train.py:421] (7/8) Epoch 0, batch 63400, loss[loss=2.453, over 4060.00 frames. , ppl: 11.623012094966002] tot_loss[loss=2.443, over 5505654.30 frames. , ppl: 11.508145845344949], batch size: 70
+2022-12-09 19:30:58,089 INFO [train.py:421] (7/8) Epoch 0, batch 63600, loss[loss=2.372, over 1890.00 frames. , ppl: 10.72184993685374] tot_loss[loss=2.443, over 5525877.25 frames. , ppl: 11.50881180574794], batch size: 70
+2022-12-09 19:32:37,332 INFO [train.py:421] (7/8) Epoch 0, batch 63800, loss[loss=2.524, over 1260.00 frames. , ppl: 12.47633375744663] tot_loss[loss=2.443, over 5497794.23 frames. , ppl: 11.50920432052498], batch size: 70
+2022-12-09 19:34:18,415 INFO [train.py:421] (7/8) Epoch 0, batch 64000, loss[loss=2.72, over 770.00 frames. , ppl: 15.18148514900073] tot_loss[loss=2.441, over 5587059.48 frames. , ppl: 11.487923211344729], batch size: 70
+2022-12-09 19:34:18,415 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 19:34:19,175 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.418, over 211138.00 frames. , ppl: 11.224827241902219
+2022-12-09 19:35:57,968 INFO [train.py:421] (7/8) Epoch 0, batch 64200, loss[loss=2.479, over 2240.00 frames. , ppl: 11.93256683562414] tot_loss[loss=2.441, over 5588846.96 frames. , ppl: 11.482416118645329], batch size: 70
+2022-12-09 19:37:37,733 INFO [train.py:421] (7/8) Epoch 0, batch 64400, loss[loss=2.334, over 3500.00 frames. , ppl: 10.323779424297127] tot_loss[loss=2.44, over 5577419.15 frames. , ppl: 11.476108054527781], batch size: 70
+2022-12-09 19:39:14,490 INFO [train.py:421] (7/8) Epoch 0, batch 64600, loss[loss=2.524, over 1400.00 frames. , ppl: 12.47763247615871] tot_loss[loss=2.44, over 5577268.15 frames. , ppl: 11.4695792460896], batch size: 70
+2022-12-09 19:40:56,625 INFO [train.py:421] (7/8) Epoch 0, batch 64800, loss[loss=2.354, over 4760.00 frames. , ppl: 10.524907424639114] tot_loss[loss=2.439, over 5568101.53 frames. , ppl: 11.45620517599479], batch size: 70
+2022-12-09 19:42:37,262 INFO [train.py:421] (7/8) Epoch 0, batch 65000, loss[loss=2.655, over 910.00 frames. , ppl: 14.22692948783945] tot_loss[loss=2.439, over 5541253.56 frames. , ppl: 11.457223610293319], batch size: 70
+2022-12-09 19:42:37,262 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 19:42:38,022 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.417, over 211138.00 frames. , ppl: 11.211114467296362
+2022-12-09 19:44:16,900 INFO [train.py:421] (7/8) Epoch 0, batch 65200, loss[loss=2.5, over 2380.00 frames. , ppl: 12.177266415699004] tot_loss[loss=2.44, over 5506421.82 frames. , ppl: 11.47119127484289], batch size: 70
+2022-12-09 19:45:56,839 INFO [train.py:421] (7/8) Epoch 0, batch 65400, loss[loss=2.485, over 1610.00 frames. , ppl: 12.000886224203443] tot_loss[loss=2.44, over 5514720.73 frames. , ppl: 11.469526918254925], batch size: 70
+2022-12-09 19:47:35,896 INFO [train.py:421] (7/8) Epoch 0, batch 65600, loss[loss=2.583, over 3080.00 frames. , ppl: 13.23061735992518] tot_loss[loss=2.44, over 5479054.20 frames. , ppl: 11.477724226068212], batch size: 70
+2022-12-09 19:49:13,441 INFO [train.py:421] (7/8) Epoch 0, batch 65800, loss[loss=4.137, over 350.00 frames. , ppl: 62.620146385264924] tot_loss[loss=2.44, over 5483486.22 frames. , ppl: 11.467427039653346], batch size: 70
+2022-12-09 19:50:53,678 INFO [train.py:421] (7/8) Epoch 0, batch 66000, loss[loss=2.47, over 3290.00 frames. , ppl: 11.818046397753921] tot_loss[loss=2.439, over 5488549.18 frames. , ppl: 11.465735366549657], batch size: 70
+2022-12-09 19:50:53,679 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 19:50:54,438 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.415, over 211138.00 frames. , ppl: 11.192550351531178
+2022-12-09 19:52:35,268 INFO [train.py:421] (7/8) Epoch 0, batch 66200, loss[loss=2.528, over 1540.00 frames. , ppl: 12.529549389133246] tot_loss[loss=2.44, over 5458822.65 frames. , ppl: 11.47341659167798], batch size: 70
+2022-12-09 19:54:17,400 INFO [train.py:421] (7/8) Epoch 0, batch 66400, loss[loss=2.593, over 2030.00 frames. , ppl: 13.374800325851252] tot_loss[loss=2.44, over 5453386.59 frames. , ppl: 11.468416165930135], batch size: 70
+2022-12-09 19:56:01,942 INFO [train.py:421] (7/8) Epoch 0, batch 66600, loss[loss=2.347, over 5670.00 frames. , ppl: 10.457463323241805] tot_loss[loss=2.439, over 5452224.02 frames. , ppl: 11.4601841825465], batch size: 70
+2022-12-09 19:57:44,180 INFO [train.py:421] (7/8) Epoch 0, batch 66800, loss[loss=2.581, over 980.00 frames. , ppl: 13.211251957570825] tot_loss[loss=2.438, over 5422967.17 frames. , ppl: 11.455704374057117], batch size: 70
+2022-12-09 19:59:25,913 INFO [train.py:421] (7/8) Epoch 0, batch 67000, loss[loss=2.583, over 980.00 frames. , ppl: 13.232111754541966] tot_loss[loss=2.438, over 5467290.45 frames. , ppl: 11.448112167162847], batch size: 70
+2022-12-09 19:59:25,913 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 19:59:26,673 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.412, over 211138.00 frames. , ppl: 11.1568600153867
+2022-12-09 20:01:08,430 INFO [train.py:421] (7/8) Epoch 0, batch 67200, loss[loss=2.586, over 1540.00 frames. , ppl: 13.278943427456786] tot_loss[loss=2.437, over 5461424.81 frames. , ppl: 11.44103462840489], batch size: 70
+2022-12-09 20:02:47,733 INFO [train.py:421] (7/8) Epoch 0, batch 67400, loss[loss=2.581, over 1890.00 frames. , ppl: 13.214259385021087] tot_loss[loss=2.437, over 5470160.64 frames. , ppl: 11.435394941966795], batch size: 70
+2022-12-09 20:04:25,981 INFO [train.py:421] (7/8) Epoch 0, batch 67600, loss[loss=2.356, over 3010.00 frames. , ppl: 10.546309561006499] tot_loss[loss=2.436, over 5477859.05 frames. , ppl: 11.423506815253585], batch size: 70
+2022-12-09 20:06:07,198 INFO [train.py:421] (7/8) Epoch 0, batch 67800, loss[loss=2.456, over 2520.00 frames. , ppl: 11.656794331208786] tot_loss[loss=2.438, over 5423238.17 frames. , ppl: 11.446577107519785], batch size: 70
+2022-12-09 20:07:47,436 INFO [train.py:421] (7/8) Epoch 0, batch 68000, loss[loss=2.358, over 2940.00 frames. , ppl: 10.56926767560465] tot_loss[loss=2.438, over 5410263.87 frames. , ppl: 11.446376549459263], batch size: 70
+2022-12-09 20:07:47,436 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 20:07:48,196 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.413, over 211138.00 frames. , ppl: 11.167173836606553
+2022-12-09 20:09:29,902 INFO [train.py:421] (7/8) Epoch 0, batch 68200, loss[loss=2.698, over 1050.00 frames. , ppl: 14.854331120259896] tot_loss[loss=2.437, over 5427789.59 frames. , ppl: 11.441427243748176], batch size: 70
+2022-12-09 20:11:13,457 INFO [train.py:421] (7/8) Epoch 0, batch 68400, loss[loss=2.45, over 3150.00 frames. , ppl: 11.585334701031197] tot_loss[loss=2.437, over 5446536.06 frames. , ppl: 11.434175223601192], batch size: 70
+2022-12-09 20:12:55,462 INFO [train.py:421] (7/8) Epoch 0, batch 68600, loss[loss=2.65, over 770.00 frames. , ppl: 14.158432845191697] tot_loss[loss=2.436, over 5448459.11 frames. , ppl: 11.422703914681934], batch size: 70
+2022-12-09 20:14:35,017 INFO [train.py:421] (7/8) Epoch 0, batch 68800, loss[loss=2.585, over 1680.00 frames. , ppl: 13.2651611567083] tot_loss[loss=2.435, over 5457633.67 frames. , ppl: 11.41093941270675], batch size: 70
+2022-12-09 20:16:15,817 INFO [train.py:421] (7/8) Epoch 0, batch 69000, loss[loss=2.417, over 1820.00 frames. , ppl: 11.20862597423786] tot_loss[loss=2.433, over 5528903.30 frames. , ppl: 11.389570316317805], batch size: 70
+2022-12-09 20:16:15,818 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 20:16:16,582 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.409, over 211138.00 frames. , ppl: 11.12763404873676
+2022-12-09 20:17:58,588 INFO [train.py:421] (7/8) Epoch 0, batch 69200, loss[loss=2.386, over 3990.00 frames. , ppl: 10.874452554616257] tot_loss[loss=2.432, over 5540220.86 frames. , ppl: 11.381177549852742], batch size: 70
+2022-12-09 20:19:40,454 INFO [train.py:421] (7/8) Epoch 0, batch 69400, loss[loss=2.569, over 1540.00 frames. , ppl: 13.049092752764683] tot_loss[loss=2.431, over 5579356.53 frames. , ppl: 11.373778929457757], batch size: 70
+2022-12-09 20:21:21,257 INFO [train.py:421] (7/8) Epoch 0, batch 69600, loss[loss=2.502, over 1540.00 frames. , ppl: 12.208498006276994] tot_loss[loss=2.432, over 5551820.78 frames. , ppl: 11.380552823057595], batch size: 70
+2022-12-09 20:23:03,000 INFO [train.py:421] (7/8) Epoch 0, batch 69800, loss[loss=2.446, over 2940.00 frames. , ppl: 11.542692602655066] tot_loss[loss=2.431, over 5578812.59 frames. , ppl: 11.37395251928573], batch size: 70
+2022-12-09 20:24:45,775 INFO [train.py:421] (7/8) Epoch 0, batch 70000, loss[loss=2.404, over 5320.00 frames. , ppl: 11.068765927545908] tot_loss[loss=2.432, over 5567662.19 frames. , ppl: 11.375985382149429], batch size: 70
+2022-12-09 20:24:45,775 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 20:24:46,509 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.41, over 211138.00 frames. , ppl: 11.135786255375706
+2022-12-09 20:26:29,617 INFO [train.py:421] (7/8) Epoch 0, batch 70200, loss[loss=2.694, over 840.00 frames. , ppl: 14.794898998211709] tot_loss[loss=2.431, over 5570909.07 frames. , ppl: 11.36519867933417], batch size: 70
+2022-12-09 20:28:07,721 INFO [train.py:421] (7/8) Epoch 0, batch 70400, loss[loss=2.428, over 3430.00 frames. , ppl: 11.332840672636214] tot_loss[loss=2.431, over 5547801.02 frames. , ppl: 11.366848038909003], batch size: 70
+2022-12-09 20:29:47,725 INFO [train.py:421] (7/8) Epoch 0, batch 70600, loss[loss=2.354, over 7350.00 frames. , ppl: 10.529946731877248] tot_loss[loss=2.431, over 5506448.22 frames. , ppl: 11.37386765986476], batch size: 70
+2022-12-09 20:31:33,136 INFO [train.py:421] (7/8) Epoch 0, batch 70800, loss[loss=3.022, over 560.00 frames. , ppl: 20.52340861834952] tot_loss[loss=2.431, over 5506136.63 frames. , ppl: 11.36466595401156], batch size: 70
+2022-12-09 20:33:13,791 INFO [train.py:421] (7/8) Epoch 0, batch 71000, loss[loss=2.673, over 1050.00 frames. , ppl: 14.487202470907786] tot_loss[loss=2.43, over 5486252.65 frames. , ppl: 11.360916650248274], batch size: 70
+2022-12-09 20:33:13,791 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 20:33:14,538 INFO [train.py:452] (7/8) Epoch 0, validation: loss=2.406, over 211138.00 frames. , ppl: 11.087587669142305
+2022-12-09 20:34:53,368 INFO [train.py:421] (7/8) Epoch 0, batch 71200, loss[loss=2.485, over 2170.00 frames. , ppl: 11.995192666313002] tot_loss[loss=2.431, over 5441367.71 frames. , ppl: 11.367771366927842], batch size: 70
+2022-12-09 20:36:32,753 INFO [train.py:421] (7/8) Epoch 0, batch 71400, loss[loss=2.424, over 2800.00 frames. , ppl: 11.29088637120208] tot_loss[loss=2.43, over 5491236.43 frames. , ppl: 11.358456689655346], batch size: 70
+2022-12-09 20:38:12,564 INFO [train.py:421] (7/8) Epoch 0, batch 71600, loss[loss=2.407, over 2660.00 frames. , ppl: 11.095524927731157] tot_loss[loss=2.43, over 5456117.64 frames. , ppl: 11.362561540254594], batch size: 70
+2022-12-09 20:39:51,525 INFO [train.py:421] (7/8) Epoch 0, batch 71800, loss[loss=2.37, over 4340.00 frames. , ppl: 10.698174128145427] tot_loss[loss=2.43, over 5461361.52 frames. , ppl: 11.357245011376348], batch size: 70
+2022-12-09 20:41:07,495 INFO [train.py:421] (7/8) Epoch 1, batch 0, loss[loss=2.71, over 840.00 frames. , ppl: 15.0255307187428] tot_loss[loss=2.71, over 840.00 frames. , ppl: 15.0255307187428], batch size: 70
+2022-12-09 20:42:47,123 INFO [train.py:421] (7/8) Epoch 1, batch 200, loss[loss=2.423, over 4060.00 frames. , ppl: 11.280558870521679] tot_loss[loss=2.422, over 521291.79 frames. , ppl: 11.265572015196646], batch size: 70
+2022-12-09 20:44:26,270 INFO [train.py:421] (7/8) Epoch 1, batch 400, loss[loss=2.292, over 6580.00 frames. , ppl: 9.894888476716927] tot_loss[loss=2.419, over 985741.90 frames. , ppl: 11.2364376616059], batch size: 70
+2022-12-09 20:46:09,603 INFO [train.py:421] (7/8) Epoch 1, batch 600, loss[loss=2.51, over 1750.00 frames. , ppl: 12.30780063009245] tot_loss[loss=2.42, over 1376911.24 frames. , ppl: 11.24250019106756], batch size: 70
+2022-12-09 20:47:54,143 INFO [train.py:421] (7/8) Epoch 1, batch 800, loss[loss=2.47, over 2310.00 frames. , ppl: 11.816941347924566] tot_loss[loss=2.414, over 1854546.88 frames. , ppl: 11.174303710997142], batch size: 70
+2022-12-09 20:49:35,988 INFO [train.py:421] (7/8) Epoch 1, batch 1000, loss[loss=2.624, over 770.00 frames. , ppl: 13.788150676076208] tot_loss[loss=2.414, over 2228654.53 frames. , ppl: 11.176770027861885], batch size: 70
+2022-12-09 20:49:35,989 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 20:49:36,749 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.403, over 211138.00 frames. , ppl: 11.059317373352997
+2022-12-09 20:51:14,565 INFO [train.py:421] (7/8) Epoch 1, batch 1200, loss[loss=2.5, over 1120.00 frames. , ppl: 12.182342593986421] tot_loss[loss=2.415, over 2515143.42 frames. , ppl: 11.187270270333505], batch size: 70
+2022-12-09 20:52:52,417 INFO [train.py:421] (7/8) Epoch 1, batch 1400, loss[loss=2.447, over 1330.00 frames. , ppl: 11.550849537717339] tot_loss[loss=2.416, over 2780379.32 frames. , ppl: 11.201171043736759], batch size: 70
+2022-12-09 20:54:34,023 INFO [train.py:421] (7/8) Epoch 1, batch 1600, loss[loss=2.264, over 3430.00 frames. , ppl: 9.62029584268608] tot_loss[loss=2.417, over 3034713.59 frames. , ppl: 11.212101416149117], batch size: 70
+2022-12-09 20:56:14,666 INFO [train.py:421] (7/8) Epoch 1, batch 1800, loss[loss=2.483, over 2590.00 frames. , ppl: 11.972226084368673] tot_loss[loss=2.418, over 3262182.52 frames. , ppl: 11.226502918846613], batch size: 70
+2022-12-09 20:57:57,543 INFO [train.py:421] (7/8) Epoch 1, batch 2000, loss[loss=2.326, over 4200.00 frames. , ppl: 10.2354105391993] tot_loss[loss=2.417, over 3492929.78 frames. , ppl: 11.215779805629115], batch size: 70
+2022-12-09 20:57:57,543 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 20:57:58,304 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.404, over 211138.00 frames. , ppl: 11.068564594231407
+2022-12-09 20:59:42,327 INFO [train.py:421] (7/8) Epoch 1, batch 2200, loss[loss=2.401, over 3500.00 frames. , ppl: 11.032807410898263] tot_loss[loss=2.417, over 3716297.04 frames. , ppl: 11.207193264736496], batch size: 70
+2022-12-09 21:01:20,653 INFO [train.py:421] (7/8) Epoch 1, batch 2400, loss[loss=2.359, over 1470.00 frames. , ppl: 10.583689057994956] tot_loss[loss=2.419, over 3825480.13 frames. , ppl: 11.239311196293732], batch size: 70
+2022-12-09 21:03:02,887 INFO [train.py:421] (7/8) Epoch 1, batch 2600, loss[loss=2.324, over 7770.00 frames. , ppl: 10.218981304592468] tot_loss[loss=2.416, over 4062180.45 frames. , ppl: 11.206565823039222], batch size: 70
+2022-12-09 21:04:41,925 INFO [train.py:421] (7/8) Epoch 1, batch 2800, loss[loss=2.451, over 1890.00 frames. , ppl: 11.595126773385262] tot_loss[loss=2.417, over 4203706.38 frames. , ppl: 11.207366928645323], batch size: 70
+2022-12-09 21:06:24,203 INFO [train.py:421] (7/8) Epoch 1, batch 3000, loss[loss=2.347, over 12600.00 frames. , ppl: 10.458449844753188] tot_loss[loss=2.418, over 4285713.99 frames. , ppl: 11.225982785677585], batch size: 70
+2022-12-09 21:06:24,203 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 21:06:24,931 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.404, over 211138.00 frames. , ppl: 11.068386028582267
+2022-12-09 21:08:06,437 INFO [train.py:421] (7/8) Epoch 1, batch 3200, loss[loss=2.449, over 2310.00 frames. , ppl: 11.577387889114393] tot_loss[loss=2.416, over 4446532.15 frames. , ppl: 11.205547284106627], batch size: 70
+2022-12-09 21:09:45,261 INFO [train.py:421] (7/8) Epoch 1, batch 3400, loss[loss=2.562, over 1330.00 frames. , ppl: 12.962444926843869] tot_loss[loss=2.417, over 4528203.38 frames. , ppl: 11.206858614089029], batch size: 70
+2022-12-09 21:11:24,262 INFO [train.py:421] (7/8) Epoch 1, batch 3600, loss[loss=2.361, over 5530.00 frames. , ppl: 10.603251658215251] tot_loss[loss=2.417, over 4624195.54 frames. , ppl: 11.213041545379223], batch size: 70
+2022-12-09 21:13:06,616 INFO [train.py:421] (7/8) Epoch 1, batch 3800, loss[loss=2.348, over 3920.00 frames. , ppl: 10.467960031848559] tot_loss[loss=2.416, over 4720395.27 frames. , ppl: 11.20253475180028], batch size: 70
+2022-12-09 21:14:40,525 INFO [train.py:421] (7/8) Epoch 1, batch 4000, loss[loss=2.665, over 840.00 frames. , ppl: 14.37279196127243] tot_loss[loss=2.417, over 4752482.05 frames. , ppl: 11.215818161959831], batch size: 70
+2022-12-09 21:14:40,526 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 21:14:41,285 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.405, over 211138.00 frames. , ppl: 11.079054234738054
+2022-12-09 21:16:21,688 INFO [train.py:421] (7/8) Epoch 1, batch 4200, loss[loss=2.419, over 2800.00 frames. , ppl: 11.230461328722047] tot_loss[loss=2.417, over 4801605.54 frames. , ppl: 11.216367108097165], batch size: 70
+2022-12-09 21:18:00,239 INFO [train.py:421] (7/8) Epoch 1, batch 4400, loss[loss=2.542, over 1050.00 frames. , ppl: 12.705435002997548] tot_loss[loss=2.417, over 4875267.57 frames. , ppl: 11.214252928565688], batch size: 70
+2022-12-09 21:19:45,667 INFO [train.py:421] (7/8) Epoch 1, batch 4600, loss[loss=2.454, over 2520.00 frames. , ppl: 11.6330192312021] tot_loss[loss=2.416, over 4976016.97 frames. , ppl: 11.201548340582143], batch size: 70
+2022-12-09 21:21:25,276 INFO [train.py:421] (7/8) Epoch 1, batch 4800, loss[loss=2.605, over 1330.00 frames. , ppl: 13.537470151168064] tot_loss[loss=2.416, over 5036665.74 frames. , ppl: 11.198743133687808], batch size: 70
+2022-12-09 21:23:05,013 INFO [train.py:421] (7/8) Epoch 1, batch 5000, loss[loss=2.368, over 6790.00 frames. , ppl: 10.676182746033279] tot_loss[loss=2.415, over 5094223.53 frames. , ppl: 11.193305680425672], batch size: 70
+2022-12-09 21:23:05,014 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 21:23:05,773 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.399, over 211138.00 frames. , ppl: 11.009013517670198
+2022-12-09 21:24:42,080 INFO [train.py:421] (7/8) Epoch 1, batch 5200, loss[loss=2.474, over 1750.00 frames. , ppl: 11.874296618872032] tot_loss[loss=2.416, over 5107597.48 frames. , ppl: 11.196842112399754], batch size: 70
+2022-12-09 21:26:20,268 INFO [train.py:421] (7/8) Epoch 1, batch 5400, loss[loss=2.474, over 2660.00 frames. , ppl: 11.874228438117678] tot_loss[loss=2.415, over 5147124.49 frames. , ppl: 11.189817474357167], batch size: 70
+2022-12-09 21:28:00,128 INFO [train.py:421] (7/8) Epoch 1, batch 5600, loss[loss=2.573, over 1400.00 frames. , ppl: 13.109503200301612] tot_loss[loss=2.415, over 5180854.88 frames. , ppl: 11.185025588499187], batch size: 70
+2022-12-09 21:29:38,417 INFO [train.py:421] (7/8) Epoch 1, batch 5800, loss[loss=2.344, over 2240.00 frames. , ppl: 10.422083850185023] tot_loss[loss=2.415, over 5203892.96 frames. , ppl: 11.189830182194823], batch size: 70
+2022-12-09 21:31:19,572 INFO [train.py:421] (7/8) Epoch 1, batch 6000, loss[loss=2.698, over 910.00 frames. , ppl: 14.852487142884494] tot_loss[loss=2.415, over 5219990.53 frames. , ppl: 11.1853735833348], batch size: 70
+2022-12-09 21:31:19,573 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 21:31:20,318 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.4, over 211138.00 frames. , ppl: 11.020588453227733
+2022-12-09 21:33:01,337 INFO [train.py:421] (7/8) Epoch 1, batch 6200, loss[loss=3.08, over 630.00 frames. , ppl: 21.75524992949009] tot_loss[loss=2.415, over 5269916.21 frames. , ppl: 11.184625375126974], batch size: 70
+2022-12-09 21:34:44,218 INFO [train.py:421] (7/8) Epoch 1, batch 6400, loss[loss=2.344, over 3430.00 frames. , ppl: 10.423604142543185] tot_loss[loss=2.416, over 5250096.28 frames. , ppl: 11.204010625632767], batch size: 70
+2022-12-09 21:36:22,198 INFO [train.py:421] (7/8) Epoch 1, batch 6600, loss[loss=2.535, over 1610.00 frames. , ppl: 12.62017813175733] tot_loss[loss=2.417, over 5238094.89 frames. , ppl: 11.213542034244831], batch size: 70
+2022-12-09 21:38:05,957 INFO [train.py:421] (7/8) Epoch 1, batch 6800, loss[loss=2.314, over 8960.00 frames. , ppl: 10.11548817144183] tot_loss[loss=2.415, over 5309192.41 frames. , ppl: 11.193592821343156], batch size: 70
+2022-12-09 21:39:45,054 INFO [train.py:421] (7/8) Epoch 1, batch 7000, loss[loss=2.746, over 700.00 frames. , ppl: 15.579150113548854] tot_loss[loss=2.415, over 5331449.54 frames. , ppl: 11.186176770494912], batch size: 70
+2022-12-09 21:39:45,055 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 21:39:45,806 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.398, over 211138.00 frames. , ppl: 11.000016301250483
+2022-12-09 21:41:28,147 INFO [train.py:421] (7/8) Epoch 1, batch 7200, loss[loss=2.34, over 3710.00 frames. , ppl: 10.380070903281604] tot_loss[loss=2.415, over 5347982.32 frames. , ppl: 11.190975229513375], batch size: 70
+2022-12-09 21:43:10,159 INFO [train.py:421] (7/8) Epoch 1, batch 7400, loss[loss=2.566, over 1120.00 frames. , ppl: 13.012368290876019] tot_loss[loss=2.415, over 5387145.64 frames. , ppl: 11.189531292262439], batch size: 70
+2022-12-09 21:44:48,898 INFO [train.py:421] (7/8) Epoch 1, batch 7600, loss[loss=2.309, over 7490.00 frames. , ppl: 10.060493063373634] tot_loss[loss=2.414, over 5421063.07 frames. , ppl: 11.176264603633507], batch size: 70
+2022-12-09 21:46:32,005 INFO [train.py:421] (7/8) Epoch 1, batch 7800, loss[loss=2.311, over 7070.00 frames. , ppl: 10.087050081816843] tot_loss[loss=2.413, over 5430539.74 frames. , ppl: 11.165395089900713], batch size: 70
+2022-12-09 21:48:11,093 INFO [train.py:421] (7/8) Epoch 1, batch 8000, loss[loss=2.443, over 3570.00 frames. , ppl: 11.511761164210911] tot_loss[loss=2.413, over 5433792.28 frames. , ppl: 11.166306777951398], batch size: 70
+2022-12-09 21:48:11,094 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 21:48:11,857 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.397, over 211138.00 frames. , ppl: 10.99293966703717
+2022-12-09 21:49:52,603 INFO [train.py:421] (7/8) Epoch 1, batch 8200, loss[loss=2.366, over 2240.00 frames. , ppl: 10.650584303331767] tot_loss[loss=2.413, over 5443139.18 frames. , ppl: 11.168289303994209], batch size: 70
+2022-12-09 21:51:31,078 INFO [train.py:421] (7/8) Epoch 1, batch 8400, loss[loss=2.575, over 3010.00 frames. , ppl: 13.134227276906486] tot_loss[loss=2.415, over 5389099.70 frames. , ppl: 11.193855780072258], batch size: 70
+2022-12-09 21:53:08,555 INFO [train.py:421] (7/8) Epoch 1, batch 8600, loss[loss=2.464, over 2310.00 frames. , ppl: 11.754451553810433] tot_loss[loss=2.416, over 5381303.44 frames. , ppl: 11.199721497445442], batch size: 70
+2022-12-09 21:54:48,828 INFO [train.py:421] (7/8) Epoch 1, batch 8800, loss[loss=2.475, over 1610.00 frames. , ppl: 11.878356342332728] tot_loss[loss=2.415, over 5399636.90 frames. , ppl: 11.18789008299388], batch size: 70
+2022-12-09 21:56:32,531 INFO [train.py:421] (7/8) Epoch 1, batch 9000, loss[loss=2.466, over 3430.00 frames. , ppl: 11.772257663162026] tot_loss[loss=2.414, over 5431208.16 frames. , ppl: 11.175543775212429], batch size: 70
+2022-12-09 21:56:32,531 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 21:56:33,273 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.396, over 211138.00 frames. , ppl: 10.981821240677286
+2022-12-09 21:58:14,745 INFO [train.py:421] (7/8) Epoch 1, batch 9200, loss[loss=2.432, over 2590.00 frames. , ppl: 11.38045270102322] tot_loss[loss=2.414, over 5430084.90 frames. , ppl: 11.175201278132718], batch size: 70
+2022-12-09 21:59:56,481 INFO [train.py:421] (7/8) Epoch 1, batch 9400, loss[loss=2.364, over 3150.00 frames. , ppl: 10.634959818224491] tot_loss[loss=2.414, over 5409646.47 frames. , ppl: 11.17778497103416], batch size: 70
+2022-12-09 22:01:34,866 INFO [train.py:421] (7/8) Epoch 1, batch 9600, loss[loss=2.499, over 2170.00 frames. , ppl: 12.173171842348616] tot_loss[loss=2.414, over 5414443.69 frames. , ppl: 11.177699114383923], batch size: 70
+2022-12-09 22:03:13,427 INFO [train.py:421] (7/8) Epoch 1, batch 9800, loss[loss=2.415, over 3920.00 frames. , ppl: 11.190767816067885] tot_loss[loss=2.414, over 5401071.13 frames. , ppl: 11.177077875782134], batch size: 70
+2022-12-09 22:04:51,394 INFO [train.py:421] (7/8) Epoch 1, batch 10000, loss[loss=2.59, over 1540.00 frames. , ppl: 13.326907247591395] tot_loss[loss=2.414, over 5413135.96 frames. , ppl: 11.180489718594279], batch size: 70
+2022-12-09 22:04:51,394 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 22:04:52,141 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.395, over 211138.00 frames. , ppl: 10.972836503018678
+2022-12-09 22:06:33,532 INFO [train.py:421] (7/8) Epoch 1, batch 10200, loss[loss=2.474, over 2590.00 frames. , ppl: 11.87348465850562] tot_loss[loss=2.413, over 5461007.25 frames. , ppl: 11.170325504171505], batch size: 70
+2022-12-09 22:08:13,458 INFO [train.py:421] (7/8) Epoch 1, batch 10400, loss[loss=2.499, over 3360.00 frames. , ppl: 12.173655880653754] tot_loss[loss=2.414, over 5419942.70 frames. , ppl: 11.181679980037769], batch size: 70
+2022-12-09 22:09:54,329 INFO [train.py:421] (7/8) Epoch 1, batch 10600, loss[loss=2.42, over 3010.00 frames. , ppl: 11.240886279075344] tot_loss[loss=2.414, over 5443819.19 frames. , ppl: 11.180733325430015], batch size: 70
+2022-12-09 22:11:32,887 INFO [train.py:421] (7/8) Epoch 1, batch 10800, loss[loss=2.32, over 8260.00 frames. , ppl: 10.176443323834883] tot_loss[loss=2.415, over 5446582.13 frames. , ppl: 11.184245772481397], batch size: 70
+2022-12-09 22:13:12,636 INFO [train.py:421] (7/8) Epoch 1, batch 11000, loss[loss=2.691, over 910.00 frames. , ppl: 14.75225651446895] tot_loss[loss=2.414, over 5460381.31 frames. , ppl: 11.177426822750501], batch size: 70
+2022-12-09 22:13:12,636 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 22:13:13,393 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.394, over 211138.00 frames. , ppl: 10.959451037049323
+2022-12-09 22:14:51,720 INFO [train.py:421] (7/8) Epoch 1, batch 11200, loss[loss=2.417, over 4620.00 frames. , ppl: 11.208269681515254] tot_loss[loss=2.413, over 5497614.23 frames. , ppl: 11.162586347808197], batch size: 70
+2022-12-09 22:16:32,960 INFO [train.py:421] (7/8) Epoch 1, batch 11400, loss[loss=2.531, over 1750.00 frames. , ppl: 12.566963529845054] tot_loss[loss=2.412, over 5481466.71 frames. , ppl: 11.156713275010175], batch size: 70
+2022-12-09 22:18:09,022 INFO [train.py:421] (7/8) Epoch 1, batch 11600, loss[loss=2.428, over 2940.00 frames. , ppl: 11.337150343092055] tot_loss[loss=2.412, over 5468597.15 frames. , ppl: 11.157988989856413], batch size: 70
+2022-12-09 22:19:53,238 INFO [train.py:421] (7/8) Epoch 1, batch 11800, loss[loss=2.393, over 2940.00 frames. , ppl: 10.946301473692065] tot_loss[loss=2.411, over 5537195.07 frames. , ppl: 11.148983275420532], batch size: 70
+2022-12-09 22:21:30,853 INFO [train.py:421] (7/8) Epoch 1, batch 12000, loss[loss=2.402, over 3710.00 frames. , ppl: 11.040192694914106] tot_loss[loss=2.412, over 5503236.72 frames. , ppl: 11.161784911835571], batch size: 70
+2022-12-09 22:21:30,853 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 22:21:31,611 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.393, over 211138.00 frames. , ppl: 10.943533776107909
+2022-12-09 22:23:19,196 INFO [train.py:421] (7/8) Epoch 1, batch 12200, loss[loss=2.464, over 1190.00 frames. , ppl: 11.751656174244463] tot_loss[loss=2.411, over 5539154.42 frames. , ppl: 11.149332392920973], batch size: 70
+2022-12-09 22:24:55,378 INFO [train.py:421] (7/8) Epoch 1, batch 12400, loss[loss=2.299, over 3710.00 frames. , ppl: 9.961425690793497] tot_loss[loss=2.411, over 5500637.24 frames. , ppl: 11.150111747036844], batch size: 70
+2022-12-09 22:26:36,505 INFO [train.py:421] (7/8) Epoch 1, batch 12600, loss[loss=2.372, over 7490.00 frames. , ppl: 10.71687624322506] tot_loss[loss=2.41, over 5530766.66 frames. , ppl: 11.134792149771076], batch size: 70
+2022-12-09 22:28:14,893 INFO [train.py:421] (7/8) Epoch 1, batch 12800, loss[loss=2.382, over 2380.00 frames. , ppl: 10.822169057182577] tot_loss[loss=2.41, over 5515420.33 frames. , ppl: 11.132581198551405], batch size: 70
+2022-12-09 22:29:53,722 INFO [train.py:421] (7/8) Epoch 1, batch 13000, loss[loss=2.538, over 1330.00 frames. , ppl: 12.657324926476475] tot_loss[loss=2.409, over 5551264.03 frames. , ppl: 11.11895014755753], batch size: 70
+2022-12-09 22:29:53,723 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 22:29:54,481 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.391, over 211138.00 frames. , ppl: 10.927798136667734
+2022-12-09 22:31:36,555 INFO [train.py:421] (7/8) Epoch 1, batch 13200, loss[loss=2.363, over 3920.00 frames. , ppl: 10.61931894629737] tot_loss[loss=2.409, over 5554205.43 frames. , ppl: 11.127905120370928], batch size: 70
+2022-12-09 22:33:15,727 INFO [train.py:421] (7/8) Epoch 1, batch 13400, loss[loss=2.412, over 2730.00 frames. , ppl: 11.150776412522692] tot_loss[loss=2.41, over 5504528.12 frames. , ppl: 11.135861562855053], batch size: 70
+2022-12-09 22:34:54,070 INFO [train.py:421] (7/8) Epoch 1, batch 13600, loss[loss=2.319, over 9030.00 frames. , ppl: 10.167175239183596] tot_loss[loss=2.409, over 5533492.87 frames. , ppl: 11.12590911372214], batch size: 70
+2022-12-09 22:36:30,649 INFO [train.py:421] (7/8) Epoch 1, batch 13800, loss[loss=2.393, over 1820.00 frames. , ppl: 10.94935443479509] tot_loss[loss=2.408, over 5534815.60 frames. , ppl: 11.11372722076997], batch size: 70
+2022-12-09 22:38:12,925 INFO [train.py:421] (7/8) Epoch 1, batch 14000, loss[loss=2.404, over 3010.00 frames. , ppl: 11.062839576370079] tot_loss[loss=2.407, over 5547578.76 frames. , ppl: 11.105753219053636], batch size: 70
+2022-12-09 22:38:12,926 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 22:38:13,682 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.39, over 211138.00 frames. , ppl: 10.914509612851669
+2022-12-09 22:39:52,639 INFO [train.py:421] (7/8) Epoch 1, batch 14200, loss[loss=2.509, over 2520.00 frames. , ppl: 12.29088636631977] tot_loss[loss=2.408, over 5538400.23 frames. , ppl: 11.11233330742123], batch size: 70
+2022-12-09 22:41:35,427 INFO [train.py:421] (7/8) Epoch 1, batch 14400, loss[loss=2.319, over 3640.00 frames. , ppl: 10.161059681705876] tot_loss[loss=2.407, over 5574401.30 frames. , ppl: 11.098636564521726], batch size: 70
+2022-12-09 22:43:15,961 INFO [train.py:421] (7/8) Epoch 1, batch 14600, loss[loss=2.325, over 5670.00 frames. , ppl: 10.224549044954612] tot_loss[loss=2.406, over 5588380.52 frames. , ppl: 11.093918872150422], batch size: 70
+2022-12-09 22:44:53,639 INFO [train.py:421] (7/8) Epoch 1, batch 14800, loss[loss=2.458, over 2100.00 frames. , ppl: 11.676916360261632] tot_loss[loss=2.407, over 5551187.24 frames. , ppl: 11.09898265992301], batch size: 70
+2022-12-09 22:46:32,345 INFO [train.py:421] (7/8) Epoch 1, batch 15000, loss[loss=2.317, over 4900.00 frames. , ppl: 10.140806002820653] tot_loss[loss=2.407, over 5542152.88 frames. , ppl: 11.103980627886802], batch size: 70
+2022-12-09 22:46:32,346 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 22:46:33,092 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.389, over 211138.00 frames. , ppl: 10.905875331584172
+2022-12-09 22:48:15,324 INFO [train.py:421] (7/8) Epoch 1, batch 15200, loss[loss=2.506, over 3290.00 frames. , ppl: 12.254943741244233] tot_loss[loss=2.407, over 5542727.84 frames. , ppl: 11.099473951023922], batch size: 70
+2022-12-09 22:49:57,179 INFO [train.py:421] (7/8) Epoch 1, batch 15400, loss[loss=2.517, over 1470.00 frames. , ppl: 12.395164225743072] tot_loss[loss=2.408, over 5502977.73 frames. , ppl: 11.10647913744729], batch size: 70
+2022-12-09 22:51:38,846 INFO [train.py:421] (7/8) Epoch 1, batch 15600, loss[loss=2.59, over 1050.00 frames. , ppl: 13.325420797555159] tot_loss[loss=2.407, over 5530610.78 frames. , ppl: 11.0992773427574], batch size: 70
+2022-12-09 22:53:18,734 INFO [train.py:421] (7/8) Epoch 1, batch 15800, loss[loss=2.346, over 4550.00 frames. , ppl: 10.447331459828685] tot_loss[loss=2.406, over 5548791.84 frames. , ppl: 11.088355263847378], batch size: 70
+2022-12-09 22:55:01,064 INFO [train.py:421] (7/8) Epoch 1, batch 16000, loss[loss=2.784, over 770.00 frames. , ppl: 16.186678114816583] tot_loss[loss=2.407, over 5526118.30 frames. , ppl: 11.097368466698901], batch size: 70
+2022-12-09 22:55:01,064 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 22:55:01,823 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.387, over 211138.00 frames. , ppl: 10.886231072245774
+2022-12-09 22:56:40,412 INFO [train.py:421] (7/8) Epoch 1, batch 16200, loss[loss=2.413, over 3640.00 frames. , ppl: 11.172286805197876] tot_loss[loss=2.407, over 5525798.36 frames. , ppl: 11.098191767271247], batch size: 70
+2022-12-09 22:58:20,171 INFO [train.py:421] (7/8) Epoch 1, batch 16400, loss[loss=2.527, over 2100.00 frames. , ppl: 12.516723901262864] tot_loss[loss=2.407, over 5499825.34 frames. , ppl: 11.103469531137476], batch size: 70
+2022-12-09 23:00:00,604 INFO [train.py:421] (7/8) Epoch 1, batch 16600, loss[loss=2.652, over 980.00 frames. , ppl: 14.1833072684177] tot_loss[loss=2.407, over 5485398.89 frames. , ppl: 11.104618807000772], batch size: 70
+2022-12-09 23:01:39,180 INFO [train.py:421] (7/8) Epoch 1, batch 16800, loss[loss=2.441, over 3150.00 frames. , ppl: 11.487768516803682] tot_loss[loss=2.409, over 5428389.04 frames. , ppl: 11.11962472011758], batch size: 70
+2022-12-09 23:03:20,353 INFO [train.py:421] (7/8) Epoch 1, batch 17000, loss[loss=2.368, over 1680.00 frames. , ppl: 10.678565064640475] tot_loss[loss=2.408, over 5472927.07 frames. , ppl: 11.10959863411808], batch size: 70
+2022-12-09 23:03:20,353 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 23:03:21,099 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.388, over 211138.00 frames. , ppl: 10.88762972140702
+2022-12-09 23:04:58,074 INFO [train.py:421] (7/8) Epoch 1, batch 17200, loss[loss=2.559, over 1400.00 frames. , ppl: 12.926066793989726] tot_loss[loss=2.407, over 5469550.96 frames. , ppl: 11.100148303741596], batch size: 70
+2022-12-09 23:06:36,552 INFO [train.py:421] (7/8) Epoch 1, batch 17400, loss[loss=2.747, over 700.00 frames. , ppl: 15.590855715599204] tot_loss[loss=2.407, over 5456437.24 frames. , ppl: 11.103249532739204], batch size: 70
+2022-12-09 23:08:16,407 INFO [train.py:421] (7/8) Epoch 1, batch 17600, loss[loss=2.491, over 1470.00 frames. , ppl: 12.07073314607289] tot_loss[loss=2.407, over 5467064.64 frames. , ppl: 11.099512168040366], batch size: 70
+2022-12-09 23:09:57,152 INFO [train.py:421] (7/8) Epoch 1, batch 17800, loss[loss=2.342, over 5250.00 frames. , ppl: 10.404003273265127] tot_loss[loss=2.406, over 5467127.38 frames. , ppl: 11.090558033691034], batch size: 70
+2022-12-09 23:11:36,560 INFO [train.py:421] (7/8) Epoch 1, batch 18000, loss[loss=2.507, over 3430.00 frames. , ppl: 12.271461792469614] tot_loss[loss=2.408, over 5431430.74 frames. , ppl: 11.108423684834989], batch size: 70
+2022-12-09 23:11:36,560 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 23:11:37,293 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.386, over 211138.00 frames. , ppl: 10.869570686577362
+2022-12-09 23:13:24,087 INFO [train.py:421] (7/8) Epoch 1, batch 18200, loss[loss=2.388, over 3990.00 frames. , ppl: 10.887789766775152] tot_loss[loss=2.407, over 5474732.03 frames. , ppl: 11.096554687004293], batch size: 70
+2022-12-09 23:15:06,574 INFO [train.py:421] (7/8) Epoch 1, batch 18400, loss[loss=2.495, over 1330.00 frames. , ppl: 12.117936726110692] tot_loss[loss=2.406, over 5472143.25 frames. , ppl: 11.08934970962634], batch size: 70
+2022-12-09 23:16:40,258 INFO [train.py:421] (7/8) Epoch 1, batch 18600, loss[loss=2.463, over 2170.00 frames. , ppl: 11.743143627963711] tot_loss[loss=2.405, over 5472757.53 frames. , ppl: 11.079768731366848], batch size: 70
+2022-12-09 23:18:19,349 INFO [train.py:421] (7/8) Epoch 1, batch 18800, loss[loss=2.663, over 910.00 frames. , ppl: 14.337897199497732] tot_loss[loss=2.407, over 5451429.56 frames. , ppl: 11.095693079777147], batch size: 70
+2022-12-09 23:19:58,914 INFO [train.py:421] (7/8) Epoch 1, batch 19000, loss[loss=2.442, over 1470.00 frames. , ppl: 11.500109666427985] tot_loss[loss=2.407, over 5435435.61 frames. , ppl: 11.105000518552448], batch size: 70
+2022-12-09 23:19:58,914 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 23:19:59,658 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.385, over 211138.00 frames. , ppl: 10.86154424255148
+2022-12-09 23:21:39,329 INFO [train.py:421] (7/8) Epoch 1, batch 19200, loss[loss=2.358, over 5530.00 frames. , ppl: 10.571211710821096] tot_loss[loss=2.407, over 5429076.81 frames. , ppl: 11.096656445164637], batch size: 70
+2022-12-09 23:23:22,547 INFO [train.py:421] (7/8) Epoch 1, batch 19400, loss[loss=3.283, over 490.00 frames. , ppl: 26.662389679127934] tot_loss[loss=2.406, over 5480950.00 frames. , ppl: 11.09182742305595], batch size: 70
+2022-12-09 23:25:00,329 INFO [train.py:421] (7/8) Epoch 1, batch 19600, loss[loss=2.667, over 770.00 frames. , ppl: 14.398783803529605] tot_loss[loss=2.406, over 5470109.63 frames. , ppl: 11.08726901499826], batch size: 70
+2022-12-09 23:26:38,754 INFO [train.py:421] (7/8) Epoch 1, batch 19800, loss[loss=2.421, over 1470.00 frames. , ppl: 11.259693916032651] tot_loss[loss=2.406, over 5455787.92 frames. , ppl: 11.094981151610357], batch size: 70
+2022-12-09 23:28:20,838 INFO [train.py:421] (7/8) Epoch 1, batch 20000, loss[loss=2.603, over 1190.00 frames. , ppl: 13.503367852248333] tot_loss[loss=2.405, over 5489562.47 frames. , ppl: 11.078015618776787], batch size: 70
+2022-12-09 23:28:20,838 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 23:28:21,595 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.383, over 211138.00 frames. , ppl: 10.840206792981473
+2022-12-09 23:30:07,793 INFO [train.py:421] (7/8) Epoch 1, batch 20200, loss[loss=2.472, over 1050.00 frames. , ppl: 11.84510293253795] tot_loss[loss=2.405, over 5470769.57 frames. , ppl: 11.072990103517544], batch size: 70
+2022-12-09 23:31:46,079 INFO [train.py:421] (7/8) Epoch 1, batch 20400, loss[loss=2.456, over 2450.00 frames. , ppl: 11.659662134932434] tot_loss[loss=2.404, over 5490492.39 frames. , ppl: 11.072146176920933], batch size: 70
+2022-12-09 23:33:26,966 INFO [train.py:421] (7/8) Epoch 1, batch 20600, loss[loss=2.346, over 7490.00 frames. , ppl: 10.440867123888763] tot_loss[loss=2.403, over 5508347.50 frames. , ppl: 11.059424009090591], batch size: 70
+2022-12-09 23:35:04,517 INFO [train.py:421] (7/8) Epoch 1, batch 20800, loss[loss=2.522, over 1330.00 frames. , ppl: 12.449474367597158] tot_loss[loss=2.403, over 5505897.42 frames. , ppl: 11.057118156309619], batch size: 70
+2022-12-09 23:36:45,000 INFO [train.py:421] (7/8) Epoch 1, batch 21000, loss[loss=2.315, over 3920.00 frames. , ppl: 10.123663838892332] tot_loss[loss=2.402, over 5510474.66 frames. , ppl: 11.04863694065187], batch size: 70
+2022-12-09 23:36:45,000 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 23:36:45,739 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.381, over 211138.00 frames. , ppl: 10.817335716309938
+2022-12-09 23:38:28,734 INFO [train.py:421] (7/8) Epoch 1, batch 21200, loss[loss=2.335, over 11480.00 frames. , ppl: 10.324506008042329] tot_loss[loss=2.403, over 5475386.50 frames. , ppl: 11.059977803148175], batch size: 70
+2022-12-09 23:40:05,783 INFO [train.py:421] (7/8) Epoch 1, batch 21400, loss[loss=2.303, over 3080.00 frames. , ppl: 10.006720320690361] tot_loss[loss=2.402, over 5501607.20 frames. , ppl: 11.049508233213713], batch size: 70
+2022-12-09 23:41:45,964 INFO [train.py:421] (7/8) Epoch 1, batch 21600, loss[loss=2.559, over 1050.00 frames. , ppl: 12.92332606596239] tot_loss[loss=2.402, over 5519986.77 frames. , ppl: 11.043107807698442], batch size: 70
+2022-12-09 23:43:25,713 INFO [train.py:421] (7/8) Epoch 1, batch 21800, loss[loss=2.322, over 4900.00 frames. , ppl: 10.200138996014807] tot_loss[loss=2.403, over 5487180.68 frames. , ppl: 11.052140602004659], batch size: 70
+2022-12-09 23:45:06,450 INFO [train.py:421] (7/8) Epoch 1, batch 22000, loss[loss=2.342, over 3640.00 frames. , ppl: 10.40226785437076] tot_loss[loss=2.402, over 5523319.04 frames. , ppl: 11.04343872332988], batch size: 70
+2022-12-09 23:45:06,451 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 23:45:07,207 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.382, over 211138.00 frames. , ppl: 10.821137268370757
+2022-12-09 23:46:46,114 INFO [train.py:421] (7/8) Epoch 1, batch 22200, loss[loss=2.562, over 1190.00 frames. , ppl: 12.956411083985445] tot_loss[loss=2.402, over 5504358.15 frames. , ppl: 11.048460426832731], batch size: 70
+2022-12-09 23:48:27,640 INFO [train.py:421] (7/8) Epoch 1, batch 22400, loss[loss=2.325, over 4970.00 frames. , ppl: 10.226392737736502] tot_loss[loss=2.402, over 5477063.80 frames. , ppl: 11.048671775121331], batch size: 70
+2022-12-09 23:50:05,039 INFO [train.py:421] (7/8) Epoch 1, batch 22600, loss[loss=2.396, over 3500.00 frames. , ppl: 10.98011224253402] tot_loss[loss=2.401, over 5538783.43 frames. , ppl: 11.030773999104744], batch size: 70
+2022-12-09 23:51:43,349 INFO [train.py:421] (7/8) Epoch 1, batch 22800, loss[loss=2.271, over 8540.00 frames. , ppl: 9.685480240702713] tot_loss[loss=2.4, over 5598237.56 frames. , ppl: 11.022761136087649], batch size: 70
+2022-12-09 23:53:27,618 INFO [train.py:421] (7/8) Epoch 1, batch 23000, loss[loss=2.332, over 2520.00 frames. , ppl: 10.29469394708245] tot_loss[loss=2.399, over 5610726.30 frames. , ppl: 11.011024445288115], batch size: 70
+2022-12-09 23:53:27,618 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-09 23:53:28,375 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.38, over 211138.00 frames. , ppl: 10.800644888892075
+2022-12-09 23:55:09,817 INFO [train.py:421] (7/8) Epoch 1, batch 23200, loss[loss=2.744, over 840.00 frames. , ppl: 15.550005442936827] tot_loss[loss=2.399, over 5636275.04 frames. , ppl: 11.007657458932815], batch size: 70
+2022-12-09 23:56:52,353 INFO [train.py:421] (7/8) Epoch 1, batch 23400, loss[loss=2.4, over 3430.00 frames. , ppl: 11.021748486713852] tot_loss[loss=2.398, over 5675906.18 frames. , ppl: 10.999854787658176], batch size: 70
+2022-12-09 23:58:28,689 INFO [train.py:421] (7/8) Epoch 1, batch 23600, loss[loss=2.342, over 5740.00 frames. , ppl: 10.397973379538858] tot_loss[loss=2.398, over 5666263.97 frames. , ppl: 10.998746779791366], batch size: 70
+2022-12-10 00:00:06,982 INFO [train.py:421] (7/8) Epoch 1, batch 23800, loss[loss=2.397, over 1960.00 frames. , ppl: 10.993336227107713] tot_loss[loss=2.399, over 5609590.07 frames. , ppl: 11.009251358925237], batch size: 70
+2022-12-10 00:01:47,277 INFO [train.py:421] (7/8) Epoch 1, batch 24000, loss[loss=2.677, over 910.00 frames. , ppl: 14.54234491001007] tot_loss[loss=2.397, over 5644947.06 frames. , ppl: 10.993901013187749], batch size: 70
+2022-12-10 00:01:47,277 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 00:01:48,035 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.379, over 211138.00 frames. , ppl: 10.78979920368168
+2022-12-10 00:03:26,227 INFO [train.py:421] (7/8) Epoch 1, batch 24200, loss[loss=2.487, over 2170.00 frames. , ppl: 12.027611994935505] tot_loss[loss=2.397, over 5637386.37 frames. , ppl: 10.9908205138753], batch size: 70
+2022-12-10 00:05:05,803 INFO [train.py:421] (7/8) Epoch 1, batch 24400, loss[loss=2.334, over 3080.00 frames. , ppl: 10.315696581013224] tot_loss[loss=2.397, over 5605866.96 frames. , ppl: 10.993913828160709], batch size: 70
+2022-12-10 00:06:43,341 INFO [train.py:421] (7/8) Epoch 1, batch 24600, loss[loss=2.492, over 1120.00 frames. , ppl: 12.083226331928469] tot_loss[loss=2.395, over 5680302.50 frames. , ppl: 10.966604372651522], batch size: 70
+2022-12-10 00:08:25,288 INFO [train.py:421] (7/8) Epoch 1, batch 24800, loss[loss=2.398, over 2870.00 frames. , ppl: 11.006136513226647] tot_loss[loss=2.396, over 5642365.05 frames. , ppl: 10.980648402595639], batch size: 70
+2022-12-10 00:10:06,626 INFO [train.py:421] (7/8) Epoch 1, batch 25000, loss[loss=2.588, over 980.00 frames. , ppl: 13.298015927858211] tot_loss[loss=2.396, over 5585115.71 frames. , ppl: 10.978998509015616], batch size: 70
+2022-12-10 00:10:06,627 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 00:10:07,386 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.38, over 211138.00 frames. , ppl: 10.800197296869092
+2022-12-10 00:11:43,293 INFO [train.py:421] (7/8) Epoch 1, batch 25200, loss[loss=2.34, over 3080.00 frames. , ppl: 10.382254355096054] tot_loss[loss=2.395, over 5604493.94 frames. , ppl: 10.970885077754483], batch size: 70
+2022-12-10 00:13:24,087 INFO [train.py:421] (7/8) Epoch 1, batch 25400, loss[loss=2.323, over 5250.00 frames. , ppl: 10.20598707642868] tot_loss[loss=2.396, over 5596694.20 frames. , ppl: 10.976652453416817], batch size: 70
+2022-12-10 00:15:07,555 INFO [train.py:421] (7/8) Epoch 1, batch 25600, loss[loss=2.46, over 1470.00 frames. , ppl: 11.710514172206338] tot_loss[loss=2.396, over 5587238.80 frames. , ppl: 10.976865877344391], batch size: 70
+2022-12-10 00:16:48,182 INFO [train.py:421] (7/8) Epoch 1, batch 25800, loss[loss=2.638, over 1190.00 frames. , ppl: 13.983930993935834] tot_loss[loss=2.396, over 5607304.72 frames. , ppl: 10.976994016830114], batch size: 70
+2022-12-10 00:18:27,901 INFO [train.py:421] (7/8) Epoch 1, batch 26000, loss[loss=2.219, over 2170.00 frames. , ppl: 9.202336739945935] tot_loss[loss=2.397, over 5557979.81 frames. , ppl: 10.991069291225426], batch size: 70
+2022-12-10 00:18:27,902 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 00:18:28,648 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.379, over 211138.00 frames. , ppl: 10.799350119895008
+2022-12-10 00:20:08,713 INFO [train.py:421] (7/8) Epoch 1, batch 26200, loss[loss=2.315, over 3990.00 frames. , ppl: 10.120219585968071] tot_loss[loss=2.397, over 5512913.99 frames. , ppl: 10.9948012434011], batch size: 70
+2022-12-10 00:21:44,687 INFO [train.py:421] (7/8) Epoch 1, batch 26400, loss[loss=2.474, over 1400.00 frames. , ppl: 11.872548237545258] tot_loss[loss=2.397, over 5500873.50 frames. , ppl: 10.990306138509048], batch size: 70
+2022-12-10 00:23:22,416 INFO [train.py:421] (7/8) Epoch 1, batch 26600, loss[loss=2.451, over 1960.00 frames. , ppl: 11.602579330220209] tot_loss[loss=2.395, over 5588675.66 frames. , ppl: 10.966022044727538], batch size: 70
+2022-12-10 00:25:04,487 INFO [train.py:421] (7/8) Epoch 1, batch 26800, loss[loss=2.482, over 1890.00 frames. , ppl: 11.96582298253073] tot_loss[loss=2.394, over 5638163.43 frames. , ppl: 10.955008327986056], batch size: 70
+2022-12-10 00:26:48,139 INFO [train.py:421] (7/8) Epoch 1, batch 27000, loss[loss=2.383, over 4130.00 frames. , ppl: 10.838142828712195] tot_loss[loss=2.394, over 5614669.10 frames. , ppl: 10.962518384906884], batch size: 70
+2022-12-10 00:26:48,139 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 00:26:48,899 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.379, over 211138.00 frames. , ppl: 10.791004984020308
+2022-12-10 00:28:29,579 INFO [train.py:421] (7/8) Epoch 1, batch 27200, loss[loss=2.43, over 1820.00 frames. , ppl: 11.354851650064079] tot_loss[loss=2.394, over 5624773.57 frames. , ppl: 10.95991926968837], batch size: 70
+2022-12-10 00:30:09,129 INFO [train.py:421] (7/8) Epoch 1, batch 27400, loss[loss=2.422, over 3850.00 frames. , ppl: 11.273171280180778] tot_loss[loss=2.396, over 5559300.01 frames. , ppl: 10.978151196791272], batch size: 70
+2022-12-10 00:31:48,115 INFO [train.py:421] (7/8) Epoch 1, batch 27600, loss[loss=2.455, over 1260.00 frames. , ppl: 11.651061033181223] tot_loss[loss=2.395, over 5574328.04 frames. , ppl: 10.969873435830184], batch size: 70
+2022-12-10 00:33:29,297 INFO [train.py:421] (7/8) Epoch 1, batch 27800, loss[loss=2.75, over 630.00 frames. , ppl: 15.64812796893116] tot_loss[loss=2.395, over 5562107.91 frames. , ppl: 10.972801182466153], batch size: 70
+2022-12-10 00:35:07,718 INFO [train.py:421] (7/8) Epoch 1, batch 28000, loss[loss=2.647, over 770.00 frames. , ppl: 14.111240876503242] tot_loss[loss=2.395, over 5558413.97 frames. , ppl: 10.968684100529652], batch size: 70
+2022-12-10 00:35:07,718 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 00:35:08,463 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.377, over 211138.00 frames. , ppl: 10.77500384045564
+2022-12-10 00:36:52,791 INFO [train.py:421] (7/8) Epoch 1, batch 28200, loss[loss=2.577, over 980.00 frames. , ppl: 13.162831500163527] tot_loss[loss=2.395, over 5561873.51 frames. , ppl: 10.970338202953062], batch size: 70
+2022-12-10 00:38:30,675 INFO [train.py:421] (7/8) Epoch 1, batch 28400, loss[loss=2.535, over 1610.00 frames. , ppl: 12.620476676478276] tot_loss[loss=2.395, over 5541359.20 frames. , ppl: 10.96905929406397], batch size: 70
+2022-12-10 00:40:09,208 INFO [train.py:421] (7/8) Epoch 1, batch 28600, loss[loss=2.357, over 8540.00 frames. , ppl: 10.563094764168826] tot_loss[loss=2.395, over 5564046.60 frames. , ppl: 10.96381819707056], batch size: 70
+2022-12-10 00:41:48,511 INFO [train.py:421] (7/8) Epoch 1, batch 28800, loss[loss=2.788, over 630.00 frames. , ppl: 16.240374381645477] tot_loss[loss=2.395, over 5539325.03 frames. , ppl: 10.966989389376002], batch size: 70
+2022-12-10 00:43:30,619 INFO [train.py:421] (7/8) Epoch 1, batch 29000, loss[loss=4.15, over 350.00 frames. , ppl: 63.41798452724486] tot_loss[loss=2.394, over 5543184.81 frames. , ppl: 10.961619462035282], batch size: 70
+2022-12-10 00:43:30,619 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 00:43:31,364 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.375, over 211138.00 frames. , ppl: 10.749719593753966
+2022-12-10 00:45:08,474 INFO [train.py:421] (7/8) Epoch 1, batch 29200, loss[loss=2.523, over 1750.00 frames. , ppl: 12.460256323054493] tot_loss[loss=2.394, over 5526670.11 frames. , ppl: 10.960756620228057], batch size: 70
+2022-12-10 00:46:48,134 INFO [train.py:421] (7/8) Epoch 1, batch 29400, loss[loss=2.3, over 4970.00 frames. , ppl: 9.973990392191036] tot_loss[loss=2.394, over 5514385.57 frames. , ppl: 10.95322416261337], batch size: 70
+2022-12-10 00:48:31,857 INFO [train.py:421] (7/8) Epoch 1, batch 29600, loss[loss=2.974, over 560.00 frames. , ppl: 19.57009256147981] tot_loss[loss=2.392, over 5592092.04 frames. , ppl: 10.940372192754067], batch size: 70
+2022-12-10 00:50:13,023 INFO [train.py:421] (7/8) Epoch 1, batch 29800, loss[loss=4.154, over 350.00 frames. , ppl: 63.67125844359641] tot_loss[loss=2.391, over 5616349.19 frames. , ppl: 10.928798611220767], batch size: 70
+2022-12-10 00:51:49,955 INFO [train.py:421] (7/8) Epoch 1, batch 30000, loss[loss=2.306, over 4480.00 frames. , ppl: 10.03018994639488] tot_loss[loss=2.391, over 5587329.12 frames. , ppl: 10.925412108216195], batch size: 70
+2022-12-10 00:51:49,956 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 00:51:50,686 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.373, over 211138.00 frames. , ppl: 10.73370182407569
+2022-12-10 00:53:27,765 INFO [train.py:421] (7/8) Epoch 1, batch 30200, loss[loss=2.374, over 6650.00 frames. , ppl: 10.736781815469069] tot_loss[loss=2.392, over 5571593.16 frames. , ppl: 10.936507054999899], batch size: 70
+2022-12-10 00:55:09,232 INFO [train.py:421] (7/8) Epoch 1, batch 30400, loss[loss=2.299, over 8820.00 frames. , ppl: 9.96734663117704] tot_loss[loss=2.393, over 5526772.55 frames. , ppl: 10.950871988244234], batch size: 70
+2022-12-10 00:56:50,148 INFO [train.py:421] (7/8) Epoch 1, batch 30600, loss[loss=2.333, over 4970.00 frames. , ppl: 10.31007711405064] tot_loss[loss=2.392, over 5545106.29 frames. , ppl: 10.94041546109694], batch size: 70
+2022-12-10 00:58:29,427 INFO [train.py:421] (7/8) Epoch 1, batch 30800, loss[loss=2.328, over 3780.00 frames. , ppl: 10.258757356909026] tot_loss[loss=2.392, over 5562061.33 frames. , ppl: 10.930467664216732], batch size: 70
+2022-12-10 01:00:09,322 INFO [train.py:421] (7/8) Epoch 1, batch 31000, loss[loss=2.413, over 2240.00 frames. , ppl: 11.166474164265344] tot_loss[loss=2.392, over 5541890.39 frames. , ppl: 10.935902133344136], batch size: 70
+2022-12-10 01:00:09,323 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 01:00:10,085 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.373, over 211138.00 frames. , ppl: 10.729127435277624
+2022-12-10 01:01:48,640 INFO [train.py:421] (7/8) Epoch 1, batch 31200, loss[loss=2.926, over 630.00 frames. , ppl: 18.645010457945872] tot_loss[loss=2.392, over 5520002.81 frames. , ppl: 10.93727856457868], batch size: 70
+2022-12-10 01:03:31,209 INFO [train.py:421] (7/8) Epoch 1, batch 31400, loss[loss=2.569, over 1400.00 frames. , ppl: 13.055393081952346] tot_loss[loss=2.392, over 5502468.44 frames. , ppl: 10.936919213893468], batch size: 70
+2022-12-10 01:05:10,006 INFO [train.py:421] (7/8) Epoch 1, batch 31600, loss[loss=2.346, over 3150.00 frames. , ppl: 10.440588544513774] tot_loss[loss=2.392, over 5481148.14 frames. , ppl: 10.9337525872972], batch size: 70
+2022-12-10 01:06:49,293 INFO [train.py:421] (7/8) Epoch 1, batch 31800, loss[loss=2.391, over 4410.00 frames. , ppl: 10.921985711447405] tot_loss[loss=2.391, over 5489251.71 frames. , ppl: 10.929152057668178], batch size: 70
+2022-12-10 01:08:31,500 INFO [train.py:421] (7/8) Epoch 1, batch 32000, loss[loss=2.383, over 2520.00 frames. , ppl: 10.834188171892269] tot_loss[loss=2.391, over 5507945.20 frames. , ppl: 10.925292272504166], batch size: 70
+2022-12-10 01:08:31,500 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 01:08:32,284 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.372, over 211138.00 frames. , ppl: 10.718152095318677
+2022-12-10 01:10:13,324 INFO [train.py:421] (7/8) Epoch 1, batch 32200, loss[loss=2.431, over 2870.00 frames. , ppl: 11.372292394724067] tot_loss[loss=2.39, over 5516039.17 frames. , ppl: 10.918542721966615], batch size: 70
+2022-12-10 01:11:53,782 INFO [train.py:421] (7/8) Epoch 1, batch 32400, loss[loss=3.293, over 490.00 frames. , ppl: 26.92904427419182] tot_loss[loss=2.391, over 5510990.23 frames. , ppl: 10.920317917551152], batch size: 70
+2022-12-10 01:13:33,500 INFO [train.py:421] (7/8) Epoch 1, batch 32600, loss[loss=2.364, over 4550.00 frames. , ppl: 10.634434459194845] tot_loss[loss=2.39, over 5508305.70 frames. , ppl: 10.918507830356006], batch size: 70
+2022-12-10 01:15:16,740 INFO [train.py:421] (7/8) Epoch 1, batch 32800, loss[loss=2.406, over 1680.00 frames. , ppl: 11.09010622320716] tot_loss[loss=2.391, over 5530056.60 frames. , ppl: 10.922650763907491], batch size: 70
+2022-12-10 01:16:56,205 INFO [train.py:421] (7/8) Epoch 1, batch 33000, loss[loss=2.42, over 1750.00 frames. , ppl: 11.250723949859085] tot_loss[loss=2.391, over 5514630.15 frames. , ppl: 10.926052116233606], batch size: 70
+2022-12-10 01:16:56,206 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 01:16:56,953 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.371, over 211138.00 frames. , ppl: 10.707864689524108
+2022-12-10 01:18:40,595 INFO [train.py:421] (7/8) Epoch 1, batch 33200, loss[loss=2.63, over 910.00 frames. , ppl: 13.872821532305858] tot_loss[loss=2.391, over 5524881.73 frames. , ppl: 10.923747157344343], batch size: 70
+2022-12-10 01:20:20,452 INFO [train.py:421] (7/8) Epoch 1, batch 33400, loss[loss=2.508, over 1260.00 frames. , ppl: 12.284336573577058] tot_loss[loss=2.389, over 5579567.90 frames. , ppl: 10.90644961898367], batch size: 70
+2022-12-10 01:21:57,291 INFO [train.py:421] (7/8) Epoch 1, batch 33600, loss[loss=2.286, over 4760.00 frames. , ppl: 9.839984081765472] tot_loss[loss=2.39, over 5553579.62 frames. , ppl: 10.912444945460157], batch size: 70
+2022-12-10 01:23:38,629 INFO [train.py:421] (7/8) Epoch 1, batch 33800, loss[loss=2.362, over 4550.00 frames. , ppl: 10.616714529874725] tot_loss[loss=2.39, over 5569614.52 frames. , ppl: 10.908408772429048], batch size: 70
+2022-12-10 01:25:17,021 INFO [train.py:421] (7/8) Epoch 1, batch 34000, loss[loss=2.389, over 2940.00 frames. , ppl: 10.90489358990357] tot_loss[loss=2.391, over 5534793.24 frames. , ppl: 10.920096782251473], batch size: 70
+2022-12-10 01:25:17,022 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 01:25:17,782 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.373, over 211138.00 frames. , ppl: 10.73305843282348
+2022-12-10 01:27:03,120 INFO [train.py:421] (7/8) Epoch 1, batch 34200, loss[loss=2.519, over 1890.00 frames. , ppl: 12.412737108849255] tot_loss[loss=2.39, over 5549848.26 frames. , ppl: 10.914672284534907], batch size: 70
+2022-12-10 01:28:41,224 INFO [train.py:421] (7/8) Epoch 1, batch 34400, loss[loss=2.779, over 1050.00 frames. , ppl: 16.104803894532527] tot_loss[loss=2.39, over 5553048.06 frames. , ppl: 10.915140847051028], batch size: 70
+2022-12-10 01:30:22,448 INFO [train.py:421] (7/8) Epoch 1, batch 34600, loss[loss=2.366, over 5740.00 frames. , ppl: 10.654472179506488] tot_loss[loss=2.39, over 5571813.14 frames. , ppl: 10.909172031531385], batch size: 70
+2022-12-10 01:32:03,741 INFO [train.py:421] (7/8) Epoch 1, batch 34800, loss[loss=2.507, over 910.00 frames. , ppl: 12.27066603046989] tot_loss[loss=2.389, over 5581338.46 frames. , ppl: 10.903470755116656], batch size: 70
+2022-12-10 01:33:43,071 INFO [train.py:421] (7/8) Epoch 1, batch 35000, loss[loss=2.457, over 1750.00 frames. , ppl: 11.666002591193676] tot_loss[loss=2.389, over 5561032.13 frames. , ppl: 10.903576084900811], batch size: 70
+2022-12-10 01:33:43,071 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 01:33:43,828 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.372, over 211138.00 frames. , ppl: 10.721890226540799
+2022-12-10 01:35:22,948 INFO [train.py:421] (7/8) Epoch 1, batch 35200, loss[loss=2.382, over 8190.00 frames. , ppl: 10.826198758308912] tot_loss[loss=2.389, over 5546831.76 frames. , ppl: 10.901994733291765], batch size: 70
+2022-12-10 01:37:03,047 INFO [train.py:421] (7/8) Epoch 1, batch 35400, loss[loss=2.638, over 770.00 frames. , ppl: 13.984311916899015] tot_loss[loss=2.389, over 5530448.87 frames. , ppl: 10.904323035263129], batch size: 70
+2022-12-10 01:38:46,644 INFO [train.py:421] (7/8) Epoch 1, batch 35600, loss[loss=2.916, over 630.00 frames. , ppl: 18.464811051791514] tot_loss[loss=2.389, over 5511758.20 frames. , ppl: 10.9033497354068], batch size: 70
+2022-12-10 01:40:24,031 INFO [train.py:421] (7/8) Epoch 1, batch 35800, loss[loss=2.254, over 4200.00 frames. , ppl: 9.526894211603217] tot_loss[loss=2.388, over 5500036.71 frames. , ppl: 10.895759641682599], batch size: 70
+2022-12-10 01:42:02,449 INFO [train.py:421] (7/8) Epoch 1, batch 36000, loss[loss=2.262, over 6930.00 frames. , ppl: 9.601546781846778] tot_loss[loss=2.389, over 5476042.86 frames. , ppl: 10.89790551566335], batch size: 70
+2022-12-10 01:42:02,450 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 01:42:03,181 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.371, over 211138.00 frames. , ppl: 10.709730213282327
+2022-12-10 01:43:40,133 INFO [train.py:421] (7/8) Epoch 1, batch 36200, loss[loss=2.327, over 4200.00 frames. , ppl: 10.250214601665451] tot_loss[loss=2.389, over 5466350.21 frames. , ppl: 10.899434508336064], batch size: 70
+2022-12-10 01:45:21,084 INFO [train.py:421] (7/8) Epoch 1, batch 36400, loss[loss=2.331, over 6930.00 frames. , ppl: 10.286914198069022] tot_loss[loss=2.39, over 5435625.51 frames. , ppl: 10.90988765003079], batch size: 70
+2022-12-10 01:47:02,481 INFO [train.py:421] (7/8) Epoch 1, batch 36600, loss[loss=2.392, over 2310.00 frames. , ppl: 10.935927685458532] tot_loss[loss=2.388, over 5463255.39 frames. , ppl: 10.896838705510396], batch size: 70
+2022-12-10 01:48:44,160 INFO [train.py:421] (7/8) Epoch 1, batch 36800, loss[loss=2.362, over 1400.00 frames. , ppl: 10.617406409378491] tot_loss[loss=2.389, over 5441318.63 frames. , ppl: 10.898082358585237], batch size: 70
+2022-12-10 01:50:20,592 INFO [train.py:421] (7/8) Epoch 1, batch 37000, loss[loss=2.402, over 4410.00 frames. , ppl: 11.043910202215942] tot_loss[loss=2.388, over 5434977.51 frames. , ppl: 10.897071546189268], batch size: 70
+2022-12-10 01:50:20,593 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 01:50:21,353 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.371, over 211138.00 frames. , ppl: 10.706359193662431
+2022-12-10 01:52:04,192 INFO [train.py:421] (7/8) Epoch 1, batch 37200, loss[loss=2.506, over 1050.00 frames. , ppl: 12.258736166760155] tot_loss[loss=2.387, over 5478229.65 frames. , ppl: 10.880277391050235], batch size: 70
+2022-12-10 01:53:44,572 INFO [train.py:421] (7/8) Epoch 1, batch 37400, loss[loss=2.363, over 1750.00 frames. , ppl: 10.627562825782022] tot_loss[loss=2.387, over 5474560.99 frames. , ppl: 10.8804425708202], batch size: 70
+2022-12-10 01:55:24,460 INFO [train.py:421] (7/8) Epoch 1, batch 37600, loss[loss=2.322, over 4900.00 frames. , ppl: 10.199197819661673] tot_loss[loss=2.386, over 5476942.50 frames. , ppl: 10.873508200914895], batch size: 70
+2022-12-10 01:57:05,240 INFO [train.py:421] (7/8) Epoch 1, batch 37800, loss[loss=2.321, over 8750.00 frames. , ppl: 10.187578626018365] tot_loss[loss=2.387, over 5464250.49 frames. , ppl: 10.875686550210615], batch size: 70
+2022-12-10 01:58:47,484 INFO [train.py:421] (7/8) Epoch 1, batch 38000, loss[loss=2.424, over 3290.00 frames. , ppl: 11.292080638232873] tot_loss[loss=2.387, over 5475171.87 frames. , ppl: 10.882147269591243], batch size: 70
+2022-12-10 01:58:47,484 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 01:58:48,230 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.367, over 211138.00 frames. , ppl: 10.660825546799813
+2022-12-10 02:00:27,319 INFO [train.py:421] (7/8) Epoch 1, batch 38200, loss[loss=2.304, over 3360.00 frames. , ppl: 10.01905128595011] tot_loss[loss=2.387, over 5456571.38 frames. , ppl: 10.882982238620576], batch size: 70
+2022-12-10 02:02:09,572 INFO [train.py:421] (7/8) Epoch 1, batch 38400, loss[loss=3.323, over 490.00 frames. , ppl: 27.73321630684808] tot_loss[loss=2.388, over 5417772.30 frames. , ppl: 10.890102046863586], batch size: 70
+2022-12-10 02:03:49,947 INFO [train.py:421] (7/8) Epoch 1, batch 38600, loss[loss=2.309, over 4690.00 frames. , ppl: 10.06516622084443] tot_loss[loss=2.387, over 5449949.35 frames. , ppl: 10.881758406789412], batch size: 70
+2022-12-10 02:05:31,055 INFO [train.py:421] (7/8) Epoch 1, batch 38800, loss[loss=2.527, over 1400.00 frames. , ppl: 12.514717393318339] tot_loss[loss=2.387, over 5425158.11 frames. , ppl: 10.881969752876811], batch size: 70
+2022-12-10 02:07:09,882 INFO [train.py:421] (7/8) Epoch 1, batch 39000, loss[loss=2.338, over 1610.00 frames. , ppl: 10.360307443081487] tot_loss[loss=2.387, over 5404342.72 frames. , ppl: 10.881756971477051], batch size: 70
+2022-12-10 02:07:09,883 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 02:07:10,643 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.368, over 211138.00 frames. , ppl: 10.674933246579991
+2022-12-10 02:08:52,862 INFO [train.py:421] (7/8) Epoch 1, batch 39200, loss[loss=2.889, over 630.00 frames. , ppl: 17.972816209869816] tot_loss[loss=2.387, over 5425206.37 frames. , ppl: 10.88263896873241], batch size: 70
+2022-12-10 02:10:35,769 INFO [train.py:421] (7/8) Epoch 1, batch 39400, loss[loss=2.349, over 4130.00 frames. , ppl: 10.477386027365359] tot_loss[loss=2.385, over 5488411.34 frames. , ppl: 10.859503501606731], batch size: 70
+2022-12-10 02:12:14,142 INFO [train.py:421] (7/8) Epoch 1, batch 39600, loss[loss=2.463, over 2030.00 frames. , ppl: 11.735784001050348] tot_loss[loss=2.385, over 5509055.33 frames. , ppl: 10.856451195975081], batch size: 70
+2022-12-10 02:13:56,725 INFO [train.py:421] (7/8) Epoch 1, batch 39800, loss[loss=2.354, over 3150.00 frames. , ppl: 10.524719711862115] tot_loss[loss=2.384, over 5527774.11 frames. , ppl: 10.848372526305596], batch size: 70
+2022-12-10 02:15:38,370 INFO [train.py:421] (7/8) Epoch 1, batch 40000, loss[loss=2.44, over 1960.00 frames. , ppl: 11.469007960837683] tot_loss[loss=2.383, over 5569835.36 frames. , ppl: 10.839733876216439], batch size: 70
+2022-12-10 02:15:38,370 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 02:15:39,131 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.368, over 211138.00 frames. , ppl: 10.68034759574071
+2022-12-10 02:17:21,027 INFO [train.py:421] (7/8) Epoch 1, batch 40200, loss[loss=4.922, over 280.00 frames. , ppl: 137.25757982076703] tot_loss[loss=2.384, over 5537155.04 frames. , ppl: 10.848850422587766], batch size: 70
+2022-12-10 02:19:03,109 INFO [train.py:421] (7/8) Epoch 1, batch 40400, loss[loss=2.329, over 3850.00 frames. , ppl: 10.270162504073715] tot_loss[loss=2.384, over 5552037.62 frames. , ppl: 10.84380137614994], batch size: 70
+2022-12-10 02:20:42,127 INFO [train.py:421] (7/8) Epoch 1, batch 40600, loss[loss=2.426, over 1120.00 frames. , ppl: 11.30951443520553] tot_loss[loss=2.384, over 5537060.14 frames. , ppl: 10.847447243662618], batch size: 70
+2022-12-10 02:22:24,717 INFO [train.py:421] (7/8) Epoch 1, batch 40800, loss[loss=2.401, over 1680.00 frames. , ppl: 11.038005595825867] tot_loss[loss=2.383, over 5556442.48 frames. , ppl: 10.83621000862829], batch size: 70
+2022-12-10 02:24:04,606 INFO [train.py:421] (7/8) Epoch 1, batch 41000, loss[loss=2.254, over 2660.00 frames. , ppl: 9.5264959602325] tot_loss[loss=2.382, over 5573613.67 frames. , ppl: 10.827714799013478], batch size: 70
+2022-12-10 02:24:04,606 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 02:24:05,368 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.367, over 211138.00 frames. , ppl: 10.668684715535875
+2022-12-10 02:25:40,536 INFO [train.py:421] (7/8) Epoch 1, batch 41200, loss[loss=2.784, over 700.00 frames. , ppl: 16.18352004170719] tot_loss[loss=2.382, over 5573831.57 frames. , ppl: 10.829685789174832], batch size: 70
+2022-12-10 02:27:22,749 INFO [train.py:421] (7/8) Epoch 1, batch 41400, loss[loss=2.344, over 4410.00 frames. , ppl: 10.426351299974918] tot_loss[loss=2.382, over 5583248.62 frames. , ppl: 10.829668450868027], batch size: 70
+2022-12-10 02:29:04,771 INFO [train.py:421] (7/8) Epoch 1, batch 41600, loss[loss=2.375, over 2520.00 frames. , ppl: 10.753196540696061] tot_loss[loss=2.383, over 5554506.39 frames. , ppl: 10.836636333747865], batch size: 70
+2022-12-10 02:30:42,769 INFO [train.py:421] (7/8) Epoch 1, batch 41800, loss[loss=2.494, over 2520.00 frames. , ppl: 12.106839475427273] tot_loss[loss=2.384, over 5529618.97 frames. , ppl: 10.847776116419187], batch size: 70
+2022-12-10 02:32:23,880 INFO [train.py:421] (7/8) Epoch 1, batch 42000, loss[loss=2.318, over 1120.00 frames. , ppl: 10.159418717595914] tot_loss[loss=2.383, over 5545472.91 frames. , ppl: 10.833700160024025], batch size: 70
+2022-12-10 02:32:23,881 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 02:32:24,639 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.364, over 211138.00 frames. , ppl: 10.63275418399596
+2022-12-10 02:34:04,508 INFO [train.py:421] (7/8) Epoch 1, batch 42200, loss[loss=2.373, over 2310.00 frames. , ppl: 10.732721354151403] tot_loss[loss=2.382, over 5546956.20 frames. , ppl: 10.830868572831525], batch size: 70
+2022-12-10 02:35:44,519 INFO [train.py:421] (7/8) Epoch 1, batch 42400, loss[loss=2.502, over 1470.00 frames. , ppl: 12.202646429173752] tot_loss[loss=2.382, over 5586214.35 frames. , ppl: 10.823168721019485], batch size: 70
+2022-12-10 02:37:26,151 INFO [train.py:421] (7/8) Epoch 1, batch 42600, loss[loss=2.319, over 4060.00 frames. , ppl: 10.17034780467838] tot_loss[loss=2.38, over 5599127.82 frames. , ppl: 10.807281334331762], batch size: 70
+2022-12-10 02:39:06,182 INFO [train.py:421] (7/8) Epoch 1, batch 42800, loss[loss=2.358, over 2940.00 frames. , ppl: 10.565064410707143] tot_loss[loss=2.38, over 5618808.58 frames. , ppl: 10.80407511410268], batch size: 70
+2022-12-10 02:40:45,346 INFO [train.py:421] (7/8) Epoch 1, batch 43000, loss[loss=2.651, over 770.00 frames. , ppl: 14.168546030325963] tot_loss[loss=2.38, over 5611849.84 frames. , ppl: 10.801252618357227], batch size: 70
+2022-12-10 02:40:45,346 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 02:40:46,105 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.364, over 211138.00 frames. , ppl: 10.630343507571958
+2022-12-10 02:42:23,866 INFO [train.py:421] (7/8) Epoch 1, batch 43200, loss[loss=2.477, over 2450.00 frames. , ppl: 11.90819195072482] tot_loss[loss=2.381, over 5598954.47 frames. , ppl: 10.81309899373713], batch size: 70
+2022-12-10 02:44:06,619 INFO [train.py:421] (7/8) Epoch 1, batch 43400, loss[loss=2.266, over 3290.00 frames. , ppl: 9.63967501113892] tot_loss[loss=2.379, over 5640212.37 frames. , ppl: 10.797622872432646], batch size: 70
+2022-12-10 02:45:46,629 INFO [train.py:421] (7/8) Epoch 1, batch 43600, loss[loss=2.387, over 1680.00 frames. , ppl: 10.88338597017982] tot_loss[loss=2.379, over 5655525.57 frames. , ppl: 10.790834551205155], batch size: 70
+2022-12-10 02:47:26,672 INFO [train.py:421] (7/8) Epoch 1, batch 43800, loss[loss=2.42, over 1470.00 frames. , ppl: 11.243145075768304] tot_loss[loss=2.379, over 5628132.13 frames. , ppl: 10.795768433152963], batch size: 70
+2022-12-10 02:49:05,961 INFO [train.py:421] (7/8) Epoch 1, batch 44000, loss[loss=2.719, over 630.00 frames. , ppl: 15.1674056916072] tot_loss[loss=2.38, over 5599298.53 frames. , ppl: 10.803167482309878], batch size: 70
+2022-12-10 02:49:05,962 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 02:49:06,722 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.365, over 211138.00 frames. , ppl: 10.648347077171886
+2022-12-10 02:50:46,017 INFO [train.py:421] (7/8) Epoch 1, batch 44200, loss[loss=2.32, over 3010.00 frames. , ppl: 10.174250516465513] tot_loss[loss=2.381, over 5556264.76 frames. , ppl: 10.815391640206693], batch size: 70
+2022-12-10 02:52:25,665 INFO [train.py:421] (7/8) Epoch 1, batch 44400, loss[loss=2.384, over 1820.00 frames. , ppl: 10.850667920883504] tot_loss[loss=2.381, over 5544783.97 frames. , ppl: 10.815912305802552], batch size: 70
+2022-12-10 02:54:07,191 INFO [train.py:421] (7/8) Epoch 1, batch 44600, loss[loss=2.235, over 3220.00 frames. , ppl: 9.348855283656208] tot_loss[loss=2.381, over 5529557.75 frames. , ppl: 10.817209004769888], batch size: 70
+2022-12-10 02:55:46,321 INFO [train.py:421] (7/8) Epoch 1, batch 44800, loss[loss=2.476, over 2590.00 frames. , ppl: 11.897422176592798] tot_loss[loss=2.381, over 5520608.70 frames. , ppl: 10.813166813306145], batch size: 70
+2022-12-10 02:57:25,620 INFO [train.py:421] (7/8) Epoch 1, batch 45000, loss[loss=2.341, over 2870.00 frames. , ppl: 10.394126436436066] tot_loss[loss=2.38, over 5523674.33 frames. , ppl: 10.803831027736955], batch size: 70
+2022-12-10 02:57:25,621 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 02:57:26,378 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.364, over 211138.00 frames. , ppl: 10.628203939461411
+2022-12-10 02:59:10,687 INFO [train.py:421] (7/8) Epoch 1, batch 45200, loss[loss=2.627, over 1400.00 frames. , ppl: 13.832628752027853] tot_loss[loss=2.381, over 5526742.21 frames. , ppl: 10.811149051952048], batch size: 70
+2022-12-10 03:00:53,880 INFO [train.py:421] (7/8) Epoch 1, batch 45400, loss[loss=2.808, over 630.00 frames. , ppl: 16.580147259718505] tot_loss[loss=2.381, over 5502963.53 frames. , ppl: 10.817599183854218], batch size: 70
+2022-12-10 03:02:33,641 INFO [train.py:421] (7/8) Epoch 1, batch 45600, loss[loss=2.438, over 1680.00 frames. , ppl: 11.447491112663503] tot_loss[loss=2.382, over 5490049.28 frames. , ppl: 10.824463181622532], batch size: 70
+2022-12-10 03:04:17,137 INFO [train.py:421] (7/8) Epoch 1, batch 45800, loss[loss=2.306, over 5320.00 frames. , ppl: 10.035946223092244] tot_loss[loss=2.381, over 5541533.57 frames. , ppl: 10.813364448600908], batch size: 70
+2022-12-10 03:05:58,453 INFO [train.py:421] (7/8) Epoch 1, batch 46000, loss[loss=2.932, over 630.00 frames. , ppl: 18.770106203666] tot_loss[loss=2.381, over 5533739.09 frames. , ppl: 10.813557016049565], batch size: 70
+2022-12-10 03:05:58,453 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 03:05:59,200 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.363, over 211138.00 frames. , ppl: 10.624262598332244
+2022-12-10 03:07:41,816 INFO [train.py:421] (7/8) Epoch 1, batch 46200, loss[loss=2.27, over 4970.00 frames. , ppl: 9.683453511532296] tot_loss[loss=2.38, over 5560500.75 frames. , ppl: 10.804869939847148], batch size: 70
+2022-12-10 03:09:19,255 INFO [train.py:421] (7/8) Epoch 1, batch 46400, loss[loss=2.478, over 2030.00 frames. , ppl: 11.911633055539138] tot_loss[loss=2.38, over 5562888.42 frames. , ppl: 10.802862301286549], batch size: 70
+2022-12-10 03:11:00,974 INFO [train.py:421] (7/8) Epoch 1, batch 46600, loss[loss=2.545, over 1190.00 frames. , ppl: 12.73869865356021] tot_loss[loss=2.381, over 5543559.27 frames. , ppl: 10.811465362977472], batch size: 70
+2022-12-10 03:12:37,299 INFO [train.py:421] (7/8) Epoch 1, batch 46800, loss[loss=2.444, over 1610.00 frames. , ppl: 11.521984810292384] tot_loss[loss=2.382, over 5467451.29 frames. , ppl: 10.828906139151467], batch size: 70
+2022-12-10 03:14:18,444 INFO [train.py:421] (7/8) Epoch 1, batch 47000, loss[loss=2.571, over 1540.00 frames. , ppl: 13.077315611516147] tot_loss[loss=2.381, over 5467676.58 frames. , ppl: 10.817630444921392], batch size: 70
+2022-12-10 03:14:18,444 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 03:14:19,231 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.363, over 211138.00 frames. , ppl: 10.618849962774785
+2022-12-10 03:15:58,273 INFO [train.py:421] (7/8) Epoch 1, batch 47200, loss[loss=2.251, over 4620.00 frames. , ppl: 9.497776621104672] tot_loss[loss=2.379, over 5539602.63 frames. , ppl: 10.797594226392436], batch size: 70
+2022-12-10 03:17:35,094 INFO [train.py:421] (7/8) Epoch 1, batch 47400, loss[loss=2.388, over 2310.00 frames. , ppl: 10.891745311111816] tot_loss[loss=2.379, over 5547190.42 frames. , ppl: 10.797009714508532], batch size: 70
+2022-12-10 03:19:18,544 INFO [train.py:421] (7/8) Epoch 1, batch 47600, loss[loss=2.329, over 3640.00 frames. , ppl: 10.26921576109609] tot_loss[loss=2.379, over 5547475.43 frames. , ppl: 10.795449174703384], batch size: 70
+2022-12-10 03:20:57,292 INFO [train.py:421] (7/8) Epoch 1, batch 47800, loss[loss=2.289, over 5810.00 frames. , ppl: 9.869047778198478] tot_loss[loss=2.379, over 5539228.54 frames. , ppl: 10.795654342584491], batch size: 70
+2022-12-10 03:22:37,636 INFO [train.py:421] (7/8) Epoch 1, batch 48000, loss[loss=2.334, over 4200.00 frames. , ppl: 10.31703593270806] tot_loss[loss=2.379, over 5569624.84 frames. , ppl: 10.790044307093298], batch size: 70
+2022-12-10 03:22:37,636 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 03:22:38,366 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.361, over 211138.00 frames. , ppl: 10.600952749654093
+2022-12-10 03:24:15,508 INFO [train.py:421] (7/8) Epoch 1, batch 48200, loss[loss=2.534, over 1260.00 frames. , ppl: 12.605406655364035] tot_loss[loss=2.38, over 5537617.18 frames. , ppl: 10.805919226675648], batch size: 70
+2022-12-10 03:25:55,537 INFO [train.py:421] (7/8) Epoch 1, batch 48400, loss[loss=2.358, over 3010.00 frames. , ppl: 10.565392171383463] tot_loss[loss=2.379, over 5518296.05 frames. , ppl: 10.798950062555168], batch size: 70
+2022-12-10 03:27:34,539 INFO [train.py:421] (7/8) Epoch 1, batch 48600, loss[loss=2.384, over 4410.00 frames. , ppl: 10.848231707308946] tot_loss[loss=2.38, over 5490818.55 frames. , ppl: 10.805939241494091], batch size: 70
+2022-12-10 03:29:11,886 INFO [train.py:421] (7/8) Epoch 1, batch 48800, loss[loss=2.368, over 1890.00 frames. , ppl: 10.677243678390003] tot_loss[loss=2.38, over 5483903.23 frames. , ppl: 10.802228797827839], batch size: 70
+2022-12-10 03:30:50,524 INFO [train.py:421] (7/8) Epoch 1, batch 49000, loss[loss=2.396, over 2380.00 frames. , ppl: 10.974935538710158] tot_loss[loss=2.38, over 5494376.94 frames. , ppl: 10.799767271488502], batch size: 70
+2022-12-10 03:30:50,525 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 03:30:51,282 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.36, over 211138.00 frames. , ppl: 10.585974491786418
+2022-12-10 03:32:29,120 INFO [train.py:421] (7/8) Epoch 1, batch 49200, loss[loss=2.553, over 770.00 frames. , ppl: 12.84459408588449] tot_loss[loss=2.38, over 5479060.88 frames. , ppl: 10.804033242591366], batch size: 70
+2022-12-10 03:34:05,533 INFO [train.py:421] (7/8) Epoch 1, batch 49400, loss[loss=2.394, over 4270.00 frames. , ppl: 10.957936732248077] tot_loss[loss=2.38, over 5467472.69 frames. , ppl: 10.800661242655853], batch size: 70
+2022-12-10 03:35:47,725 INFO [train.py:421] (7/8) Epoch 1, batch 49600, loss[loss=2.412, over 1890.00 frames. , ppl: 11.160605383399227] tot_loss[loss=2.381, over 5438848.24 frames. , ppl: 10.816694703261701], batch size: 70
+2022-12-10 03:37:28,158 INFO [train.py:421] (7/8) Epoch 1, batch 49800, loss[loss=2.296, over 5530.00 frames. , ppl: 9.931932222939702] tot_loss[loss=2.38, over 5434924.19 frames. , ppl: 10.807621329828537], batch size: 70
+2022-12-10 03:39:06,578 INFO [train.py:421] (7/8) Epoch 1, batch 50000, loss[loss=2.421, over 2240.00 frames. , ppl: 11.262086059362419] tot_loss[loss=2.378, over 5477646.94 frames. , ppl: 10.786290377454904], batch size: 70
+2022-12-10 03:39:06,579 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 03:39:07,338 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.359, over 211138.00 frames. , ppl: 10.58257820728752
+2022-12-10 03:40:43,903 INFO [train.py:421] (7/8) Epoch 1, batch 50200, loss[loss=2.383, over 2030.00 frames. , ppl: 10.839129794372973] tot_loss[loss=2.379, over 5415848.42 frames. , ppl: 10.799332532426416], batch size: 70
+2022-12-10 03:42:22,999 INFO [train.py:421] (7/8) Epoch 1, batch 50400, loss[loss=2.593, over 1400.00 frames. , ppl: 13.369841479325679] tot_loss[loss=2.379, over 5428593.02 frames. , ppl: 10.790132314762104], batch size: 70
+2022-12-10 03:44:03,136 INFO [train.py:421] (7/8) Epoch 1, batch 50600, loss[loss=2.708, over 840.00 frames. , ppl: 14.992503949192912] tot_loss[loss=2.378, over 5415590.70 frames. , ppl: 10.787614074547673], batch size: 70
+2022-12-10 03:45:44,370 INFO [train.py:421] (7/8) Epoch 1, batch 50800, loss[loss=2.455, over 1680.00 frames. , ppl: 11.649510208100319] tot_loss[loss=2.379, over 5389142.90 frames. , ppl: 10.797549465733844], batch size: 70
+2022-12-10 03:47:26,038 INFO [train.py:421] (7/8) Epoch 1, batch 51000, loss[loss=2.292, over 6370.00 frames. , ppl: 9.890747486627525] tot_loss[loss=2.379, over 5383844.53 frames. , ppl: 10.796359676792104], batch size: 70
+2022-12-10 03:47:26,038 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 03:47:26,769 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.361, over 211138.00 frames. , ppl: 10.598020656585552
+2022-12-10 03:49:07,095 INFO [train.py:421] (7/8) Epoch 1, batch 51200, loss[loss=2.861, over 560.00 frames. , ppl: 17.476899014388707] tot_loss[loss=2.379, over 5371975.43 frames. , ppl: 10.79491612810722], batch size: 70
+2022-12-10 03:50:49,016 INFO [train.py:421] (7/8) Epoch 1, batch 51400, loss[loss=2.422, over 1330.00 frames. , ppl: 11.272827923361133] tot_loss[loss=2.38, over 5350140.24 frames. , ppl: 10.80195639410046], batch size: 70
+2022-12-10 03:52:29,259 INFO [train.py:421] (7/8) Epoch 1, batch 51600, loss[loss=3.287, over 490.00 frames. , ppl: 26.76264268453004] tot_loss[loss=2.38, over 5368156.51 frames. , ppl: 10.802740004716398], batch size: 70
+2022-12-10 03:54:10,139 INFO [train.py:421] (7/8) Epoch 1, batch 51800, loss[loss=2.362, over 4270.00 frames. , ppl: 10.607411344089467] tot_loss[loss=2.379, over 5384283.43 frames. , ppl: 10.79807159483733], batch size: 70
+2022-12-10 03:55:47,568 INFO [train.py:421] (7/8) Epoch 1, batch 52000, loss[loss=2.353, over 2170.00 frames. , ppl: 10.51717428995101] tot_loss[loss=2.38, over 5369668.09 frames. , ppl: 10.801665620499213], batch size: 70
+2022-12-10 03:55:47,568 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 03:55:48,316 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.359, over 211138.00 frames. , ppl: 10.580972870980991
+2022-12-10 03:57:25,693 INFO [train.py:421] (7/8) Epoch 1, batch 52200, loss[loss=2.497, over 1400.00 frames. , ppl: 12.150846717320706] tot_loss[loss=2.38, over 5352741.89 frames. , ppl: 10.80637025023496], batch size: 70
+2022-12-10 03:59:05,789 INFO [train.py:421] (7/8) Epoch 1, batch 52400, loss[loss=2.417, over 1890.00 frames. , ppl: 11.21239174608952] tot_loss[loss=2.38, over 5352353.87 frames. , ppl: 10.807016328630253], batch size: 70
+2022-12-10 04:00:46,745 INFO [train.py:421] (7/8) Epoch 1, batch 52600, loss[loss=2.302, over 8820.00 frames. , ppl: 9.998983925396573] tot_loss[loss=2.379, over 5362865.92 frames. , ppl: 10.795177492487538], batch size: 70
+2022-12-10 04:02:26,553 INFO [train.py:421] (7/8) Epoch 1, batch 52800, loss[loss=2.44, over 2310.00 frames. , ppl: 11.477481546163576] tot_loss[loss=2.38, over 5313255.84 frames. , ppl: 10.805630842696548], batch size: 70
+2022-12-10 04:04:06,247 INFO [train.py:421] (7/8) Epoch 1, batch 53000, loss[loss=2.585, over 840.00 frames. , ppl: 13.266930919055524] tot_loss[loss=2.379, over 5318968.30 frames. , ppl: 10.79926119184296], batch size: 70
+2022-12-10 04:04:06,248 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 04:04:07,006 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.358, over 211138.00 frames. , ppl: 10.567887116951528
+2022-12-10 04:05:52,841 INFO [train.py:421] (7/8) Epoch 1, batch 53200, loss[loss=2.311, over 4480.00 frames. , ppl: 10.085935894786989] tot_loss[loss=2.38, over 5327679.78 frames. , ppl: 10.805373848794016], batch size: 70
+2022-12-10 04:07:33,549 INFO [train.py:421] (7/8) Epoch 1, batch 53400, loss[loss=2.478, over 1330.00 frames. , ppl: 11.912910974959194] tot_loss[loss=2.38, over 5311974.54 frames. , ppl: 10.804899188274119], batch size: 70
+2022-12-10 04:09:19,576 INFO [train.py:421] (7/8) Epoch 1, batch 53600, loss[loss=2.399, over 1120.00 frames. , ppl: 11.012954543299687] tot_loss[loss=2.38, over 5346428.70 frames. , ppl: 10.807280540997192], batch size: 70
+2022-12-10 04:10:59,121 INFO [train.py:421] (7/8) Epoch 1, batch 53800, loss[loss=2.431, over 1260.00 frames. , ppl: 11.374799742453563] tot_loss[loss=2.378, over 5379300.81 frames. , ppl: 10.788265602243946], batch size: 70
+2022-12-10 04:12:36,568 INFO [train.py:421] (7/8) Epoch 1, batch 54000, loss[loss=2.383, over 3710.00 frames. , ppl: 10.83521463900271] tot_loss[loss=2.378, over 5403047.51 frames. , ppl: 10.78417839177244], batch size: 70
+2022-12-10 04:12:36,569 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 04:12:37,329 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.356, over 211138.00 frames. , ppl: 10.55320704955568
+2022-12-10 04:14:15,873 INFO [train.py:421] (7/8) Epoch 1, batch 54200, loss[loss=2.375, over 1890.00 frames. , ppl: 10.754941320807692] tot_loss[loss=2.378, over 5413249.51 frames. , ppl: 10.77998817188157], batch size: 70
+2022-12-10 04:15:51,798 INFO [train.py:421] (7/8) Epoch 1, batch 54400, loss[loss=2.44, over 1470.00 frames. , ppl: 11.470636677433] tot_loss[loss=2.377, over 5437719.37 frames. , ppl: 10.773785438313675], batch size: 70
+2022-12-10 04:17:31,785 INFO [train.py:421] (7/8) Epoch 1, batch 54600, loss[loss=2.458, over 1260.00 frames. , ppl: 11.686528900732375] tot_loss[loss=2.375, over 5501783.63 frames. , ppl: 10.751487546585004], batch size: 70
+2022-12-10 04:19:11,954 INFO [train.py:421] (7/8) Epoch 1, batch 54800, loss[loss=4.191, over 350.00 frames. , ppl: 66.07293960571315] tot_loss[loss=2.376, over 5471127.90 frames. , ppl: 10.760915494216498], batch size: 70
+2022-12-10 04:20:51,944 INFO [train.py:421] (7/8) Epoch 1, batch 55000, loss[loss=2.352, over 9800.00 frames. , ppl: 10.507380193586977] tot_loss[loss=2.376, over 5500663.68 frames. , ppl: 10.760648734714337], batch size: 70
+2022-12-10 04:20:51,944 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 04:20:52,675 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.355, over 211138.00 frames. , ppl: 10.542236908630983
+2022-12-10 04:22:35,385 INFO [train.py:421] (7/8) Epoch 1, batch 55200, loss[loss=2.452, over 1050.00 frames. , ppl: 11.610354409004204] tot_loss[loss=2.376, over 5485941.18 frames. , ppl: 10.757613482074094], batch size: 70
+2022-12-10 04:24:13,633 INFO [train.py:421] (7/8) Epoch 1, batch 55400, loss[loss=2.249, over 2940.00 frames. , ppl: 9.477174788123198] tot_loss[loss=2.375, over 5492113.74 frames. , ppl: 10.749738193532325], batch size: 70
+2022-12-10 04:25:54,098 INFO [train.py:421] (7/8) Epoch 1, batch 55600, loss[loss=2.412, over 3360.00 frames. , ppl: 11.16009378232016] tot_loss[loss=2.376, over 5483243.69 frames. , ppl: 10.762192876325585], batch size: 70
+2022-12-10 04:27:33,002 INFO [train.py:421] (7/8) Epoch 1, batch 55800, loss[loss=2.335, over 2170.00 frames. , ppl: 10.328942558213589] tot_loss[loss=2.375, over 5499710.63 frames. , ppl: 10.75361789620878], batch size: 70
+2022-12-10 04:29:13,179 INFO [train.py:421] (7/8) Epoch 1, batch 56000, loss[loss=2.365, over 4690.00 frames. , ppl: 10.648130054932066] tot_loss[loss=2.376, over 5460381.89 frames. , ppl: 10.759876414964594], batch size: 70
+2022-12-10 04:29:13,179 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 04:29:13,929 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.355, over 211138.00 frames. , ppl: 10.539062115723747
+2022-12-10 04:30:54,313 INFO [train.py:421] (7/8) Epoch 1, batch 56200, loss[loss=2.367, over 2240.00 frames. , ppl: 10.662926338830752] tot_loss[loss=2.376, over 5447911.11 frames. , ppl: 10.76571649877172], batch size: 70
+2022-12-10 04:32:32,227 INFO [train.py:421] (7/8) Epoch 1, batch 56400, loss[loss=2.891, over 700.00 frames. , ppl: 18.00248682204959] tot_loss[loss=2.375, over 5473094.68 frames. , ppl: 10.7536155284058], batch size: 70
+2022-12-10 04:34:13,605 INFO [train.py:421] (7/8) Epoch 1, batch 56600, loss[loss=2.527, over 1540.00 frames. , ppl: 12.518109292421261] tot_loss[loss=2.374, over 5538618.10 frames. , ppl: 10.737921152792369], batch size: 70
+2022-12-10 04:35:52,338 INFO [train.py:421] (7/8) Epoch 1, batch 56800, loss[loss=2.29, over 3150.00 frames. , ppl: 9.871302906180524] tot_loss[loss=2.373, over 5558193.57 frames. , ppl: 10.73037678878659], batch size: 70
+2022-12-10 04:37:33,496 INFO [train.py:421] (7/8) Epoch 1, batch 57000, loss[loss=2.561, over 980.00 frames. , ppl: 12.952192733459148] tot_loss[loss=2.373, over 5544048.59 frames. , ppl: 10.731911013391487], batch size: 70
+2022-12-10 04:37:33,496 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 04:37:34,257 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.354, over 211138.00 frames. , ppl: 10.531887643629647
+2022-12-10 04:39:15,038 INFO [train.py:421] (7/8) Epoch 1, batch 57200, loss[loss=2.414, over 2030.00 frames. , ppl: 11.182778398161371] tot_loss[loss=2.373, over 5558448.88 frames. , ppl: 10.728994233599675], batch size: 70
+2022-12-10 04:40:55,986 INFO [train.py:421] (7/8) Epoch 1, batch 57400, loss[loss=2.323, over 2310.00 frames. , ppl: 10.207098843311982] tot_loss[loss=2.373, over 5538714.94 frames. , ppl: 10.731447012105324], batch size: 70
+2022-12-10 04:42:35,564 INFO [train.py:421] (7/8) Epoch 1, batch 57600, loss[loss=2.455, over 3290.00 frames. , ppl: 11.648002087157172] tot_loss[loss=2.373, over 5556907.58 frames. , ppl: 10.727036817540526], batch size: 70
+2022-12-10 04:44:14,430 INFO [train.py:421] (7/8) Epoch 1, batch 57800, loss[loss=2.876, over 560.00 frames. , ppl: 17.74918717082075] tot_loss[loss=2.373, over 5552739.86 frames. , ppl: 10.734095644041753], batch size: 70
+2022-12-10 04:45:53,664 INFO [train.py:421] (7/8) Epoch 1, batch 58000, loss[loss=2.196, over 6160.00 frames. , ppl: 8.989078691105219] tot_loss[loss=2.374, over 5507252.43 frames. , ppl: 10.739309276166468], batch size: 70
+2022-12-10 04:45:53,664 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 04:45:54,422 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.353, over 211138.00 frames. , ppl: 10.515346212674748
+2022-12-10 04:47:35,225 INFO [train.py:421] (7/8) Epoch 1, batch 58200, loss[loss=2.314, over 2870.00 frames. , ppl: 10.11061768948449] tot_loss[loss=2.373, over 5525450.46 frames. , ppl: 10.725049916886025], batch size: 70
+2022-12-10 04:49:15,815 INFO [train.py:421] (7/8) Epoch 1, batch 58400, loss[loss=2.424, over 1330.00 frames. , ppl: 11.29224007037873] tot_loss[loss=2.373, over 5523173.94 frames. , ppl: 10.729044449999893], batch size: 70
+2022-12-10 04:50:58,467 INFO [train.py:421] (7/8) Epoch 1, batch 58600, loss[loss=2.371, over 1890.00 frames. , ppl: 10.706401770613237] tot_loss[loss=2.373, over 5511457.12 frames. , ppl: 10.733287136275203], batch size: 70
+2022-12-10 04:52:37,254 INFO [train.py:421] (7/8) Epoch 1, batch 58800, loss[loss=2.342, over 3430.00 frames. , ppl: 10.397867201773876] tot_loss[loss=2.373, over 5493194.48 frames. , ppl: 10.733600403399597], batch size: 70
+2022-12-10 04:54:20,778 INFO [train.py:421] (7/8) Epoch 1, batch 59000, loss[loss=2.346, over 2940.00 frames. , ppl: 10.440867836952254] tot_loss[loss=2.374, over 5486999.91 frames. , ppl: 10.735370897530652], batch size: 70
+2022-12-10 04:54:20,778 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 04:54:21,536 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.352, over 211138.00 frames. , ppl: 10.503966120477648
+2022-12-10 04:55:59,455 INFO [train.py:421] (7/8) Epoch 1, batch 59200, loss[loss=2.268, over 4410.00 frames. , ppl: 9.66004184931412] tot_loss[loss=2.372, over 5510086.96 frames. , ppl: 10.72395383870396], batch size: 70
+2022-12-10 04:57:42,859 INFO [train.py:421] (7/8) Epoch 1, batch 59400, loss[loss=2.319, over 3360.00 frames. , ppl: 10.164098459213394] tot_loss[loss=2.372, over 5523854.23 frames. , ppl: 10.717444164963036], batch size: 70
+2022-12-10 04:59:24,823 INFO [train.py:421] (7/8) Epoch 1, batch 59600, loss[loss=2.389, over 2730.00 frames. , ppl: 10.897991555922399] tot_loss[loss=2.371, over 5588368.51 frames. , ppl: 10.704928281951986], batch size: 70
+2022-12-10 05:01:09,093 INFO [train.py:421] (7/8) Epoch 1, batch 59800, loss[loss=2.312, over 9520.00 frames. , ppl: 10.097935005113557] tot_loss[loss=2.37, over 5658077.64 frames. , ppl: 10.693935598168343], batch size: 70
+2022-12-10 05:02:50,324 INFO [train.py:421] (7/8) Epoch 1, batch 60000, loss[loss=2.402, over 2380.00 frames. , ppl: 11.043834317140337] tot_loss[loss=2.369, over 5688553.01 frames. , ppl: 10.689003492407206], batch size: 70
+2022-12-10 05:02:50,324 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 05:02:51,100 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.353, over 211138.00 frames. , ppl: 10.521841308858221
+2022-12-10 05:04:30,567 INFO [train.py:421] (7/8) Epoch 1, batch 60200, loss[loss=2.748, over 630.00 frames. , ppl: 15.611111454089677] tot_loss[loss=2.37, over 5655204.39 frames. , ppl: 10.69556087018115], batch size: 70
+2022-12-10 05:06:11,841 INFO [train.py:421] (7/8) Epoch 1, batch 60400, loss[loss=2.507, over 1610.00 frames. , ppl: 12.263575137561256] tot_loss[loss=2.371, over 5617028.58 frames. , ppl: 10.705391816394519], batch size: 70
+2022-12-10 05:07:53,825 INFO [train.py:421] (7/8) Epoch 1, batch 60600, loss[loss=2.262, over 7700.00 frames. , ppl: 9.59965218303055] tot_loss[loss=2.37, over 5654302.67 frames. , ppl: 10.692579847162081], batch size: 70
+2022-12-10 05:09:33,766 INFO [train.py:421] (7/8) Epoch 1, batch 60800, loss[loss=2.293, over 5180.00 frames. , ppl: 9.908004574004492] tot_loss[loss=2.371, over 5619087.95 frames. , ppl: 10.705093521031221], batch size: 70
+2022-12-10 05:11:18,590 INFO [train.py:421] (7/8) Epoch 1, batch 61000, loss[loss=2.43, over 1540.00 frames. , ppl: 11.355581413356223] tot_loss[loss=2.37, over 5637777.00 frames. , ppl: 10.698933969798713], batch size: 70
+2022-12-10 05:11:18,591 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 05:11:19,337 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.352, over 211138.00 frames. , ppl: 10.508142781873898
+2022-12-10 05:12:58,138 INFO [train.py:421] (7/8) Epoch 1, batch 61200, loss[loss=2.27, over 8610.00 frames. , ppl: 9.675628437992431] tot_loss[loss=2.37, over 5592740.83 frames. , ppl: 10.701071480163439], batch size: 70
+2022-12-10 05:14:39,408 INFO [train.py:421] (7/8) Epoch 1, batch 61400, loss[loss=3.102, over 630.00 frames. , ppl: 22.24518484067265] tot_loss[loss=2.37, over 5618106.99 frames. , ppl: 10.694074539294434], batch size: 70
+2022-12-10 05:16:19,247 INFO [train.py:421] (7/8) Epoch 1, batch 61600, loss[loss=2.372, over 2450.00 frames. , ppl: 10.716093230713076] tot_loss[loss=2.369, over 5640431.06 frames. , ppl: 10.691806250802136], batch size: 70
+2022-12-10 05:17:59,812 INFO [train.py:421] (7/8) Epoch 1, batch 61800, loss[loss=2.405, over 4620.00 frames. , ppl: 11.079551089507204] tot_loss[loss=2.369, over 5650499.08 frames. , ppl: 10.687171715189159], batch size: 70
+2022-12-10 05:19:41,043 INFO [train.py:421] (7/8) Epoch 1, batch 62000, loss[loss=2.359, over 3010.00 frames. , ppl: 10.585343812603229] tot_loss[loss=2.369, over 5663879.28 frames. , ppl: 10.686892193919963], batch size: 70
+2022-12-10 05:19:41,043 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 05:19:41,789 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.351, over 211138.00 frames. , ppl: 10.500484247218756
+2022-12-10 05:21:23,044 INFO [train.py:421] (7/8) Epoch 1, batch 62200, loss[loss=2.283, over 5880.00 frames. , ppl: 9.801640387852464] tot_loss[loss=2.369, over 5665866.03 frames. , ppl: 10.687487193978027], batch size: 70
+2022-12-10 05:23:03,310 INFO [train.py:421] (7/8) Epoch 1, batch 62400, loss[loss=2.424, over 2380.00 frames. , ppl: 11.288005781816008] tot_loss[loss=2.368, over 5681350.00 frames. , ppl: 10.679079988991354], batch size: 70
+2022-12-10 05:24:44,528 INFO [train.py:421] (7/8) Epoch 1, batch 62600, loss[loss=2.311, over 4200.00 frames. , ppl: 10.088575977422373] tot_loss[loss=2.368, over 5684314.77 frames. , ppl: 10.675992977917703], batch size: 70
+2022-12-10 05:26:22,733 INFO [train.py:421] (7/8) Epoch 1, batch 62800, loss[loss=2.37, over 3850.00 frames. , ppl: 10.69880878382457] tot_loss[loss=2.369, over 5641965.09 frames. , ppl: 10.683468285536414], batch size: 70
+2022-12-10 05:28:05,201 INFO [train.py:421] (7/8) Epoch 1, batch 63000, loss[loss=2.549, over 1120.00 frames. , ppl: 12.794134406516017] tot_loss[loss=2.369, over 5613905.20 frames. , ppl: 10.687235896749941], batch size: 70
+2022-12-10 05:28:05,202 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 05:28:05,959 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.352, over 211138.00 frames. , ppl: 10.50832786224836
+2022-12-10 05:29:47,034 INFO [train.py:421] (7/8) Epoch 1, batch 63200, loss[loss=2.28, over 4830.00 frames. , ppl: 9.774123663766234] tot_loss[loss=2.369, over 5605021.39 frames. , ppl: 10.689813858262454], batch size: 70
+2022-12-10 05:31:24,722 INFO [train.py:421] (7/8) Epoch 1, batch 63400, loss[loss=2.289, over 5320.00 frames. , ppl: 9.862868580520443] tot_loss[loss=2.371, over 5517572.89 frames. , ppl: 10.709635046567902], batch size: 70
+2022-12-10 05:33:03,889 INFO [train.py:421] (7/8) Epoch 1, batch 63600, loss[loss=2.298, over 7840.00 frames. , ppl: 9.953044336030274] tot_loss[loss=2.371, over 5517086.11 frames. , ppl: 10.711631334157778], batch size: 70
+2022-12-10 05:34:41,285 INFO [train.py:421] (7/8) Epoch 1, batch 63800, loss[loss=2.983, over 560.00 frames. , ppl: 19.73870518397574] tot_loss[loss=2.371, over 5528043.94 frames. , ppl: 10.709066597323925], batch size: 70
+2022-12-10 05:36:22,762 INFO [train.py:421] (7/8) Epoch 1, batch 64000, loss[loss=2.327, over 2730.00 frames. , ppl: 10.245610680652698] tot_loss[loss=2.37, over 5550221.25 frames. , ppl: 10.696710679230835], batch size: 70
+2022-12-10 05:36:22,763 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 05:36:23,521 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.351, over 211138.00 frames. , ppl: 10.500185854649434
+2022-12-10 05:38:06,568 INFO [train.py:421] (7/8) Epoch 1, batch 64200, loss[loss=2.462, over 2520.00 frames. , ppl: 11.732666511039724] tot_loss[loss=2.369, over 5604231.72 frames. , ppl: 10.683853347296502], batch size: 70
+2022-12-10 05:39:48,015 INFO [train.py:421] (7/8) Epoch 1, batch 64400, loss[loss=2.318, over 7630.00 frames. , ppl: 10.154698416487886] tot_loss[loss=2.37, over 5570330.51 frames. , ppl: 10.693958398875735], batch size: 70
+2022-12-10 05:41:29,579 INFO [train.py:421] (7/8) Epoch 1, batch 64600, loss[loss=2.321, over 4060.00 frames. , ppl: 10.181158856246858] tot_loss[loss=2.369, over 5585268.74 frames. , ppl: 10.681933061986502], batch size: 70
+2022-12-10 05:43:06,386 INFO [train.py:421] (7/8) Epoch 1, batch 64800, loss[loss=2.49, over 1190.00 frames. , ppl: 12.06690542215173] tot_loss[loss=2.369, over 5526507.93 frames. , ppl: 10.691578416879596], batch size: 70
+2022-12-10 05:44:45,913 INFO [train.py:421] (7/8) Epoch 1, batch 65000, loss[loss=2.314, over 6300.00 frames. , ppl: 10.114535263708882] tot_loss[loss=2.369, over 5557148.33 frames. , ppl: 10.6837829050986], batch size: 70
+2022-12-10 05:44:45,913 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 05:44:46,659 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.351, over 211138.00 frames. , ppl: 10.499536258484806
+2022-12-10 05:46:27,198 INFO [train.py:421] (7/8) Epoch 1, batch 65200, loss[loss=2.309, over 3990.00 frames. , ppl: 10.06372261792443] tot_loss[loss=2.369, over 5492336.62 frames. , ppl: 10.686881386060138], batch size: 70
+2022-12-10 05:48:06,794 INFO [train.py:421] (7/8) Epoch 1, batch 65400, loss[loss=2.256, over 3430.00 frames. , ppl: 9.547532478491222] tot_loss[loss=2.369, over 5484043.61 frames. , ppl: 10.689952696538908], batch size: 70
+2022-12-10 05:49:47,266 INFO [train.py:421] (7/8) Epoch 1, batch 65600, loss[loss=2.382, over 2730.00 frames. , ppl: 10.82362565773072] tot_loss[loss=2.369, over 5474127.28 frames. , ppl: 10.690282089599593], batch size: 70
+2022-12-10 05:51:25,721 INFO [train.py:421] (7/8) Epoch 1, batch 65800, loss[loss=2.349, over 4130.00 frames. , ppl: 10.475364632313283] tot_loss[loss=2.369, over 5467274.93 frames. , ppl: 10.68615888346276], batch size: 70
+2022-12-10 05:53:05,372 INFO [train.py:421] (7/8) Epoch 1, batch 66000, loss[loss=2.509, over 1120.00 frames. , ppl: 12.288158052205063] tot_loss[loss=2.369, over 5469350.32 frames. , ppl: 10.68388589895595], batch size: 70
+2022-12-10 05:53:05,373 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 05:53:06,133 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.349, over 211138.00 frames. , ppl: 10.479744419827652
+2022-12-10 05:54:45,807 INFO [train.py:421] (7/8) Epoch 1, batch 66200, loss[loss=3.532, over 420.00 frames. , ppl: 34.17809088639017] tot_loss[loss=2.368, over 5473888.84 frames. , ppl: 10.677984334455086], batch size: 70
+2022-12-10 05:56:26,077 INFO [train.py:421] (7/8) Epoch 1, batch 66400, loss[loss=2.269, over 9800.00 frames. , ppl: 9.673420554869745] tot_loss[loss=2.367, over 5524955.69 frames. , ppl: 10.662359033243714], batch size: 70
+2022-12-10 05:58:06,911 INFO [train.py:421] (7/8) Epoch 1, batch 66600, loss[loss=2.397, over 1050.00 frames. , ppl: 10.98978690522617] tot_loss[loss=2.367, over 5493421.49 frames. , ppl: 10.669731725145573], batch size: 70
+2022-12-10 05:59:44,020 INFO [train.py:421] (7/8) Epoch 1, batch 66800, loss[loss=2.377, over 3150.00 frames. , ppl: 10.7734912573997] tot_loss[loss=2.367, over 5490840.83 frames. , ppl: 10.670634109314204], batch size: 70
+2022-12-10 06:01:21,584 INFO [train.py:421] (7/8) Epoch 1, batch 67000, loss[loss=2.351, over 2940.00 frames. , ppl: 10.496689646500466] tot_loss[loss=2.368, over 5472292.81 frames. , ppl: 10.67434087079412], batch size: 70
+2022-12-10 06:01:21,584 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 06:01:22,329 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.348, over 211138.00 frames. , ppl: 10.464386029268178
+2022-12-10 06:02:59,572 INFO [train.py:421] (7/8) Epoch 1, batch 67200, loss[loss=2.367, over 3640.00 frames. , ppl: 10.66681011323095] tot_loss[loss=2.368, over 5468328.36 frames. , ppl: 10.671470211881031], batch size: 70
+2022-12-10 06:04:38,156 INFO [train.py:421] (7/8) Epoch 1, batch 67400, loss[loss=2.559, over 1540.00 frames. , ppl: 12.928212491276716] tot_loss[loss=2.368, over 5451708.35 frames. , ppl: 10.672805888301658], batch size: 70
+2022-12-10 06:06:18,488 INFO [train.py:421] (7/8) Epoch 1, batch 67600, loss[loss=2.433, over 2170.00 frames. , ppl: 11.3952627940272] tot_loss[loss=2.366, over 5502580.30 frames. , ppl: 10.659030313088389], batch size: 70
+2022-12-10 06:08:00,615 INFO [train.py:421] (7/8) Epoch 1, batch 67800, loss[loss=2.633, over 910.00 frames. , ppl: 13.918549426653126] tot_loss[loss=2.365, over 5541312.23 frames. , ppl: 10.64678623922872], batch size: 70
+2022-12-10 06:09:41,544 INFO [train.py:421] (7/8) Epoch 1, batch 68000, loss[loss=2.342, over 3990.00 frames. , ppl: 10.401587218376857] tot_loss[loss=2.366, over 5509377.75 frames. , ppl: 10.658518224271246], batch size: 70
+2022-12-10 06:09:41,545 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 06:09:42,303 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.35, over 211138.00 frames. , ppl: 10.481405758605055
+2022-12-10 06:11:26,715 INFO [train.py:421] (7/8) Epoch 1, batch 68200, loss[loss=2.38, over 3010.00 frames. , ppl: 10.807384367129409] tot_loss[loss=2.366, over 5559382.27 frames. , ppl: 10.651871798100057], batch size: 70
+2022-12-10 06:13:04,727 INFO [train.py:421] (7/8) Epoch 1, batch 68400, loss[loss=2.614, over 980.00 frames. , ppl: 13.657307861934925] tot_loss[loss=2.365, over 5577496.96 frames. , ppl: 10.640659338945827], batch size: 70
+2022-12-10 06:14:45,540 INFO [train.py:421] (7/8) Epoch 1, batch 68600, loss[loss=2.68, over 980.00 frames. , ppl: 14.591648119144256] tot_loss[loss=2.366, over 5518342.84 frames. , ppl: 10.655792940258065], batch size: 70
+2022-12-10 06:16:28,499 INFO [train.py:421] (7/8) Epoch 1, batch 68800, loss[loss=2.347, over 3570.00 frames. , ppl: 10.454517736883284] tot_loss[loss=2.367, over 5482269.38 frames. , ppl: 10.662935500522968], batch size: 70
+2022-12-10 06:18:08,237 INFO [train.py:421] (7/8) Epoch 1, batch 69000, loss[loss=2.332, over 3430.00 frames. , ppl: 10.295749739751987] tot_loss[loss=2.367, over 5481144.78 frames. , ppl: 10.664968433853213], batch size: 70
+2022-12-10 06:18:08,238 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 06:18:08,996 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.348, over 211138.00 frames. , ppl: 10.467406639264686
+2022-12-10 06:19:44,539 INFO [train.py:421] (7/8) Epoch 1, batch 69200, loss[loss=2.365, over 2170.00 frames. , ppl: 10.64599720035391] tot_loss[loss=2.366, over 5491474.93 frames. , ppl: 10.657319810631549], batch size: 70
+2022-12-10 06:21:26,219 INFO [train.py:421] (7/8) Epoch 1, batch 69400, loss[loss=2.337, over 3640.00 frames. , ppl: 10.348086780494052] tot_loss[loss=2.365, over 5521266.12 frames. , ppl: 10.647151018346491], batch size: 70
+2022-12-10 06:23:06,573 INFO [train.py:421] (7/8) Epoch 1, batch 69600, loss[loss=2.302, over 5600.00 frames. , ppl: 9.997825715509641] tot_loss[loss=2.365, over 5533204.21 frames. , ppl: 10.641678832078867], batch size: 70
+2022-12-10 06:24:43,354 INFO [train.py:421] (7/8) Epoch 1, batch 69800, loss[loss=2.34, over 2870.00 frames. , ppl: 10.384632793614744] tot_loss[loss=2.366, over 5493644.23 frames. , ppl: 10.65689533049981], batch size: 70
+2022-12-10 06:26:25,254 INFO [train.py:421] (7/8) Epoch 1, batch 70000, loss[loss=2.144, over 3220.00 frames. , ppl: 8.536722770461946] tot_loss[loss=2.364, over 5539453.56 frames. , ppl: 10.63725539651651], batch size: 70
+2022-12-10 06:26:25,255 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 06:26:26,013 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.348, over 211138.00 frames. , ppl: 10.463410326196138
+2022-12-10 06:28:04,630 INFO [train.py:421] (7/8) Epoch 1, batch 70200, loss[loss=2.268, over 12950.00 frames. , ppl: 9.658500815713293] tot_loss[loss=2.363, over 5545366.10 frames. , ppl: 10.625559730519255], batch size: 70
+2022-12-10 06:29:39,961 INFO [train.py:421] (7/8) Epoch 1, batch 70400, loss[loss=2.457, over 1820.00 frames. , ppl: 11.67065607373612] tot_loss[loss=2.364, over 5514448.51 frames. , ppl: 10.636535138523291], batch size: 70
+2022-12-10 06:31:16,085 INFO [train.py:421] (7/8) Epoch 1, batch 70600, loss[loss=2.638, over 980.00 frames. , ppl: 13.985626643774953] tot_loss[loss=2.365, over 5478056.36 frames. , ppl: 10.648749000849467], batch size: 70
+2022-12-10 06:32:52,997 INFO [train.py:421] (7/8) Epoch 1, batch 70800, loss[loss=2.33, over 2800.00 frames. , ppl: 10.27543257625546] tot_loss[loss=2.366, over 5455204.13 frames. , ppl: 10.654762291302259], batch size: 70
+2022-12-10 06:34:35,544 INFO [train.py:421] (7/8) Epoch 1, batch 71000, loss[loss=2.485, over 2310.00 frames. , ppl: 11.99581756307268] tot_loss[loss=2.366, over 5452128.22 frames. , ppl: 10.65569735887198], batch size: 70
+2022-12-10 06:34:35,545 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 06:34:36,305 INFO [train.py:452] (7/8) Epoch 1, validation: loss=2.347, over 211138.00 frames. , ppl: 10.45096802929164
+2022-12-10 06:36:12,871 INFO [train.py:421] (7/8) Epoch 1, batch 71200, loss[loss=2.636, over 1120.00 frames. , ppl: 13.954090695170052] tot_loss[loss=2.366, over 5452509.83 frames. , ppl: 10.654487593315075], batch size: 70
+2022-12-10 06:37:52,690 INFO [train.py:421] (7/8) Epoch 1, batch 71400, loss[loss=2.311, over 3920.00 frames. , ppl: 10.079496172023138] tot_loss[loss=2.367, over 5426825.00 frames. , ppl: 10.66116239320255], batch size: 70
+2022-12-10 06:39:34,127 INFO [train.py:421] (7/8) Epoch 1, batch 71600, loss[loss=2.426, over 1890.00 frames. , ppl: 11.312217068543122] tot_loss[loss=2.366, over 5441432.74 frames. , ppl: 10.658869700767585], batch size: 70
+2022-12-10 06:41:16,767 INFO [train.py:421] (7/8) Epoch 1, batch 71800, loss[loss=2.33, over 3500.00 frames. , ppl: 10.282103450574663] tot_loss[loss=2.366, over 5478366.54 frames. , ppl: 10.652116309798977], batch size: 70
+2022-12-10 06:42:32,558 INFO [train.py:421] (7/8) Epoch 2, batch 0, loss[loss=2.458, over 1400.00 frames. , ppl: 11.67697677043208] tot_loss[loss=2.458, over 1400.00 frames. , ppl: 11.67697677043208], batch size: 70
+2022-12-10 06:44:11,584 INFO [train.py:421] (7/8) Epoch 2, batch 200, loss[loss=2.476, over 1400.00 frames. , ppl: 11.89534665861467] tot_loss[loss=2.368, over 490805.35 frames. , ppl: 10.672599861107978], batch size: 70
+2022-12-10 06:45:50,262 INFO [train.py:421] (7/8) Epoch 2, batch 400, loss[loss=2.251, over 3990.00 frames. , ppl: 9.494281904149128] tot_loss[loss=2.355, over 1009854.53 frames. , ppl: 10.537390006371043], batch size: 70
+2022-12-10 06:47:30,623 INFO [train.py:421] (7/8) Epoch 2, batch 600, loss[loss=2.255, over 9100.00 frames. , ppl: 9.531520215658153] tot_loss[loss=2.355, over 1435583.80 frames. , ppl: 10.536003892785295], batch size: 70
+2022-12-10 06:49:11,826 INFO [train.py:421] (7/8) Epoch 2, batch 800, loss[loss=2.259, over 5040.00 frames. , ppl: 9.57319619281577] tot_loss[loss=2.352, over 1823412.92 frames. , ppl: 10.50932637958097], batch size: 70
+2022-12-10 06:50:52,992 INFO [train.py:421] (7/8) Epoch 2, batch 1000, loss[loss=2.488, over 1330.00 frames. , ppl: 12.03433240353994] tot_loss[loss=2.355, over 2149692.82 frames. , ppl: 10.534889050040354], batch size: 70
+2022-12-10 06:50:52,993 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 06:50:53,753 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.346, over 211138.00 frames. , ppl: 10.441904495381296
+2022-12-10 06:52:33,146 INFO [train.py:421] (7/8) Epoch 2, batch 1200, loss[loss=2.311, over 5320.00 frames. , ppl: 10.085486241526283] tot_loss[loss=2.355, over 2488287.91 frames. , ppl: 10.533052806789156], batch size: 70
+2022-12-10 06:54:14,267 INFO [train.py:421] (7/8) Epoch 2, batch 1400, loss[loss=2.468, over 2450.00 frames. , ppl: 11.79548506608011] tot_loss[loss=2.355, over 2777673.16 frames. , ppl: 10.539644992185393], batch size: 70
+2022-12-10 06:55:55,748 INFO [train.py:421] (7/8) Epoch 2, batch 1600, loss[loss=2.541, over 1540.00 frames. , ppl: 12.687980414227681] tot_loss[loss=2.356, over 3023993.85 frames. , ppl: 10.552621298489075], batch size: 70
+2022-12-10 06:57:35,279 INFO [train.py:421] (7/8) Epoch 2, batch 1800, loss[loss=2.326, over 5390.00 frames. , ppl: 10.23371786987953] tot_loss[loss=2.356, over 3232194.15 frames. , ppl: 10.547473498727662], batch size: 70
+2022-12-10 06:59:14,994 INFO [train.py:421] (7/8) Epoch 2, batch 2000, loss[loss=2.433, over 1820.00 frames. , ppl: 11.394627309862887] tot_loss[loss=2.356, over 3428651.80 frames. , ppl: 10.552283479246753], batch size: 70
+2022-12-10 06:59:14,994 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 06:59:15,754 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.345, over 211138.00 frames. , ppl: 10.430619322580018
+2022-12-10 07:00:58,121 INFO [train.py:421] (7/8) Epoch 2, batch 2200, loss[loss=2.248, over 5600.00 frames. , ppl: 9.467301267096197] tot_loss[loss=2.356, over 3625531.13 frames. , ppl: 10.547672453299564], batch size: 70
+2022-12-10 07:02:37,018 INFO [train.py:421] (7/8) Epoch 2, batch 2400, loss[loss=2.339, over 2170.00 frames. , ppl: 10.37313779172031] tot_loss[loss=2.357, over 3778330.77 frames. , ppl: 10.556293879473557], batch size: 70
+2022-12-10 07:04:16,524 INFO [train.py:421] (7/8) Epoch 2, batch 2600, loss[loss=2.308, over 2590.00 frames. , ppl: 10.058006937607262] tot_loss[loss=2.357, over 3934133.98 frames. , ppl: 10.55940792405715], batch size: 70
+2022-12-10 07:05:57,379 INFO [train.py:421] (7/8) Epoch 2, batch 2800, loss[loss=2.229, over 3290.00 frames. , ppl: 9.288110384321769] tot_loss[loss=2.357, over 4118643.73 frames. , ppl: 10.557600718160154], batch size: 70
+2022-12-10 07:07:34,886 INFO [train.py:421] (7/8) Epoch 2, batch 3000, loss[loss=2.308, over 4410.00 frames. , ppl: 10.049481904138275] tot_loss[loss=2.356, over 4271239.92 frames. , ppl: 10.551789001145226], batch size: 70
+2022-12-10 07:07:34,887 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 07:07:35,617 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.346, over 211138.00 frames. , ppl: 10.439906381190209
+2022-12-10 07:09:13,505 INFO [train.py:421] (7/8) Epoch 2, batch 3200, loss[loss=2.381, over 1540.00 frames. , ppl: 10.814072310637854] tot_loss[loss=2.356, over 4383770.07 frames. , ppl: 10.551168750178563], batch size: 70
+2022-12-10 07:10:54,075 INFO [train.py:421] (7/8) Epoch 2, batch 3400, loss[loss=2.325, over 2450.00 frames. , ppl: 10.2243262799627] tot_loss[loss=2.356, over 4487702.91 frames. , ppl: 10.543897365052622], batch size: 70
+2022-12-10 07:12:38,051 INFO [train.py:421] (7/8) Epoch 2, batch 3600, loss[loss=2.428, over 1400.00 frames. , ppl: 11.331777074895266] tot_loss[loss=2.355, over 4611313.27 frames. , ppl: 10.533729241373155], batch size: 70
+2022-12-10 07:14:17,882 INFO [train.py:421] (7/8) Epoch 2, batch 3800, loss[loss=2.334, over 3780.00 frames. , ppl: 10.32299803312745] tot_loss[loss=2.354, over 4745810.45 frames. , ppl: 10.523849275271848], batch size: 70
+2022-12-10 07:15:59,665 INFO [train.py:421] (7/8) Epoch 2, batch 4000, loss[loss=2.293, over 5110.00 frames. , ppl: 9.90362365085803] tot_loss[loss=2.353, over 4866438.32 frames. , ppl: 10.517815781598006], batch size: 70
+2022-12-10 07:15:59,665 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 07:16:00,395 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.345, over 211138.00 frames. , ppl: 10.432709850132296
+2022-12-10 07:17:44,081 INFO [train.py:421] (7/8) Epoch 2, batch 4200, loss[loss=2.24, over 5460.00 frames. , ppl: 9.393590693631406] tot_loss[loss=2.352, over 4949435.05 frames. , ppl: 10.511067591544391], batch size: 70
+2022-12-10 07:19:26,559 INFO [train.py:421] (7/8) Epoch 2, batch 4400, loss[loss=2.562, over 1400.00 frames. , ppl: 12.963584730227854] tot_loss[loss=2.353, over 4983902.84 frames. , ppl: 10.517367638826665], batch size: 70
+2022-12-10 07:21:09,715 INFO [train.py:421] (7/8) Epoch 2, batch 4600, loss[loss=2.339, over 4340.00 frames. , ppl: 10.374015452472305] tot_loss[loss=2.353, over 5044160.10 frames. , ppl: 10.518571409732324], batch size: 70
+2022-12-10 07:22:49,463 INFO [train.py:421] (7/8) Epoch 2, batch 4800, loss[loss=2.29, over 13370.00 frames. , ppl: 9.875663891090076] tot_loss[loss=2.355, over 5058333.32 frames. , ppl: 10.53432260680123], batch size: 70
+2022-12-10 07:24:27,422 INFO [train.py:421] (7/8) Epoch 2, batch 5000, loss[loss=2.408, over 3220.00 frames. , ppl: 11.113487409490387] tot_loss[loss=2.356, over 5068291.23 frames. , ppl: 10.549531285443635], batch size: 70
+2022-12-10 07:24:27,423 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 07:24:28,168 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.343, over 211138.00 frames. , ppl: 10.417051893133054
+2022-12-10 07:26:10,651 INFO [train.py:421] (7/8) Epoch 2, batch 5200, loss[loss=2.524, over 1120.00 frames. , ppl: 12.478534430258371] tot_loss[loss=2.355, over 5122864.23 frames. , ppl: 10.542772710410098], batch size: 70
+2022-12-10 07:27:50,416 INFO [train.py:421] (7/8) Epoch 2, batch 5400, loss[loss=2.519, over 840.00 frames. , ppl: 12.414737529607178] tot_loss[loss=2.357, over 5132139.36 frames. , ppl: 10.55498963700956], batch size: 70
+2022-12-10 07:29:28,162 INFO [train.py:421] (7/8) Epoch 2, batch 5600, loss[loss=2.273, over 5670.00 frames. , ppl: 9.707620107554986] tot_loss[loss=2.358, over 5142174.31 frames. , ppl: 10.567400415271472], batch size: 70
+2022-12-10 07:31:06,308 INFO [train.py:421] (7/8) Epoch 2, batch 5800, loss[loss=2.54, over 1680.00 frames. , ppl: 12.683483582277118] tot_loss[loss=2.358, over 5164451.58 frames. , ppl: 10.568606265895216], batch size: 70
+2022-12-10 07:32:43,836 INFO [train.py:421] (7/8) Epoch 2, batch 6000, loss[loss=2.235, over 9590.00 frames. , ppl: 9.346434644785644] tot_loss[loss=2.359, over 5131488.20 frames. , ppl: 10.583588660980624], batch size: 70
+2022-12-10 07:32:43,837 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 07:32:44,567 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.343, over 211138.00 frames. , ppl: 10.413985701421621
+2022-12-10 07:34:23,915 INFO [train.py:421] (7/8) Epoch 2, batch 6200, loss[loss=2.333, over 3990.00 frames. , ppl: 10.306470182584778] tot_loss[loss=2.359, over 5149298.38 frames. , ppl: 10.582217256280021], batch size: 70
+2022-12-10 07:36:04,957 INFO [train.py:421] (7/8) Epoch 2, batch 6400, loss[loss=2.629, over 770.00 frames. , ppl: 13.854440988213693] tot_loss[loss=2.359, over 5172654.33 frames. , ppl: 10.582878377582656], batch size: 70
+2022-12-10 07:37:46,139 INFO [train.py:421] (7/8) Epoch 2, batch 6600, loss[loss=2.58, over 1050.00 frames. , ppl: 13.199117510578581] tot_loss[loss=2.36, over 5179260.26 frames. , ppl: 10.59018441097971], batch size: 70
+2022-12-10 07:39:25,818 INFO [train.py:421] (7/8) Epoch 2, batch 6800, loss[loss=2.302, over 8820.00 frames. , ppl: 9.997046685953835] tot_loss[loss=2.359, over 5218119.84 frames. , ppl: 10.584447759967995], batch size: 70
+2022-12-10 07:41:05,168 INFO [train.py:421] (7/8) Epoch 2, batch 7000, loss[loss=3.326, over 490.00 frames. , ppl: 27.840581947110845] tot_loss[loss=2.359, over 5251843.28 frames. , ppl: 10.581834904627861], batch size: 70
+2022-12-10 07:41:05,169 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 07:41:05,947 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.342, over 211138.00 frames. , ppl: 10.402274966255137
+2022-12-10 07:42:45,100 INFO [train.py:421] (7/8) Epoch 2, batch 7200, loss[loss=2.482, over 1330.00 frames. , ppl: 11.96879155284656] tot_loss[loss=2.357, over 5306117.56 frames. , ppl: 10.56444066227302], batch size: 70
+2022-12-10 07:44:25,831 INFO [train.py:421] (7/8) Epoch 2, batch 7400, loss[loss=2.365, over 5530.00 frames. , ppl: 10.639962972110885] tot_loss[loss=2.358, over 5316246.96 frames. , ppl: 10.570304916573702], batch size: 70
+2022-12-10 07:46:04,861 INFO [train.py:421] (7/8) Epoch 2, batch 7600, loss[loss=2.567, over 840.00 frames. , ppl: 13.020614633508709] tot_loss[loss=2.358, over 5332156.06 frames. , ppl: 10.570371639447885], batch size: 70
+2022-12-10 07:47:41,317 INFO [train.py:421] (7/8) Epoch 2, batch 7800, loss[loss=5.013, over 280.00 frames. , ppl: 150.42810791814702] tot_loss[loss=2.36, over 5276549.04 frames. , ppl: 10.588541302558298], batch size: 70
+2022-12-10 07:49:26,401 INFO [train.py:421] (7/8) Epoch 2, batch 8000, loss[loss=2.488, over 1750.00 frames. , ppl: 12.0406341574119] tot_loss[loss=2.359, over 5303175.78 frames. , ppl: 10.585127458996004], batch size: 70
+2022-12-10 07:49:26,402 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 07:49:27,161 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.343, over 211138.00 frames. , ppl: 10.408854278509716
+2022-12-10 07:51:05,854 INFO [train.py:421] (7/8) Epoch 2, batch 8200, loss[loss=2.399, over 2240.00 frames. , ppl: 11.012632863098588] tot_loss[loss=2.36, over 5296123.20 frames. , ppl: 10.593374954579884], batch size: 70
+2022-12-10 07:52:44,237 INFO [train.py:421] (7/8) Epoch 2, batch 8400, loss[loss=2.542, over 1400.00 frames. , ppl: 12.707677440717827] tot_loss[loss=2.361, over 5301231.12 frames. , ppl: 10.600015252750218], batch size: 70
+2022-12-10 07:54:24,069 INFO [train.py:421] (7/8) Epoch 2, batch 8600, loss[loss=2.402, over 3080.00 frames. , ppl: 11.044550215977134] tot_loss[loss=2.361, over 5297813.70 frames. , ppl: 10.600444973708921], batch size: 70
+2022-12-10 07:56:01,957 INFO [train.py:421] (7/8) Epoch 2, batch 8800, loss[loss=2.428, over 2170.00 frames. , ppl: 11.33775209658218] tot_loss[loss=2.361, over 5285989.16 frames. , ppl: 10.601061995703896], batch size: 70
+2022-12-10 07:57:42,039 INFO [train.py:421] (7/8) Epoch 2, batch 9000, loss[loss=2.248, over 6720.00 frames. , ppl: 9.464097283746902] tot_loss[loss=2.359, over 5347130.03 frames. , ppl: 10.57592477458189], batch size: 70
+2022-12-10 07:57:42,039 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 07:57:42,768 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.342, over 211138.00 frames. , ppl: 10.399154636076556
+2022-12-10 07:59:22,477 INFO [train.py:421] (7/8) Epoch 2, batch 9200, loss[loss=2.355, over 3150.00 frames. , ppl: 10.54231475702048] tot_loss[loss=2.358, over 5373495.35 frames. , ppl: 10.568655659536232], batch size: 70
+2022-12-10 08:00:56,951 INFO [train.py:421] (7/8) Epoch 2, batch 9400, loss[loss=2.302, over 3430.00 frames. , ppl: 9.99156277626161] tot_loss[loss=2.357, over 5431547.38 frames. , ppl: 10.558344157080752], batch size: 70
+2022-12-10 08:02:37,356 INFO [train.py:421] (7/8) Epoch 2, batch 9600, loss[loss=2.459, over 1400.00 frames. , ppl: 11.696103122433362] tot_loss[loss=2.354, over 5522540.84 frames. , ppl: 10.524940840689366], batch size: 70
+2022-12-10 08:04:17,627 INFO [train.py:421] (7/8) Epoch 2, batch 9800, loss[loss=2.848, over 910.00 frames. , ppl: 17.24621443107462] tot_loss[loss=2.355, over 5506505.82 frames. , ppl: 10.534975951540996], batch size: 70
+2022-12-10 08:06:01,214 INFO [train.py:421] (7/8) Epoch 2, batch 10000, loss[loss=2.421, over 3360.00 frames. , ppl: 11.251811915132471] tot_loss[loss=2.355, over 5504013.47 frames. , ppl: 10.538220270253161], batch size: 70
+2022-12-10 08:06:01,215 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 08:06:01,975 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.343, over 211138.00 frames. , ppl: 10.415013831030345
+2022-12-10 08:07:39,460 INFO [train.py:421] (7/8) Epoch 2, batch 10200, loss[loss=2.302, over 4410.00 frames. , ppl: 9.998078357609833] tot_loss[loss=2.355, over 5506914.88 frames. , ppl: 10.542314004709533], batch size: 70
+2022-12-10 08:09:21,337 INFO [train.py:421] (7/8) Epoch 2, batch 10400, loss[loss=2.499, over 980.00 frames. , ppl: 12.164794917228676] tot_loss[loss=2.355, over 5524874.01 frames. , ppl: 10.53576125477356], batch size: 70
+2022-12-10 08:11:01,467 INFO [train.py:421] (7/8) Epoch 2, batch 10600, loss[loss=2.58, over 1330.00 frames. , ppl: 13.202247283491847] tot_loss[loss=2.355, over 5531869.39 frames. , ppl: 10.535047552287445], batch size: 70
+2022-12-10 08:12:42,387 INFO [train.py:421] (7/8) Epoch 2, batch 10800, loss[loss=2.4, over 2590.00 frames. , ppl: 11.018954387137029] tot_loss[loss=2.354, over 5542005.20 frames. , ppl: 10.53191091044722], batch size: 70
+2022-12-10 08:14:21,837 INFO [train.py:421] (7/8) Epoch 2, batch 11000, loss[loss=2.286, over 3570.00 frames. , ppl: 9.836821845633528] tot_loss[loss=2.354, over 5558666.45 frames. , ppl: 10.525197661989054], batch size: 70
+2022-12-10 08:14:21,838 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 08:14:22,596 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.342, over 211138.00 frames. , ppl: 10.400310603854379
+2022-12-10 08:16:01,434 INFO [train.py:421] (7/8) Epoch 2, batch 11200, loss[loss=2.431, over 1960.00 frames. , ppl: 11.368585506834915] tot_loss[loss=2.355, over 5512769.06 frames. , ppl: 10.535483379600235], batch size: 70
+2022-12-10 08:17:42,444 INFO [train.py:421] (7/8) Epoch 2, batch 11400, loss[loss=2.28, over 5110.00 frames. , ppl: 9.772669397562025] tot_loss[loss=2.354, over 5516281.83 frames. , ppl: 10.531615460993093], batch size: 70
+2022-12-10 08:19:25,308 INFO [train.py:421] (7/8) Epoch 2, batch 11600, loss[loss=2.576, over 1050.00 frames. , ppl: 13.147778252653472] tot_loss[loss=2.355, over 5508977.05 frames. , ppl: 10.533914615890968], batch size: 70
+2022-12-10 08:21:08,342 INFO [train.py:421] (7/8) Epoch 2, batch 11800, loss[loss=2.459, over 1470.00 frames. , ppl: 11.69616178646931] tot_loss[loss=2.355, over 5511469.58 frames. , ppl: 10.535444315867942], batch size: 70
+2022-12-10 08:22:51,114 INFO [train.py:421] (7/8) Epoch 2, batch 12000, loss[loss=2.264, over 3360.00 frames. , ppl: 9.625805863737176] tot_loss[loss=2.353, over 5529447.53 frames. , ppl: 10.519395433340469], batch size: 70
+2022-12-10 08:22:51,114 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 08:22:51,875 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.342, over 211138.00 frames. , ppl: 10.405858265858988
+2022-12-10 08:24:33,719 INFO [train.py:421] (7/8) Epoch 2, batch 12200, loss[loss=2.347, over 2800.00 frames. , ppl: 10.452135293594583] tot_loss[loss=2.353, over 5558187.83 frames. , ppl: 10.51417533461839], batch size: 70
+2022-12-10 08:26:16,321 INFO [train.py:421] (7/8) Epoch 2, batch 12400, loss[loss=2.336, over 4410.00 frames. , ppl: 10.3404534528957] tot_loss[loss=2.352, over 5561962.90 frames. , ppl: 10.509561746329165], batch size: 70
+2022-12-10 08:27:55,050 INFO [train.py:421] (7/8) Epoch 2, batch 12600, loss[loss=2.333, over 2170.00 frames. , ppl: 10.305430259213736] tot_loss[loss=2.353, over 5512718.06 frames. , ppl: 10.517799728756803], batch size: 70
+2022-12-10 08:29:33,546 INFO [train.py:421] (7/8) Epoch 2, batch 12800, loss[loss=2.388, over 1750.00 frames. , ppl: 10.895944164602684] tot_loss[loss=2.352, over 5534933.46 frames. , ppl: 10.508362240978377], batch size: 70
+2022-12-10 08:31:14,851 INFO [train.py:421] (7/8) Epoch 2, batch 13000, loss[loss=2.38, over 2450.00 frames. , ppl: 10.803453722512964] tot_loss[loss=2.352, over 5568585.86 frames. , ppl: 10.506275161221904], batch size: 70
+2022-12-10 08:31:14,851 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 08:31:15,609 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.345, over 211138.00 frames. , ppl: 10.435761475361208
+2022-12-10 08:32:58,530 INFO [train.py:421] (7/8) Epoch 2, batch 13200, loss[loss=2.631, over 840.00 frames. , ppl: 13.886932804090275] tot_loss[loss=2.352, over 5555380.89 frames. , ppl: 10.506539257433507], batch size: 70
+2022-12-10 08:34:37,207 INFO [train.py:421] (7/8) Epoch 2, batch 13400, loss[loss=2.354, over 3290.00 frames. , ppl: 10.530449902396795] tot_loss[loss=2.352, over 5563556.54 frames. , ppl: 10.507722463122528], batch size: 70
+2022-12-10 08:36:18,009 INFO [train.py:421] (7/8) Epoch 2, batch 13600, loss[loss=2.242, over 8890.00 frames. , ppl: 9.413312264429878] tot_loss[loss=2.352, over 5572831.36 frames. , ppl: 10.504412395913674], batch size: 70
+2022-12-10 08:38:00,747 INFO [train.py:421] (7/8) Epoch 2, batch 13800, loss[loss=2.302, over 11690.00 frames. , ppl: 9.99786247486871] tot_loss[loss=2.352, over 5545888.22 frames. , ppl: 10.509920462941821], batch size: 70
+2022-12-10 08:39:39,900 INFO [train.py:421] (7/8) Epoch 2, batch 14000, loss[loss=2.41, over 1050.00 frames. , ppl: 11.138673779337708] tot_loss[loss=2.353, over 5517298.07 frames. , ppl: 10.514326979780694], batch size: 70
+2022-12-10 08:39:39,901 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 08:39:40,646 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.34, over 211138.00 frames. , ppl: 10.38519312924439
+2022-12-10 08:41:22,077 INFO [train.py:421] (7/8) Epoch 2, batch 14200, loss[loss=2.54, over 1400.00 frames. , ppl: 12.68546553142259] tot_loss[loss=2.354, over 5462871.32 frames. , ppl: 10.532255107365824], batch size: 70
+2022-12-10 08:43:05,915 INFO [train.py:421] (7/8) Epoch 2, batch 14400, loss[loss=2.839, over 700.00 frames. , ppl: 17.099616694174884] tot_loss[loss=2.355, over 5471731.57 frames. , ppl: 10.535796660128048], batch size: 70
+2022-12-10 08:44:46,235 INFO [train.py:421] (7/8) Epoch 2, batch 14600, loss[loss=2.741, over 700.00 frames. , ppl: 15.500197229465533] tot_loss[loss=2.354, over 5519489.87 frames. , ppl: 10.52402017472037], batch size: 70
+2022-12-10 08:46:23,519 INFO [train.py:421] (7/8) Epoch 2, batch 14800, loss[loss=2.735, over 700.00 frames. , ppl: 15.405535783257955] tot_loss[loss=2.353, over 5532454.98 frames. , ppl: 10.521139097026866], batch size: 70
+2022-12-10 08:48:03,536 INFO [train.py:421] (7/8) Epoch 2, batch 15000, loss[loss=2.351, over 3640.00 frames. , ppl: 10.495138749971685] tot_loss[loss=2.354, over 5534389.76 frames. , ppl: 10.52638987302624], batch size: 70
+2022-12-10 08:48:03,536 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 08:48:04,267 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.339, over 211138.00 frames. , ppl: 10.36868412657422
+2022-12-10 08:49:43,367 INFO [train.py:421] (7/8) Epoch 2, batch 15200, loss[loss=6.268, over 210.00 frames. , ppl: 527.6349781685497] tot_loss[loss=2.354, over 5557424.08 frames. , ppl: 10.522790459783064], batch size: 70
+2022-12-10 08:51:24,497 INFO [train.py:421] (7/8) Epoch 2, batch 15400, loss[loss=2.341, over 2730.00 frames. , ppl: 10.388603840690958] tot_loss[loss=2.354, over 5535768.83 frames. , ppl: 10.530192709293905], batch size: 70
+2022-12-10 08:53:07,426 INFO [train.py:421] (7/8) Epoch 2, batch 15600, loss[loss=2.42, over 1330.00 frames. , ppl: 11.25118533218449] tot_loss[loss=2.354, over 5540213.98 frames. , ppl: 10.52694347051626], batch size: 70
+2022-12-10 08:54:45,435 INFO [train.py:421] (7/8) Epoch 2, batch 15800, loss[loss=2.555, over 980.00 frames. , ppl: 12.874864538632828] tot_loss[loss=2.355, over 5507404.90 frames. , ppl: 10.535845973724681], batch size: 70
+2022-12-10 08:56:24,668 INFO [train.py:421] (7/8) Epoch 2, batch 16000, loss[loss=2.277, over 4130.00 frames. , ppl: 9.74741911938123] tot_loss[loss=2.355, over 5487331.61 frames. , ppl: 10.536897180389438], batch size: 70
+2022-12-10 08:56:24,668 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 08:56:25,397 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.34, over 211138.00 frames. , ppl: 10.380303272822726
+2022-12-10 08:58:07,185 INFO [train.py:421] (7/8) Epoch 2, batch 16200, loss[loss=2.279, over 5810.00 frames. , ppl: 9.763885555241204] tot_loss[loss=2.354, over 5508077.11 frames. , ppl: 10.523135327479938], batch size: 70
+2022-12-10 08:59:47,489 INFO [train.py:421] (7/8) Epoch 2, batch 16400, loss[loss=2.333, over 3570.00 frames. , ppl: 10.306296871089716] tot_loss[loss=2.353, over 5517207.19 frames. , ppl: 10.521434652510207], batch size: 70
+2022-12-10 09:01:27,415 INFO [train.py:421] (7/8) Epoch 2, batch 16600, loss[loss=2.343, over 2240.00 frames. , ppl: 10.413041332303077] tot_loss[loss=2.354, over 5497781.18 frames. , ppl: 10.530043143049015], batch size: 70
+2022-12-10 09:03:04,464 INFO [train.py:421] (7/8) Epoch 2, batch 16800, loss[loss=2.491, over 1890.00 frames. , ppl: 12.077918462039182] tot_loss[loss=2.354, over 5499689.35 frames. , ppl: 10.526593506391428], batch size: 70
+2022-12-10 09:04:43,292 INFO [train.py:421] (7/8) Epoch 2, batch 17000, loss[loss=2.364, over 2380.00 frames. , ppl: 10.632843032827022] tot_loss[loss=2.354, over 5466858.85 frames. , ppl: 10.527101500412197], batch size: 70
+2022-12-10 09:04:43,292 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 09:04:44,079 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.34, over 211138.00 frames. , ppl: 10.380625913933697
+2022-12-10 09:06:22,856 INFO [train.py:421] (7/8) Epoch 2, batch 17200, loss[loss=2.522, over 1190.00 frames. , ppl: 12.454466823252165] tot_loss[loss=2.354, over 5467175.75 frames. , ppl: 10.52441087717581], batch size: 70
+2022-12-10 09:08:07,700 INFO [train.py:421] (7/8) Epoch 2, batch 17400, loss[loss=2.366, over 3850.00 frames. , ppl: 10.653892567528898] tot_loss[loss=2.353, over 5494734.65 frames. , ppl: 10.517771490419594], batch size: 70
+2022-12-10 09:09:46,650 INFO [train.py:421] (7/8) Epoch 2, batch 17600, loss[loss=2.601, over 1610.00 frames. , ppl: 13.477338159199835] tot_loss[loss=2.353, over 5495400.64 frames. , ppl: 10.521444248044286], batch size: 70
+2022-12-10 09:11:23,695 INFO [train.py:421] (7/8) Epoch 2, batch 17800, loss[loss=2.267, over 4200.00 frames. , ppl: 9.651542484548022] tot_loss[loss=2.354, over 5474829.87 frames. , ppl: 10.522517361884999], batch size: 70
+2022-12-10 09:13:01,349 INFO [train.py:421] (7/8) Epoch 2, batch 18000, loss[loss=2.388, over 3150.00 frames. , ppl: 10.88775636782634] tot_loss[loss=2.353, over 5488221.58 frames. , ppl: 10.519040793725765], batch size: 70
+2022-12-10 09:13:01,349 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 09:13:02,108 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.339, over 211138.00 frames. , ppl: 10.371116820501767
+2022-12-10 09:14:39,902 INFO [train.py:421] (7/8) Epoch 2, batch 18200, loss[loss=2.339, over 3010.00 frames. , ppl: 10.367982871369074] tot_loss[loss=2.354, over 5450618.61 frames. , ppl: 10.525579876270863], batch size: 70
+2022-12-10 09:16:18,861 INFO [train.py:421] (7/8) Epoch 2, batch 18400, loss[loss=2.205, over 4830.00 frames. , ppl: 9.070965711029446] tot_loss[loss=2.353, over 5466317.77 frames. , ppl: 10.519085911367753], batch size: 70
+2022-12-10 09:17:58,063 INFO [train.py:421] (7/8) Epoch 2, batch 18600, loss[loss=2.426, over 3010.00 frames. , ppl: 11.310292113979507] tot_loss[loss=2.354, over 5449090.70 frames. , ppl: 10.522985013015198], batch size: 70
+2022-12-10 09:19:35,460 INFO [train.py:421] (7/8) Epoch 2, batch 18800, loss[loss=2.237, over 4620.00 frames. , ppl: 9.369855502604233] tot_loss[loss=2.353, over 5456527.42 frames. , ppl: 10.513909143881232], batch size: 70
+2022-12-10 09:21:19,017 INFO [train.py:421] (7/8) Epoch 2, batch 19000, loss[loss=2.888, over 700.00 frames. , ppl: 17.960674899065] tot_loss[loss=2.352, over 5472375.63 frames. , ppl: 10.507189420936792], batch size: 70
+2022-12-10 09:21:19,018 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 09:21:19,781 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.337, over 211138.00 frames. , ppl: 10.346198405029323
+2022-12-10 09:23:00,683 INFO [train.py:421] (7/8) Epoch 2, batch 19200, loss[loss=2.428, over 840.00 frames. , ppl: 11.336289421010518] tot_loss[loss=2.352, over 5470389.67 frames. , ppl: 10.509082430836116], batch size: 70
+2022-12-10 09:24:40,866 INFO [train.py:421] (7/8) Epoch 2, batch 19400, loss[loss=2.622, over 910.00 frames. , ppl: 13.762410494576867] tot_loss[loss=2.353, over 5448724.64 frames. , ppl: 10.519769332762593], batch size: 70
+2022-12-10 09:26:20,690 INFO [train.py:421] (7/8) Epoch 2, batch 19600, loss[loss=2.498, over 980.00 frames. , ppl: 12.162285896127697] tot_loss[loss=2.353, over 5476425.64 frames. , ppl: 10.512779736383298], batch size: 70
+2022-12-10 09:28:00,786 INFO [train.py:421] (7/8) Epoch 2, batch 19800, loss[loss=2.34, over 3570.00 frames. , ppl: 10.380662380094803] tot_loss[loss=2.353, over 5474029.26 frames. , ppl: 10.51625935126194], batch size: 70
+2022-12-10 09:29:37,936 INFO [train.py:421] (7/8) Epoch 2, batch 20000, loss[loss=2.378, over 2590.00 frames. , ppl: 10.785183160051808] tot_loss[loss=2.354, over 5439706.07 frames. , ppl: 10.530799994410575], batch size: 70
+2022-12-10 09:29:37,937 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 09:29:38,694 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.339, over 211138.00 frames. , ppl: 10.367246266120773
+2022-12-10 09:31:19,563 INFO [train.py:421] (7/8) Epoch 2, batch 20200, loss[loss=2.311, over 3990.00 frames. , ppl: 10.08389113313749] tot_loss[loss=2.353, over 5479067.10 frames. , ppl: 10.517451539216486], batch size: 70
+2022-12-10 09:32:58,820 INFO [train.py:421] (7/8) Epoch 2, batch 20400, loss[loss=2.267, over 7560.00 frames. , ppl: 9.646893274324341] tot_loss[loss=2.352, over 5501535.33 frames. , ppl: 10.511003537576375], batch size: 70
+2022-12-10 09:34:39,601 INFO [train.py:421] (7/8) Epoch 2, batch 20600, loss[loss=2.537, over 1540.00 frames. , ppl: 12.640678761329136] tot_loss[loss=2.353, over 5472622.96 frames. , ppl: 10.519897907683701], batch size: 70
+2022-12-10 09:36:18,784 INFO [train.py:421] (7/8) Epoch 2, batch 20800, loss[loss=2.418, over 1890.00 frames. , ppl: 11.22379033556837] tot_loss[loss=2.353, over 5479119.87 frames. , ppl: 10.518924430898698], batch size: 70
+2022-12-10 09:37:55,972 INFO [train.py:421] (7/8) Epoch 2, batch 21000, loss[loss=2.543, over 1120.00 frames. , ppl: 12.720488745198816] tot_loss[loss=2.354, over 5439755.37 frames. , ppl: 10.532760613202353], batch size: 70
+2022-12-10 09:37:55,973 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 09:37:56,718 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.338, over 211138.00 frames. , ppl: 10.362088796314158
+2022-12-10 09:39:34,400 INFO [train.py:421] (7/8) Epoch 2, batch 21200, loss[loss=2.474, over 1120.00 frames. , ppl: 11.872032199540149] tot_loss[loss=2.355, over 5413374.50 frames. , ppl: 10.533770878535757], batch size: 70
+2022-12-10 09:41:12,856 INFO [train.py:421] (7/8) Epoch 2, batch 21400, loss[loss=2.453, over 1890.00 frames. , ppl: 11.620755448266301] tot_loss[loss=2.355, over 5399742.32 frames. , ppl: 10.542287051789765], batch size: 70
+2022-12-10 09:42:51,083 INFO [train.py:421] (7/8) Epoch 2, batch 21600, loss[loss=2.451, over 1610.00 frames. , ppl: 11.60219867408324] tot_loss[loss=2.357, over 5344773.74 frames. , ppl: 10.555603243105985], batch size: 70
+2022-12-10 09:44:31,994 INFO [train.py:421] (7/8) Epoch 2, batch 21800, loss[loss=2.298, over 3640.00 frames. , ppl: 9.953139703145904] tot_loss[loss=2.356, over 5357921.19 frames. , ppl: 10.550720787386036], batch size: 70
+2022-12-10 09:46:13,456 INFO [train.py:421] (7/8) Epoch 2, batch 22000, loss[loss=2.451, over 1750.00 frames. , ppl: 11.60209015732586] tot_loss[loss=2.356, over 5371929.08 frames. , ppl: 10.543961323324599], batch size: 70
+2022-12-10 09:46:13,457 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 09:46:14,216 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.337, over 211138.00 frames. , ppl: 10.353811838414043
+2022-12-10 09:47:52,621 INFO [train.py:421] (7/8) Epoch 2, batch 22200, loss[loss=2.574, over 1190.00 frames. , ppl: 13.11512529218125] tot_loss[loss=2.355, over 5413573.19 frames. , ppl: 10.536611560649796], batch size: 70
+2022-12-10 09:49:28,393 INFO [train.py:421] (7/8) Epoch 2, batch 22400, loss[loss=2.431, over 1330.00 frames. , ppl: 11.366786471418497] tot_loss[loss=2.355, over 5383989.16 frames. , ppl: 10.540110229020229], batch size: 70
+2022-12-10 09:51:04,811 INFO [train.py:421] (7/8) Epoch 2, batch 22600, loss[loss=2.219, over 5180.00 frames. , ppl: 9.198389848591718] tot_loss[loss=2.355, over 5358364.31 frames. , ppl: 10.542583293411049], batch size: 70
+2022-12-10 09:52:46,964 INFO [train.py:421] (7/8) Epoch 2, batch 22800, loss[loss=2.31, over 5530.00 frames. , ppl: 10.077705454449859] tot_loss[loss=2.355, over 5376882.79 frames. , ppl: 10.541275614802782], batch size: 70
+2022-12-10 09:54:25,159 INFO [train.py:421] (7/8) Epoch 2, batch 23000, loss[loss=2.688, over 700.00 frames. , ppl: 14.70671612903508] tot_loss[loss=2.356, over 5365980.26 frames. , ppl: 10.54462713486148], batch size: 70
+2022-12-10 09:54:25,160 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 09:54:25,907 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.337, over 211138.00 frames. , ppl: 10.35141844156331
+2022-12-10 09:56:05,776 INFO [train.py:421] (7/8) Epoch 2, batch 23200, loss[loss=2.465, over 1330.00 frames. , ppl: 11.761862314417334] tot_loss[loss=2.356, over 5371317.99 frames. , ppl: 10.546808978770233], batch size: 70
+2022-12-10 09:57:48,629 INFO [train.py:421] (7/8) Epoch 2, batch 23400, loss[loss=2.252, over 3780.00 frames. , ppl: 9.502527821660866] tot_loss[loss=2.356, over 5366258.85 frames. , ppl: 10.549166678573688], batch size: 70
+2022-12-10 09:59:32,019 INFO [train.py:421] (7/8) Epoch 2, batch 23600, loss[loss=2.306, over 2730.00 frames. , ppl: 10.033273816128442] tot_loss[loss=2.355, over 5385723.92 frames. , ppl: 10.538355053247258], batch size: 70
+2022-12-10 10:01:14,604 INFO [train.py:421] (7/8) Epoch 2, batch 23800, loss[loss=2.483, over 1330.00 frames. , ppl: 11.975586740494832] tot_loss[loss=2.354, over 5383211.07 frames. , ppl: 10.532378254988707], batch size: 70
+2022-12-10 10:02:54,345 INFO [train.py:421] (7/8) Epoch 2, batch 24000, loss[loss=4.387, over 350.00 frames. , ppl: 80.39865274044011] tot_loss[loss=2.353, over 5420248.57 frames. , ppl: 10.517430785859649], batch size: 70
+2022-12-10 10:02:54,345 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 10:02:55,105 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.335, over 211138.00 frames. , ppl: 10.32757755196688
+2022-12-10 10:04:39,373 INFO [train.py:421] (7/8) Epoch 2, batch 24200, loss[loss=2.261, over 2380.00 frames. , ppl: 9.592868658917105] tot_loss[loss=2.352, over 5464601.76 frames. , ppl: 10.50258793077945], batch size: 70
+2022-12-10 10:06:16,095 INFO [train.py:421] (7/8) Epoch 2, batch 24400, loss[loss=2.535, over 1610.00 frames. , ppl: 12.615218729778803] tot_loss[loss=2.351, over 5470534.69 frames. , ppl: 10.50058475293574], batch size: 70
+2022-12-10 10:07:52,408 INFO [train.py:421] (7/8) Epoch 2, batch 24600, loss[loss=2.491, over 910.00 frames. , ppl: 12.077335454706095] tot_loss[loss=2.351, over 5486539.55 frames. , ppl: 10.492181328557109], batch size: 70
+2022-12-10 10:09:36,258 INFO [train.py:421] (7/8) Epoch 2, batch 24800, loss[loss=2.31, over 3080.00 frames. , ppl: 10.070915738289909] tot_loss[loss=2.351, over 5479929.18 frames. , ppl: 10.496340678735791], batch size: 70
+2022-12-10 10:11:14,033 INFO [train.py:421] (7/8) Epoch 2, batch 25000, loss[loss=2.33, over 3290.00 frames. , ppl: 10.280016880222576] tot_loss[loss=2.352, over 5467986.90 frames. , ppl: 10.501783559414173], batch size: 70
+2022-12-10 10:11:14,033 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 10:11:14,793 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.336, over 211138.00 frames. , ppl: 10.337237971792588
+2022-12-10 10:12:54,451 INFO [train.py:421] (7/8) Epoch 2, batch 25200, loss[loss=2.345, over 2730.00 frames. , ppl: 10.432397950547841] tot_loss[loss=2.352, over 5431845.74 frames. , ppl: 10.509776999110448], batch size: 70
+2022-12-10 10:14:32,510 INFO [train.py:421] (7/8) Epoch 2, batch 25400, loss[loss=2.443, over 840.00 frames. , ppl: 11.50180870301523] tot_loss[loss=2.353, over 5380528.63 frames. , ppl: 10.519570593083596], batch size: 70
+2022-12-10 10:16:11,534 INFO [train.py:421] (7/8) Epoch 2, batch 25600, loss[loss=2.268, over 4340.00 frames. , ppl: 9.658385878102235] tot_loss[loss=2.353, over 5397132.41 frames. , ppl: 10.516836978142836], batch size: 70
+2022-12-10 10:17:49,159 INFO [train.py:421] (7/8) Epoch 2, batch 25800, loss[loss=2.465, over 980.00 frames. , ppl: 11.764859007282702] tot_loss[loss=2.353, over 5384093.50 frames. , ppl: 10.513245750189574], batch size: 70
+2022-12-10 10:19:31,238 INFO [train.py:421] (7/8) Epoch 2, batch 26000, loss[loss=2.53, over 1890.00 frames. , ppl: 12.5584315724694] tot_loss[loss=2.351, over 5431629.47 frames. , ppl: 10.496288589623521], batch size: 70
+2022-12-10 10:19:31,239 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 10:19:31,994 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.335, over 211138.00 frames. , ppl: 10.33015502328756
+2022-12-10 10:21:14,004 INFO [train.py:421] (7/8) Epoch 2, batch 26200, loss[loss=2.469, over 1260.00 frames. , ppl: 11.816416398653082] tot_loss[loss=2.351, over 5418724.61 frames. , ppl: 10.494785854079637], batch size: 70
+2022-12-10 10:22:55,797 INFO [train.py:421] (7/8) Epoch 2, batch 26400, loss[loss=2.357, over 2730.00 frames. , ppl: 10.561868159797633] tot_loss[loss=2.35, over 5450269.06 frames. , ppl: 10.481270778568113], batch size: 70
+2022-12-10 10:24:38,308 INFO [train.py:421] (7/8) Epoch 2, batch 26600, loss[loss=2.517, over 1540.00 frames. , ppl: 12.391513530134642] tot_loss[loss=2.349, over 5474118.11 frames. , ppl: 10.471899601015588], batch size: 70
+2022-12-10 10:26:19,547 INFO [train.py:421] (7/8) Epoch 2, batch 26800, loss[loss=2.53, over 1400.00 frames. , ppl: 12.552855973656833] tot_loss[loss=2.349, over 5455770.07 frames. , ppl: 10.478940278576598], batch size: 70
+2022-12-10 10:27:59,905 INFO [train.py:421] (7/8) Epoch 2, batch 27000, loss[loss=2.463, over 1330.00 frames. , ppl: 11.742410182801628] tot_loss[loss=2.35, over 5460690.82 frames. , ppl: 10.48404651177324], batch size: 70
+2022-12-10 10:27:59,905 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 10:28:00,666 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.335, over 211138.00 frames. , ppl: 10.332974773515254
+2022-12-10 10:29:43,668 INFO [train.py:421] (7/8) Epoch 2, batch 27200, loss[loss=2.542, over 1050.00 frames. , ppl: 12.699657896313386] tot_loss[loss=2.35, over 5463470.27 frames. , ppl: 10.483632483715255], batch size: 70
+2022-12-10 10:31:24,576 INFO [train.py:421] (7/8) Epoch 2, batch 27400, loss[loss=2.766, over 840.00 frames. , ppl: 15.899666443030123] tot_loss[loss=2.35, over 5480635.82 frames. , ppl: 10.481707951452648], batch size: 70
+2022-12-10 10:33:03,927 INFO [train.py:421] (7/8) Epoch 2, batch 27600, loss[loss=2.254, over 4690.00 frames. , ppl: 9.5244572690823] tot_loss[loss=2.35, over 5466732.09 frames. , ppl: 10.483927441095078], batch size: 70
+2022-12-10 10:34:44,431 INFO [train.py:421] (7/8) Epoch 2, batch 27800, loss[loss=3.062, over 560.00 frames. , ppl: 21.3800153047849] tot_loss[loss=2.349, over 5484646.44 frames. , ppl: 10.477209213433104], batch size: 70
+2022-12-10 10:36:25,385 INFO [train.py:421] (7/8) Epoch 2, batch 28000, loss[loss=2.297, over 3010.00 frames. , ppl: 9.946173673382773] tot_loss[loss=2.349, over 5469226.41 frames. , ppl: 10.47791116273604], batch size: 70
+2022-12-10 10:36:25,385 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 10:36:26,133 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.333, over 211138.00 frames. , ppl: 10.313298466854016
+2022-12-10 10:38:05,396 INFO [train.py:421] (7/8) Epoch 2, batch 28200, loss[loss=2.504, over 2030.00 frames. , ppl: 12.23566250000258] tot_loss[loss=2.349, over 5470188.48 frames. , ppl: 10.47017578578724], batch size: 70
+2022-12-10 10:39:46,481 INFO [train.py:421] (7/8) Epoch 2, batch 28400, loss[loss=2.29, over 3640.00 frames. , ppl: 9.873940530676231] tot_loss[loss=2.348, over 5482046.30 frames. , ppl: 10.467025745259615], batch size: 70
+2022-12-10 10:41:25,662 INFO [train.py:421] (7/8) Epoch 2, batch 28600, loss[loss=2.433, over 2030.00 frames. , ppl: 11.396985467734403] tot_loss[loss=2.348, over 5485048.46 frames. , ppl: 10.46185906991699], batch size: 70
+2022-12-10 10:43:03,862 INFO [train.py:421] (7/8) Epoch 2, batch 28800, loss[loss=2.224, over 5880.00 frames. , ppl: 9.243170227875549] tot_loss[loss=2.349, over 5447367.33 frames. , ppl: 10.472563592773335], batch size: 70
+2022-12-10 10:44:44,079 INFO [train.py:421] (7/8) Epoch 2, batch 29000, loss[loss=2.518, over 1540.00 frames. , ppl: 12.409946023822156] tot_loss[loss=2.35, over 5438975.35 frames. , ppl: 10.482910544117578], batch size: 70
+2022-12-10 10:44:44,079 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 10:44:44,826 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.335, over 211138.00 frames. , ppl: 10.328367846981726
+2022-12-10 10:46:24,219 INFO [train.py:421] (7/8) Epoch 2, batch 29200, loss[loss=2.435, over 1960.00 frames. , ppl: 11.41579653062533] tot_loss[loss=2.351, over 5403474.09 frames. , ppl: 10.500016688911293], batch size: 70
+2022-12-10 10:48:02,852 INFO [train.py:421] (7/8) Epoch 2, batch 29400, loss[loss=2.312, over 3290.00 frames. , ppl: 10.090005734855382] tot_loss[loss=2.352, over 5410436.69 frames. , ppl: 10.507536180306158], batch size: 70
+2022-12-10 10:49:40,056 INFO [train.py:421] (7/8) Epoch 2, batch 29600, loss[loss=2.394, over 1960.00 frames. , ppl: 10.962645525035684] tot_loss[loss=2.353, over 5360558.09 frames. , ppl: 10.521258764434913], batch size: 70
+2022-12-10 10:51:22,076 INFO [train.py:421] (7/8) Epoch 2, batch 29800, loss[loss=2.383, over 1400.00 frames. , ppl: 10.834533295455417] tot_loss[loss=2.352, over 5435630.94 frames. , ppl: 10.505992927109112], batch size: 70
+2022-12-10 10:53:03,453 INFO [train.py:421] (7/8) Epoch 2, batch 30000, loss[loss=2.332, over 1890.00 frames. , ppl: 10.295009118395937] tot_loss[loss=2.35, over 5494721.40 frames. , ppl: 10.486719220537475], batch size: 70
+2022-12-10 10:53:03,453 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 10:53:04,215 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.333, over 211138.00 frames. , ppl: 10.311935441408778
+2022-12-10 10:54:45,306 INFO [train.py:421] (7/8) Epoch 2, batch 30200, loss[loss=2.405, over 2380.00 frames. , ppl: 11.080682453686302] tot_loss[loss=2.35, over 5505776.64 frames. , ppl: 10.482493185387945], batch size: 70
+2022-12-10 10:56:29,741 INFO [train.py:421] (7/8) Epoch 2, batch 30400, loss[loss=2.743, over 700.00 frames. , ppl: 15.534081426845702] tot_loss[loss=2.35, over 5493815.65 frames. , ppl: 10.483957372620264], batch size: 70
+2022-12-10 10:58:09,969 INFO [train.py:421] (7/8) Epoch 2, batch 30600, loss[loss=2.608, over 840.00 frames. , ppl: 13.574786923542453] tot_loss[loss=2.352, over 5426422.93 frames. , ppl: 10.50342980306718], batch size: 70
+2022-12-10 10:59:47,280 INFO [train.py:421] (7/8) Epoch 2, batch 30800, loss[loss=2.343, over 2800.00 frames. , ppl: 10.416914438484135] tot_loss[loss=2.351, over 5429747.26 frames. , ppl: 10.497662354758123], batch size: 70
+2022-12-10 11:01:28,588 INFO [train.py:421] (7/8) Epoch 2, batch 31000, loss[loss=2.364, over 910.00 frames. , ppl: 10.630804256782538] tot_loss[loss=2.351, over 5431188.92 frames. , ppl: 10.499075782020705], batch size: 70
+2022-12-10 11:01:28,589 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 11:01:29,350 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.334, over 211138.00 frames. , ppl: 10.318448451765484
+2022-12-10 11:03:12,432 INFO [train.py:421] (7/8) Epoch 2, batch 31200, loss[loss=3.019, over 560.00 frames. , ppl: 20.47358243534108] tot_loss[loss=2.35, over 5463373.57 frames. , ppl: 10.48537603324088], batch size: 70
+2022-12-10 11:04:53,783 INFO [train.py:421] (7/8) Epoch 2, batch 31400, loss[loss=2.458, over 2100.00 frames. , ppl: 11.680006503730768] tot_loss[loss=2.35, over 5449958.96 frames. , ppl: 10.483911538225337], batch size: 70
+2022-12-10 11:06:34,444 INFO [train.py:421] (7/8) Epoch 2, batch 31600, loss[loss=2.446, over 1540.00 frames. , ppl: 11.537421526988627] tot_loss[loss=2.35, over 5447586.96 frames. , ppl: 10.488078348856222], batch size: 70
+2022-12-10 11:08:17,181 INFO [train.py:421] (7/8) Epoch 2, batch 31800, loss[loss=2.336, over 2730.00 frames. , ppl: 10.342507095469399] tot_loss[loss=2.35, over 5455804.53 frames. , ppl: 10.490568021555308], batch size: 70
+2022-12-10 11:09:56,530 INFO [train.py:421] (7/8) Epoch 2, batch 32000, loss[loss=2.393, over 3080.00 frames. , ppl: 10.940856560639] tot_loss[loss=2.351, over 5436058.24 frames. , ppl: 10.493701249061468], batch size: 70
+2022-12-10 11:09:56,530 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 11:09:57,291 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.334, over 211138.00 frames. , ppl: 10.31484792506888
+2022-12-10 11:11:36,923 INFO [train.py:421] (7/8) Epoch 2, batch 32200, loss[loss=2.3, over 6090.00 frames. , ppl: 9.978460196696957] tot_loss[loss=2.351, over 5433710.90 frames. , ppl: 10.498348689781377], batch size: 70
+2022-12-10 11:13:14,856 INFO [train.py:421] (7/8) Epoch 2, batch 32400, loss[loss=2.453, over 1610.00 frames. , ppl: 11.620950985846532] tot_loss[loss=2.352, over 5391821.12 frames. , ppl: 10.502677149223565], batch size: 70
+2022-12-10 11:14:55,254 INFO [train.py:421] (7/8) Epoch 2, batch 32600, loss[loss=2.312, over 4270.00 frames. , ppl: 10.097369618221663] tot_loss[loss=2.351, over 5394837.48 frames. , ppl: 10.497508171837575], batch size: 70
+2022-12-10 11:16:38,284 INFO [train.py:421] (7/8) Epoch 2, batch 32800, loss[loss=2.304, over 3920.00 frames. , ppl: 10.011628921119064] tot_loss[loss=2.351, over 5415473.81 frames. , ppl: 10.49364394183596], batch size: 70
+2022-12-10 11:18:17,211 INFO [train.py:421] (7/8) Epoch 2, batch 33000, loss[loss=2.363, over 3780.00 frames. , ppl: 10.62804705602318] tot_loss[loss=2.351, over 5428794.76 frames. , ppl: 10.496623516830248], batch size: 70
+2022-12-10 11:18:17,212 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 11:18:17,973 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.332, over 211138.00 frames. , ppl: 10.303007731813349
+2022-12-10 11:20:00,441 INFO [train.py:421] (7/8) Epoch 2, batch 33200, loss[loss=2.392, over 700.00 frames. , ppl: 10.934982742004335] tot_loss[loss=2.351, over 5433481.53 frames. , ppl: 10.492143526061222], batch size: 70
+2022-12-10 11:21:39,768 INFO [train.py:421] (7/8) Epoch 2, batch 33400, loss[loss=2.372, over 1330.00 frames. , ppl: 10.723021997629798] tot_loss[loss=2.352, over 5385357.45 frames. , ppl: 10.503027819530383], batch size: 70
+2022-12-10 11:23:22,972 INFO [train.py:421] (7/8) Epoch 2, batch 33600, loss[loss=2.526, over 980.00 frames. , ppl: 12.50525188103972] tot_loss[loss=2.35, over 5397663.12 frames. , ppl: 10.489396678979192], batch size: 70
+2022-12-10 11:25:04,059 INFO [train.py:421] (7/8) Epoch 2, batch 33800, loss[loss=2.392, over 2380.00 frames. , ppl: 10.936038099167266] tot_loss[loss=2.349, over 5430280.53 frames. , ppl: 10.472904289875068], batch size: 70
+2022-12-10 11:26:42,438 INFO [train.py:421] (7/8) Epoch 2, batch 34000, loss[loss=2.336, over 2450.00 frames. , ppl: 10.34033117731693] tot_loss[loss=2.349, over 5433146.98 frames. , ppl: 10.473270604585677], batch size: 70
+2022-12-10 11:26:42,438 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 11:26:43,186 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.331, over 211138.00 frames. , ppl: 10.291255765342557
+2022-12-10 11:28:20,403 INFO [train.py:421] (7/8) Epoch 2, batch 34200, loss[loss=2.326, over 3220.00 frames. , ppl: 10.235975001463629] tot_loss[loss=2.349, over 5453662.55 frames. , ppl: 10.476637284430995], batch size: 70
+2022-12-10 11:30:00,226 INFO [train.py:421] (7/8) Epoch 2, batch 34400, loss[loss=2.404, over 2310.00 frames. , ppl: 11.065379567842523] tot_loss[loss=2.348, over 5473570.37 frames. , ppl: 10.4660319317485], batch size: 70
+2022-12-10 11:31:39,797 INFO [train.py:421] (7/8) Epoch 2, batch 34600, loss[loss=4.242, over 350.00 frames. , ppl: 69.56761150861439] tot_loss[loss=2.348, over 5461372.16 frames. , ppl: 10.466904392096557], batch size: 70
+2022-12-10 11:33:17,811 INFO [train.py:421] (7/8) Epoch 2, batch 34800, loss[loss=2.291, over 1400.00 frames. , ppl: 9.883208716967385] tot_loss[loss=2.346, over 5520476.35 frames. , ppl: 10.44863297442317], batch size: 70
+2022-12-10 11:35:00,058 INFO [train.py:421] (7/8) Epoch 2, batch 35000, loss[loss=2.446, over 840.00 frames. , ppl: 11.540685642408329] tot_loss[loss=2.347, over 5514818.50 frames. , ppl: 10.452379553511754], batch size: 70
+2022-12-10 11:35:00,059 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 11:35:00,819 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.332, over 211138.00 frames. , ppl: 10.297171983552662
+2022-12-10 11:36:40,680 INFO [train.py:421] (7/8) Epoch 2, batch 35200, loss[loss=2.674, over 840.00 frames. , ppl: 14.504658389487114] tot_loss[loss=2.347, over 5496922.16 frames. , ppl: 10.459228959398475], batch size: 70
+2022-12-10 11:38:22,525 INFO [train.py:421] (7/8) Epoch 2, batch 35400, loss[loss=2.247, over 5390.00 frames. , ppl: 9.454985528620183] tot_loss[loss=2.348, over 5476522.27 frames. , ppl: 10.46093831379858], batch size: 70
+2022-12-10 11:40:03,279 INFO [train.py:421] (7/8) Epoch 2, batch 35600, loss[loss=2.27, over 3850.00 frames. , ppl: 9.681605839425378] tot_loss[loss=2.347, over 5471073.81 frames. , ppl: 10.458000440098704], batch size: 70
+2022-12-10 11:41:42,466 INFO [train.py:421] (7/8) Epoch 2, batch 35800, loss[loss=2.441, over 1400.00 frames. , ppl: 11.48899371617754] tot_loss[loss=2.348, over 5429567.22 frames. , ppl: 10.469739651839804], batch size: 70
+2022-12-10 11:43:21,035 INFO [train.py:421] (7/8) Epoch 2, batch 36000, loss[loss=3.057, over 560.00 frames. , ppl: 21.267783779708537] tot_loss[loss=2.348, over 5436611.58 frames. , ppl: 10.469434097754977], batch size: 70
+2022-12-10 11:43:21,035 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 11:43:21,794 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.331, over 211138.00 frames. , ppl: 10.288832667020564
+2022-12-10 11:45:02,847 INFO [train.py:421] (7/8) Epoch 2, batch 36200, loss[loss=2.286, over 11830.00 frames. , ppl: 9.834229920528156] tot_loss[loss=2.348, over 5457553.00 frames. , ppl: 10.465193195388293], batch size: 70
+2022-12-10 11:46:46,963 INFO [train.py:421] (7/8) Epoch 2, batch 36400, loss[loss=2.407, over 840.00 frames. , ppl: 11.10148535965232] tot_loss[loss=2.346, over 5499745.02 frames. , ppl: 10.444581763885525], batch size: 70
+2022-12-10 11:48:25,554 INFO [train.py:421] (7/8) Epoch 2, batch 36600, loss[loss=2.457, over 2310.00 frames. , ppl: 11.669887466760603] tot_loss[loss=2.347, over 5494203.64 frames. , ppl: 10.450530324150678], batch size: 70
+2022-12-10 11:50:04,157 INFO [train.py:421] (7/8) Epoch 2, batch 36800, loss[loss=2.3, over 7000.00 frames. , ppl: 9.973944513289094] tot_loss[loss=2.347, over 5504794.56 frames. , ppl: 10.449949152091545], batch size: 70
+2022-12-10 11:51:43,188 INFO [train.py:421] (7/8) Epoch 2, batch 37000, loss[loss=2.299, over 2240.00 frames. , ppl: 9.968557214064353] tot_loss[loss=2.347, over 5506037.42 frames. , ppl: 10.45001404773384], batch size: 70
+2022-12-10 11:51:43,188 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 11:51:43,927 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.333, over 211138.00 frames. , ppl: 10.313814418221853
+2022-12-10 11:53:27,751 INFO [train.py:421] (7/8) Epoch 2, batch 37200, loss[loss=2.368, over 3640.00 frames. , ppl: 10.6801771778089] tot_loss[loss=2.347, over 5511912.36 frames. , ppl: 10.45086491825651], batch size: 70
+2022-12-10 11:55:05,726 INFO [train.py:421] (7/8) Epoch 2, batch 37400, loss[loss=2.333, over 3990.00 frames. , ppl: 10.30370837751201] tot_loss[loss=2.346, over 5501440.79 frames. , ppl: 10.448380340300528], batch size: 70
+2022-12-10 11:56:46,032 INFO [train.py:421] (7/8) Epoch 2, batch 37600, loss[loss=2.263, over 3290.00 frames. , ppl: 9.61165769492913] tot_loss[loss=2.346, over 5495434.02 frames. , ppl: 10.44680850464029], batch size: 70
+2022-12-10 11:58:29,014 INFO [train.py:421] (7/8) Epoch 2, batch 37800, loss[loss=2.264, over 5740.00 frames. , ppl: 9.616983641618923] tot_loss[loss=2.346, over 5510040.56 frames. , ppl: 10.442356544709856], batch size: 70
+2022-12-10 12:00:10,578 INFO [train.py:421] (7/8) Epoch 2, batch 38000, loss[loss=2.298, over 3990.00 frames. , ppl: 9.95146852173365] tot_loss[loss=2.344, over 5550774.57 frames. , ppl: 10.426226760039263], batch size: 70
+2022-12-10 12:00:10,578 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 12:00:11,327 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.329, over 211138.00 frames. , ppl: 10.269646244641864
+2022-12-10 12:01:54,475 INFO [train.py:421] (7/8) Epoch 2, batch 38200, loss[loss=2.423, over 1890.00 frames. , ppl: 11.279185500326562] tot_loss[loss=2.343, over 5595958.83 frames. , ppl: 10.41395539861255], batch size: 70
+2022-12-10 12:03:35,678 INFO [train.py:421] (7/8) Epoch 2, batch 38400, loss[loss=2.477, over 2310.00 frames. , ppl: 11.908102341595356] tot_loss[loss=2.343, over 5591932.37 frames. , ppl: 10.416038305756292], batch size: 70
+2022-12-10 12:05:13,551 INFO [train.py:421] (7/8) Epoch 2, batch 38600, loss[loss=2.215, over 4760.00 frames. , ppl: 9.165209234889016] tot_loss[loss=2.343, over 5606715.95 frames. , ppl: 10.40846962317268], batch size: 70
+2022-12-10 12:06:50,148 INFO [train.py:421] (7/8) Epoch 2, batch 38800, loss[loss=2.271, over 5180.00 frames. , ppl: 9.690841128175455] tot_loss[loss=2.343, over 5571057.99 frames. , ppl: 10.416393047798573], batch size: 70
+2022-12-10 12:08:30,334 INFO [train.py:421] (7/8) Epoch 2, batch 39000, loss[loss=2.311, over 2100.00 frames. , ppl: 10.082708632664296] tot_loss[loss=2.343, over 5598356.60 frames. , ppl: 10.409788391163572], batch size: 70
+2022-12-10 12:08:30,335 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 12:08:31,096 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.328, over 211138.00 frames. , ppl: 10.258752219498415
+2022-12-10 12:10:14,098 INFO [train.py:421] (7/8) Epoch 2, batch 39200, loss[loss=2.279, over 6160.00 frames. , ppl: 9.762414157064557] tot_loss[loss=2.344, over 5558955.49 frames. , ppl: 10.418352612201987], batch size: 70
+2022-12-10 12:11:55,247 INFO [train.py:421] (7/8) Epoch 2, batch 39400, loss[loss=2.303, over 4760.00 frames. , ppl: 10.001878697668152] tot_loss[loss=2.344, over 5547552.00 frames. , ppl: 10.421972368334774], batch size: 70
+2022-12-10 12:13:32,408 INFO [train.py:421] (7/8) Epoch 2, batch 39600, loss[loss=2.653, over 770.00 frames. , ppl: 14.192452056971556] tot_loss[loss=2.344, over 5537757.74 frames. , ppl: 10.421582114734248], batch size: 70
+2022-12-10 12:15:17,703 INFO [train.py:421] (7/8) Epoch 2, batch 39800, loss[loss=2.315, over 4340.00 frames. , ppl: 10.12065346087012] tot_loss[loss=2.343, over 5575537.21 frames. , ppl: 10.415577393074232], batch size: 70
+2022-12-10 12:16:56,218 INFO [train.py:421] (7/8) Epoch 2, batch 40000, loss[loss=2.373, over 1540.00 frames. , ppl: 10.725243080039919] tot_loss[loss=2.344, over 5579314.76 frames. , ppl: 10.42126392659476], batch size: 70
+2022-12-10 12:16:56,218 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 12:16:56,977 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.331, over 211138.00 frames. , ppl: 10.292756209643162
+2022-12-10 12:18:37,702 INFO [train.py:421] (7/8) Epoch 2, batch 40200, loss[loss=2.31, over 4130.00 frames. , ppl: 10.072373350914537] tot_loss[loss=2.344, over 5554167.47 frames. , ppl: 10.419847819556292], batch size: 70
+2022-12-10 12:20:17,610 INFO [train.py:421] (7/8) Epoch 2, batch 40400, loss[loss=2.595, over 1120.00 frames. , ppl: 13.399535944300153] tot_loss[loss=2.344, over 5552626.83 frames. , ppl: 10.421895451815681], batch size: 70
+2022-12-10 12:22:00,253 INFO [train.py:421] (7/8) Epoch 2, batch 40600, loss[loss=2.616, over 980.00 frames. , ppl: 13.685624320113778] tot_loss[loss=2.344, over 5565689.99 frames. , ppl: 10.421747372740304], batch size: 70
+2022-12-10 12:23:41,677 INFO [train.py:421] (7/8) Epoch 2, batch 40800, loss[loss=2.702, over 700.00 frames. , ppl: 14.906815118504628] tot_loss[loss=2.344, over 5559551.92 frames. , ppl: 10.423235991749541], batch size: 70
+2022-12-10 12:25:27,338 INFO [train.py:421] (7/8) Epoch 2, batch 41000, loss[loss=2.281, over 3710.00 frames. , ppl: 9.790465339463507] tot_loss[loss=2.343, over 5593254.91 frames. , ppl: 10.410111428393714], batch size: 70
+2022-12-10 12:25:27,338 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 12:25:28,086 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.329, over 211138.00 frames. , ppl: 10.27130012072034
+2022-12-10 12:27:08,688 INFO [train.py:421] (7/8) Epoch 2, batch 41200, loss[loss=2.451, over 3290.00 frames. , ppl: 11.599467571969768] tot_loss[loss=2.343, over 5584398.87 frames. , ppl: 10.410133379419973], batch size: 70
+2022-12-10 12:28:47,118 INFO [train.py:421] (7/8) Epoch 2, batch 41400, loss[loss=2.449, over 1750.00 frames. , ppl: 11.579128856938713] tot_loss[loss=2.344, over 5535471.48 frames. , ppl: 10.425157053447467], batch size: 70
+2022-12-10 12:30:25,486 INFO [train.py:421] (7/8) Epoch 2, batch 41600, loss[loss=2.314, over 2730.00 frames. , ppl: 10.116249434426328] tot_loss[loss=2.345, over 5499234.68 frames. , ppl: 10.429912557450452], batch size: 70
+2022-12-10 12:32:02,260 INFO [train.py:421] (7/8) Epoch 2, batch 41800, loss[loss=2.528, over 840.00 frames. , ppl: 12.534007872477886] tot_loss[loss=2.345, over 5458719.70 frames. , ppl: 10.435097878143692], batch size: 70
+2022-12-10 12:33:43,237 INFO [train.py:421] (7/8) Epoch 2, batch 42000, loss[loss=2.902, over 630.00 frames. , ppl: 18.211483039259214] tot_loss[loss=2.346, over 5415329.79 frames. , ppl: 10.445243030194247], batch size: 70
+2022-12-10 12:33:43,238 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 12:33:43,996 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.331, over 211138.00 frames. , ppl: 10.283807052673856
+2022-12-10 12:35:25,663 INFO [train.py:421] (7/8) Epoch 2, batch 42200, loss[loss=2.279, over 2940.00 frames. , ppl: 9.76637093417799] tot_loss[loss=2.345, over 5440416.61 frames. , ppl: 10.437693893330458], batch size: 70
+2022-12-10 12:37:03,139 INFO [train.py:421] (7/8) Epoch 2, batch 42400, loss[loss=2.247, over 4270.00 frames. , ppl: 9.4611877378278] tot_loss[loss=2.345, over 5428438.73 frames. , ppl: 10.434420354653735], batch size: 70
+2022-12-10 12:38:43,243 INFO [train.py:421] (7/8) Epoch 2, batch 42600, loss[loss=2.244, over 3710.00 frames. , ppl: 9.433098234960571] tot_loss[loss=2.346, over 5448977.35 frames. , ppl: 10.439576555902537], batch size: 70
+2022-12-10 12:40:22,492 INFO [train.py:421] (7/8) Epoch 2, batch 42800, loss[loss=2.578, over 1120.00 frames. , ppl: 13.174869078029126] tot_loss[loss=2.345, over 5472189.87 frames. , ppl: 10.436904790541192], batch size: 70
+2022-12-10 12:42:04,986 INFO [train.py:421] (7/8) Epoch 2, batch 43000, loss[loss=2.619, over 910.00 frames. , ppl: 13.716165178198832] tot_loss[loss=2.345, over 5484405.92 frames. , ppl: 10.433571296776496], batch size: 70
+2022-12-10 12:42:04,986 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 12:42:05,730 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.328, over 211138.00 frames. , ppl: 10.261654238592559
+2022-12-10 12:43:44,226 INFO [train.py:421] (7/8) Epoch 2, batch 43200, loss[loss=2.37, over 1680.00 frames. , ppl: 10.69328342721125] tot_loss[loss=2.345, over 5480675.24 frames. , ppl: 10.431808223129874], batch size: 70
+2022-12-10 12:45:21,822 INFO [train.py:421] (7/8) Epoch 2, batch 43400, loss[loss=2.52, over 1050.00 frames. , ppl: 12.422928102990399] tot_loss[loss=2.343, over 5547860.03 frames. , ppl: 10.409722457157594], batch size: 70
+2022-12-10 12:47:02,706 INFO [train.py:421] (7/8) Epoch 2, batch 43600, loss[loss=2.199, over 3360.00 frames. , ppl: 9.013982399801199] tot_loss[loss=2.342, over 5566722.70 frames. , ppl: 10.404185929841292], batch size: 70
+2022-12-10 12:48:41,287 INFO [train.py:421] (7/8) Epoch 2, batch 43800, loss[loss=2.314, over 4270.00 frames. , ppl: 10.114750498844916] tot_loss[loss=2.343, over 5556120.29 frames. , ppl: 10.414464496291208], batch size: 70
+2022-12-10 12:50:21,842 INFO [train.py:421] (7/8) Epoch 2, batch 44000, loss[loss=2.289, over 5950.00 frames. , ppl: 9.860529963131095] tot_loss[loss=2.344, over 5522972.97 frames. , ppl: 10.423137796796606], batch size: 70
+2022-12-10 12:50:21,843 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 12:50:22,572 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.329, over 211138.00 frames. , ppl: 10.270837981475065
+2022-12-10 12:52:01,317 INFO [train.py:421] (7/8) Epoch 2, batch 44200, loss[loss=2.373, over 2380.00 frames. , ppl: 10.72864442651037] tot_loss[loss=2.344, over 5528298.08 frames. , ppl: 10.42393141163982], batch size: 70
+2022-12-10 12:53:43,813 INFO [train.py:421] (7/8) Epoch 2, batch 44400, loss[loss=2.353, over 5180.00 frames. , ppl: 10.516270767496083] tot_loss[loss=2.342, over 5584153.63 frames. , ppl: 10.406308654399599], batch size: 70
+2022-12-10 12:55:21,483 INFO [train.py:421] (7/8) Epoch 2, batch 44600, loss[loss=2.39, over 1680.00 frames. , ppl: 10.918181169301537] tot_loss[loss=2.344, over 5567024.57 frames. , ppl: 10.418587977944929], batch size: 70
+2022-12-10 12:57:01,758 INFO [train.py:421] (7/8) Epoch 2, batch 44800, loss[loss=2.367, over 2730.00 frames. , ppl: 10.66151526379057] tot_loss[loss=2.344, over 5537280.08 frames. , ppl: 10.427700754246866], batch size: 70
+2022-12-10 12:58:44,441 INFO [train.py:421] (7/8) Epoch 2, batch 45000, loss[loss=2.416, over 2660.00 frames. , ppl: 11.204620254167148] tot_loss[loss=2.344, over 5542027.65 frames. , ppl: 10.425027804576361], batch size: 70
+2022-12-10 12:58:44,441 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 12:58:45,186 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.329, over 211138.00 frames. , ppl: 10.267509369063996
+2022-12-10 13:00:27,491 INFO [train.py:421] (7/8) Epoch 2, batch 45200, loss[loss=2.337, over 2380.00 frames. , ppl: 10.347708727342768] tot_loss[loss=2.346, over 5501252.59 frames. , ppl: 10.43861208706131], batch size: 70
+2022-12-10 13:02:10,352 INFO [train.py:421] (7/8) Epoch 2, batch 45400, loss[loss=2.4, over 1470.00 frames. , ppl: 11.02403503668479] tot_loss[loss=2.345, over 5516069.08 frames. , ppl: 10.431371467502263], batch size: 70
+2022-12-10 13:03:49,610 INFO [train.py:421] (7/8) Epoch 2, batch 45600, loss[loss=2.305, over 3640.00 frames. , ppl: 10.020417094441536] tot_loss[loss=2.345, over 5509237.78 frames. , ppl: 10.428119051649846], batch size: 70
+2022-12-10 13:05:28,561 INFO [train.py:421] (7/8) Epoch 2, batch 45800, loss[loss=2.174, over 6580.00 frames. , ppl: 8.79308446367004] tot_loss[loss=2.344, over 5493624.46 frames. , ppl: 10.421593632262056], batch size: 70
+2022-12-10 13:07:05,406 INFO [train.py:421] (7/8) Epoch 2, batch 46000, loss[loss=2.297, over 3010.00 frames. , ppl: 9.946533482620156] tot_loss[loss=2.344, over 5481564.54 frames. , ppl: 10.419616964602362], batch size: 70
+2022-12-10 13:07:05,406 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 13:07:06,169 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.329, over 211138.00 frames. , ppl: 10.269302733935248
+2022-12-10 13:08:48,310 INFO [train.py:421] (7/8) Epoch 2, batch 46200, loss[loss=2.29, over 6650.00 frames. , ppl: 9.874343137798144] tot_loss[loss=2.344, over 5487285.96 frames. , ppl: 10.41784786672615], batch size: 70
+2022-12-10 13:10:28,307 INFO [train.py:421] (7/8) Epoch 2, batch 46400, loss[loss=2.383, over 1820.00 frames. , ppl: 10.835055361759995] tot_loss[loss=2.344, over 5466003.31 frames. , ppl: 10.426024930912288], batch size: 70
+2022-12-10 13:12:09,473 INFO [train.py:421] (7/8) Epoch 2, batch 46600, loss[loss=2.428, over 1470.00 frames. , ppl: 11.338831895037666] tot_loss[loss=2.343, over 5499667.31 frames. , ppl: 10.414482971821567], batch size: 70
+2022-12-10 13:13:46,936 INFO [train.py:421] (7/8) Epoch 2, batch 46800, loss[loss=2.173, over 6580.00 frames. , ppl: 8.788398100231927] tot_loss[loss=2.344, over 5483711.12 frames. , ppl: 10.418767454960648], batch size: 70
+2022-12-10 13:15:22,166 INFO [train.py:421] (7/8) Epoch 2, batch 47000, loss[loss=2.304, over 6580.00 frames. , ppl: 10.01572171922075] tot_loss[loss=2.344, over 5474343.93 frames. , ppl: 10.418528698248343], batch size: 70
+2022-12-10 13:15:22,166 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 13:15:22,923 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.329, over 211138.00 frames. , ppl: 10.265565897614955
+2022-12-10 13:17:01,354 INFO [train.py:421] (7/8) Epoch 2, batch 47200, loss[loss=2.326, over 1120.00 frames. , ppl: 10.232181098247041] tot_loss[loss=2.343, over 5507078.09 frames. , ppl: 10.415133841171869], batch size: 70
+2022-12-10 13:18:45,163 INFO [train.py:421] (7/8) Epoch 2, batch 47400, loss[loss=2.455, over 1400.00 frames. , ppl: 11.650016743109992] tot_loss[loss=2.344, over 5484998.22 frames. , ppl: 10.419690886378714], batch size: 70
+2022-12-10 13:20:26,207 INFO [train.py:421] (7/8) Epoch 2, batch 47600, loss[loss=2.407, over 3220.00 frames. , ppl: 11.104855538407463] tot_loss[loss=2.344, over 5489557.24 frames. , ppl: 10.420111745815628], batch size: 70
+2022-12-10 13:22:08,949 INFO [train.py:421] (7/8) Epoch 2, batch 47800, loss[loss=2.472, over 1400.00 frames. , ppl: 11.846479405317432] tot_loss[loss=2.343, over 5513459.28 frames. , ppl: 10.410812128511353], batch size: 70
+2022-12-10 13:23:44,826 INFO [train.py:421] (7/8) Epoch 2, batch 48000, loss[loss=2.253, over 9590.00 frames. , ppl: 9.515349830590548] tot_loss[loss=2.343, over 5501657.16 frames. , ppl: 10.413230242448355], batch size: 70
+2022-12-10 13:23:44,826 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 13:23:45,556 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.328, over 211138.00 frames. , ppl: 10.26050912621634
+2022-12-10 13:25:25,336 INFO [train.py:421] (7/8) Epoch 2, batch 48200, loss[loss=2.394, over 2240.00 frames. , ppl: 10.96190850820773] tot_loss[loss=2.342, over 5542819.85 frames. , ppl: 10.398905903956793], batch size: 70
+2022-12-10 13:27:08,697 INFO [train.py:421] (7/8) Epoch 2, batch 48400, loss[loss=2.336, over 2380.00 frames. , ppl: 10.342158733691152] tot_loss[loss=2.342, over 5525848.69 frames. , ppl: 10.397251868749732], batch size: 70
+2022-12-10 13:28:49,083 INFO [train.py:421] (7/8) Epoch 2, batch 48600, loss[loss=2.249, over 6440.00 frames. , ppl: 9.481824532905831] tot_loss[loss=2.341, over 5556149.04 frames. , ppl: 10.38691590957625], batch size: 70
+2022-12-10 13:30:27,731 INFO [train.py:421] (7/8) Epoch 2, batch 48800, loss[loss=2.29, over 3430.00 frames. , ppl: 9.872863563822687] tot_loss[loss=2.342, over 5532218.47 frames. , ppl: 10.399691345398628], batch size: 70
+2022-12-10 13:32:08,064 INFO [train.py:421] (7/8) Epoch 2, batch 49000, loss[loss=2.407, over 1960.00 frames. , ppl: 11.101409765850825] tot_loss[loss=2.34, over 5560615.87 frames. , ppl: 10.386335904615212], batch size: 70
+2022-12-10 13:32:08,065 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 13:32:08,810 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.328, over 211138.00 frames. , ppl: 10.253641134938565
+2022-12-10 13:33:44,603 INFO [train.py:421] (7/8) Epoch 2, batch 49200, loss[loss=2.413, over 1960.00 frames. , ppl: 11.170240001311026] tot_loss[loss=2.34, over 5547993.03 frames. , ppl: 10.385869738750957], batch size: 70
+2022-12-10 13:35:23,415 INFO [train.py:421] (7/8) Epoch 2, batch 49400, loss[loss=2.479, over 1540.00 frames. , ppl: 11.927123516666795] tot_loss[loss=2.34, over 5568180.90 frames. , ppl: 10.382129993362339], batch size: 70
+2022-12-10 13:37:03,015 INFO [train.py:421] (7/8) Epoch 2, batch 49600, loss[loss=2.364, over 3010.00 frames. , ppl: 10.634758201782724] tot_loss[loss=2.34, over 5549067.85 frames. , ppl: 10.384105255154612], batch size: 70
+2022-12-10 13:38:43,472 INFO [train.py:421] (7/8) Epoch 2, batch 49800, loss[loss=2.504, over 1890.00 frames. , ppl: 12.232045558106847] tot_loss[loss=2.34, over 5549030.80 frames. , ppl: 10.384823358325212], batch size: 70
+2022-12-10 13:40:22,317 INFO [train.py:421] (7/8) Epoch 2, batch 50000, loss[loss=2.509, over 1120.00 frames. , ppl: 12.296405567636398] tot_loss[loss=2.34, over 5565504.91 frames. , ppl: 10.383560189325436], batch size: 70
+2022-12-10 13:40:22,318 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 13:40:23,076 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.327, over 211138.00 frames. , ppl: 10.24865242939489
+2022-12-10 13:42:06,039 INFO [train.py:421] (7/8) Epoch 2, batch 50200, loss[loss=2.199, over 4830.00 frames. , ppl: 9.016483228634211] tot_loss[loss=2.341, over 5522894.57 frames. , ppl: 10.387873620471536], batch size: 70
+2022-12-10 13:43:50,047 INFO [train.py:421] (7/8) Epoch 2, batch 50400, loss[loss=2.731, over 770.00 frames. , ppl: 15.347227466552031] tot_loss[loss=2.339, over 5544083.11 frames. , ppl: 10.375786123238559], batch size: 70
+2022-12-10 13:45:26,741 INFO [train.py:421] (7/8) Epoch 2, batch 50600, loss[loss=2.28, over 4760.00 frames. , ppl: 9.77619863169844] tot_loss[loss=2.339, over 5533859.65 frames. , ppl: 10.375447538313498], batch size: 70
+2022-12-10 13:47:06,669 INFO [train.py:421] (7/8) Epoch 2, batch 50800, loss[loss=2.521, over 3150.00 frames. , ppl: 12.44076689151592] tot_loss[loss=2.339, over 5560213.23 frames. , ppl: 10.371747460126446], batch size: 70
+2022-12-10 13:48:47,680 INFO [train.py:421] (7/8) Epoch 2, batch 51000, loss[loss=2.312, over 3710.00 frames. , ppl: 10.09883408226568] tot_loss[loss=2.339, over 5574385.26 frames. , ppl: 10.36985948637928], batch size: 70
+2022-12-10 13:48:47,680 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 13:48:48,425 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.329, over 211138.00 frames. , ppl: 10.265193656171405
+2022-12-10 13:50:27,916 INFO [train.py:421] (7/8) Epoch 2, batch 51200, loss[loss=2.242, over 5460.00 frames. , ppl: 9.41170297239853] tot_loss[loss=2.339, over 5555050.97 frames. , ppl: 10.370934700699033], batch size: 70
+2022-12-10 13:52:05,820 INFO [train.py:421] (7/8) Epoch 2, batch 51400, loss[loss=2.463, over 1120.00 frames. , ppl: 11.74571568502982] tot_loss[loss=2.34, over 5518505.26 frames. , ppl: 10.377895587744291], batch size: 70
+2022-12-10 13:53:44,960 INFO [train.py:421] (7/8) Epoch 2, batch 51600, loss[loss=2.311, over 3010.00 frames. , ppl: 10.082961120077725] tot_loss[loss=2.34, over 5504165.70 frames. , ppl: 10.380125102364609], batch size: 70
+2022-12-10 13:55:22,667 INFO [train.py:421] (7/8) Epoch 2, batch 51800, loss[loss=2.481, over 1190.00 frames. , ppl: 11.9536740738898] tot_loss[loss=2.341, over 5422537.85 frames. , ppl: 10.396740290489669], batch size: 70
+2022-12-10 13:57:00,778 INFO [train.py:421] (7/8) Epoch 2, batch 52000, loss[loss=2.661, over 1190.00 frames. , ppl: 14.309087524930352] tot_loss[loss=2.341, over 5450163.14 frames. , ppl: 10.395476338982427], batch size: 70
+2022-12-10 13:57:00,779 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 13:57:01,533 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.329, over 211138.00 frames. , ppl: 10.267428826974491
+2022-12-10 13:58:39,505 INFO [train.py:421] (7/8) Epoch 2, batch 52200, loss[loss=2.449, over 3220.00 frames. , ppl: 11.576622953016058] tot_loss[loss=2.343, over 5429392.90 frames. , ppl: 10.412387542503966], batch size: 70
+2022-12-10 14:00:16,927 INFO [train.py:421] (7/8) Epoch 2, batch 52400, loss[loss=2.436, over 2030.00 frames. , ppl: 11.424599558965722] tot_loss[loss=2.342, over 5430275.63 frames. , ppl: 10.404510263663397], batch size: 70
+2022-12-10 14:01:58,867 INFO [train.py:421] (7/8) Epoch 2, batch 52600, loss[loss=2.328, over 4410.00 frames. , ppl: 10.257039317646278] tot_loss[loss=2.341, over 5451529.63 frames. , ppl: 10.395120204019948], batch size: 70
+2022-12-10 14:03:38,028 INFO [train.py:421] (7/8) Epoch 2, batch 52800, loss[loss=2.44, over 1890.00 frames. , ppl: 11.476569107728086] tot_loss[loss=2.342, over 5453604.69 frames. , ppl: 10.398216167954402], batch size: 70
+2022-12-10 14:05:17,809 INFO [train.py:421] (7/8) Epoch 2, batch 53000, loss[loss=2.341, over 4550.00 frames. , ppl: 10.390630089528898] tot_loss[loss=2.341, over 5526511.61 frames. , ppl: 10.386936993468199], batch size: 70
+2022-12-10 14:05:17,809 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 14:05:18,555 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.326, over 211138.00 frames. , ppl: 10.233852338507358
+2022-12-10 14:06:58,238 INFO [train.py:421] (7/8) Epoch 2, batch 53200, loss[loss=2.205, over 4620.00 frames. , ppl: 9.071313016270057] tot_loss[loss=2.341, over 5519619.63 frames. , ppl: 10.386512674971472], batch size: 70
+2022-12-10 14:08:37,578 INFO [train.py:421] (7/8) Epoch 2, batch 53400, loss[loss=2.289, over 3360.00 frames. , ppl: 9.868417274091936] tot_loss[loss=2.34, over 5535122.89 frames. , ppl: 10.3808141851993], batch size: 70
+2022-12-10 14:10:19,462 INFO [train.py:421] (7/8) Epoch 2, batch 53600, loss[loss=2.265, over 4270.00 frames. , ppl: 9.626737444153262] tot_loss[loss=2.34, over 5535734.28 frames. , ppl: 10.383419177432112], batch size: 70
+2022-12-10 14:11:57,927 INFO [train.py:421] (7/8) Epoch 2, batch 53800, loss[loss=2.587, over 770.00 frames. , ppl: 13.290781744163205] tot_loss[loss=2.34, over 5528515.74 frames. , ppl: 10.3823815532118], batch size: 70
+2022-12-10 14:13:35,071 INFO [train.py:421] (7/8) Epoch 2, batch 54000, loss[loss=2.308, over 2730.00 frames. , ppl: 10.056924805253649] tot_loss[loss=2.341, over 5518628.72 frames. , ppl: 10.387134192189947], batch size: 70
+2022-12-10 14:13:35,071 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 14:13:35,832 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.325, over 211138.00 frames. , ppl: 10.222168662360373
+2022-12-10 14:15:13,906 INFO [train.py:421] (7/8) Epoch 2, batch 54200, loss[loss=2.285, over 3920.00 frames. , ppl: 9.826550826880524] tot_loss[loss=2.34, over 5506035.42 frames. , ppl: 10.383010044502841], batch size: 70
+2022-12-10 14:16:54,971 INFO [train.py:421] (7/8) Epoch 2, batch 54400, loss[loss=2.328, over 5110.00 frames. , ppl: 10.262151308379138] tot_loss[loss=2.341, over 5499280.02 frames. , ppl: 10.386628173216973], batch size: 70
+2022-12-10 14:18:34,363 INFO [train.py:421] (7/8) Epoch 2, batch 54600, loss[loss=3.241, over 490.00 frames. , ppl: 25.546541186874304] tot_loss[loss=2.341, over 5445559.29 frames. , ppl: 10.395965269230723], batch size: 70
+2022-12-10 14:20:12,830 INFO [train.py:421] (7/8) Epoch 2, batch 54800, loss[loss=2.493, over 1190.00 frames. , ppl: 12.100298528568619] tot_loss[loss=2.341, over 5447817.01 frames. , ppl: 10.395055477691528], batch size: 70
+2022-12-10 14:21:50,926 INFO [train.py:421] (7/8) Epoch 2, batch 55000, loss[loss=2.283, over 3430.00 frames. , ppl: 9.804076459038999] tot_loss[loss=2.34, over 5464338.76 frames. , ppl: 10.385400209644917], batch size: 70
+2022-12-10 14:21:50,926 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 14:21:51,690 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.326, over 211138.00 frames. , ppl: 10.232852694220295
+2022-12-10 14:23:32,584 INFO [train.py:421] (7/8) Epoch 2, batch 55200, loss[loss=2.224, over 3780.00 frames. , ppl: 9.243008188351943] tot_loss[loss=2.34, over 5465433.89 frames. , ppl: 10.386263200181263], batch size: 70
+2022-12-10 14:25:08,971 INFO [train.py:421] (7/8) Epoch 2, batch 55400, loss[loss=2.695, over 910.00 frames. , ppl: 14.805589457180849] tot_loss[loss=2.341, over 5435890.98 frames. , ppl: 10.396461535515247], batch size: 70
+2022-12-10 14:26:48,398 INFO [train.py:421] (7/8) Epoch 2, batch 55600, loss[loss=2.258, over 2100.00 frames. , ppl: 9.56540904567212] tot_loss[loss=2.341, over 5437127.85 frames. , ppl: 10.395319458481032], batch size: 70
+2022-12-10 14:28:34,517 INFO [train.py:421] (7/8) Epoch 2, batch 55800, loss[loss=2.242, over 6720.00 frames. , ppl: 9.40941830627468] tot_loss[loss=2.341, over 5451166.83 frames. , ppl: 10.391365008612409], batch size: 70
+2022-12-10 14:30:15,194 INFO [train.py:421] (7/8) Epoch 2, batch 56000, loss[loss=2.408, over 2380.00 frames. , ppl: 11.115060454583041] tot_loss[loss=2.342, over 5427557.72 frames. , ppl: 10.400088009814475], batch size: 70
+2022-12-10 14:30:15,195 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 14:30:15,958 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.327, over 211138.00 frames. , ppl: 10.2458754038067
+2022-12-10 14:31:57,770 INFO [train.py:421] (7/8) Epoch 2, batch 56200, loss[loss=2.226, over 6300.00 frames. , ppl: 9.26067471803392] tot_loss[loss=2.343, over 5399439.08 frames. , ppl: 10.40727617260381], batch size: 70
+2022-12-10 14:33:41,530 INFO [train.py:421] (7/8) Epoch 2, batch 56400, loss[loss=2.236, over 6930.00 frames. , ppl: 9.359026048090026] tot_loss[loss=2.342, over 5398308.60 frames. , ppl: 10.400035924942998], batch size: 70
+2022-12-10 14:35:23,939 INFO [train.py:421] (7/8) Epoch 2, batch 56600, loss[loss=2.536, over 980.00 frames. , ppl: 12.634085724936561] tot_loss[loss=2.341, over 5416652.23 frames. , ppl: 10.393836144354504], batch size: 70
+2022-12-10 14:37:04,931 INFO [train.py:421] (7/8) Epoch 2, batch 56800, loss[loss=2.327, over 2590.00 frames. , ppl: 10.24468020640906] tot_loss[loss=2.341, over 5398359.93 frames. , ppl: 10.396529667597054], batch size: 70
+2022-12-10 14:38:48,270 INFO [train.py:421] (7/8) Epoch 2, batch 57000, loss[loss=2.411, over 910.00 frames. , ppl: 11.141504310046079] tot_loss[loss=2.341, over 5387005.32 frames. , ppl: 10.395900116302526], batch size: 70
+2022-12-10 14:38:48,271 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 14:38:49,030 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.324, over 211138.00 frames. , ppl: 10.216746149309023
+2022-12-10 14:40:28,410 INFO [train.py:421] (7/8) Epoch 2, batch 57200, loss[loss=2.378, over 2800.00 frames. , ppl: 10.786133456679302] tot_loss[loss=2.341, over 5373185.21 frames. , ppl: 10.394472825029814], batch size: 70
+2022-12-10 14:42:06,874 INFO [train.py:421] (7/8) Epoch 2, batch 57400, loss[loss=2.357, over 2100.00 frames. , ppl: 10.55644829665624] tot_loss[loss=2.341, over 5359388.68 frames. , ppl: 10.39455603388031], batch size: 70
+2022-12-10 14:43:46,026 INFO [train.py:421] (7/8) Epoch 2, batch 57600, loss[loss=2.408, over 2100.00 frames. , ppl: 11.110892875588041] tot_loss[loss=2.342, over 5345627.66 frames. , ppl: 10.40413196460975], batch size: 70
+2022-12-10 14:45:24,393 INFO [train.py:421] (7/8) Epoch 2, batch 57800, loss[loss=2.365, over 2100.00 frames. , ppl: 10.643798755167602] tot_loss[loss=2.341, over 5362395.65 frames. , ppl: 10.394604474026787], batch size: 70
+2022-12-10 14:47:02,165 INFO [train.py:421] (7/8) Epoch 2, batch 58000, loss[loss=2.218, over 5670.00 frames. , ppl: 9.189362815604625] tot_loss[loss=2.341, over 5362058.73 frames. , ppl: 10.394191619343314], batch size: 70
+2022-12-10 14:47:02,165 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 14:47:02,926 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.325, over 211138.00 frames. , ppl: 10.22471528659933
+2022-12-10 14:48:40,205 INFO [train.py:421] (7/8) Epoch 2, batch 58200, loss[loss=2.929, over 630.00 frames. , ppl: 18.704338510345867] tot_loss[loss=2.34, over 5448947.67 frames. , ppl: 10.379679191165891], batch size: 70
+2022-12-10 14:50:20,525 INFO [train.py:421] (7/8) Epoch 2, batch 58400, loss[loss=2.481, over 1260.00 frames. , ppl: 11.948960638475617] tot_loss[loss=2.34, over 5447026.84 frames. , ppl: 10.385291600287776], batch size: 70
+2022-12-10 14:51:59,909 INFO [train.py:421] (7/8) Epoch 2, batch 58600, loss[loss=2.254, over 4130.00 frames. , ppl: 9.521789258362368] tot_loss[loss=2.341, over 5448634.89 frames. , ppl: 10.38920376548734], batch size: 70
+2022-12-10 14:53:41,811 INFO [train.py:421] (7/8) Epoch 2, batch 58800, loss[loss=2.279, over 4620.00 frames. , ppl: 9.770878385116243] tot_loss[loss=2.341, over 5458119.09 frames. , ppl: 10.39011426596567], batch size: 70
+2022-12-10 14:55:21,056 INFO [train.py:421] (7/8) Epoch 2, batch 59000, loss[loss=2.343, over 1750.00 frames. , ppl: 10.413728669465014] tot_loss[loss=2.341, over 5452559.58 frames. , ppl: 10.388440848953705], batch size: 70
+2022-12-10 14:55:21,056 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 14:55:21,801 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.325, over 211138.00 frames. , ppl: 10.225733811230693
+2022-12-10 14:57:02,578 INFO [train.py:421] (7/8) Epoch 2, batch 59200, loss[loss=2.51, over 980.00 frames. , ppl: 12.308618953351578] tot_loss[loss=2.341, over 5451413.17 frames. , ppl: 10.389456773017045], batch size: 70
+2022-12-10 14:58:41,106 INFO [train.py:421] (7/8) Epoch 2, batch 59400, loss[loss=2.321, over 5250.00 frames. , ppl: 10.185316992079576] tot_loss[loss=2.341, over 5443895.11 frames. , ppl: 10.396267874376521], batch size: 70
+2022-12-10 15:00:19,437 INFO [train.py:421] (7/8) Epoch 2, batch 59600, loss[loss=3.035, over 560.00 frames. , ppl: 20.807947307310407] tot_loss[loss=2.341, over 5464283.43 frames. , ppl: 10.390658159713102], batch size: 70
+2022-12-10 15:02:02,512 INFO [train.py:421] (7/8) Epoch 2, batch 59800, loss[loss=2.438, over 1260.00 frames. , ppl: 11.451012877489983] tot_loss[loss=2.342, over 5448047.92 frames. , ppl: 10.399740789294244], batch size: 70
+2022-12-10 15:03:44,827 INFO [train.py:421] (7/8) Epoch 2, batch 60000, loss[loss=2.316, over 4060.00 frames. , ppl: 10.130344051704904] tot_loss[loss=2.341, over 5465013.11 frames. , ppl: 10.393832297991082], batch size: 70
+2022-12-10 15:03:44,827 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 15:03:45,573 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.324, over 211138.00 frames. , ppl: 10.21343657885031
+2022-12-10 15:05:24,018 INFO [train.py:421] (7/8) Epoch 2, batch 60200, loss[loss=2.273, over 5670.00 frames. , ppl: 9.711556734475383] tot_loss[loss=2.341, over 5477658.73 frames. , ppl: 10.396241938712214], batch size: 70
+2022-12-10 15:07:02,398 INFO [train.py:421] (7/8) Epoch 2, batch 60400, loss[loss=2.427, over 2380.00 frames. , ppl: 11.327060512665193] tot_loss[loss=2.342, over 5455769.42 frames. , ppl: 10.400562021031964], batch size: 70
+2022-12-10 15:08:40,165 INFO [train.py:421] (7/8) Epoch 2, batch 60600, loss[loss=2.215, over 2800.00 frames. , ppl: 9.157765658318205] tot_loss[loss=2.342, over 5416804.32 frames. , ppl: 10.404104768543068], batch size: 70
+2022-12-10 15:10:20,018 INFO [train.py:421] (7/8) Epoch 2, batch 60800, loss[loss=2.508, over 980.00 frames. , ppl: 12.280679365359662] tot_loss[loss=2.343, over 5382384.29 frames. , ppl: 10.410686754221132], batch size: 70
+2022-12-10 15:11:55,176 INFO [train.py:421] (7/8) Epoch 2, batch 61000, loss[loss=2.372, over 1820.00 frames. , ppl: 10.72102898630458] tot_loss[loss=2.343, over 5349179.22 frames. , ppl: 10.416419097728468], batch size: 70
+2022-12-10 15:11:55,176 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 15:11:55,926 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.324, over 211138.00 frames. , ppl: 10.211778417126597
+2022-12-10 15:13:35,398 INFO [train.py:421] (7/8) Epoch 2, batch 61200, loss[loss=2.269, over 2170.00 frames. , ppl: 9.669632604177348] tot_loss[loss=2.342, over 5385204.06 frames. , ppl: 10.401480844424208], batch size: 70
+2022-12-10 15:15:14,572 INFO [train.py:421] (7/8) Epoch 2, batch 61400, loss[loss=2.535, over 1050.00 frames. , ppl: 12.612477099009489] tot_loss[loss=2.342, over 5377197.42 frames. , ppl: 10.406122828800845], batch size: 70
+2022-12-10 15:16:52,146 INFO [train.py:421] (7/8) Epoch 2, batch 61600, loss[loss=2.296, over 3220.00 frames. , ppl: 9.932300647343537] tot_loss[loss=2.343, over 5365857.66 frames. , ppl: 10.415422961316013], batch size: 70
+2022-12-10 15:18:32,315 INFO [train.py:421] (7/8) Epoch 2, batch 61800, loss[loss=2.636, over 700.00 frames. , ppl: 13.955443731331547] tot_loss[loss=2.343, over 5377767.57 frames. , ppl: 10.414711750933755], batch size: 70
+2022-12-10 15:20:14,993 INFO [train.py:421] (7/8) Epoch 2, batch 62000, loss[loss=2.363, over 4830.00 frames. , ppl: 10.618355024810757] tot_loss[loss=2.342, over 5416806.21 frames. , ppl: 10.399613592684819], batch size: 70
+2022-12-10 15:20:14,993 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 15:20:15,753 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.324, over 211138.00 frames. , ppl: 10.219063032959546
+2022-12-10 15:21:54,099 INFO [train.py:421] (7/8) Epoch 2, batch 62200, loss[loss=2.202, over 4130.00 frames. , ppl: 9.044802561846637] tot_loss[loss=2.341, over 5452032.45 frames. , ppl: 10.389337979771238], batch size: 70
+2022-12-10 15:23:35,865 INFO [train.py:421] (7/8) Epoch 2, batch 62400, loss[loss=2.465, over 1470.00 frames. , ppl: 11.76190405629796] tot_loss[loss=2.34, over 5454736.13 frames. , ppl: 10.384790269259687], batch size: 70
+2022-12-10 15:25:13,343 INFO [train.py:421] (7/8) Epoch 2, batch 62600, loss[loss=2.283, over 9030.00 frames. , ppl: 9.801811581394224] tot_loss[loss=2.342, over 5440629.94 frames. , ppl: 10.398369193764477], batch size: 70
+2022-12-10 15:26:54,709 INFO [train.py:421] (7/8) Epoch 2, batch 62800, loss[loss=2.348, over 2450.00 frames. , ppl: 10.464526108757854] tot_loss[loss=2.34, over 5478845.33 frames. , ppl: 10.38309622711988], batch size: 70
+2022-12-10 15:28:32,241 INFO [train.py:421] (7/8) Epoch 2, batch 63000, loss[loss=3.093, over 560.00 frames. , ppl: 22.050440149623274] tot_loss[loss=2.339, over 5500232.85 frames. , ppl: 10.369944418931976], batch size: 70
+2022-12-10 15:28:32,242 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 15:28:33,000 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.323, over 211138.00 frames. , ppl: 10.20283624301792
+2022-12-10 15:30:14,781 INFO [train.py:421] (7/8) Epoch 2, batch 63200, loss[loss=2.843, over 630.00 frames. , ppl: 17.16025494940483] tot_loss[loss=2.338, over 5531160.67 frames. , ppl: 10.363528905002052], batch size: 70
+2022-12-10 15:31:59,064 INFO [train.py:421] (7/8) Epoch 2, batch 63400, loss[loss=2.498, over 1750.00 frames. , ppl: 12.154259536696244] tot_loss[loss=2.338, over 5515634.84 frames. , ppl: 10.362585724282459], batch size: 70
+2022-12-10 15:33:37,719 INFO [train.py:421] (7/8) Epoch 2, batch 63600, loss[loss=2.706, over 1050.00 frames. , ppl: 14.963812190096089] tot_loss[loss=2.338, over 5528578.54 frames. , ppl: 10.359603059882517], batch size: 70
+2022-12-10 15:35:17,820 INFO [train.py:421] (7/8) Epoch 2, batch 63800, loss[loss=2.816, over 630.00 frames. , ppl: 16.709503803284722] tot_loss[loss=2.338, over 5529675.81 frames. , ppl: 10.362604864920728], batch size: 70
+2022-12-10 15:36:57,204 INFO [train.py:421] (7/8) Epoch 2, batch 64000, loss[loss=2.311, over 2030.00 frames. , ppl: 10.087786948515795] tot_loss[loss=2.338, over 5512643.02 frames. , ppl: 10.35755969419752], batch size: 70
+2022-12-10 15:36:57,204 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 15:36:57,966 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.324, over 211138.00 frames. , ppl: 10.220371427142487
+2022-12-10 15:38:37,721 INFO [train.py:421] (7/8) Epoch 2, batch 64200, loss[loss=2.398, over 1820.00 frames. , ppl: 11.003518558145032] tot_loss[loss=2.339, over 5479764.29 frames. , ppl: 10.36593327849837], batch size: 70
+2022-12-10 15:40:17,494 INFO [train.py:421] (7/8) Epoch 2, batch 64400, loss[loss=2.408, over 1680.00 frames. , ppl: 11.116112989217728] tot_loss[loss=2.338, over 5526966.81 frames. , ppl: 10.359635488578014], batch size: 70
+2022-12-10 15:41:55,772 INFO [train.py:421] (7/8) Epoch 2, batch 64600, loss[loss=2.619, over 770.00 frames. , ppl: 13.721666334535863] tot_loss[loss=2.338, over 5524272.88 frames. , ppl: 10.355549221325687], batch size: 70
+2022-12-10 15:43:33,789 INFO [train.py:421] (7/8) Epoch 2, batch 64800, loss[loss=2.264, over 3850.00 frames. , ppl: 9.618541813142464] tot_loss[loss=2.338, over 5528798.42 frames. , ppl: 10.363354248628466], batch size: 70
+2022-12-10 15:45:14,670 INFO [train.py:421] (7/8) Epoch 2, batch 65000, loss[loss=2.275, over 7000.00 frames. , ppl: 9.72418490337189] tot_loss[loss=2.339, over 5533012.91 frames. , ppl: 10.372004799423921], batch size: 70
+2022-12-10 15:45:14,670 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 15:45:15,399 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.323, over 211138.00 frames. , ppl: 10.211031803223284
+2022-12-10 15:46:58,769 INFO [train.py:421] (7/8) Epoch 2, batch 65200, loss[loss=2.624, over 770.00 frames. , ppl: 13.789621848529176] tot_loss[loss=2.338, over 5556222.41 frames. , ppl: 10.365250228208643], batch size: 70
+2022-12-10 15:48:38,205 INFO [train.py:421] (7/8) Epoch 2, batch 65400, loss[loss=2.573, over 1190.00 frames. , ppl: 13.105076682574225] tot_loss[loss=2.339, over 5557117.23 frames. , ppl: 10.3658395620137], batch size: 70
+2022-12-10 15:50:19,933 INFO [train.py:421] (7/8) Epoch 2, batch 65600, loss[loss=2.457, over 910.00 frames. , ppl: 11.664871275157848] tot_loss[loss=2.337, over 5600288.17 frames. , ppl: 10.35418054017422], batch size: 70
+2022-12-10 15:51:59,510 INFO [train.py:421] (7/8) Epoch 2, batch 65800, loss[loss=2.78, over 770.00 frames. , ppl: 16.124405552767076] tot_loss[loss=2.338, over 5577776.59 frames. , ppl: 10.359026250848874], batch size: 70
+2022-12-10 15:53:41,831 INFO [train.py:421] (7/8) Epoch 2, batch 66000, loss[loss=2.314, over 2520.00 frames. , ppl: 10.115513651490474] tot_loss[loss=2.336, over 5618877.57 frames. , ppl: 10.337367855472236], batch size: 70
+2022-12-10 15:53:41,831 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 15:53:42,595 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.321, over 211138.00 frames. , ppl: 10.187981682837393
+2022-12-10 15:55:24,781 INFO [train.py:421] (7/8) Epoch 2, batch 66200, loss[loss=2.226, over 8890.00 frames. , ppl: 9.263486411997125] tot_loss[loss=2.336, over 5614322.06 frames. , ppl: 10.335248330370508], batch size: 70
+2022-12-10 15:57:04,876 INFO [train.py:421] (7/8) Epoch 2, batch 66400, loss[loss=2.468, over 1190.00 frames. , ppl: 11.804563145871175] tot_loss[loss=2.336, over 5596433.51 frames. , ppl: 10.336902549175425], batch size: 70
+2022-12-10 15:58:43,336 INFO [train.py:421] (7/8) Epoch 2, batch 66600, loss[loss=2.453, over 1680.00 frames. , ppl: 11.624272331246603] tot_loss[loss=2.336, over 5568834.11 frames. , ppl: 10.3406514281434], batch size: 70
+2022-12-10 16:00:20,767 INFO [train.py:421] (7/8) Epoch 2, batch 66800, loss[loss=2.962, over 560.00 frames. , ppl: 19.338637067731597] tot_loss[loss=2.336, over 5562011.65 frames. , ppl: 10.3359651925891], batch size: 70
+2022-12-10 16:02:02,722 INFO [train.py:421] (7/8) Epoch 2, batch 67000, loss[loss=2.65, over 980.00 frames. , ppl: 14.150273273864592] tot_loss[loss=2.336, over 5515533.54 frames. , ppl: 10.336825819590102], batch size: 70
+2022-12-10 16:02:02,723 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 16:02:03,483 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.323, over 211138.00 frames. , ppl: 10.203262098954827
+2022-12-10 16:03:41,290 INFO [train.py:421] (7/8) Epoch 2, batch 67200, loss[loss=2.272, over 1540.00 frames. , ppl: 9.69637377989177] tot_loss[loss=2.335, over 5533222.69 frames. , ppl: 10.331610288114952], batch size: 70
+2022-12-10 16:05:20,742 INFO [train.py:421] (7/8) Epoch 2, batch 67400, loss[loss=2.289, over 3990.00 frames. , ppl: 9.867437457661222] tot_loss[loss=2.336, over 5533839.69 frames. , ppl: 10.335551147774652], batch size: 70
+2022-12-10 16:07:01,226 INFO [train.py:421] (7/8) Epoch 2, batch 67600, loss[loss=2.764, over 770.00 frames. , ppl: 15.863415946688297] tot_loss[loss=2.336, over 5534301.45 frames. , ppl: 10.337173174997554], batch size: 70
+2022-12-10 16:08:44,332 INFO [train.py:421] (7/8) Epoch 2, batch 67800, loss[loss=2.294, over 1470.00 frames. , ppl: 9.91668162179997] tot_loss[loss=2.335, over 5579634.43 frames. , ppl: 10.327838385748395], batch size: 70
+2022-12-10 16:10:23,874 INFO [train.py:421] (7/8) Epoch 2, batch 68000, loss[loss=2.305, over 3150.00 frames. , ppl: 10.027905070323504] tot_loss[loss=2.335, over 5588359.23 frames. , ppl: 10.329113021966046], batch size: 70
+2022-12-10 16:10:23,875 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 16:10:24,633 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.323, over 211138.00 frames. , ppl: 10.201776210751579
+2022-12-10 16:12:06,512 INFO [train.py:421] (7/8) Epoch 2, batch 68200, loss[loss=2.255, over 9240.00 frames. , ppl: 9.53791710218081] tot_loss[loss=2.335, over 5568757.97 frames. , ppl: 10.332127115152693], batch size: 70
+2022-12-10 16:13:47,729 INFO [train.py:421] (7/8) Epoch 2, batch 68400, loss[loss=2.342, over 2310.00 frames. , ppl: 10.405839829184869] tot_loss[loss=2.334, over 5613251.81 frames. , ppl: 10.320514777374424], batch size: 70
+2022-12-10 16:15:28,277 INFO [train.py:421] (7/8) Epoch 2, batch 68600, loss[loss=2.311, over 3150.00 frames. , ppl: 10.088950521506879] tot_loss[loss=2.334, over 5612534.74 frames. , ppl: 10.318710367265293], batch size: 70
+2022-12-10 16:17:07,770 INFO [train.py:421] (7/8) Epoch 2, batch 68800, loss[loss=2.259, over 5810.00 frames. , ppl: 9.568972610232139] tot_loss[loss=2.334, over 5632184.70 frames. , ppl: 10.31681832562201], batch size: 70
+2022-12-10 16:18:50,959 INFO [train.py:421] (7/8) Epoch 2, batch 69000, loss[loss=2.327, over 3010.00 frames. , ppl: 10.245789330173086] tot_loss[loss=2.334, over 5617124.56 frames. , ppl: 10.323067625230598], batch size: 70
+2022-12-10 16:18:50,960 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 16:18:51,729 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.32, over 211138.00 frames. , ppl: 10.176567267443412
+2022-12-10 16:20:33,668 INFO [train.py:421] (7/8) Epoch 2, batch 69200, loss[loss=2.543, over 910.00 frames. , ppl: 12.721253007309533] tot_loss[loss=2.335, over 5562982.22 frames. , ppl: 10.332532808389713], batch size: 70
+2022-12-10 16:22:12,410 INFO [train.py:421] (7/8) Epoch 2, batch 69400, loss[loss=2.302, over 3360.00 frames. , ppl: 9.994780315601526] tot_loss[loss=2.336, over 5538503.53 frames. , ppl: 10.339299471977052], batch size: 70
+2022-12-10 16:23:54,609 INFO [train.py:421] (7/8) Epoch 2, batch 69600, loss[loss=2.351, over 3290.00 frames. , ppl: 10.495780270593892] tot_loss[loss=2.335, over 5591923.19 frames. , ppl: 10.329771689609936], batch size: 70
+2022-12-10 16:25:37,453 INFO [train.py:421] (7/8) Epoch 2, batch 69800, loss[loss=2.417, over 1890.00 frames. , ppl: 11.212950826973143] tot_loss[loss=2.334, over 5622737.93 frames. , ppl: 10.317706496352693], batch size: 70
+2022-12-10 16:27:18,879 INFO [train.py:421] (7/8) Epoch 2, batch 70000, loss[loss=2.309, over 2870.00 frames. , ppl: 10.063030324414314] tot_loss[loss=2.335, over 5575331.85 frames. , ppl: 10.330070622839191], batch size: 70
+2022-12-10 16:27:18,879 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 16:27:19,638 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.322, over 211138.00 frames. , ppl: 10.191266412638488
+2022-12-10 16:29:02,810 INFO [train.py:421] (7/8) Epoch 2, batch 70200, loss[loss=2.464, over 1330.00 frames. , ppl: 11.754422392222995] tot_loss[loss=2.335, over 5586124.21 frames. , ppl: 10.326983964128694], batch size: 70
+2022-12-10 16:30:41,311 INFO [train.py:421] (7/8) Epoch 2, batch 70400, loss[loss=2.403, over 2940.00 frames. , ppl: 11.05113073161853] tot_loss[loss=2.337, over 5518690.02 frames. , ppl: 10.346202072330902], batch size: 70
+2022-12-10 16:32:24,263 INFO [train.py:421] (7/8) Epoch 2, batch 70600, loss[loss=2.307, over 9800.00 frames. , ppl: 10.042843104478775] tot_loss[loss=2.337, over 5548061.08 frames. , ppl: 10.347582430600324], batch size: 70
+2022-12-10 16:34:01,884 INFO [train.py:421] (7/8) Epoch 2, batch 70800, loss[loss=2.28, over 4340.00 frames. , ppl: 9.777998674812963] tot_loss[loss=2.336, over 5554536.68 frames. , ppl: 10.342911811931302], batch size: 70
+2022-12-10 16:35:42,855 INFO [train.py:421] (7/8) Epoch 2, batch 71000, loss[loss=2.232, over 3500.00 frames. , ppl: 9.32021099935629] tot_loss[loss=2.335, over 5609316.44 frames. , ppl: 10.332637204516768], batch size: 70
+2022-12-10 16:35:42,855 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 16:35:43,613 INFO [train.py:452] (7/8) Epoch 2, validation: loss=2.319, over 211138.00 frames. , ppl: 10.169496572570102
+2022-12-10 16:37:26,618 INFO [train.py:421] (7/8) Epoch 2, batch 71200, loss[loss=2.365, over 2170.00 frames. , ppl: 10.645618717658117] tot_loss[loss=2.336, over 5563662.28 frames. , ppl: 10.337104062790646], batch size: 70
+2022-12-10 16:39:05,518 INFO [train.py:421] (7/8) Epoch 2, batch 71400, loss[loss=2.438, over 1260.00 frames. , ppl: 11.449839205271912] tot_loss[loss=2.337, over 5533963.51 frames. , ppl: 10.34823924313534], batch size: 70
+2022-12-10 16:40:47,632 INFO [train.py:421] (7/8) Epoch 2, batch 71600, loss[loss=2.696, over 770.00 frames. , ppl: 14.823455350711297] tot_loss[loss=2.336, over 5515865.45 frames. , ppl: 10.344046339600402], batch size: 70
+2022-12-10 16:42:29,323 INFO [train.py:421] (7/8) Epoch 2, batch 71800, loss[loss=2.824, over 770.00 frames. , ppl: 16.84487179951393] tot_loss[loss=2.337, over 5508653.16 frames. , ppl: 10.34948722874659], batch size: 70
+2022-12-10 16:43:45,588 INFO [train.py:421] (7/8) Epoch 3, batch 0, loss[loss=2.492, over 1120.00 frames. , ppl: 12.090637861234578] tot_loss[loss=2.492, over 1120.00 frames. , ppl: 12.090637861234578], batch size: 70
+2022-12-10 16:45:28,193 INFO [train.py:421] (7/8) Epoch 3, batch 200, loss[loss=2.268, over 6650.00 frames. , ppl: 9.664526990936947] tot_loss[loss=2.331, over 548965.49 frames. , ppl: 10.287956778073513], batch size: 70
+2022-12-10 16:47:09,532 INFO [train.py:421] (7/8) Epoch 3, batch 400, loss[loss=2.467, over 1400.00 frames. , ppl: 11.788735143146944] tot_loss[loss=2.331, over 1007047.18 frames. , ppl: 10.29090395024398], batch size: 70
+2022-12-10 16:48:48,730 INFO [train.py:421] (7/8) Epoch 3, batch 600, loss[loss=2.453, over 1400.00 frames. , ppl: 11.625152131244151] tot_loss[loss=2.329, over 1432580.78 frames. , ppl: 10.27076178259887], batch size: 70
+2022-12-10 16:50:28,169 INFO [train.py:421] (7/8) Epoch 3, batch 800, loss[loss=2.571, over 1190.00 frames. , ppl: 13.077431710359017] tot_loss[loss=2.329, over 1815592.86 frames. , ppl: 10.266692993524313], batch size: 70
+2022-12-10 16:52:09,311 INFO [train.py:421] (7/8) Epoch 3, batch 1000, loss[loss=2.301, over 2030.00 frames. , ppl: 9.985075589052384] tot_loss[loss=2.331, over 2131837.11 frames. , ppl: 10.285835331146595], batch size: 70
+2022-12-10 16:52:09,312 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 16:52:10,090 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.319, over 211138.00 frames. , ppl: 10.164404381725806
+2022-12-10 16:53:53,057 INFO [train.py:421] (7/8) Epoch 3, batch 1200, loss[loss=2.529, over 980.00 frames. , ppl: 12.545395114075491] tot_loss[loss=2.329, over 2456418.76 frames. , ppl: 10.270864820912577], batch size: 70
+2022-12-10 16:55:35,529 INFO [train.py:421] (7/8) Epoch 3, batch 1400, loss[loss=2.274, over 5810.00 frames. , ppl: 9.717134980941147] tot_loss[loss=2.329, over 2745361.63 frames. , ppl: 10.26649769749629], batch size: 70
+2022-12-10 16:57:16,468 INFO [train.py:421] (7/8) Epoch 3, batch 1600, loss[loss=2.324, over 4130.00 frames. , ppl: 10.213014541198586] tot_loss[loss=2.329, over 3003918.75 frames. , ppl: 10.267461083926797], batch size: 70
+2022-12-10 16:58:58,252 INFO [train.py:421] (7/8) Epoch 3, batch 1800, loss[loss=2.236, over 5670.00 frames. , ppl: 9.359928628909431] tot_loss[loss=2.327, over 3252401.63 frames. , ppl: 10.25012237862639], batch size: 70
+2022-12-10 17:00:33,686 INFO [train.py:421] (7/8) Epoch 3, batch 2000, loss[loss=4.091, over 350.00 frames. , ppl: 59.81916127948638] tot_loss[loss=2.329, over 3420255.30 frames. , ppl: 10.26996705732681], batch size: 70
+2022-12-10 17:00:33,687 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 17:00:34,445 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.321, over 211138.00 frames. , ppl: 10.184881917574328
+2022-12-10 17:02:13,490 INFO [train.py:421] (7/8) Epoch 3, batch 2200, loss[loss=2.416, over 3080.00 frames. , ppl: 11.200400278249065] tot_loss[loss=2.33, over 3611378.28 frames. , ppl: 10.273945547026907], batch size: 70
+2022-12-10 17:03:54,053 INFO [train.py:421] (7/8) Epoch 3, batch 2400, loss[loss=2.399, over 1260.00 frames. , ppl: 11.012350667143602] tot_loss[loss=2.327, over 3810624.62 frames. , ppl: 10.25001850747046], batch size: 70
+2022-12-10 17:05:32,323 INFO [train.py:421] (7/8) Epoch 3, batch 2600, loss[loss=2.253, over 4130.00 frames. , ppl: 9.511606748914028] tot_loss[loss=2.329, over 3911700.56 frames. , ppl: 10.269160141421498], batch size: 70
+2022-12-10 17:07:12,598 INFO [train.py:421] (7/8) Epoch 3, batch 2800, loss[loss=2.46, over 1820.00 frames. , ppl: 11.706006148905287] tot_loss[loss=2.329, over 4054229.91 frames. , ppl: 10.266804641870248], batch size: 70
+2022-12-10 17:08:55,682 INFO [train.py:421] (7/8) Epoch 3, batch 3000, loss[loss=2.848, over 630.00 frames. , ppl: 17.2467028356082] tot_loss[loss=2.329, over 4221289.52 frames. , ppl: 10.2633720250658], batch size: 70
+2022-12-10 17:08:55,683 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 17:08:56,443 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.32, over 211138.00 frames. , ppl: 10.171098190408838
+2022-12-10 17:10:38,823 INFO [train.py:421] (7/8) Epoch 3, batch 3200, loss[loss=2.302, over 3640.00 frames. , ppl: 9.998954885322188] tot_loss[loss=2.327, over 4382935.66 frames. , ppl: 10.243617622542228], batch size: 70
+2022-12-10 17:12:18,589 INFO [train.py:421] (7/8) Epoch 3, batch 3400, loss[loss=2.272, over 2870.00 frames. , ppl: 9.693990447346136] tot_loss[loss=2.328, over 4439262.96 frames. , ppl: 10.25941589026314], batch size: 70
+2022-12-10 17:13:58,760 INFO [train.py:421] (7/8) Epoch 3, batch 3600, loss[loss=2.428, over 2380.00 frames. , ppl: 11.331214015173048] tot_loss[loss=2.328, over 4546514.62 frames. , ppl: 10.260642933972864], batch size: 70
+2022-12-10 17:15:38,953 INFO [train.py:421] (7/8) Epoch 3, batch 3800, loss[loss=2.247, over 3360.00 frames. , ppl: 9.463961126100175] tot_loss[loss=2.328, over 4675242.56 frames. , ppl: 10.2554695813205], batch size: 70
+2022-12-10 17:17:17,265 INFO [train.py:421] (7/8) Epoch 3, batch 4000, loss[loss=2.286, over 3990.00 frames. , ppl: 9.834088552255956] tot_loss[loss=2.329, over 4757240.96 frames. , ppl: 10.263766041884494], batch size: 70
+2022-12-10 17:17:17,266 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 17:17:18,024 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.319, over 211138.00 frames. , ppl: 10.163163321129922
+2022-12-10 17:18:57,022 INFO [train.py:421] (7/8) Epoch 3, batch 4200, loss[loss=2.457, over 1330.00 frames. , ppl: 11.666719489216426] tot_loss[loss=2.328, over 4831776.45 frames. , ppl: 10.256620941069965], batch size: 70
+2022-12-10 17:20:36,279 INFO [train.py:421] (7/8) Epoch 3, batch 4400, loss[loss=2.523, over 1050.00 frames. , ppl: 12.460471876228086] tot_loss[loss=2.329, over 4878823.80 frames. , ppl: 10.263537897405806], batch size: 70
+2022-12-10 17:22:15,217 INFO [train.py:421] (7/8) Epoch 3, batch 4600, loss[loss=2.42, over 1820.00 frames. , ppl: 11.24206081020934] tot_loss[loss=2.329, over 4943247.15 frames. , ppl: 10.263493808838382], batch size: 70
+2022-12-10 17:23:55,352 INFO [train.py:421] (7/8) Epoch 3, batch 4800, loss[loss=2.711, over 770.00 frames. , ppl: 15.044884150330903] tot_loss[loss=2.329, over 4974756.93 frames. , ppl: 10.267609128707928], batch size: 70
+2022-12-10 17:25:31,818 INFO [train.py:421] (7/8) Epoch 3, batch 5000, loss[loss=2.433, over 1540.00 frames. , ppl: 11.394542130388633] tot_loss[loss=2.329, over 5021137.02 frames. , ppl: 10.269969655653265], batch size: 70
+2022-12-10 17:25:31,819 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 17:25:32,565 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.319, over 211138.00 frames. , ppl: 10.167579177724292
+2022-12-10 17:27:12,749 INFO [train.py:421] (7/8) Epoch 3, batch 5200, loss[loss=6.292, over 210.00 frames. , ppl: 540.4838592442532] tot_loss[loss=2.33, over 5051571.97 frames. , ppl: 10.279261644579579], batch size: 70
+2022-12-10 17:28:53,461 INFO [train.py:421] (7/8) Epoch 3, batch 5400, loss[loss=2.996, over 560.00 frames. , ppl: 20.00840840254058] tot_loss[loss=2.331, over 5059197.24 frames. , ppl: 10.284135393262636], batch size: 70
+2022-12-10 17:30:38,110 INFO [train.py:421] (7/8) Epoch 3, batch 5600, loss[loss=2.669, over 1260.00 frames. , ppl: 14.422372034202207] tot_loss[loss=2.33, over 5128240.64 frames. , ppl: 10.28087670182978], batch size: 70
+2022-12-10 17:32:21,541 INFO [train.py:421] (7/8) Epoch 3, batch 5800, loss[loss=2.915, over 630.00 frames. , ppl: 18.455736439016178] tot_loss[loss=2.329, over 5215843.84 frames. , ppl: 10.264268216249837], batch size: 70
+2022-12-10 17:34:02,534 INFO [train.py:421] (7/8) Epoch 3, batch 6000, loss[loss=2.225, over 5390.00 frames. , ppl: 9.25208801946668] tot_loss[loss=2.33, over 5220636.80 frames. , ppl: 10.27463167116271], batch size: 70
+2022-12-10 17:34:02,535 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 17:34:03,279 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.317, over 211138.00 frames. , ppl: 10.146697899157441
+2022-12-10 17:35:42,386 INFO [train.py:421] (7/8) Epoch 3, batch 6200, loss[loss=2.759, over 700.00 frames. , ppl: 15.787762937042233] tot_loss[loss=2.33, over 5231778.64 frames. , ppl: 10.276530549447891], batch size: 70
+2022-12-10 17:37:19,188 INFO [train.py:421] (7/8) Epoch 3, batch 6400, loss[loss=2.351, over 910.00 frames. , ppl: 10.495445666086734] tot_loss[loss=2.33, over 5211190.75 frames. , ppl: 10.277750948245822], batch size: 70
+2022-12-10 17:38:59,205 INFO [train.py:421] (7/8) Epoch 3, batch 6600, loss[loss=2.239, over 6440.00 frames. , ppl: 9.381737515385073] tot_loss[loss=2.329, over 5238410.49 frames. , ppl: 10.271563871677689], batch size: 70
+2022-12-10 17:40:37,940 INFO [train.py:421] (7/8) Epoch 3, batch 6800, loss[loss=2.443, over 910.00 frames. , ppl: 11.508504219731202] tot_loss[loss=2.33, over 5258298.87 frames. , ppl: 10.277713931152928], batch size: 70
+2022-12-10 17:42:18,036 INFO [train.py:421] (7/8) Epoch 3, batch 7000, loss[loss=3, over 560.00 frames. , ppl: 20.077311782843474] tot_loss[loss=2.331, over 5257686.33 frames. , ppl: 10.286620932459334], batch size: 70
+2022-12-10 17:42:18,037 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 17:42:18,803 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.318, over 211138.00 frames. , ppl: 10.159209485439936
+2022-12-10 17:44:00,387 INFO [train.py:421] (7/8) Epoch 3, batch 7200, loss[loss=2.253, over 2170.00 frames. , ppl: 9.516955971726455] tot_loss[loss=2.329, over 5317039.48 frames. , ppl: 10.269383105142852], batch size: 70
+2022-12-10 17:45:38,827 INFO [train.py:421] (7/8) Epoch 3, batch 7400, loss[loss=2.265, over 4480.00 frames. , ppl: 9.629917930923241] tot_loss[loss=2.33, over 5332511.60 frames. , ppl: 10.282285552767352], batch size: 70
+2022-12-10 17:47:16,694 INFO [train.py:421] (7/8) Epoch 3, batch 7600, loss[loss=2.504, over 1120.00 frames. , ppl: 12.235166601721055] tot_loss[loss=2.331, over 5309660.52 frames. , ppl: 10.292072420034518], batch size: 70
+2022-12-10 17:48:56,788 INFO [train.py:421] (7/8) Epoch 3, batch 7800, loss[loss=3.411, over 490.00 frames. , ppl: 30.302726541033355] tot_loss[loss=2.331, over 5335026.50 frames. , ppl: 10.289454955133829], batch size: 70
+2022-12-10 17:50:40,363 INFO [train.py:421] (7/8) Epoch 3, batch 8000, loss[loss=2.329, over 2030.00 frames. , ppl: 10.268721471676669] tot_loss[loss=2.33, over 5376691.74 frames. , ppl: 10.275346075198046], batch size: 70
+2022-12-10 17:50:40,364 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 17:50:41,126 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.318, over 211138.00 frames. , ppl: 10.153032911836572
+2022-12-10 17:52:20,458 INFO [train.py:421] (7/8) Epoch 3, batch 8200, loss[loss=2.442, over 1260.00 frames. , ppl: 11.492623780046882] tot_loss[loss=2.33, over 5362032.71 frames. , ppl: 10.282723369512292], batch size: 70
+2022-12-10 17:53:58,391 INFO [train.py:421] (7/8) Epoch 3, batch 8400, loss[loss=2.605, over 1120.00 frames. , ppl: 13.532545006076088] tot_loss[loss=2.33, over 5406130.39 frames. , ppl: 10.275222054845779], batch size: 70
+2022-12-10 17:55:40,042 INFO [train.py:421] (7/8) Epoch 3, batch 8600, loss[loss=2.467, over 1610.00 frames. , ppl: 11.783661199353647] tot_loss[loss=2.328, over 5489080.98 frames. , ppl: 10.255049234753603], batch size: 70
+2022-12-10 17:57:23,066 INFO [train.py:421] (7/8) Epoch 3, batch 8800, loss[loss=2.824, over 630.00 frames. , ppl: 16.83686141680067] tot_loss[loss=2.328, over 5468752.34 frames. , ppl: 10.261609840257423], batch size: 70
+2022-12-10 17:59:05,018 INFO [train.py:421] (7/8) Epoch 3, batch 9000, loss[loss=2.474, over 1260.00 frames. , ppl: 11.870472949840966] tot_loss[loss=2.328, over 5502114.48 frames. , ppl: 10.25617562347189], batch size: 70
+2022-12-10 17:59:05,019 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 17:59:05,778 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.318, over 211138.00 frames. , ppl: 10.158504303301722
+2022-12-10 18:00:47,946 INFO [train.py:421] (7/8) Epoch 3, batch 9200, loss[loss=2.438, over 2310.00 frames. , ppl: 11.450409386390039] tot_loss[loss=2.327, over 5541520.88 frames. , ppl: 10.250293188229868], batch size: 70
+2022-12-10 18:02:28,019 INFO [train.py:421] (7/8) Epoch 3, batch 9400, loss[loss=2.317, over 1890.00 frames. , ppl: 10.147651203351966] tot_loss[loss=2.327, over 5584067.40 frames. , ppl: 10.242773226005037], batch size: 70
+2022-12-10 18:04:09,126 INFO [train.py:421] (7/8) Epoch 3, batch 9600, loss[loss=2.38, over 1330.00 frames. , ppl: 10.806982852411876] tot_loss[loss=2.327, over 5560657.66 frames. , ppl: 10.242224224451947], batch size: 70
+2022-12-10 18:05:47,177 INFO [train.py:421] (7/8) Epoch 3, batch 9800, loss[loss=2.343, over 2310.00 frames. , ppl: 10.410917645077223] tot_loss[loss=2.328, over 5524048.63 frames. , ppl: 10.257892316469785], batch size: 70
+2022-12-10 18:07:29,483 INFO [train.py:421] (7/8) Epoch 3, batch 10000, loss[loss=2.446, over 1750.00 frames. , ppl: 11.545580630759105] tot_loss[loss=2.328, over 5504780.45 frames. , ppl: 10.260368276685071], batch size: 70
+2022-12-10 18:07:29,483 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 18:07:30,247 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.318, over 211138.00 frames. , ppl: 10.15942601173964
+2022-12-10 18:09:07,695 INFO [train.py:421] (7/8) Epoch 3, batch 10200, loss[loss=2.204, over 6580.00 frames. , ppl: 9.063574968128648] tot_loss[loss=2.328, over 5517168.55 frames. , ppl: 10.258769792654176], batch size: 70
+2022-12-10 18:10:48,660 INFO [train.py:421] (7/8) Epoch 3, batch 10400, loss[loss=2.333, over 3010.00 frames. , ppl: 10.311139982074689] tot_loss[loss=2.327, over 5548302.74 frames. , ppl: 10.246096521688981], batch size: 70
+2022-12-10 18:12:27,610 INFO [train.py:421] (7/8) Epoch 3, batch 10600, loss[loss=2.259, over 3640.00 frames. , ppl: 9.57128623818707] tot_loss[loss=2.328, over 5509153.57 frames. , ppl: 10.25275730862543], batch size: 70
+2022-12-10 18:14:05,264 INFO [train.py:421] (7/8) Epoch 3, batch 10800, loss[loss=2.38, over 1890.00 frames. , ppl: 10.802040336957312] tot_loss[loss=2.328, over 5515710.45 frames. , ppl: 10.253690437726595], batch size: 70
+2022-12-10 18:15:47,984 INFO [train.py:421] (7/8) Epoch 3, batch 11000, loss[loss=2.325, over 4550.00 frames. , ppl: 10.231272938320126] tot_loss[loss=2.326, over 5587631.70 frames. , ppl: 10.241098894093119], batch size: 70
+2022-12-10 18:15:47,985 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 18:15:48,745 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.319, over 211138.00 frames. , ppl: 10.163211456412954
+2022-12-10 18:17:26,891 INFO [train.py:421] (7/8) Epoch 3, batch 11200, loss[loss=2.334, over 3430.00 frames. , ppl: 10.31481511708664] tot_loss[loss=2.327, over 5581631.76 frames. , ppl: 10.244650121049892], batch size: 70
+2022-12-10 18:19:04,367 INFO [train.py:421] (7/8) Epoch 3, batch 11400, loss[loss=2.314, over 4340.00 frames. , ppl: 10.111648499159834] tot_loss[loss=2.327, over 5576376.33 frames. , ppl: 10.24289668937861], batch size: 70
+2022-12-10 18:20:41,828 INFO [train.py:421] (7/8) Epoch 3, batch 11600, loss[loss=2.443, over 2730.00 frames. , ppl: 11.505978860350307] tot_loss[loss=2.327, over 5589609.49 frames. , ppl: 10.243277447383171], batch size: 70
+2022-12-10 18:22:26,236 INFO [train.py:421] (7/8) Epoch 3, batch 11800, loss[loss=2.806, over 770.00 frames. , ppl: 16.536439596726197] tot_loss[loss=2.326, over 5602101.72 frames. , ppl: 10.237998591638148], batch size: 70
+2022-12-10 18:24:10,841 INFO [train.py:421] (7/8) Epoch 3, batch 12000, loss[loss=2.271, over 4690.00 frames. , ppl: 9.693880267148902] tot_loss[loss=2.326, over 5627944.69 frames. , ppl: 10.235468539036788], batch size: 70
+2022-12-10 18:24:10,842 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 18:24:11,627 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.317, over 211138.00 frames. , ppl: 10.149768016214665
+2022-12-10 18:25:51,546 INFO [train.py:421] (7/8) Epoch 3, batch 12200, loss[loss=2.752, over 700.00 frames. , ppl: 15.668130843034866] tot_loss[loss=2.327, over 5601472.02 frames. , ppl: 10.242289813316685], batch size: 70
+2022-12-10 18:27:29,144 INFO [train.py:421] (7/8) Epoch 3, batch 12400, loss[loss=2.72, over 770.00 frames. , ppl: 15.187431021278888] tot_loss[loss=2.327, over 5577121.43 frames. , ppl: 10.246344857341912], batch size: 70
+2022-12-10 18:29:06,471 INFO [train.py:421] (7/8) Epoch 3, batch 12600, loss[loss=2.484, over 1050.00 frames. , ppl: 11.989774115621893] tot_loss[loss=2.327, over 5573438.53 frames. , ppl: 10.243076405553728], batch size: 70
+2022-12-10 18:30:46,102 INFO [train.py:421] (7/8) Epoch 3, batch 12800, loss[loss=2.224, over 6720.00 frames. , ppl: 9.247385105964035] tot_loss[loss=2.325, over 5629631.94 frames. , ppl: 10.224795450699775], batch size: 70
+2022-12-10 18:32:27,345 INFO [train.py:421] (7/8) Epoch 3, batch 13000, loss[loss=2.291, over 1960.00 frames. , ppl: 9.88435638493659] tot_loss[loss=2.324, over 5674854.07 frames. , ppl: 10.21554793550185], batch size: 70
+2022-12-10 18:32:27,345 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 18:32:28,107 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.318, over 211138.00 frames. , ppl: 10.154893455412658
+2022-12-10 18:34:13,398 INFO [train.py:421] (7/8) Epoch 3, batch 13200, loss[loss=2.407, over 1400.00 frames. , ppl: 11.09705034952529] tot_loss[loss=2.324, over 5670977.38 frames. , ppl: 10.215988415697463], batch size: 70
+2022-12-10 18:35:54,364 INFO [train.py:421] (7/8) Epoch 3, batch 13400, loss[loss=2.334, over 1050.00 frames. , ppl: 10.317165472197907] tot_loss[loss=2.323, over 5691109.01 frames. , ppl: 10.20858736961999], batch size: 70
+2022-12-10 18:37:33,223 INFO [train.py:421] (7/8) Epoch 3, batch 13600, loss[loss=2.43, over 2660.00 frames. , ppl: 11.359415040522537] tot_loss[loss=2.324, over 5666797.17 frames. , ppl: 10.21244008047265], batch size: 70
+2022-12-10 18:39:15,491 INFO [train.py:421] (7/8) Epoch 3, batch 13800, loss[loss=2.333, over 3710.00 frames. , ppl: 10.308207546094426] tot_loss[loss=2.324, over 5661728.92 frames. , ppl: 10.218390868555636], batch size: 70
+2022-12-10 18:40:59,171 INFO [train.py:421] (7/8) Epoch 3, batch 14000, loss[loss=2.465, over 2030.00 frames. , ppl: 11.762852321838189] tot_loss[loss=2.324, over 5688020.66 frames. , ppl: 10.212963773070312], batch size: 70
+2022-12-10 18:40:59,172 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 18:40:59,950 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.317, over 211138.00 frames. , ppl: 10.146131741243801
+2022-12-10 18:42:39,824 INFO [train.py:421] (7/8) Epoch 3, batch 14200, loss[loss=2.286, over 4340.00 frames. , ppl: 9.832049987720712] tot_loss[loss=2.325, over 5643517.23 frames. , ppl: 10.224222380080363], batch size: 70
+2022-12-10 18:44:22,940 INFO [train.py:421] (7/8) Epoch 3, batch 14400, loss[loss=2.62, over 840.00 frames. , ppl: 13.72895128989689] tot_loss[loss=2.324, over 5676752.14 frames. , ppl: 10.21986394212402], batch size: 70
+2022-12-10 18:46:05,765 INFO [train.py:421] (7/8) Epoch 3, batch 14600, loss[loss=2.432, over 1750.00 frames. , ppl: 11.380041200328522] tot_loss[loss=2.325, over 5643254.86 frames. , ppl: 10.22523653381727], batch size: 70
+2022-12-10 18:47:46,147 INFO [train.py:421] (7/8) Epoch 3, batch 14800, loss[loss=2.321, over 2170.00 frames. , ppl: 10.186991122336364] tot_loss[loss=2.325, over 5655218.46 frames. , ppl: 10.225245618726758], batch size: 70
+2022-12-10 18:49:30,929 INFO [train.py:421] (7/8) Epoch 3, batch 15000, loss[loss=2.777, over 700.00 frames. , ppl: 16.069601930665197] tot_loss[loss=2.325, over 5645910.78 frames. , ppl: 10.225652942645592], batch size: 70
+2022-12-10 18:49:30,930 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 18:49:31,678 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.315, over 211138.00 frames. , ppl: 10.126931133917406
+2022-12-10 18:51:11,706 INFO [train.py:421] (7/8) Epoch 3, batch 15200, loss[loss=2.724, over 770.00 frames. , ppl: 15.240570372083397] tot_loss[loss=2.324, over 5679581.94 frames. , ppl: 10.216236532402721], batch size: 70
+2022-12-10 18:52:50,273 INFO [train.py:421] (7/8) Epoch 3, batch 15400, loss[loss=2.144, over 8610.00 frames. , ppl: 8.533720120033047] tot_loss[loss=2.324, over 5668528.68 frames. , ppl: 10.217833000823639], batch size: 70
+2022-12-10 18:54:28,590 INFO [train.py:421] (7/8) Epoch 3, batch 15600, loss[loss=2.252, over 6300.00 frames. , ppl: 9.508760595960638] tot_loss[loss=2.324, over 5651071.10 frames. , ppl: 10.217506965738247], batch size: 70
+2022-12-10 18:56:05,397 INFO [train.py:421] (7/8) Epoch 3, batch 15800, loss[loss=2.458, over 1680.00 frames. , ppl: 11.686508521061073] tot_loss[loss=2.324, over 5635364.19 frames. , ppl: 10.21827823104182], batch size: 70
+2022-12-10 18:57:45,623 INFO [train.py:421] (7/8) Epoch 3, batch 16000, loss[loss=2.878, over 700.00 frames. , ppl: 17.77114425068419] tot_loss[loss=2.324, over 5638740.81 frames. , ppl: 10.215469321847813], batch size: 70
+2022-12-10 18:57:45,624 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 18:57:46,369 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.316, over 211138.00 frames. , ppl: 10.134522713241985
+2022-12-10 18:59:25,144 INFO [train.py:421] (7/8) Epoch 3, batch 16200, loss[loss=2.416, over 2940.00 frames. , ppl: 11.201605827898945] tot_loss[loss=2.325, over 5578293.94 frames. , ppl: 10.23013021297224], batch size: 70
+2022-12-10 19:01:05,961 INFO [train.py:421] (7/8) Epoch 3, batch 16400, loss[loss=2.318, over 3990.00 frames. , ppl: 10.157984083476837] tot_loss[loss=2.326, over 5554529.78 frames. , ppl: 10.239487886005577], batch size: 70
+2022-12-10 19:02:45,402 INFO [train.py:421] (7/8) Epoch 3, batch 16600, loss[loss=2.496, over 1120.00 frames. , ppl: 12.132930532199797] tot_loss[loss=2.327, over 5516660.59 frames. , ppl: 10.243968995237081], batch size: 70
+2022-12-10 19:04:28,701 INFO [train.py:421] (7/8) Epoch 3, batch 16800, loss[loss=2.793, over 700.00 frames. , ppl: 16.33652942015338] tot_loss[loss=2.327, over 5526730.06 frames. , ppl: 10.243341053143013], batch size: 70
+2022-12-10 19:06:10,451 INFO [train.py:421] (7/8) Epoch 3, batch 17000, loss[loss=2.502, over 1120.00 frames. , ppl: 12.204225284356703] tot_loss[loss=2.326, over 5518444.78 frames. , ppl: 10.241242448232176], batch size: 70
+2022-12-10 19:06:10,451 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 19:06:11,210 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.317, over 211138.00 frames. , ppl: 10.149083017239782
+2022-12-10 19:07:50,801 INFO [train.py:421] (7/8) Epoch 3, batch 17200, loss[loss=2.274, over 3500.00 frames. , ppl: 9.718774889099391] tot_loss[loss=2.327, over 5484673.40 frames. , ppl: 10.250703011616647], batch size: 70
+2022-12-10 19:09:33,685 INFO [train.py:421] (7/8) Epoch 3, batch 17400, loss[loss=2.308, over 1680.00 frames. , ppl: 10.05882312318184] tot_loss[loss=2.326, over 5540206.86 frames. , ppl: 10.23427433168285], batch size: 70
+2022-12-10 19:11:12,084 INFO [train.py:421] (7/8) Epoch 3, batch 17600, loss[loss=2.229, over 7420.00 frames. , ppl: 9.288702292711433] tot_loss[loss=2.327, over 5515360.87 frames. , ppl: 10.245614502229856], batch size: 70
+2022-12-10 19:12:53,523 INFO [train.py:421] (7/8) Epoch 3, batch 17800, loss[loss=2.389, over 840.00 frames. , ppl: 10.902548005642034] tot_loss[loss=2.327, over 5518964.03 frames. , ppl: 10.244564467936161], batch size: 70
+2022-12-10 19:14:33,707 INFO [train.py:421] (7/8) Epoch 3, batch 18000, loss[loss=2.483, over 1050.00 frames. , ppl: 11.982073895456281] tot_loss[loss=2.326, over 5527975.92 frames. , ppl: 10.238521596671088], batch size: 70
+2022-12-10 19:14:33,708 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 19:14:34,466 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.315, over 211138.00 frames. , ppl: 10.129355082846555
+2022-12-10 19:16:15,835 INFO [train.py:421] (7/8) Epoch 3, batch 18200, loss[loss=2.349, over 2450.00 frames. , ppl: 10.47784464671851] tot_loss[loss=2.325, over 5533471.52 frames. , ppl: 10.231238888695584], batch size: 70
+2022-12-10 19:17:56,507 INFO [train.py:421] (7/8) Epoch 3, batch 18400, loss[loss=2.28, over 2100.00 frames. , ppl: 9.773932468353577] tot_loss[loss=2.325, over 5546638.51 frames. , ppl: 10.223155691790614], batch size: 70
+2022-12-10 19:19:35,455 INFO [train.py:421] (7/8) Epoch 3, batch 18600, loss[loss=2.547, over 980.00 frames. , ppl: 12.769475638530654] tot_loss[loss=2.324, over 5566696.43 frames. , ppl: 10.217243986039833], batch size: 70
+2022-12-10 19:21:19,541 INFO [train.py:421] (7/8) Epoch 3, batch 18800, loss[loss=2.712, over 840.00 frames. , ppl: 15.063835031543205] tot_loss[loss=2.325, over 5529195.13 frames. , ppl: 10.222588958307155], batch size: 70
+2022-12-10 19:22:57,489 INFO [train.py:421] (7/8) Epoch 3, batch 19000, loss[loss=2.26, over 3920.00 frames. , ppl: 9.580786110176295] tot_loss[loss=2.325, over 5522606.42 frames. , ppl: 10.230772012965401], batch size: 70
+2022-12-10 19:22:57,490 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 19:22:58,219 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.317, over 211138.00 frames. , ppl: 10.14855577978015
+2022-12-10 19:24:36,564 INFO [train.py:421] (7/8) Epoch 3, batch 19200, loss[loss=2.353, over 1750.00 frames. , ppl: 10.522013507573098] tot_loss[loss=2.325, over 5543356.23 frames. , ppl: 10.222360632371723], batch size: 70
+2022-12-10 19:26:16,123 INFO [train.py:421] (7/8) Epoch 3, batch 19400, loss[loss=2.531, over 1120.00 frames. , ppl: 12.563230856346342] tot_loss[loss=2.325, over 5551640.94 frames. , ppl: 10.222909511751903], batch size: 70
+2022-12-10 19:27:55,650 INFO [train.py:421] (7/8) Epoch 3, batch 19600, loss[loss=2.375, over 1400.00 frames. , ppl: 10.749249117753381] tot_loss[loss=2.326, over 5493982.24 frames. , ppl: 10.23559176720962], batch size: 70
+2022-12-10 19:29:36,918 INFO [train.py:421] (7/8) Epoch 3, batch 19800, loss[loss=2.333, over 3920.00 frames. , ppl: 10.304383176875579] tot_loss[loss=2.326, over 5494603.80 frames. , ppl: 10.232804076224873], batch size: 70
+2022-12-10 19:31:19,066 INFO [train.py:421] (7/8) Epoch 3, batch 20000, loss[loss=2.526, over 1330.00 frames. , ppl: 12.50948143367741] tot_loss[loss=2.327, over 5475703.38 frames. , ppl: 10.242542145915312], batch size: 70
+2022-12-10 19:31:19,067 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 19:31:19,811 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.315, over 211138.00 frames. , ppl: 10.12899827473271
+2022-12-10 19:33:00,567 INFO [train.py:421] (7/8) Epoch 3, batch 20200, loss[loss=2.314, over 2310.00 frames. , ppl: 10.111480406623713] tot_loss[loss=2.327, over 5474147.54 frames. , ppl: 10.2445360146245], batch size: 70
+2022-12-10 19:34:42,567 INFO [train.py:421] (7/8) Epoch 3, batch 20400, loss[loss=2.273, over 4620.00 frames. , ppl: 9.707579220254562] tot_loss[loss=2.327, over 5461774.26 frames. , ppl: 10.248893288026732], batch size: 70
+2022-12-10 19:36:23,578 INFO [train.py:421] (7/8) Epoch 3, batch 20600, loss[loss=2.387, over 1330.00 frames. , ppl: 10.882867636147486] tot_loss[loss=2.327, over 5460274.98 frames. , ppl: 10.24709683134452], batch size: 70
+2022-12-10 19:38:05,420 INFO [train.py:421] (7/8) Epoch 3, batch 20800, loss[loss=2.396, over 1890.00 frames. , ppl: 10.983582995705934] tot_loss[loss=2.328, over 5441997.31 frames. , ppl: 10.257613076359887], batch size: 70
+2022-12-10 19:39:45,172 INFO [train.py:421] (7/8) Epoch 3, batch 21000, loss[loss=2.269, over 3220.00 frames. , ppl: 9.670241470789131] tot_loss[loss=2.326, over 5505717.11 frames. , ppl: 10.239072249631949], batch size: 70
+2022-12-10 19:39:45,173 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 19:39:45,934 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.314, over 211138.00 frames. , ppl: 10.115766279020953
+2022-12-10 19:41:26,043 INFO [train.py:421] (7/8) Epoch 3, batch 21200, loss[loss=2.348, over 2310.00 frames. , ppl: 10.462225921263817] tot_loss[loss=2.325, over 5537275.18 frames. , ppl: 10.229350016631837], batch size: 70
+2022-12-10 19:43:03,117 INFO [train.py:421] (7/8) Epoch 3, batch 21400, loss[loss=2.248, over 4760.00 frames. , ppl: 9.469887616262683] tot_loss[loss=2.326, over 5508768.79 frames. , ppl: 10.236943646731675], batch size: 70
+2022-12-10 19:44:44,718 INFO [train.py:421] (7/8) Epoch 3, batch 21600, loss[loss=2.512, over 1400.00 frames. , ppl: 12.330225076985387] tot_loss[loss=2.327, over 5473111.59 frames. , ppl: 10.243310971685169], batch size: 70
+2022-12-10 19:46:24,995 INFO [train.py:421] (7/8) Epoch 3, batch 21800, loss[loss=2.273, over 5600.00 frames. , ppl: 9.711293107043408] tot_loss[loss=2.327, over 5426400.51 frames. , ppl: 10.251220908638015], batch size: 70
+2022-12-10 19:48:03,094 INFO [train.py:421] (7/8) Epoch 3, batch 22000, loss[loss=2.305, over 1750.00 frames. , ppl: 10.027725380430146] tot_loss[loss=2.328, over 5428399.16 frames. , ppl: 10.25706989553556], batch size: 70
+2022-12-10 19:48:03,095 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 19:48:03,838 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.314, over 211138.00 frames. , ppl: 10.119331761662655
+2022-12-10 19:49:42,910 INFO [train.py:421] (7/8) Epoch 3, batch 22200, loss[loss=2.534, over 1260.00 frames. , ppl: 12.607165344814323] tot_loss[loss=2.328, over 5427189.58 frames. , ppl: 10.256132396348594], batch size: 70
+2022-12-10 19:51:27,708 INFO [train.py:421] (7/8) Epoch 3, batch 22400, loss[loss=2.321, over 3990.00 frames. , ppl: 10.181650323866789] tot_loss[loss=2.327, over 5445589.14 frames. , ppl: 10.250684418377366], batch size: 70
+2022-12-10 19:53:09,802 INFO [train.py:421] (7/8) Epoch 3, batch 22600, loss[loss=2.341, over 2380.00 frames. , ppl: 10.38801031014337] tot_loss[loss=2.328, over 5440302.07 frames. , ppl: 10.253207762326243], batch size: 70
+2022-12-10 19:54:48,468 INFO [train.py:421] (7/8) Epoch 3, batch 22800, loss[loss=2.243, over 4060.00 frames. , ppl: 9.419679821193926] tot_loss[loss=2.327, over 5442740.54 frames. , ppl: 10.250688104305143], batch size: 70
+2022-12-10 19:56:25,458 INFO [train.py:421] (7/8) Epoch 3, batch 23000, loss[loss=2.231, over 7000.00 frames. , ppl: 9.307555138985824] tot_loss[loss=2.327, over 5461788.25 frames. , ppl: 10.242794047827767], batch size: 70
+2022-12-10 19:56:25,458 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 19:56:26,223 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.314, over 211138.00 frames. , ppl: 10.111284628584807
+2022-12-10 19:58:04,891 INFO [train.py:421] (7/8) Epoch 3, batch 23200, loss[loss=2.358, over 3010.00 frames. , ppl: 10.56793935545226] tot_loss[loss=2.326, over 5480363.87 frames. , ppl: 10.239661105245187], batch size: 70
+2022-12-10 19:59:44,528 INFO [train.py:421] (7/8) Epoch 3, batch 23400, loss[loss=2.267, over 2730.00 frames. , ppl: 9.648496131108079] tot_loss[loss=2.326, over 5482327.90 frames. , ppl: 10.238359157897825], batch size: 70
+2022-12-10 20:01:22,838 INFO [train.py:421] (7/8) Epoch 3, batch 23600, loss[loss=2.476, over 1050.00 frames. , ppl: 11.892635747894218] tot_loss[loss=2.327, over 5466840.66 frames. , ppl: 10.24511629051383], batch size: 70
+2022-12-10 20:03:03,134 INFO [train.py:421] (7/8) Epoch 3, batch 23800, loss[loss=2.336, over 4550.00 frames. , ppl: 10.3371202964745] tot_loss[loss=2.326, over 5497761.18 frames. , ppl: 10.23746272524693], batch size: 70
+2022-12-10 20:04:45,087 INFO [train.py:421] (7/8) Epoch 3, batch 24000, loss[loss=2.76, over 630.00 frames. , ppl: 15.79891965232344] tot_loss[loss=2.326, over 5515196.65 frames. , ppl: 10.234588883505237], batch size: 70
+2022-12-10 20:04:45,088 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 20:04:45,874 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.314, over 211138.00 frames. , ppl: 10.115662972133224
+2022-12-10 20:06:27,303 INFO [train.py:421] (7/8) Epoch 3, batch 24200, loss[loss=2.398, over 2170.00 frames. , ppl: 11.003764727479492] tot_loss[loss=2.327, over 5481591.16 frames. , ppl: 10.244380634193533], batch size: 70
+2022-12-10 20:08:06,570 INFO [train.py:421] (7/8) Epoch 3, batch 24400, loss[loss=2.474, over 1330.00 frames. , ppl: 11.86956482746737] tot_loss[loss=2.327, over 5435960.03 frames. , ppl: 10.251860866639886], batch size: 70
+2022-12-10 20:09:46,779 INFO [train.py:421] (7/8) Epoch 3, batch 24600, loss[loss=2.534, over 840.00 frames. , ppl: 12.60208169303268] tot_loss[loss=2.327, over 5458517.29 frames. , ppl: 10.248143490713836], batch size: 70
+2022-12-10 20:11:29,175 INFO [train.py:421] (7/8) Epoch 3, batch 24800, loss[loss=2.35, over 3290.00 frames. , ppl: 10.48389382829377] tot_loss[loss=2.326, over 5487954.22 frames. , ppl: 10.241765802786245], batch size: 70
+2022-12-10 20:13:09,466 INFO [train.py:421] (7/8) Epoch 3, batch 25000, loss[loss=2.494, over 1330.00 frames. , ppl: 12.112001199149772] tot_loss[loss=2.327, over 5477582.45 frames. , ppl: 10.24735335680758], batch size: 70
+2022-12-10 20:13:09,466 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 20:13:10,215 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.315, over 211138.00 frames. , ppl: 10.122748675677348
+2022-12-10 20:14:53,083 INFO [train.py:421] (7/8) Epoch 3, batch 25200, loss[loss=2.337, over 1960.00 frames. , ppl: 10.353737200086957] tot_loss[loss=2.327, over 5470972.48 frames. , ppl: 10.244780224381966], batch size: 70
+2022-12-10 20:16:34,328 INFO [train.py:421] (7/8) Epoch 3, batch 25400, loss[loss=2.569, over 1120.00 frames. , ppl: 13.056758022885411] tot_loss[loss=2.327, over 5472954.49 frames. , ppl: 10.244792225652569], batch size: 70
+2022-12-10 20:18:12,372 INFO [train.py:421] (7/8) Epoch 3, batch 25600, loss[loss=2.254, over 2800.00 frames. , ppl: 9.525584043626305] tot_loss[loss=2.326, over 5479783.63 frames. , ppl: 10.234074914836528], batch size: 70
+2022-12-10 20:19:49,967 INFO [train.py:421] (7/8) Epoch 3, batch 25800, loss[loss=2.256, over 3920.00 frames. , ppl: 9.542982452579837] tot_loss[loss=2.326, over 5469126.44 frames. , ppl: 10.241693862019304], batch size: 70
+2022-12-10 20:21:34,337 INFO [train.py:421] (7/8) Epoch 3, batch 26000, loss[loss=2.229, over 5950.00 frames. , ppl: 9.290035351931618] tot_loss[loss=2.326, over 5474945.11 frames. , ppl: 10.233249508873158], batch size: 70
+2022-12-10 20:21:34,338 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 20:21:35,067 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.316, over 211138.00 frames. , ppl: 10.132153014018082
+2022-12-10 20:23:08,526 INFO [train.py:421] (7/8) Epoch 3, batch 26200, loss[loss=2.502, over 1680.00 frames. , ppl: 12.205520037227394] tot_loss[loss=2.326, over 5458352.42 frames. , ppl: 10.238296535751022], batch size: 70
+2022-12-10 20:24:45,539 INFO [train.py:421] (7/8) Epoch 3, batch 26400, loss[loss=2.353, over 2310.00 frames. , ppl: 10.51233372830696] tot_loss[loss=2.326, over 5452459.71 frames. , ppl: 10.241768240641994], batch size: 70
+2022-12-10 20:26:27,608 INFO [train.py:421] (7/8) Epoch 3, batch 26600, loss[loss=2.426, over 1050.00 frames. , ppl: 11.310060754116504] tot_loss[loss=2.327, over 5427417.75 frames. , ppl: 10.247944607519202], batch size: 70
+2022-12-10 20:28:07,421 INFO [train.py:421] (7/8) Epoch 3, batch 26800, loss[loss=2.272, over 3570.00 frames. , ppl: 9.70227381769413] tot_loss[loss=2.326, over 5457730.02 frames. , ppl: 10.234007810350207], batch size: 70
+2022-12-10 20:29:49,944 INFO [train.py:421] (7/8) Epoch 3, batch 27000, loss[loss=2.308, over 2310.00 frames. , ppl: 10.058073132149433] tot_loss[loss=2.325, over 5499609.55 frames. , ppl: 10.22560851209255], batch size: 70
+2022-12-10 20:29:49,944 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 20:29:50,703 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.313, over 211138.00 frames. , ppl: 10.101093802370023
+2022-12-10 20:31:29,520 INFO [train.py:421] (7/8) Epoch 3, batch 27200, loss[loss=2.547, over 840.00 frames. , ppl: 12.768635836953822] tot_loss[loss=2.324, over 5514316.43 frames. , ppl: 10.219735549101394], batch size: 70
+2022-12-10 20:33:11,515 INFO [train.py:421] (7/8) Epoch 3, batch 27400, loss[loss=2.401, over 1960.00 frames. , ppl: 11.037633230374242] tot_loss[loss=2.324, over 5527812.73 frames. , ppl: 10.219106762896773], batch size: 70
+2022-12-10 20:34:50,137 INFO [train.py:421] (7/8) Epoch 3, batch 27600, loss[loss=2.275, over 1890.00 frames. , ppl: 9.723300835397914] tot_loss[loss=2.323, over 5556726.25 frames. , ppl: 10.207021171589293], batch size: 70
+2022-12-10 20:36:32,924 INFO [train.py:421] (7/8) Epoch 3, batch 27800, loss[loss=2.367, over 1960.00 frames. , ppl: 10.666933578452502] tot_loss[loss=2.323, over 5592188.72 frames. , ppl: 10.204523882950708], batch size: 70
+2022-12-10 20:38:09,408 INFO [train.py:421] (7/8) Epoch 3, batch 28000, loss[loss=2.268, over 3920.00 frames. , ppl: 9.660127682935602] tot_loss[loss=2.324, over 5586890.56 frames. , ppl: 10.212477565132215], batch size: 70
+2022-12-10 20:38:09,409 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 20:38:10,154 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.313, over 211138.00 frames. , ppl: 10.106116881121231
+2022-12-10 20:39:49,691 INFO [train.py:421] (7/8) Epoch 3, batch 28200, loss[loss=2.336, over 3850.00 frames. , ppl: 10.340782317678203] tot_loss[loss=2.324, over 5549300.06 frames. , ppl: 10.213374080200422], batch size: 70
+2022-12-10 20:41:31,328 INFO [train.py:421] (7/8) Epoch 3, batch 28400, loss[loss=2.289, over 2450.00 frames. , ppl: 9.868217076297688] tot_loss[loss=2.323, over 5547702.78 frames. , ppl: 10.210803482094692], batch size: 70
+2022-12-10 20:43:09,536 INFO [train.py:421] (7/8) Epoch 3, batch 28600, loss[loss=2.339, over 2380.00 frames. , ppl: 10.36906413626474] tot_loss[loss=2.323, over 5559923.19 frames. , ppl: 10.208100256986118], batch size: 70
+2022-12-10 20:44:46,043 INFO [train.py:421] (7/8) Epoch 3, batch 28800, loss[loss=2.498, over 1050.00 frames. , ppl: 12.1563261173542] tot_loss[loss=2.324, over 5524418.71 frames. , ppl: 10.213418999911976], batch size: 70
+2022-12-10 20:46:28,959 INFO [train.py:421] (7/8) Epoch 3, batch 29000, loss[loss=2.333, over 1750.00 frames. , ppl: 10.305113274530372] tot_loss[loss=2.326, over 5460436.59 frames. , ppl: 10.235217921317963], batch size: 70
+2022-12-10 20:46:28,960 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 20:46:29,722 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.313, over 211138.00 frames. , ppl: 10.10355792431578
+2022-12-10 20:48:07,970 INFO [train.py:421] (7/8) Epoch 3, batch 29200, loss[loss=2.347, over 1470.00 frames. , ppl: 10.44943577811349] tot_loss[loss=2.326, over 5455928.15 frames. , ppl: 10.233470129947426], batch size: 70
+2022-12-10 20:49:48,613 INFO [train.py:421] (7/8) Epoch 3, batch 29400, loss[loss=2.245, over 6090.00 frames. , ppl: 9.438123610465853] tot_loss[loss=2.326, over 5441740.99 frames. , ppl: 10.241831906834916], batch size: 70
+2022-12-10 20:51:26,257 INFO [train.py:421] (7/8) Epoch 3, batch 29600, loss[loss=2.468, over 1470.00 frames. , ppl: 11.803317470226999] tot_loss[loss=2.325, over 5478398.09 frames. , ppl: 10.227523018802504], batch size: 70
+2022-12-10 20:53:01,786 INFO [train.py:421] (7/8) Epoch 3, batch 29800, loss[loss=2.355, over 2380.00 frames. , ppl: 10.539812765330117] tot_loss[loss=2.326, over 5427108.71 frames. , ppl: 10.234697289850324], batch size: 70
+2022-12-10 20:54:41,555 INFO [train.py:421] (7/8) Epoch 3, batch 30000, loss[loss=2.36, over 2100.00 frames. , ppl: 10.586982559526925] tot_loss[loss=2.326, over 5439094.05 frames. , ppl: 10.232571625363638], batch size: 70
+2022-12-10 20:54:41,556 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 20:54:42,324 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.313, over 211138.00 frames. , ppl: 10.100455441623417
+2022-12-10 20:56:19,484 INFO [train.py:421] (7/8) Epoch 3, batch 30200, loss[loss=2.256, over 1610.00 frames. , ppl: 9.543426102158874] tot_loss[loss=2.325, over 5483484.45 frames. , ppl: 10.225669075378015], batch size: 70
+2022-12-10 20:58:04,769 INFO [train.py:421] (7/8) Epoch 3, batch 30400, loss[loss=2.394, over 1400.00 frames. , ppl: 10.954513569668622] tot_loss[loss=2.325, over 5493487.59 frames. , ppl: 10.222349116540832], batch size: 70
+2022-12-10 20:59:43,369 INFO [train.py:421] (7/8) Epoch 3, batch 30600, loss[loss=2.277, over 3080.00 frames. , ppl: 9.74281258335869] tot_loss[loss=2.324, over 5493971.15 frames. , ppl: 10.220098132014693], batch size: 70
+2022-12-10 21:01:20,875 INFO [train.py:421] (7/8) Epoch 3, batch 30800, loss[loss=2.354, over 4620.00 frames. , ppl: 10.529711309491121] tot_loss[loss=2.324, over 5514185.57 frames. , ppl: 10.219884573747965], batch size: 70
+2022-12-10 21:02:59,412 INFO [train.py:421] (7/8) Epoch 3, batch 31000, loss[loss=2.405, over 1960.00 frames. , ppl: 11.083199299081157] tot_loss[loss=2.324, over 5524542.34 frames. , ppl: 10.219443408618227], batch size: 70
+2022-12-10 21:02:59,413 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 21:03:00,157 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.312, over 211138.00 frames. , ppl: 10.091295598195819
+2022-12-10 21:04:37,248 INFO [train.py:421] (7/8) Epoch 3, batch 31200, loss[loss=2.474, over 910.00 frames. , ppl: 11.866298206311516] tot_loss[loss=2.326, over 5484113.28 frames. , ppl: 10.232044380487578], batch size: 70
+2022-12-10 21:06:17,359 INFO [train.py:421] (7/8) Epoch 3, batch 31400, loss[loss=2.235, over 4970.00 frames. , ppl: 9.343854551954664] tot_loss[loss=2.326, over 5457802.27 frames. , ppl: 10.237924521221036], batch size: 70
+2022-12-10 21:07:59,103 INFO [train.py:421] (7/8) Epoch 3, batch 31600, loss[loss=3.042, over 560.00 frames. , ppl: 20.937664842254357] tot_loss[loss=2.326, over 5441105.28 frames. , ppl: 10.241010881916619], batch size: 70
+2022-12-10 21:09:38,631 INFO [train.py:421] (7/8) Epoch 3, batch 31800, loss[loss=2.336, over 2940.00 frames. , ppl: 10.344380091869452] tot_loss[loss=2.326, over 5441454.10 frames. , ppl: 10.241342372654568], batch size: 70
+2022-12-10 21:11:16,581 INFO [train.py:421] (7/8) Epoch 3, batch 32000, loss[loss=2.402, over 2100.00 frames. , ppl: 11.041075878233547] tot_loss[loss=2.327, over 5422833.22 frames. , ppl: 10.243155604489864], batch size: 70
+2022-12-10 21:11:16,582 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 21:11:17,340 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.313, over 211138.00 frames. , ppl: 10.101464578420366
+2022-12-10 21:12:58,764 INFO [train.py:421] (7/8) Epoch 3, batch 32200, loss[loss=2.301, over 5250.00 frames. , ppl: 9.984221055733904] tot_loss[loss=2.325, over 5500930.68 frames. , ppl: 10.223029070596718], batch size: 70
+2022-12-10 21:14:34,253 INFO [train.py:421] (7/8) Epoch 3, batch 32400, loss[loss=2.502, over 980.00 frames. , ppl: 12.211271818707925] tot_loss[loss=2.326, over 5466822.21 frames. , ppl: 10.233347187689693], batch size: 70
+2022-12-10 21:16:14,625 INFO [train.py:421] (7/8) Epoch 3, batch 32600, loss[loss=2.239, over 3290.00 frames. , ppl: 9.382590598117046] tot_loss[loss=2.326, over 5478558.46 frames. , ppl: 10.231859343844203], batch size: 70
+2022-12-10 21:17:51,468 INFO [train.py:421] (7/8) Epoch 3, batch 32800, loss[loss=2.437, over 1330.00 frames. , ppl: 11.43874215309773] tot_loss[loss=2.325, over 5490175.19 frames. , ppl: 10.222437869587074], batch size: 70
+2022-12-10 21:19:29,970 INFO [train.py:421] (7/8) Epoch 3, batch 33000, loss[loss=2.21, over 6580.00 frames. , ppl: 9.114867895101975] tot_loss[loss=2.325, over 5489386.35 frames. , ppl: 10.228659979616406], batch size: 70
+2022-12-10 21:19:29,971 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 21:19:30,729 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.314, over 211138.00 frames. , ppl: 10.111637819514526
+2022-12-10 21:21:05,638 INFO [train.py:421] (7/8) Epoch 3, batch 33200, loss[loss=2.315, over 3150.00 frames. , ppl: 10.121018846439902] tot_loss[loss=2.325, over 5496055.99 frames. , ppl: 10.225242975877423], batch size: 70
+2022-12-10 21:22:50,830 INFO [train.py:421] (7/8) Epoch 3, batch 33400, loss[loss=2.259, over 12670.00 frames. , ppl: 9.574220217685431] tot_loss[loss=2.325, over 5500014.18 frames. , ppl: 10.226348889952392], batch size: 70
+2022-12-10 21:24:31,327 INFO [train.py:421] (7/8) Epoch 3, batch 33600, loss[loss=2.221, over 8190.00 frames. , ppl: 9.212310821256544] tot_loss[loss=2.324, over 5540770.93 frames. , ppl: 10.215385080114109], batch size: 70
+2022-12-10 21:26:13,404 INFO [train.py:421] (7/8) Epoch 3, batch 33800, loss[loss=2.324, over 2660.00 frames. , ppl: 10.221282527646029] tot_loss[loss=2.324, over 5522477.76 frames. , ppl: 10.217679582055773], batch size: 70
+2022-12-10 21:27:54,538 INFO [train.py:421] (7/8) Epoch 3, batch 34000, loss[loss=2.263, over 4200.00 frames. , ppl: 9.611161094792896] tot_loss[loss=2.324, over 5527030.05 frames. , ppl: 10.215175319784256], batch size: 70
+2022-12-10 21:27:54,539 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 21:27:55,295 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.31, over 211138.00 frames. , ppl: 10.071958753555176
+2022-12-10 21:29:32,491 INFO [train.py:421] (7/8) Epoch 3, batch 34200, loss[loss=2.235, over 3570.00 frames. , ppl: 9.344582927390507] tot_loss[loss=2.325, over 5518923.20 frames. , ppl: 10.222414822985813], batch size: 70
+2022-12-10 21:31:11,668 INFO [train.py:421] (7/8) Epoch 3, batch 34400, loss[loss=2.219, over 5880.00 frames. , ppl: 9.199684510351913] tot_loss[loss=2.325, over 5513521.70 frames. , ppl: 10.227404077795388], batch size: 70
+2022-12-10 21:32:50,594 INFO [train.py:421] (7/8) Epoch 3, batch 34600, loss[loss=2.421, over 1680.00 frames. , ppl: 11.260586190944995] tot_loss[loss=2.326, over 5522025.88 frames. , ppl: 10.232884905397043], batch size: 70
+2022-12-10 21:34:29,939 INFO [train.py:421] (7/8) Epoch 3, batch 34800, loss[loss=2.28, over 5110.00 frames. , ppl: 9.77790017910905] tot_loss[loss=2.326, over 5512553.05 frames. , ppl: 10.23654058265835], batch size: 70
+2022-12-10 21:36:14,348 INFO [train.py:421] (7/8) Epoch 3, batch 35000, loss[loss=2.225, over 5950.00 frames. , ppl: 9.249893158733334] tot_loss[loss=2.326, over 5530423.36 frames. , ppl: 10.235376371218482], batch size: 70
+2022-12-10 21:36:14,349 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 21:36:15,077 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.311, over 211138.00 frames. , ppl: 10.083123013689438
+2022-12-10 21:37:54,335 INFO [train.py:421] (7/8) Epoch 3, batch 35200, loss[loss=2.239, over 6020.00 frames. , ppl: 9.386843431453256] tot_loss[loss=2.327, over 5499474.44 frames. , ppl: 10.242653826770962], batch size: 70
+2022-12-10 21:39:36,772 INFO [train.py:421] (7/8) Epoch 3, batch 35400, loss[loss=2.362, over 1960.00 frames. , ppl: 10.612680772972604] tot_loss[loss=2.326, over 5498787.33 frames. , ppl: 10.241357910123238], batch size: 70
+2022-12-10 21:41:19,924 INFO [train.py:421] (7/8) Epoch 3, batch 35600, loss[loss=2.352, over 2940.00 frames. , ppl: 10.508514212521314] tot_loss[loss=2.325, over 5533494.33 frames. , ppl: 10.230533511948167], batch size: 70
+2022-12-10 21:42:54,212 INFO [train.py:421] (7/8) Epoch 3, batch 35800, loss[loss=2.35, over 1680.00 frames. , ppl: 10.483186800688399] tot_loss[loss=2.326, over 5490548.79 frames. , ppl: 10.239379485109698], batch size: 70
+2022-12-10 21:44:36,451 INFO [train.py:421] (7/8) Epoch 3, batch 36000, loss[loss=2.309, over 4480.00 frames. , ppl: 10.062671227930267] tot_loss[loss=2.326, over 5502467.70 frames. , ppl: 10.23444040376662], batch size: 70
+2022-12-10 21:44:36,451 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 21:44:37,180 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.311, over 211138.00 frames. , ppl: 10.086282871808761
+2022-12-10 21:46:17,617 INFO [train.py:421] (7/8) Epoch 3, batch 36200, loss[loss=2.238, over 4130.00 frames. , ppl: 9.370586295580466] tot_loss[loss=2.325, over 5492613.99 frames. , ppl: 10.22742089950786], batch size: 70
+2022-12-10 21:47:56,620 INFO [train.py:421] (7/8) Epoch 3, batch 36400, loss[loss=3.269, over 490.00 frames. , ppl: 26.292870575829042] tot_loss[loss=2.325, over 5461457.42 frames. , ppl: 10.230830797900829], batch size: 70
+2022-12-10 21:49:39,009 INFO [train.py:421] (7/8) Epoch 3, batch 36600, loss[loss=2.274, over 6160.00 frames. , ppl: 9.721721363945843] tot_loss[loss=2.325, over 5480528.58 frames. , ppl: 10.223415656854888], batch size: 70
+2022-12-10 21:51:17,825 INFO [train.py:421] (7/8) Epoch 3, batch 36800, loss[loss=2.413, over 1190.00 frames. , ppl: 11.163404186251263] tot_loss[loss=2.326, over 5472248.26 frames. , ppl: 10.233755165672635], batch size: 70
+2022-12-10 21:53:00,122 INFO [train.py:421] (7/8) Epoch 3, batch 37000, loss[loss=2.425, over 1260.00 frames. , ppl: 11.302032325758512] tot_loss[loss=2.326, over 5469526.58 frames. , ppl: 10.238317795739636], batch size: 70
+2022-12-10 21:53:00,122 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 21:53:00,870 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.312, over 211138.00 frames. , ppl: 10.091421060289873
+2022-12-10 21:54:40,045 INFO [train.py:421] (7/8) Epoch 3, batch 37200, loss[loss=2.549, over 1120.00 frames. , ppl: 12.795701864310885] tot_loss[loss=2.327, over 5437608.77 frames. , ppl: 10.245865226359692], batch size: 70
+2022-12-10 21:56:18,551 INFO [train.py:421] (7/8) Epoch 3, batch 37400, loss[loss=2.425, over 1540.00 frames. , ppl: 11.302146997934464] tot_loss[loss=2.325, over 5460901.20 frames. , ppl: 10.230960241207956], batch size: 70
+2022-12-10 21:57:58,919 INFO [train.py:421] (7/8) Epoch 3, batch 37600, loss[loss=2.431, over 1610.00 frames. , ppl: 11.373365502476748] tot_loss[loss=2.324, over 5471751.41 frames. , ppl: 10.221071817333186], batch size: 70
+2022-12-10 21:59:41,113 INFO [train.py:421] (7/8) Epoch 3, batch 37800, loss[loss=2.34, over 1050.00 frames. , ppl: 10.37959531393549] tot_loss[loss=2.325, over 5457574.95 frames. , ppl: 10.224623993700616], batch size: 70
+2022-12-10 22:01:19,424 INFO [train.py:421] (7/8) Epoch 3, batch 38000, loss[loss=2.258, over 4060.00 frames. , ppl: 9.560256350799767] tot_loss[loss=2.325, over 5455282.60 frames. , ppl: 10.226721773553535], batch size: 70
+2022-12-10 22:01:19,424 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 22:01:20,188 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.311, over 211138.00 frames. , ppl: 10.088428318438387
+2022-12-10 22:02:59,193 INFO [train.py:421] (7/8) Epoch 3, batch 38200, loss[loss=2.311, over 6510.00 frames. , ppl: 10.081989236232626] tot_loss[loss=2.325, over 5444161.94 frames. , ppl: 10.226806148330686], batch size: 70
+2022-12-10 22:04:43,418 INFO [train.py:421] (7/8) Epoch 3, batch 38400, loss[loss=2.35, over 2590.00 frames. , ppl: 10.481561544442833] tot_loss[loss=2.325, over 5445259.37 frames. , ppl: 10.227298542375179], batch size: 70
+2022-12-10 22:06:21,542 INFO [train.py:421] (7/8) Epoch 3, batch 38600, loss[loss=2.256, over 3500.00 frames. , ppl: 9.544187573644944] tot_loss[loss=2.324, over 5473949.42 frames. , ppl: 10.21395000984249], batch size: 70
+2022-12-10 22:08:03,080 INFO [train.py:421] (7/8) Epoch 3, batch 38800, loss[loss=2.292, over 2520.00 frames. , ppl: 9.89338966213299] tot_loss[loss=2.324, over 5452923.92 frames. , ppl: 10.213113954833016], batch size: 70
+2022-12-10 22:09:44,367 INFO [train.py:421] (7/8) Epoch 3, batch 39000, loss[loss=2.222, over 7630.00 frames. , ppl: 9.222953313358856] tot_loss[loss=2.324, over 5466949.14 frames. , ppl: 10.213541670687917], batch size: 70
+2022-12-10 22:09:44,368 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 22:09:45,098 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.311, over 211138.00 frames. , ppl: 10.087220422135697
+2022-12-10 22:11:24,490 INFO [train.py:421] (7/8) Epoch 3, batch 39200, loss[loss=2.331, over 2380.00 frames. , ppl: 10.2912424788423] tot_loss[loss=2.324, over 5474630.26 frames. , ppl: 10.213770746757469], batch size: 70
+2022-12-10 22:13:02,104 INFO [train.py:421] (7/8) Epoch 3, batch 39400, loss[loss=2.469, over 1050.00 frames. , ppl: 11.816285435562406] tot_loss[loss=2.323, over 5522988.10 frames. , ppl: 10.205882457510661], batch size: 70
+2022-12-10 22:14:41,112 INFO [train.py:421] (7/8) Epoch 3, batch 39600, loss[loss=2.259, over 6300.00 frames. , ppl: 9.569199662861108] tot_loss[loss=2.324, over 5509128.07 frames. , ppl: 10.211585041815292], batch size: 70
+2022-12-10 22:16:21,149 INFO [train.py:421] (7/8) Epoch 3, batch 39800, loss[loss=2.463, over 1330.00 frames. , ppl: 11.744143323237978] tot_loss[loss=2.324, over 5497209.00 frames. , ppl: 10.21686239466908], batch size: 70
+2022-12-10 22:17:59,552 INFO [train.py:421] (7/8) Epoch 3, batch 40000, loss[loss=2.427, over 1400.00 frames. , ppl: 11.325814758822466] tot_loss[loss=2.326, over 5447540.71 frames. , ppl: 10.234869987176411], batch size: 70
+2022-12-10 22:17:59,553 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 22:18:00,311 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.311, over 211138.00 frames. , ppl: 10.0863605000554
+2022-12-10 22:19:42,218 INFO [train.py:421] (7/8) Epoch 3, batch 40200, loss[loss=2.161, over 7140.00 frames. , ppl: 8.680847265610682] tot_loss[loss=2.325, over 5448971.74 frames. , ppl: 10.224378268904637], batch size: 70
+2022-12-10 22:21:21,721 INFO [train.py:421] (7/8) Epoch 3, batch 40400, loss[loss=2.745, over 770.00 frames. , ppl: 15.56030922838864] tot_loss[loss=2.326, over 5409162.99 frames. , ppl: 10.233978507999296], batch size: 70
+2022-12-10 22:23:02,852 INFO [train.py:421] (7/8) Epoch 3, batch 40600, loss[loss=2.183, over 5880.00 frames. , ppl: 8.872447428229567] tot_loss[loss=2.325, over 5425628.41 frames. , ppl: 10.22716596515116], batch size: 70
+2022-12-10 22:24:42,986 INFO [train.py:421] (7/8) Epoch 3, batch 40800, loss[loss=2.562, over 1610.00 frames. , ppl: 12.96726916253782] tot_loss[loss=2.326, over 5410390.95 frames. , ppl: 10.234416127607188], batch size: 70
+2022-12-10 22:26:20,571 INFO [train.py:421] (7/8) Epoch 3, batch 41000, loss[loss=2.27, over 8610.00 frames. , ppl: 9.677252767902548] tot_loss[loss=2.326, over 5393515.84 frames. , ppl: 10.236409663863633], batch size: 70
+2022-12-10 22:26:20,571 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 22:26:21,300 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.312, over 211138.00 frames. , ppl: 10.09838814732227
+2022-12-10 22:28:02,988 INFO [train.py:421] (7/8) Epoch 3, batch 41200, loss[loss=2.468, over 1820.00 frames. , ppl: 11.797320568038602] tot_loss[loss=2.324, over 5470113.32 frames. , ppl: 10.212989591985398], batch size: 70
+2022-12-10 22:29:45,194 INFO [train.py:421] (7/8) Epoch 3, batch 41400, loss[loss=2.265, over 3430.00 frames. , ppl: 9.631651646708908] tot_loss[loss=2.323, over 5506558.46 frames. , ppl: 10.208183865550003], batch size: 70
+2022-12-10 22:31:24,835 INFO [train.py:421] (7/8) Epoch 3, batch 41600, loss[loss=2.264, over 8820.00 frames. , ppl: 9.620484684381038] tot_loss[loss=2.324, over 5470524.59 frames. , ppl: 10.211412379741185], batch size: 70
+2022-12-10 22:32:59,982 INFO [train.py:421] (7/8) Epoch 3, batch 41800, loss[loss=2.315, over 2730.00 frames. , ppl: 10.12526772367208] tot_loss[loss=2.324, over 5452731.83 frames. , ppl: 10.213619557817099], batch size: 70
+2022-12-10 22:34:40,204 INFO [train.py:421] (7/8) Epoch 3, batch 42000, loss[loss=2.712, over 840.00 frames. , ppl: 15.059973947649775] tot_loss[loss=2.324, over 5417789.65 frames. , ppl: 10.217769720655742], batch size: 70
+2022-12-10 22:34:40,205 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 22:34:40,954 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.31, over 211138.00 frames. , ppl: 10.07229715383208
+2022-12-10 22:36:24,003 INFO [train.py:421] (7/8) Epoch 3, batch 42200, loss[loss=2.474, over 1190.00 frames. , ppl: 11.866608139915375] tot_loss[loss=2.325, over 5407190.13 frames. , ppl: 10.223353863527363], batch size: 70
+2022-12-10 22:38:04,419 INFO [train.py:421] (7/8) Epoch 3, batch 42400, loss[loss=2.302, over 2730.00 frames. , ppl: 9.991693087115388] tot_loss[loss=2.326, over 5351091.74 frames. , ppl: 10.238030947085166], batch size: 70
+2022-12-10 22:39:45,498 INFO [train.py:421] (7/8) Epoch 3, batch 42600, loss[loss=2.275, over 2380.00 frames. , ppl: 9.726987027151536] tot_loss[loss=2.325, over 5389849.73 frames. , ppl: 10.227258112888158], batch size: 70
+2022-12-10 22:41:24,895 INFO [train.py:421] (7/8) Epoch 3, batch 42800, loss[loss=2.282, over 4060.00 frames. , ppl: 9.792582691680598] tot_loss[loss=2.324, over 5409944.29 frames. , ppl: 10.21718074921611], batch size: 70
+2022-12-10 22:43:08,206 INFO [train.py:421] (7/8) Epoch 3, batch 43000, loss[loss=2.425, over 2030.00 frames. , ppl: 11.303836199504696] tot_loss[loss=2.323, over 5472233.71 frames. , ppl: 10.201423382955616], batch size: 70
+2022-12-10 22:43:08,207 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 22:43:08,978 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.31, over 211138.00 frames. , ppl: 10.073643413765264
+2022-12-10 22:44:46,749 INFO [train.py:421] (7/8) Epoch 3, batch 43200, loss[loss=2.424, over 1330.00 frames. , ppl: 11.29158299508157] tot_loss[loss=2.323, over 5464272.15 frames. , ppl: 10.202450636142322], batch size: 70
+2022-12-10 22:46:25,133 INFO [train.py:421] (7/8) Epoch 3, batch 43400, loss[loss=2.371, over 1610.00 frames. , ppl: 10.708046703379383] tot_loss[loss=2.323, over 5459886.32 frames. , ppl: 10.208370587304271], batch size: 70
+2022-12-10 22:48:04,841 INFO [train.py:421] (7/8) Epoch 3, batch 43600, loss[loss=2.404, over 1050.00 frames. , ppl: 11.063258326708855] tot_loss[loss=2.324, over 5437353.21 frames. , ppl: 10.211773669536845], batch size: 70
+2022-12-10 22:49:41,095 INFO [train.py:421] (7/8) Epoch 3, batch 43800, loss[loss=2.817, over 560.00 frames. , ppl: 16.730527090801957] tot_loss[loss=2.325, over 5418002.24 frames. , ppl: 10.222166717223395], batch size: 70
+2022-12-10 22:51:19,561 INFO [train.py:421] (7/8) Epoch 3, batch 44000, loss[loss=2.297, over 2450.00 frames. , ppl: 9.946337971591454] tot_loss[loss=2.326, over 5352084.67 frames. , ppl: 10.2353481745209], batch size: 70
+2022-12-10 22:51:19,561 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 22:51:20,323 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.312, over 211138.00 frames. , ppl: 10.093368910010755
+2022-12-10 22:53:02,987 INFO [train.py:421] (7/8) Epoch 3, batch 44200, loss[loss=2.341, over 2730.00 frames. , ppl: 10.387284687113548] tot_loss[loss=2.325, over 5373489.38 frames. , ppl: 10.224572870967922], batch size: 70
+2022-12-10 22:54:43,986 INFO [train.py:421] (7/8) Epoch 3, batch 44400, loss[loss=2.612, over 770.00 frames. , ppl: 13.622465914553546] tot_loss[loss=2.324, over 5392737.18 frames. , ppl: 10.218846287583148], batch size: 70
+2022-12-10 22:56:24,870 INFO [train.py:421] (7/8) Epoch 3, batch 44600, loss[loss=2.554, over 1190.00 frames. , ppl: 12.863134102703782] tot_loss[loss=2.324, over 5406197.39 frames. , ppl: 10.216323910203002], batch size: 70
+2022-12-10 22:58:04,159 INFO [train.py:421] (7/8) Epoch 3, batch 44800, loss[loss=2.264, over 1960.00 frames. , ppl: 9.620474565050369] tot_loss[loss=2.325, over 5389771.40 frames. , ppl: 10.22307948360924], batch size: 70
+2022-12-10 22:59:45,448 INFO [train.py:421] (7/8) Epoch 3, batch 45000, loss[loss=2.251, over 6090.00 frames. , ppl: 9.492751718369576] tot_loss[loss=2.325, over 5386748.43 frames. , ppl: 10.222727901098976], batch size: 70
+2022-12-10 22:59:45,448 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 22:59:46,181 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.313, over 211138.00 frames. , ppl: 10.10122686156436
+2022-12-10 23:01:30,008 INFO [train.py:421] (7/8) Epoch 3, batch 45200, loss[loss=2.958, over 560.00 frames. , ppl: 19.256533947575605] tot_loss[loss=2.323, over 5436559.51 frames. , ppl: 10.210145510995474], batch size: 70
+2022-12-10 23:03:11,266 INFO [train.py:421] (7/8) Epoch 3, batch 45400, loss[loss=2.789, over 700.00 frames. , ppl: 16.25824561086887] tot_loss[loss=2.323, over 5448125.52 frames. , ppl: 10.204314288640024], batch size: 70
+2022-12-10 23:04:51,283 INFO [train.py:421] (7/8) Epoch 3, batch 45600, loss[loss=2.162, over 3640.00 frames. , ppl: 8.686489777777885] tot_loss[loss=2.323, over 5444437.02 frames. , ppl: 10.203915970673592], batch size: 70
+2022-12-10 23:06:30,768 INFO [train.py:421] (7/8) Epoch 3, batch 45800, loss[loss=2.399, over 1750.00 frames. , ppl: 11.016141509321894] tot_loss[loss=2.324, over 5395862.32 frames. , ppl: 10.213033016055887], batch size: 70
+2022-12-10 23:08:09,340 INFO [train.py:421] (7/8) Epoch 3, batch 46000, loss[loss=2.393, over 1330.00 frames. , ppl: 10.944734005069177] tot_loss[loss=2.324, over 5404678.41 frames. , ppl: 10.211913887028718], batch size: 70
+2022-12-10 23:08:09,341 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 23:08:10,128 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.31, over 211138.00 frames. , ppl: 10.07448734063421
+2022-12-10 23:09:50,389 INFO [train.py:421] (7/8) Epoch 3, batch 46200, loss[loss=2.404, over 1890.00 frames. , ppl: 11.072886043696329] tot_loss[loss=2.323, over 5423280.22 frames. , ppl: 10.2104195809801], batch size: 70
+2022-12-10 23:11:28,889 INFO [train.py:421] (7/8) Epoch 3, batch 46400, loss[loss=2.427, over 1050.00 frames. , ppl: 11.3226801056226] tot_loss[loss=2.323, over 5442681.99 frames. , ppl: 10.208204617627759], batch size: 70
+2022-12-10 23:13:11,853 INFO [train.py:421] (7/8) Epoch 3, batch 46600, loss[loss=3.046, over 560.00 frames. , ppl: 21.02934677963473] tot_loss[loss=2.323, over 5441045.22 frames. , ppl: 10.204963969037706], batch size: 70
+2022-12-10 23:14:52,147 INFO [train.py:421] (7/8) Epoch 3, batch 46800, loss[loss=2.177, over 4200.00 frames. , ppl: 8.821173825163427] tot_loss[loss=2.322, over 5454737.89 frames. , ppl: 10.197391464281427], batch size: 70
+2022-12-10 23:16:28,907 INFO [train.py:421] (7/8) Epoch 3, batch 47000, loss[loss=2.351, over 2870.00 frames. , ppl: 10.500494072078004] tot_loss[loss=2.323, over 5428333.14 frames. , ppl: 10.208447633647333], batch size: 70
+2022-12-10 23:16:28,908 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 23:16:29,653 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.307, over 211138.00 frames. , ppl: 10.048629133994561
+2022-12-10 23:18:11,357 INFO [train.py:421] (7/8) Epoch 3, batch 47200, loss[loss=2.263, over 4200.00 frames. , ppl: 9.611581234715398] tot_loss[loss=2.324, over 5398594.92 frames. , ppl: 10.214883309358157], batch size: 70
+2022-12-10 23:19:51,597 INFO [train.py:421] (7/8) Epoch 3, batch 47400, loss[loss=2.328, over 3780.00 frames. , ppl: 10.257487918474526] tot_loss[loss=2.325, over 5358612.18 frames. , ppl: 10.224047187385098], batch size: 70
+2022-12-10 23:21:30,719 INFO [train.py:421] (7/8) Epoch 3, batch 47600, loss[loss=2.473, over 1540.00 frames. , ppl: 11.853610089274236] tot_loss[loss=2.326, over 5312463.69 frames. , ppl: 10.235356326363393], batch size: 70
+2022-12-10 23:23:11,824 INFO [train.py:421] (7/8) Epoch 3, batch 47800, loss[loss=2.383, over 2310.00 frames. , ppl: 10.840140631263363] tot_loss[loss=2.325, over 5360641.25 frames. , ppl: 10.225108666061475], batch size: 70
+2022-12-10 23:24:53,396 INFO [train.py:421] (7/8) Epoch 3, batch 48000, loss[loss=2.564, over 910.00 frames. , ppl: 12.983375465099224] tot_loss[loss=2.323, over 5415796.72 frames. , ppl: 10.209063671725726], batch size: 70
+2022-12-10 23:24:53,397 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 23:24:54,156 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.309, over 211138.00 frames. , ppl: 10.0626251790151
+2022-12-10 23:26:31,206 INFO [train.py:421] (7/8) Epoch 3, batch 48200, loss[loss=2.397, over 1400.00 frames. , ppl: 10.990438523237078] tot_loss[loss=2.324, over 5377140.98 frames. , ppl: 10.217279583487992], batch size: 70
+2022-12-10 23:28:10,238 INFO [train.py:421] (7/8) Epoch 3, batch 48400, loss[loss=2.296, over 4830.00 frames. , ppl: 9.93809543612669] tot_loss[loss=2.324, over 5393904.90 frames. , ppl: 10.214231598174702], batch size: 70
+2022-12-10 23:29:50,971 INFO [train.py:421] (7/8) Epoch 3, batch 48600, loss[loss=2.356, over 2100.00 frames. , ppl: 10.547333649955993] tot_loss[loss=2.323, over 5412822.93 frames. , ppl: 10.210484217012256], batch size: 70
+2022-12-10 23:31:26,391 INFO [train.py:421] (7/8) Epoch 3, batch 48800, loss[loss=2.391, over 1120.00 frames. , ppl: 10.924836018997865] tot_loss[loss=2.322, over 5469370.99 frames. , ppl: 10.194186472138211], batch size: 70
+2022-12-10 23:33:09,329 INFO [train.py:421] (7/8) Epoch 3, batch 49000, loss[loss=2.962, over 630.00 frames. , ppl: 19.334180405000232] tot_loss[loss=2.321, over 5492879.15 frames. , ppl: 10.185770254636607], batch size: 70
+2022-12-10 23:33:09,329 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 23:33:10,087 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.309, over 211138.00 frames. , ppl: 10.064253163288134
+2022-12-10 23:34:51,168 INFO [train.py:421] (7/8) Epoch 3, batch 49200, loss[loss=2.576, over 840.00 frames. , ppl: 13.143894839053669] tot_loss[loss=2.322, over 5460458.96 frames. , ppl: 10.197277004433374], batch size: 70
+2022-12-10 23:36:30,870 INFO [train.py:421] (7/8) Epoch 3, batch 49400, loss[loss=2.224, over 3640.00 frames. , ppl: 9.2476654573003] tot_loss[loss=2.323, over 5439927.87 frames. , ppl: 10.204931993664239], batch size: 70
+2022-12-10 23:38:10,945 INFO [train.py:421] (7/8) Epoch 3, batch 49600, loss[loss=2.264, over 10290.00 frames. , ppl: 9.625078894349459] tot_loss[loss=2.322, over 5461992.13 frames. , ppl: 10.19396538086341], batch size: 70
+2022-12-10 23:39:52,727 INFO [train.py:421] (7/8) Epoch 3, batch 49800, loss[loss=2.397, over 2310.00 frames. , ppl: 10.990102139489471] tot_loss[loss=2.323, over 5417079.94 frames. , ppl: 10.20727141717485], batch size: 70
+2022-12-10 23:41:29,023 INFO [train.py:421] (7/8) Epoch 3, batch 50000, loss[loss=2.319, over 4130.00 frames. , ppl: 10.169508385064503] tot_loss[loss=2.324, over 5400874.63 frames. , ppl: 10.213188875639714], batch size: 70
+2022-12-10 23:41:29,024 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 23:41:29,779 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.31, over 211138.00 frames. , ppl: 10.074415768120824
+2022-12-10 23:43:13,649 INFO [train.py:421] (7/8) Epoch 3, batch 50200, loss[loss=2.34, over 3360.00 frames. , ppl: 10.381770326205768] tot_loss[loss=2.323, over 5404968.71 frames. , ppl: 10.208853415064768], batch size: 70
+2022-12-10 23:44:54,565 INFO [train.py:421] (7/8) Epoch 3, batch 50400, loss[loss=2.402, over 1540.00 frames. , ppl: 11.048026347594043] tot_loss[loss=2.323, over 5404742.06 frames. , ppl: 10.208758167463504], batch size: 70
+2022-12-10 23:46:36,439 INFO [train.py:421] (7/8) Epoch 3, batch 50600, loss[loss=2.411, over 2030.00 frames. , ppl: 11.147001925268562] tot_loss[loss=2.322, over 5420815.07 frames. , ppl: 10.200752541266803], batch size: 70
+2022-12-10 23:48:17,654 INFO [train.py:421] (7/8) Epoch 3, batch 50800, loss[loss=2.548, over 1260.00 frames. , ppl: 12.776582584623409] tot_loss[loss=2.322, over 5463672.96 frames. , ppl: 10.200261766732924], batch size: 70
+2022-12-10 23:49:58,956 INFO [train.py:421] (7/8) Epoch 3, batch 51000, loss[loss=3.181, over 490.00 frames. , ppl: 24.07089340710399] tot_loss[loss=2.321, over 5489916.37 frames. , ppl: 10.18758564498326], batch size: 70
+2022-12-10 23:49:58,957 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 23:49:59,716 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.309, over 211138.00 frames. , ppl: 10.069029904707316
+2022-12-10 23:51:40,231 INFO [train.py:421] (7/8) Epoch 3, batch 51200, loss[loss=2.266, over 3780.00 frames. , ppl: 9.637574182896682] tot_loss[loss=2.321, over 5499135.66 frames. , ppl: 10.18746583794463], batch size: 70
+2022-12-10 23:53:19,771 INFO [train.py:421] (7/8) Epoch 3, batch 51400, loss[loss=2.539, over 1050.00 frames. , ppl: 12.667751058892819] tot_loss[loss=2.322, over 5501119.43 frames. , ppl: 10.195321522032208], batch size: 70
+2022-12-10 23:55:01,899 INFO [train.py:421] (7/8) Epoch 3, batch 51600, loss[loss=3.034, over 560.00 frames. , ppl: 20.78712039810133] tot_loss[loss=2.323, over 5487137.62 frames. , ppl: 10.201854687807256], batch size: 70
+2022-12-10 23:56:41,060 INFO [train.py:421] (7/8) Epoch 3, batch 51800, loss[loss=2.311, over 2730.00 frames. , ppl: 10.08711360223138] tot_loss[loss=2.323, over 5478068.46 frames. , ppl: 10.204646819115048], batch size: 70
+2022-12-10 23:58:20,734 INFO [train.py:421] (7/8) Epoch 3, batch 52000, loss[loss=2.636, over 1050.00 frames. , ppl: 13.954959446120212] tot_loss[loss=2.322, over 5513092.03 frames. , ppl: 10.196230553691507], batch size: 70
+2022-12-10 23:58:20,735 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-10 23:58:21,496 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.309, over 211138.00 frames. , ppl: 10.064753676155952
+2022-12-11 00:00:01,560 INFO [train.py:421] (7/8) Epoch 3, batch 52200, loss[loss=2.519, over 1610.00 frames. , ppl: 12.41385934058205] tot_loss[loss=2.323, over 5492127.30 frames. , ppl: 10.203649478324325], batch size: 70
+2022-12-11 00:01:45,812 INFO [train.py:421] (7/8) Epoch 3, batch 52400, loss[loss=2.346, over 2170.00 frames. , ppl: 10.441743620229477] tot_loss[loss=2.322, over 5512174.42 frames. , ppl: 10.194029221441072], batch size: 70
+2022-12-11 00:03:24,671 INFO [train.py:421] (7/8) Epoch 3, batch 52600, loss[loss=2.402, over 1470.00 frames. , ppl: 11.050759988141817] tot_loss[loss=2.323, over 5458278.67 frames. , ppl: 10.204039518964686], batch size: 70
+2022-12-11 00:05:03,993 INFO [train.py:421] (7/8) Epoch 3, batch 52800, loss[loss=2.54, over 910.00 frames. , ppl: 12.678254547390097] tot_loss[loss=2.322, over 5441374.94 frames. , ppl: 10.19831054758994], batch size: 70
+2022-12-11 00:06:42,494 INFO [train.py:421] (7/8) Epoch 3, batch 53000, loss[loss=2.256, over 2800.00 frames. , ppl: 9.545606724610057] tot_loss[loss=2.322, over 5463589.95 frames. , ppl: 10.193851379806722], batch size: 70
+2022-12-11 00:06:42,495 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 00:06:43,239 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.311, over 211138.00 frames. , ppl: 10.088516415422001
+2022-12-11 00:08:25,724 INFO [train.py:421] (7/8) Epoch 3, batch 53200, loss[loss=2.58, over 1400.00 frames. , ppl: 13.199640016678423] tot_loss[loss=2.322, over 5441980.62 frames. , ppl: 10.19995481560674], batch size: 70
+2022-12-11 00:10:06,550 INFO [train.py:421] (7/8) Epoch 3, batch 53400, loss[loss=3.062, over 560.00 frames. , ppl: 21.370682414010542] tot_loss[loss=2.321, over 5486521.11 frames. , ppl: 10.187033435303361], batch size: 70
+2022-12-11 00:11:48,856 INFO [train.py:421] (7/8) Epoch 3, batch 53600, loss[loss=2.434, over 1120.00 frames. , ppl: 11.405776758313674] tot_loss[loss=2.322, over 5468915.91 frames. , ppl: 10.194634005341369], batch size: 70
+2022-12-11 00:13:30,374 INFO [train.py:421] (7/8) Epoch 3, batch 53800, loss[loss=2.398, over 2660.00 frames. , ppl: 11.004822684275728] tot_loss[loss=2.322, over 5481788.47 frames. , ppl: 10.190955165979485], batch size: 70
+2022-12-11 00:15:11,540 INFO [train.py:421] (7/8) Epoch 3, batch 54000, loss[loss=2.426, over 1750.00 frames. , ppl: 11.309866679683314] tot_loss[loss=2.322, over 5475088.55 frames. , ppl: 10.192135663295254], batch size: 70
+2022-12-11 00:15:11,540 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 00:15:12,298 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.306, over 211138.00 frames. , ppl: 10.032199299773053
+2022-12-11 00:16:54,777 INFO [train.py:421] (7/8) Epoch 3, batch 54200, loss[loss=2.278, over 4620.00 frames. , ppl: 9.752712035467049] tot_loss[loss=2.322, over 5456118.67 frames. , ppl: 10.19372961359199], batch size: 70
+2022-12-11 00:18:34,609 INFO [train.py:421] (7/8) Epoch 3, batch 54400, loss[loss=2.41, over 1400.00 frames. , ppl: 11.135747568402746] tot_loss[loss=2.322, over 5422056.57 frames. , ppl: 10.199421257147268], batch size: 70
+2022-12-11 00:20:14,979 INFO [train.py:421] (7/8) Epoch 3, batch 54600, loss[loss=2.557, over 1050.00 frames. , ppl: 12.896721364582515] tot_loss[loss=2.321, over 5453745.68 frames. , ppl: 10.182512115551352], batch size: 70
+2022-12-11 00:21:53,922 INFO [train.py:421] (7/8) Epoch 3, batch 54800, loss[loss=2.351, over 1680.00 frames. , ppl: 10.497573324872373] tot_loss[loss=2.322, over 5447062.54 frames. , ppl: 10.192285351078452], batch size: 70
+2022-12-11 00:23:33,754 INFO [train.py:421] (7/8) Epoch 3, batch 55000, loss[loss=2.437, over 1190.00 frames. , ppl: 11.434321066959477] tot_loss[loss=2.321, over 5466068.57 frames. , ppl: 10.188046218583825], batch size: 70
+2022-12-11 00:23:33,754 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 00:23:34,513 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.307, over 211138.00 frames. , ppl: 10.042009979542168
+2022-12-11 00:25:14,235 INFO [train.py:421] (7/8) Epoch 3, batch 55200, loss[loss=2.39, over 2310.00 frames. , ppl: 10.908537158211644] tot_loss[loss=2.321, over 5477254.24 frames. , ppl: 10.190641639418017], batch size: 70
+2022-12-11 00:26:51,669 INFO [train.py:421] (7/8) Epoch 3, batch 55400, loss[loss=2.221, over 7770.00 frames. , ppl: 9.218201643496219] tot_loss[loss=2.323, over 5419651.80 frames. , ppl: 10.20248412080429], batch size: 70
+2022-12-11 00:28:28,804 INFO [train.py:421] (7/8) Epoch 3, batch 55600, loss[loss=2.358, over 2240.00 frames. , ppl: 10.568131576203495] tot_loss[loss=2.324, over 5395131.51 frames. , ppl: 10.211439885503992], batch size: 70
+2022-12-11 00:30:05,108 INFO [train.py:421] (7/8) Epoch 3, batch 55800, loss[loss=2.299, over 2800.00 frames. , ppl: 9.965273958035509] tot_loss[loss=2.323, over 5399062.47 frames. , ppl: 10.203794692580683], batch size: 70
+2022-12-11 00:31:49,155 INFO [train.py:421] (7/8) Epoch 3, batch 56000, loss[loss=2.808, over 700.00 frames. , ppl: 16.574288496020575] tot_loss[loss=2.322, over 5388420.69 frames. , ppl: 10.198807733319047], batch size: 70
+2022-12-11 00:31:49,156 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 00:31:49,915 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.306, over 211138.00 frames. , ppl: 10.029381468540643
+2022-12-11 00:33:27,283 INFO [train.py:421] (7/8) Epoch 3, batch 56200, loss[loss=2.406, over 1470.00 frames. , ppl: 11.08807275752316] tot_loss[loss=2.324, over 5364798.53 frames. , ppl: 10.213060921191518], batch size: 70
+2022-12-11 00:35:04,951 INFO [train.py:421] (7/8) Epoch 3, batch 56400, loss[loss=2.894, over 630.00 frames. , ppl: 18.063396020337475] tot_loss[loss=2.324, over 5360073.35 frames. , ppl: 10.218815374823816], batch size: 70
+2022-12-11 00:36:45,127 INFO [train.py:421] (7/8) Epoch 3, batch 56600, loss[loss=2.293, over 3850.00 frames. , ppl: 9.90659392517886] tot_loss[loss=2.325, over 5360073.94 frames. , ppl: 10.221873413010627], batch size: 70
+2022-12-11 00:38:27,988 INFO [train.py:421] (7/8) Epoch 3, batch 56800, loss[loss=2.705, over 770.00 frames. , ppl: 14.947985281689226] tot_loss[loss=2.324, over 5386827.06 frames. , ppl: 10.213747144307193], batch size: 70
+2022-12-11 00:40:12,327 INFO [train.py:421] (7/8) Epoch 3, batch 57000, loss[loss=2.316, over 2940.00 frames. , ppl: 10.138303918377227] tot_loss[loss=2.324, over 5363681.75 frames. , ppl: 10.218073431254863], batch size: 70
+2022-12-11 00:40:12,327 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 00:40:13,085 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.307, over 211138.00 frames. , ppl: 10.04296571105421
+2022-12-11 00:41:53,208 INFO [train.py:421] (7/8) Epoch 3, batch 57200, loss[loss=2.485, over 910.00 frames. , ppl: 12.004908551648986] tot_loss[loss=2.325, over 5348699.98 frames. , ppl: 10.222209855428614], batch size: 70
+2022-12-11 00:43:33,461 INFO [train.py:421] (7/8) Epoch 3, batch 57400, loss[loss=2.204, over 9660.00 frames. , ppl: 9.057720855218689] tot_loss[loss=2.324, over 5371319.33 frames. , ppl: 10.216813358812079], batch size: 70
+2022-12-11 00:45:12,037 INFO [train.py:421] (7/8) Epoch 3, batch 57600, loss[loss=2.372, over 2310.00 frames. , ppl: 10.720255549296903] tot_loss[loss=2.325, over 5350678.40 frames. , ppl: 10.2270782250209], batch size: 70
+2022-12-11 00:46:53,807 INFO [train.py:421] (7/8) Epoch 3, batch 57800, loss[loss=2.615, over 770.00 frames. , ppl: 13.671562175032603] tot_loss[loss=2.324, over 5396691.46 frames. , ppl: 10.214070691522725], batch size: 70
+2022-12-11 00:48:33,992 INFO [train.py:421] (7/8) Epoch 3, batch 58000, loss[loss=3.259, over 490.00 frames. , ppl: 26.02345057666894] tot_loss[loss=2.324, over 5390138.66 frames. , ppl: 10.217790684100478], batch size: 70
+2022-12-11 00:48:33,992 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 00:48:34,750 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.306, over 211138.00 frames. , ppl: 10.037739283472558
+2022-12-11 00:50:13,899 INFO [train.py:421] (7/8) Epoch 3, batch 58200, loss[loss=2.363, over 1120.00 frames. , ppl: 10.62631136606303] tot_loss[loss=2.323, over 5428188.44 frames. , ppl: 10.207015288143781], batch size: 70
+2022-12-11 00:51:51,056 INFO [train.py:421] (7/8) Epoch 3, batch 58400, loss[loss=2.325, over 5460.00 frames. , ppl: 10.229237514521275] tot_loss[loss=2.324, over 5397775.73 frames. , ppl: 10.215470479886312], batch size: 70
+2022-12-11 00:53:28,837 INFO [train.py:421] (7/8) Epoch 3, batch 58600, loss[loss=2.358, over 2870.00 frames. , ppl: 10.57380507089317] tot_loss[loss=2.324, over 5368786.78 frames. , ppl: 10.216577946541689], batch size: 70
+2022-12-11 00:55:08,240 INFO [train.py:421] (7/8) Epoch 3, batch 58800, loss[loss=2.221, over 5250.00 frames. , ppl: 9.218980982256197] tot_loss[loss=2.325, over 5356663.07 frames. , ppl: 10.222821153485599], batch size: 70
+2022-12-11 00:56:50,231 INFO [train.py:421] (7/8) Epoch 3, batch 59000, loss[loss=2.271, over 7210.00 frames. , ppl: 9.685731496512568] tot_loss[loss=2.325, over 5362917.56 frames. , ppl: 10.224797595149905], batch size: 70
+2022-12-11 00:56:50,231 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 00:56:50,962 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.309, over 211138.00 frames. , ppl: 10.063399667509817
+2022-12-11 00:58:29,070 INFO [train.py:421] (7/8) Epoch 3, batch 59200, loss[loss=2.722, over 700.00 frames. , ppl: 15.207785680788191] tot_loss[loss=2.324, over 5373307.39 frames. , ppl: 10.220261088775317], batch size: 70
+2022-12-11 01:00:05,133 INFO [train.py:421] (7/8) Epoch 3, batch 59400, loss[loss=2.547, over 1120.00 frames. , ppl: 12.768808405306983] tot_loss[loss=2.325, over 5349186.01 frames. , ppl: 10.225541453754731], batch size: 70
+2022-12-11 01:01:44,065 INFO [train.py:421] (7/8) Epoch 3, batch 59600, loss[loss=2.324, over 1120.00 frames. , ppl: 10.219883165492089] tot_loss[loss=2.324, over 5375546.22 frames. , ppl: 10.215612371273545], batch size: 70
+2022-12-11 01:03:24,742 INFO [train.py:421] (7/8) Epoch 3, batch 59800, loss[loss=2.217, over 3220.00 frames. , ppl: 9.183635486926418] tot_loss[loss=2.323, over 5391517.28 frames. , ppl: 10.209384023520704], batch size: 70
+2022-12-11 01:05:04,179 INFO [train.py:421] (7/8) Epoch 3, batch 60000, loss[loss=2.264, over 6230.00 frames. , ppl: 9.619376085537315] tot_loss[loss=2.323, over 5407175.67 frames. , ppl: 10.205646034724591], batch size: 70
+2022-12-11 01:05:04,180 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 01:05:04,908 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.307, over 211138.00 frames. , ppl: 10.045027606490608
+2022-12-11 01:06:48,969 INFO [train.py:421] (7/8) Epoch 3, batch 60200, loss[loss=2.359, over 910.00 frames. , ppl: 10.582925811667625] tot_loss[loss=2.323, over 5383118.98 frames. , ppl: 10.211159791088283], batch size: 70
+2022-12-11 01:08:28,495 INFO [train.py:421] (7/8) Epoch 3, batch 60400, loss[loss=2.47, over 980.00 frames. , ppl: 11.828304626438769] tot_loss[loss=2.322, over 5422953.22 frames. , ppl: 10.192897591279731], batch size: 70
+2022-12-11 01:10:08,958 INFO [train.py:421] (7/8) Epoch 3, batch 60600, loss[loss=2.456, over 2030.00 frames. , ppl: 11.662131103216451] tot_loss[loss=2.322, over 5456628.25 frames. , ppl: 10.191133059248408], batch size: 70
+2022-12-11 01:11:50,386 INFO [train.py:421] (7/8) Epoch 3, batch 60800, loss[loss=2.43, over 1260.00 frames. , ppl: 11.359175246896353] tot_loss[loss=2.32, over 5515271.74 frames. , ppl: 10.174071549645902], batch size: 70
+2022-12-11 01:13:29,063 INFO [train.py:421] (7/8) Epoch 3, batch 61000, loss[loss=2.339, over 2100.00 frames. , ppl: 10.370819039414911] tot_loss[loss=2.319, over 5523063.67 frames. , ppl: 10.169412626900433], batch size: 70
+2022-12-11 01:13:29,064 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 01:13:29,818 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.306, over 211138.00 frames. , ppl: 10.0369311167839
+2022-12-11 01:15:11,768 INFO [train.py:421] (7/8) Epoch 3, batch 61200, loss[loss=2.338, over 2380.00 frames. , ppl: 10.360530717777934] tot_loss[loss=2.32, over 5528561.60 frames. , ppl: 10.173655328624902], batch size: 70
+2022-12-11 01:16:52,651 INFO [train.py:421] (7/8) Epoch 3, batch 61400, loss[loss=2.337, over 2660.00 frames. , ppl: 10.347293533716945] tot_loss[loss=2.319, over 5537309.16 frames. , ppl: 10.164825548352923], batch size: 70
+2022-12-11 01:18:30,898 INFO [train.py:421] (7/8) Epoch 3, batch 61600, loss[loss=2.367, over 2450.00 frames. , ppl: 10.667660662240321] tot_loss[loss=2.32, over 5503159.58 frames. , ppl: 10.172921510558588], batch size: 70
+2022-12-11 01:20:08,761 INFO [train.py:421] (7/8) Epoch 3, batch 61800, loss[loss=2.465, over 1750.00 frames. , ppl: 11.762868392556424] tot_loss[loss=2.32, over 5488788.40 frames. , ppl: 10.170900763148232], batch size: 70
+2022-12-11 01:21:46,207 INFO [train.py:421] (7/8) Epoch 3, batch 62000, loss[loss=2.424, over 2030.00 frames. , ppl: 11.285908136613065] tot_loss[loss=2.319, over 5527310.48 frames. , ppl: 10.162403728236024], batch size: 70
+2022-12-11 01:21:46,207 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 01:21:46,967 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.307, over 211138.00 frames. , ppl: 10.04664679581944
+2022-12-11 01:23:28,133 INFO [train.py:421] (7/8) Epoch 3, batch 62200, loss[loss=3.201, over 490.00 frames. , ppl: 24.55903226122184] tot_loss[loss=2.319, over 5509195.65 frames. , ppl: 10.170077280934851], batch size: 70
+2022-12-11 01:25:03,204 INFO [train.py:421] (7/8) Epoch 3, batch 62400, loss[loss=2.398, over 1540.00 frames. , ppl: 10.996194301118802] tot_loss[loss=2.32, over 5485119.02 frames. , ppl: 10.174923452818785], batch size: 70
+2022-12-11 01:26:46,723 INFO [train.py:421] (7/8) Epoch 3, batch 62600, loss[loss=2.274, over 2520.00 frames. , ppl: 9.719259845648544] tot_loss[loss=2.319, over 5512273.19 frames. , ppl: 10.166600584646764], batch size: 70
+2022-12-11 01:28:27,850 INFO [train.py:421] (7/8) Epoch 3, batch 62800, loss[loss=2.264, over 4340.00 frames. , ppl: 9.625404179579908] tot_loss[loss=2.319, over 5515453.05 frames. , ppl: 10.169425233095001], batch size: 70
+2022-12-11 01:30:02,598 INFO [train.py:421] (7/8) Epoch 3, batch 63000, loss[loss=2.603, over 770.00 frames. , ppl: 13.50334531166366] tot_loss[loss=2.32, over 5470530.20 frames. , ppl: 10.180660285637734], batch size: 70
+2022-12-11 01:30:02,599 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 01:30:03,344 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.306, over 211138.00 frames. , ppl: 10.036726114257576
+2022-12-11 01:31:44,153 INFO [train.py:421] (7/8) Epoch 3, batch 63200, loss[loss=2.222, over 4690.00 frames. , ppl: 9.227100459327971] tot_loss[loss=2.32, over 5482484.38 frames. , ppl: 10.17651345098105], batch size: 70
+2022-12-11 01:33:23,261 INFO [train.py:421] (7/8) Epoch 3, batch 63400, loss[loss=2.393, over 1750.00 frames. , ppl: 10.947212103531214] tot_loss[loss=2.322, over 5444985.92 frames. , ppl: 10.193243924558818], batch size: 70
+2022-12-11 01:35:03,944 INFO [train.py:421] (7/8) Epoch 3, batch 63600, loss[loss=2.305, over 3640.00 frames. , ppl: 10.02846384180968] tot_loss[loss=2.322, over 5432316.64 frames. , ppl: 10.200667217144831], batch size: 70
+2022-12-11 01:36:42,934 INFO [train.py:421] (7/8) Epoch 3, batch 63800, loss[loss=2.22, over 6300.00 frames. , ppl: 9.20739651858715] tot_loss[loss=2.321, over 5443014.93 frames. , ppl: 10.189678773607936], batch size: 70
+2022-12-11 01:38:28,652 INFO [train.py:421] (7/8) Epoch 3, batch 64000, loss[loss=2.292, over 3500.00 frames. , ppl: 9.89664835236765] tot_loss[loss=2.32, over 5496864.75 frames. , ppl: 10.175384894605426], batch size: 70
+2022-12-11 01:38:28,653 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 01:38:29,412 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.306, over 211138.00 frames. , ppl: 10.036485464460732
+2022-12-11 01:40:09,937 INFO [train.py:421] (7/8) Epoch 3, batch 64200, loss[loss=2.593, over 980.00 frames. , ppl: 13.363875463889972] tot_loss[loss=2.32, over 5472611.79 frames. , ppl: 10.179699034378045], batch size: 70
+2022-12-11 01:41:46,095 INFO [train.py:421] (7/8) Epoch 3, batch 64400, loss[loss=2.284, over 4410.00 frames. , ppl: 9.819023056134865] tot_loss[loss=2.319, over 5516387.93 frames. , ppl: 10.164224219063108], batch size: 70
+2022-12-11 01:43:25,727 INFO [train.py:421] (7/8) Epoch 3, batch 64600, loss[loss=2.376, over 2380.00 frames. , ppl: 10.763674621469624] tot_loss[loss=2.318, over 5519088.91 frames. , ppl: 10.157076672476743], batch size: 70
+2022-12-11 01:45:05,816 INFO [train.py:421] (7/8) Epoch 3, batch 64800, loss[loss=2.362, over 2660.00 frames. , ppl: 10.612799051748752] tot_loss[loss=2.319, over 5517179.35 frames. , ppl: 10.164678743821439], batch size: 70
+2022-12-11 01:46:48,565 INFO [train.py:421] (7/8) Epoch 3, batch 65000, loss[loss=2.509, over 840.00 frames. , ppl: 12.290002857253821] tot_loss[loss=2.318, over 5542119.85 frames. , ppl: 10.155292535403166], batch size: 70
+2022-12-11 01:46:48,566 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 01:46:49,313 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.305, over 211138.00 frames. , ppl: 10.022263217124767
+2022-12-11 01:48:29,576 INFO [train.py:421] (7/8) Epoch 3, batch 65200, loss[loss=2.908, over 630.00 frames. , ppl: 18.317815602097067] tot_loss[loss=2.318, over 5560714.66 frames. , ppl: 10.153102875043391], batch size: 70
+2022-12-11 01:50:10,537 INFO [train.py:421] (7/8) Epoch 3, batch 65400, loss[loss=2.402, over 2310.00 frames. , ppl: 11.044827449134349] tot_loss[loss=2.318, over 5552044.11 frames. , ppl: 10.154980760076596], batch size: 70
+2022-12-11 01:51:49,276 INFO [train.py:421] (7/8) Epoch 3, batch 65600, loss[loss=2.45, over 1540.00 frames. , ppl: 11.586748522944731] tot_loss[loss=2.316, over 5606761.89 frames. , ppl: 10.138196781148899], batch size: 70
+2022-12-11 01:53:27,734 INFO [train.py:421] (7/8) Epoch 3, batch 65800, loss[loss=2.281, over 4480.00 frames. , ppl: 9.782405067583849] tot_loss[loss=2.317, over 5568545.33 frames. , ppl: 10.147885171000711], batch size: 70
+2022-12-11 01:55:11,466 INFO [train.py:421] (7/8) Epoch 3, batch 66000, loss[loss=2.503, over 1470.00 frames. , ppl: 12.221070327130548] tot_loss[loss=2.319, over 5527061.27 frames. , ppl: 10.161612659126018], batch size: 70
+2022-12-11 01:55:11,467 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 01:55:12,223 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.305, over 211138.00 frames. , ppl: 10.026417513222102
+2022-12-11 01:56:53,404 INFO [train.py:421] (7/8) Epoch 3, batch 66200, loss[loss=2.242, over 4690.00 frames. , ppl: 9.41320389063767] tot_loss[loss=2.318, over 5544646.06 frames. , ppl: 10.15319565758391], batch size: 70
+2022-12-11 01:58:33,167 INFO [train.py:421] (7/8) Epoch 3, batch 66400, loss[loss=2.271, over 3010.00 frames. , ppl: 9.692721094159989] tot_loss[loss=2.317, over 5608714.63 frames. , ppl: 10.140425181641062], batch size: 70
+2022-12-11 02:00:07,973 INFO [train.py:421] (7/8) Epoch 3, batch 66600, loss[loss=2.473, over 1400.00 frames. , ppl: 11.861021663365365] tot_loss[loss=2.319, over 5519788.14 frames. , ppl: 10.161802839722125], batch size: 70
+2022-12-11 02:01:49,360 INFO [train.py:421] (7/8) Epoch 3, batch 66800, loss[loss=2.464, over 1400.00 frames. , ppl: 11.74681618052504] tot_loss[loss=2.319, over 5508684.72 frames. , ppl: 10.167998767940494], batch size: 70
+2022-12-11 02:03:29,979 INFO [train.py:421] (7/8) Epoch 3, batch 67000, loss[loss=2.282, over 5950.00 frames. , ppl: 9.795898653458417] tot_loss[loss=2.32, over 5484308.88 frames. , ppl: 10.173853171988839], batch size: 70
+2022-12-11 02:03:29,980 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 02:03:30,724 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.305, over 211138.00 frames. , ppl: 10.023177014556284
+2022-12-11 02:05:08,154 INFO [train.py:421] (7/8) Epoch 3, batch 67200, loss[loss=2.549, over 1120.00 frames. , ppl: 12.790679426031375] tot_loss[loss=2.319, over 5485113.85 frames. , ppl: 10.170127137683702], batch size: 70
+2022-12-11 02:06:47,989 INFO [train.py:421] (7/8) Epoch 3, batch 67400, loss[loss=2.218, over 5390.00 frames. , ppl: 9.184864138532937] tot_loss[loss=2.319, over 5478801.07 frames. , ppl: 10.167378899187263], batch size: 70
+2022-12-11 02:08:29,680 INFO [train.py:421] (7/8) Epoch 3, batch 67600, loss[loss=2.878, over 630.00 frames. , ppl: 17.785258067098678] tot_loss[loss=2.319, over 5467985.70 frames. , ppl: 10.161506649684812], batch size: 70
+2022-12-11 02:10:11,842 INFO [train.py:421] (7/8) Epoch 3, batch 67800, loss[loss=2.317, over 2940.00 frames. , ppl: 10.146163529244813] tot_loss[loss=2.321, over 5382660.34 frames. , ppl: 10.187027809009743], batch size: 70
+2022-12-11 02:11:53,374 INFO [train.py:421] (7/8) Epoch 3, batch 68000, loss[loss=2.497, over 1120.00 frames. , ppl: 12.150387975576983] tot_loss[loss=2.321, over 5373592.04 frames. , ppl: 10.18238966964757], batch size: 70
+2022-12-11 02:11:53,375 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 02:11:54,123 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.305, over 211138.00 frames. , ppl: 10.025138400067002
+2022-12-11 02:13:31,881 INFO [train.py:421] (7/8) Epoch 3, batch 68200, loss[loss=2.244, over 3710.00 frames. , ppl: 9.430191064781377] tot_loss[loss=2.321, over 5371948.18 frames. , ppl: 10.182672901534568], batch size: 70
+2022-12-11 02:15:11,917 INFO [train.py:421] (7/8) Epoch 3, batch 68400, loss[loss=2.464, over 1470.00 frames. , ppl: 11.756623137095039] tot_loss[loss=2.321, over 5344632.18 frames. , ppl: 10.182111175779426], batch size: 70
+2022-12-11 02:16:58,788 INFO [train.py:421] (7/8) Epoch 3, batch 68600, loss[loss=2.338, over 2590.00 frames. , ppl: 10.365193080666156] tot_loss[loss=2.32, over 5371474.98 frames. , ppl: 10.175681845849152], batch size: 70
+2022-12-11 02:18:39,314 INFO [train.py:421] (7/8) Epoch 3, batch 68800, loss[loss=2.327, over 1890.00 frames. , ppl: 10.249956675920066] tot_loss[loss=2.319, over 5406441.11 frames. , ppl: 10.163784331498467], batch size: 70
+2022-12-11 02:20:20,722 INFO [train.py:421] (7/8) Epoch 3, batch 69000, loss[loss=2.561, over 1050.00 frames. , ppl: 12.942412027863204] tot_loss[loss=2.319, over 5415100.17 frames. , ppl: 10.164342464377498], batch size: 70
+2022-12-11 02:20:20,723 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 02:20:21,480 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.305, over 211138.00 frames. , ppl: 10.019322126504301
+2022-12-11 02:22:00,181 INFO [train.py:421] (7/8) Epoch 3, batch 69200, loss[loss=2.657, over 770.00 frames. , ppl: 14.254409333510116] tot_loss[loss=2.319, over 5436853.47 frames. , ppl: 10.162773751999858], batch size: 70
+2022-12-11 02:23:42,000 INFO [train.py:421] (7/8) Epoch 3, batch 69400, loss[loss=2.221, over 4340.00 frames. , ppl: 9.215416021056999] tot_loss[loss=2.319, over 5471076.16 frames. , ppl: 10.160657199757921], batch size: 70
+2022-12-11 02:25:20,934 INFO [train.py:421] (7/8) Epoch 3, batch 69600, loss[loss=2.919, over 630.00 frames. , ppl: 18.52543935505209] tot_loss[loss=2.318, over 5490998.95 frames. , ppl: 10.150848095425696], batch size: 70
+2022-12-11 02:27:00,943 INFO [train.py:421] (7/8) Epoch 3, batch 69800, loss[loss=2.5, over 1890.00 frames. , ppl: 12.187883408322469] tot_loss[loss=2.317, over 5503397.74 frames. , ppl: 10.146548319130607], batch size: 70
+2022-12-11 02:28:40,258 INFO [train.py:421] (7/8) Epoch 3, batch 70000, loss[loss=2.235, over 5740.00 frames. , ppl: 9.350487327621122] tot_loss[loss=2.317, over 5501542.96 frames. , ppl: 10.1479092245589], batch size: 70
+2022-12-11 02:28:40,258 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 02:28:40,991 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.305, over 211138.00 frames. , ppl: 10.023684386112267
+2022-12-11 02:30:18,975 INFO [train.py:421] (7/8) Epoch 3, batch 70200, loss[loss=2.383, over 2100.00 frames. , ppl: 10.83784401713129] tot_loss[loss=2.317, over 5474013.04 frames. , ppl: 10.147203293135256], batch size: 70
+2022-12-11 02:31:59,182 INFO [train.py:421] (7/8) Epoch 3, batch 70400, loss[loss=2.405, over 1400.00 frames. , ppl: 11.080847383910262] tot_loss[loss=2.317, over 5473769.05 frames. , ppl: 10.148999773374847], batch size: 70
+2022-12-11 02:33:37,899 INFO [train.py:421] (7/8) Epoch 3, batch 70600, loss[loss=2.647, over 630.00 frames. , ppl: 14.105803296542216] tot_loss[loss=2.317, over 5497417.61 frames. , ppl: 10.143694100536951], batch size: 70
+2022-12-11 02:35:16,197 INFO [train.py:421] (7/8) Epoch 3, batch 70800, loss[loss=2.215, over 6860.00 frames. , ppl: 9.165197761008816] tot_loss[loss=2.318, over 5457830.83 frames. , ppl: 10.155690891464465], batch size: 70
+2022-12-11 02:36:54,122 INFO [train.py:421] (7/8) Epoch 3, batch 71000, loss[loss=2.901, over 700.00 frames. , ppl: 18.193488504357862] tot_loss[loss=2.319, over 5409327.66 frames. , ppl: 10.169764828986008], batch size: 70
+2022-12-11 02:36:54,123 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 02:36:54,881 INFO [train.py:452] (7/8) Epoch 3, validation: loss=2.303, over 211138.00 frames. , ppl: 10.006615510581163
+2022-12-11 02:38:34,996 INFO [train.py:421] (7/8) Epoch 3, batch 71200, loss[loss=2.236, over 5460.00 frames. , ppl: 9.351848846580742] tot_loss[loss=2.318, over 5468570.31 frames. , ppl: 10.152154924024956], batch size: 70
+2022-12-11 02:40:17,302 INFO [train.py:421] (7/8) Epoch 3, batch 71400, loss[loss=2.881, over 560.00 frames. , ppl: 17.82835690942696] tot_loss[loss=2.318, over 5454821.30 frames. , ppl: 10.15844157161736], batch size: 70
+2022-12-11 02:41:59,129 INFO [train.py:421] (7/8) Epoch 3, batch 71600, loss[loss=2.454, over 1050.00 frames. , ppl: 11.63205228748661] tot_loss[loss=2.319, over 5431976.89 frames. , ppl: 10.164548706709978], batch size: 70
+2022-12-11 02:43:42,996 INFO [train.py:421] (7/8) Epoch 3, batch 71800, loss[loss=2.226, over 8260.00 frames. , ppl: 9.262431835046966] tot_loss[loss=2.318, over 5460500.87 frames. , ppl: 10.15988786240943], batch size: 70
+2022-12-11 02:44:57,812 INFO [train.py:421] (7/8) Epoch 4, batch 0, loss[loss=2.284, over 3640.00 frames. , ppl: 9.812807842491079] tot_loss[loss=2.284, over 3640.00 frames. , ppl: 9.812807842491079], batch size: 70
+2022-12-11 02:46:37,254 INFO [train.py:421] (7/8) Epoch 4, batch 200, loss[loss=2.252, over 5740.00 frames. , ppl: 9.50444756790511] tot_loss[loss=2.315, over 511071.90 frames. , ppl: 10.124166921888156], batch size: 70
+2022-12-11 02:48:15,755 INFO [train.py:421] (7/8) Epoch 4, batch 400, loss[loss=2.345, over 2030.00 frames. , ppl: 10.438391442036835] tot_loss[loss=2.317, over 963873.02 frames. , ppl: 10.147654050533282], batch size: 70
+2022-12-11 02:49:54,210 INFO [train.py:421] (7/8) Epoch 4, batch 600, loss[loss=2.602, over 910.00 frames. , ppl: 13.485153352944865] tot_loss[loss=2.318, over 1372206.29 frames. , ppl: 10.157910789003434], batch size: 70
+2022-12-11 02:51:35,083 INFO [train.py:421] (7/8) Epoch 4, batch 800, loss[loss=2.312, over 3220.00 frames. , ppl: 10.093150705266655] tot_loss[loss=2.314, over 1774453.88 frames. , ppl: 10.111820854781808], batch size: 70
+2022-12-11 02:53:15,879 INFO [train.py:421] (7/8) Epoch 4, batch 1000, loss[loss=2.431, over 1960.00 frames. , ppl: 11.37062485724874] tot_loss[loss=2.314, over 2099016.15 frames. , ppl: 10.116416896334368], batch size: 70
+2022-12-11 02:53:15,880 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 02:53:16,642 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.303, over 211138.00 frames. , ppl: 10.006100117136109
+2022-12-11 02:54:58,858 INFO [train.py:421] (7/8) Epoch 4, batch 1200, loss[loss=2.257, over 3500.00 frames. , ppl: 9.553761858736443] tot_loss[loss=2.316, over 2380544.16 frames. , ppl: 10.137719031081293], batch size: 70
+2022-12-11 02:56:36,318 INFO [train.py:421] (7/8) Epoch 4, batch 1400, loss[loss=2.342, over 2310.00 frames. , ppl: 10.400927179040217] tot_loss[loss=2.317, over 2631577.43 frames. , ppl: 10.14772964654811], batch size: 70
+2022-12-11 02:58:17,503 INFO [train.py:421] (7/8) Epoch 4, batch 1600, loss[loss=2.527, over 770.00 frames. , ppl: 12.516871005805445] tot_loss[loss=2.316, over 2921068.60 frames. , ppl: 10.130597338265458], batch size: 70
+2022-12-11 02:59:58,143 INFO [train.py:421] (7/8) Epoch 4, batch 1800, loss[loss=2.475, over 840.00 frames. , ppl: 11.879034526901508] tot_loss[loss=2.315, over 3145198.52 frames. , ppl: 10.126613391647275], batch size: 70
+2022-12-11 03:01:36,821 INFO [train.py:421] (7/8) Epoch 4, batch 2000, loss[loss=2.187, over 10500.00 frames. , ppl: 8.904711717875372] tot_loss[loss=2.315, over 3389941.98 frames. , ppl: 10.122849287272953], batch size: 70
+2022-12-11 03:01:36,821 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 03:01:37,550 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.305, over 211138.00 frames. , ppl: 10.020806653868545
+2022-12-11 03:03:19,551 INFO [train.py:421] (7/8) Epoch 4, batch 2200, loss[loss=2.283, over 3430.00 frames. , ppl: 9.809412159633714] tot_loss[loss=2.315, over 3572261.38 frames. , ppl: 10.12011405182261], batch size: 70
+2022-12-11 03:04:59,304 INFO [train.py:421] (7/8) Epoch 4, batch 2400, loss[loss=2.28, over 2450.00 frames. , ppl: 9.778738218241708] tot_loss[loss=2.316, over 3729053.85 frames. , ppl: 10.134745155696036], batch size: 70
+2022-12-11 03:06:39,921 INFO [train.py:421] (7/8) Epoch 4, batch 2600, loss[loss=2.344, over 3500.00 frames. , ppl: 10.418826367680115] tot_loss[loss=2.317, over 3887556.92 frames. , ppl: 10.141156377854832], batch size: 70
+2022-12-11 03:08:21,018 INFO [train.py:421] (7/8) Epoch 4, batch 2800, loss[loss=2.237, over 4410.00 frames. , ppl: 9.360716974548367] tot_loss[loss=2.316, over 4059326.80 frames. , ppl: 10.131449279642307], batch size: 70
+2022-12-11 03:09:57,239 INFO [train.py:421] (7/8) Epoch 4, batch 3000, loss[loss=2.33, over 3570.00 frames. , ppl: 10.275095565313041] tot_loss[loss=2.315, over 4152700.43 frames. , ppl: 10.129559787231717], batch size: 70
+2022-12-11 03:09:57,240 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 03:09:58,000 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.303, over 211138.00 frames. , ppl: 10.00204158109846
+2022-12-11 03:11:38,667 INFO [train.py:421] (7/8) Epoch 4, batch 3200, loss[loss=2.231, over 2870.00 frames. , ppl: 9.30968920953265] tot_loss[loss=2.315, over 4287578.07 frames. , ppl: 10.123962973764474], batch size: 70
+2022-12-11 03:13:21,675 INFO [train.py:421] (7/8) Epoch 4, batch 3400, loss[loss=2.296, over 6020.00 frames. , ppl: 9.931390808069782] tot_loss[loss=2.313, over 4457438.64 frames. , ppl: 10.100509916984478], batch size: 70
+2022-12-11 03:15:01,796 INFO [train.py:421] (7/8) Epoch 4, batch 3600, loss[loss=2.409, over 1400.00 frames. , ppl: 11.11868728721186] tot_loss[loss=2.311, over 4595854.75 frames. , ppl: 10.088072194940931], batch size: 70
+2022-12-11 03:16:43,478 INFO [train.py:421] (7/8) Epoch 4, batch 3800, loss[loss=2.217, over 2870.00 frames. , ppl: 9.182460472873892] tot_loss[loss=2.311, over 4707403.11 frames. , ppl: 10.08693793617128], batch size: 70
+2022-12-11 03:18:23,717 INFO [train.py:421] (7/8) Epoch 4, batch 4000, loss[loss=2.866, over 560.00 frames. , ppl: 17.57186428138323] tot_loss[loss=2.311, over 4800592.84 frames. , ppl: 10.079861706234054], batch size: 70
+2022-12-11 03:18:23,717 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 03:18:24,476 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.305, over 211138.00 frames. , ppl: 10.024831259142056
+2022-12-11 03:20:05,986 INFO [train.py:421] (7/8) Epoch 4, batch 4200, loss[loss=2.318, over 2310.00 frames. , ppl: 10.152905385064205] tot_loss[loss=2.309, over 4904942.28 frames. , ppl: 10.068903291674225], batch size: 70
+2022-12-11 03:21:49,027 INFO [train.py:421] (7/8) Epoch 4, batch 4400, loss[loss=2.305, over 3710.00 frames. , ppl: 10.025383641136564] tot_loss[loss=2.31, over 4948224.59 frames. , ppl: 10.074442002192258], batch size: 70
+2022-12-11 03:23:27,758 INFO [train.py:421] (7/8) Epoch 4, batch 4600, loss[loss=2.196, over 3430.00 frames. , ppl: 8.988625415699339] tot_loss[loss=2.31, over 5010114.68 frames. , ppl: 10.076723976268982], batch size: 70
+2022-12-11 03:25:07,824 INFO [train.py:421] (7/8) Epoch 4, batch 4800, loss[loss=2.315, over 3710.00 frames. , ppl: 10.127277565420767] tot_loss[loss=2.311, over 5041582.81 frames. , ppl: 10.086725357436002], batch size: 70
+2022-12-11 03:26:49,290 INFO [train.py:421] (7/8) Epoch 4, batch 5000, loss[loss=2.391, over 3360.00 frames. , ppl: 10.920301139152524] tot_loss[loss=2.311, over 5071009.07 frames. , ppl: 10.087508811002392], batch size: 70
+2022-12-11 03:26:49,291 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 03:26:50,036 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.303, over 211138.00 frames. , ppl: 10.007444935075092
+2022-12-11 03:28:31,282 INFO [train.py:421] (7/8) Epoch 4, batch 5200, loss[loss=2.328, over 3150.00 frames. , ppl: 10.259625117741406] tot_loss[loss=2.31, over 5142787.62 frames. , ppl: 10.078062924906714], batch size: 70
+2022-12-11 03:30:12,449 INFO [train.py:421] (7/8) Epoch 4, batch 5400, loss[loss=2.456, over 1190.00 frames. , ppl: 11.659326152454248] tot_loss[loss=2.31, over 5183386.70 frames. , ppl: 10.077486399491468], batch size: 70
+2022-12-11 03:31:52,291 INFO [train.py:421] (7/8) Epoch 4, batch 5600, loss[loss=2.357, over 2870.00 frames. , ppl: 10.562062643689458] tot_loss[loss=2.311, over 5202283.58 frames. , ppl: 10.083075057130744], batch size: 70
+2022-12-11 03:33:32,829 INFO [train.py:421] (7/8) Epoch 4, batch 5800, loss[loss=2.416, over 1680.00 frames. , ppl: 11.20299492453008] tot_loss[loss=2.309, over 5270979.94 frames. , ppl: 10.06927527654611], batch size: 70
+2022-12-11 03:35:14,371 INFO [train.py:421] (7/8) Epoch 4, batch 6000, loss[loss=2.22, over 4900.00 frames. , ppl: 9.210212277563064] tot_loss[loss=2.309, over 5306161.30 frames. , ppl: 10.065619586235218], batch size: 70
+2022-12-11 03:35:14,372 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 03:35:15,103 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.303, over 211138.00 frames. , ppl: 10.002629307959912
+2022-12-11 03:36:56,274 INFO [train.py:421] (7/8) Epoch 4, batch 6200, loss[loss=2.538, over 1190.00 frames. , ppl: 12.657174587522334] tot_loss[loss=2.309, over 5321657.61 frames. , ppl: 10.068539417572289], batch size: 70
+2022-12-11 03:38:34,614 INFO [train.py:421] (7/8) Epoch 4, batch 6400, loss[loss=2.401, over 1890.00 frames. , ppl: 11.029913571153113] tot_loss[loss=2.31, over 5310727.97 frames. , ppl: 10.078940208158661], batch size: 70
+2022-12-11 03:40:16,695 INFO [train.py:421] (7/8) Epoch 4, batch 6600, loss[loss=2.285, over 3920.00 frames. , ppl: 9.82923667254786] tot_loss[loss=2.31, over 5355402.78 frames. , ppl: 10.075070346269154], batch size: 70
+2022-12-11 03:41:57,722 INFO [train.py:421] (7/8) Epoch 4, batch 6800, loss[loss=2.48, over 1470.00 frames. , ppl: 11.94335968557655] tot_loss[loss=2.311, over 5374938.66 frames. , ppl: 10.079772578076291], batch size: 70
+2022-12-11 03:43:38,827 INFO [train.py:421] (7/8) Epoch 4, batch 7000, loss[loss=3.672, over 420.00 frames. , ppl: 39.32505789012363] tot_loss[loss=2.311, over 5374920.70 frames. , ppl: 10.08402481207658], batch size: 70
+2022-12-11 03:43:38,827 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 03:43:39,587 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.304, over 211138.00 frames. , ppl: 10.018172918207874
+2022-12-11 03:45:21,083 INFO [train.py:421] (7/8) Epoch 4, batch 7200, loss[loss=2.483, over 840.00 frames. , ppl: 11.97480252580457] tot_loss[loss=2.311, over 5403584.92 frames. , ppl: 10.082357813545066], batch size: 70
+2022-12-11 03:47:01,074 INFO [train.py:421] (7/8) Epoch 4, batch 7400, loss[loss=3.03, over 700.00 frames. , ppl: 20.699585993903252] tot_loss[loss=2.31, over 5401232.15 frames. , ppl: 10.076922717262848], batch size: 70
+2022-12-11 03:48:40,871 INFO [train.py:421] (7/8) Epoch 4, batch 7600, loss[loss=2.699, over 770.00 frames. , ppl: 14.869506933680906] tot_loss[loss=2.309, over 5474074.45 frames. , ppl: 10.065127330868785], batch size: 70
+2022-12-11 03:50:23,893 INFO [train.py:421] (7/8) Epoch 4, batch 7800, loss[loss=2.685, over 840.00 frames. , ppl: 14.651636005421002] tot_loss[loss=2.31, over 5461799.93 frames. , ppl: 10.074176942770887], batch size: 70
+2022-12-11 03:52:01,578 INFO [train.py:421] (7/8) Epoch 4, batch 8000, loss[loss=2.298, over 2240.00 frames. , ppl: 9.949379641017769] tot_loss[loss=2.31, over 5445438.28 frames. , ppl: 10.06976993357872], batch size: 70
+2022-12-11 03:52:01,578 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 03:52:02,323 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.304, over 211138.00 frames. , ppl: 10.015572487058913
+2022-12-11 03:53:42,802 INFO [train.py:421] (7/8) Epoch 4, batch 8200, loss[loss=2.577, over 980.00 frames. , ppl: 13.157395766920994] tot_loss[loss=2.31, over 5452354.72 frames. , ppl: 10.069895515455377], batch size: 70
+2022-12-11 03:55:20,982 INFO [train.py:421] (7/8) Epoch 4, batch 8400, loss[loss=2.205, over 5040.00 frames. , ppl: 9.066897522311717] tot_loss[loss=2.309, over 5478370.78 frames. , ppl: 10.061383478780112], batch size: 70
+2022-12-11 03:56:59,260 INFO [train.py:421] (7/8) Epoch 4, batch 8600, loss[loss=2.991, over 560.00 frames. , ppl: 19.898340476263296] tot_loss[loss=2.31, over 5459909.04 frames. , ppl: 10.07577524527637], batch size: 70
+2022-12-11 03:58:39,458 INFO [train.py:421] (7/8) Epoch 4, batch 8800, loss[loss=2.465, over 1260.00 frames. , ppl: 11.768515056347482] tot_loss[loss=2.311, over 5440213.09 frames. , ppl: 10.080960248917794], batch size: 70
+2022-12-11 04:00:15,936 INFO [train.py:421] (7/8) Epoch 4, batch 9000, loss[loss=2.32, over 1120.00 frames. , ppl: 10.17924965780181] tot_loss[loss=2.31, over 5472448.94 frames. , ppl: 10.070250397470577], batch size: 70
+2022-12-11 04:00:15,937 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 04:00:16,697 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.305, over 211138.00 frames. , ppl: 10.02282839694073
+2022-12-11 04:01:59,797 INFO [train.py:421] (7/8) Epoch 4, batch 9200, loss[loss=2.616, over 770.00 frames. , ppl: 13.675106320313681] tot_loss[loss=2.31, over 5482158.94 frames. , ppl: 10.072522088835548], batch size: 70
+2022-12-11 04:03:46,667 INFO [train.py:421] (7/8) Epoch 4, batch 9400, loss[loss=2.335, over 2450.00 frames. , ppl: 10.331506425751252] tot_loss[loss=2.308, over 5546983.16 frames. , ppl: 10.05790899731676], batch size: 70
+2022-12-11 04:05:23,922 INFO [train.py:421] (7/8) Epoch 4, batch 9600, loss[loss=2.318, over 1400.00 frames. , ppl: 10.153290615949553] tot_loss[loss=2.31, over 5502368.53 frames. , ppl: 10.071473792318388], batch size: 70
+2022-12-11 04:07:04,993 INFO [train.py:421] (7/8) Epoch 4, batch 9800, loss[loss=2.339, over 8190.00 frames. , ppl: 10.375263960654163] tot_loss[loss=2.311, over 5464034.39 frames. , ppl: 10.085808136559239], batch size: 70
+2022-12-11 04:08:44,055 INFO [train.py:421] (7/8) Epoch 4, batch 10000, loss[loss=2.434, over 1680.00 frames. , ppl: 11.401943586530157] tot_loss[loss=2.312, over 5457089.83 frames. , ppl: 10.090194577774161], batch size: 70
+2022-12-11 04:08:44,056 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 04:08:44,815 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.305, over 211138.00 frames. , ppl: 10.02091344153873
+2022-12-11 04:10:25,961 INFO [train.py:421] (7/8) Epoch 4, batch 10200, loss[loss=2.394, over 2800.00 frames. , ppl: 10.953548902786173] tot_loss[loss=2.31, over 5491719.70 frames. , ppl: 10.076186915672618], batch size: 70
+2022-12-11 04:12:05,341 INFO [train.py:421] (7/8) Epoch 4, batch 10400, loss[loss=2.309, over 4830.00 frames. , ppl: 10.069225342647847] tot_loss[loss=2.311, over 5444935.94 frames. , ppl: 10.088041535457094], batch size: 70
+2022-12-11 04:13:45,273 INFO [train.py:421] (7/8) Epoch 4, batch 10600, loss[loss=3.504, over 490.00 frames. , ppl: 33.24965078001617] tot_loss[loss=2.311, over 5468810.62 frames. , ppl: 10.080538926240093], batch size: 70
+2022-12-11 04:15:25,275 INFO [train.py:421] (7/8) Epoch 4, batch 10800, loss[loss=2.415, over 2100.00 frames. , ppl: 11.191060918878598] tot_loss[loss=2.312, over 5433033.74 frames. , ppl: 10.092474320970984], batch size: 70
+2022-12-11 04:17:08,163 INFO [train.py:421] (7/8) Epoch 4, batch 11000, loss[loss=2.282, over 2520.00 frames. , ppl: 9.797569371498941] tot_loss[loss=2.31, over 5487595.96 frames. , ppl: 10.078734290675166], batch size: 70
+2022-12-11 04:17:08,164 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 04:17:08,910 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.303, over 211138.00 frames. , ppl: 10.005364098386623
+2022-12-11 04:18:47,980 INFO [train.py:421] (7/8) Epoch 4, batch 11200, loss[loss=2.331, over 2940.00 frames. , ppl: 10.287451086423907] tot_loss[loss=2.309, over 5522930.82 frames. , ppl: 10.062525898118158], batch size: 70
+2022-12-11 04:20:23,516 INFO [train.py:421] (7/8) Epoch 4, batch 11400, loss[loss=2.384, over 3150.00 frames. , ppl: 10.843937312722213] tot_loss[loss=2.308, over 5553720.66 frames. , ppl: 10.055465156300418], batch size: 70
+2022-12-11 04:22:05,496 INFO [train.py:421] (7/8) Epoch 4, batch 11600, loss[loss=2.515, over 1190.00 frames. , ppl: 12.363880136926932] tot_loss[loss=2.308, over 5567309.45 frames. , ppl: 10.056768135908314], batch size: 70
+2022-12-11 04:23:44,973 INFO [train.py:421] (7/8) Epoch 4, batch 11800, loss[loss=2.261, over 4620.00 frames. , ppl: 9.59144697936644] tot_loss[loss=2.308, over 5591685.67 frames. , ppl: 10.051659009176612], batch size: 70
+2022-12-11 04:25:25,251 INFO [train.py:421] (7/8) Epoch 4, batch 12000, loss[loss=2.306, over 2940.00 frames. , ppl: 10.033503005516126] tot_loss[loss=2.308, over 5570870.03 frames. , ppl: 10.056484533660385], batch size: 70
+2022-12-11 04:25:25,252 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 04:25:25,998 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.301, over 211138.00 frames. , ppl: 9.98219907371343
+2022-12-11 04:27:07,828 INFO [train.py:421] (7/8) Epoch 4, batch 12200, loss[loss=2.395, over 1750.00 frames. , ppl: 10.970429261544371] tot_loss[loss=2.31, over 5538392.35 frames. , ppl: 10.07061114856269], batch size: 70
+2022-12-11 04:28:46,459 INFO [train.py:421] (7/8) Epoch 4, batch 12400, loss[loss=2.228, over 4760.00 frames. , ppl: 9.281386388338811] tot_loss[loss=2.309, over 5519992.45 frames. , ppl: 10.068151149726651], batch size: 70
+2022-12-11 04:30:27,176 INFO [train.py:421] (7/8) Epoch 4, batch 12600, loss[loss=2.416, over 1960.00 frames. , ppl: 11.19956703068304] tot_loss[loss=2.31, over 5515186.09 frames. , ppl: 10.078372261034302], batch size: 70
+2022-12-11 04:32:07,001 INFO [train.py:421] (7/8) Epoch 4, batch 12800, loss[loss=2.44, over 1400.00 frames. , ppl: 11.472426532201595] tot_loss[loss=2.311, over 5505255.53 frames. , ppl: 10.081020799228984], batch size: 70
+2022-12-11 04:33:50,382 INFO [train.py:421] (7/8) Epoch 4, batch 13000, loss[loss=2.379, over 2450.00 frames. , ppl: 10.794158433814811] tot_loss[loss=2.31, over 5525296.15 frames. , ppl: 10.079457712864336], batch size: 70
+2022-12-11 04:33:50,383 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 04:33:51,146 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.3, over 211138.00 frames. , ppl: 9.97099750372906
+2022-12-11 04:35:32,578 INFO [train.py:421] (7/8) Epoch 4, batch 13200, loss[loss=2.346, over 1960.00 frames. , ppl: 10.44382913151495] tot_loss[loss=2.311, over 5499502.41 frames. , ppl: 10.088577768482388], batch size: 70
+2022-12-11 04:37:11,863 INFO [train.py:421] (7/8) Epoch 4, batch 13400, loss[loss=2.226, over 6020.00 frames. , ppl: 9.262260877135096] tot_loss[loss=2.311, over 5510031.78 frames. , ppl: 10.084455215140414], batch size: 70
+2022-12-11 04:38:49,025 INFO [train.py:421] (7/8) Epoch 4, batch 13600, loss[loss=2.286, over 1610.00 frames. , ppl: 9.834159451938625] tot_loss[loss=2.312, over 5512947.80 frames. , ppl: 10.093394815078991], batch size: 70
+2022-12-11 04:40:27,701 INFO [train.py:421] (7/8) Epoch 4, batch 13800, loss[loss=2.521, over 1330.00 frames. , ppl: 12.445560298302405] tot_loss[loss=2.311, over 5518883.05 frames. , ppl: 10.088359496685147], batch size: 70
+2022-12-11 04:42:07,536 INFO [train.py:421] (7/8) Epoch 4, batch 14000, loss[loss=2.25, over 5740.00 frames. , ppl: 9.484687148872933] tot_loss[loss=2.31, over 5566414.77 frames. , ppl: 10.071356093835297], batch size: 70
+2022-12-11 04:42:07,536 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 04:42:08,266 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.301, over 211138.00 frames. , ppl: 9.986692979928648
+2022-12-11 04:43:46,529 INFO [train.py:421] (7/8) Epoch 4, batch 14200, loss[loss=2.313, over 2520.00 frames. , ppl: 10.107535653937722] tot_loss[loss=2.31, over 5533550.90 frames. , ppl: 10.074837848478856], batch size: 70
+2022-12-11 04:45:27,609 INFO [train.py:421] (7/8) Epoch 4, batch 14400, loss[loss=2.221, over 3850.00 frames. , ppl: 9.217348443045172] tot_loss[loss=2.311, over 5513816.50 frames. , ppl: 10.083788924378288], batch size: 70
+2022-12-11 04:47:07,724 INFO [train.py:421] (7/8) Epoch 4, batch 14600, loss[loss=2.467, over 1680.00 frames. , ppl: 11.781806419116117] tot_loss[loss=2.309, over 5552469.04 frames. , ppl: 10.06791919980658], batch size: 70
+2022-12-11 04:48:49,493 INFO [train.py:421] (7/8) Epoch 4, batch 14800, loss[loss=2.425, over 910.00 frames. , ppl: 11.29700305583568] tot_loss[loss=2.31, over 5536783.89 frames. , ppl: 10.072095646462717], batch size: 70
+2022-12-11 04:50:23,944 INFO [train.py:421] (7/8) Epoch 4, batch 15000, loss[loss=2.254, over 2940.00 frames. , ppl: 9.528307895231098] tot_loss[loss=2.31, over 5499087.54 frames. , ppl: 10.078328783782208], batch size: 70
+2022-12-11 04:50:23,945 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 04:50:24,691 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.3, over 211138.00 frames. , ppl: 9.975186652961758
+2022-12-11 04:52:04,460 INFO [train.py:421] (7/8) Epoch 4, batch 15200, loss[loss=2.79, over 700.00 frames. , ppl: 16.27826034829459] tot_loss[loss=2.31, over 5507233.48 frames. , ppl: 10.078647482829968], batch size: 70
+2022-12-11 04:53:41,645 INFO [train.py:421] (7/8) Epoch 4, batch 15400, loss[loss=2.353, over 2030.00 frames. , ppl: 10.513074162529465] tot_loss[loss=2.31, over 5533320.10 frames. , ppl: 10.07062704286552], batch size: 70
+2022-12-11 04:55:25,233 INFO [train.py:421] (7/8) Epoch 4, batch 15600, loss[loss=2.545, over 1050.00 frames. , ppl: 12.743844402922468] tot_loss[loss=2.309, over 5560561.89 frames. , ppl: 10.062774519337792], batch size: 70
+2022-12-11 04:57:01,736 INFO [train.py:421] (7/8) Epoch 4, batch 15800, loss[loss=2.422, over 1820.00 frames. , ppl: 11.264513878927453] tot_loss[loss=2.31, over 5541669.44 frames. , ppl: 10.078558721840821], batch size: 70
+2022-12-11 04:58:46,139 INFO [train.py:421] (7/8) Epoch 4, batch 16000, loss[loss=2.284, over 2590.00 frames. , ppl: 9.818469728676313] tot_loss[loss=2.31, over 5519827.33 frames. , ppl: 10.069819379468735], batch size: 70
+2022-12-11 04:58:46,140 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 04:58:46,898 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.301, over 211138.00 frames. , ppl: 9.980866511809946
+2022-12-11 05:00:26,708 INFO [train.py:421] (7/8) Epoch 4, batch 16200, loss[loss=2.511, over 1260.00 frames. , ppl: 12.315679059329268] tot_loss[loss=2.309, over 5546822.94 frames. , ppl: 10.061401174356122], batch size: 70
+2022-12-11 05:02:10,988 INFO [train.py:421] (7/8) Epoch 4, batch 16400, loss[loss=2.425, over 1820.00 frames. , ppl: 11.306457144627112] tot_loss[loss=2.308, over 5586984.85 frames. , ppl: 10.05394542630478], batch size: 70
+2022-12-11 05:03:48,549 INFO [train.py:421] (7/8) Epoch 4, batch 16600, loss[loss=3.304, over 490.00 frames. , ppl: 27.234070188303182] tot_loss[loss=2.307, over 5596475.67 frames. , ppl: 10.045770807343526], batch size: 70
+2022-12-11 05:05:30,768 INFO [train.py:421] (7/8) Epoch 4, batch 16800, loss[loss=2.222, over 7700.00 frames. , ppl: 9.227816952872201] tot_loss[loss=2.308, over 5586035.28 frames. , ppl: 10.049837365369266], batch size: 70
+2022-12-11 05:07:12,261 INFO [train.py:421] (7/8) Epoch 4, batch 17000, loss[loss=2.288, over 2730.00 frames. , ppl: 9.859700718083346] tot_loss[loss=2.308, over 5580684.36 frames. , ppl: 10.053227562592275], batch size: 70
+2022-12-11 05:07:12,261 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 05:07:13,003 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.302, over 211138.00 frames. , ppl: 9.993913175932885
+2022-12-11 05:08:54,242 INFO [train.py:421] (7/8) Epoch 4, batch 17200, loss[loss=3.287, over 490.00 frames. , ppl: 26.752990331342428] tot_loss[loss=2.308, over 5581138.67 frames. , ppl: 10.054581535356345], batch size: 70
+2022-12-11 05:10:34,555 INFO [train.py:421] (7/8) Epoch 4, batch 17400, loss[loss=2.266, over 4970.00 frames. , ppl: 9.644549031791735] tot_loss[loss=2.308, over 5566015.50 frames. , ppl: 10.052619543253709], batch size: 70
+2022-12-11 05:12:12,663 INFO [train.py:421] (7/8) Epoch 4, batch 17600, loss[loss=2.331, over 2520.00 frames. , ppl: 10.286698208073611] tot_loss[loss=2.308, over 5552680.40 frames. , ppl: 10.05192034357244], batch size: 70
+2022-12-11 05:13:51,762 INFO [train.py:421] (7/8) Epoch 4, batch 17800, loss[loss=3.754, over 420.00 frames. , ppl: 42.71149398894531] tot_loss[loss=2.31, over 5506930.34 frames. , ppl: 10.06990523271033], batch size: 70
+2022-12-11 05:15:30,815 INFO [train.py:421] (7/8) Epoch 4, batch 18000, loss[loss=2.797, over 910.00 frames. , ppl: 16.39522436005143] tot_loss[loss=2.309, over 5524998.91 frames. , ppl: 10.063693086116213], batch size: 70
+2022-12-11 05:15:30,816 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 05:15:31,578 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.302, over 211138.00 frames. , ppl: 9.995456073238609
+2022-12-11 05:17:10,758 INFO [train.py:421] (7/8) Epoch 4, batch 18200, loss[loss=2.36, over 2870.00 frames. , ppl: 10.594062655348901] tot_loss[loss=2.308, over 5534238.58 frames. , ppl: 10.054929361659562], batch size: 70
+2022-12-11 05:18:48,983 INFO [train.py:421] (7/8) Epoch 4, batch 18400, loss[loss=2.571, over 840.00 frames. , ppl: 13.08120652079882] tot_loss[loss=2.308, over 5552536.61 frames. , ppl: 10.053217031983953], batch size: 70
+2022-12-11 05:20:26,265 INFO [train.py:421] (7/8) Epoch 4, batch 18600, loss[loss=2.455, over 1050.00 frames. , ppl: 11.64836719932776] tot_loss[loss=2.309, over 5533331.05 frames. , ppl: 10.063062448845761], batch size: 70
+2022-12-11 05:22:06,445 INFO [train.py:421] (7/8) Epoch 4, batch 18800, loss[loss=2.276, over 3500.00 frames. , ppl: 9.739907150648992] tot_loss[loss=2.308, over 5539475.52 frames. , ppl: 10.056998714261134], batch size: 70
+2022-12-11 05:23:48,712 INFO [train.py:421] (7/8) Epoch 4, batch 19000, loss[loss=2.476, over 1330.00 frames. , ppl: 11.8961588622018] tot_loss[loss=2.309, over 5533570.77 frames. , ppl: 10.061755023435225], batch size: 70
+2022-12-11 05:23:48,713 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 05:23:49,478 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.3, over 211138.00 frames. , ppl: 9.977298131379836
+2022-12-11 05:25:29,343 INFO [train.py:421] (7/8) Epoch 4, batch 19200, loss[loss=2.265, over 2870.00 frames. , ppl: 9.629931140252403] tot_loss[loss=2.309, over 5524179.26 frames. , ppl: 10.064329540085582], batch size: 70
+2022-12-11 05:27:11,515 INFO [train.py:421] (7/8) Epoch 4, batch 19400, loss[loss=2.369, over 1470.00 frames. , ppl: 10.684791927825403] tot_loss[loss=2.308, over 5572139.82 frames. , ppl: 10.050852168426792], batch size: 70
+2022-12-11 05:28:50,710 INFO [train.py:421] (7/8) Epoch 4, batch 19600, loss[loss=2.234, over 3850.00 frames. , ppl: 9.334924439419586] tot_loss[loss=2.308, over 5559067.65 frames. , ppl: 10.04970331572328], batch size: 70
+2022-12-11 05:30:32,742 INFO [train.py:421] (7/8) Epoch 4, batch 19800, loss[loss=2.21, over 5880.00 frames. , ppl: 9.112933862162423] tot_loss[loss=2.307, over 5560124.11 frames. , ppl: 10.046833501804654], batch size: 70
+2022-12-11 05:32:10,663 INFO [train.py:421] (7/8) Epoch 4, batch 20000, loss[loss=2.302, over 2520.00 frames. , ppl: 9.996221259257934] tot_loss[loss=2.308, over 5528914.73 frames. , ppl: 10.056300450169902], batch size: 70
+2022-12-11 05:32:10,664 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 05:32:11,424 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.302, over 211138.00 frames. , ppl: 9.990693533416067
+2022-12-11 05:33:50,994 INFO [train.py:421] (7/8) Epoch 4, batch 20200, loss[loss=2.248, over 3640.00 frames. , ppl: 9.465874177780655] tot_loss[loss=2.31, over 5479254.59 frames. , ppl: 10.073993056338384], batch size: 70
+2022-12-11 05:35:32,014 INFO [train.py:421] (7/8) Epoch 4, batch 20400, loss[loss=2.639, over 1120.00 frames. , ppl: 13.998973790186666] tot_loss[loss=2.309, over 5536931.90 frames. , ppl: 10.059411644589565], batch size: 70
+2022-12-11 05:37:16,460 INFO [train.py:421] (7/8) Epoch 4, batch 20600, loss[loss=2.361, over 2380.00 frames. , ppl: 10.60537937875061] tot_loss[loss=2.309, over 5495167.00 frames. , ppl: 10.069133339831598], batch size: 70
+2022-12-11 05:38:53,403 INFO [train.py:421] (7/8) Epoch 4, batch 20800, loss[loss=2.392, over 2870.00 frames. , ppl: 10.932169435509106] tot_loss[loss=2.309, over 5512167.39 frames. , ppl: 10.064999271411494], batch size: 70
+2022-12-11 05:40:32,938 INFO [train.py:421] (7/8) Epoch 4, batch 21000, loss[loss=2.54, over 910.00 frames. , ppl: 12.684082490301552] tot_loss[loss=2.308, over 5557904.61 frames. , ppl: 10.055830348793446], batch size: 70
+2022-12-11 05:40:32,938 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 05:40:33,720 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.301, over 211138.00 frames. , ppl: 9.982080879215324
+2022-12-11 05:42:16,405 INFO [train.py:421] (7/8) Epoch 4, batch 21200, loss[loss=2.828, over 630.00 frames. , ppl: 16.90924173286332] tot_loss[loss=2.307, over 5607888.74 frames. , ppl: 10.044235736003518], batch size: 70
+2022-12-11 05:43:57,357 INFO [train.py:421] (7/8) Epoch 4, batch 21400, loss[loss=2.266, over 5180.00 frames. , ppl: 9.642699824269467] tot_loss[loss=2.307, over 5588587.52 frames. , ppl: 10.047640078077055], batch size: 70
+2022-12-11 05:45:35,241 INFO [train.py:421] (7/8) Epoch 4, batch 21600, loss[loss=2.388, over 1960.00 frames. , ppl: 10.89380529416309] tot_loss[loss=2.307, over 5589796.60 frames. , ppl: 10.047264182099081], batch size: 70
+2022-12-11 05:47:14,433 INFO [train.py:421] (7/8) Epoch 4, batch 21800, loss[loss=2.442, over 1190.00 frames. , ppl: 11.491807476288475] tot_loss[loss=2.308, over 5575930.98 frames. , ppl: 10.054744636334863], batch size: 70
+2022-12-11 05:48:55,727 INFO [train.py:421] (7/8) Epoch 4, batch 22000, loss[loss=2.289, over 2030.00 frames. , ppl: 9.869073518536435] tot_loss[loss=2.307, over 5597584.53 frames. , ppl: 10.04314057605754], batch size: 70
+2022-12-11 05:48:55,728 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 05:48:56,472 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.301, over 211138.00 frames. , ppl: 9.988403293971805
+2022-12-11 05:50:35,530 INFO [train.py:421] (7/8) Epoch 4, batch 22200, loss[loss=2.423, over 1260.00 frames. , ppl: 11.28035770811315] tot_loss[loss=2.308, over 5550502.52 frames. , ppl: 10.053960526444675], batch size: 70
+2022-12-11 05:52:14,295 INFO [train.py:421] (7/8) Epoch 4, batch 22400, loss[loss=2.535, over 910.00 frames. , ppl: 12.616019261024514] tot_loss[loss=2.308, over 5539641.22 frames. , ppl: 10.056748744420817], batch size: 70
+2022-12-11 05:53:54,670 INFO [train.py:421] (7/8) Epoch 4, batch 22600, loss[loss=2.497, over 1260.00 frames. , ppl: 12.142299568494588] tot_loss[loss=2.309, over 5522464.41 frames. , ppl: 10.064971111489214], batch size: 70
+2022-12-11 05:55:36,839 INFO [train.py:421] (7/8) Epoch 4, batch 22800, loss[loss=2.557, over 1470.00 frames. , ppl: 12.894723113621726] tot_loss[loss=2.309, over 5504144.88 frames. , ppl: 10.065150130847954], batch size: 70
+2022-12-11 05:57:12,503 INFO [train.py:421] (7/8) Epoch 4, batch 23000, loss[loss=3.183, over 490.00 frames. , ppl: 24.115970141959114] tot_loss[loss=2.31, over 5490597.88 frames. , ppl: 10.071539146234574], batch size: 70
+2022-12-11 05:57:12,503 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 05:57:13,263 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.298, over 211138.00 frames. , ppl: 9.957022795141143
+2022-12-11 05:58:56,279 INFO [train.py:421] (7/8) Epoch 4, batch 23200, loss[loss=2.39, over 2800.00 frames. , ppl: 10.908240576705037] tot_loss[loss=2.309, over 5513127.92 frames. , ppl: 10.065800326881682], batch size: 70
+2022-12-11 06:00:34,257 INFO [train.py:421] (7/8) Epoch 4, batch 23400, loss[loss=2.289, over 5390.00 frames. , ppl: 9.868308618624654] tot_loss[loss=2.31, over 5483238.51 frames. , ppl: 10.072842696406283], batch size: 70
+2022-12-11 06:02:14,833 INFO [train.py:421] (7/8) Epoch 4, batch 23600, loss[loss=2.376, over 980.00 frames. , ppl: 10.765560971213805] tot_loss[loss=2.309, over 5523956.81 frames. , ppl: 10.064161869403543], batch size: 70
+2022-12-11 06:03:55,550 INFO [train.py:421] (7/8) Epoch 4, batch 23800, loss[loss=2.295, over 3850.00 frames. , ppl: 9.925203836472502] tot_loss[loss=2.309, over 5512982.46 frames. , ppl: 10.065647197993528], batch size: 70
+2022-12-11 06:05:34,129 INFO [train.py:421] (7/8) Epoch 4, batch 24000, loss[loss=2.411, over 1610.00 frames. , ppl: 11.142694040972968] tot_loss[loss=2.31, over 5498060.55 frames. , ppl: 10.07065246548771], batch size: 70
+2022-12-11 06:05:34,130 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 06:05:34,888 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.3, over 211138.00 frames. , ppl: 9.975346105661082
+2022-12-11 06:07:17,273 INFO [train.py:421] (7/8) Epoch 4, batch 24200, loss[loss=2.982, over 560.00 frames. , ppl: 19.719137621322417] tot_loss[loss=2.309, over 5492890.80 frames. , ppl: 10.066874271030803], batch size: 70
+2022-12-11 06:08:57,886 INFO [train.py:421] (7/8) Epoch 4, batch 24400, loss[loss=3.443, over 490.00 frames. , ppl: 31.295192920685643] tot_loss[loss=2.31, over 5460835.48 frames. , ppl: 10.071597558165413], batch size: 70
+2022-12-11 06:10:39,363 INFO [train.py:421] (7/8) Epoch 4, batch 24600, loss[loss=2.391, over 2380.00 frames. , ppl: 10.926125706937778] tot_loss[loss=2.309, over 5492440.38 frames. , ppl: 10.065383075716326], batch size: 70
+2022-12-11 06:12:21,103 INFO [train.py:421] (7/8) Epoch 4, batch 24800, loss[loss=2.538, over 980.00 frames. , ppl: 12.659460674409141] tot_loss[loss=2.309, over 5511595.23 frames. , ppl: 10.068705188853746], batch size: 70
+2022-12-11 06:14:01,870 INFO [train.py:421] (7/8) Epoch 4, batch 25000, loss[loss=2.385, over 2380.00 frames. , ppl: 10.86111604315361] tot_loss[loss=2.31, over 5486572.98 frames. , ppl: 10.077844309399199], batch size: 70
+2022-12-11 06:14:01,870 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 06:14:02,628 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.3, over 211138.00 frames. , ppl: 9.974898758710204
+2022-12-11 06:15:42,490 INFO [train.py:421] (7/8) Epoch 4, batch 25200, loss[loss=2.386, over 1610.00 frames. , ppl: 10.865319177084125] tot_loss[loss=2.31, over 5511161.84 frames. , ppl: 10.071483189206678], batch size: 70
+2022-12-11 06:17:23,861 INFO [train.py:421] (7/8) Epoch 4, batch 25400, loss[loss=2.365, over 2380.00 frames. , ppl: 10.643834422062188] tot_loss[loss=2.309, over 5544365.04 frames. , ppl: 10.060638022132071], batch size: 70
+2022-12-11 06:19:05,300 INFO [train.py:421] (7/8) Epoch 4, batch 25600, loss[loss=2.343, over 2100.00 frames. , ppl: 10.412343751146672] tot_loss[loss=2.307, over 5553795.44 frames. , ppl: 10.04746152573082], batch size: 70
+2022-12-11 06:20:48,747 INFO [train.py:421] (7/8) Epoch 4, batch 25800, loss[loss=2.672, over 770.00 frames. , ppl: 14.464629448977607] tot_loss[loss=2.307, over 5560788.53 frames. , ppl: 10.046298239767655], batch size: 70
+2022-12-11 06:22:27,271 INFO [train.py:421] (7/8) Epoch 4, batch 26000, loss[loss=2.428, over 1260.00 frames. , ppl: 11.340453739875446] tot_loss[loss=2.307, over 5572328.81 frames. , ppl: 10.047941465609188], batch size: 70
+2022-12-11 06:22:27,271 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 06:22:28,032 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.301, over 211138.00 frames. , ppl: 9.983234812864332
+2022-12-11 06:24:08,766 INFO [train.py:421] (7/8) Epoch 4, batch 26200, loss[loss=2.805, over 700.00 frames. , ppl: 16.534245226686288] tot_loss[loss=2.307, over 5572165.00 frames. , ppl: 10.047446986040176], batch size: 70
+2022-12-11 06:25:49,614 INFO [train.py:421] (7/8) Epoch 4, batch 26400, loss[loss=2.307, over 4550.00 frames. , ppl: 10.039396457143782] tot_loss[loss=2.306, over 5603980.17 frames. , ppl: 10.038479031616122], batch size: 70
+2022-12-11 06:27:29,120 INFO [train.py:421] (7/8) Epoch 4, batch 26600, loss[loss=2.97, over 630.00 frames. , ppl: 19.495597791979137] tot_loss[loss=2.308, over 5573474.96 frames. , ppl: 10.050376961620502], batch size: 70
+2022-12-11 06:29:04,075 INFO [train.py:421] (7/8) Epoch 4, batch 26800, loss[loss=2.385, over 2170.00 frames. , ppl: 10.860471158232874] tot_loss[loss=2.308, over 5544584.27 frames. , ppl: 10.054738463265515], batch size: 70
+2022-12-11 06:30:43,401 INFO [train.py:421] (7/8) Epoch 4, batch 27000, loss[loss=2.417, over 2030.00 frames. , ppl: 11.20702920255061] tot_loss[loss=2.308, over 5551214.63 frames. , ppl: 10.050818761682201], batch size: 70
+2022-12-11 06:30:43,402 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 06:30:44,146 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.299, over 211138.00 frames. , ppl: 9.968636532001739
+2022-12-11 06:32:23,960 INFO [train.py:421] (7/8) Epoch 4, batch 27200, loss[loss=2.31, over 2310.00 frames. , ppl: 10.075509056460671] tot_loss[loss=2.308, over 5537255.96 frames. , ppl: 10.05496895233409], batch size: 70
+2022-12-11 06:34:06,620 INFO [train.py:421] (7/8) Epoch 4, batch 27400, loss[loss=3.591, over 420.00 frames. , ppl: 36.27149574726276] tot_loss[loss=2.31, over 5500192.83 frames. , ppl: 10.069999562500666], batch size: 70
+2022-12-11 06:35:42,979 INFO [train.py:421] (7/8) Epoch 4, batch 27600, loss[loss=2.402, over 1330.00 frames. , ppl: 11.046564054631181] tot_loss[loss=2.31, over 5484579.56 frames. , ppl: 10.076365999432964], batch size: 70
+2022-12-11 06:37:23,604 INFO [train.py:421] (7/8) Epoch 4, batch 27800, loss[loss=2.352, over 2590.00 frames. , ppl: 10.508379072450264] tot_loss[loss=2.309, over 5556582.06 frames. , ppl: 10.061151119091946], batch size: 70
+2022-12-11 06:39:01,492 INFO [train.py:421] (7/8) Epoch 4, batch 28000, loss[loss=2.265, over 3570.00 frames. , ppl: 9.633134456562058] tot_loss[loss=2.309, over 5536234.57 frames. , ppl: 10.065942170581408], batch size: 70
+2022-12-11 06:39:01,493 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 06:39:02,238 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.299, over 211138.00 frames. , ppl: 9.969008347954837
+2022-12-11 06:40:41,649 INFO [train.py:421] (7/8) Epoch 4, batch 28200, loss[loss=2.272, over 4340.00 frames. , ppl: 9.69923834246593] tot_loss[loss=2.308, over 5598741.91 frames. , ppl: 10.05400374904958], batch size: 70
+2022-12-11 06:42:23,115 INFO [train.py:421] (7/8) Epoch 4, batch 28400, loss[loss=2.496, over 910.00 frames. , ppl: 12.131880400924256] tot_loss[loss=2.307, over 5588473.12 frames. , ppl: 10.047563338672513], batch size: 70
+2022-12-11 06:44:01,461 INFO [train.py:421] (7/8) Epoch 4, batch 28600, loss[loss=2.246, over 4480.00 frames. , ppl: 9.45236809697938] tot_loss[loss=2.309, over 5547361.95 frames. , ppl: 10.06469949911017], batch size: 70
+2022-12-11 06:45:43,570 INFO [train.py:421] (7/8) Epoch 4, batch 28800, loss[loss=2.238, over 3150.00 frames. , ppl: 9.37728176543636] tot_loss[loss=2.31, over 5544713.05 frames. , ppl: 10.069392808738822], batch size: 70
+2022-12-11 06:47:27,935 INFO [train.py:421] (7/8) Epoch 4, batch 29000, loss[loss=2.325, over 2170.00 frames. , ppl: 10.229416519528606] tot_loss[loss=2.308, over 5551779.92 frames. , ppl: 10.058020049727347], batch size: 70
+2022-12-11 06:47:27,936 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 06:47:28,683 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.302, over 211138.00 frames. , ppl: 9.996510942600489
+2022-12-11 06:49:06,728 INFO [train.py:421] (7/8) Epoch 4, batch 29200, loss[loss=2.282, over 2800.00 frames. , ppl: 9.799657265035288] tot_loss[loss=2.308, over 5560096.69 frames. , ppl: 10.058754086937645], batch size: 70
+2022-12-11 06:50:43,148 INFO [train.py:421] (7/8) Epoch 4, batch 29400, loss[loss=2.631, over 910.00 frames. , ppl: 13.893635047811339] tot_loss[loss=2.309, over 5536165.67 frames. , ppl: 10.059668895175419], batch size: 70
+2022-12-11 06:52:19,514 INFO [train.py:421] (7/8) Epoch 4, batch 29600, loss[loss=2.323, over 4340.00 frames. , ppl: 10.201646646019924] tot_loss[loss=2.31, over 5513043.88 frames. , ppl: 10.06971195682292], batch size: 70
+2022-12-11 06:53:56,648 INFO [train.py:421] (7/8) Epoch 4, batch 29800, loss[loss=2.349, over 2380.00 frames. , ppl: 10.475111402553996] tot_loss[loss=2.31, over 5481308.38 frames. , ppl: 10.079191031394924], batch size: 70
+2022-12-11 06:55:37,413 INFO [train.py:421] (7/8) Epoch 4, batch 30000, loss[loss=2.226, over 2800.00 frames. , ppl: 9.267269043907808] tot_loss[loss=2.31, over 5510909.25 frames. , ppl: 10.073381748022447], batch size: 70
+2022-12-11 06:55:37,413 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 06:55:38,158 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.3, over 211138.00 frames. , ppl: 9.970644798055698
+2022-12-11 06:57:17,486 INFO [train.py:421] (7/8) Epoch 4, batch 30200, loss[loss=2.271, over 2940.00 frames. , ppl: 9.690698364459111] tot_loss[loss=2.311, over 5508055.87 frames. , ppl: 10.082494258917093], batch size: 70
+2022-12-11 06:58:56,930 INFO [train.py:421] (7/8) Epoch 4, batch 30400, loss[loss=2.385, over 1890.00 frames. , ppl: 10.855104353268338] tot_loss[loss=2.311, over 5479978.24 frames. , ppl: 10.082790114889388], batch size: 70
+2022-12-11 07:00:39,367 INFO [train.py:421] (7/8) Epoch 4, batch 30600, loss[loss=2.637, over 910.00 frames. , ppl: 13.96572438772752] tot_loss[loss=2.311, over 5460616.99 frames. , ppl: 10.088680726345673], batch size: 70
+2022-12-11 07:02:17,072 INFO [train.py:421] (7/8) Epoch 4, batch 30800, loss[loss=2.255, over 3290.00 frames. , ppl: 9.538368118227599] tot_loss[loss=2.312, over 5415301.55 frames. , ppl: 10.099641746509219], batch size: 70
+2022-12-11 07:04:02,219 INFO [train.py:421] (7/8) Epoch 4, batch 31000, loss[loss=2.911, over 560.00 frames. , ppl: 18.380577853060704] tot_loss[loss=2.313, over 5432477.24 frames. , ppl: 10.100900514266199], batch size: 70
+2022-12-11 07:04:02,219 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 07:04:02,984 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.3, over 211138.00 frames. , ppl: 9.976530269338536
+2022-12-11 07:05:48,984 INFO [train.py:421] (7/8) Epoch 4, batch 31200, loss[loss=2.331, over 1750.00 frames. , ppl: 10.283109045855667] tot_loss[loss=2.311, over 5522241.26 frames. , ppl: 10.085074464938646], batch size: 70
+2022-12-11 07:07:34,382 INFO [train.py:421] (7/8) Epoch 4, batch 31400, loss[loss=2.217, over 4760.00 frames. , ppl: 9.183210423721858] tot_loss[loss=2.309, over 5567578.98 frames. , ppl: 10.068596383133045], batch size: 70
+2022-12-11 07:09:13,737 INFO [train.py:421] (7/8) Epoch 4, batch 31600, loss[loss=2.545, over 770.00 frames. , ppl: 12.737369177529509] tot_loss[loss=2.31, over 5554784.75 frames. , ppl: 10.069845218993022], batch size: 70
+2022-12-11 07:10:54,255 INFO [train.py:421] (7/8) Epoch 4, batch 31800, loss[loss=2.226, over 3080.00 frames. , ppl: 9.265619757131194] tot_loss[loss=2.309, over 5534904.73 frames. , ppl: 10.066327651393737], batch size: 70
+2022-12-11 07:12:34,103 INFO [train.py:421] (7/8) Epoch 4, batch 32000, loss[loss=2.29, over 2940.00 frames. , ppl: 9.87764118154174] tot_loss[loss=2.311, over 5467668.12 frames. , ppl: 10.083677189041666], batch size: 70
+2022-12-11 07:12:34,104 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 07:12:34,843 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.299, over 211138.00 frames. , ppl: 9.965888179968418
+2022-12-11 07:14:15,365 INFO [train.py:421] (7/8) Epoch 4, batch 32200, loss[loss=2.251, over 4130.00 frames. , ppl: 9.497948937120237] tot_loss[loss=2.311, over 5454433.25 frames. , ppl: 10.088111684990443], batch size: 70
+2022-12-11 07:15:52,081 INFO [train.py:421] (7/8) Epoch 4, batch 32400, loss[loss=2.375, over 2450.00 frames. , ppl: 10.755522289031614] tot_loss[loss=2.31, over 5476755.06 frames. , ppl: 10.078011972529202], batch size: 70
+2022-12-11 07:17:32,126 INFO [train.py:421] (7/8) Epoch 4, batch 32600, loss[loss=2.959, over 560.00 frames. , ppl: 19.274541633652515] tot_loss[loss=2.31, over 5479097.26 frames. , ppl: 10.072039164073049], batch size: 70
+2022-12-11 07:19:13,615 INFO [train.py:421] (7/8) Epoch 4, batch 32800, loss[loss=2.358, over 2450.00 frames. , ppl: 10.573897588802778] tot_loss[loss=2.31, over 5456396.15 frames. , ppl: 10.078285728968012], batch size: 70
+2022-12-11 07:20:53,531 INFO [train.py:421] (7/8) Epoch 4, batch 33000, loss[loss=2.457, over 1120.00 frames. , ppl: 11.664725166312198] tot_loss[loss=2.31, over 5474496.85 frames. , ppl: 10.075072768500497], batch size: 70
+2022-12-11 07:20:53,531 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 07:20:54,297 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.301, over 211138.00 frames. , ppl: 9.98494896820417
+2022-12-11 07:22:34,987 INFO [train.py:421] (7/8) Epoch 4, batch 33200, loss[loss=2.274, over 8820.00 frames. , ppl: 9.719213572177996] tot_loss[loss=2.31, over 5457573.48 frames. , ppl: 10.075317583689701], batch size: 70
+2022-12-11 07:24:11,944 INFO [train.py:421] (7/8) Epoch 4, batch 33400, loss[loss=2.742, over 700.00 frames. , ppl: 15.51772269854207] tot_loss[loss=2.311, over 5419505.14 frames. , ppl: 10.086498128079755], batch size: 70
+2022-12-11 07:25:47,474 INFO [train.py:421] (7/8) Epoch 4, batch 33600, loss[loss=2.294, over 2660.00 frames. , ppl: 9.91591268396991] tot_loss[loss=2.312, over 5419389.83 frames. , ppl: 10.094092286609389], batch size: 70
+2022-12-11 07:27:27,208 INFO [train.py:421] (7/8) Epoch 4, batch 33800, loss[loss=2.33, over 2170.00 frames. , ppl: 10.273139671199111] tot_loss[loss=2.311, over 5444147.22 frames. , ppl: 10.084196658786974], batch size: 70
+2022-12-11 07:29:07,736 INFO [train.py:421] (7/8) Epoch 4, batch 34000, loss[loss=2.402, over 1540.00 frames. , ppl: 11.047735606509603] tot_loss[loss=2.312, over 5446879.10 frames. , ppl: 10.089899714045849], batch size: 70
+2022-12-11 07:29:07,736 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 07:29:08,495 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.299, over 211138.00 frames. , ppl: 9.963913316067512
+2022-12-11 07:30:52,336 INFO [train.py:421] (7/8) Epoch 4, batch 34200, loss[loss=2.847, over 700.00 frames. , ppl: 17.233096538376667] tot_loss[loss=2.312, over 5463095.25 frames. , ppl: 10.08957341520902], batch size: 70
+2022-12-11 07:32:31,251 INFO [train.py:421] (7/8) Epoch 4, batch 34400, loss[loss=2.64, over 840.00 frames. , ppl: 14.007219428472206] tot_loss[loss=2.312, over 5446221.53 frames. , ppl: 10.089674694568656], batch size: 70
+2022-12-11 07:34:12,813 INFO [train.py:421] (7/8) Epoch 4, batch 34600, loss[loss=2.242, over 4830.00 frames. , ppl: 9.416326892403507] tot_loss[loss=2.312, over 5431566.52 frames. , ppl: 10.09461640995174], batch size: 70
+2022-12-11 07:35:50,516 INFO [train.py:421] (7/8) Epoch 4, batch 34800, loss[loss=3.023, over 630.00 frames. , ppl: 20.562875647640922] tot_loss[loss=2.311, over 5478434.89 frames. , ppl: 10.082112463876438], batch size: 70
+2022-12-11 07:37:31,269 INFO [train.py:421] (7/8) Epoch 4, batch 35000, loss[loss=2.383, over 1120.00 frames. , ppl: 10.842247596644382] tot_loss[loss=2.31, over 5491808.72 frames. , ppl: 10.075570242576836], batch size: 70
+2022-12-11 07:37:31,270 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 07:37:32,028 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.3, over 211138.00 frames. , ppl: 9.97713864747801
+2022-12-11 07:39:12,242 INFO [train.py:421] (7/8) Epoch 4, batch 35200, loss[loss=2.454, over 1190.00 frames. , ppl: 11.639825908592735] tot_loss[loss=2.311, over 5474544.19 frames. , ppl: 10.081996145903572], batch size: 70
+2022-12-11 07:40:54,304 INFO [train.py:421] (7/8) Epoch 4, batch 35400, loss[loss=2.247, over 3920.00 frames. , ppl: 9.46115883563884] tot_loss[loss=2.31, over 5471987.89 frames. , ppl: 10.074516274434348], batch size: 70
+2022-12-11 07:42:36,895 INFO [train.py:421] (7/8) Epoch 4, batch 35600, loss[loss=2.207, over 5390.00 frames. , ppl: 9.092774016054088] tot_loss[loss=2.31, over 5480518.27 frames. , ppl: 10.075347869922695], batch size: 70
+2022-12-11 07:44:17,400 INFO [train.py:421] (7/8) Epoch 4, batch 35800, loss[loss=2.41, over 1540.00 frames. , ppl: 11.133965734323267] tot_loss[loss=2.31, over 5473998.23 frames. , ppl: 10.072612799840368], batch size: 70
+2022-12-11 07:46:03,626 INFO [train.py:421] (7/8) Epoch 4, batch 36000, loss[loss=2.473, over 1400.00 frames. , ppl: 11.860012328074768] tot_loss[loss=2.308, over 5515856.46 frames. , ppl: 10.058059554506746], batch size: 70
+2022-12-11 07:46:03,626 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 07:46:04,385 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.299, over 211138.00 frames. , ppl: 9.962801429018057
+2022-12-11 07:47:46,401 INFO [train.py:421] (7/8) Epoch 4, batch 36200, loss[loss=2.26, over 3850.00 frames. , ppl: 9.581579774086356] tot_loss[loss=2.309, over 5519864.44 frames. , ppl: 10.065027629191762], batch size: 70
+2022-12-11 07:49:21,366 INFO [train.py:421] (7/8) Epoch 4, batch 36400, loss[loss=2.22, over 3360.00 frames. , ppl: 9.204476496355554] tot_loss[loss=2.308, over 5535108.23 frames. , ppl: 10.055562891205227], batch size: 70
+2022-12-11 07:51:00,558 INFO [train.py:421] (7/8) Epoch 4, batch 36600, loss[loss=2.218, over 6510.00 frames. , ppl: 9.186742725733806] tot_loss[loss=2.308, over 5554183.79 frames. , ppl: 10.050330568646723], batch size: 70
+2022-12-11 07:52:42,151 INFO [train.py:421] (7/8) Epoch 4, batch 36800, loss[loss=2.229, over 8540.00 frames. , ppl: 9.287792231299186] tot_loss[loss=2.31, over 5483636.65 frames. , ppl: 10.069606750083631], batch size: 70
+2022-12-11 07:54:20,223 INFO [train.py:421] (7/8) Epoch 4, batch 37000, loss[loss=2.349, over 2870.00 frames. , ppl: 10.476352593585755] tot_loss[loss=2.311, over 5460259.01 frames. , ppl: 10.080844064422447], batch size: 70
+2022-12-11 07:54:20,224 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 07:54:20,987 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.297, over 211138.00 frames. , ppl: 9.946271967014194
+2022-12-11 07:56:00,678 INFO [train.py:421] (7/8) Epoch 4, batch 37200, loss[loss=2.408, over 910.00 frames. , ppl: 11.115744059736514] tot_loss[loss=2.31, over 5461486.59 frames. , ppl: 10.0748217085699], batch size: 70
+2022-12-11 07:57:39,427 INFO [train.py:421] (7/8) Epoch 4, batch 37400, loss[loss=2.383, over 2380.00 frames. , ppl: 10.835374441263118] tot_loss[loss=2.311, over 5431643.32 frames. , ppl: 10.08009802688017], batch size: 70
+2022-12-11 07:59:17,911 INFO [train.py:421] (7/8) Epoch 4, batch 37600, loss[loss=2.659, over 700.00 frames. , ppl: 14.282431828987336] tot_loss[loss=2.31, over 5440227.21 frames. , ppl: 10.076244074578465], batch size: 70
+2022-12-11 08:00:55,524 INFO [train.py:421] (7/8) Epoch 4, batch 37800, loss[loss=2.375, over 1330.00 frames. , ppl: 10.74673153724302] tot_loss[loss=2.311, over 5426368.05 frames. , ppl: 10.08555818227603], batch size: 70
+2022-12-11 08:02:37,239 INFO [train.py:421] (7/8) Epoch 4, batch 38000, loss[loss=2.245, over 2800.00 frames. , ppl: 9.441442889717433] tot_loss[loss=2.31, over 5437840.24 frames. , ppl: 10.072098444401071], batch size: 70
+2022-12-11 08:02:37,240 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 08:02:37,986 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.297, over 211138.00 frames. , ppl: 9.945532988975891
+2022-12-11 08:04:17,128 INFO [train.py:421] (7/8) Epoch 4, batch 38200, loss[loss=2.189, over 4130.00 frames. , ppl: 8.930653202545846] tot_loss[loss=2.311, over 5440897.53 frames. , ppl: 10.0821060767005], batch size: 70
+2022-12-11 08:05:57,530 INFO [train.py:421] (7/8) Epoch 4, batch 38400, loss[loss=2.864, over 630.00 frames. , ppl: 17.523880148136527] tot_loss[loss=2.311, over 5454073.49 frames. , ppl: 10.079570337559685], batch size: 70
+2022-12-11 08:07:37,179 INFO [train.py:421] (7/8) Epoch 4, batch 38600, loss[loss=3.24, over 490.00 frames. , ppl: 25.536201400974218] tot_loss[loss=2.309, over 5484517.99 frames. , ppl: 10.068448293787021], batch size: 70
+2022-12-11 08:09:17,865 INFO [train.py:421] (7/8) Epoch 4, batch 38800, loss[loss=2.828, over 770.00 frames. , ppl: 16.90554698097859] tot_loss[loss=2.309, over 5481909.08 frames. , ppl: 10.06519736964234], batch size: 70
+2022-12-11 08:10:56,273 INFO [train.py:421] (7/8) Epoch 4, batch 39000, loss[loss=2.269, over 4900.00 frames. , ppl: 9.669201306764718] tot_loss[loss=2.308, over 5522710.52 frames. , ppl: 10.053421428921467], batch size: 70
+2022-12-11 08:10:56,273 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 08:10:57,005 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.298, over 211138.00 frames. , ppl: 9.949938227560008
+2022-12-11 08:12:35,872 INFO [train.py:421] (7/8) Epoch 4, batch 39200, loss[loss=2.293, over 2870.00 frames. , ppl: 9.903657164897] tot_loss[loss=2.309, over 5502232.13 frames. , ppl: 10.06345271798973], batch size: 70
+2022-12-11 08:14:16,247 INFO [train.py:421] (7/8) Epoch 4, batch 39400, loss[loss=2.22, over 3080.00 frames. , ppl: 9.205871608846904] tot_loss[loss=2.309, over 5503963.23 frames. , ppl: 10.066601918326509], batch size: 70
+2022-12-11 08:15:56,341 INFO [train.py:421] (7/8) Epoch 4, batch 39600, loss[loss=2.48, over 1120.00 frames. , ppl: 11.939568430620936] tot_loss[loss=2.308, over 5567518.54 frames. , ppl: 10.056699459814922], batch size: 70
+2022-12-11 08:17:35,781 INFO [train.py:421] (7/8) Epoch 4, batch 39800, loss[loss=2.605, over 980.00 frames. , ppl: 13.533300612920966] tot_loss[loss=2.309, over 5536422.18 frames. , ppl: 10.06392110214063], batch size: 70
+2022-12-11 08:19:17,014 INFO [train.py:421] (7/8) Epoch 4, batch 40000, loss[loss=2.234, over 4410.00 frames. , ppl: 9.339152984317055] tot_loss[loss=2.309, over 5553985.56 frames. , ppl: 10.06306635055042], batch size: 70
+2022-12-11 08:19:17,014 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 08:19:17,760 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.296, over 211138.00 frames. , ppl: 9.93333160275137
+2022-12-11 08:20:58,979 INFO [train.py:421] (7/8) Epoch 4, batch 40200, loss[loss=2.538, over 1120.00 frames. , ppl: 12.653289474626424] tot_loss[loss=2.308, over 5565460.38 frames. , ppl: 10.05820042666496], batch size: 70
+2022-12-11 08:22:39,535 INFO [train.py:421] (7/8) Epoch 4, batch 40400, loss[loss=2.332, over 2520.00 frames. , ppl: 10.301466269020048] tot_loss[loss=2.309, over 5552251.00 frames. , ppl: 10.05945335751474], batch size: 70
+2022-12-11 08:24:20,707 INFO [train.py:421] (7/8) Epoch 4, batch 40600, loss[loss=2.208, over 4620.00 frames. , ppl: 9.093800149935346] tot_loss[loss=2.309, over 5564878.04 frames. , ppl: 10.061835757886426], batch size: 70
+2022-12-11 08:26:03,850 INFO [train.py:421] (7/8) Epoch 4, batch 40800, loss[loss=2.283, over 4270.00 frames. , ppl: 9.807766159578184] tot_loss[loss=2.308, over 5557649.49 frames. , ppl: 10.056268473635628], batch size: 70
+2022-12-11 08:27:44,151 INFO [train.py:421] (7/8) Epoch 4, batch 41000, loss[loss=2.288, over 2240.00 frames. , ppl: 9.85669906670683] tot_loss[loss=2.308, over 5564966.00 frames. , ppl: 10.051517340946242], batch size: 70
+2022-12-11 08:27:44,151 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 08:27:44,908 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.296, over 211138.00 frames. , ppl: 9.931032464771791
+2022-12-11 08:29:23,728 INFO [train.py:421] (7/8) Epoch 4, batch 41200, loss[loss=2.313, over 3640.00 frames. , ppl: 10.106079568215451] tot_loss[loss=2.308, over 5596976.23 frames. , ppl: 10.049353765227659], batch size: 70
+2022-12-11 08:31:02,542 INFO [train.py:421] (7/8) Epoch 4, batch 41400, loss[loss=3.261, over 490.00 frames. , ppl: 26.082792589695675] tot_loss[loss=2.306, over 5645366.30 frames. , ppl: 10.03441661693861], batch size: 70
+2022-12-11 08:32:46,788 INFO [train.py:421] (7/8) Epoch 4, batch 41600, loss[loss=2.347, over 2520.00 frames. , ppl: 10.458706397020604] tot_loss[loss=2.306, over 5616375.27 frames. , ppl: 10.038719898109992], batch size: 70
+2022-12-11 08:34:26,739 INFO [train.py:421] (7/8) Epoch 4, batch 41800, loss[loss=2.415, over 1260.00 frames. , ppl: 11.186964247340581] tot_loss[loss=2.306, over 5644454.44 frames. , ppl: 10.031776335779915], batch size: 70
+2022-12-11 08:36:06,526 INFO [train.py:421] (7/8) Epoch 4, batch 42000, loss[loss=2.38, over 3010.00 frames. , ppl: 10.804283453499036] tot_loss[loss=2.306, over 5632202.67 frames. , ppl: 10.036677034845122], batch size: 70
+2022-12-11 08:36:06,526 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 08:36:07,272 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.298, over 211138.00 frames. , ppl: 9.952867789688982
+2022-12-11 08:37:48,693 INFO [train.py:421] (7/8) Epoch 4, batch 42200, loss[loss=3.08, over 560.00 frames. , ppl: 21.760766413543426] tot_loss[loss=2.305, over 5658126.09 frames. , ppl: 10.028505367161605], batch size: 70
+2022-12-11 08:39:25,696 INFO [train.py:421] (7/8) Epoch 4, batch 42400, loss[loss=2.384, over 2030.00 frames. , ppl: 10.852520634349807] tot_loss[loss=2.307, over 5599031.62 frames. , ppl: 10.041841643515866], batch size: 70
+2022-12-11 08:41:06,768 INFO [train.py:421] (7/8) Epoch 4, batch 42600, loss[loss=4.268, over 350.00 frames. , ppl: 71.40000869122909] tot_loss[loss=2.307, over 5573490.42 frames. , ppl: 10.044914563402028], batch size: 70
+2022-12-11 08:42:47,991 INFO [train.py:421] (7/8) Epoch 4, batch 42800, loss[loss=2.349, over 1610.00 frames. , ppl: 10.476724922133696] tot_loss[loss=2.307, over 5545267.45 frames. , ppl: 10.045910938269602], batch size: 70
+2022-12-11 08:44:22,385 INFO [train.py:421] (7/8) Epoch 4, batch 43000, loss[loss=2.426, over 1330.00 frames. , ppl: 11.313035400880349] tot_loss[loss=2.308, over 5515162.90 frames. , ppl: 10.056140941420775], batch size: 70
+2022-12-11 08:44:22,385 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 08:44:23,129 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.296, over 211138.00 frames. , ppl: 9.932262819602796
+2022-12-11 08:46:01,986 INFO [train.py:421] (7/8) Epoch 4, batch 43200, loss[loss=2.362, over 3500.00 frames. , ppl: 10.609957731160986] tot_loss[loss=2.309, over 5458738.32 frames. , ppl: 10.065654813861153], batch size: 70
+2022-12-11 08:47:41,483 INFO [train.py:421] (7/8) Epoch 4, batch 43400, loss[loss=2.419, over 1330.00 frames. , ppl: 11.238470170580294] tot_loss[loss=2.309, over 5451224.16 frames. , ppl: 10.064259649389847], batch size: 70
+2022-12-11 08:49:23,893 INFO [train.py:421] (7/8) Epoch 4, batch 43600, loss[loss=3.194, over 490.00 frames. , ppl: 24.377833751090126] tot_loss[loss=2.309, over 5445776.03 frames. , ppl: 10.061435511042484], batch size: 70
+2022-12-11 08:51:04,766 INFO [train.py:421] (7/8) Epoch 4, batch 43800, loss[loss=2.335, over 2450.00 frames. , ppl: 10.328657088805015] tot_loss[loss=2.308, over 5481907.48 frames. , ppl: 10.049965403156047], batch size: 70
+2022-12-11 08:52:41,191 INFO [train.py:421] (7/8) Epoch 4, batch 44000, loss[loss=2.18, over 3290.00 frames. , ppl: 8.846868728753332] tot_loss[loss=2.308, over 5464203.64 frames. , ppl: 10.053500901279344], batch size: 70
+2022-12-11 08:52:41,191 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 08:52:41,937 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.296, over 211138.00 frames. , ppl: 9.938447770769514
+2022-12-11 08:54:20,561 INFO [train.py:421] (7/8) Epoch 4, batch 44200, loss[loss=2.485, over 1330.00 frames. , ppl: 12.004912619970153] tot_loss[loss=2.308, over 5444736.23 frames. , ppl: 10.059200540096912], batch size: 70
+2022-12-11 08:55:59,767 INFO [train.py:421] (7/8) Epoch 4, batch 44400, loss[loss=2.198, over 11060.00 frames. , ppl: 9.002938285544124] tot_loss[loss=2.309, over 5438538.86 frames. , ppl: 10.063508599888566], batch size: 70
+2022-12-11 08:57:40,778 INFO [train.py:421] (7/8) Epoch 4, batch 44600, loss[loss=2.459, over 1750.00 frames. , ppl: 11.69322677000643] tot_loss[loss=2.31, over 5408102.04 frames. , ppl: 10.071950842108604], batch size: 70
+2022-12-11 08:59:24,321 INFO [train.py:421] (7/8) Epoch 4, batch 44800, loss[loss=2.348, over 1960.00 frames. , ppl: 10.468424232412378] tot_loss[loss=2.309, over 5431370.89 frames. , ppl: 10.064225628891341], batch size: 70
+2022-12-11 09:01:09,957 INFO [train.py:421] (7/8) Epoch 4, batch 45000, loss[loss=2.236, over 12250.00 frames. , ppl: 9.360037514766923] tot_loss[loss=2.308, over 5481149.08 frames. , ppl: 10.051274251405221], batch size: 70
+2022-12-11 09:01:09,958 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 09:01:10,691 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.293, over 211138.00 frames. , ppl: 9.909560376874897
+2022-12-11 09:02:55,712 INFO [train.py:421] (7/8) Epoch 4, batch 45200, loss[loss=2.188, over 3360.00 frames. , ppl: 8.915318929515033] tot_loss[loss=2.308, over 5493564.47 frames. , ppl: 10.054364939088298], batch size: 70
+2022-12-11 09:04:33,451 INFO [train.py:421] (7/8) Epoch 4, batch 45400, loss[loss=2.37, over 1890.00 frames. , ppl: 10.69649302373119] tot_loss[loss=2.308, over 5479069.38 frames. , ppl: 10.056631653723015], batch size: 70
+2022-12-11 09:06:16,159 INFO [train.py:421] (7/8) Epoch 4, batch 45600, loss[loss=2.222, over 3570.00 frames. , ppl: 9.221595879120617] tot_loss[loss=2.308, over 5492620.43 frames. , ppl: 10.051862859477936], batch size: 70
+2022-12-11 09:07:57,232 INFO [train.py:421] (7/8) Epoch 4, batch 45800, loss[loss=2.317, over 2310.00 frames. , ppl: 10.148832918759435] tot_loss[loss=2.308, over 5473886.68 frames. , ppl: 10.054471241437405], batch size: 70
+2022-12-11 09:09:38,446 INFO [train.py:421] (7/8) Epoch 4, batch 46000, loss[loss=2.356, over 1540.00 frames. , ppl: 10.547973191517562] tot_loss[loss=2.308, over 5449640.58 frames. , ppl: 10.055353022441052], batch size: 70
+2022-12-11 09:09:38,446 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 09:09:39,192 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.295, over 211138.00 frames. , ppl: 9.921327269150712
+2022-12-11 09:11:18,480 INFO [train.py:421] (7/8) Epoch 4, batch 46200, loss[loss=2.484, over 1050.00 frames. , ppl: 11.984208169546363] tot_loss[loss=2.308, over 5441048.73 frames. , ppl: 10.058985739280754], batch size: 70
+2022-12-11 09:12:54,786 INFO [train.py:421] (7/8) Epoch 4, batch 46400, loss[loss=4.807, over 280.00 frames. , ppl: 122.34208724365234] tot_loss[loss=2.309, over 5407792.75 frames. , ppl: 10.069141488392745], batch size: 70
+2022-12-11 09:14:38,861 INFO [train.py:421] (7/8) Epoch 4, batch 46600, loss[loss=2.983, over 560.00 frames. , ppl: 19.750597114577968] tot_loss[loss=2.309, over 5437037.18 frames. , ppl: 10.066977740112177], batch size: 70
+2022-12-11 09:16:20,822 INFO [train.py:421] (7/8) Epoch 4, batch 46800, loss[loss=2.229, over 5180.00 frames. , ppl: 9.289579069503798] tot_loss[loss=2.309, over 5439097.08 frames. , ppl: 10.061649136277442], batch size: 70
+2022-12-11 09:18:01,884 INFO [train.py:421] (7/8) Epoch 4, batch 47000, loss[loss=2.465, over 1960.00 frames. , ppl: 11.768989367417463] tot_loss[loss=2.308, over 5475579.04 frames. , ppl: 10.057643495362138], batch size: 70
+2022-12-11 09:18:01,884 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 09:18:02,643 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.912724529894838
+2022-12-11 09:19:43,177 INFO [train.py:421] (7/8) Epoch 4, batch 47200, loss[loss=2.303, over 3010.00 frames. , ppl: 10.007919854110757] tot_loss[loss=2.311, over 5408008.72 frames. , ppl: 10.080137271032289], batch size: 70
+2022-12-11 09:21:18,454 INFO [train.py:421] (7/8) Epoch 4, batch 47400, loss[loss=3.155, over 490.00 frames. , ppl: 23.443057558525513] tot_loss[loss=2.311, over 5381527.42 frames. , ppl: 10.088612030504784], batch size: 70
+2022-12-11 09:22:56,913 INFO [train.py:421] (7/8) Epoch 4, batch 47600, loss[loss=2.712, over 700.00 frames. , ppl: 15.054745989468236] tot_loss[loss=2.31, over 5415653.69 frames. , ppl: 10.076382994036281], batch size: 70
+2022-12-11 09:24:37,052 INFO [train.py:421] (7/8) Epoch 4, batch 47800, loss[loss=2.354, over 1820.00 frames. , ppl: 10.522867755763073] tot_loss[loss=2.31, over 5410036.21 frames. , ppl: 10.073673936205365], batch size: 70
+2022-12-11 09:26:19,533 INFO [train.py:421] (7/8) Epoch 4, batch 48000, loss[loss=3.291, over 490.00 frames. , ppl: 26.87838802753127] tot_loss[loss=2.309, over 5429123.68 frames. , ppl: 10.069171191710124], batch size: 70
+2022-12-11 09:26:19,533 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 09:26:20,321 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.295, over 211138.00 frames. , ppl: 9.92101743515498
+2022-12-11 09:28:03,644 INFO [train.py:421] (7/8) Epoch 4, batch 48200, loss[loss=3.037, over 560.00 frames. , ppl: 20.84179352479672] tot_loss[loss=2.31, over 5435475.13 frames. , ppl: 10.076083979350445], batch size: 70
+2022-12-11 09:29:44,758 INFO [train.py:421] (7/8) Epoch 4, batch 48400, loss[loss=2.497, over 1120.00 frames. , ppl: 12.142693655676496] tot_loss[loss=2.311, over 5410600.47 frames. , ppl: 10.083196666512626], batch size: 70
+2022-12-11 09:31:30,700 INFO [train.py:421] (7/8) Epoch 4, batch 48600, loss[loss=2.327, over 1890.00 frames. , ppl: 10.250796150054363] tot_loss[loss=2.311, over 5411551.58 frames. , ppl: 10.082572192008023], batch size: 70
+2022-12-11 09:33:10,104 INFO [train.py:421] (7/8) Epoch 4, batch 48800, loss[loss=2.407, over 1960.00 frames. , ppl: 11.103843776014868] tot_loss[loss=2.311, over 5389997.57 frames. , ppl: 10.083036276811287], batch size: 70
+2022-12-11 09:34:51,409 INFO [train.py:421] (7/8) Epoch 4, batch 49000, loss[loss=2.251, over 5250.00 frames. , ppl: 9.500477646227715] tot_loss[loss=2.312, over 5356521.11 frames. , ppl: 10.093908413521541], batch size: 70
+2022-12-11 09:34:51,409 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 09:34:52,168 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.912736267159561
+2022-12-11 09:36:32,397 INFO [train.py:421] (7/8) Epoch 4, batch 49200, loss[loss=2.213, over 3080.00 frames. , ppl: 9.146502938666732] tot_loss[loss=2.311, over 5394808.55 frames. , ppl: 10.080655925191547], batch size: 70
+2022-12-11 09:38:12,919 INFO [train.py:421] (7/8) Epoch 4, batch 49400, loss[loss=2.584, over 1050.00 frames. , ppl: 13.255800382446619] tot_loss[loss=2.309, over 5420466.78 frames. , ppl: 10.065668639068905], batch size: 70
+2022-12-11 09:39:55,521 INFO [train.py:421] (7/8) Epoch 4, batch 49600, loss[loss=2.391, over 2100.00 frames. , ppl: 10.920794376783109] tot_loss[loss=2.307, over 5447361.40 frames. , ppl: 10.044249699138668], batch size: 70
+2022-12-11 09:41:35,001 INFO [train.py:421] (7/8) Epoch 4, batch 49800, loss[loss=2.324, over 4060.00 frames. , ppl: 10.219234370851286] tot_loss[loss=2.307, over 5459886.14 frames. , ppl: 10.043959188556624], batch size: 70
+2022-12-11 09:43:18,274 INFO [train.py:421] (7/8) Epoch 4, batch 50000, loss[loss=2.836, over 630.00 frames. , ppl: 17.051652712503618] tot_loss[loss=2.307, over 5452269.86 frames. , ppl: 10.039280151446237], batch size: 70
+2022-12-11 09:43:18,274 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 09:43:19,051 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.911439383482614
+2022-12-11 09:44:57,856 INFO [train.py:421] (7/8) Epoch 4, batch 50200, loss[loss=2.287, over 3850.00 frames. , ppl: 9.841914585145716] tot_loss[loss=2.306, over 5475222.16 frames. , ppl: 10.032270846269698], batch size: 70
+2022-12-11 09:46:40,422 INFO [train.py:421] (7/8) Epoch 4, batch 50400, loss[loss=2.299, over 2870.00 frames. , ppl: 9.961102571377587] tot_loss[loss=2.305, over 5514290.27 frames. , ppl: 10.026623128406165], batch size: 70
+2022-12-11 09:48:16,334 INFO [train.py:421] (7/8) Epoch 4, batch 50600, loss[loss=2.495, over 1260.00 frames. , ppl: 12.11762580540007] tot_loss[loss=2.305, over 5515617.40 frames. , ppl: 10.023614686174103], batch size: 70
+2022-12-11 09:49:58,424 INFO [train.py:421] (7/8) Epoch 4, batch 50800, loss[loss=2.439, over 1330.00 frames. , ppl: 11.465134860509643] tot_loss[loss=2.305, over 5516614.04 frames. , ppl: 10.021808339122588], batch size: 70
+2022-12-11 09:51:36,250 INFO [train.py:421] (7/8) Epoch 4, batch 51000, loss[loss=2.298, over 3010.00 frames. , ppl: 9.951052374679387] tot_loss[loss=2.306, over 5481325.09 frames. , ppl: 10.03683428056506], batch size: 70
+2022-12-11 09:51:36,251 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 09:51:36,999 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.293, over 211138.00 frames. , ppl: 9.909437175772835
+2022-12-11 09:53:14,569 INFO [train.py:421] (7/8) Epoch 4, batch 51200, loss[loss=2.905, over 560.00 frames. , ppl: 18.267869246713847] tot_loss[loss=2.306, over 5487441.07 frames. , ppl: 10.03580950545442], batch size: 70
+2022-12-11 09:54:54,290 INFO [train.py:421] (7/8) Epoch 4, batch 51400, loss[loss=2.427, over 2240.00 frames. , ppl: 11.326194471501568] tot_loss[loss=2.307, over 5457786.51 frames. , ppl: 10.04598469498515], batch size: 70
+2022-12-11 09:56:32,680 INFO [train.py:421] (7/8) Epoch 4, batch 51600, loss[loss=2.506, over 2240.00 frames. , ppl: 12.255706809361726] tot_loss[loss=2.307, over 5473413.74 frames. , ppl: 10.047061312322585], batch size: 70
+2022-12-11 09:58:13,023 INFO [train.py:421] (7/8) Epoch 4, batch 51800, loss[loss=2.759, over 700.00 frames. , ppl: 15.779348747403041] tot_loss[loss=2.307, over 5467527.26 frames. , ppl: 10.043861540459224], batch size: 70
+2022-12-11 09:59:53,318 INFO [train.py:421] (7/8) Epoch 4, batch 52000, loss[loss=2.345, over 4620.00 frames. , ppl: 10.436692471207028] tot_loss[loss=2.306, over 5507394.22 frames. , ppl: 10.030595572755283], batch size: 70
+2022-12-11 09:59:53,318 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 09:59:54,080 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.914090547381605
+2022-12-11 10:01:33,676 INFO [train.py:421] (7/8) Epoch 4, batch 52200, loss[loss=6.104, over 210.00 frames. , ppl: 447.7693579354079] tot_loss[loss=2.306, over 5481871.97 frames. , ppl: 10.037095696404394], batch size: 70
+2022-12-11 10:03:14,832 INFO [train.py:421] (7/8) Epoch 4, batch 52400, loss[loss=2.39, over 1540.00 frames. , ppl: 10.911179943029245] tot_loss[loss=2.308, over 5464681.20 frames. , ppl: 10.050522725167957], batch size: 70
+2022-12-11 10:04:57,998 INFO [train.py:421] (7/8) Epoch 4, batch 52600, loss[loss=2.243, over 3290.00 frames. , ppl: 9.423530197292504] tot_loss[loss=2.307, over 5488914.05 frames. , ppl: 10.040475835337448], batch size: 70
+2022-12-11 10:06:38,657 INFO [train.py:421] (7/8) Epoch 4, batch 52800, loss[loss=2.324, over 3500.00 frames. , ppl: 10.214896522009235] tot_loss[loss=2.308, over 5436439.70 frames. , ppl: 10.055483616027994], batch size: 70
+2022-12-11 10:08:18,150 INFO [train.py:421] (7/8) Epoch 4, batch 53000, loss[loss=2.206, over 3920.00 frames. , ppl: 9.079583127153446] tot_loss[loss=2.307, over 5465115.96 frames. , ppl: 10.046277608364576], batch size: 70
+2022-12-11 10:08:18,151 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 10:08:18,896 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.296, over 211138.00 frames. , ppl: 9.929699384943623
+2022-12-11 10:09:58,044 INFO [train.py:421] (7/8) Epoch 4, batch 53200, loss[loss=2.812, over 630.00 frames. , ppl: 16.6451691291239] tot_loss[loss=2.307, over 5462121.23 frames. , ppl: 10.043084290179417], batch size: 70
+2022-12-11 10:11:38,308 INFO [train.py:421] (7/8) Epoch 4, batch 53400, loss[loss=2.502, over 1190.00 frames. , ppl: 12.200853103218838] tot_loss[loss=2.306, over 5473320.47 frames. , ppl: 10.038798796230415], batch size: 70
+2022-12-11 10:13:16,458 INFO [train.py:421] (7/8) Epoch 4, batch 53600, loss[loss=2.193, over 5460.00 frames. , ppl: 8.96558178616233] tot_loss[loss=2.306, over 5496419.94 frames. , ppl: 10.033598940276242], batch size: 70
+2022-12-11 10:14:54,533 INFO [train.py:421] (7/8) Epoch 4, batch 53800, loss[loss=2.379, over 1540.00 frames. , ppl: 10.791373694630053] tot_loss[loss=2.306, over 5497373.16 frames. , ppl: 10.034560144340952], batch size: 70
+2022-12-11 10:16:36,544 INFO [train.py:421] (7/8) Epoch 4, batch 54000, loss[loss=2.331, over 3080.00 frames. , ppl: 10.29136148307733] tot_loss[loss=2.306, over 5464283.99 frames. , ppl: 10.035989015274742], batch size: 70
+2022-12-11 10:16:36,544 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 10:16:37,305 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.293, over 211138.00 frames. , ppl: 9.903191128032574
+2022-12-11 10:18:18,582 INFO [train.py:421] (7/8) Epoch 4, batch 54200, loss[loss=2.137, over 8470.00 frames. , ppl: 8.475693973401075] tot_loss[loss=2.306, over 5465344.03 frames. , ppl: 10.036729925983348], batch size: 70
+2022-12-11 10:19:56,517 INFO [train.py:421] (7/8) Epoch 4, batch 54400, loss[loss=2.431, over 1540.00 frames. , ppl: 11.369284046159196] tot_loss[loss=2.307, over 5462140.12 frames. , ppl: 10.040775290009261], batch size: 70
+2022-12-11 10:21:35,664 INFO [train.py:421] (7/8) Epoch 4, batch 54600, loss[loss=2.352, over 3640.00 frames. , ppl: 10.50749569215517] tot_loss[loss=2.306, over 5505979.42 frames. , ppl: 10.034546424242595], batch size: 70
+2022-12-11 10:23:17,362 INFO [train.py:421] (7/8) Epoch 4, batch 54800, loss[loss=2.246, over 5880.00 frames. , ppl: 9.450329155535167] tot_loss[loss=2.305, over 5528582.12 frames. , ppl: 10.026529885316151], batch size: 70
+2022-12-11 10:24:58,185 INFO [train.py:421] (7/8) Epoch 4, batch 55000, loss[loss=2.345, over 3220.00 frames. , ppl: 10.435612603711883] tot_loss[loss=2.305, over 5560854.23 frames. , ppl: 10.020642687110021], batch size: 70
+2022-12-11 10:24:58,186 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 10:24:58,943 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.91692148777633
+2022-12-11 10:26:38,691 INFO [train.py:421] (7/8) Epoch 4, batch 55200, loss[loss=2.833, over 770.00 frames. , ppl: 16.99879141640997] tot_loss[loss=2.305, over 5574232.08 frames. , ppl: 10.020966701947952], batch size: 70
+2022-12-11 10:28:18,395 INFO [train.py:421] (7/8) Epoch 4, batch 55400, loss[loss=2.623, over 910.00 frames. , ppl: 13.77501427939613] tot_loss[loss=2.306, over 5538155.69 frames. , ppl: 10.029202185695475], batch size: 70
+2022-12-11 10:29:59,490 INFO [train.py:421] (7/8) Epoch 4, batch 55600, loss[loss=2.941, over 630.00 frames. , ppl: 18.938090896121366] tot_loss[loss=2.305, over 5527719.89 frames. , ppl: 10.026792556661341], batch size: 70
+2022-12-11 10:31:38,227 INFO [train.py:421] (7/8) Epoch 4, batch 55800, loss[loss=2.237, over 2870.00 frames. , ppl: 9.369233285042831] tot_loss[loss=2.305, over 5533155.48 frames. , ppl: 10.021485681687878], batch size: 70
+2022-12-11 10:33:18,378 INFO [train.py:421] (7/8) Epoch 4, batch 56000, loss[loss=2.473, over 1190.00 frames. , ppl: 11.8585330332964] tot_loss[loss=2.306, over 5507697.77 frames. , ppl: 10.031324596049663], batch size: 70
+2022-12-11 10:33:18,379 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 10:33:19,123 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.91445299177917
+2022-12-11 10:34:53,563 INFO [train.py:421] (7/8) Epoch 4, batch 56200, loss[loss=2.224, over 4130.00 frames. , ppl: 9.244828779713172] tot_loss[loss=2.306, over 5496268.56 frames. , ppl: 10.031138208597401], batch size: 70
+2022-12-11 10:36:32,169 INFO [train.py:421] (7/8) Epoch 4, batch 56400, loss[loss=2.263, over 2800.00 frames. , ppl: 9.60806536399533] tot_loss[loss=2.307, over 5467702.51 frames. , ppl: 10.044322516367476], batch size: 70
+2022-12-11 10:38:13,265 INFO [train.py:421] (7/8) Epoch 4, batch 56600, loss[loss=2.494, over 1330.00 frames. , ppl: 12.108244350853687] tot_loss[loss=2.308, over 5440262.08 frames. , ppl: 10.054083096863822], batch size: 70
+2022-12-11 10:39:51,830 INFO [train.py:421] (7/8) Epoch 4, batch 56800, loss[loss=2.206, over 9520.00 frames. , ppl: 9.078567442647428] tot_loss[loss=2.308, over 5443647.71 frames. , ppl: 10.056438537079224], batch size: 70
+2022-12-11 10:41:31,981 INFO [train.py:421] (7/8) Epoch 4, batch 57000, loss[loss=2.426, over 1260.00 frames. , ppl: 11.316128793435153] tot_loss[loss=2.309, over 5419470.09 frames. , ppl: 10.060029513981902], batch size: 70
+2022-12-11 10:41:31,982 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 10:41:32,726 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.293, over 211138.00 frames. , ppl: 9.90575504999001
+2022-12-11 10:43:12,835 INFO [train.py:421] (7/8) Epoch 4, batch 57200, loss[loss=2.265, over 4620.00 frames. , ppl: 9.63128909513958] tot_loss[loss=2.308, over 5443125.78 frames. , ppl: 10.051133062455968], batch size: 70
+2022-12-11 10:44:55,984 INFO [train.py:421] (7/8) Epoch 4, batch 57400, loss[loss=2.246, over 7980.00 frames. , ppl: 9.4522502904251] tot_loss[loss=2.307, over 5490053.46 frames. , ppl: 10.04252757254639], batch size: 70
+2022-12-11 10:46:33,849 INFO [train.py:421] (7/8) Epoch 4, batch 57600, loss[loss=2.13, over 7490.00 frames. , ppl: 8.414578485715227] tot_loss[loss=2.306, over 5511186.83 frames. , ppl: 10.03787383670496], batch size: 70
+2022-12-11 10:48:10,535 INFO [train.py:421] (7/8) Epoch 4, batch 57800, loss[loss=2.197, over 4410.00 frames. , ppl: 8.999626053452092] tot_loss[loss=2.306, over 5563555.08 frames. , ppl: 10.029303425916583], batch size: 70
+2022-12-11 10:49:55,350 INFO [train.py:421] (7/8) Epoch 4, batch 58000, loss[loss=2.385, over 1960.00 frames. , ppl: 10.863498005142377] tot_loss[loss=2.304, over 5620375.01 frames. , ppl: 10.016559596093758], batch size: 70
+2022-12-11 10:49:55,350 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 10:49:56,110 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.915101609561932
+2022-12-11 10:51:34,571 INFO [train.py:421] (7/8) Epoch 4, batch 58200, loss[loss=2.714, over 700.00 frames. , ppl: 15.089003580737389] tot_loss[loss=2.306, over 5575420.37 frames. , ppl: 10.032781895746155], batch size: 70
+2022-12-11 10:53:13,740 INFO [train.py:421] (7/8) Epoch 4, batch 58400, loss[loss=2.295, over 3500.00 frames. , ppl: 9.924964923498774] tot_loss[loss=2.307, over 5546516.13 frames. , ppl: 10.042976970963549], batch size: 70
+2022-12-11 10:54:51,410 INFO [train.py:421] (7/8) Epoch 4, batch 58600, loss[loss=2.24, over 3850.00 frames. , ppl: 9.388819645653125] tot_loss[loss=2.307, over 5522482.24 frames. , ppl: 10.046923564751065], batch size: 70
+2022-12-11 10:56:31,628 INFO [train.py:421] (7/8) Epoch 4, batch 58800, loss[loss=2.256, over 2660.00 frames. , ppl: 9.549205701752056] tot_loss[loss=2.307, over 5521527.74 frames. , ppl: 10.046432295810474], batch size: 70
+2022-12-11 10:58:12,949 INFO [train.py:421] (7/8) Epoch 4, batch 59000, loss[loss=2.199, over 8960.00 frames. , ppl: 9.020261761673503] tot_loss[loss=2.308, over 5476251.77 frames. , ppl: 10.056408596690309], batch size: 70
+2022-12-11 10:58:12,949 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 10:58:13,677 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.911222274742915
+2022-12-11 10:59:52,992 INFO [train.py:421] (7/8) Epoch 4, batch 59200, loss[loss=2.213, over 5740.00 frames. , ppl: 9.14266147182882] tot_loss[loss=2.308, over 5476750.90 frames. , ppl: 10.058110971453097], batch size: 70
+2022-12-11 11:01:31,037 INFO [train.py:421] (7/8) Epoch 4, batch 59400, loss[loss=2.427, over 2240.00 frames. , ppl: 11.327320352451537] tot_loss[loss=2.309, over 5477666.38 frames. , ppl: 10.060684521874776], batch size: 70
+2022-12-11 11:03:11,585 INFO [train.py:421] (7/8) Epoch 4, batch 59600, loss[loss=2.394, over 3010.00 frames. , ppl: 10.953440868939191] tot_loss[loss=2.307, over 5544417.93 frames. , ppl: 10.041621106019639], batch size: 70
+2022-12-11 11:04:50,760 INFO [train.py:421] (7/8) Epoch 4, batch 59800, loss[loss=2.507, over 980.00 frames. , ppl: 12.274198205994956] tot_loss[loss=2.306, over 5549786.49 frames. , ppl: 10.033572271788492], batch size: 70
+2022-12-11 11:06:31,798 INFO [train.py:421] (7/8) Epoch 4, batch 60000, loss[loss=2.483, over 1190.00 frames. , ppl: 11.974188967524286] tot_loss[loss=2.306, over 5554147.87 frames. , ppl: 10.035761596504765], batch size: 70
+2022-12-11 11:06:31,799 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 11:06:32,558 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.293, over 211138.00 frames. , ppl: 9.908699467886942
+2022-12-11 11:08:12,354 INFO [train.py:421] (7/8) Epoch 4, batch 60200, loss[loss=2.354, over 1750.00 frames. , ppl: 10.529661185933916] tot_loss[loss=2.308, over 5486183.32 frames. , ppl: 10.0508521471549], batch size: 70
+2022-12-11 11:09:54,656 INFO [train.py:421] (7/8) Epoch 4, batch 60400, loss[loss=2.228, over 3290.00 frames. , ppl: 9.278007464670848] tot_loss[loss=2.307, over 5519670.01 frames. , ppl: 10.042863895148987], batch size: 70
+2022-12-11 11:11:33,932 INFO [train.py:421] (7/8) Epoch 4, batch 60600, loss[loss=2.428, over 3080.00 frames. , ppl: 11.331451561167228] tot_loss[loss=2.308, over 5493955.90 frames. , ppl: 10.051588786639629], batch size: 70
+2022-12-11 11:13:09,650 INFO [train.py:421] (7/8) Epoch 4, batch 60800, loss[loss=2.343, over 3220.00 frames. , ppl: 10.411122784109539] tot_loss[loss=2.307, over 5497177.73 frames. , ppl: 10.041467757846936], batch size: 70
+2022-12-11 11:14:48,152 INFO [train.py:421] (7/8) Epoch 4, batch 61000, loss[loss=2.387, over 2310.00 frames. , ppl: 10.878041641396749] tot_loss[loss=2.307, over 5491439.32 frames. , ppl: 10.043672590799046], batch size: 70
+2022-12-11 11:14:48,153 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 11:14:48,898 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.292, over 211138.00 frames. , ppl: 9.890057963547763
+2022-12-11 11:16:30,419 INFO [train.py:421] (7/8) Epoch 4, batch 61200, loss[loss=2.621, over 1330.00 frames. , ppl: 13.747090675942617] tot_loss[loss=2.306, over 5527855.11 frames. , ppl: 10.030749770269159], batch size: 70
+2022-12-11 11:18:08,906 INFO [train.py:421] (7/8) Epoch 4, batch 61400, loss[loss=2.578, over 980.00 frames. , ppl: 13.164477744038013] tot_loss[loss=2.305, over 5543119.21 frames. , ppl: 10.021588914969666], batch size: 70
+2022-12-11 11:19:47,063 INFO [train.py:421] (7/8) Epoch 4, batch 61600, loss[loss=2.29, over 910.00 frames. , ppl: 9.87748028776046] tot_loss[loss=2.304, over 5550572.94 frames. , ppl: 10.018725907622233], batch size: 70
+2022-12-11 11:21:28,028 INFO [train.py:421] (7/8) Epoch 4, batch 61800, loss[loss=2.216, over 9590.00 frames. , ppl: 9.170888359584694] tot_loss[loss=2.303, over 5581847.69 frames. , ppl: 10.001839945667522], batch size: 70
+2022-12-11 11:23:08,282 INFO [train.py:421] (7/8) Epoch 4, batch 62000, loss[loss=4.106, over 350.00 frames. , ppl: 60.673420544333524] tot_loss[loss=2.303, over 5585018.57 frames. , ppl: 10.003712416884259], batch size: 70
+2022-12-11 11:23:08,282 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 11:23:09,027 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.916335861485702
+2022-12-11 11:24:49,053 INFO [train.py:421] (7/8) Epoch 4, batch 62200, loss[loss=2.27, over 3290.00 frames. , ppl: 9.67876386600756] tot_loss[loss=2.303, over 5563047.37 frames. , ppl: 10.005765155253462], batch size: 70
+2022-12-11 11:26:31,324 INFO [train.py:421] (7/8) Epoch 4, batch 62400, loss[loss=3.596, over 420.00 frames. , ppl: 36.44218228871915] tot_loss[loss=2.303, over 5598491.49 frames. , ppl: 10.008672794472265], batch size: 70
+2022-12-11 11:28:12,735 INFO [train.py:421] (7/8) Epoch 4, batch 62600, loss[loss=2.382, over 1470.00 frames. , ppl: 10.823460278872123] tot_loss[loss=2.303, over 5611698.99 frames. , ppl: 10.003120419492918], batch size: 70
+2022-12-11 11:29:56,769 INFO [train.py:421] (7/8) Epoch 4, batch 62800, loss[loss=2.229, over 4340.00 frames. , ppl: 9.294469146804548] tot_loss[loss=2.303, over 5614146.25 frames. , ppl: 10.001903787836646], batch size: 70
+2022-12-11 11:31:39,103 INFO [train.py:421] (7/8) Epoch 4, batch 63000, loss[loss=2.264, over 4340.00 frames. , ppl: 9.618724836843407] tot_loss[loss=2.302, over 5631106.44 frames. , ppl: 9.998982855066906], batch size: 70
+2022-12-11 11:31:39,104 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 11:31:39,834 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.912125947821703
+2022-12-11 11:33:18,808 INFO [train.py:421] (7/8) Epoch 4, batch 63200, loss[loss=2.246, over 3500.00 frames. , ppl: 9.44535831747857] tot_loss[loss=2.304, over 5594778.23 frames. , ppl: 10.009955663595921], batch size: 70
+2022-12-11 11:34:57,558 INFO [train.py:421] (7/8) Epoch 4, batch 63400, loss[loss=2.314, over 1750.00 frames. , ppl: 10.116256599526547] tot_loss[loss=2.303, over 5612530.82 frames. , ppl: 10.008747208850687], batch size: 70
+2022-12-11 11:36:40,498 INFO [train.py:421] (7/8) Epoch 4, batch 63600, loss[loss=2.359, over 1820.00 frames. , ppl: 10.575154785784573] tot_loss[loss=2.304, over 5600884.88 frames. , ppl: 10.010468543578272], batch size: 70
+2022-12-11 11:38:20,357 INFO [train.py:421] (7/8) Epoch 4, batch 63800, loss[loss=2.456, over 1400.00 frames. , ppl: 11.655253357231594] tot_loss[loss=2.305, over 5528395.90 frames. , ppl: 10.026583345104743], batch size: 70
+2022-12-11 11:39:59,622 INFO [train.py:421] (7/8) Epoch 4, batch 64000, loss[loss=2.312, over 4340.00 frames. , ppl: 10.09163461019232] tot_loss[loss=2.306, over 5504627.90 frames. , ppl: 10.036560931260437], batch size: 70
+2022-12-11 11:39:59,623 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 11:40:00,404 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.292, over 211138.00 frames. , ppl: 9.899215356849181
+2022-12-11 11:41:39,829 INFO [train.py:421] (7/8) Epoch 4, batch 64200, loss[loss=2.236, over 3990.00 frames. , ppl: 9.351631228642308] tot_loss[loss=2.305, over 5507721.93 frames. , ppl: 10.029102099907622], batch size: 70
+2022-12-11 11:43:17,866 INFO [train.py:421] (7/8) Epoch 4, batch 64400, loss[loss=2.181, over 5250.00 frames. , ppl: 8.853733953731174] tot_loss[loss=2.304, over 5554969.76 frames. , ppl: 10.014387965321031], batch size: 70
+2022-12-11 11:44:57,184 INFO [train.py:421] (7/8) Epoch 4, batch 64600, loss[loss=2.291, over 3150.00 frames. , ppl: 9.881347326366322] tot_loss[loss=2.305, over 5527564.56 frames. , ppl: 10.020619782541386], batch size: 70
+2022-12-11 11:46:37,646 INFO [train.py:421] (7/8) Epoch 4, batch 64800, loss[loss=2.468, over 980.00 frames. , ppl: 11.797307681727165] tot_loss[loss=2.305, over 5529127.31 frames. , ppl: 10.021305133427875], batch size: 70
+2022-12-11 11:48:19,731 INFO [train.py:421] (7/8) Epoch 4, batch 65000, loss[loss=2.253, over 3990.00 frames. , ppl: 9.520201463673628] tot_loss[loss=2.305, over 5520515.64 frames. , ppl: 10.021788550890955], batch size: 70
+2022-12-11 11:48:19,731 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 11:48:20,473 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.916086357031197
+2022-12-11 11:50:01,972 INFO [train.py:421] (7/8) Epoch 4, batch 65200, loss[loss=2.295, over 4550.00 frames. , ppl: 9.92353290243666] tot_loss[loss=2.306, over 5483919.12 frames. , ppl: 10.030468279785374], batch size: 70
+2022-12-11 11:51:41,798 INFO [train.py:421] (7/8) Epoch 4, batch 65400, loss[loss=2.341, over 3500.00 frames. , ppl: 10.394923087798581] tot_loss[loss=2.306, over 5481976.47 frames. , ppl: 10.03296625287386], batch size: 70
+2022-12-11 11:53:19,725 INFO [train.py:421] (7/8) Epoch 4, batch 65600, loss[loss=2.357, over 2520.00 frames. , ppl: 10.558277490038016] tot_loss[loss=2.306, over 5490328.22 frames. , ppl: 10.03891037782799], batch size: 70
+2022-12-11 11:55:00,756 INFO [train.py:421] (7/8) Epoch 4, batch 65800, loss[loss=3.098, over 560.00 frames. , ppl: 22.1534888693057] tot_loss[loss=2.305, over 5551394.03 frames. , ppl: 10.023747424951981], batch size: 70
+2022-12-11 11:56:40,732 INFO [train.py:421] (7/8) Epoch 4, batch 66000, loss[loss=2.39, over 1540.00 frames. , ppl: 10.9121728823328] tot_loss[loss=2.306, over 5515929.99 frames. , ppl: 10.0321452416162], batch size: 70
+2022-12-11 11:56:40,732 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 11:56:41,491 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.919058803417657
+2022-12-11 11:58:22,194 INFO [train.py:421] (7/8) Epoch 4, batch 66200, loss[loss=2.707, over 840.00 frames. , ppl: 14.979297903611734] tot_loss[loss=2.307, over 5486881.19 frames. , ppl: 10.04109614229849], batch size: 70
+2022-12-11 12:00:04,132 INFO [train.py:421] (7/8) Epoch 4, batch 66400, loss[loss=2.321, over 2030.00 frames. , ppl: 10.190375791201346] tot_loss[loss=2.305, over 5525306.17 frames. , ppl: 10.02821523964254], batch size: 70
+2022-12-11 12:01:41,417 INFO [train.py:421] (7/8) Epoch 4, batch 66600, loss[loss=2.471, over 1260.00 frames. , ppl: 11.83863700589946] tot_loss[loss=2.304, over 5535181.10 frames. , ppl: 10.018606908265957], batch size: 70
+2022-12-11 12:03:22,241 INFO [train.py:421] (7/8) Epoch 4, batch 66800, loss[loss=2.209, over 4480.00 frames. , ppl: 9.10348783745428] tot_loss[loss=2.302, over 5609687.85 frames. , ppl: 9.992670499699676], batch size: 70
+2022-12-11 12:05:01,145 INFO [train.py:421] (7/8) Epoch 4, batch 67000, loss[loss=2.224, over 10990.00 frames. , ppl: 9.24333514281] tot_loss[loss=2.302, over 5632130.16 frames. , ppl: 9.991080041690475], batch size: 70
+2022-12-11 12:05:01,146 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 12:05:01,878 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.293, over 211138.00 frames. , ppl: 9.901741611125681
+2022-12-11 12:06:40,988 INFO [train.py:421] (7/8) Epoch 4, batch 67200, loss[loss=2.266, over 3780.00 frames. , ppl: 9.644740190241256] tot_loss[loss=2.302, over 5617967.09 frames. , ppl: 9.993329867492351], batch size: 70
+2022-12-11 12:08:24,021 INFO [train.py:421] (7/8) Epoch 4, batch 67400, loss[loss=2.2, over 6090.00 frames. , ppl: 9.025808050971028] tot_loss[loss=2.302, over 5591977.67 frames. , ppl: 9.995937267910447], batch size: 70
+2022-12-11 12:10:06,523 INFO [train.py:421] (7/8) Epoch 4, batch 67600, loss[loss=2.32, over 2730.00 frames. , ppl: 10.17503587126265] tot_loss[loss=2.302, over 5563593.52 frames. , ppl: 9.998755410917928], batch size: 70
+2022-12-11 12:11:44,333 INFO [train.py:421] (7/8) Epoch 4, batch 67800, loss[loss=2.15, over 4900.00 frames. , ppl: 8.583811360160349] tot_loss[loss=2.302, over 5594324.63 frames. , ppl: 9.993370133555674], batch size: 70
+2022-12-11 12:13:27,434 INFO [train.py:421] (7/8) Epoch 4, batch 68000, loss[loss=2.244, over 3850.00 frames. , ppl: 9.434830640154091] tot_loss[loss=2.302, over 5576605.18 frames. , ppl: 9.996360557271744], batch size: 70
+2022-12-11 12:13:27,434 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 12:13:28,169 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.910991968643046
+2022-12-11 12:15:09,925 INFO [train.py:421] (7/8) Epoch 4, batch 68200, loss[loss=2.426, over 1750.00 frames. , ppl: 11.316801778601588] tot_loss[loss=2.302, over 5574431.08 frames. , ppl: 9.994711680080234], batch size: 70
+2022-12-11 12:16:49,666 INFO [train.py:421] (7/8) Epoch 4, batch 68400, loss[loss=2.236, over 4620.00 frames. , ppl: 9.358588857451776] tot_loss[loss=2.303, over 5541610.36 frames. , ppl: 9.999887435905034], batch size: 70
+2022-12-11 12:18:30,841 INFO [train.py:421] (7/8) Epoch 4, batch 68600, loss[loss=2.22, over 13440.00 frames. , ppl: 9.206786840624067] tot_loss[loss=2.305, over 5517004.73 frames. , ppl: 10.019576060618482], batch size: 70
+2022-12-11 12:20:12,551 INFO [train.py:421] (7/8) Epoch 4, batch 68800, loss[loss=2.484, over 1540.00 frames. , ppl: 11.991426001439288] tot_loss[loss=2.306, over 5476437.30 frames. , ppl: 10.033835605847917], batch size: 70
+2022-12-11 12:21:53,589 INFO [train.py:421] (7/8) Epoch 4, batch 69000, loss[loss=2.292, over 3570.00 frames. , ppl: 9.897607775577713] tot_loss[loss=2.306, over 5470811.58 frames. , ppl: 10.029725571914721], batch size: 70
+2022-12-11 12:21:53,590 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 12:21:54,350 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.294, over 211138.00 frames. , ppl: 9.910044396033411
+2022-12-11 12:23:33,521 INFO [train.py:421] (7/8) Epoch 4, batch 69200, loss[loss=2.204, over 9940.00 frames. , ppl: 9.059764952131173] tot_loss[loss=2.306, over 5446273.71 frames. , ppl: 10.03509760716646], batch size: 70
+2022-12-11 12:25:12,764 INFO [train.py:421] (7/8) Epoch 4, batch 69400, loss[loss=2.33, over 2170.00 frames. , ppl: 10.277620537398022] tot_loss[loss=2.307, over 5427034.29 frames. , ppl: 10.043556597249989], batch size: 70
+2022-12-11 12:26:51,730 INFO [train.py:421] (7/8) Epoch 4, batch 69600, loss[loss=2.391, over 1330.00 frames. , ppl: 10.922510240809046] tot_loss[loss=2.306, over 5442129.65 frames. , ppl: 10.030739304862482], batch size: 70
+2022-12-11 12:28:30,366 INFO [train.py:421] (7/8) Epoch 4, batch 69800, loss[loss=2.4, over 2590.00 frames. , ppl: 11.025333712156604] tot_loss[loss=2.307, over 5413710.62 frames. , ppl: 10.041165475878918], batch size: 70
+2022-12-11 12:30:08,286 INFO [train.py:421] (7/8) Epoch 4, batch 70000, loss[loss=2.237, over 6300.00 frames. , ppl: 9.364594860252373] tot_loss[loss=2.306, over 5433702.47 frames. , ppl: 10.037155717017646], batch size: 70
+2022-12-11 12:30:08,286 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 12:30:09,018 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.292, over 211138.00 frames. , ppl: 9.896056980662939
+2022-12-11 12:31:48,797 INFO [train.py:421] (7/8) Epoch 4, batch 70200, loss[loss=2.249, over 6580.00 frames. , ppl: 9.474961616611315] tot_loss[loss=2.306, over 5432291.19 frames. , ppl: 10.03879098010484], batch size: 70
+2022-12-11 12:33:26,604 INFO [train.py:421] (7/8) Epoch 4, batch 70400, loss[loss=2.18, over 5250.00 frames. , ppl: 8.847726454981961] tot_loss[loss=2.306, over 5438632.38 frames. , ppl: 10.037637659569844], batch size: 70
+2022-12-11 12:35:03,418 INFO [train.py:421] (7/8) Epoch 4, batch 70600, loss[loss=2.411, over 1120.00 frames. , ppl: 11.140590799503224] tot_loss[loss=2.307, over 5417498.09 frames. , ppl: 10.039371592894009], batch size: 70
+2022-12-11 12:36:42,022 INFO [train.py:421] (7/8) Epoch 4, batch 70800, loss[loss=2.26, over 6090.00 frames. , ppl: 9.586577181851503] tot_loss[loss=2.307, over 5409298.14 frames. , ppl: 10.043885384643964], batch size: 70
+2022-12-11 12:38:21,443 INFO [train.py:421] (7/8) Epoch 4, batch 71000, loss[loss=2.548, over 980.00 frames. , ppl: 12.778847625217121] tot_loss[loss=2.307, over 5394314.50 frames. , ppl: 10.039923648325146], batch size: 70
+2022-12-11 12:38:21,444 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 12:38:22,205 INFO [train.py:452] (7/8) Epoch 4, validation: loss=2.295, over 211138.00 frames. , ppl: 9.920506450462009
+2022-12-11 12:40:01,639 INFO [train.py:421] (7/8) Epoch 4, batch 71200, loss[loss=2.452, over 1540.00 frames. , ppl: 11.611315253885897] tot_loss[loss=2.306, over 5408718.04 frames. , ppl: 10.030936401964114], batch size: 70
+2022-12-11 12:41:40,333 INFO [train.py:421] (7/8) Epoch 4, batch 71400, loss[loss=2.38, over 1260.00 frames. , ppl: 10.806953095796288] tot_loss[loss=2.306, over 5427901.66 frames. , ppl: 10.036305976063208], batch size: 70
+2022-12-11 12:43:20,029 INFO [train.py:421] (7/8) Epoch 4, batch 71600, loss[loss=2.276, over 1120.00 frames. , ppl: 9.742355598548139] tot_loss[loss=2.306, over 5453441.48 frames. , ppl: 10.030613978862217], batch size: 70
+2022-12-11 12:45:06,137 INFO [train.py:421] (7/8) Epoch 4, batch 71800, loss[loss=2.261, over 1470.00 frames. , ppl: 9.590449544102704] tot_loss[loss=2.304, over 5511693.51 frames. , ppl: 10.011031856555931], batch size: 70
+2022-12-11 12:46:20,323 INFO [train.py:421] (7/8) Epoch 5, batch 0, loss[loss=2.35, over 1610.00 frames. , ppl: 10.48844489897742] tot_loss[loss=2.35, over 1610.00 frames. , ppl: 10.48844489897742], batch size: 70
+2022-12-11 12:48:02,182 INFO [train.py:421] (7/8) Epoch 5, batch 200, loss[loss=2.258, over 5670.00 frames. , ppl: 9.566161809560944] tot_loss[loss=2.294, over 540975.70 frames. , ppl: 9.913206721052333], batch size: 70
+2022-12-11 12:49:43,371 INFO [train.py:421] (7/8) Epoch 5, batch 400, loss[loss=2.265, over 6790.00 frames. , ppl: 9.634878625416619] tot_loss[loss=2.294, over 1037425.10 frames. , ppl: 9.914346965202967], batch size: 70
+2022-12-11 12:51:24,416 INFO [train.py:421] (7/8) Epoch 5, batch 600, loss[loss=2.241, over 2660.00 frames. , ppl: 9.402213462387346] tot_loss[loss=2.295, over 1438812.89 frames. , ppl: 9.923058581340392], batch size: 70
+2022-12-11 12:53:04,463 INFO [train.py:421] (7/8) Epoch 5, batch 800, loss[loss=2.197, over 8610.00 frames. , ppl: 8.998389226880764] tot_loss[loss=2.295, over 1854247.58 frames. , ppl: 9.925569456594175], batch size: 70
+2022-12-11 12:54:44,630 INFO [train.py:421] (7/8) Epoch 5, batch 1000, loss[loss=2.587, over 1050.00 frames. , ppl: 13.287390146345626] tot_loss[loss=2.295, over 2197170.84 frames. , ppl: 9.925192494734254], batch size: 70
+2022-12-11 12:54:44,631 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 12:54:45,418 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.293, over 211138.00 frames. , ppl: 9.90861440768603
+2022-12-11 12:56:25,130 INFO [train.py:421] (7/8) Epoch 5, batch 1200, loss[loss=2.275, over 4690.00 frames. , ppl: 9.726817165162938] tot_loss[loss=2.293, over 2546952.66 frames. , ppl: 9.90671408475087], batch size: 70
+2022-12-11 12:58:03,059 INFO [train.py:421] (7/8) Epoch 5, batch 1400, loss[loss=2.311, over 2520.00 frames. , ppl: 10.08089658992863] tot_loss[loss=2.294, over 2826456.34 frames. , ppl: 9.912639095437733], batch size: 70
+2022-12-11 12:59:45,913 INFO [train.py:421] (7/8) Epoch 5, batch 1600, loss[loss=2.241, over 6580.00 frames. , ppl: 9.406401970417546] tot_loss[loss=2.291, over 3143129.32 frames. , ppl: 9.885617446983053], batch size: 70
+2022-12-11 13:01:25,814 INFO [train.py:421] (7/8) Epoch 5, batch 1800, loss[loss=2.352, over 2800.00 frames. , ppl: 10.504065225207345] tot_loss[loss=2.292, over 3367213.24 frames. , ppl: 9.895464692409512], batch size: 70
+2022-12-11 13:03:08,707 INFO [train.py:421] (7/8) Epoch 5, batch 2000, loss[loss=2.179, over 11970.00 frames. , ppl: 8.840976962790878] tot_loss[loss=2.292, over 3602895.80 frames. , ppl: 9.896836108758123], batch size: 70
+2022-12-11 13:03:08,707 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 13:03:09,438 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.292, over 211138.00 frames. , ppl: 9.893647858407924
+2022-12-11 13:04:49,705 INFO [train.py:421] (7/8) Epoch 5, batch 2200, loss[loss=2.302, over 4830.00 frames. , ppl: 9.99305999385133] tot_loss[loss=2.291, over 3823292.17 frames. , ppl: 9.8859769042197], batch size: 70
+2022-12-11 13:06:31,487 INFO [train.py:421] (7/8) Epoch 5, batch 2400, loss[loss=2.722, over 910.00 frames. , ppl: 15.203516720023963] tot_loss[loss=2.293, over 3956209.20 frames. , ppl: 9.905766034692643], batch size: 70
+2022-12-11 13:08:14,049 INFO [train.py:421] (7/8) Epoch 5, batch 2600, loss[loss=2.242, over 2800.00 frames. , ppl: 9.413028370800442] tot_loss[loss=2.294, over 4095350.23 frames. , ppl: 9.916138510688818], batch size: 70
+2022-12-11 13:09:54,955 INFO [train.py:421] (7/8) Epoch 5, batch 2800, loss[loss=2.16, over 5390.00 frames. , ppl: 8.674595264981168] tot_loss[loss=2.293, over 4289203.23 frames. , ppl: 9.902009858738813], batch size: 70
+2022-12-11 13:11:38,194 INFO [train.py:421] (7/8) Epoch 5, batch 3000, loss[loss=2.196, over 2520.00 frames. , ppl: 8.9887483988965] tot_loss[loss=2.292, over 4450124.92 frames. , ppl: 9.89159268009857], batch size: 70
+2022-12-11 13:11:38,194 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 13:11:38,953 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.29, over 211138.00 frames. , ppl: 9.878481675447484
+2022-12-11 13:13:17,482 INFO [train.py:421] (7/8) Epoch 5, batch 3200, loss[loss=2.387, over 2380.00 frames. , ppl: 10.881108621171965] tot_loss[loss=2.294, over 4527193.04 frames. , ppl: 9.912143331771762], batch size: 70
+2022-12-11 13:14:57,411 INFO [train.py:421] (7/8) Epoch 5, batch 3400, loss[loss=2.473, over 1470.00 frames. , ppl: 11.85941157403826] tot_loss[loss=2.294, over 4622965.75 frames. , ppl: 9.911744044276196], batch size: 70
+2022-12-11 13:16:37,749 INFO [train.py:421] (7/8) Epoch 5, batch 3600, loss[loss=2.447, over 1680.00 frames. , ppl: 11.553472323499479] tot_loss[loss=2.294, over 4686007.60 frames. , ppl: 9.919154842781138], batch size: 70
+2022-12-11 13:18:14,023 INFO [train.py:421] (7/8) Epoch 5, batch 3800, loss[loss=2.272, over 3290.00 frames. , ppl: 9.697353708812154] tot_loss[loss=2.295, over 4761983.48 frames. , ppl: 9.920625926039692], batch size: 70
+2022-12-11 13:19:56,338 INFO [train.py:421] (7/8) Epoch 5, batch 4000, loss[loss=2.34, over 3640.00 frames. , ppl: 10.382536192544226] tot_loss[loss=2.298, over 4731325.22 frames. , ppl: 9.95445101323391], batch size: 70
+2022-12-11 13:19:56,338 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 13:19:57,099 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.293, over 211138.00 frames. , ppl: 9.905227258803862
+2022-12-11 13:21:39,464 INFO [train.py:421] (7/8) Epoch 5, batch 4200, loss[loss=2.484, over 1050.00 frames. , ppl: 11.991603052493149] tot_loss[loss=2.299, over 4769708.09 frames. , ppl: 9.96889829971293], batch size: 70
+2022-12-11 13:23:20,069 INFO [train.py:421] (7/8) Epoch 5, batch 4400, loss[loss=2.402, over 1890.00 frames. , ppl: 11.042632860940884] tot_loss[loss=2.298, over 4867396.30 frames. , ppl: 9.95399983696686], batch size: 70
+2022-12-11 13:25:01,537 INFO [train.py:421] (7/8) Epoch 5, batch 4600, loss[loss=2.679, over 700.00 frames. , ppl: 14.56550164270386] tot_loss[loss=2.297, over 4951105.42 frames. , ppl: 9.94817539032882], batch size: 70
+2022-12-11 13:26:39,729 INFO [train.py:421] (7/8) Epoch 5, batch 4800, loss[loss=2.243, over 5740.00 frames. , ppl: 9.421034776139779] tot_loss[loss=2.296, over 5024540.94 frames. , ppl: 9.938815780710993], batch size: 70
+2022-12-11 13:28:19,899 INFO [train.py:421] (7/8) Epoch 5, batch 5000, loss[loss=2.358, over 2100.00 frames. , ppl: 10.570890811374959] tot_loss[loss=2.296, over 5076862.32 frames. , ppl: 9.93803217903406], batch size: 70
+2022-12-11 13:28:19,899 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 13:28:20,645 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.292, over 211138.00 frames. , ppl: 9.89573182475821
+2022-12-11 13:30:01,901 INFO [train.py:421] (7/8) Epoch 5, batch 5200, loss[loss=2.267, over 2030.00 frames. , ppl: 9.65298425052422] tot_loss[loss=2.296, over 5139389.85 frames. , ppl: 9.935055760402932], batch size: 70
+2022-12-11 13:31:43,064 INFO [train.py:421] (7/8) Epoch 5, batch 5400, loss[loss=2.377, over 1120.00 frames. , ppl: 10.77474654278988] tot_loss[loss=2.297, over 5134417.77 frames. , ppl: 9.941757510578576], batch size: 70
+2022-12-11 13:33:23,012 INFO [train.py:421] (7/8) Epoch 5, batch 5600, loss[loss=2.283, over 2030.00 frames. , ppl: 9.802364988125245] tot_loss[loss=2.296, over 5174290.87 frames. , ppl: 9.937731004755358], batch size: 70
+2022-12-11 13:35:01,445 INFO [train.py:421] (7/8) Epoch 5, batch 5800, loss[loss=2.969, over 630.00 frames. , ppl: 19.47118390926267] tot_loss[loss=2.297, over 5186017.58 frames. , ppl: 9.93936269058492], batch size: 70
+2022-12-11 13:36:38,804 INFO [train.py:421] (7/8) Epoch 5, batch 6000, loss[loss=2.496, over 1400.00 frames. , ppl: 12.134569341719866] tot_loss[loss=2.297, over 5214556.38 frames. , ppl: 9.939694168028042], batch size: 70
+2022-12-11 13:36:38,804 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 13:36:39,553 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.292, over 211138.00 frames. , ppl: 9.896351387792528
+2022-12-11 13:38:21,623 INFO [train.py:421] (7/8) Epoch 5, batch 6200, loss[loss=2.481, over 910.00 frames. , ppl: 11.954352847013238] tot_loss[loss=2.297, over 5252790.21 frames. , ppl: 9.946689316484136], batch size: 70
+2022-12-11 13:39:57,552 INFO [train.py:421] (7/8) Epoch 5, batch 6400, loss[loss=2.236, over 8470.00 frames. , ppl: 9.356695919196083] tot_loss[loss=2.297, over 5273116.31 frames. , ppl: 9.944948161768645], batch size: 70
+2022-12-11 13:41:36,936 INFO [train.py:421] (7/8) Epoch 5, batch 6600, loss[loss=2.468, over 1960.00 frames. , ppl: 11.79647010167577] tot_loss[loss=2.298, over 5260045.70 frames. , ppl: 9.950111910082692], batch size: 70
+2022-12-11 13:43:15,781 INFO [train.py:421] (7/8) Epoch 5, batch 6800, loss[loss=2.262, over 3640.00 frames. , ppl: 9.606473757887976] tot_loss[loss=2.298, over 5255318.24 frames. , ppl: 9.958171770343037], batch size: 70
+2022-12-11 13:44:54,864 INFO [train.py:421] (7/8) Epoch 5, batch 7000, loss[loss=2.446, over 1610.00 frames. , ppl: 11.539877739625046] tot_loss[loss=2.299, over 5294359.20 frames. , ppl: 9.960848053454567], batch size: 70
+2022-12-11 13:44:54,864 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 13:44:55,610 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.291, over 211138.00 frames. , ppl: 9.88711469496257
+2022-12-11 13:46:38,711 INFO [train.py:421] (7/8) Epoch 5, batch 7200, loss[loss=2.482, over 910.00 frames. , ppl: 11.959934660885265] tot_loss[loss=2.299, over 5296783.56 frames. , ppl: 9.965351767937168], batch size: 70
+2022-12-11 13:48:18,509 INFO [train.py:421] (7/8) Epoch 5, batch 7400, loss[loss=2.34, over 2800.00 frames. , ppl: 10.37768527539149] tot_loss[loss=2.3, over 5300791.34 frames. , ppl: 9.977310091902194], batch size: 70
+2022-12-11 13:49:58,378 INFO [train.py:421] (7/8) Epoch 5, batch 7600, loss[loss=2.302, over 2240.00 frames. , ppl: 9.997937734884093] tot_loss[loss=2.3, over 5295306.53 frames. , ppl: 9.976720664115012], batch size: 70
+2022-12-11 13:51:37,160 INFO [train.py:421] (7/8) Epoch 5, batch 7800, loss[loss=2.404, over 2030.00 frames. , ppl: 11.065532005119165] tot_loss[loss=2.3, over 5302573.42 frames. , ppl: 9.976918965905206], batch size: 70
+2022-12-11 13:53:18,459 INFO [train.py:421] (7/8) Epoch 5, batch 8000, loss[loss=2.516, over 1400.00 frames. , ppl: 12.375870380855421] tot_loss[loss=2.3, over 5344823.60 frames. , ppl: 9.969353523234215], batch size: 70
+2022-12-11 13:53:18,460 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 13:53:19,219 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.293, over 211138.00 frames. , ppl: 9.903350895657939
+2022-12-11 13:54:59,220 INFO [train.py:421] (7/8) Epoch 5, batch 8200, loss[loss=2.481, over 1260.00 frames. , ppl: 11.949863623720395] tot_loss[loss=2.299, over 5366405.44 frames. , ppl: 9.96842257730376], batch size: 70
+2022-12-11 13:56:40,076 INFO [train.py:421] (7/8) Epoch 5, batch 8400, loss[loss=2.427, over 1400.00 frames. , ppl: 11.329099768814393] tot_loss[loss=2.3, over 5343321.31 frames. , ppl: 9.97446047665439], batch size: 70
+2022-12-11 13:58:20,792 INFO [train.py:421] (7/8) Epoch 5, batch 8600, loss[loss=2.11, over 7236.00 frames. , ppl: 8.249264309943449] tot_loss[loss=2.3, over 5347769.45 frames. , ppl: 9.973458519252361], batch size: 36
+2022-12-11 14:00:00,770 INFO [train.py:421] (7/8) Epoch 5, batch 8800, loss[loss=2.586, over 910.00 frames. , ppl: 13.277374860190601] tot_loss[loss=2.3, over 5353412.21 frames. , ppl: 9.970306678218957], batch size: 70
+2022-12-11 14:01:38,185 INFO [train.py:421] (7/8) Epoch 5, batch 9000, loss[loss=2.372, over 3360.00 frames. , ppl: 10.715640382686704] tot_loss[loss=2.3, over 5365143.92 frames. , ppl: 9.970411522564891], batch size: 70
+2022-12-11 14:01:38,185 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 14:01:38,944 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.292, over 211138.00 frames. , ppl: 9.898942841256256
+2022-12-11 14:03:18,628 INFO [train.py:421] (7/8) Epoch 5, batch 9200, loss[loss=2.16, over 3290.00 frames. , ppl: 8.674160893885304] tot_loss[loss=2.3, over 5363308.57 frames. , ppl: 9.97132455343642], batch size: 70
+2022-12-11 14:04:53,956 INFO [train.py:421] (7/8) Epoch 5, batch 9400, loss[loss=2.522, over 1260.00 frames. , ppl: 12.449379401877708] tot_loss[loss=2.301, over 5324839.94 frames. , ppl: 9.980557821176042], batch size: 70
+2022-12-11 14:06:31,801 INFO [train.py:421] (7/8) Epoch 5, batch 9600, loss[loss=2.688, over 770.00 frames. , ppl: 14.697124677651093] tot_loss[loss=2.3, over 5394291.24 frames. , ppl: 9.9763754248274], batch size: 70
+2022-12-11 14:08:10,023 INFO [train.py:421] (7/8) Epoch 5, batch 9800, loss[loss=2.434, over 980.00 frames. , ppl: 11.403443462509774] tot_loss[loss=2.301, over 5383101.56 frames. , ppl: 9.97919322126909], batch size: 70
+2022-12-11 14:09:51,392 INFO [train.py:421] (7/8) Epoch 5, batch 10000, loss[loss=2.333, over 3010.00 frames. , ppl: 10.313458563160468] tot_loss[loss=2.303, over 5333075.10 frames. , ppl: 10.002215807906031], batch size: 70
+2022-12-11 14:09:51,392 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 14:09:52,185 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.293, over 211138.00 frames. , ppl: 9.904837297826665
+2022-12-11 14:11:34,860 INFO [train.py:421] (7/8) Epoch 5, batch 10200, loss[loss=2.361, over 1890.00 frames. , ppl: 10.597790803679905] tot_loss[loss=2.303, over 5342282.84 frames. , ppl: 10.00542274045438], batch size: 70
+2022-12-11 14:13:12,043 INFO [train.py:421] (7/8) Epoch 5, batch 10400, loss[loss=2.721, over 770.00 frames. , ppl: 15.20254931064809] tot_loss[loss=2.303, over 5339229.86 frames. , ppl: 10.002350963870509], batch size: 70
+2022-12-11 14:14:53,715 INFO [train.py:421] (7/8) Epoch 5, batch 10600, loss[loss=2.491, over 1120.00 frames. , ppl: 12.076917073082457] tot_loss[loss=2.303, over 5370542.31 frames. , ppl: 9.999700206346263], batch size: 70
+2022-12-11 14:16:33,812 INFO [train.py:421] (7/8) Epoch 5, batch 10800, loss[loss=2.526, over 1680.00 frames. , ppl: 12.507431775430717] tot_loss[loss=2.301, over 5408391.22 frames. , ppl: 9.983077793455985], batch size: 70
+2022-12-11 14:18:14,048 INFO [train.py:421] (7/8) Epoch 5, batch 11000, loss[loss=2.979, over 560.00 frames. , ppl: 19.66533033561215] tot_loss[loss=2.301, over 5422960.99 frames. , ppl: 9.986431225715023], batch size: 70
+2022-12-11 14:18:14,048 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 14:18:14,795 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.292, over 211138.00 frames. , ppl: 9.8904824753545
+2022-12-11 14:19:51,222 INFO [train.py:421] (7/8) Epoch 5, batch 11200, loss[loss=2.212, over 5250.00 frames. , ppl: 9.135104488063297] tot_loss[loss=2.302, over 5389976.29 frames. , ppl: 9.993798057460664], batch size: 70
+2022-12-11 14:21:32,935 INFO [train.py:421] (7/8) Epoch 5, batch 11400, loss[loss=2.354, over 2240.00 frames. , ppl: 10.522452056267733] tot_loss[loss=2.299, over 5462340.82 frames. , ppl: 9.964458073391297], batch size: 70
+2022-12-11 14:23:12,624 INFO [train.py:421] (7/8) Epoch 5, batch 11600, loss[loss=2.237, over 3080.00 frames. , ppl: 9.361942493593526] tot_loss[loss=2.3, over 5424873.88 frames. , ppl: 9.972149382518937], batch size: 70
+2022-12-11 14:24:53,851 INFO [train.py:421] (7/8) Epoch 5, batch 11800, loss[loss=2.221, over 13510.00 frames. , ppl: 9.214758164975745] tot_loss[loss=2.299, over 5443381.39 frames. , ppl: 9.964657566300273], batch size: 70
+2022-12-11 14:26:33,014 INFO [train.py:421] (7/8) Epoch 5, batch 12000, loss[loss=2.25, over 3010.00 frames. , ppl: 9.484270421788425] tot_loss[loss=2.301, over 5396946.04 frames. , ppl: 9.979515228312744], batch size: 70
+2022-12-11 14:26:33,014 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 14:26:33,774 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.291, over 211138.00 frames. , ppl: 9.883088329655019
+2022-12-11 14:28:11,316 INFO [train.py:421] (7/8) Epoch 5, batch 12200, loss[loss=2.342, over 2660.00 frames. , ppl: 10.401633043139533] tot_loss[loss=2.3, over 5394341.79 frames. , ppl: 9.978324496656134], batch size: 70
+2022-12-11 14:29:52,535 INFO [train.py:421] (7/8) Epoch 5, batch 12400, loss[loss=2.793, over 700.00 frames. , ppl: 16.326962885945875] tot_loss[loss=2.301, over 5392631.39 frames. , ppl: 9.98480867771561], batch size: 70
+2022-12-11 14:31:29,830 INFO [train.py:421] (7/8) Epoch 5, batch 12600, loss[loss=3.012, over 630.00 frames. , ppl: 20.324496230503996] tot_loss[loss=2.3, over 5435514.58 frames. , ppl: 9.974160172995377], batch size: 70
+2022-12-11 14:33:09,823 INFO [train.py:421] (7/8) Epoch 5, batch 12800, loss[loss=2.234, over 5950.00 frames. , ppl: 9.334557851156074] tot_loss[loss=2.3, over 5438589.37 frames. , ppl: 9.976659380287384], batch size: 70
+2022-12-11 14:34:47,876 INFO [train.py:421] (7/8) Epoch 5, batch 13000, loss[loss=2.464, over 980.00 frames. , ppl: 11.748410593133487] tot_loss[loss=2.3, over 5449700.76 frames. , ppl: 9.973506730310454], batch size: 70
+2022-12-11 14:34:47,877 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 14:34:48,636 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.291, over 211138.00 frames. , ppl: 9.882500313269402
+2022-12-11 14:36:27,619 INFO [train.py:421] (7/8) Epoch 5, batch 13200, loss[loss=2.241, over 2380.00 frames. , ppl: 9.407240863278087] tot_loss[loss=2.3, over 5464038.66 frames. , ppl: 9.97057461771368], batch size: 70
+2022-12-11 14:38:12,177 INFO [train.py:421] (7/8) Epoch 5, batch 13400, loss[loss=2.194, over 4760.00 frames. , ppl: 8.96997733186993] tot_loss[loss=2.301, over 5412157.98 frames. , ppl: 9.985208786794093], batch size: 70
+2022-12-11 14:39:51,873 INFO [train.py:421] (7/8) Epoch 5, batch 13600, loss[loss=2.603, over 770.00 frames. , ppl: 13.506464706973478] tot_loss[loss=2.301, over 5422971.71 frames. , ppl: 9.979918384376424], batch size: 70
+2022-12-11 14:41:35,233 INFO [train.py:421] (7/8) Epoch 5, batch 13800, loss[loss=2.383, over 2100.00 frames. , ppl: 10.83509005079843] tot_loss[loss=2.3, over 5429410.08 frames. , ppl: 9.977529970739155], batch size: 70
+2022-12-11 14:43:18,792 INFO [train.py:421] (7/8) Epoch 5, batch 14000, loss[loss=2.507, over 1260.00 frames. , ppl: 12.272529108010028] tot_loss[loss=2.301, over 5428160.41 frames. , ppl: 9.982492764665322], batch size: 70
+2022-12-11 14:43:18,792 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 14:43:19,550 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.291, over 211138.00 frames. , ppl: 9.88920899459524
+2022-12-11 14:45:00,094 INFO [train.py:421] (7/8) Epoch 5, batch 14200, loss[loss=3.036, over 560.00 frames. , ppl: 20.828313815250905] tot_loss[loss=2.299, over 5483688.36 frames. , ppl: 9.96582123964333], batch size: 70
+2022-12-11 14:46:37,397 INFO [train.py:421] (7/8) Epoch 5, batch 14400, loss[loss=2.242, over 1680.00 frames. , ppl: 9.410473993359068] tot_loss[loss=2.3, over 5448315.89 frames. , ppl: 9.976167825916129], batch size: 70
+2022-12-11 14:48:13,462 INFO [train.py:421] (7/8) Epoch 5, batch 14600, loss[loss=2.883, over 560.00 frames. , ppl: 17.86108212549694] tot_loss[loss=2.3, over 5460336.95 frames. , ppl: 9.972049933776999], batch size: 70
+2022-12-11 14:49:54,268 INFO [train.py:421] (7/8) Epoch 5, batch 14800, loss[loss=2.376, over 1330.00 frames. , ppl: 10.756439715054803] tot_loss[loss=2.3, over 5464606.15 frames. , ppl: 9.977155187949306], batch size: 70
+2022-12-11 14:51:36,211 INFO [train.py:421] (7/8) Epoch 5, batch 15000, loss[loss=2.368, over 2030.00 frames. , ppl: 10.670899858823168] tot_loss[loss=2.3, over 5449604.84 frames. , ppl: 9.977198012356654], batch size: 70
+2022-12-11 14:51:36,212 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 14:51:36,973 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.291, over 211138.00 frames. , ppl: 9.882491537170422
+2022-12-11 14:53:18,628 INFO [train.py:421] (7/8) Epoch 5, batch 15200, loss[loss=2.207, over 11270.00 frames. , ppl: 9.086042162612292] tot_loss[loss=2.298, over 5498880.99 frames. , ppl: 9.957684033894214], batch size: 70
+2022-12-11 14:55:01,723 INFO [train.py:421] (7/8) Epoch 5, batch 15400, loss[loss=2.517, over 980.00 frames. , ppl: 12.389578405300881] tot_loss[loss=2.298, over 5513933.11 frames. , ppl: 9.957348402979314], batch size: 70
+2022-12-11 14:56:39,994 INFO [train.py:421] (7/8) Epoch 5, batch 15600, loss[loss=2.275, over 2170.00 frames. , ppl: 9.730694961485181] tot_loss[loss=2.298, over 5535615.09 frames. , ppl: 9.958150187981554], batch size: 70
+2022-12-11 14:58:22,473 INFO [train.py:421] (7/8) Epoch 5, batch 15800, loss[loss=2.319, over 3150.00 frames. , ppl: 10.166939646291414] tot_loss[loss=2.298, over 5560562.46 frames. , ppl: 9.951425711458162], batch size: 70
+2022-12-11 15:00:04,357 INFO [train.py:421] (7/8) Epoch 5, batch 16000, loss[loss=2.757, over 770.00 frames. , ppl: 15.756723245468917] tot_loss[loss=2.298, over 5533200.57 frames. , ppl: 9.956174505330615], batch size: 70
+2022-12-11 15:00:04,357 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 15:00:05,117 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.29, over 211138.00 frames. , ppl: 9.876905669210421
+2022-12-11 15:01:47,812 INFO [train.py:421] (7/8) Epoch 5, batch 16200, loss[loss=2.449, over 1190.00 frames. , ppl: 11.57790008405111] tot_loss[loss=2.298, over 5524019.37 frames. , ppl: 9.951082626176428], batch size: 70
+2022-12-11 15:03:30,636 INFO [train.py:421] (7/8) Epoch 5, batch 16400, loss[loss=2.236, over 5180.00 frames. , ppl: 9.35471919143948] tot_loss[loss=2.298, over 5519102.23 frames. , ppl: 9.956580154730478], batch size: 70
+2022-12-11 15:05:08,591 INFO [train.py:421] (7/8) Epoch 5, batch 16600, loss[loss=2.168, over 3920.00 frames. , ppl: 8.740886364002474] tot_loss[loss=2.299, over 5515770.84 frames. , ppl: 9.961910259372129], batch size: 70
+2022-12-11 15:06:50,339 INFO [train.py:421] (7/8) Epoch 5, batch 16800, loss[loss=2.233, over 2730.00 frames. , ppl: 9.328891525138397] tot_loss[loss=2.298, over 5528879.44 frames. , ppl: 9.954463848103211], batch size: 70
+2022-12-11 15:08:31,276 INFO [train.py:421] (7/8) Epoch 5, batch 17000, loss[loss=2.269, over 3570.00 frames. , ppl: 9.669288704863403] tot_loss[loss=2.298, over 5551637.40 frames. , ppl: 9.953520917101221], batch size: 70
+2022-12-11 15:08:31,277 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 15:08:32,009 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.292, over 211138.00 frames. , ppl: 9.891302273858114
+2022-12-11 15:10:09,656 INFO [train.py:421] (7/8) Epoch 5, batch 17200, loss[loss=2.468, over 1050.00 frames. , ppl: 11.794828029597676] tot_loss[loss=2.299, over 5499816.18 frames. , ppl: 9.965019117915306], batch size: 70
+2022-12-11 15:11:48,000 INFO [train.py:421] (7/8) Epoch 5, batch 17400, loss[loss=2.406, over 910.00 frames. , ppl: 11.088398146472414] tot_loss[loss=2.299, over 5487213.50 frames. , ppl: 9.968732076801457], batch size: 70
+2022-12-11 15:13:29,110 INFO [train.py:421] (7/8) Epoch 5, batch 17600, loss[loss=2.329, over 2310.00 frames. , ppl: 10.268481513867666] tot_loss[loss=2.299, over 5495154.09 frames. , ppl: 9.960460152373257], batch size: 70
+2022-12-11 15:15:10,239 INFO [train.py:421] (7/8) Epoch 5, batch 17800, loss[loss=2.519, over 1050.00 frames. , ppl: 12.417700989663333] tot_loss[loss=2.298, over 5493051.37 frames. , ppl: 9.95794649290747], batch size: 70
+2022-12-11 15:16:49,288 INFO [train.py:421] (7/8) Epoch 5, batch 18000, loss[loss=2.288, over 1540.00 frames. , ppl: 9.859955304104107] tot_loss[loss=2.298, over 5502614.61 frames. , ppl: 9.951179469584387], batch size: 70
+2022-12-11 15:16:49,289 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 15:16:50,060 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.291, over 211138.00 frames. , ppl: 9.884169376428208
+2022-12-11 15:18:27,178 INFO [train.py:421] (7/8) Epoch 5, batch 18200, loss[loss=2.777, over 700.00 frames. , ppl: 16.07204013069831] tot_loss[loss=2.299, over 5477019.08 frames. , ppl: 9.966642153427621], batch size: 70
+2022-12-11 15:20:07,210 INFO [train.py:421] (7/8) Epoch 5, batch 18400, loss[loss=3.358, over 490.00 frames. , ppl: 28.726369231077754] tot_loss[loss=2.3, over 5455491.39 frames. , ppl: 9.969804088157963], batch size: 70
+2022-12-11 15:21:46,262 INFO [train.py:421] (7/8) Epoch 5, batch 18600, loss[loss=2.725, over 630.00 frames. , ppl: 15.261250904790248] tot_loss[loss=2.3, over 5416411.12 frames. , ppl: 9.973342221046996], batch size: 70
+2022-12-11 15:23:25,437 INFO [train.py:421] (7/8) Epoch 5, batch 18800, loss[loss=2.309, over 1400.00 frames. , ppl: 10.064368253524265] tot_loss[loss=2.298, over 5454823.09 frames. , ppl: 9.95833915574599], batch size: 70
+2022-12-11 15:25:02,769 INFO [train.py:421] (7/8) Epoch 5, batch 19000, loss[loss=2.534, over 910.00 frames. , ppl: 12.601923070322483] tot_loss[loss=2.299, over 5427551.31 frames. , ppl: 9.966455931794346], batch size: 70
+2022-12-11 15:25:02,770 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 15:25:03,528 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.292, over 211138.00 frames. , ppl: 9.892699015651312
+2022-12-11 15:26:43,247 INFO [train.py:421] (7/8) Epoch 5, batch 19200, loss[loss=2.227, over 3080.00 frames. , ppl: 9.274278590671903] tot_loss[loss=2.3, over 5412497.31 frames. , ppl: 9.977661528009968], batch size: 70
+2022-12-11 15:28:24,622 INFO [train.py:421] (7/8) Epoch 5, batch 19400, loss[loss=2.251, over 3290.00 frames. , ppl: 9.499904074911804] tot_loss[loss=2.299, over 5429337.68 frames. , ppl: 9.968802210924641], batch size: 70
+2022-12-11 15:30:03,435 INFO [train.py:421] (7/8) Epoch 5, batch 19600, loss[loss=2.281, over 2240.00 frames. , ppl: 9.787056926955163] tot_loss[loss=2.299, over 5420246.42 frames. , ppl: 9.96389330492337], batch size: 70
+2022-12-11 15:31:37,912 INFO [train.py:421] (7/8) Epoch 5, batch 19800, loss[loss=2.61, over 910.00 frames. , ppl: 13.605343677998851] tot_loss[loss=2.3, over 5389154.19 frames. , ppl: 9.972500295896559], batch size: 70
+2022-12-11 15:33:17,501 INFO [train.py:421] (7/8) Epoch 5, batch 20000, loss[loss=2.34, over 1890.00 frames. , ppl: 10.38595311059062] tot_loss[loss=2.3, over 5386332.91 frames. , ppl: 9.977615559469422], batch size: 70
+2022-12-11 15:33:17,501 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 15:33:18,262 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.292, over 211138.00 frames. , ppl: 9.897619928623687
+2022-12-11 15:34:59,004 INFO [train.py:421] (7/8) Epoch 5, batch 20200, loss[loss=2.207, over 6370.00 frames. , ppl: 9.085965066215017] tot_loss[loss=2.299, over 5452079.15 frames. , ppl: 9.960205430448108], batch size: 70
+2022-12-11 15:36:41,035 INFO [train.py:421] (7/8) Epoch 5, batch 20400, loss[loss=2.525, over 840.00 frames. , ppl: 12.494867551362763] tot_loss[loss=2.298, over 5467802.11 frames. , ppl: 9.956437250422969], batch size: 70
+2022-12-11 15:38:20,077 INFO [train.py:421] (7/8) Epoch 5, batch 20600, loss[loss=2.264, over 3010.00 frames. , ppl: 9.626265019335717] tot_loss[loss=2.298, over 5487225.28 frames. , ppl: 9.958204210289441], batch size: 70
+2022-12-11 15:40:02,095 INFO [train.py:421] (7/8) Epoch 5, batch 20800, loss[loss=2.27, over 2800.00 frames. , ppl: 9.679589866716201] tot_loss[loss=2.299, over 5451554.33 frames. , ppl: 9.965449103404916], batch size: 70
+2022-12-11 15:41:40,028 INFO [train.py:421] (7/8) Epoch 5, batch 21000, loss[loss=2.339, over 2870.00 frames. , ppl: 10.369283875096384] tot_loss[loss=2.3, over 5432039.88 frames. , ppl: 9.971425522550282], batch size: 70
+2022-12-11 15:41:40,028 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 15:41:40,786 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.289, over 211138.00 frames. , ppl: 9.8614396619666
+2022-12-11 15:43:22,021 INFO [train.py:421] (7/8) Epoch 5, batch 21200, loss[loss=2.194, over 5600.00 frames. , ppl: 8.969580759812736] tot_loss[loss=2.299, over 5458314.16 frames. , ppl: 9.967668548869325], batch size: 70
+2022-12-11 15:45:08,224 INFO [train.py:421] (7/8) Epoch 5, batch 21400, loss[loss=2.683, over 770.00 frames. , ppl: 14.626677101736275] tot_loss[loss=2.3, over 5433386.98 frames. , ppl: 9.9758083005698], batch size: 70
+2022-12-11 15:46:45,919 INFO [train.py:421] (7/8) Epoch 5, batch 21600, loss[loss=2.417, over 1750.00 frames. , ppl: 11.214863036358794] tot_loss[loss=2.301, over 5438356.71 frames. , ppl: 9.979463656554799], batch size: 70
+2022-12-11 15:48:20,256 INFO [train.py:421] (7/8) Epoch 5, batch 21800, loss[loss=2.319, over 1330.00 frames. , ppl: 10.169914239333874] tot_loss[loss=2.3, over 5451045.14 frames. , ppl: 9.97382037377052], batch size: 70
+2022-12-11 15:49:59,710 INFO [train.py:421] (7/8) Epoch 5, batch 22000, loss[loss=2.475, over 1260.00 frames. , ppl: 11.88470499221462] tot_loss[loss=2.3, over 5456023.17 frames. , ppl: 9.975540048225525], batch size: 70
+2022-12-11 15:49:59,710 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 15:50:00,468 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.291, over 211138.00 frames. , ppl: 9.884660933415132
+2022-12-11 15:51:45,368 INFO [train.py:421] (7/8) Epoch 5, batch 22200, loss[loss=2.314, over 4060.00 frames. , ppl: 10.117922177537402] tot_loss[loss=2.301, over 5467904.05 frames. , ppl: 9.980318630392302], batch size: 70
+2022-12-11 15:53:28,192 INFO [train.py:421] (7/8) Epoch 5, batch 22400, loss[loss=2.21, over 3010.00 frames. , ppl: 9.111572698439504] tot_loss[loss=2.3, over 5510308.50 frames. , ppl: 9.973535430952372], batch size: 70
+2022-12-11 15:55:07,006 INFO [train.py:421] (7/8) Epoch 5, batch 22600, loss[loss=2.453, over 1610.00 frames. , ppl: 11.627011018021463] tot_loss[loss=2.3, over 5504364.14 frames. , ppl: 9.970572531066951], batch size: 70
+2022-12-11 15:56:53,263 INFO [train.py:421] (7/8) Epoch 5, batch 22800, loss[loss=2.255, over 3500.00 frames. , ppl: 9.532324635278576] tot_loss[loss=2.299, over 5504077.48 frames. , ppl: 9.969058956258829], batch size: 70
+2022-12-11 15:58:36,998 INFO [train.py:421] (7/8) Epoch 5, batch 23000, loss[loss=2.294, over 1680.00 frames. , ppl: 9.910309845922844] tot_loss[loss=2.298, over 5531363.89 frames. , ppl: 9.953800909420893], batch size: 70
+2022-12-11 15:58:36,999 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 15:58:37,745 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.29, over 211138.00 frames. , ppl: 9.87439159731824
+2022-12-11 16:00:16,695 INFO [train.py:421] (7/8) Epoch 5, batch 23200, loss[loss=2.215, over 5810.00 frames. , ppl: 9.162994398705276] tot_loss[loss=2.297, over 5555438.99 frames. , ppl: 9.949003749185994], batch size: 70
+2022-12-11 16:01:54,226 INFO [train.py:421] (7/8) Epoch 5, batch 23400, loss[loss=2.154, over 4270.00 frames. , ppl: 8.620494937459037] tot_loss[loss=2.296, over 5594622.70 frames. , ppl: 9.937781730854029], batch size: 70
+2022-12-11 16:03:33,364 INFO [train.py:421] (7/8) Epoch 5, batch 23600, loss[loss=2.37, over 2730.00 frames. , ppl: 10.694815748650814] tot_loss[loss=2.297, over 5571673.91 frames. , ppl: 9.944882663024332], batch size: 70
+2022-12-11 16:05:15,465 INFO [train.py:421] (7/8) Epoch 5, batch 23800, loss[loss=2.442, over 980.00 frames. , ppl: 11.49057717971084] tot_loss[loss=2.296, over 5609578.83 frames. , ppl: 9.935976351122509], batch size: 70
+2022-12-11 16:06:54,575 INFO [train.py:421] (7/8) Epoch 5, batch 24000, loss[loss=2.411, over 1400.00 frames. , ppl: 11.147086383947668] tot_loss[loss=2.296, over 5624192.87 frames. , ppl: 9.93269748422013], batch size: 70
+2022-12-11 16:06:54,575 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 16:06:55,332 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.289, over 211138.00 frames. , ppl: 9.869746633606848
+2022-12-11 16:08:33,925 INFO [train.py:421] (7/8) Epoch 5, batch 24200, loss[loss=2.192, over 5180.00 frames. , ppl: 8.953975049534428] tot_loss[loss=2.295, over 5632443.53 frames. , ppl: 9.925074220028089], batch size: 70
+2022-12-11 16:10:16,217 INFO [train.py:421] (7/8) Epoch 5, batch 24400, loss[loss=2.619, over 1330.00 frames. , ppl: 13.726612793196688] tot_loss[loss=2.294, over 5643051.11 frames. , ppl: 9.918297741135957], batch size: 70
+2022-12-11 16:11:57,882 INFO [train.py:421] (7/8) Epoch 5, batch 24600, loss[loss=2.565, over 1050.00 frames. , ppl: 13.007086530074623] tot_loss[loss=2.296, over 5576820.73 frames. , ppl: 9.932956360402398], batch size: 70
+2022-12-11 16:13:31,672 INFO [train.py:421] (7/8) Epoch 5, batch 24800, loss[loss=2.511, over 1540.00 frames. , ppl: 12.32162133344259] tot_loss[loss=2.296, over 5543040.66 frames. , ppl: 9.93920722874788], batch size: 70
+2022-12-11 16:15:09,431 INFO [train.py:421] (7/8) Epoch 5, batch 25000, loss[loss=2.287, over 3290.00 frames. , ppl: 9.84668697193498] tot_loss[loss=2.296, over 5527230.61 frames. , ppl: 9.937830981462437], batch size: 70
+2022-12-11 16:15:09,431 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 16:15:10,164 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.289, over 211138.00 frames. , ppl: 9.867343916412231
+2022-12-11 16:16:49,416 INFO [train.py:421] (7/8) Epoch 5, batch 25200, loss[loss=2.321, over 980.00 frames. , ppl: 10.182334396573415] tot_loss[loss=2.295, over 5573818.70 frames. , ppl: 9.923741865172316], batch size: 70
+2022-12-11 16:18:26,296 INFO [train.py:421] (7/8) Epoch 5, batch 25400, loss[loss=2.463, over 1330.00 frames. , ppl: 11.741817438496305] tot_loss[loss=2.296, over 5534335.04 frames. , ppl: 9.938833724480576], batch size: 70
+2022-12-11 16:20:05,536 INFO [train.py:421] (7/8) Epoch 5, batch 25600, loss[loss=2.172, over 6650.00 frames. , ppl: 8.775963508385743] tot_loss[loss=2.298, over 5481704.85 frames. , ppl: 9.957148322230761], batch size: 70
+2022-12-11 16:21:46,553 INFO [train.py:421] (7/8) Epoch 5, batch 25800, loss[loss=2.281, over 5390.00 frames. , ppl: 9.789318601887176] tot_loss[loss=2.299, over 5477549.59 frames. , ppl: 9.961751001499978], batch size: 70
+2022-12-11 16:23:25,042 INFO [train.py:421] (7/8) Epoch 5, batch 26000, loss[loss=2.409, over 1890.00 frames. , ppl: 11.120182242631769] tot_loss[loss=2.298, over 5487171.92 frames. , ppl: 9.954722331346955], batch size: 70
+2022-12-11 16:23:25,043 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 16:23:25,801 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.289, over 211138.00 frames. , ppl: 9.864416167537827
+2022-12-11 16:25:05,334 INFO [train.py:421] (7/8) Epoch 5, batch 26200, loss[loss=2.998, over 560.00 frames. , ppl: 20.041819087409287] tot_loss[loss=2.299, over 5491099.95 frames. , ppl: 9.960609139179809], batch size: 70
+2022-12-11 16:26:45,413 INFO [train.py:421] (7/8) Epoch 5, batch 26400, loss[loss=2.23, over 3850.00 frames. , ppl: 9.295375751287866] tot_loss[loss=2.298, over 5512058.07 frames. , ppl: 9.957472987269892], batch size: 70
+2022-12-11 16:28:28,142 INFO [train.py:421] (7/8) Epoch 5, batch 26600, loss[loss=2.134, over 3220.00 frames. , ppl: 8.444506488524981] tot_loss[loss=2.298, over 5536110.84 frames. , ppl: 9.957532172901358], batch size: 70
+2022-12-11 16:30:12,514 INFO [train.py:421] (7/8) Epoch 5, batch 26800, loss[loss=2.341, over 2450.00 frames. , ppl: 10.390083084455807] tot_loss[loss=2.299, over 5542662.29 frames. , ppl: 9.959833821983002], batch size: 70
+2022-12-11 16:31:49,995 INFO [train.py:421] (7/8) Epoch 5, batch 27000, loss[loss=2.443, over 1820.00 frames. , ppl: 11.509294666121201] tot_loss[loss=2.299, over 5543287.93 frames. , ppl: 9.965253524406942], batch size: 70
+2022-12-11 16:31:49,995 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 16:31:50,754 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.29, over 211138.00 frames. , ppl: 9.875375224811005
+2022-12-11 16:33:32,097 INFO [train.py:421] (7/8) Epoch 5, batch 27200, loss[loss=2.209, over 5110.00 frames. , ppl: 9.10695720740745] tot_loss[loss=2.299, over 5558231.29 frames. , ppl: 9.959964952789655], batch size: 70
+2022-12-11 16:35:10,658 INFO [train.py:421] (7/8) Epoch 5, batch 27400, loss[loss=2.207, over 4060.00 frames. , ppl: 9.092092118112364] tot_loss[loss=2.298, over 5578379.84 frames. , ppl: 9.956032147451618], batch size: 70
+2022-12-11 16:36:49,938 INFO [train.py:421] (7/8) Epoch 5, batch 27600, loss[loss=2.282, over 2240.00 frames. , ppl: 9.80114969708106] tot_loss[loss=2.298, over 5562454.29 frames. , ppl: 9.953310904991719], batch size: 70
+2022-12-11 16:38:28,364 INFO [train.py:421] (7/8) Epoch 5, batch 27800, loss[loss=2.24, over 4480.00 frames. , ppl: 9.392191262010446] tot_loss[loss=2.298, over 5536852.69 frames. , ppl: 9.956282441220917], batch size: 70
+2022-12-11 16:40:08,914 INFO [train.py:421] (7/8) Epoch 5, batch 28000, loss[loss=2.341, over 1680.00 frames. , ppl: 10.389481124108551] tot_loss[loss=2.299, over 5537183.71 frames. , ppl: 9.9597382980395], batch size: 70
+2022-12-11 16:40:08,915 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 16:40:09,677 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.288, over 211138.00 frames. , ppl: 9.858846353025392
+2022-12-11 16:41:47,858 INFO [train.py:421] (7/8) Epoch 5, batch 28200, loss[loss=2.21, over 4410.00 frames. , ppl: 9.117266009197905] tot_loss[loss=2.299, over 5568141.91 frames. , ppl: 9.960264619986782], batch size: 70
+2022-12-11 16:43:28,938 INFO [train.py:421] (7/8) Epoch 5, batch 28400, loss[loss=2.294, over 3990.00 frames. , ppl: 9.919187779552765] tot_loss[loss=2.298, over 5574663.59 frames. , ppl: 9.95247432703665], batch size: 70
+2022-12-11 16:45:09,674 INFO [train.py:421] (7/8) Epoch 5, batch 28600, loss[loss=2.211, over 5670.00 frames. , ppl: 9.122673020444049] tot_loss[loss=2.298, over 5580876.44 frames. , ppl: 9.952119459504258], batch size: 70
+2022-12-11 16:46:50,656 INFO [train.py:421] (7/8) Epoch 5, batch 28800, loss[loss=2.471, over 1470.00 frames. , ppl: 11.829760387672003] tot_loss[loss=2.297, over 5591191.04 frames. , ppl: 9.947710700191724], batch size: 70
+2022-12-11 16:48:28,318 INFO [train.py:421] (7/8) Epoch 5, batch 29000, loss[loss=2.216, over 4620.00 frames. , ppl: 9.169756958405008] tot_loss[loss=2.297, over 5588637.30 frames. , ppl: 9.941432844108462], batch size: 70
+2022-12-11 16:48:28,319 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 16:48:29,078 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.289, over 211138.00 frames. , ppl: 9.86421176864417
+2022-12-11 16:50:05,475 INFO [train.py:421] (7/8) Epoch 5, batch 29200, loss[loss=2.2, over 6790.00 frames. , ppl: 9.02353259122789] tot_loss[loss=2.296, over 5589297.10 frames. , ppl: 9.938394628971189], batch size: 70
+2022-12-11 16:51:46,726 INFO [train.py:421] (7/8) Epoch 5, batch 29400, loss[loss=2.15, over 3430.00 frames. , ppl: 8.580657822943001] tot_loss[loss=2.297, over 5589523.29 frames. , ppl: 9.942795724134628], batch size: 70
+2022-12-11 16:53:26,109 INFO [train.py:421] (7/8) Epoch 5, batch 29600, loss[loss=2.446, over 1260.00 frames. , ppl: 11.545879153165146] tot_loss[loss=2.297, over 5543384.91 frames. , ppl: 9.947454140020875], batch size: 70
+2022-12-11 16:55:06,785 INFO [train.py:421] (7/8) Epoch 5, batch 29800, loss[loss=4.173, over 350.00 frames. , ppl: 64.881674614439] tot_loss[loss=2.297, over 5553461.55 frames. , ppl: 9.944791562715155], batch size: 70
+2022-12-11 16:56:46,813 INFO [train.py:421] (7/8) Epoch 5, batch 30000, loss[loss=2.261, over 4130.00 frames. , ppl: 9.59705957189029] tot_loss[loss=2.297, over 5551336.00 frames. , ppl: 9.942630383414448], batch size: 70
+2022-12-11 16:56:46,813 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 16:56:47,572 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.289, over 211138.00 frames. , ppl: 9.86519146183926
+2022-12-11 16:58:29,824 INFO [train.py:421] (7/8) Epoch 5, batch 30200, loss[loss=3.555, over 420.00 frames. , ppl: 34.98101554401414] tot_loss[loss=2.296, over 5600702.03 frames. , ppl: 9.930580021369428], batch size: 70
+2022-12-11 17:00:10,463 INFO [train.py:421] (7/8) Epoch 5, batch 30400, loss[loss=2.198, over 3220.00 frames. , ppl: 9.005968292935487] tot_loss[loss=2.296, over 5619521.42 frames. , ppl: 9.930442915511957], batch size: 70
+2022-12-11 17:01:51,075 INFO [train.py:421] (7/8) Epoch 5, batch 30600, loss[loss=2.389, over 1330.00 frames. , ppl: 10.898847026830124] tot_loss[loss=2.297, over 5584423.08 frames. , ppl: 9.943495909186227], batch size: 70
+2022-12-11 17:03:31,209 INFO [train.py:421] (7/8) Epoch 5, batch 30800, loss[loss=2.179, over 6090.00 frames. , ppl: 8.835519375591183] tot_loss[loss=2.297, over 5563801.54 frames. , ppl: 9.945709185772166], batch size: 70
+2022-12-11 17:05:13,224 INFO [train.py:421] (7/8) Epoch 5, batch 31000, loss[loss=2.374, over 1470.00 frames. , ppl: 10.739791505756028] tot_loss[loss=2.297, over 5557469.53 frames. , ppl: 9.945549768022437], batch size: 70
+2022-12-11 17:05:13,225 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 17:05:13,971 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.289, over 211138.00 frames. , ppl: 9.862906635580453
+2022-12-11 17:06:53,705 INFO [train.py:421] (7/8) Epoch 5, batch 31200, loss[loss=2.462, over 1330.00 frames. , ppl: 11.724361077092382] tot_loss[loss=2.296, over 5570786.46 frames. , ppl: 9.935560802534635], batch size: 70
+2022-12-11 17:08:34,076 INFO [train.py:421] (7/8) Epoch 5, batch 31400, loss[loss=2.239, over 4200.00 frames. , ppl: 9.38433714820839] tot_loss[loss=2.296, over 5586224.54 frames. , ppl: 9.935077300167416], batch size: 70
+2022-12-11 17:10:13,744 INFO [train.py:421] (7/8) Epoch 5, batch 31600, loss[loss=2.378, over 2310.00 frames. , ppl: 10.786906042797662] tot_loss[loss=2.295, over 5593342.00 frames. , ppl: 9.925975575862047], batch size: 70
+2022-12-11 17:11:57,205 INFO [train.py:421] (7/8) Epoch 5, batch 31800, loss[loss=3.492, over 420.00 frames. , ppl: 32.862406145536674] tot_loss[loss=2.296, over 5560999.74 frames. , ppl: 9.933661814447984], batch size: 70
+2022-12-11 17:13:39,189 INFO [train.py:421] (7/8) Epoch 5, batch 32000, loss[loss=2.398, over 1470.00 frames. , ppl: 10.999387666772034] tot_loss[loss=2.297, over 5537201.69 frames. , ppl: 9.939437287926355], batch size: 70
+2022-12-11 17:13:39,190 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 17:13:39,950 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.289, over 211138.00 frames. , ppl: 9.866756836775595
+2022-12-11 17:15:20,454 INFO [train.py:421] (7/8) Epoch 5, batch 32200, loss[loss=2.325, over 5320.00 frames. , ppl: 10.222802413980414] tot_loss[loss=2.297, over 5546566.62 frames. , ppl: 9.939678762637557], batch size: 70
+2022-12-11 17:17:01,709 INFO [train.py:421] (7/8) Epoch 5, batch 32400, loss[loss=2.28, over 4480.00 frames. , ppl: 9.7804775723523] tot_loss[loss=2.297, over 5540074.81 frames. , ppl: 9.941595383178559], batch size: 70
+2022-12-11 17:18:38,647 INFO [train.py:421] (7/8) Epoch 5, batch 32600, loss[loss=2.486, over 1190.00 frames. , ppl: 12.017242412782704] tot_loss[loss=2.297, over 5507838.61 frames. , ppl: 9.94502607777856], batch size: 70
+2022-12-11 17:20:17,509 INFO [train.py:421] (7/8) Epoch 5, batch 32800, loss[loss=2.209, over 4970.00 frames. , ppl: 9.108914672042873] tot_loss[loss=2.299, over 5470024.44 frames. , ppl: 9.96151065031435], batch size: 70
+2022-12-11 17:21:54,551 INFO [train.py:421] (7/8) Epoch 5, batch 33000, loss[loss=2.215, over 5180.00 frames. , ppl: 9.164423847087718] tot_loss[loss=2.299, over 5461733.08 frames. , ppl: 9.963296193108627], batch size: 70
+2022-12-11 17:21:54,551 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 17:21:55,298 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.29, over 211138.00 frames. , ppl: 9.874875360260138
+2022-12-11 17:23:34,426 INFO [train.py:421] (7/8) Epoch 5, batch 33200, loss[loss=2.333, over 2100.00 frames. , ppl: 10.310321298429887] tot_loss[loss=2.297, over 5549932.69 frames. , ppl: 9.942373467957296], batch size: 70
+2022-12-11 17:25:20,346 INFO [train.py:421] (7/8) Epoch 5, batch 33400, loss[loss=2.306, over 2590.00 frames. , ppl: 10.036816595815884] tot_loss[loss=2.297, over 5569223.92 frames. , ppl: 9.943271442710259], batch size: 70
+2022-12-11 17:27:01,195 INFO [train.py:421] (7/8) Epoch 5, batch 33600, loss[loss=2.241, over 4690.00 frames. , ppl: 9.399583644179577] tot_loss[loss=2.295, over 5627814.92 frames. , ppl: 9.925769307559943], batch size: 70
+2022-12-11 17:28:43,676 INFO [train.py:421] (7/8) Epoch 5, batch 33800, loss[loss=2.328, over 2450.00 frames. , ppl: 10.257686671948589] tot_loss[loss=2.295, over 5623040.40 frames. , ppl: 9.922796138228987], batch size: 70
+2022-12-11 17:30:21,119 INFO [train.py:421] (7/8) Epoch 5, batch 34000, loss[loss=2.25, over 2800.00 frames. , ppl: 9.488808032265139] tot_loss[loss=2.296, over 5588152.59 frames. , ppl: 9.931141772825224], batch size: 70
+2022-12-11 17:30:21,120 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 17:30:21,881 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.288, over 211138.00 frames. , ppl: 9.858973302750663
+2022-12-11 17:32:01,801 INFO [train.py:421] (7/8) Epoch 5, batch 34200, loss[loss=2.27, over 2730.00 frames. , ppl: 9.682429563055091] tot_loss[loss=2.297, over 5548871.50 frames. , ppl: 9.940789699492793], batch size: 70
+2022-12-11 17:33:39,864 INFO [train.py:421] (7/8) Epoch 5, batch 34400, loss[loss=2.264, over 4970.00 frames. , ppl: 9.622591237137156] tot_loss[loss=2.298, over 5497387.22 frames. , ppl: 9.949886480463029], batch size: 70
+2022-12-11 17:35:26,824 INFO [train.py:421] (7/8) Epoch 5, batch 34600, loss[loss=2.164, over 6440.00 frames. , ppl: 8.708350371951122] tot_loss[loss=2.297, over 5519495.26 frames. , ppl: 9.944594267376386], batch size: 70
+2022-12-11 17:37:05,658 INFO [train.py:421] (7/8) Epoch 5, batch 34800, loss[loss=2.292, over 1750.00 frames. , ppl: 9.899161492275836] tot_loss[loss=2.297, over 5504644.98 frames. , ppl: 9.948508109623107], batch size: 70
+2022-12-11 17:38:42,834 INFO [train.py:421] (7/8) Epoch 5, batch 35000, loss[loss=2.313, over 1470.00 frames. , ppl: 10.103648577936587] tot_loss[loss=2.297, over 5522230.62 frames. , ppl: 9.945128760408238], batch size: 70
+2022-12-11 17:38:42,834 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 17:38:43,595 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.289, over 211138.00 frames. , ppl: 9.860366938807065
+2022-12-11 17:40:23,339 INFO [train.py:421] (7/8) Epoch 5, batch 35200, loss[loss=2.302, over 1400.00 frames. , ppl: 9.990002285393674] tot_loss[loss=2.298, over 5512810.85 frames. , ppl: 9.953718368137665], batch size: 70
+2022-12-11 17:42:03,845 INFO [train.py:421] (7/8) Epoch 5, batch 35400, loss[loss=2.376, over 1330.00 frames. , ppl: 10.757411212522452] tot_loss[loss=2.298, over 5511615.52 frames. , ppl: 9.951803366753818], batch size: 70
+2022-12-11 17:44:04,292 INFO [train.py:421] (7/8) Epoch 5, batch 35600, loss[loss=2.808, over 630.00 frames. , ppl: 16.574998246955385] tot_loss[loss=2.298, over 5524811.07 frames. , ppl: 9.950069808230836], batch size: 70
+2022-12-11 17:45:45,025 INFO [train.py:421] (7/8) Epoch 5, batch 35800, loss[loss=2.331, over 2590.00 frames. , ppl: 10.284400602884636] tot_loss[loss=2.298, over 5494719.67 frames. , ppl: 9.956538196262567], batch size: 70
+2022-12-11 17:47:22,413 INFO [train.py:421] (7/8) Epoch 5, batch 36000, loss[loss=2.218, over 3360.00 frames. , ppl: 9.189152218165681] tot_loss[loss=2.299, over 5470450.11 frames. , ppl: 9.959530258485906], batch size: 70
+2022-12-11 17:47:22,414 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 17:47:23,172 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.287, over 211138.00 frames. , ppl: 9.84657788756117
+2022-12-11 17:49:05,398 INFO [train.py:421] (7/8) Epoch 5, batch 36200, loss[loss=2.209, over 2800.00 frames. , ppl: 9.105518107949553] tot_loss[loss=2.298, over 5494937.68 frames. , ppl: 9.951143208072715], batch size: 70
+2022-12-11 17:50:49,469 INFO [train.py:421] (7/8) Epoch 5, batch 36400, loss[loss=2.428, over 1680.00 frames. , ppl: 11.336205403412334] tot_loss[loss=2.297, over 5526144.91 frames. , ppl: 9.944576243979453], batch size: 70
+2022-12-11 17:52:28,496 INFO [train.py:421] (7/8) Epoch 5, batch 36600, loss[loss=2.349, over 9380.00 frames. , ppl: 10.479071967664696] tot_loss[loss=2.298, over 5530514.63 frames. , ppl: 9.955551535352877], batch size: 70
+2022-12-11 17:54:09,082 INFO [train.py:421] (7/8) Epoch 5, batch 36800, loss[loss=2.23, over 6230.00 frames. , ppl: 9.299734006555859] tot_loss[loss=2.297, over 5551224.83 frames. , ppl: 9.94667213056906], batch size: 70
+2022-12-11 17:55:52,424 INFO [train.py:421] (7/8) Epoch 5, batch 37000, loss[loss=2.282, over 3010.00 frames. , ppl: 9.796211446974958] tot_loss[loss=2.296, over 5584766.90 frames. , ppl: 9.931584914832602], batch size: 70
+2022-12-11 17:55:52,424 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 17:55:53,182 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.287, over 211138.00 frames. , ppl: 9.841108451353056
+2022-12-11 17:57:35,867 INFO [train.py:421] (7/8) Epoch 5, batch 37200, loss[loss=2.626, over 770.00 frames. , ppl: 13.815739941252373] tot_loss[loss=2.295, over 5599453.17 frames. , ppl: 9.929291837509522], batch size: 70
+2022-12-11 17:59:14,079 INFO [train.py:421] (7/8) Epoch 5, batch 37400, loss[loss=2.246, over 1820.00 frames. , ppl: 9.453835411693488] tot_loss[loss=2.296, over 5592671.71 frames. , ppl: 9.93503797500498], batch size: 70
+2022-12-11 18:00:54,462 INFO [train.py:421] (7/8) Epoch 5, batch 37600, loss[loss=2.313, over 3080.00 frames. , ppl: 10.109654217892476] tot_loss[loss=2.297, over 5541248.97 frames. , ppl: 9.946588451612634], batch size: 70
+2022-12-11 18:02:36,712 INFO [train.py:421] (7/8) Epoch 5, batch 37800, loss[loss=2.519, over 1050.00 frames. , ppl: 12.41732564630135] tot_loss[loss=2.297, over 5531863.13 frames. , ppl: 9.948260065517212], batch size: 70
+2022-12-11 18:04:14,229 INFO [train.py:421] (7/8) Epoch 5, batch 38000, loss[loss=2.33, over 1330.00 frames. , ppl: 10.280518284300824] tot_loss[loss=2.298, over 5517059.25 frames. , ppl: 9.949816350441479], batch size: 70
+2022-12-11 18:04:14,230 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 18:04:14,993 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.287, over 211138.00 frames. , ppl: 9.84971901441481
+2022-12-11 18:05:55,143 INFO [train.py:421] (7/8) Epoch 5, batch 38200, loss[loss=2.262, over 3780.00 frames. , ppl: 9.604505867316] tot_loss[loss=2.298, over 5492330.82 frames. , ppl: 9.954788766791893], batch size: 70
+2022-12-11 18:07:31,754 INFO [train.py:421] (7/8) Epoch 5, batch 38400, loss[loss=2.351, over 2240.00 frames. , ppl: 10.491779450101484] tot_loss[loss=2.299, over 5453765.56 frames. , ppl: 9.966160844152403], batch size: 70
+2022-12-11 18:09:11,040 INFO [train.py:421] (7/8) Epoch 5, batch 38600, loss[loss=2.399, over 2240.00 frames. , ppl: 11.007808787453191] tot_loss[loss=2.3, over 5404354.54 frames. , ppl: 9.976978903865446], batch size: 70
+2022-12-11 18:10:51,067 INFO [train.py:421] (7/8) Epoch 5, batch 38800, loss[loss=2.345, over 1120.00 frames. , ppl: 10.431486666454031] tot_loss[loss=2.299, over 5438716.36 frames. , ppl: 9.964174742628552], batch size: 70
+2022-12-11 18:12:31,787 INFO [train.py:421] (7/8) Epoch 5, batch 39000, loss[loss=2.449, over 1680.00 frames. , ppl: 11.573466005175163] tot_loss[loss=2.299, over 5412212.28 frames. , ppl: 9.964544527365305], batch size: 70
+2022-12-11 18:12:31,787 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 18:12:32,547 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.286, over 211138.00 frames. , ppl: 9.839695691985794
+2022-12-11 18:14:11,145 INFO [train.py:421] (7/8) Epoch 5, batch 39200, loss[loss=2.239, over 8120.00 frames. , ppl: 9.382380476193054] tot_loss[loss=2.301, over 5367435.08 frames. , ppl: 9.980045037536561], batch size: 70
+2022-12-11 18:15:49,011 INFO [train.py:421] (7/8) Epoch 5, batch 39400, loss[loss=2.339, over 2380.00 frames. , ppl: 10.367615533115135] tot_loss[loss=2.3, over 5386018.86 frames. , ppl: 9.975678276548043], batch size: 70
+2022-12-11 18:17:29,911 INFO [train.py:421] (7/8) Epoch 5, batch 39600, loss[loss=2.438, over 1330.00 frames. , ppl: 11.445717534201966] tot_loss[loss=2.301, over 5355636.80 frames. , ppl: 9.98590726209966], batch size: 70
+2022-12-11 18:19:09,420 INFO [train.py:421] (7/8) Epoch 5, batch 39800, loss[loss=2.304, over 3570.00 frames. , ppl: 10.014776222653865] tot_loss[loss=2.3, over 5389384.55 frames. , ppl: 9.975192692514456], batch size: 70
+2022-12-11 18:20:46,138 INFO [train.py:421] (7/8) Epoch 5, batch 40000, loss[loss=2.512, over 980.00 frames. , ppl: 12.324442339982784] tot_loss[loss=2.301, over 5375010.98 frames. , ppl: 9.97960352034496], batch size: 70
+2022-12-11 18:20:46,139 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 18:20:46,898 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.289, over 211138.00 frames. , ppl: 9.863040936604593
+2022-12-11 18:22:26,598 INFO [train.py:421] (7/8) Epoch 5, batch 40200, loss[loss=2.261, over 6510.00 frames. , ppl: 9.59586402834719] tot_loss[loss=2.302, over 5352964.16 frames. , ppl: 9.989952727756156], batch size: 70
+2022-12-11 18:24:04,875 INFO [train.py:421] (7/8) Epoch 5, batch 40400, loss[loss=2.46, over 1540.00 frames. , ppl: 11.706633136125308] tot_loss[loss=2.302, over 5361773.88 frames. , ppl: 9.991283309883546], batch size: 70
+2022-12-11 18:25:44,574 INFO [train.py:421] (7/8) Epoch 5, batch 40600, loss[loss=2.408, over 1540.00 frames. , ppl: 11.109445534444033] tot_loss[loss=2.302, over 5367071.31 frames. , ppl: 9.994522396170721], batch size: 70
+2022-12-11 18:27:25,886 INFO [train.py:421] (7/8) Epoch 5, batch 40800, loss[loss=2.746, over 840.00 frames. , ppl: 15.573284766672414] tot_loss[loss=2.303, over 5341222.24 frames. , ppl: 10.000658189204444], batch size: 70
+2022-12-11 18:29:07,904 INFO [train.py:421] (7/8) Epoch 5, batch 41000, loss[loss=2.239, over 4620.00 frames. , ppl: 9.38299789371464] tot_loss[loss=2.303, over 5342516.91 frames. , ppl: 10.001425975398027], batch size: 70
+2022-12-11 18:29:07,905 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 18:29:08,657 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.287, over 211138.00 frames. , ppl: 9.844880201345818
+2022-12-11 18:30:49,881 INFO [train.py:421] (7/8) Epoch 5, batch 41200, loss[loss=2.29, over 6440.00 frames. , ppl: 9.873556541943143] tot_loss[loss=2.303, over 5330784.85 frames. , ppl: 10.0082031699569], batch size: 70
+2022-12-11 18:32:28,300 INFO [train.py:421] (7/8) Epoch 5, batch 41400, loss[loss=2.515, over 840.00 frames. , ppl: 12.364166350563508] tot_loss[loss=2.304, over 5309749.14 frames. , ppl: 10.016047081669184], batch size: 70
+2022-12-11 18:34:08,975 INFO [train.py:421] (7/8) Epoch 5, batch 41600, loss[loss=2.52, over 1890.00 frames. , ppl: 12.423773504001161] tot_loss[loss=2.304, over 5319995.67 frames. , ppl: 10.014247578113867], batch size: 70
+2022-12-11 18:35:50,123 INFO [train.py:421] (7/8) Epoch 5, batch 41800, loss[loss=2.384, over 2240.00 frames. , ppl: 10.851090400557592] tot_loss[loss=2.304, over 5287790.57 frames. , ppl: 10.016535182191184], batch size: 70
+2022-12-11 18:37:33,725 INFO [train.py:421] (7/8) Epoch 5, batch 42000, loss[loss=2.422, over 1470.00 frames. , ppl: 11.272370521087465] tot_loss[loss=2.304, over 5318734.76 frames. , ppl: 10.009523189551215], batch size: 70
+2022-12-11 18:37:33,726 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 18:37:34,472 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.285, over 211138.00 frames. , ppl: 9.829064270772456
+2022-12-11 18:39:16,853 INFO [train.py:421] (7/8) Epoch 5, batch 42200, loss[loss=2.43, over 1750.00 frames. , ppl: 11.35866339827183] tot_loss[loss=2.302, over 5360847.97 frames. , ppl: 9.989634363041217], batch size: 70
+2022-12-11 18:40:58,488 INFO [train.py:421] (7/8) Epoch 5, batch 42400, loss[loss=2.199, over 4200.00 frames. , ppl: 9.017575462692665] tot_loss[loss=2.3, over 5398534.70 frames. , ppl: 9.977448509815883], batch size: 70
+2022-12-11 18:42:36,706 INFO [train.py:421] (7/8) Epoch 5, batch 42600, loss[loss=3.201, over 560.00 frames. , ppl: 24.56816081489141] tot_loss[loss=2.3, over 5406932.31 frames. , ppl: 9.973476768133978], batch size: 70
+2022-12-11 18:44:18,978 INFO [train.py:421] (7/8) Epoch 5, batch 42800, loss[loss=2.574, over 980.00 frames. , ppl: 13.11279170057662] tot_loss[loss=2.3, over 5419019.55 frames. , ppl: 9.972693327479154], batch size: 70
+2022-12-11 18:45:56,835 INFO [train.py:421] (7/8) Epoch 5, batch 43000, loss[loss=2.224, over 4480.00 frames. , ppl: 9.245607367740378] tot_loss[loss=2.3, over 5421259.52 frames. , ppl: 9.973399589300634], batch size: 70
+2022-12-11 18:45:56,836 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 18:45:57,597 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.287, over 211138.00 frames. , ppl: 9.842544721854633
+2022-12-11 18:47:37,852 INFO [train.py:421] (7/8) Epoch 5, batch 43200, loss[loss=2.215, over 5390.00 frames. , ppl: 9.163513401931965] tot_loss[loss=2.299, over 5458854.84 frames. , ppl: 9.963519104922016], batch size: 70
+2022-12-11 18:49:19,128 INFO [train.py:421] (7/8) Epoch 5, batch 43400, loss[loss=2.626, over 840.00 frames. , ppl: 13.823195369305445] tot_loss[loss=2.299, over 5437825.64 frames. , ppl: 9.961552521161574], batch size: 70
+2022-12-11 18:51:01,642 INFO [train.py:421] (7/8) Epoch 5, batch 43600, loss[loss=2.462, over 1610.00 frames. , ppl: 11.728922703952742] tot_loss[loss=2.297, over 5504657.65 frames. , ppl: 9.945843106827892], batch size: 70
+2022-12-11 18:52:42,486 INFO [train.py:421] (7/8) Epoch 5, batch 43800, loss[loss=2.31, over 4270.00 frames. , ppl: 10.077939409267374] tot_loss[loss=2.297, over 5470578.56 frames. , ppl: 9.949229678948008], batch size: 70
+2022-12-11 18:54:22,155 INFO [train.py:421] (7/8) Epoch 5, batch 44000, loss[loss=3.231, over 490.00 frames. , ppl: 25.300231258706653] tot_loss[loss=2.298, over 5446191.65 frames. , ppl: 9.9551468081966], batch size: 70
+2022-12-11 18:54:22,156 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 18:54:22,915 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.287, over 211138.00 frames. , ppl: 9.849284590078504
+2022-12-11 18:56:01,422 INFO [train.py:421] (7/8) Epoch 5, batch 44200, loss[loss=2.302, over 910.00 frames. , ppl: 9.9913124441422] tot_loss[loss=2.296, over 5498462.99 frames. , ppl: 9.935470740028613], batch size: 70
+2022-12-11 18:57:41,945 INFO [train.py:421] (7/8) Epoch 5, batch 44400, loss[loss=2.252, over 3640.00 frames. , ppl: 9.503084456743014] tot_loss[loss=2.296, over 5511343.86 frames. , ppl: 9.937084581776217], batch size: 70
+2022-12-11 18:59:21,018 INFO [train.py:421] (7/8) Epoch 5, batch 44600, loss[loss=2.358, over 1750.00 frames. , ppl: 10.570056145082326] tot_loss[loss=2.296, over 5531879.01 frames. , ppl: 9.938348174244448], batch size: 70
+2022-12-11 19:01:02,199 INFO [train.py:421] (7/8) Epoch 5, batch 44800, loss[loss=2.423, over 1750.00 frames. , ppl: 11.284898339718392] tot_loss[loss=2.297, over 5513519.29 frames. , ppl: 9.943816501686769], batch size: 70
+2022-12-11 19:02:40,863 INFO [train.py:421] (7/8) Epoch 5, batch 45000, loss[loss=2.653, over 770.00 frames. , ppl: 14.202729140068504] tot_loss[loss=2.297, over 5511273.13 frames. , ppl: 9.94327253134811], batch size: 70
+2022-12-11 19:02:40,863 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 19:02:41,620 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.286, over 211138.00 frames. , ppl: 9.835643508977666
+2022-12-11 19:04:22,576 INFO [train.py:421] (7/8) Epoch 5, batch 45200, loss[loss=2.3, over 2170.00 frames. , ppl: 9.97413307957376] tot_loss[loss=2.296, over 5534706.41 frames. , ppl: 9.9357335278557], batch size: 70
+2022-12-11 19:06:01,354 INFO [train.py:421] (7/8) Epoch 5, batch 45400, loss[loss=2.223, over 3570.00 frames. , ppl: 9.231066567166303] tot_loss[loss=2.297, over 5518044.49 frames. , ppl: 9.940599567990398], batch size: 70
+2022-12-11 19:07:43,220 INFO [train.py:421] (7/8) Epoch 5, batch 45600, loss[loss=2.385, over 2030.00 frames. , ppl: 10.854930287540066] tot_loss[loss=2.297, over 5513559.72 frames. , ppl: 9.944635437191508], batch size: 70
+2022-12-11 19:09:21,551 INFO [train.py:421] (7/8) Epoch 5, batch 45800, loss[loss=2.162, over 5600.00 frames. , ppl: 8.691299561623339] tot_loss[loss=2.298, over 5492227.53 frames. , ppl: 9.950118180249193], batch size: 70
+2022-12-11 19:11:03,176 INFO [train.py:421] (7/8) Epoch 5, batch 46000, loss[loss=2.226, over 9310.00 frames. , ppl: 9.265775307779565] tot_loss[loss=2.296, over 5531213.68 frames. , ppl: 9.9318645506862], batch size: 70
+2022-12-11 19:11:03,177 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 19:11:03,906 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.285, over 211138.00 frames. , ppl: 9.824885591047718
+2022-12-11 19:12:44,282 INFO [train.py:421] (7/8) Epoch 5, batch 46200, loss[loss=2.828, over 630.00 frames. , ppl: 16.919309753841866] tot_loss[loss=2.296, over 5534369.86 frames. , ppl: 9.934192128943224], batch size: 70
+2022-12-11 19:14:23,631 INFO [train.py:421] (7/8) Epoch 5, batch 46400, loss[loss=2.235, over 3360.00 frames. , ppl: 9.350578137653656] tot_loss[loss=2.296, over 5533441.92 frames. , ppl: 9.935949905842149], batch size: 70
+2022-12-11 19:15:58,262 INFO [train.py:421] (7/8) Epoch 5, batch 46600, loss[loss=2.523, over 980.00 frames. , ppl: 12.460036676219778] tot_loss[loss=2.296, over 5494442.78 frames. , ppl: 9.937578859149257], batch size: 70
+2022-12-11 19:17:38,453 INFO [train.py:421] (7/8) Epoch 5, batch 46800, loss[loss=2.219, over 3360.00 frames. , ppl: 9.197940574923628] tot_loss[loss=2.296, over 5483894.09 frames. , ppl: 9.938610586844467], batch size: 70
+2022-12-11 19:19:20,572 INFO [train.py:421] (7/8) Epoch 5, batch 47000, loss[loss=2.464, over 1260.00 frames. , ppl: 11.755847994676692] tot_loss[loss=2.296, over 5517169.36 frames. , ppl: 9.930529789689901], batch size: 70
+2022-12-11 19:19:20,573 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 19:19:21,331 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.286, over 211138.00 frames. , ppl: 9.837504131725721
+2022-12-11 19:21:03,346 INFO [train.py:421] (7/8) Epoch 5, batch 47200, loss[loss=2.427, over 980.00 frames. , ppl: 11.322517444058969] tot_loss[loss=2.295, over 5536196.13 frames. , ppl: 9.92848786239457], batch size: 70
+2022-12-11 19:22:43,310 INFO [train.py:421] (7/8) Epoch 5, batch 47400, loss[loss=2.288, over 3850.00 frames. , ppl: 9.854739591265194] tot_loss[loss=2.295, over 5549059.31 frames. , ppl: 9.927367549255928], batch size: 70
+2022-12-11 19:24:25,850 INFO [train.py:421] (7/8) Epoch 5, batch 47600, loss[loss=2.33, over 1330.00 frames. , ppl: 10.277691741770333] tot_loss[loss=2.296, over 5527407.92 frames. , ppl: 9.931714717218034], batch size: 70
+2022-12-11 19:26:04,800 INFO [train.py:421] (7/8) Epoch 5, batch 47800, loss[loss=2.365, over 1540.00 frames. , ppl: 10.640499852673937] tot_loss[loss=2.297, over 5486013.15 frames. , ppl: 9.945978021335684], batch size: 70
+2022-12-11 19:27:44,284 INFO [train.py:421] (7/8) Epoch 5, batch 48000, loss[loss=2.178, over 8960.00 frames. , ppl: 8.825613166727386] tot_loss[loss=2.296, over 5508676.95 frames. , ppl: 9.93730527645224], batch size: 70
+2022-12-11 19:27:44,284 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 19:27:45,017 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.287, over 211138.00 frames. , ppl: 9.847490241584369
+2022-12-11 19:29:31,078 INFO [train.py:421] (7/8) Epoch 5, batch 48200, loss[loss=2.209, over 4690.00 frames. , ppl: 9.102705512836891] tot_loss[loss=2.297, over 5485356.72 frames. , ppl: 9.94775281241485], batch size: 70
+2022-12-11 19:31:11,713 INFO [train.py:421] (7/8) Epoch 5, batch 48400, loss[loss=2.248, over 3220.00 frames. , ppl: 9.47293144364918] tot_loss[loss=2.298, over 5458595.17 frames. , ppl: 9.954364987180877], batch size: 70
+2022-12-11 19:32:50,746 INFO [train.py:421] (7/8) Epoch 5, batch 48600, loss[loss=2.271, over 3430.00 frames. , ppl: 9.691259849246286] tot_loss[loss=2.298, over 5473692.01 frames. , ppl: 9.952378326746775], batch size: 70
+2022-12-11 19:34:30,309 INFO [train.py:421] (7/8) Epoch 5, batch 48800, loss[loss=2.269, over 1890.00 frames. , ppl: 9.671873219247512] tot_loss[loss=2.297, over 5506448.10 frames. , ppl: 9.947118029026482], batch size: 70
+2022-12-11 19:36:12,833 INFO [train.py:421] (7/8) Epoch 5, batch 49000, loss[loss=2.578, over 910.00 frames. , ppl: 13.172176400744897] tot_loss[loss=2.297, over 5528726.84 frames. , ppl: 9.941293877741085], batch size: 70
+2022-12-11 19:36:12,833 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 19:36:13,593 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.288, over 211138.00 frames. , ppl: 9.8508430669708
+2022-12-11 19:37:58,714 INFO [train.py:421] (7/8) Epoch 5, batch 49200, loss[loss=2.357, over 2310.00 frames. , ppl: 10.554914549151054] tot_loss[loss=2.296, over 5527871.51 frames. , ppl: 9.937788630819083], batch size: 70
+2022-12-11 19:39:40,034 INFO [train.py:421] (7/8) Epoch 5, batch 49400, loss[loss=2.418, over 1470.00 frames. , ppl: 11.226931940561549] tot_loss[loss=2.296, over 5550496.30 frames. , ppl: 9.93487932239173], batch size: 70
+2022-12-11 19:41:17,703 INFO [train.py:421] (7/8) Epoch 5, batch 49600, loss[loss=2.517, over 1400.00 frames. , ppl: 12.39116189638196] tot_loss[loss=2.296, over 5535334.42 frames. , ppl: 9.938935000231933], batch size: 70
+2022-12-11 19:42:57,230 INFO [train.py:421] (7/8) Epoch 5, batch 49800, loss[loss=2.295, over 2100.00 frames. , ppl: 9.922451692697203] tot_loss[loss=2.296, over 5587089.50 frames. , ppl: 9.935727252863686], batch size: 70
+2022-12-11 19:44:39,906 INFO [train.py:421] (7/8) Epoch 5, batch 50000, loss[loss=2.481, over 1540.00 frames. , ppl: 11.957432437869127] tot_loss[loss=2.295, over 5589411.24 frames. , ppl: 9.92506407540681], batch size: 70
+2022-12-11 19:44:39,907 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 19:44:40,663 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.286, over 211138.00 frames. , ppl: 9.837191091537502
+2022-12-11 19:46:20,686 INFO [train.py:421] (7/8) Epoch 5, batch 50200, loss[loss=3.167, over 490.00 frames. , ppl: 23.73981554278452] tot_loss[loss=2.295, over 5581848.66 frames. , ppl: 9.924919331816838], batch size: 70
+2022-12-11 19:48:00,104 INFO [train.py:421] (7/8) Epoch 5, batch 50400, loss[loss=2.237, over 8400.00 frames. , ppl: 9.362823343801951] tot_loss[loss=2.296, over 5560499.15 frames. , ppl: 9.931270853301076], batch size: 70
+2022-12-11 19:49:38,978 INFO [train.py:421] (7/8) Epoch 5, batch 50600, loss[loss=2.194, over 4760.00 frames. , ppl: 8.9722430054024] tot_loss[loss=2.296, over 5543818.62 frames. , ppl: 9.933442043714985], batch size: 70
+2022-12-11 19:51:17,598 INFO [train.py:421] (7/8) Epoch 5, batch 50800, loss[loss=2.182, over 5600.00 frames. , ppl: 8.865745215053632] tot_loss[loss=2.297, over 5512129.58 frames. , ppl: 9.941590951392225], batch size: 70
+2022-12-11 19:52:59,293 INFO [train.py:421] (7/8) Epoch 5, batch 51000, loss[loss=2.141, over 7840.00 frames. , ppl: 8.509884550130138] tot_loss[loss=2.297, over 5504710.85 frames. , ppl: 9.945857103349693], batch size: 70
+2022-12-11 19:52:59,293 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 19:53:00,024 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.288, over 211138.00 frames. , ppl: 9.852051821719042
+2022-12-11 19:54:41,943 INFO [train.py:421] (7/8) Epoch 5, batch 51200, loss[loss=2.348, over 1400.00 frames. , ppl: 10.468954176420938] tot_loss[loss=2.297, over 5524143.48 frames. , ppl: 9.948726410566108], batch size: 70
+2022-12-11 19:56:21,647 INFO [train.py:421] (7/8) Epoch 5, batch 51400, loss[loss=2.384, over 2170.00 frames. , ppl: 10.842902513150634] tot_loss[loss=2.297, over 5509366.60 frames. , ppl: 9.946895202119139], batch size: 70
+2022-12-11 19:58:02,207 INFO [train.py:421] (7/8) Epoch 5, batch 51600, loss[loss=2.448, over 1470.00 frames. , ppl: 11.561191453571954] tot_loss[loss=2.296, over 5517709.95 frames. , ppl: 9.937680281326468], batch size: 70
+2022-12-11 19:59:40,710 INFO [train.py:421] (7/8) Epoch 5, batch 51800, loss[loss=2.417, over 2240.00 frames. , ppl: 11.211065579410208] tot_loss[loss=2.297, over 5483839.25 frames. , ppl: 9.947100534871282], batch size: 70
+2022-12-11 20:01:19,072 INFO [train.py:421] (7/8) Epoch 5, batch 52000, loss[loss=2.588, over 980.00 frames. , ppl: 13.299500164245735] tot_loss[loss=2.298, over 5452314.17 frames. , ppl: 9.957526513224902], batch size: 70
+2022-12-11 20:01:19,073 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 20:01:19,832 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.286, over 211138.00 frames. , ppl: 9.840256402098536
+2022-12-11 20:03:00,930 INFO [train.py:421] (7/8) Epoch 5, batch 52200, loss[loss=2.378, over 1960.00 frames. , ppl: 10.788134438202897] tot_loss[loss=2.299, over 5414067.96 frames. , ppl: 9.96737426103408], batch size: 70
+2022-12-11 20:04:40,909 INFO [train.py:421] (7/8) Epoch 5, batch 52400, loss[loss=2.32, over 1890.00 frames. , ppl: 10.177676661196756] tot_loss[loss=2.299, over 5419216.23 frames. , ppl: 9.965123571764359], batch size: 70
+2022-12-11 20:06:20,202 INFO [train.py:421] (7/8) Epoch 5, batch 52600, loss[loss=2.359, over 1540.00 frames. , ppl: 10.578466281801083] tot_loss[loss=2.3, over 5400473.39 frames. , ppl: 9.969577497866236], batch size: 70
+2022-12-11 20:07:55,989 INFO [train.py:421] (7/8) Epoch 5, batch 52800, loss[loss=2.306, over 2870.00 frames. , ppl: 10.037091983434783] tot_loss[loss=2.299, over 5425835.15 frames. , ppl: 9.961316031793826], batch size: 70
+2022-12-11 20:09:33,201 INFO [train.py:421] (7/8) Epoch 5, batch 53000, loss[loss=2.357, over 1820.00 frames. , ppl: 10.558037819748472] tot_loss[loss=2.299, over 5414423.12 frames. , ppl: 9.96442705218105], batch size: 70
+2022-12-11 20:09:33,202 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 20:09:33,930 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.287, over 211138.00 frames. , ppl: 9.842675832035669
+2022-12-11 20:11:15,344 INFO [train.py:421] (7/8) Epoch 5, batch 53200, loss[loss=2.333, over 1750.00 frames. , ppl: 10.30768268483929] tot_loss[loss=2.299, over 5412626.57 frames. , ppl: 9.965385227782791], batch size: 70
+2022-12-11 20:12:50,608 INFO [train.py:421] (7/8) Epoch 5, batch 53400, loss[loss=2.383, over 1540.00 frames. , ppl: 10.835454671198798] tot_loss[loss=2.298, over 5406042.69 frames. , ppl: 9.958885232503546], batch size: 70
+2022-12-11 20:14:31,570 INFO [train.py:421] (7/8) Epoch 5, batch 53600, loss[loss=2.851, over 630.00 frames. , ppl: 17.297116685727683] tot_loss[loss=2.298, over 5414989.16 frames. , ppl: 9.954093950389842], batch size: 70
+2022-12-11 20:16:11,457 INFO [train.py:421] (7/8) Epoch 5, batch 53800, loss[loss=2.458, over 1610.00 frames. , ppl: 11.686291435463657] tot_loss[loss=2.297, over 5435459.20 frames. , ppl: 9.947325463007514], batch size: 70
+2022-12-11 20:17:55,394 INFO [train.py:421] (7/8) Epoch 5, batch 54000, loss[loss=2.193, over 7630.00 frames. , ppl: 8.966464583393378] tot_loss[loss=2.296, over 5468973.45 frames. , ppl: 9.938644441336319], batch size: 70
+2022-12-11 20:17:55,394 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 20:17:56,155 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.286, over 211138.00 frames. , ppl: 9.832751361696745
+2022-12-11 20:19:35,175 INFO [train.py:421] (7/8) Epoch 5, batch 54200, loss[loss=2.266, over 3150.00 frames. , ppl: 9.64060632063689] tot_loss[loss=2.298, over 5421367.35 frames. , ppl: 9.950073453181442], batch size: 70
+2022-12-11 20:21:11,753 INFO [train.py:421] (7/8) Epoch 5, batch 54400, loss[loss=2.325, over 1610.00 frames. , ppl: 10.230086155206553] tot_loss[loss=2.297, over 5430222.13 frames. , ppl: 9.948754230755858], batch size: 70
+2022-12-11 20:22:53,113 INFO [train.py:421] (7/8) Epoch 5, batch 54600, loss[loss=2.452, over 1750.00 frames. , ppl: 11.612505633756475] tot_loss[loss=2.298, over 5422061.38 frames. , ppl: 9.954839161997498], batch size: 70
+2022-12-11 20:24:36,518 INFO [train.py:421] (7/8) Epoch 5, batch 54800, loss[loss=2.56, over 1190.00 frames. , ppl: 12.929657984731799] tot_loss[loss=2.298, over 5458859.13 frames. , ppl: 9.952600631815972], batch size: 70
+2022-12-11 20:26:21,051 INFO [train.py:421] (7/8) Epoch 5, batch 55000, loss[loss=2.616, over 770.00 frames. , ppl: 13.682067223347048] tot_loss[loss=2.297, over 5460801.60 frames. , ppl: 9.942720913495567], batch size: 70
+2022-12-11 20:26:21,051 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 20:26:21,809 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.286, over 211138.00 frames. , ppl: 9.833813803126963
+2022-12-11 20:27:59,954 INFO [train.py:421] (7/8) Epoch 5, batch 55200, loss[loss=2.34, over 1890.00 frames. , ppl: 10.379260659759357] tot_loss[loss=2.295, over 5519081.02 frames. , ppl: 9.929360005151777], batch size: 70
+2022-12-11 20:29:36,235 INFO [train.py:421] (7/8) Epoch 5, batch 55400, loss[loss=2.194, over 5670.00 frames. , ppl: 8.974211320772099] tot_loss[loss=2.295, over 5502215.70 frames. , ppl: 9.928490463745991], batch size: 70
+2022-12-11 20:31:18,004 INFO [train.py:421] (7/8) Epoch 5, batch 55600, loss[loss=2.435, over 1540.00 frames. , ppl: 11.412242419449072] tot_loss[loss=2.297, over 5484061.60 frames. , ppl: 9.942008249254878], batch size: 70
+2022-12-11 20:32:57,833 INFO [train.py:421] (7/8) Epoch 5, batch 55800, loss[loss=2.339, over 2100.00 frames. , ppl: 10.37163411441984] tot_loss[loss=2.297, over 5458572.87 frames. , ppl: 9.946078847628279], batch size: 70
+2022-12-11 20:34:40,845 INFO [train.py:421] (7/8) Epoch 5, batch 56000, loss[loss=2.395, over 1960.00 frames. , ppl: 10.967980559700987] tot_loss[loss=2.298, over 5435154.30 frames. , ppl: 9.952820630309763], batch size: 70
+2022-12-11 20:34:40,846 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 20:34:41,592 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.286, over 211138.00 frames. , ppl: 9.835016101318848
+2022-12-11 20:36:19,909 INFO [train.py:421] (7/8) Epoch 5, batch 56200, loss[loss=2.305, over 3780.00 frames. , ppl: 10.025614109948448] tot_loss[loss=2.297, over 5465813.18 frames. , ppl: 9.941844223474664], batch size: 70
+2022-12-11 20:38:00,525 INFO [train.py:421] (7/8) Epoch 5, batch 56400, loss[loss=2.433, over 1120.00 frames. , ppl: 11.387492540908752] tot_loss[loss=2.295, over 5526907.81 frames. , ppl: 9.923827171963888], batch size: 70
+2022-12-11 20:39:43,938 INFO [train.py:421] (7/8) Epoch 5, batch 56600, loss[loss=2.456, over 2170.00 frames. , ppl: 11.66201880834408] tot_loss[loss=2.295, over 5541990.12 frames. , ppl: 9.92292743780287], batch size: 70
+2022-12-11 20:41:26,617 INFO [train.py:421] (7/8) Epoch 5, batch 56800, loss[loss=2.545, over 770.00 frames. , ppl: 12.739061456411017] tot_loss[loss=2.294, over 5550801.79 frames. , ppl: 9.918838974318987], batch size: 70
+2022-12-11 20:43:05,304 INFO [train.py:421] (7/8) Epoch 5, batch 57000, loss[loss=2.176, over 3780.00 frames. , ppl: 8.808916589127346] tot_loss[loss=2.295, over 5516454.38 frames. , ppl: 9.926397660630577], batch size: 70
+2022-12-11 20:43:05,304 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 20:43:06,065 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.287, over 211138.00 frames. , ppl: 9.842181992787078
+2022-12-11 20:44:43,548 INFO [train.py:421] (7/8) Epoch 5, batch 57200, loss[loss=2.395, over 1680.00 frames. , ppl: 10.967962799263747] tot_loss[loss=2.296, over 5513188.95 frames. , ppl: 9.935684126388972], batch size: 70
+2022-12-11 20:46:22,291 INFO [train.py:421] (7/8) Epoch 5, batch 57400, loss[loss=2.685, over 770.00 frames. , ppl: 14.6557792442119] tot_loss[loss=2.296, over 5501027.75 frames. , ppl: 9.93649839661216], batch size: 70
+2022-12-11 20:48:03,947 INFO [train.py:421] (7/8) Epoch 5, batch 57600, loss[loss=2.204, over 4760.00 frames. , ppl: 9.065049738635599] tot_loss[loss=2.296, over 5503528.26 frames. , ppl: 9.931136444580538], batch size: 70
+2022-12-11 20:49:40,764 INFO [train.py:421] (7/8) Epoch 5, batch 57800, loss[loss=2.258, over 2800.00 frames. , ppl: 9.562295812487017] tot_loss[loss=2.295, over 5513204.74 frames. , ppl: 9.920915763550312], batch size: 70
+2022-12-11 20:51:22,001 INFO [train.py:421] (7/8) Epoch 5, batch 58000, loss[loss=2.214, over 7560.00 frames. , ppl: 9.152155149222192] tot_loss[loss=2.293, over 5583172.03 frames. , ppl: 9.908302491347234], batch size: 70
+2022-12-11 20:51:22,002 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 20:51:22,729 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.287, over 211138.00 frames. , ppl: 9.846384059654563
+2022-12-11 20:53:06,174 INFO [train.py:421] (7/8) Epoch 5, batch 58200, loss[loss=2.311, over 2240.00 frames. , ppl: 10.08016632681918] tot_loss[loss=2.293, over 5580832.86 frames. , ppl: 9.904736159692078], batch size: 70
+2022-12-11 20:54:48,427 INFO [train.py:421] (7/8) Epoch 5, batch 58400, loss[loss=2.23, over 5880.00 frames. , ppl: 9.303251402413526] tot_loss[loss=2.292, over 5588338.62 frames. , ppl: 9.898041677120329], batch size: 70
+2022-12-11 20:56:30,698 INFO [train.py:421] (7/8) Epoch 5, batch 58600, loss[loss=2.396, over 2100.00 frames. , ppl: 10.973733539753704] tot_loss[loss=2.293, over 5574888.99 frames. , ppl: 9.900468361931607], batch size: 70
+2022-12-11 20:58:11,551 INFO [train.py:421] (7/8) Epoch 5, batch 58800, loss[loss=2.271, over 1680.00 frames. , ppl: 9.69288907502399] tot_loss[loss=2.293, over 5541537.29 frames. , ppl: 9.908323344290093], batch size: 70
+2022-12-11 20:59:49,674 INFO [train.py:421] (7/8) Epoch 5, batch 59000, loss[loss=2.295, over 3990.00 frames. , ppl: 9.928833045610054] tot_loss[loss=2.294, over 5532923.44 frames. , ppl: 9.910869023080366], batch size: 70
+2022-12-11 20:59:49,674 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 20:59:50,433 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.286, over 211138.00 frames. , ppl: 9.833901132185455
+2022-12-11 21:01:27,628 INFO [train.py:421] (7/8) Epoch 5, batch 59200, loss[loss=2.461, over 980.00 frames. , ppl: 11.718428724322692] tot_loss[loss=2.294, over 5537926.29 frames. , ppl: 9.913796088637698], batch size: 70
+2022-12-11 21:03:06,547 INFO [train.py:421] (7/8) Epoch 5, batch 59400, loss[loss=2.287, over 2170.00 frames. , ppl: 9.848368555393973] tot_loss[loss=2.294, over 5559499.88 frames. , ppl: 9.914746652366219], batch size: 70
+2022-12-11 21:04:48,215 INFO [train.py:421] (7/8) Epoch 5, batch 59600, loss[loss=2.309, over 2380.00 frames. , ppl: 10.068415160858363] tot_loss[loss=2.295, over 5544360.52 frames. , ppl: 9.920530669127697], batch size: 70
+2022-12-11 21:06:24,261 INFO [train.py:421] (7/8) Epoch 5, batch 59800, loss[loss=2.374, over 1050.00 frames. , ppl: 10.738147072550039] tot_loss[loss=2.295, over 5528316.06 frames. , ppl: 9.922526056462468], batch size: 70
+2022-12-11 21:08:10,095 INFO [train.py:421] (7/8) Epoch 5, batch 60000, loss[loss=2.267, over 2240.00 frames. , ppl: 9.646376764448325] tot_loss[loss=2.293, over 5581046.21 frames. , ppl: 9.90726026319789], batch size: 70
+2022-12-11 21:08:10,095 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 21:08:10,853 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.286, over 211138.00 frames. , ppl: 9.831021137755421
+2022-12-11 21:09:53,973 INFO [train.py:421] (7/8) Epoch 5, batch 60200, loss[loss=2.226, over 4900.00 frames. , ppl: 9.265610859766076] tot_loss[loss=2.293, over 5587496.67 frames. , ppl: 9.901194634804407], batch size: 70
+2022-12-11 21:11:35,813 INFO [train.py:421] (7/8) Epoch 5, batch 60400, loss[loss=2.333, over 2240.00 frames. , ppl: 10.305617364752818] tot_loss[loss=2.292, over 5595130.68 frames. , ppl: 9.897131000980375], batch size: 70
+2022-12-11 21:13:18,738 INFO [train.py:421] (7/8) Epoch 5, batch 60600, loss[loss=2.81, over 700.00 frames. , ppl: 16.616332396202623] tot_loss[loss=2.293, over 5594005.74 frames. , ppl: 9.899989209440033], batch size: 70
+2022-12-11 21:14:58,853 INFO [train.py:421] (7/8) Epoch 5, batch 60800, loss[loss=2.424, over 1750.00 frames. , ppl: 11.285786304710923] tot_loss[loss=2.294, over 5555354.91 frames. , ppl: 9.912518708054144], batch size: 70
+2022-12-11 21:16:39,574 INFO [train.py:421] (7/8) Epoch 5, batch 61000, loss[loss=2.233, over 7000.00 frames. , ppl: 9.323520729877528] tot_loss[loss=2.294, over 5547495.50 frames. , ppl: 9.917792444033399], batch size: 70
+2022-12-11 21:16:39,574 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 21:16:40,311 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.284, over 211138.00 frames. , ppl: 9.816234263345795
+2022-12-11 21:18:20,760 INFO [train.py:421] (7/8) Epoch 5, batch 61200, loss[loss=2.252, over 3710.00 frames. , ppl: 9.508386831270684] tot_loss[loss=2.295, over 5537964.00 frames. , ppl: 9.924897250458075], batch size: 70
+2022-12-11 21:20:01,607 INFO [train.py:421] (7/8) Epoch 5, batch 61400, loss[loss=2.243, over 6650.00 frames. , ppl: 9.418782988434723] tot_loss[loss=2.294, over 5575711.96 frames. , ppl: 9.91810789041377], batch size: 70
+2022-12-11 21:21:39,916 INFO [train.py:421] (7/8) Epoch 5, batch 61600, loss[loss=2.23, over 3780.00 frames. , ppl: 9.303459650311533] tot_loss[loss=2.294, over 5625402.81 frames. , ppl: 9.91347592734649], batch size: 70
+2022-12-11 21:23:20,544 INFO [train.py:421] (7/8) Epoch 5, batch 61800, loss[loss=2.621, over 770.00 frames. , ppl: 13.745866500398046] tot_loss[loss=2.293, over 5641658.08 frames. , ppl: 9.906304158337683], batch size: 70
+2022-12-11 21:24:59,392 INFO [train.py:421] (7/8) Epoch 5, batch 62000, loss[loss=2.308, over 1820.00 frames. , ppl: 10.056341125402255] tot_loss[loss=2.294, over 5621731.20 frames. , ppl: 9.91491302676912], batch size: 70
+2022-12-11 21:24:59,392 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 21:25:00,150 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.287, over 211138.00 frames. , ppl: 9.841092429233514
+2022-12-11 21:26:42,942 INFO [train.py:421] (7/8) Epoch 5, batch 62200, loss[loss=4.948, over 280.00 frames. , ppl: 140.93728352370388] tot_loss[loss=2.294, over 5627980.05 frames. , ppl: 9.916273874936202], batch size: 70
+2022-12-11 21:28:21,528 INFO [train.py:421] (7/8) Epoch 5, batch 62400, loss[loss=3.338, over 490.00 frames. , ppl: 28.1641127232588] tot_loss[loss=2.295, over 5575616.10 frames. , ppl: 9.925301597333828], batch size: 70
+2022-12-11 21:30:03,694 INFO [train.py:421] (7/8) Epoch 5, batch 62600, loss[loss=2.492, over 1330.00 frames. , ppl: 12.088567744673565] tot_loss[loss=2.296, over 5570740.62 frames. , ppl: 9.93136253224384], batch size: 70
+2022-12-11 21:31:48,086 INFO [train.py:421] (7/8) Epoch 5, batch 62800, loss[loss=2.123, over 8470.00 frames. , ppl: 8.353177064121937] tot_loss[loss=2.294, over 5606229.97 frames. , ppl: 9.91838306934643], batch size: 70
+2022-12-11 21:33:23,582 INFO [train.py:421] (7/8) Epoch 5, batch 63000, loss[loss=2.232, over 4830.00 frames. , ppl: 9.318999845602706] tot_loss[loss=2.296, over 5551641.00 frames. , ppl: 9.935823627425798], batch size: 70
+2022-12-11 21:33:23,582 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 21:33:24,313 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.286, over 211138.00 frames. , ppl: 9.831210297961553
+2022-12-11 21:35:04,616 INFO [train.py:421] (7/8) Epoch 5, batch 63200, loss[loss=2.389, over 1120.00 frames. , ppl: 10.900223178967911] tot_loss[loss=2.296, over 5516851.22 frames. , ppl: 9.937337840369972], batch size: 70
+2022-12-11 21:36:45,648 INFO [train.py:421] (7/8) Epoch 5, batch 63400, loss[loss=2.238, over 2520.00 frames. , ppl: 9.37897751013388] tot_loss[loss=2.296, over 5492802.56 frames. , ppl: 9.938712704864757], batch size: 70
+2022-12-11 21:38:24,036 INFO [train.py:421] (7/8) Epoch 5, batch 63600, loss[loss=2.236, over 4480.00 frames. , ppl: 9.354369398177617] tot_loss[loss=2.297, over 5480612.28 frames. , ppl: 9.940725422276945], batch size: 70
+2022-12-11 21:40:04,571 INFO [train.py:421] (7/8) Epoch 5, batch 63800, loss[loss=2.418, over 1610.00 frames. , ppl: 11.222824914802473] tot_loss[loss=2.298, over 5451343.37 frames. , ppl: 9.951077771173727], batch size: 70
+2022-12-11 21:41:46,269 INFO [train.py:421] (7/8) Epoch 5, batch 64000, loss[loss=2.361, over 2310.00 frames. , ppl: 10.603296484015399] tot_loss[loss=2.295, over 5530261.33 frames. , ppl: 9.927548715889086], batch size: 70
+2022-12-11 21:41:46,270 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 21:41:47,016 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.285, over 211138.00 frames. , ppl: 9.828019797907846
+2022-12-11 21:43:27,813 INFO [train.py:421] (7/8) Epoch 5, batch 64200, loss[loss=2.61, over 840.00 frames. , ppl: 13.602812549225519] tot_loss[loss=2.296, over 5505268.08 frames. , ppl: 9.934320037557214], batch size: 70
+2022-12-11 21:45:08,809 INFO [train.py:421] (7/8) Epoch 5, batch 64400, loss[loss=2.677, over 840.00 frames. , ppl: 14.543621411158602] tot_loss[loss=2.296, over 5504320.81 frames. , ppl: 9.935929618123316], batch size: 70
+2022-12-11 21:46:48,252 INFO [train.py:421] (7/8) Epoch 5, batch 64600, loss[loss=2.329, over 3010.00 frames. , ppl: 10.271407189188379] tot_loss[loss=2.297, over 5455600.77 frames. , ppl: 9.943061861376327], batch size: 70
+2022-12-11 21:48:30,059 INFO [train.py:421] (7/8) Epoch 5, batch 64800, loss[loss=2.223, over 4830.00 frames. , ppl: 9.232514732909676] tot_loss[loss=2.295, over 5486180.80 frames. , ppl: 9.926801198356921], batch size: 70
+2022-12-11 21:50:08,871 INFO [train.py:421] (7/8) Epoch 5, batch 65000, loss[loss=2.393, over 1820.00 frames. , ppl: 10.944144438139622] tot_loss[loss=2.295, over 5481278.11 frames. , ppl: 9.928996426360243], batch size: 70
+2022-12-11 21:50:08,872 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 21:50:09,631 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.286, over 211138.00 frames. , ppl: 9.835764336858247
+2022-12-11 21:51:51,528 INFO [train.py:421] (7/8) Epoch 5, batch 65200, loss[loss=2.497, over 980.00 frames. , ppl: 12.144967175021025] tot_loss[loss=2.295, over 5513983.46 frames. , ppl: 9.924434630973886], batch size: 70
+2022-12-11 21:53:29,533 INFO [train.py:421] (7/8) Epoch 5, batch 65400, loss[loss=3.247, over 490.00 frames. , ppl: 25.720050339629427] tot_loss[loss=2.296, over 5465672.38 frames. , ppl: 9.934352600331898], batch size: 70
+2022-12-11 21:55:05,987 INFO [train.py:421] (7/8) Epoch 5, batch 65600, loss[loss=2.234, over 4340.00 frames. , ppl: 9.335826090694257] tot_loss[loss=2.297, over 5437649.51 frames. , ppl: 9.947710495976981], batch size: 70
+2022-12-11 21:56:43,519 INFO [train.py:421] (7/8) Epoch 5, batch 65800, loss[loss=2.465, over 1050.00 frames. , ppl: 11.760178512902012] tot_loss[loss=2.298, over 5437026.82 frames. , ppl: 9.951531656764084], batch size: 70
+2022-12-11 21:58:21,358 INFO [train.py:421] (7/8) Epoch 5, batch 66000, loss[loss=2.412, over 1750.00 frames. , ppl: 11.155812454902179] tot_loss[loss=2.299, over 5385728.50 frames. , ppl: 9.968699615184207], batch size: 70
+2022-12-11 21:58:21,359 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 21:58:22,104 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.284, over 211138.00 frames. , ppl: 9.816399892600549
+2022-12-11 22:00:01,647 INFO [train.py:421] (7/8) Epoch 5, batch 66200, loss[loss=2.197, over 7140.00 frames. , ppl: 8.994834048972727] tot_loss[loss=2.298, over 5429305.73 frames. , ppl: 9.958158688702689], batch size: 70
+2022-12-11 22:01:40,833 INFO [train.py:421] (7/8) Epoch 5, batch 66400, loss[loss=2.22, over 4480.00 frames. , ppl: 9.204956042425735] tot_loss[loss=2.298, over 5476661.43 frames. , ppl: 9.954522395962648], batch size: 70
+2022-12-11 22:03:20,546 INFO [train.py:421] (7/8) Epoch 5, batch 66600, loss[loss=2.39, over 980.00 frames. , ppl: 10.91278381472511] tot_loss[loss=2.297, over 5479351.76 frames. , ppl: 9.948688979445118], batch size: 70
+2022-12-11 22:05:00,238 INFO [train.py:421] (7/8) Epoch 5, batch 66800, loss[loss=2.174, over 6300.00 frames. , ppl: 8.795403809576172] tot_loss[loss=2.296, over 5506663.80 frames. , ppl: 9.939139942002884], batch size: 70
+2022-12-11 22:06:37,508 INFO [train.py:421] (7/8) Epoch 5, batch 67000, loss[loss=2.265, over 4760.00 frames. , ppl: 9.63500293374919] tot_loss[loss=2.297, over 5512308.92 frames. , ppl: 9.94551008721548], batch size: 70
+2022-12-11 22:06:37,508 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 22:06:38,242 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.284, over 211138.00 frames. , ppl: 9.812880145960932
+2022-12-11 22:08:16,540 INFO [train.py:421] (7/8) Epoch 5, batch 67200, loss[loss=2.181, over 4830.00 frames. , ppl: 8.853066912789165] tot_loss[loss=2.297, over 5501323.45 frames. , ppl: 9.946000174934904], batch size: 70
+2022-12-11 22:09:55,866 INFO [train.py:421] (7/8) Epoch 5, batch 67400, loss[loss=2.572, over 1750.00 frames. , ppl: 13.091098267706478] tot_loss[loss=2.297, over 5485447.20 frames. , ppl: 9.946505888552302], batch size: 70
+2022-12-11 22:11:35,245 INFO [train.py:421] (7/8) Epoch 5, batch 67600, loss[loss=2.207, over 6090.00 frames. , ppl: 9.086215510247564] tot_loss[loss=2.297, over 5461967.19 frames. , ppl: 9.946993906589897], batch size: 70
+2022-12-11 22:13:14,516 INFO [train.py:421] (7/8) Epoch 5, batch 67800, loss[loss=2.403, over 1050.00 frames. , ppl: 11.054027363746341] tot_loss[loss=2.295, over 5517701.04 frames. , ppl: 9.928916062474395], batch size: 70
+2022-12-11 22:14:52,340 INFO [train.py:421] (7/8) Epoch 5, batch 68000, loss[loss=2.381, over 1960.00 frames. , ppl: 10.816444791185964] tot_loss[loss=2.296, over 5481535.63 frames. , ppl: 9.938278129244868], batch size: 70
+2022-12-11 22:14:52,340 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 22:14:53,100 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.284, over 211138.00 frames. , ppl: 9.814543261416496
+2022-12-11 22:16:33,229 INFO [train.py:421] (7/8) Epoch 5, batch 68200, loss[loss=2.349, over 1820.00 frames. , ppl: 10.480136154740741] tot_loss[loss=2.296, over 5486155.71 frames. , ppl: 9.93475033681594], batch size: 70
+2022-12-11 22:18:14,689 INFO [train.py:421] (7/8) Epoch 5, batch 68400, loss[loss=2.199, over 9590.00 frames. , ppl: 9.012189296091394] tot_loss[loss=2.295, over 5526183.04 frames. , ppl: 9.92423380193953], batch size: 70
+2022-12-11 22:19:55,896 INFO [train.py:421] (7/8) Epoch 5, batch 68600, loss[loss=2.138, over 3360.00 frames. , ppl: 8.483469513198433] tot_loss[loss=2.295, over 5509826.47 frames. , ppl: 9.928035674819032], batch size: 70
+2022-12-11 22:21:39,031 INFO [train.py:421] (7/8) Epoch 5, batch 68800, loss[loss=2.273, over 3360.00 frames. , ppl: 9.711086782643026] tot_loss[loss=2.295, over 5518362.89 frames. , ppl: 9.925946886162386], batch size: 70
+2022-12-11 22:23:22,190 INFO [train.py:421] (7/8) Epoch 5, batch 69000, loss[loss=2.378, over 2520.00 frames. , ppl: 10.785889353618618] tot_loss[loss=2.294, over 5529392.69 frames. , ppl: 9.914463302199216], batch size: 70
+2022-12-11 22:23:22,191 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 22:23:22,952 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.284, over 211138.00 frames. , ppl: 9.816581506837656
+2022-12-11 22:25:00,963 INFO [train.py:421] (7/8) Epoch 5, batch 69200, loss[loss=2.731, over 700.00 frames. , ppl: 15.355714553017268] tot_loss[loss=2.294, over 5518539.03 frames. , ppl: 9.917086478969958], batch size: 70
+2022-12-11 22:26:43,991 INFO [train.py:421] (7/8) Epoch 5, batch 69400, loss[loss=2.46, over 770.00 frames. , ppl: 11.704384018146442] tot_loss[loss=2.293, over 5543304.69 frames. , ppl: 9.904522636589068], batch size: 70
+2022-12-11 22:28:25,074 INFO [train.py:421] (7/8) Epoch 5, batch 69600, loss[loss=2.572, over 840.00 frames. , ppl: 13.08820021061138] tot_loss[loss=2.293, over 5537071.11 frames. , ppl: 9.900966157910647], batch size: 70
+2022-12-11 22:30:05,482 INFO [train.py:421] (7/8) Epoch 5, batch 69800, loss[loss=2.194, over 8400.00 frames. , ppl: 8.973607839078051] tot_loss[loss=2.293, over 5538029.20 frames. , ppl: 9.907368432083627], batch size: 70
+2022-12-11 22:31:48,594 INFO [train.py:421] (7/8) Epoch 5, batch 70000, loss[loss=2.212, over 6720.00 frames. , ppl: 9.132664867152327] tot_loss[loss=2.294, over 5530639.79 frames. , ppl: 9.916068127332279], batch size: 70
+2022-12-11 22:31:48,594 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 22:31:49,328 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.283, over 211138.00 frames. , ppl: 9.80977109406468
+2022-12-11 22:33:34,154 INFO [train.py:421] (7/8) Epoch 5, batch 70200, loss[loss=2.413, over 1610.00 frames. , ppl: 11.172389107296949] tot_loss[loss=2.295, over 5532735.56 frames. , ppl: 9.919610071651634], batch size: 70
+2022-12-11 22:35:14,440 INFO [train.py:421] (7/8) Epoch 5, batch 70400, loss[loss=2.538, over 1330.00 frames. , ppl: 12.649371988034536] tot_loss[loss=2.294, over 5550086.03 frames. , ppl: 9.913101012180155], batch size: 70
+2022-12-11 22:36:54,990 INFO [train.py:421] (7/8) Epoch 5, batch 70600, loss[loss=2.284, over 3010.00 frames. , ppl: 9.816758275276747] tot_loss[loss=2.293, over 5584013.59 frames. , ppl: 9.9064910640128], batch size: 70
+2022-12-11 22:38:32,952 INFO [train.py:421] (7/8) Epoch 5, batch 70800, loss[loss=2.226, over 3500.00 frames. , ppl: 9.259487638556621] tot_loss[loss=2.294, over 5549448.62 frames. , ppl: 9.911943939501537], batch size: 70
+2022-12-11 22:40:16,525 INFO [train.py:421] (7/8) Epoch 5, batch 71000, loss[loss=2.172, over 5530.00 frames. , ppl: 8.775217101396375] tot_loss[loss=2.294, over 5563595.28 frames. , ppl: 9.909972098158104], batch size: 70
+2022-12-11 22:40:16,525 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 22:40:17,255 INFO [train.py:452] (7/8) Epoch 5, validation: loss=2.283, over 211138.00 frames. , ppl: 9.803261396653303
+2022-12-11 22:41:56,412 INFO [train.py:421] (7/8) Epoch 5, batch 71200, loss[loss=2.178, over 6090.00 frames. , ppl: 8.828615074622359] tot_loss[loss=2.294, over 5566145.67 frames. , ppl: 9.914113981292138], batch size: 70
+2022-12-11 22:43:36,050 INFO [train.py:421] (7/8) Epoch 5, batch 71400, loss[loss=2.265, over 6300.00 frames. , ppl: 9.626918471667997] tot_loss[loss=2.294, over 5530181.55 frames. , ppl: 9.919048356092313], batch size: 70
+2022-12-11 22:45:15,378 INFO [train.py:421] (7/8) Epoch 5, batch 71600, loss[loss=2.792, over 630.00 frames. , ppl: 16.30638904798026] tot_loss[loss=2.294, over 5544642.29 frames. , ppl: 9.916279524926775], batch size: 70
+2022-12-11 22:46:51,071 INFO [train.py:421] (7/8) Epoch 5, batch 71800, loss[loss=2.817, over 630.00 frames. , ppl: 16.730675401388932] tot_loss[loss=2.295, over 5535703.80 frames. , ppl: 9.920122249546006], batch size: 70
+2022-12-11 22:48:06,696 INFO [train.py:421] (7/8) Epoch 6, batch 0, loss[loss=2.234, over 4830.00 frames. , ppl: 9.335268844614866] tot_loss[loss=2.234, over 4830.00 frames. , ppl: 9.335268844614866], batch size: 70
+2022-12-11 22:49:46,722 INFO [train.py:421] (7/8) Epoch 6, batch 200, loss[loss=2.228, over 5320.00 frames. , ppl: 9.284781544717578] tot_loss[loss=2.302, over 473253.06 frames. , ppl: 9.990107364811609], batch size: 70
+2022-12-11 22:51:26,928 INFO [train.py:421] (7/8) Epoch 6, batch 400, loss[loss=2.947, over 560.00 frames. , ppl: 19.05174303893546] tot_loss[loss=2.285, over 989099.02 frames. , ppl: 9.822397642535321], batch size: 70
+2022-12-11 22:53:08,635 INFO [train.py:421] (7/8) Epoch 6, batch 600, loss[loss=2.269, over 2100.00 frames. , ppl: 9.671236814376611] tot_loss[loss=2.283, over 1439526.93 frames. , ppl: 9.809435658763853], batch size: 70
+2022-12-11 22:54:51,850 INFO [train.py:421] (7/8) Epoch 6, batch 800, loss[loss=2.124, over 6790.00 frames. , ppl: 8.364926935660675] tot_loss[loss=2.283, over 1866613.66 frames. , ppl: 9.805118639512143], batch size: 70
+2022-12-11 22:56:35,371 INFO [train.py:421] (7/8) Epoch 6, batch 1000, loss[loss=2.273, over 1610.00 frames. , ppl: 9.708432739547847] tot_loss[loss=2.281, over 2248329.15 frames. , ppl: 9.787486229236869], batch size: 70
+2022-12-11 22:56:35,371 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 22:56:36,121 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.284, over 211138.00 frames. , ppl: 9.816725347697853
+2022-12-11 22:58:21,089 INFO [train.py:421] (7/8) Epoch 6, batch 1200, loss[loss=2.171, over 5600.00 frames. , ppl: 8.767364100724336] tot_loss[loss=2.28, over 2582227.65 frames. , ppl: 9.778900186337914], batch size: 70
+2022-12-11 22:59:58,492 INFO [train.py:421] (7/8) Epoch 6, batch 1400, loss[loss=2.193, over 7490.00 frames. , ppl: 8.964448094235632] tot_loss[loss=2.282, over 2854646.69 frames. , ppl: 9.79190350096551], batch size: 70
+2022-12-11 23:01:38,948 INFO [train.py:421] (7/8) Epoch 6, batch 1600, loss[loss=2.209, over 3220.00 frames. , ppl: 9.108631222829777] tot_loss[loss=2.282, over 3126960.72 frames. , ppl: 9.792146628459232], batch size: 70
+2022-12-11 23:03:19,724 INFO [train.py:421] (7/8) Epoch 6, batch 1800, loss[loss=2.42, over 1400.00 frames. , ppl: 11.24897008490143] tot_loss[loss=2.278, over 3425852.35 frames. , ppl: 9.760762395499494], batch size: 70
+2022-12-11 23:04:57,210 INFO [train.py:421] (7/8) Epoch 6, batch 2000, loss[loss=2.344, over 1890.00 frames. , ppl: 10.424655210275576] tot_loss[loss=2.279, over 3638138.92 frames. , ppl: 9.766970068025305], batch size: 70
+2022-12-11 23:04:57,210 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 23:04:57,952 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.286, over 211138.00 frames. , ppl: 9.840409328583648
+2022-12-11 23:06:35,144 INFO [train.py:421] (7/8) Epoch 6, batch 2200, loss[loss=2.477, over 1400.00 frames. , ppl: 11.908239713169738] tot_loss[loss=2.28, over 3809977.91 frames. , ppl: 9.77943858115687], batch size: 70
+2022-12-11 23:08:19,875 INFO [train.py:421] (7/8) Epoch 6, batch 2400, loss[loss=2.242, over 4760.00 frames. , ppl: 9.409738603570636] tot_loss[loss=2.279, over 4024739.44 frames. , ppl: 9.768979350307557], batch size: 70
+2022-12-11 23:10:02,603 INFO [train.py:421] (7/8) Epoch 6, batch 2600, loss[loss=2.372, over 1190.00 frames. , ppl: 10.721684634989982] tot_loss[loss=2.28, over 4201920.32 frames. , ppl: 9.772471050347095], batch size: 70
+2022-12-11 23:11:44,591 INFO [train.py:421] (7/8) Epoch 6, batch 2800, loss[loss=2.516, over 840.00 frames. , ppl: 12.38328811122246] tot_loss[loss=2.28, over 4335520.75 frames. , ppl: 9.776970096367851], batch size: 70
+2022-12-11 23:13:24,433 INFO [train.py:421] (7/8) Epoch 6, batch 3000, loss[loss=2.206, over 3080.00 frames. , ppl: 9.077335865655078] tot_loss[loss=2.28, over 4462059.71 frames. , ppl: 9.778012283865712], batch size: 70
+2022-12-11 23:13:24,434 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 23:13:25,195 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.285, over 211138.00 frames. , ppl: 9.824575860616017
+2022-12-11 23:15:01,092 INFO [train.py:421] (7/8) Epoch 6, batch 3200, loss[loss=2.112, over 11410.00 frames. , ppl: 8.268757465623903] tot_loss[loss=2.282, over 4536943.15 frames. , ppl: 9.796288603925234], batch size: 70
+2022-12-11 23:16:39,623 INFO [train.py:421] (7/8) Epoch 6, batch 3400, loss[loss=2.238, over 4550.00 frames. , ppl: 9.375542113310123] tot_loss[loss=2.282, over 4666413.71 frames. , ppl: 9.797623411533994], batch size: 70
+2022-12-11 23:18:19,912 INFO [train.py:421] (7/8) Epoch 6, batch 3600, loss[loss=2.277, over 2380.00 frames. , ppl: 9.751739843856301] tot_loss[loss=2.282, over 4770786.88 frames. , ppl: 9.797799193315623], batch size: 70
+2022-12-11 23:19:59,225 INFO [train.py:421] (7/8) Epoch 6, batch 3800, loss[loss=2.18, over 5460.00 frames. , ppl: 8.846182529269546] tot_loss[loss=2.282, over 4834155.73 frames. , ppl: 9.797401265755227], batch size: 70
+2022-12-11 23:21:41,563 INFO [train.py:421] (7/8) Epoch 6, batch 4000, loss[loss=2.376, over 2100.00 frames. , ppl: 10.760231289950656] tot_loss[loss=2.283, over 4893528.97 frames. , ppl: 9.802515831113748], batch size: 70
+2022-12-11 23:21:41,564 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 23:21:42,322 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.283, over 211138.00 frames. , ppl: 9.808357026550453
+2022-12-11 23:23:26,051 INFO [train.py:421] (7/8) Epoch 6, batch 4200, loss[loss=2.565, over 840.00 frames. , ppl: 12.996379478998913] tot_loss[loss=2.283, over 4946029.31 frames. , ppl: 9.806824455466476], batch size: 70
+2022-12-11 23:25:03,906 INFO [train.py:421] (7/8) Epoch 6, batch 4400, loss[loss=2.353, over 2380.00 frames. , ppl: 10.514127285665534] tot_loss[loss=2.283, over 4970500.09 frames. , ppl: 9.81077371064775], batch size: 70
+2022-12-11 23:26:43,143 INFO [train.py:421] (7/8) Epoch 6, batch 4600, loss[loss=2.306, over 2100.00 frames. , ppl: 10.030671550735743] tot_loss[loss=2.283, over 5061366.09 frames. , ppl: 9.805137042592357], batch size: 70
+2022-12-11 23:28:17,781 INFO [train.py:421] (7/8) Epoch 6, batch 4800, loss[loss=2.843, over 700.00 frames. , ppl: 17.174058301108744] tot_loss[loss=2.287, over 5011061.99 frames. , ppl: 9.842969800866411], batch size: 70
+2022-12-11 23:29:55,651 INFO [train.py:421] (7/8) Epoch 6, batch 5000, loss[loss=2.396, over 1470.00 frames. , ppl: 10.978401328777775] tot_loss[loss=2.289, over 5001334.63 frames. , ppl: 9.869308078501742], batch size: 70
+2022-12-11 23:29:55,652 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 23:29:56,411 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.285, over 211138.00 frames. , ppl: 9.82324543954202
+2022-12-11 23:31:38,998 INFO [train.py:421] (7/8) Epoch 6, batch 5200, loss[loss=2.277, over 3920.00 frames. , ppl: 9.747282229672232] tot_loss[loss=2.291, over 4996173.30 frames. , ppl: 9.886098824383978], batch size: 70
+2022-12-11 23:33:16,576 INFO [train.py:421] (7/8) Epoch 6, batch 5400, loss[loss=2.323, over 2380.00 frames. , ppl: 10.203103593418696] tot_loss[loss=2.291, over 5056027.94 frames. , ppl: 9.885916281025702], batch size: 70
+2022-12-11 23:34:57,715 INFO [train.py:421] (7/8) Epoch 6, batch 5600, loss[loss=2.57, over 1260.00 frames. , ppl: 13.070976889573805] tot_loss[loss=2.29, over 5140184.01 frames. , ppl: 9.870619483053733], batch size: 70
+2022-12-11 23:36:40,249 INFO [train.py:421] (7/8) Epoch 6, batch 5800, loss[loss=2.752, over 700.00 frames. , ppl: 15.675340322272094] tot_loss[loss=2.288, over 5196244.78 frames. , ppl: 9.856442529260912], batch size: 70
+2022-12-11 23:38:22,677 INFO [train.py:421] (7/8) Epoch 6, batch 6000, loss[loss=2.469, over 910.00 frames. , ppl: 11.806759387819614] tot_loss[loss=2.288, over 5254852.22 frames. , ppl: 9.855473743762117], batch size: 70
+2022-12-11 23:38:22,678 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 23:38:23,436 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.284, over 211138.00 frames. , ppl: 9.813196769801683
+2022-12-11 23:40:02,703 INFO [train.py:421] (7/8) Epoch 6, batch 6200, loss[loss=2.336, over 910.00 frames. , ppl: 10.335737062599142] tot_loss[loss=2.289, over 5245211.59 frames. , ppl: 9.863300834497288], batch size: 70
+2022-12-11 23:41:42,435 INFO [train.py:421] (7/8) Epoch 6, batch 6400, loss[loss=2.24, over 13650.00 frames. , ppl: 9.390753743739738] tot_loss[loss=2.289, over 5252939.11 frames. , ppl: 9.861249091470736], batch size: 70
+2022-12-11 23:43:22,495 INFO [train.py:421] (7/8) Epoch 6, batch 6600, loss[loss=2.438, over 1120.00 frames. , ppl: 11.447727342043827] tot_loss[loss=2.289, over 5276725.53 frames. , ppl: 9.866952148938848], batch size: 70
+2022-12-11 23:45:02,954 INFO [train.py:421] (7/8) Epoch 6, batch 6800, loss[loss=2.207, over 4620.00 frames. , ppl: 9.0897394024174] tot_loss[loss=2.29, over 5277836.46 frames. , ppl: 9.878008633676572], batch size: 70
+2022-12-11 23:46:38,675 INFO [train.py:421] (7/8) Epoch 6, batch 7000, loss[loss=2.487, over 980.00 frames. , ppl: 12.01945307684033] tot_loss[loss=2.291, over 5270700.41 frames. , ppl: 9.880612972086332], batch size: 70
+2022-12-11 23:46:38,675 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 23:46:39,429 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.285, over 211138.00 frames. , ppl: 9.822367314949352
+2022-12-11 23:48:19,183 INFO [train.py:421] (7/8) Epoch 6, batch 7200, loss[loss=2.29, over 2800.00 frames. , ppl: 9.874650102598299] tot_loss[loss=2.29, over 5287675.43 frames. , ppl: 9.877955752754701], batch size: 70
+2022-12-11 23:50:03,958 INFO [train.py:421] (7/8) Epoch 6, batch 7400, loss[loss=2.267, over 2730.00 frames. , ppl: 9.647362408308222] tot_loss[loss=2.29, over 5312350.32 frames. , ppl: 9.877701621253076], batch size: 70
+2022-12-11 23:51:43,016 INFO [train.py:421] (7/8) Epoch 6, batch 7600, loss[loss=2.371, over 2100.00 frames. , ppl: 10.706118812810095] tot_loss[loss=2.29, over 5305684.56 frames. , ppl: 9.879625691689016], batch size: 70
+2022-12-11 23:53:23,585 INFO [train.py:421] (7/8) Epoch 6, batch 7800, loss[loss=2.171, over 10290.00 frames. , ppl: 8.766989994532466] tot_loss[loss=2.289, over 5364555.58 frames. , ppl: 9.869909437011492], batch size: 70
+2022-12-11 23:55:07,612 INFO [train.py:421] (7/8) Epoch 6, batch 8000, loss[loss=2.147, over 5460.00 frames. , ppl: 8.558286886679081] tot_loss[loss=2.288, over 5425626.00 frames. , ppl: 9.85627394360919], batch size: 70
+2022-12-11 23:55:07,612 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-11 23:55:08,354 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.282, over 211138.00 frames. , ppl: 9.793563654653626
+2022-12-11 23:56:47,539 INFO [train.py:421] (7/8) Epoch 6, batch 8200, loss[loss=2.347, over 3500.00 frames. , ppl: 10.452596813384678] tot_loss[loss=2.289, over 5424384.07 frames. , ppl: 9.865865210365074], batch size: 70
+2022-12-11 23:58:28,579 INFO [train.py:421] (7/8) Epoch 6, batch 8400, loss[loss=2.35, over 1120.00 frames. , ppl: 10.489252590241202] tot_loss[loss=2.29, over 5379966.33 frames. , ppl: 9.879768240193403], batch size: 70
+2022-12-12 00:00:05,802 INFO [train.py:421] (7/8) Epoch 6, batch 8600, loss[loss=2.35, over 1890.00 frames. , ppl: 10.484851878729577] tot_loss[loss=2.291, over 5357647.74 frames. , ppl: 9.88497830619053], batch size: 70
+2022-12-12 00:01:46,888 INFO [train.py:421] (7/8) Epoch 6, batch 8800, loss[loss=2.369, over 2240.00 frames. , ppl: 10.687883977854687] tot_loss[loss=2.29, over 5377434.11 frames. , ppl: 9.87721408826957], batch size: 70
+2022-12-12 00:03:27,032 INFO [train.py:421] (7/8) Epoch 6, batch 9000, loss[loss=2.162, over 10220.00 frames. , ppl: 8.691993753547006] tot_loss[loss=2.29, over 5395324.96 frames. , ppl: 9.870854714168493], batch size: 70
+2022-12-12 00:03:27,032 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 00:03:27,760 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.285, over 211138.00 frames. , ppl: 9.82595299982713
+2022-12-12 00:05:06,483 INFO [train.py:421] (7/8) Epoch 6, batch 9200, loss[loss=2.355, over 2660.00 frames. , ppl: 10.542858818449366] tot_loss[loss=2.29, over 5364107.41 frames. , ppl: 9.878892962041624], batch size: 70
+2022-12-12 00:06:43,069 INFO [train.py:421] (7/8) Epoch 6, batch 9400, loss[loss=2.317, over 1960.00 frames. , ppl: 10.147532761896834] tot_loss[loss=2.291, over 5347243.62 frames. , ppl: 9.885173895420163], batch size: 70
+2022-12-12 00:08:21,541 INFO [train.py:421] (7/8) Epoch 6, batch 9600, loss[loss=2.515, over 1190.00 frames. , ppl: 12.36711723157779] tot_loss[loss=2.292, over 5342196.98 frames. , ppl: 9.890529817223275], batch size: 70
+2022-12-12 00:10:01,633 INFO [train.py:421] (7/8) Epoch 6, batch 9800, loss[loss=2.121, over 7236.00 frames. , ppl: 8.34195221904215] tot_loss[loss=2.29, over 5384215.79 frames. , ppl: 9.877663241750327], batch size: 36
+2022-12-12 00:11:46,129 INFO [train.py:421] (7/8) Epoch 6, batch 10000, loss[loss=2.412, over 1470.00 frames. , ppl: 11.15976595085442] tot_loss[loss=2.292, over 5352247.55 frames. , ppl: 9.8898936670166], batch size: 70
+2022-12-12 00:11:46,130 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 00:11:46,874 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.283, over 211138.00 frames. , ppl: 9.804028982352971
+2022-12-12 00:13:23,523 INFO [train.py:421] (7/8) Epoch 6, batch 10200, loss[loss=2.391, over 2310.00 frames. , ppl: 10.919783803156177] tot_loss[loss=2.291, over 5372160.07 frames. , ppl: 9.887945355550517], batch size: 70
+2022-12-12 00:15:02,151 INFO [train.py:421] (7/8) Epoch 6, batch 10400, loss[loss=2.349, over 1820.00 frames. , ppl: 10.47887941002783] tot_loss[loss=2.291, over 5381410.74 frames. , ppl: 9.885181387706647], batch size: 70
+2022-12-12 00:16:43,004 INFO [train.py:421] (7/8) Epoch 6, batch 10600, loss[loss=2.527, over 1330.00 frames. , ppl: 12.520140782249722] tot_loss[loss=2.292, over 5343455.74 frames. , ppl: 9.89262180480112], batch size: 70
+2022-12-12 00:18:24,430 INFO [train.py:421] (7/8) Epoch 6, batch 10800, loss[loss=2.262, over 2310.00 frames. , ppl: 9.603743003633983] tot_loss[loss=2.293, over 5331936.94 frames. , ppl: 9.905359509262743], batch size: 70
+2022-12-12 00:20:06,165 INFO [train.py:421] (7/8) Epoch 6, batch 11000, loss[loss=2.201, over 5320.00 frames. , ppl: 9.032978973378585] tot_loss[loss=2.292, over 5373516.90 frames. , ppl: 9.896902696776193], batch size: 70
+2022-12-12 00:20:06,166 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 00:20:06,914 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.283, over 211138.00 frames. , ppl: 9.804163932742426
+2022-12-12 00:21:45,895 INFO [train.py:421] (7/8) Epoch 6, batch 11200, loss[loss=2.753, over 770.00 frames. , ppl: 15.682708258514346] tot_loss[loss=2.292, over 5387877.64 frames. , ppl: 9.893200587474212], batch size: 70
+2022-12-12 00:23:23,935 INFO [train.py:421] (7/8) Epoch 6, batch 11400, loss[loss=2.223, over 3500.00 frames. , ppl: 9.234521515388595] tot_loss[loss=2.291, over 5455531.06 frames. , ppl: 9.883291940382593], batch size: 70
+2022-12-12 00:25:02,701 INFO [train.py:421] (7/8) Epoch 6, batch 11600, loss[loss=2.365, over 2030.00 frames. , ppl: 10.638982011499753] tot_loss[loss=2.291, over 5437352.95 frames. , ppl: 9.886475222825919], batch size: 70
+2022-12-12 00:26:41,476 INFO [train.py:421] (7/8) Epoch 6, batch 11800, loss[loss=2.334, over 1400.00 frames. , ppl: 10.320664253228037] tot_loss[loss=2.293, over 5379492.02 frames. , ppl: 9.90428887654372], batch size: 70
+2022-12-12 00:28:20,382 INFO [train.py:421] (7/8) Epoch 6, batch 12000, loss[loss=2.294, over 2940.00 frames. , ppl: 9.91623859329888] tot_loss[loss=2.292, over 5389301.43 frames. , ppl: 9.899490222330252], batch size: 70
+2022-12-12 00:28:20,383 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 00:28:21,131 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.283, over 211138.00 frames. , ppl: 9.80987272894533
+2022-12-12 00:30:01,073 INFO [train.py:421] (7/8) Epoch 6, batch 12200, loss[loss=2.224, over 6650.00 frames. , ppl: 9.245984782328224] tot_loss[loss=2.291, over 5420887.59 frames. , ppl: 9.885534255909969], batch size: 70
+2022-12-12 00:31:40,362 INFO [train.py:421] (7/8) Epoch 6, batch 12400, loss[loss=2.436, over 770.00 frames. , ppl: 11.428957326486445] tot_loss[loss=2.291, over 5433349.80 frames. , ppl: 9.880695950715435], batch size: 70
+2022-12-12 00:33:20,724 INFO [train.py:421] (7/8) Epoch 6, batch 12600, loss[loss=2.297, over 2310.00 frames. , ppl: 9.939924388943242] tot_loss[loss=2.291, over 5426431.91 frames. , ppl: 9.880958536540778], batch size: 70
+2022-12-12 00:35:01,337 INFO [train.py:421] (7/8) Epoch 6, batch 12800, loss[loss=2.311, over 2450.00 frames. , ppl: 10.086378254668388] tot_loss[loss=2.29, over 5455107.50 frames. , ppl: 9.876585591593821], batch size: 70
+2022-12-12 00:36:42,475 INFO [train.py:421] (7/8) Epoch 6, batch 13000, loss[loss=2.145, over 5530.00 frames. , ppl: 8.538598999928508] tot_loss[loss=2.289, over 5497270.90 frames. , ppl: 9.866184516904159], batch size: 70
+2022-12-12 00:36:42,476 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 00:36:43,214 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.283, over 211138.00 frames. , ppl: 9.805265371495329
+2022-12-12 00:38:26,661 INFO [train.py:421] (7/8) Epoch 6, batch 13200, loss[loss=2.471, over 1540.00 frames. , ppl: 11.834431606226781] tot_loss[loss=2.289, over 5496095.63 frames. , ppl: 9.867827655730633], batch size: 70
+2022-12-12 00:40:05,818 INFO [train.py:421] (7/8) Epoch 6, batch 13400, loss[loss=2.18, over 4620.00 frames. , ppl: 8.847614542483095] tot_loss[loss=2.289, over 5507494.57 frames. , ppl: 9.863777372561277], batch size: 70
+2022-12-12 00:41:44,770 INFO [train.py:421] (7/8) Epoch 6, batch 13600, loss[loss=2.254, over 3710.00 frames. , ppl: 9.530136313904585] tot_loss[loss=2.288, over 5501477.57 frames. , ppl: 9.85917998906497], batch size: 70
+2022-12-12 00:43:25,850 INFO [train.py:421] (7/8) Epoch 6, batch 13800, loss[loss=2.621, over 910.00 frames. , ppl: 13.75339693010662] tot_loss[loss=2.288, over 5518705.53 frames. , ppl: 9.859201595596147], batch size: 70
+2022-12-12 00:45:05,055 INFO [train.py:421] (7/8) Epoch 6, batch 14000, loss[loss=3.126, over 560.00 frames. , ppl: 22.793726261439325] tot_loss[loss=2.289, over 5533318.03 frames. , ppl: 9.860292353995927], batch size: 70
+2022-12-12 00:45:05,055 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 00:45:05,803 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.285, over 211138.00 frames. , ppl: 9.822797644344924
+2022-12-12 00:46:45,803 INFO [train.py:421] (7/8) Epoch 6, batch 14200, loss[loss=2.398, over 1680.00 frames. , ppl: 10.997303940997051] tot_loss[loss=2.29, over 5495259.68 frames. , ppl: 9.871365368963216], batch size: 70
+2022-12-12 00:48:26,187 INFO [train.py:421] (7/8) Epoch 6, batch 14400, loss[loss=2.26, over 3220.00 frames. , ppl: 9.586391944238963] tot_loss[loss=2.291, over 5460156.96 frames. , ppl: 9.880091789243915], batch size: 70
+2022-12-12 00:50:08,160 INFO [train.py:421] (7/8) Epoch 6, batch 14600, loss[loss=2.156, over 4270.00 frames. , ppl: 8.639355522910574] tot_loss[loss=2.29, over 5473249.25 frames. , ppl: 9.877395102588387], batch size: 70
+2022-12-12 00:51:47,347 INFO [train.py:421] (7/8) Epoch 6, batch 14800, loss[loss=2.48, over 1260.00 frames. , ppl: 11.94362515734963] tot_loss[loss=2.291, over 5461323.11 frames. , ppl: 9.886390043708225], batch size: 70
+2022-12-12 00:53:30,892 INFO [train.py:421] (7/8) Epoch 6, batch 15000, loss[loss=2.386, over 1820.00 frames. , ppl: 10.871697585697731] tot_loss[loss=2.292, over 5443019.26 frames. , ppl: 9.889960419188501], batch size: 70
+2022-12-12 00:53:30,893 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 00:53:31,639 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.282, over 211138.00 frames. , ppl: 9.800679035400885
+2022-12-12 00:55:13,337 INFO [train.py:421] (7/8) Epoch 6, batch 15200, loss[loss=2.425, over 1190.00 frames. , ppl: 11.307197310815132] tot_loss[loss=2.291, over 5471847.24 frames. , ppl: 9.88251900302701], batch size: 70
+2022-12-12 00:56:51,708 INFO [train.py:421] (7/8) Epoch 6, batch 15400, loss[loss=2.253, over 3640.00 frames. , ppl: 9.51516934472434] tot_loss[loss=2.291, over 5458120.71 frames. , ppl: 9.889580000025465], batch size: 70
+2022-12-12 00:58:34,883 INFO [train.py:421] (7/8) Epoch 6, batch 15600, loss[loss=2.558, over 840.00 frames. , ppl: 12.914797316758753] tot_loss[loss=2.29, over 5501739.21 frames. , ppl: 9.873070273629674], batch size: 70
+2022-12-12 01:00:14,971 INFO [train.py:421] (7/8) Epoch 6, batch 15800, loss[loss=2.45, over 840.00 frames. , ppl: 11.590812415201814] tot_loss[loss=2.291, over 5449089.44 frames. , ppl: 9.887624920514012], batch size: 70
+2022-12-12 01:01:54,259 INFO [train.py:421] (7/8) Epoch 6, batch 16000, loss[loss=2.299, over 3360.00 frames. , ppl: 9.961387533990951] tot_loss[loss=2.291, over 5476934.36 frames. , ppl: 9.887916454008215], batch size: 70
+2022-12-12 01:01:54,260 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 01:01:55,007 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.283, over 211138.00 frames. , ppl: 9.805294396587579
+2022-12-12 01:03:38,892 INFO [train.py:421] (7/8) Epoch 6, batch 16200, loss[loss=2.225, over 3290.00 frames. , ppl: 9.249166017210246] tot_loss[loss=2.291, over 5480488.16 frames. , ppl: 9.886022384422064], batch size: 70
+2022-12-12 01:05:19,348 INFO [train.py:421] (7/8) Epoch 6, batch 16400, loss[loss=2.243, over 2940.00 frames. , ppl: 9.424619189098792] tot_loss[loss=2.291, over 5469988.73 frames. , ppl: 9.88903381643003], batch size: 70
+2022-12-12 01:07:02,719 INFO [train.py:421] (7/8) Epoch 6, batch 16600, loss[loss=2.386, over 1330.00 frames. , ppl: 10.867176982415515] tot_loss[loss=2.291, over 5513539.37 frames. , ppl: 9.881372866044352], batch size: 70
+2022-12-12 01:08:42,211 INFO [train.py:421] (7/8) Epoch 6, batch 16800, loss[loss=2.217, over 4900.00 frames. , ppl: 9.18110383628414] tot_loss[loss=2.289, over 5565159.15 frames. , ppl: 9.864730554478895], batch size: 70
+2022-12-12 01:10:19,698 INFO [train.py:421] (7/8) Epoch 6, batch 17000, loss[loss=2.566, over 910.00 frames. , ppl: 13.009878761924783] tot_loss[loss=2.288, over 5590352.24 frames. , ppl: 9.857361283983415], batch size: 70
+2022-12-12 01:10:19,699 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 01:10:20,459 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.283, over 211138.00 frames. , ppl: 9.80433371167732
+2022-12-12 01:12:00,282 INFO [train.py:421] (7/8) Epoch 6, batch 17200, loss[loss=2.484, over 1260.00 frames. , ppl: 11.98921656840557] tot_loss[loss=2.288, over 5582198.05 frames. , ppl: 9.8580190114736], batch size: 70
+2022-12-12 01:13:40,303 INFO [train.py:421] (7/8) Epoch 6, batch 17400, loss[loss=2.322, over 2730.00 frames. , ppl: 10.190972310209267] tot_loss[loss=2.288, over 5617243.41 frames. , ppl: 9.85426698487827], batch size: 70
+2022-12-12 01:15:20,954 INFO [train.py:421] (7/8) Epoch 6, batch 17600, loss[loss=2.184, over 7490.00 frames. , ppl: 8.879695702465627] tot_loss[loss=2.289, over 5578891.72 frames. , ppl: 9.864873360121846], batch size: 70
+2022-12-12 01:17:03,082 INFO [train.py:421] (7/8) Epoch 6, batch 17800, loss[loss=2.147, over 8680.00 frames. , ppl: 8.558579060654562] tot_loss[loss=2.288, over 5578806.65 frames. , ppl: 9.859061631456527], batch size: 70
+2022-12-12 01:18:44,985 INFO [train.py:421] (7/8) Epoch 6, batch 18000, loss[loss=2.205, over 3640.00 frames. , ppl: 9.074098898722315] tot_loss[loss=2.289, over 5551976.88 frames. , ppl: 9.86146979721039], batch size: 70
+2022-12-12 01:18:44,986 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 01:18:45,748 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.283, over 211138.00 frames. , ppl: 9.802139871930427
+2022-12-12 01:20:22,570 INFO [train.py:421] (7/8) Epoch 6, batch 18200, loss[loss=2.266, over 4830.00 frames. , ppl: 9.642277712888374] tot_loss[loss=2.288, over 5540727.93 frames. , ppl: 9.859826271472532], batch size: 70
+2022-12-12 01:22:05,359 INFO [train.py:421] (7/8) Epoch 6, batch 18400, loss[loss=2.254, over 3150.00 frames. , ppl: 9.529193809267566] tot_loss[loss=2.289, over 5549319.10 frames. , ppl: 9.861146796396442], batch size: 70
+2022-12-12 01:23:45,410 INFO [train.py:421] (7/8) Epoch 6, batch 18600, loss[loss=2.257, over 5460.00 frames. , ppl: 9.55322908131278] tot_loss[loss=2.289, over 5532617.65 frames. , ppl: 9.867196955439292], batch size: 70
+2022-12-12 01:25:24,440 INFO [train.py:421] (7/8) Epoch 6, batch 18800, loss[loss=2.357, over 1750.00 frames. , ppl: 10.559429500365589] tot_loss[loss=2.29, over 5507520.54 frames. , ppl: 9.878704799839463], batch size: 70
+2022-12-12 01:27:04,204 INFO [train.py:421] (7/8) Epoch 6, batch 19000, loss[loss=2.361, over 3640.00 frames. , ppl: 10.597580826987878] tot_loss[loss=2.291, over 5497072.09 frames. , ppl: 9.883312930243857], batch size: 70
+2022-12-12 01:27:04,204 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 01:27:04,968 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.282, over 211138.00 frames. , ppl: 9.798580280075496
+2022-12-12 01:28:43,251 INFO [train.py:421] (7/8) Epoch 6, batch 19200, loss[loss=2.431, over 1400.00 frames. , ppl: 11.37219710620362] tot_loss[loss=2.292, over 5488677.65 frames. , ppl: 9.890007557221871], batch size: 70
+2022-12-12 01:30:21,610 INFO [train.py:421] (7/8) Epoch 6, batch 19400, loss[loss=2.279, over 2520.00 frames. , ppl: 9.768528998494768] tot_loss[loss=2.291, over 5512803.53 frames. , ppl: 9.881248784403661], batch size: 70
+2022-12-12 01:32:02,266 INFO [train.py:421] (7/8) Epoch 6, batch 19600, loss[loss=2.275, over 11760.00 frames. , ppl: 9.727708982562204] tot_loss[loss=2.29, over 5530507.70 frames. , ppl: 9.879439566344413], batch size: 70
+2022-12-12 01:33:40,022 INFO [train.py:421] (7/8) Epoch 6, batch 19800, loss[loss=2.39, over 1680.00 frames. , ppl: 10.914063003407966] tot_loss[loss=2.29, over 5537215.69 frames. , ppl: 9.877530497741624], batch size: 70
+2022-12-12 01:35:20,121 INFO [train.py:421] (7/8) Epoch 6, batch 20000, loss[loss=3.561, over 420.00 frames. , ppl: 35.19567685575272] tot_loss[loss=2.292, over 5499711.99 frames. , ppl: 9.890948067863576], batch size: 70
+2022-12-12 01:35:20,121 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 01:35:20,866 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.284, over 211138.00 frames. , ppl: 9.811063387394697
+2022-12-12 01:36:57,458 INFO [train.py:421] (7/8) Epoch 6, batch 20200, loss[loss=2.401, over 980.00 frames. , ppl: 11.037498494462838] tot_loss[loss=2.293, over 5456796.29 frames. , ppl: 9.902038430066884], batch size: 70
+2022-12-12 01:38:35,708 INFO [train.py:421] (7/8) Epoch 6, batch 20400, loss[loss=2.503, over 1260.00 frames. , ppl: 12.219205512937] tot_loss[loss=2.293, over 5427798.80 frames. , ppl: 9.906327024937315], batch size: 70
+2022-12-12 01:40:16,783 INFO [train.py:421] (7/8) Epoch 6, batch 20600, loss[loss=2.409, over 1610.00 frames. , ppl: 11.119555968588596] tot_loss[loss=2.294, over 5379603.67 frames. , ppl: 9.918918883406166], batch size: 70
+2022-12-12 01:41:54,632 INFO [train.py:421] (7/8) Epoch 6, batch 20800, loss[loss=2.336, over 1680.00 frames. , ppl: 10.336930881218745] tot_loss[loss=2.293, over 5421107.06 frames. , ppl: 9.905678229043142], batch size: 70
+2022-12-12 01:43:37,330 INFO [train.py:421] (7/8) Epoch 6, batch 21000, loss[loss=2.435, over 1680.00 frames. , ppl: 11.419920749215805] tot_loss[loss=2.292, over 5462453.48 frames. , ppl: 9.892826711105606], batch size: 70
+2022-12-12 01:43:37,330 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 01:43:38,089 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.281, over 211138.00 frames. , ppl: 9.790676635383708
+2022-12-12 01:45:21,910 INFO [train.py:421] (7/8) Epoch 6, batch 21200, loss[loss=2.224, over 5670.00 frames. , ppl: 9.246947520029286] tot_loss[loss=2.291, over 5485423.28 frames. , ppl: 9.882551150980193], batch size: 70
+2022-12-12 01:47:02,220 INFO [train.py:421] (7/8) Epoch 6, batch 21400, loss[loss=2.204, over 6300.00 frames. , ppl: 9.063266543321824] tot_loss[loss=2.292, over 5463122.36 frames. , ppl: 9.890822131642338], batch size: 70
+2022-12-12 01:48:39,310 INFO [train.py:421] (7/8) Epoch 6, batch 21600, loss[loss=2.284, over 3080.00 frames. , ppl: 9.820456255966006] tot_loss[loss=2.291, over 5486965.61 frames. , ppl: 9.882077639644674], batch size: 70
+2022-12-12 01:50:16,075 INFO [train.py:421] (7/8) Epoch 6, batch 21800, loss[loss=2.213, over 5460.00 frames. , ppl: 9.14463944205632] tot_loss[loss=2.291, over 5489379.00 frames. , ppl: 9.881686962137353], batch size: 70
+2022-12-12 01:51:58,033 INFO [train.py:421] (7/8) Epoch 6, batch 22000, loss[loss=2.215, over 6090.00 frames. , ppl: 9.165343561029792] tot_loss[loss=2.29, over 5535194.48 frames. , ppl: 9.873983591746699], batch size: 70
+2022-12-12 01:51:58,033 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 01:51:58,792 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.28, over 211138.00 frames. , ppl: 9.776022789235363
+2022-12-12 01:53:38,880 INFO [train.py:421] (7/8) Epoch 6, batch 22200, loss[loss=2.429, over 1330.00 frames. , ppl: 11.345944404744149] tot_loss[loss=2.29, over 5522852.60 frames. , ppl: 9.876601678443524], batch size: 70
+2022-12-12 01:55:20,547 INFO [train.py:421] (7/8) Epoch 6, batch 22400, loss[loss=2.216, over 5040.00 frames. , ppl: 9.172742552791192] tot_loss[loss=2.29, over 5509856.18 frames. , ppl: 9.877627646229403], batch size: 70
+2022-12-12 01:57:04,223 INFO [train.py:421] (7/8) Epoch 6, batch 22600, loss[loss=2.311, over 2520.00 frames. , ppl: 10.087946555739821] tot_loss[loss=2.29, over 5510623.32 frames. , ppl: 9.876173459729763], batch size: 70
+2022-12-12 01:58:41,919 INFO [train.py:421] (7/8) Epoch 6, batch 22800, loss[loss=2.241, over 3570.00 frames. , ppl: 9.402811932779523] tot_loss[loss=2.291, over 5488561.26 frames. , ppl: 9.885194823392968], batch size: 70
+2022-12-12 02:00:22,244 INFO [train.py:421] (7/8) Epoch 6, batch 23000, loss[loss=2.215, over 2800.00 frames. , ppl: 9.164902181154078] tot_loss[loss=2.291, over 5472608.47 frames. , ppl: 9.88728914170054], batch size: 70
+2022-12-12 02:00:22,244 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 02:00:23,004 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.282, over 211138.00 frames. , ppl: 9.793408557185776
+2022-12-12 02:01:58,413 INFO [train.py:421] (7/8) Epoch 6, batch 23200, loss[loss=2.349, over 2450.00 frames. , ppl: 10.47829571160179] tot_loss[loss=2.293, over 5413800.42 frames. , ppl: 9.90317249769203], batch size: 70
+2022-12-12 02:03:43,853 INFO [train.py:421] (7/8) Epoch 6, batch 23400, loss[loss=2.157, over 5810.00 frames. , ppl: 8.644770780825459] tot_loss[loss=2.292, over 5433914.11 frames. , ppl: 9.899385452155276], batch size: 70
+2022-12-12 02:05:24,908 INFO [train.py:421] (7/8) Epoch 6, batch 23600, loss[loss=2.565, over 1120.00 frames. , ppl: 13.006044497260403] tot_loss[loss=2.293, over 5418144.76 frames. , ppl: 9.90238758215091], batch size: 70
+2022-12-12 02:07:03,693 INFO [train.py:421] (7/8) Epoch 6, batch 23800, loss[loss=2.259, over 2520.00 frames. , ppl: 9.570336324988576] tot_loss[loss=2.293, over 5417806.93 frames. , ppl: 9.90578562181315], batch size: 70
+2022-12-12 02:08:44,621 INFO [train.py:421] (7/8) Epoch 6, batch 24000, loss[loss=2.336, over 1890.00 frames. , ppl: 10.34152590678299] tot_loss[loss=2.293, over 5420036.56 frames. , ppl: 9.904690514928292], batch size: 70
+2022-12-12 02:08:44,622 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 02:08:45,409 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.281, over 211138.00 frames. , ppl: 9.790136138531322
+2022-12-12 02:10:29,007 INFO [train.py:421] (7/8) Epoch 6, batch 24200, loss[loss=2.18, over 3640.00 frames. , ppl: 8.848699387447876] tot_loss[loss=2.291, over 5501315.74 frames. , ppl: 9.888751930323645], batch size: 70
+2022-12-12 02:12:08,531 INFO [train.py:421] (7/8) Epoch 6, batch 24400, loss[loss=2.545, over 840.00 frames. , ppl: 12.738152013680928] tot_loss[loss=2.292, over 5480976.63 frames. , ppl: 9.898384749279913], batch size: 70
+2022-12-12 02:13:52,338 INFO [train.py:421] (7/8) Epoch 6, batch 24600, loss[loss=2.308, over 2870.00 frames. , ppl: 10.05785441096279] tot_loss[loss=2.292, over 5463272.54 frames. , ppl: 9.898817586353752], batch size: 70
+2022-12-12 02:15:29,118 INFO [train.py:421] (7/8) Epoch 6, batch 24800, loss[loss=2.386, over 1330.00 frames. , ppl: 10.865429654803288] tot_loss[loss=2.293, over 5452731.68 frames. , ppl: 9.905170936935084], batch size: 70
+2022-12-12 02:17:09,491 INFO [train.py:421] (7/8) Epoch 6, batch 25000, loss[loss=2.183, over 5040.00 frames. , ppl: 8.875977292826725] tot_loss[loss=2.293, over 5451641.91 frames. , ppl: 9.905978750581703], batch size: 70
+2022-12-12 02:17:09,491 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 02:17:10,254 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.281, over 211138.00 frames. , ppl: 9.788068615004098
+2022-12-12 02:18:49,722 INFO [train.py:421] (7/8) Epoch 6, batch 25200, loss[loss=2.279, over 2450.00 frames. , ppl: 9.76798238076426] tot_loss[loss=2.293, over 5454028.35 frames. , ppl: 9.904630143100583], batch size: 70
+2022-12-12 02:20:33,643 INFO [train.py:421] (7/8) Epoch 6, batch 25400, loss[loss=2.308, over 2450.00 frames. , ppl: 10.05088243640459] tot_loss[loss=2.292, over 5490542.47 frames. , ppl: 9.891155376092383], batch size: 70
+2022-12-12 02:22:12,267 INFO [train.py:421] (7/8) Epoch 6, batch 25600, loss[loss=2.235, over 3290.00 frames. , ppl: 9.350852107515323] tot_loss[loss=2.292, over 5472597.27 frames. , ppl: 9.898790029657862], batch size: 70
+2022-12-12 02:23:50,883 INFO [train.py:421] (7/8) Epoch 6, batch 25800, loss[loss=2.287, over 2310.00 frames. , ppl: 9.843450007629484] tot_loss[loss=2.291, over 5493513.29 frames. , ppl: 9.885562110036604], batch size: 70
+2022-12-12 02:25:30,634 INFO [train.py:421] (7/8) Epoch 6, batch 26000, loss[loss=2.202, over 6160.00 frames. , ppl: 9.046073085179263] tot_loss[loss=2.291, over 5504334.58 frames. , ppl: 9.884992007615436], batch size: 70
+2022-12-12 02:25:30,635 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 02:25:31,395 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.283, over 211138.00 frames. , ppl: 9.806832849432856
+2022-12-12 02:27:11,365 INFO [train.py:421] (7/8) Epoch 6, batch 26200, loss[loss=2.501, over 1400.00 frames. , ppl: 12.189666118025187] tot_loss[loss=2.29, over 5496049.01 frames. , ppl: 9.878746919226925], batch size: 70
+2022-12-12 02:28:48,581 INFO [train.py:421] (7/8) Epoch 6, batch 26400, loss[loss=2.496, over 770.00 frames. , ppl: 12.136153250465313] tot_loss[loss=2.289, over 5537099.78 frames. , ppl: 9.866048913695218], batch size: 70
+2022-12-12 02:30:30,703 INFO [train.py:421] (7/8) Epoch 6, batch 26600, loss[loss=2.247, over 3010.00 frames. , ppl: 9.462411523356016] tot_loss[loss=2.288, over 5556807.44 frames. , ppl: 9.855535182710552], batch size: 70
+2022-12-12 02:32:10,390 INFO [train.py:421] (7/8) Epoch 6, batch 26800, loss[loss=2.398, over 1400.00 frames. , ppl: 10.997559008377436] tot_loss[loss=2.289, over 5515792.63 frames. , ppl: 9.864636295432176], batch size: 70
+2022-12-12 02:33:50,899 INFO [train.py:421] (7/8) Epoch 6, batch 27000, loss[loss=2.196, over 1890.00 frames. , ppl: 8.985992320303048] tot_loss[loss=2.289, over 5516136.96 frames. , ppl: 9.86535115775996], batch size: 70
+2022-12-12 02:33:50,900 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 02:33:51,644 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.283, over 211138.00 frames. , ppl: 9.810623407744394
+2022-12-12 02:35:28,235 INFO [train.py:421] (7/8) Epoch 6, batch 27200, loss[loss=2.356, over 3150.00 frames. , ppl: 10.54391962759694] tot_loss[loss=2.292, over 5442413.61 frames. , ppl: 9.8927337328535], batch size: 70
+2022-12-12 02:37:07,150 INFO [train.py:421] (7/8) Epoch 6, batch 27400, loss[loss=2.458, over 1050.00 frames. , ppl: 11.687232700519958] tot_loss[loss=2.292, over 5428455.50 frames. , ppl: 9.892852221909108], batch size: 70
+2022-12-12 02:38:49,959 INFO [train.py:421] (7/8) Epoch 6, batch 27600, loss[loss=2.258, over 4060.00 frames. , ppl: 9.566833035779123] tot_loss[loss=2.291, over 5462367.65 frames. , ppl: 9.889541897241429], batch size: 70
+2022-12-12 02:40:23,827 INFO [train.py:421] (7/8) Epoch 6, batch 27800, loss[loss=2.354, over 1050.00 frames. , ppl: 10.52371642656517] tot_loss[loss=2.291, over 5463872.12 frames. , ppl: 9.887970223392184], batch size: 70
+2022-12-12 02:42:02,135 INFO [train.py:421] (7/8) Epoch 6, batch 28000, loss[loss=2.441, over 1400.00 frames. , ppl: 11.479074558541848] tot_loss[loss=2.292, over 5421859.99 frames. , ppl: 9.89867986291606], batch size: 70
+2022-12-12 02:42:02,135 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 02:42:02,898 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.284, over 211138.00 frames. , ppl: 9.819234910695574
+2022-12-12 02:43:40,809 INFO [train.py:421] (7/8) Epoch 6, batch 28200, loss[loss=2.435, over 1330.00 frames. , ppl: 11.416030783750026] tot_loss[loss=2.293, over 5402213.72 frames. , ppl: 9.90208694236865], batch size: 70
+2022-12-12 02:45:19,070 INFO [train.py:421] (7/8) Epoch 6, batch 28400, loss[loss=2.366, over 1120.00 frames. , ppl: 10.653075717766846] tot_loss[loss=2.292, over 5410651.45 frames. , ppl: 9.897581240213816], batch size: 70
+2022-12-12 02:46:59,636 INFO [train.py:421] (7/8) Epoch 6, batch 28600, loss[loss=2.405, over 1260.00 frames. , ppl: 11.076376621706114] tot_loss[loss=2.294, over 5357760.24 frames. , ppl: 9.916040303121823], batch size: 70
+2022-12-12 02:48:38,765 INFO [train.py:421] (7/8) Epoch 6, batch 28800, loss[loss=2.346, over 2030.00 frames. , ppl: 10.448560004033387] tot_loss[loss=2.293, over 5386237.28 frames. , ppl: 9.906208083667186], batch size: 70
+2022-12-12 02:50:20,988 INFO [train.py:421] (7/8) Epoch 6, batch 29000, loss[loss=3.549, over 420.00 frames. , ppl: 34.76755231436225] tot_loss[loss=2.293, over 5382622.19 frames. , ppl: 9.9057821667099], batch size: 70
+2022-12-12 02:50:20,989 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 02:50:21,747 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.282, over 211138.00 frames. , ppl: 9.796046998105865
+2022-12-12 02:51:59,585 INFO [train.py:421] (7/8) Epoch 6, batch 29200, loss[loss=2.322, over 1680.00 frames. , ppl: 10.19816188073486] tot_loss[loss=2.293, over 5388776.15 frames. , ppl: 9.902122267015404], batch size: 70
+2022-12-12 02:53:38,992 INFO [train.py:421] (7/8) Epoch 6, batch 29400, loss[loss=2.373, over 1960.00 frames. , ppl: 10.734773384168989] tot_loss[loss=2.292, over 5399318.48 frames. , ppl: 9.896488041484636], batch size: 70
+2022-12-12 02:55:17,413 INFO [train.py:421] (7/8) Epoch 6, batch 29600, loss[loss=2.303, over 2730.00 frames. , ppl: 10.005776338683344] tot_loss[loss=2.292, over 5390025.32 frames. , ppl: 9.892682586439843], batch size: 70
+2022-12-12 02:57:01,349 INFO [train.py:421] (7/8) Epoch 6, batch 29800, loss[loss=2.807, over 700.00 frames. , ppl: 16.560051085357923] tot_loss[loss=2.291, over 5391753.55 frames. , ppl: 9.889175968888745], batch size: 70
+2022-12-12 02:58:45,207 INFO [train.py:421] (7/8) Epoch 6, batch 30000, loss[loss=2.321, over 2240.00 frames. , ppl: 10.188917556967231] tot_loss[loss=2.289, over 5464694.87 frames. , ppl: 9.867157114442676], batch size: 70
+2022-12-12 02:58:45,207 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 02:58:45,956 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.282, over 211138.00 frames. , ppl: 9.793146201640242
+2022-12-12 03:00:24,701 INFO [train.py:421] (7/8) Epoch 6, batch 30200, loss[loss=2.592, over 840.00 frames. , ppl: 13.357704459787191] tot_loss[loss=2.291, over 5440678.16 frames. , ppl: 9.881598183919875], batch size: 70
+2022-12-12 03:02:01,496 INFO [train.py:421] (7/8) Epoch 6, batch 30400, loss[loss=2.278, over 2940.00 frames. , ppl: 9.758807146112959] tot_loss[loss=2.292, over 5423413.86 frames. , ppl: 9.896224343164448], batch size: 70
+2022-12-12 03:03:40,081 INFO [train.py:421] (7/8) Epoch 6, batch 30600, loss[loss=2.304, over 3010.00 frames. , ppl: 10.011065032082422] tot_loss[loss=2.292, over 5433574.64 frames. , ppl: 9.891679506970613], batch size: 70
+2022-12-12 03:05:19,259 INFO [train.py:421] (7/8) Epoch 6, batch 30800, loss[loss=2.226, over 4690.00 frames. , ppl: 9.26722709819449] tot_loss[loss=2.293, over 5376983.71 frames. , ppl: 9.905783345595998], batch size: 70
+2022-12-12 03:07:01,537 INFO [train.py:421] (7/8) Epoch 6, batch 31000, loss[loss=2.523, over 840.00 frames. , ppl: 12.464885161939169] tot_loss[loss=2.295, over 5346174.09 frames. , ppl: 9.921727963501276], batch size: 70
+2022-12-12 03:07:01,538 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 03:07:02,295 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.282, over 211138.00 frames. , ppl: 9.792647600527868
+2022-12-12 03:08:42,303 INFO [train.py:421] (7/8) Epoch 6, batch 31200, loss[loss=2.471, over 2170.00 frames. , ppl: 11.838788699116249] tot_loss[loss=2.296, over 5307794.04 frames. , ppl: 9.93378607327119], batch size: 70
+2022-12-12 03:10:23,242 INFO [train.py:421] (7/8) Epoch 6, batch 31400, loss[loss=2.419, over 1190.00 frames. , ppl: 11.231571126138986] tot_loss[loss=2.295, over 5314229.20 frames. , ppl: 9.925644435073893], batch size: 70
+2022-12-12 03:12:05,124 INFO [train.py:421] (7/8) Epoch 6, batch 31600, loss[loss=2.177, over 4410.00 frames. , ppl: 8.816739974689575] tot_loss[loss=2.294, over 5335593.47 frames. , ppl: 9.917767743137741], batch size: 70
+2022-12-12 03:13:47,715 INFO [train.py:421] (7/8) Epoch 6, batch 31800, loss[loss=2.519, over 840.00 frames. , ppl: 12.419551887062017] tot_loss[loss=2.293, over 5381406.90 frames. , ppl: 9.903934590180798], batch size: 70
+2022-12-12 03:15:28,301 INFO [train.py:421] (7/8) Epoch 6, batch 32000, loss[loss=2.387, over 1610.00 frames. , ppl: 10.875982850743908] tot_loss[loss=2.293, over 5374275.93 frames. , ppl: 9.9095508316724], batch size: 70
+2022-12-12 03:15:28,301 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 03:15:29,060 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.281, over 211138.00 frames. , ppl: 9.786621463485243
+2022-12-12 03:17:08,910 INFO [train.py:421] (7/8) Epoch 6, batch 32200, loss[loss=2.592, over 840.00 frames. , ppl: 13.356823199647145] tot_loss[loss=2.293, over 5410112.03 frames. , ppl: 9.904716567790764], batch size: 70
+2022-12-12 03:18:47,923 INFO [train.py:421] (7/8) Epoch 6, batch 32400, loss[loss=2.389, over 1750.00 frames. , ppl: 10.90001266207693] tot_loss[loss=2.293, over 5430378.03 frames. , ppl: 9.900157998984785], batch size: 70
+2022-12-12 03:20:28,911 INFO [train.py:421] (7/8) Epoch 6, batch 32600, loss[loss=2.164, over 5670.00 frames. , ppl: 8.704723502374183] tot_loss[loss=2.294, over 5418924.48 frames. , ppl: 9.909626214609078], batch size: 70
+2022-12-12 03:22:12,184 INFO [train.py:421] (7/8) Epoch 6, batch 32800, loss[loss=2.21, over 2590.00 frames. , ppl: 9.112798425836122] tot_loss[loss=2.293, over 5425650.59 frames. , ppl: 9.904619795380126], batch size: 70
+2022-12-12 03:23:51,246 INFO [train.py:421] (7/8) Epoch 6, batch 33000, loss[loss=2.371, over 2100.00 frames. , ppl: 10.71221194129101] tot_loss[loss=2.293, over 5438158.45 frames. , ppl: 9.900685684799953], batch size: 70
+2022-12-12 03:23:51,247 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 03:23:52,003 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.283, over 211138.00 frames. , ppl: 9.805240700234473
+2022-12-12 03:25:32,458 INFO [train.py:421] (7/8) Epoch 6, batch 33200, loss[loss=2.382, over 2240.00 frames. , ppl: 10.824916306320839] tot_loss[loss=2.293, over 5460703.71 frames. , ppl: 9.904832379695263], batch size: 70
+2022-12-12 03:27:11,787 INFO [train.py:421] (7/8) Epoch 6, batch 33400, loss[loss=2.323, over 1820.00 frames. , ppl: 10.204217596263245] tot_loss[loss=2.292, over 5471718.78 frames. , ppl: 9.898015230367657], batch size: 70
+2022-12-12 03:28:50,125 INFO [train.py:421] (7/8) Epoch 6, batch 33600, loss[loss=2.963, over 630.00 frames. , ppl: 19.34839135659848] tot_loss[loss=2.292, over 5480083.46 frames. , ppl: 9.892943504265368], batch size: 70
+2022-12-12 03:30:30,181 INFO [train.py:421] (7/8) Epoch 6, batch 33800, loss[loss=2.269, over 3430.00 frames. , ppl: 9.669951786950278] tot_loss[loss=2.292, over 5465262.74 frames. , ppl: 9.893879089037817], batch size: 70
+2022-12-12 03:32:08,724 INFO [train.py:421] (7/8) Epoch 6, batch 34000, loss[loss=2.249, over 2590.00 frames. , ppl: 9.479572233549925] tot_loss[loss=2.291, over 5495188.55 frames. , ppl: 9.880257727316652], batch size: 70
+2022-12-12 03:32:08,724 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 03:32:09,480 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.281, over 211138.00 frames. , ppl: 9.78966811844687
+2022-12-12 03:33:48,819 INFO [train.py:421] (7/8) Epoch 6, batch 34200, loss[loss=2.41, over 1470.00 frames. , ppl: 11.130301906498817] tot_loss[loss=2.291, over 5481777.28 frames. , ppl: 9.880734116405785], batch size: 70
+2022-12-12 03:35:27,543 INFO [train.py:421] (7/8) Epoch 6, batch 34400, loss[loss=2.284, over 3920.00 frames. , ppl: 9.816015301724212] tot_loss[loss=2.291, over 5477581.45 frames. , ppl: 9.880303158262242], batch size: 70
+2022-12-12 03:37:07,527 INFO [train.py:421] (7/8) Epoch 6, batch 34600, loss[loss=2.504, over 1610.00 frames. , ppl: 12.22665725133901] tot_loss[loss=2.291, over 5463570.22 frames. , ppl: 9.883558771262328], batch size: 70
+2022-12-12 03:38:50,946 INFO [train.py:421] (7/8) Epoch 6, batch 34800, loss[loss=2.427, over 1400.00 frames. , ppl: 11.327171710001792] tot_loss[loss=2.291, over 5474066.44 frames. , ppl: 9.880030740541946], batch size: 70
+2022-12-12 03:40:30,320 INFO [train.py:421] (7/8) Epoch 6, batch 35000, loss[loss=2.256, over 2380.00 frames. , ppl: 9.54649518435196] tot_loss[loss=2.291, over 5471116.27 frames. , ppl: 9.88203751274422], batch size: 70
+2022-12-12 03:40:30,320 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 03:40:31,078 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.28, over 211138.00 frames. , ppl: 9.778649309689856
+2022-12-12 03:42:08,436 INFO [train.py:421] (7/8) Epoch 6, batch 35200, loss[loss=2.225, over 6440.00 frames. , ppl: 9.25467981043106] tot_loss[loss=2.291, over 5456626.79 frames. , ppl: 9.885205634948072], batch size: 70
+2022-12-12 03:43:48,389 INFO [train.py:421] (7/8) Epoch 6, batch 35400, loss[loss=2.256, over 3990.00 frames. , ppl: 9.547189502207663] tot_loss[loss=2.29, over 5498486.11 frames. , ppl: 9.873421383092323], batch size: 70
+2022-12-12 03:45:30,989 INFO [train.py:421] (7/8) Epoch 6, batch 35600, loss[loss=2.233, over 3500.00 frames. , ppl: 9.326623449845318] tot_loss[loss=2.289, over 5521622.17 frames. , ppl: 9.862926188668057], batch size: 70
+2022-12-12 03:47:10,358 INFO [train.py:421] (7/8) Epoch 6, batch 35800, loss[loss=3.286, over 490.00 frames. , ppl: 26.74361461855221] tot_loss[loss=2.292, over 5432994.63 frames. , ppl: 9.891176855771823], batch size: 70
+2022-12-12 03:48:50,031 INFO [train.py:421] (7/8) Epoch 6, batch 36000, loss[loss=2.399, over 1120.00 frames. , ppl: 11.015994164804054] tot_loss[loss=2.293, over 5402252.33 frames. , ppl: 9.90152399472885], batch size: 70
+2022-12-12 03:48:50,031 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 03:48:50,790 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.281, over 211138.00 frames. , ppl: 9.788203345702467
+2022-12-12 03:50:31,023 INFO [train.py:421] (7/8) Epoch 6, batch 36200, loss[loss=2.481, over 840.00 frames. , ppl: 11.952600780451146] tot_loss[loss=2.293, over 5427550.66 frames. , ppl: 9.901121361925455], batch size: 70
+2022-12-12 03:52:13,149 INFO [train.py:421] (7/8) Epoch 6, batch 36400, loss[loss=2.753, over 700.00 frames. , ppl: 15.69680800691722] tot_loss[loss=2.294, over 5388762.90 frames. , ppl: 9.90956879204148], batch size: 70
+2022-12-12 03:53:51,589 INFO [train.py:421] (7/8) Epoch 6, batch 36600, loss[loss=2.225, over 4130.00 frames. , ppl: 9.255180878562767] tot_loss[loss=2.294, over 5364976.95 frames. , ppl: 9.915057541272533], batch size: 70
+2022-12-12 03:55:34,345 INFO [train.py:421] (7/8) Epoch 6, batch 36800, loss[loss=2.241, over 13020.00 frames. , ppl: 9.401022992884668] tot_loss[loss=2.294, over 5380820.87 frames. , ppl: 9.91557397194866], batch size: 70
+2022-12-12 03:57:15,031 INFO [train.py:421] (7/8) Epoch 6, batch 37000, loss[loss=2.244, over 3640.00 frames. , ppl: 9.434525746107592] tot_loss[loss=2.295, over 5362202.67 frames. , ppl: 9.922007213633238], batch size: 70
+2022-12-12 03:57:15,032 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 03:57:15,781 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.28, over 211138.00 frames. , ppl: 9.776730360844793
+2022-12-12 03:58:58,749 INFO [train.py:421] (7/8) Epoch 6, batch 37200, loss[loss=2.264, over 2380.00 frames. , ppl: 9.61997183882418] tot_loss[loss=2.295, over 5375970.79 frames. , ppl: 9.92159004133414], batch size: 70
+2022-12-12 04:00:39,203 INFO [train.py:421] (7/8) Epoch 6, batch 37400, loss[loss=2.311, over 3780.00 frames. , ppl: 10.07991477958323] tot_loss[loss=2.293, over 5424022.43 frames. , ppl: 9.907770422339311], batch size: 70
+2022-12-12 04:02:19,600 INFO [train.py:421] (7/8) Epoch 6, batch 37600, loss[loss=2.262, over 4130.00 frames. , ppl: 9.599247407639588] tot_loss[loss=2.292, over 5438039.40 frames. , ppl: 9.898660138029573], batch size: 70
+2022-12-12 04:04:01,661 INFO [train.py:421] (7/8) Epoch 6, batch 37800, loss[loss=2.327, over 1120.00 frames. , ppl: 10.250125078319883] tot_loss[loss=2.291, over 5449171.64 frames. , ppl: 9.884149991638465], batch size: 70
+2022-12-12 04:05:40,700 INFO [train.py:421] (7/8) Epoch 6, batch 38000, loss[loss=2.236, over 5810.00 frames. , ppl: 9.355952775549072] tot_loss[loss=2.29, over 5476597.61 frames. , ppl: 9.87807519717723], batch size: 70
+2022-12-12 04:05:40,701 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 04:05:41,464 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.281, over 211138.00 frames. , ppl: 9.785526464019718
+2022-12-12 04:07:23,631 INFO [train.py:421] (7/8) Epoch 6, batch 38200, loss[loss=2.758, over 700.00 frames. , ppl: 15.767045192285021] tot_loss[loss=2.291, over 5468688.69 frames. , ppl: 9.882108443833737], batch size: 70
+2022-12-12 04:08:58,704 INFO [train.py:421] (7/8) Epoch 6, batch 38400, loss[loss=2.259, over 2240.00 frames. , ppl: 9.570394274268482] tot_loss[loss=2.291, over 5453898.86 frames. , ppl: 9.88452100497221], batch size: 70
+2022-12-12 04:10:38,732 INFO [train.py:421] (7/8) Epoch 6, batch 38600, loss[loss=2.301, over 3080.00 frames. , ppl: 9.98354301666756] tot_loss[loss=2.292, over 5406271.97 frames. , ppl: 9.893123123911035], batch size: 70
+2022-12-12 04:12:18,447 INFO [train.py:421] (7/8) Epoch 6, batch 38800, loss[loss=2.244, over 3710.00 frames. , ppl: 9.426488265495353] tot_loss[loss=2.291, over 5417151.24 frames. , ppl: 9.886044666067681], batch size: 70
+2022-12-12 04:13:53,347 INFO [train.py:421] (7/8) Epoch 6, batch 39000, loss[loss=2.239, over 4270.00 frames. , ppl: 9.385817017252787] tot_loss[loss=2.292, over 5402852.08 frames. , ppl: 9.893145530048193], batch size: 70
+2022-12-12 04:13:53,347 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 04:13:54,080 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.281, over 211138.00 frames. , ppl: 9.790575199383582
+2022-12-12 04:15:37,675 INFO [train.py:421] (7/8) Epoch 6, batch 39200, loss[loss=2.599, over 700.00 frames. , ppl: 13.4547157717694] tot_loss[loss=2.292, over 5389171.31 frames. , ppl: 9.893785101154188], batch size: 70
+2022-12-12 04:17:15,043 INFO [train.py:421] (7/8) Epoch 6, batch 39400, loss[loss=2.383, over 2100.00 frames. , ppl: 10.832651623778753] tot_loss[loss=2.291, over 5421264.58 frames. , ppl: 9.883776448452062], batch size: 70
+2022-12-12 04:18:56,787 INFO [train.py:421] (7/8) Epoch 6, batch 39600, loss[loss=2.331, over 2380.00 frames. , ppl: 10.283925019842494] tot_loss[loss=2.291, over 5434728.85 frames. , ppl: 9.887206437147647], batch size: 70
+2022-12-12 04:20:36,867 INFO [train.py:421] (7/8) Epoch 6, batch 39800, loss[loss=2.217, over 3220.00 frames. , ppl: 9.179615908218283] tot_loss[loss=2.291, over 5462801.52 frames. , ppl: 9.881898875771258], batch size: 70
+2022-12-12 04:22:14,667 INFO [train.py:421] (7/8) Epoch 6, batch 40000, loss[loss=2.26, over 2800.00 frames. , ppl: 9.579025771916411] tot_loss[loss=2.292, over 5458284.71 frames. , ppl: 9.892595665924006], batch size: 70
+2022-12-12 04:22:14,668 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 04:22:15,413 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.282, over 211138.00 frames. , ppl: 9.796226785877156
+2022-12-12 04:23:58,048 INFO [train.py:421] (7/8) Epoch 6, batch 40200, loss[loss=2.242, over 3290.00 frames. , ppl: 9.408279830865482] tot_loss[loss=2.293, over 5445329.34 frames. , ppl: 9.901711612390091], batch size: 70
+2022-12-12 04:25:35,508 INFO [train.py:421] (7/8) Epoch 6, batch 40400, loss[loss=2.196, over 7630.00 frames. , ppl: 8.991754628261619] tot_loss[loss=2.293, over 5406228.47 frames. , ppl: 9.907208908212066], batch size: 70
+2022-12-12 04:27:15,614 INFO [train.py:421] (7/8) Epoch 6, batch 40600, loss[loss=2.246, over 3080.00 frames. , ppl: 9.452652631052098] tot_loss[loss=2.292, over 5435266.51 frames. , ppl: 9.897036336795034], batch size: 70
+2022-12-12 04:28:54,809 INFO [train.py:421] (7/8) Epoch 6, batch 40800, loss[loss=2.393, over 1610.00 frames. , ppl: 10.945304157146092] tot_loss[loss=2.293, over 5417117.71 frames. , ppl: 9.90265228399017], batch size: 70
+2022-12-12 04:30:38,996 INFO [train.py:421] (7/8) Epoch 6, batch 41000, loss[loss=2.171, over 7140.00 frames. , ppl: 8.764511504581769] tot_loss[loss=2.292, over 5447296.29 frames. , ppl: 9.894844728813734], batch size: 70
+2022-12-12 04:30:38,996 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 04:30:39,735 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.28, over 211138.00 frames. , ppl: 9.77442840863681
+2022-12-12 04:32:21,592 INFO [train.py:421] (7/8) Epoch 6, batch 41200, loss[loss=2.43, over 1190.00 frames. , ppl: 11.357795703953622] tot_loss[loss=2.291, over 5463993.51 frames. , ppl: 9.884473891345632], batch size: 70
+2022-12-12 04:34:01,968 INFO [train.py:421] (7/8) Epoch 6, batch 41400, loss[loss=2.425, over 1330.00 frames. , ppl: 11.302003280688089] tot_loss[loss=2.291, over 5423549.39 frames. , ppl: 9.88966876923535], batch size: 70
+2022-12-12 04:35:43,803 INFO [train.py:421] (7/8) Epoch 6, batch 41600, loss[loss=2.273, over 3430.00 frames. , ppl: 9.711370559747886] tot_loss[loss=2.292, over 5389943.96 frames. , ppl: 9.894984108187717], batch size: 70
+2022-12-12 04:37:22,141 INFO [train.py:421] (7/8) Epoch 6, batch 41800, loss[loss=2.218, over 4410.00 frames. , ppl: 9.192899052314155] tot_loss[loss=2.291, over 5435612.35 frames. , ppl: 9.880262426177902], batch size: 70
+2022-12-12 04:39:01,065 INFO [train.py:421] (7/8) Epoch 6, batch 42000, loss[loss=2.279, over 3850.00 frames. , ppl: 9.764972470562798] tot_loss[loss=2.292, over 5408315.75 frames. , ppl: 9.890367469669952], batch size: 70
+2022-12-12 04:39:01,065 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 04:39:01,825 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.28, over 211138.00 frames. , ppl: 9.774656988070976
+2022-12-12 04:40:40,483 INFO [train.py:421] (7/8) Epoch 6, batch 42200, loss[loss=2.362, over 3080.00 frames. , ppl: 10.610949904404968] tot_loss[loss=2.292, over 5404742.98 frames. , ppl: 9.894683418247878], batch size: 70
+2022-12-12 04:42:19,272 INFO [train.py:421] (7/8) Epoch 6, batch 42400, loss[loss=2.957, over 560.00 frames. , ppl: 19.23828727345189] tot_loss[loss=2.293, over 5363063.19 frames. , ppl: 9.90518741066931], batch size: 70
+2022-12-12 04:43:58,780 INFO [train.py:421] (7/8) Epoch 6, batch 42600, loss[loss=2.233, over 4200.00 frames. , ppl: 9.329752366267844] tot_loss[loss=2.294, over 5346223.01 frames. , ppl: 9.914238502725745], batch size: 70
+2022-12-12 04:45:37,700 INFO [train.py:421] (7/8) Epoch 6, batch 42800, loss[loss=3.028, over 560.00 frames. , ppl: 20.65514305497464] tot_loss[loss=2.295, over 5332771.03 frames. , ppl: 9.923478561108396], batch size: 70
+2022-12-12 04:47:16,098 INFO [train.py:421] (7/8) Epoch 6, batch 43000, loss[loss=2.287, over 3640.00 frames. , ppl: 9.842567518531936] tot_loss[loss=2.295, over 5324540.53 frames. , ppl: 9.928670972872753], batch size: 70
+2022-12-12 04:47:16,098 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 04:47:16,826 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.28, over 211138.00 frames. , ppl: 9.774992633382912
+2022-12-12 04:48:53,986 INFO [train.py:421] (7/8) Epoch 6, batch 43200, loss[loss=2.267, over 3080.00 frames. , ppl: 9.650835610350528] tot_loss[loss=2.297, over 5295079.02 frames. , ppl: 9.939435554265911], batch size: 70
+2022-12-12 04:50:34,706 INFO [train.py:421] (7/8) Epoch 6, batch 43400, loss[loss=2.212, over 3640.00 frames. , ppl: 9.131815208213885] tot_loss[loss=2.297, over 5286661.21 frames. , ppl: 9.939692591749035], batch size: 70
+2022-12-12 04:52:11,334 INFO [train.py:421] (7/8) Epoch 6, batch 43600, loss[loss=2.341, over 1960.00 frames. , ppl: 10.393576989332063] tot_loss[loss=2.296, over 5284938.10 frames. , ppl: 9.93596954825538], batch size: 70
+2022-12-12 04:53:48,621 INFO [train.py:421] (7/8) Epoch 6, batch 43800, loss[loss=2.567, over 770.00 frames. , ppl: 13.028190713877915] tot_loss[loss=2.296, over 5299391.60 frames. , ppl: 9.932146233496498], batch size: 70
+2022-12-12 04:55:27,840 INFO [train.py:421] (7/8) Epoch 6, batch 44000, loss[loss=2.516, over 1470.00 frames. , ppl: 12.38107896066107] tot_loss[loss=2.297, over 5282724.62 frames. , ppl: 9.944810644338869], batch size: 70
+2022-12-12 04:55:27,840 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 04:55:28,598 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.28, over 211138.00 frames. , ppl: 9.775564124978258
+2022-12-12 04:57:06,981 INFO [train.py:421] (7/8) Epoch 6, batch 44200, loss[loss=2.27, over 2870.00 frames. , ppl: 9.683136111251912] tot_loss[loss=2.295, over 5341082.72 frames. , ppl: 9.925022233403315], batch size: 70
+2022-12-12 04:58:47,002 INFO [train.py:421] (7/8) Epoch 6, batch 44400, loss[loss=2.298, over 2240.00 frames. , ppl: 9.957637490886347] tot_loss[loss=2.294, over 5389175.19 frames. , ppl: 9.915186273473804], batch size: 70
+2022-12-12 05:00:25,091 INFO [train.py:421] (7/8) Epoch 6, batch 44600, loss[loss=2.361, over 1750.00 frames. , ppl: 10.606627840177199] tot_loss[loss=2.295, over 5389660.97 frames. , ppl: 9.92173580889799], batch size: 70
+2022-12-12 05:02:08,398 INFO [train.py:421] (7/8) Epoch 6, batch 44800, loss[loss=2.447, over 2100.00 frames. , ppl: 11.558304741938658] tot_loss[loss=2.294, over 5431127.20 frames. , ppl: 9.915878070155435], batch size: 70
+2022-12-12 05:03:45,269 INFO [train.py:421] (7/8) Epoch 6, batch 45000, loss[loss=2.355, over 2100.00 frames. , ppl: 10.533432737379458] tot_loss[loss=2.293, over 5461927.85 frames. , ppl: 9.907481013271848], batch size: 70
+2022-12-12 05:03:45,270 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 05:03:46,014 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.282, over 211138.00 frames. , ppl: 9.792734564010422
+2022-12-12 05:05:26,480 INFO [train.py:421] (7/8) Epoch 6, batch 45200, loss[loss=2.397, over 2730.00 frames. , ppl: 10.994442644875617] tot_loss[loss=2.291, over 5503251.29 frames. , ppl: 9.88104160888272], batch size: 70
+2022-12-12 05:07:06,358 INFO [train.py:421] (7/8) Epoch 6, batch 45400, loss[loss=2.279, over 2870.00 frames. , ppl: 9.7655909324428] tot_loss[loss=2.292, over 5441932.10 frames. , ppl: 9.899626024076557], batch size: 70
+2022-12-12 05:08:44,595 INFO [train.py:421] (7/8) Epoch 6, batch 45600, loss[loss=2.347, over 1330.00 frames. , ppl: 10.456668679077088] tot_loss[loss=2.293, over 5417696.19 frames. , ppl: 9.901322664223393], batch size: 70
+2022-12-12 05:10:22,564 INFO [train.py:421] (7/8) Epoch 6, batch 45800, loss[loss=2.446, over 1330.00 frames. , ppl: 11.543810085855757] tot_loss[loss=2.293, over 5394134.99 frames. , ppl: 9.901749212099814], batch size: 70
+2022-12-12 05:12:00,168 INFO [train.py:421] (7/8) Epoch 6, batch 46000, loss[loss=2.698, over 700.00 frames. , ppl: 14.850910472744566] tot_loss[loss=2.291, over 5413271.12 frames. , ppl: 9.888275412555696], batch size: 70
+2022-12-12 05:12:00,168 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 05:12:00,928 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.28, over 211138.00 frames. , ppl: 9.7772122333999
+2022-12-12 05:13:38,803 INFO [train.py:421] (7/8) Epoch 6, batch 46200, loss[loss=2.264, over 2380.00 frames. , ppl: 9.621904221780293] tot_loss[loss=2.292, over 5390369.75 frames. , ppl: 9.89809375426259], batch size: 70
+2022-12-12 05:15:18,369 INFO [train.py:421] (7/8) Epoch 6, batch 46400, loss[loss=2.296, over 3780.00 frames. , ppl: 9.93450883157178] tot_loss[loss=2.292, over 5396428.90 frames. , ppl: 9.896670484665716], batch size: 70
+2022-12-12 05:16:59,476 INFO [train.py:421] (7/8) Epoch 6, batch 46600, loss[loss=2.253, over 3920.00 frames. , ppl: 9.514325867180746] tot_loss[loss=2.293, over 5372012.86 frames. , ppl: 9.909446744254994], batch size: 70
+2022-12-12 05:18:44,138 INFO [train.py:421] (7/8) Epoch 6, batch 46800, loss[loss=2.388, over 2030.00 frames. , ppl: 10.890604955139224] tot_loss[loss=2.293, over 5377879.11 frames. , ppl: 9.906579705335828], batch size: 70
+2022-12-12 05:20:24,470 INFO [train.py:421] (7/8) Epoch 6, batch 47000, loss[loss=2.396, over 1820.00 frames. , ppl: 10.98445275675228] tot_loss[loss=2.293, over 5387521.61 frames. , ppl: 9.900663182691641], batch size: 70
+2022-12-12 05:20:24,470 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 05:20:25,228 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.281, over 211138.00 frames. , ppl: 9.782431870183903
+2022-12-12 05:22:04,499 INFO [train.py:421] (7/8) Epoch 6, batch 47200, loss[loss=2.339, over 2310.00 frames. , ppl: 10.367870134324708] tot_loss[loss=2.293, over 5372317.30 frames. , ppl: 9.904728872822824], batch size: 70
+2022-12-12 05:23:42,962 INFO [train.py:421] (7/8) Epoch 6, batch 47400, loss[loss=2.387, over 1750.00 frames. , ppl: 10.8856368100894] tot_loss[loss=2.293, over 5395966.61 frames. , ppl: 9.901229459514436], batch size: 70
+2022-12-12 05:25:19,135 INFO [train.py:421] (7/8) Epoch 6, batch 47600, loss[loss=3.046, over 560.00 frames. , ppl: 21.039067177148112] tot_loss[loss=2.292, over 5398568.45 frames. , ppl: 9.897180384790053], batch size: 70
+2022-12-12 05:26:59,791 INFO [train.py:421] (7/8) Epoch 6, batch 47800, loss[loss=2.352, over 1890.00 frames. , ppl: 10.502649977876409] tot_loss[loss=2.292, over 5407560.41 frames. , ppl: 9.890913834563632], batch size: 70
+2022-12-12 05:28:40,353 INFO [train.py:421] (7/8) Epoch 6, batch 48000, loss[loss=2.437, over 1050.00 frames. , ppl: 11.435749007448715] tot_loss[loss=2.293, over 5382763.53 frames. , ppl: 9.903188423604822], batch size: 70
+2022-12-12 05:28:40,354 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 05:28:41,113 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.279, over 211138.00 frames. , ppl: 9.767148491772168
+2022-12-12 05:30:22,489 INFO [train.py:421] (7/8) Epoch 6, batch 48200, loss[loss=2.594, over 840.00 frames. , ppl: 13.383297981385239] tot_loss[loss=2.291, over 5407586.54 frames. , ppl: 9.888617190758366], batch size: 70
+2022-12-12 05:31:59,719 INFO [train.py:421] (7/8) Epoch 6, batch 48400, loss[loss=2.203, over 4480.00 frames. , ppl: 9.05474493923465] tot_loss[loss=2.29, over 5436140.11 frames. , ppl: 9.87869733015093], batch size: 70
+2022-12-12 05:33:38,677 INFO [train.py:421] (7/8) Epoch 6, batch 48600, loss[loss=2.267, over 3010.00 frames. , ppl: 9.65308322696748] tot_loss[loss=2.291, over 5419320.73 frames. , ppl: 9.888474954264968], batch size: 70
+2022-12-12 05:35:20,096 INFO [train.py:421] (7/8) Epoch 6, batch 48800, loss[loss=2.249, over 3080.00 frames. , ppl: 9.473903531152237] tot_loss[loss=2.291, over 5428022.58 frames. , ppl: 9.885956597003307], batch size: 70
+2022-12-12 05:36:57,681 INFO [train.py:421] (7/8) Epoch 6, batch 49000, loss[loss=2.397, over 1610.00 frames. , ppl: 10.992997705944777] tot_loss[loss=2.292, over 5410252.64 frames. , ppl: 9.895543443829647], batch size: 70
+2022-12-12 05:36:57,681 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 05:36:58,441 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.279, over 211138.00 frames. , ppl: 9.767533031836354
+2022-12-12 05:38:37,512 INFO [train.py:421] (7/8) Epoch 6, batch 49200, loss[loss=2.303, over 1540.00 frames. , ppl: 10.005299012501474] tot_loss[loss=2.292, over 5406790.38 frames. , ppl: 9.89289885544133], batch size: 70
+2022-12-12 05:40:16,674 INFO [train.py:421] (7/8) Epoch 6, batch 49400, loss[loss=2.425, over 1120.00 frames. , ppl: 11.302500428483153] tot_loss[loss=2.293, over 5373651.96 frames. , ppl: 9.906138070987351], batch size: 70
+2022-12-12 05:41:57,411 INFO [train.py:421] (7/8) Epoch 6, batch 49600, loss[loss=2.477, over 1330.00 frames. , ppl: 11.90681577510075] tot_loss[loss=2.292, over 5391111.06 frames. , ppl: 9.893373674174535], batch size: 70
+2022-12-12 05:43:39,730 INFO [train.py:421] (7/8) Epoch 6, batch 49800, loss[loss=2.302, over 2310.00 frames. , ppl: 9.992617705405943] tot_loss[loss=2.291, over 5430791.14 frames. , ppl: 9.883134580933147], batch size: 70
+2022-12-12 05:45:15,856 INFO [train.py:421] (7/8) Epoch 6, batch 50000, loss[loss=2.217, over 2800.00 frames. , ppl: 9.183675037072213] tot_loss[loss=2.29, over 5463060.78 frames. , ppl: 9.87846733335934], batch size: 70
+2022-12-12 05:45:15,857 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 05:45:16,606 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.281, over 211138.00 frames. , ppl: 9.785662608076919
+2022-12-12 05:46:53,731 INFO [train.py:421] (7/8) Epoch 6, batch 50200, loss[loss=2.286, over 3080.00 frames. , ppl: 9.838335983413053] tot_loss[loss=2.291, over 5449906.10 frames. , ppl: 9.880265559248587], batch size: 70
+2022-12-12 05:48:35,503 INFO [train.py:421] (7/8) Epoch 6, batch 50400, loss[loss=2.655, over 700.00 frames. , ppl: 14.226811928060462] tot_loss[loss=2.29, over 5467531.12 frames. , ppl: 9.876859517156158], batch size: 70
+2022-12-12 05:50:15,397 INFO [train.py:421] (7/8) Epoch 6, batch 50600, loss[loss=2.415, over 1610.00 frames. , ppl: 11.19395481505576] tot_loss[loss=2.292, over 5412234.46 frames. , ppl: 9.892058354810128], batch size: 70
+2022-12-12 05:51:57,534 INFO [train.py:421] (7/8) Epoch 6, batch 50800, loss[loss=2.476, over 1330.00 frames. , ppl: 11.890268668562829] tot_loss[loss=2.292, over 5398885.19 frames. , ppl: 9.896074808970946], batch size: 70
+2022-12-12 05:53:42,723 INFO [train.py:421] (7/8) Epoch 6, batch 51000, loss[loss=2.267, over 4130.00 frames. , ppl: 9.650460799759319] tot_loss[loss=2.292, over 5399507.91 frames. , ppl: 9.898757146324275], batch size: 70
+2022-12-12 05:53:42,724 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 05:53:43,469 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.279, over 211138.00 frames. , ppl: 9.76539078711788
+2022-12-12 05:55:23,428 INFO [train.py:421] (7/8) Epoch 6, batch 51200, loss[loss=2.429, over 1470.00 frames. , ppl: 11.348012328733404] tot_loss[loss=2.293, over 5401364.70 frames. , ppl: 9.905568437935734], batch size: 70
+2022-12-12 05:57:03,661 INFO [train.py:421] (7/8) Epoch 6, batch 51400, loss[loss=2.682, over 770.00 frames. , ppl: 14.613433425602436] tot_loss[loss=2.292, over 5432520.76 frames. , ppl: 9.899594429785441], batch size: 70
+2022-12-12 05:58:44,079 INFO [train.py:421] (7/8) Epoch 6, batch 51600, loss[loss=2.223, over 3080.00 frames. , ppl: 9.23720191593339] tot_loss[loss=2.292, over 5432130.66 frames. , ppl: 9.897115944831167], batch size: 70
+2022-12-12 06:00:26,224 INFO [train.py:421] (7/8) Epoch 6, batch 51800, loss[loss=2.504, over 910.00 frames. , ppl: 12.2346184316892] tot_loss[loss=2.293, over 5387224.54 frames. , ppl: 9.90296824188668], batch size: 70
+2022-12-12 06:02:05,627 INFO [train.py:421] (7/8) Epoch 6, batch 52000, loss[loss=2.2, over 6790.00 frames. , ppl: 9.02533541172252] tot_loss[loss=2.293, over 5357232.13 frames. , ppl: 9.90423738517946], batch size: 70
+2022-12-12 06:02:05,628 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 06:02:06,356 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.278, over 211138.00 frames. , ppl: 9.758165262568566
+2022-12-12 06:03:45,495 INFO [train.py:421] (7/8) Epoch 6, batch 52200, loss[loss=2.656, over 1050.00 frames. , ppl: 14.235617094682178] tot_loss[loss=2.293, over 5381681.49 frames. , ppl: 9.904668519215681], batch size: 70
+2022-12-12 06:05:23,974 INFO [train.py:421] (7/8) Epoch 6, batch 52400, loss[loss=2.858, over 630.00 frames. , ppl: 17.42017144534268] tot_loss[loss=2.292, over 5405139.57 frames. , ppl: 9.899357438883], batch size: 70
+2022-12-12 06:07:01,651 INFO [train.py:421] (7/8) Epoch 6, batch 52600, loss[loss=2.39, over 1960.00 frames. , ppl: 10.914692457341092] tot_loss[loss=2.291, over 5418941.40 frames. , ppl: 9.887131916794242], batch size: 70
+2022-12-12 06:08:40,079 INFO [train.py:421] (7/8) Epoch 6, batch 52800, loss[loss=2.213, over 6860.00 frames. , ppl: 9.14723502162016] tot_loss[loss=2.292, over 5423518.53 frames. , ppl: 9.891214789520411], batch size: 70
+2022-12-12 06:10:20,320 INFO [train.py:421] (7/8) Epoch 6, batch 53000, loss[loss=2.37, over 2100.00 frames. , ppl: 10.700384928016648] tot_loss[loss=2.291, over 5435911.03 frames. , ppl: 9.887411224952677], batch size: 70
+2022-12-12 06:10:20,321 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 06:10:21,067 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.279, over 211138.00 frames. , ppl: 9.764269259359716
+2022-12-12 06:11:59,979 INFO [train.py:421] (7/8) Epoch 6, batch 53200, loss[loss=2.282, over 3360.00 frames. , ppl: 9.797416551445426] tot_loss[loss=2.291, over 5449036.86 frames. , ppl: 9.882351674454641], batch size: 70
+2022-12-12 06:13:40,687 INFO [train.py:421] (7/8) Epoch 6, batch 53400, loss[loss=2.419, over 1400.00 frames. , ppl: 11.22948411116071] tot_loss[loss=2.291, over 5444904.79 frames. , ppl: 9.885630932560424], batch size: 70
+2022-12-12 06:15:21,184 INFO [train.py:421] (7/8) Epoch 6, batch 53600, loss[loss=2.411, over 2310.00 frames. , ppl: 11.144693879511856] tot_loss[loss=2.29, over 5477170.89 frames. , ppl: 9.877306430941491], batch size: 70
+2022-12-12 06:17:02,492 INFO [train.py:421] (7/8) Epoch 6, batch 53800, loss[loss=2.259, over 4130.00 frames. , ppl: 9.571794946338102] tot_loss[loss=2.29, over 5466533.56 frames. , ppl: 9.876175174875714], batch size: 70
+2022-12-12 06:18:44,493 INFO [train.py:421] (7/8) Epoch 6, batch 54000, loss[loss=2.193, over 4550.00 frames. , ppl: 8.959178803832094] tot_loss[loss=2.29, over 5492887.26 frames. , ppl: 9.875484763089911], batch size: 70
+2022-12-12 06:18:44,494 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 06:18:45,222 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.28, over 211138.00 frames. , ppl: 9.773898935036751
+2022-12-12 06:20:25,789 INFO [train.py:421] (7/8) Epoch 6, batch 54200, loss[loss=2.417, over 1890.00 frames. , ppl: 11.21014411673745] tot_loss[loss=2.29, over 5478530.26 frames. , ppl: 9.87660345491197], batch size: 70
+2022-12-12 06:22:07,244 INFO [train.py:421] (7/8) Epoch 6, batch 54400, loss[loss=2.482, over 1190.00 frames. , ppl: 11.967484253949864] tot_loss[loss=2.289, over 5525678.60 frames. , ppl: 9.863814259335207], batch size: 70
+2022-12-12 06:23:46,091 INFO [train.py:421] (7/8) Epoch 6, batch 54600, loss[loss=2.525, over 1050.00 frames. , ppl: 12.493837685291174] tot_loss[loss=2.289, over 5506043.57 frames. , ppl: 9.867972660031267], batch size: 70
+2022-12-12 06:25:25,862 INFO [train.py:421] (7/8) Epoch 6, batch 54800, loss[loss=3.362, over 490.00 frames. , ppl: 28.836573979885692] tot_loss[loss=2.29, over 5487420.01 frames. , ppl: 9.871269368028642], batch size: 70
+2022-12-12 06:27:05,743 INFO [train.py:421] (7/8) Epoch 6, batch 55000, loss[loss=2.17, over 5530.00 frames. , ppl: 8.756560616059536] tot_loss[loss=2.289, over 5517088.21 frames. , ppl: 9.860671078943408], batch size: 70
+2022-12-12 06:27:05,744 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 06:27:06,473 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.278, over 211138.00 frames. , ppl: 9.758666441048378
+2022-12-12 06:28:46,939 INFO [train.py:421] (7/8) Epoch 6, batch 55200, loss[loss=2.803, over 630.00 frames. , ppl: 16.493853827670577] tot_loss[loss=2.289, over 5525719.04 frames. , ppl: 9.86415223601759], batch size: 70
+2022-12-12 06:30:30,149 INFO [train.py:421] (7/8) Epoch 6, batch 55400, loss[loss=2.309, over 1540.00 frames. , ppl: 10.069158066788798] tot_loss[loss=2.289, over 5543464.10 frames. , ppl: 9.86587561321739], batch size: 70
+2022-12-12 06:32:09,448 INFO [train.py:421] (7/8) Epoch 6, batch 55600, loss[loss=2.728, over 700.00 frames. , ppl: 15.308769224340335] tot_loss[loss=2.29, over 5492245.60 frames. , ppl: 9.875163762309802], batch size: 70
+2022-12-12 06:33:49,116 INFO [train.py:421] (7/8) Epoch 6, batch 55800, loss[loss=2.492, over 1260.00 frames. , ppl: 12.08220499390128] tot_loss[loss=2.29, over 5502368.20 frames. , ppl: 9.871914721197205], batch size: 70
+2022-12-12 06:35:30,415 INFO [train.py:421] (7/8) Epoch 6, batch 56000, loss[loss=2.754, over 630.00 frames. , ppl: 15.708980353789174] tot_loss[loss=2.288, over 5526321.23 frames. , ppl: 9.859937798382843], batch size: 70
+2022-12-12 06:35:30,415 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 06:35:31,174 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.279, over 211138.00 frames. , ppl: 9.763342939887206
+2022-12-12 06:37:13,856 INFO [train.py:421] (7/8) Epoch 6, batch 56200, loss[loss=2.284, over 3710.00 frames. , ppl: 9.81477164286526] tot_loss[loss=2.289, over 5525902.04 frames. , ppl: 9.86216364526093], batch size: 70
+2022-12-12 06:38:54,634 INFO [train.py:421] (7/8) Epoch 6, batch 56400, loss[loss=2.219, over 5460.00 frames. , ppl: 9.199168328838734] tot_loss[loss=2.289, over 5504137.10 frames. , ppl: 9.869601149647703], batch size: 70
+2022-12-12 06:40:33,689 INFO [train.py:421] (7/8) Epoch 6, batch 56600, loss[loss=2.228, over 3850.00 frames. , ppl: 9.278424524918236] tot_loss[loss=2.289, over 5499351.74 frames. , ppl: 9.869830327266971], batch size: 70
+2022-12-12 06:42:12,586 INFO [train.py:421] (7/8) Epoch 6, batch 56800, loss[loss=2.974, over 560.00 frames. , ppl: 19.57852387784334] tot_loss[loss=2.289, over 5515317.84 frames. , ppl: 9.862211295745594], batch size: 70
+2022-12-12 06:43:53,583 INFO [train.py:421] (7/8) Epoch 6, batch 57000, loss[loss=2.332, over 2240.00 frames. , ppl: 10.298258388882017] tot_loss[loss=2.288, over 5535883.83 frames. , ppl: 9.858773363154691], batch size: 70
+2022-12-12 06:43:53,584 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 06:43:54,329 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.279, over 211138.00 frames. , ppl: 9.763007694592458
+2022-12-12 06:45:35,860 INFO [train.py:421] (7/8) Epoch 6, batch 57200, loss[loss=2.671, over 700.00 frames. , ppl: 14.451005338979233] tot_loss[loss=2.288, over 5557924.22 frames. , ppl: 9.855440917710053], batch size: 70
+2022-12-12 06:47:18,364 INFO [train.py:421] (7/8) Epoch 6, batch 57400, loss[loss=2.316, over 2240.00 frames. , ppl: 10.131802889461285] tot_loss[loss=2.288, over 5575041.66 frames. , ppl: 9.850371343594256], batch size: 70
+2022-12-12 06:48:59,495 INFO [train.py:421] (7/8) Epoch 6, batch 57600, loss[loss=2.452, over 770.00 frames. , ppl: 11.614584930863725] tot_loss[loss=2.286, over 5630427.22 frames. , ppl: 9.838376242597587], batch size: 70
+2022-12-12 06:50:45,869 INFO [train.py:421] (7/8) Epoch 6, batch 57800, loss[loss=2.488, over 1470.00 frames. , ppl: 12.041257530411878] tot_loss[loss=2.285, over 5677168.69 frames. , ppl: 9.828195786841915], batch size: 70
+2022-12-12 06:52:25,583 INFO [train.py:421] (7/8) Epoch 6, batch 58000, loss[loss=2.322, over 2100.00 frames. , ppl: 10.191230777005925] tot_loss[loss=2.285, over 5701484.51 frames. , ppl: 9.824013790026491], batch size: 70
+2022-12-12 06:52:25,584 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 06:52:26,339 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.278, over 211138.00 frames. , ppl: 9.758448345808779
+2022-12-12 06:54:02,193 INFO [train.py:421] (7/8) Epoch 6, batch 58200, loss[loss=2.3, over 2520.00 frames. , ppl: 9.974008520392857] tot_loss[loss=2.285, over 5697086.57 frames. , ppl: 9.821831245377462], batch size: 70
+2022-12-12 06:55:40,820 INFO [train.py:421] (7/8) Epoch 6, batch 58400, loss[loss=2.194, over 5180.00 frames. , ppl: 8.975491467157077] tot_loss[loss=2.284, over 5698734.60 frames. , ppl: 9.813858470364245], batch size: 70
+2022-12-12 06:57:22,166 INFO [train.py:421] (7/8) Epoch 6, batch 58600, loss[loss=2.598, over 770.00 frames. , ppl: 13.431009877174247] tot_loss[loss=2.283, over 5713683.03 frames. , ppl: 9.805395484170464], batch size: 70
+2022-12-12 06:59:04,024 INFO [train.py:421] (7/8) Epoch 6, batch 58800, loss[loss=4.088, over 350.00 frames. , ppl: 59.636386767652006] tot_loss[loss=2.283, over 5697041.51 frames. , ppl: 9.809002357639054], batch size: 70
+2022-12-12 07:00:45,054 INFO [train.py:421] (7/8) Epoch 6, batch 59000, loss[loss=2.19, over 4760.00 frames. , ppl: 8.938085022315205] tot_loss[loss=2.284, over 5704203.07 frames. , ppl: 9.814230420701831], batch size: 70
+2022-12-12 07:00:45,055 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 07:00:45,814 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.279, over 211138.00 frames. , ppl: 9.762743263537212
+2022-12-12 07:02:25,672 INFO [train.py:421] (7/8) Epoch 6, batch 59200, loss[loss=2.356, over 1470.00 frames. , ppl: 10.54413794062204] tot_loss[loss=2.285, over 5662116.57 frames. , ppl: 9.824720808833515], batch size: 70
+2022-12-12 07:04:06,645 INFO [train.py:421] (7/8) Epoch 6, batch 59400, loss[loss=2.191, over 8260.00 frames. , ppl: 8.940182071370463] tot_loss[loss=2.286, over 5653410.66 frames. , ppl: 9.832738000119468], batch size: 70
+2022-12-12 07:05:46,488 INFO [train.py:421] (7/8) Epoch 6, batch 59600, loss[loss=2.172, over 3920.00 frames. , ppl: 8.777952710023081] tot_loss[loss=2.287, over 5606771.03 frames. , ppl: 9.848446051152578], batch size: 70
+2022-12-12 07:07:27,937 INFO [train.py:421] (7/8) Epoch 6, batch 59800, loss[loss=2.456, over 1610.00 frames. , ppl: 11.662793862877871] tot_loss[loss=2.287, over 5603253.13 frames. , ppl: 9.847437044839737], batch size: 70
+2022-12-12 07:09:08,960 INFO [train.py:421] (7/8) Epoch 6, batch 60000, loss[loss=2.365, over 1120.00 frames. , ppl: 10.648562344116963] tot_loss[loss=2.288, over 5571763.46 frames. , ppl: 9.852083106143736], batch size: 70
+2022-12-12 07:09:08,961 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 07:09:09,719 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.279, over 211138.00 frames. , ppl: 9.763438313496728
+2022-12-12 07:10:50,272 INFO [train.py:421] (7/8) Epoch 6, batch 60200, loss[loss=2.374, over 1750.00 frames. , ppl: 10.738445691469122] tot_loss[loss=2.288, over 5555553.09 frames. , ppl: 9.853780432536164], batch size: 70
+2022-12-12 07:12:28,643 INFO [train.py:421] (7/8) Epoch 6, batch 60400, loss[loss=2.305, over 2660.00 frames. , ppl: 10.026632486251787] tot_loss[loss=2.288, over 5523165.34 frames. , ppl: 9.856461706746048], batch size: 70
+2022-12-12 07:14:10,682 INFO [train.py:421] (7/8) Epoch 6, batch 60600, loss[loss=2.206, over 4340.00 frames. , ppl: 9.075039236955627] tot_loss[loss=2.288, over 5537437.87 frames. , ppl: 9.856518966442634], batch size: 70
+2022-12-12 07:15:51,738 INFO [train.py:421] (7/8) Epoch 6, batch 60800, loss[loss=2.332, over 2240.00 frames. , ppl: 10.300577571954532] tot_loss[loss=2.289, over 5517597.08 frames. , ppl: 9.861676966935526], batch size: 70
+2022-12-12 07:17:31,916 INFO [train.py:421] (7/8) Epoch 6, batch 61000, loss[loss=2.458, over 1120.00 frames. , ppl: 11.686556922838443] tot_loss[loss=2.288, over 5493488.04 frames. , ppl: 9.85981965683163], batch size: 70
+2022-12-12 07:17:31,917 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 07:17:32,674 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.279, over 211138.00 frames. , ppl: 9.767613989568469
+2022-12-12 07:19:10,822 INFO [train.py:421] (7/8) Epoch 6, batch 61200, loss[loss=2.321, over 3780.00 frames. , ppl: 10.18390235771263] tot_loss[loss=2.287, over 5543676.65 frames. , ppl: 9.848650447348124], batch size: 70
+2022-12-12 07:20:50,835 INFO [train.py:421] (7/8) Epoch 6, batch 61400, loss[loss=2.231, over 6650.00 frames. , ppl: 9.307040132267629] tot_loss[loss=2.287, over 5579496.00 frames. , ppl: 9.846299138918704], batch size: 70
+2022-12-12 07:22:30,434 INFO [train.py:421] (7/8) Epoch 6, batch 61600, loss[loss=2.229, over 2450.00 frames. , ppl: 9.29068121759749] tot_loss[loss=2.287, over 5574779.20 frames. , ppl: 9.845519146267689], batch size: 70
+2022-12-12 07:24:09,144 INFO [train.py:421] (7/8) Epoch 6, batch 61800, loss[loss=2.433, over 1540.00 frames. , ppl: 11.390261744032358] tot_loss[loss=2.287, over 5571992.85 frames. , ppl: 9.849514384701965], batch size: 70
+2022-12-12 07:25:49,776 INFO [train.py:421] (7/8) Epoch 6, batch 62000, loss[loss=2.291, over 4270.00 frames. , ppl: 9.884375196239075] tot_loss[loss=2.287, over 5572769.05 frames. , ppl: 9.8426426698317], batch size: 70
+2022-12-12 07:25:49,777 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 07:25:50,536 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.28, over 211138.00 frames. , ppl: 9.776349799606294
+2022-12-12 07:27:29,141 INFO [train.py:421] (7/8) Epoch 6, batch 62200, loss[loss=2.32, over 2800.00 frames. , ppl: 10.1793339763637] tot_loss[loss=2.286, over 5575408.62 frames. , ppl: 9.838469278906581], batch size: 70
+2022-12-12 07:29:06,022 INFO [train.py:421] (7/8) Epoch 6, batch 62400, loss[loss=2.167, over 7350.00 frames. , ppl: 8.732514041857568] tot_loss[loss=2.288, over 5540028.23 frames. , ppl: 9.8529340811034], batch size: 70
+2022-12-12 07:30:49,311 INFO [train.py:421] (7/8) Epoch 6, batch 62600, loss[loss=2.269, over 3080.00 frames. , ppl: 9.66796355843466] tot_loss[loss=2.289, over 5502495.92 frames. , ppl: 9.865730946974228], batch size: 70
+2022-12-12 07:32:26,334 INFO [train.py:421] (7/8) Epoch 6, batch 62800, loss[loss=2.288, over 6440.00 frames. , ppl: 9.856150163984122] tot_loss[loss=2.288, over 5522354.30 frames. , ppl: 9.856772586885477], batch size: 70
+2022-12-12 07:34:06,411 INFO [train.py:421] (7/8) Epoch 6, batch 63000, loss[loss=2.414, over 1330.00 frames. , ppl: 11.17949828604603] tot_loss[loss=2.287, over 5542173.10 frames. , ppl: 9.848760566920822], batch size: 70
+2022-12-12 07:34:06,412 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 07:34:07,172 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.281, over 211138.00 frames. , ppl: 9.784635781017636
+2022-12-12 07:35:46,471 INFO [train.py:421] (7/8) Epoch 6, batch 63200, loss[loss=2.507, over 1190.00 frames. , ppl: 12.271459634513727] tot_loss[loss=2.288, over 5494950.12 frames. , ppl: 9.855004695373978], batch size: 70
+2022-12-12 07:37:31,526 INFO [train.py:421] (7/8) Epoch 6, batch 63400, loss[loss=2.096, over 3150.00 frames. , ppl: 8.131990614062076] tot_loss[loss=2.288, over 5481807.46 frames. , ppl: 9.858789912574714], batch size: 70
+2022-12-12 07:39:13,151 INFO [train.py:421] (7/8) Epoch 6, batch 63600, loss[loss=2.515, over 1260.00 frames. , ppl: 12.364681439061963] tot_loss[loss=2.288, over 5462511.07 frames. , ppl: 9.859221440496523], batch size: 70
+2022-12-12 07:40:49,344 INFO [train.py:421] (7/8) Epoch 6, batch 63800, loss[loss=2.173, over 3710.00 frames. , ppl: 8.788474833908724] tot_loss[loss=2.287, over 5463606.09 frames. , ppl: 9.849034417713082], batch size: 70
+2022-12-12 07:42:29,286 INFO [train.py:421] (7/8) Epoch 6, batch 64000, loss[loss=2.559, over 980.00 frames. , ppl: 12.927960399493676] tot_loss[loss=2.288, over 5440331.97 frames. , ppl: 9.85881951500516], batch size: 70
+2022-12-12 07:42:29,287 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 07:42:30,050 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.279, over 211138.00 frames. , ppl: 9.768704092947166
+2022-12-12 07:44:07,966 INFO [train.py:421] (7/8) Epoch 6, batch 64200, loss[loss=2.2, over 8190.00 frames. , ppl: 9.020546521097657] tot_loss[loss=2.288, over 5446418.75 frames. , ppl: 9.859058041557363], batch size: 70
+2022-12-12 07:45:49,266 INFO [train.py:421] (7/8) Epoch 6, batch 64400, loss[loss=2.436, over 1400.00 frames. , ppl: 11.42618134225017] tot_loss[loss=2.289, over 5423448.65 frames. , ppl: 9.866922357792127], batch size: 70
+2022-12-12 07:47:28,534 INFO [train.py:421] (7/8) Epoch 6, batch 64600, loss[loss=2.735, over 840.00 frames. , ppl: 15.405760556421702] tot_loss[loss=2.29, over 5388722.95 frames. , ppl: 9.87670582175505], batch size: 70
+2022-12-12 07:49:11,548 INFO [train.py:421] (7/8) Epoch 6, batch 64800, loss[loss=2.193, over 3430.00 frames. , ppl: 8.963821672824363] tot_loss[loss=2.289, over 5445749.56 frames. , ppl: 9.863357815827502], batch size: 70
+2022-12-12 07:50:54,148 INFO [train.py:421] (7/8) Epoch 6, batch 65000, loss[loss=2.332, over 1680.00 frames. , ppl: 10.303345709126503] tot_loss[loss=2.288, over 5479552.03 frames. , ppl: 9.851446998846345], batch size: 70
+2022-12-12 07:50:54,148 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 07:50:54,908 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.281, over 211138.00 frames. , ppl: 9.786995181821556
+2022-12-12 07:52:32,872 INFO [train.py:421] (7/8) Epoch 6, batch 65200, loss[loss=2.334, over 2030.00 frames. , ppl: 10.318875115687705] tot_loss[loss=2.288, over 5468759.83 frames. , ppl: 9.85159612051271], batch size: 70
+2022-12-12 07:54:12,249 INFO [train.py:421] (7/8) Epoch 6, batch 65400, loss[loss=2.171, over 5740.00 frames. , ppl: 8.765462868699576] tot_loss[loss=2.288, over 5460671.38 frames. , ppl: 9.854241995298961], batch size: 70
+2022-12-12 07:55:56,356 INFO [train.py:421] (7/8) Epoch 6, batch 65600, loss[loss=2.285, over 3570.00 frames. , ppl: 9.830460085284649] tot_loss[loss=2.287, over 5472803.21 frames. , ppl: 9.846806578839702], batch size: 70
+2022-12-12 07:57:38,643 INFO [train.py:421] (7/8) Epoch 6, batch 65800, loss[loss=2.684, over 980.00 frames. , ppl: 14.641333682534594] tot_loss[loss=2.286, over 5496920.13 frames. , ppl: 9.836044621074864], batch size: 70
+2022-12-12 07:59:17,514 INFO [train.py:421] (7/8) Epoch 6, batch 66000, loss[loss=2.138, over 5110.00 frames. , ppl: 8.48627207046767] tot_loss[loss=2.287, over 5475137.02 frames. , ppl: 9.846213403083652], batch size: 70
+2022-12-12 07:59:17,515 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 07:59:18,272 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.278, over 211138.00 frames. , ppl: 9.756986800195627
+2022-12-12 08:00:55,084 INFO [train.py:421] (7/8) Epoch 6, batch 66200, loss[loss=2.382, over 2030.00 frames. , ppl: 10.831621155524521] tot_loss[loss=2.288, over 5428962.99 frames. , ppl: 9.855308228839295], batch size: 70
+2022-12-12 08:02:34,946 INFO [train.py:421] (7/8) Epoch 6, batch 66400, loss[loss=2.346, over 3430.00 frames. , ppl: 10.441746784920102] tot_loss[loss=2.289, over 5408299.00 frames. , ppl: 9.860587310672457], batch size: 70
+2022-12-12 08:04:12,889 INFO [train.py:421] (7/8) Epoch 6, batch 66600, loss[loss=2.281, over 3640.00 frames. , ppl: 9.782335026857803] tot_loss[loss=2.288, over 5426126.19 frames. , ppl: 9.856794169179565], batch size: 70
+2022-12-12 08:05:56,266 INFO [train.py:421] (7/8) Epoch 6, batch 66800, loss[loss=2.299, over 2520.00 frames. , ppl: 9.96075012486943] tot_loss[loss=2.288, over 5449254.87 frames. , ppl: 9.850446225779208], batch size: 70
+2022-12-12 08:07:41,372 INFO [train.py:421] (7/8) Epoch 6, batch 67000, loss[loss=2.418, over 1540.00 frames. , ppl: 11.21797327079643] tot_loss[loss=2.287, over 5458872.96 frames. , ppl: 9.848374270074144], batch size: 70
+2022-12-12 08:07:41,372 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 08:07:42,129 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.279, over 211138.00 frames. , ppl: 9.766049889291654
+2022-12-12 08:09:21,215 INFO [train.py:421] (7/8) Epoch 6, batch 67200, loss[loss=2.324, over 2240.00 frames. , ppl: 10.214072598001373] tot_loss[loss=2.287, over 5451872.06 frames. , ppl: 9.847882971855185], batch size: 70
+2022-12-12 08:11:01,750 INFO [train.py:421] (7/8) Epoch 6, batch 67400, loss[loss=2.364, over 1330.00 frames. , ppl: 10.629946709870493] tot_loss[loss=2.287, over 5459956.75 frames. , ppl: 9.847179334571168], batch size: 70
+2022-12-12 08:12:41,353 INFO [train.py:421] (7/8) Epoch 6, batch 67600, loss[loss=2.357, over 3920.00 frames. , ppl: 10.561371480895174] tot_loss[loss=2.286, over 5528028.73 frames. , ppl: 9.835055222177518], batch size: 70
+2022-12-12 08:14:15,983 INFO [train.py:421] (7/8) Epoch 6, batch 67800, loss[loss=2.322, over 1680.00 frames. , ppl: 10.199485406227334] tot_loss[loss=2.288, over 5478135.98 frames. , ppl: 9.854927050515887], batch size: 70
+2022-12-12 08:15:54,493 INFO [train.py:421] (7/8) Epoch 6, batch 68000, loss[loss=2.364, over 1610.00 frames. , ppl: 10.630862662995202] tot_loss[loss=2.289, over 5461651.35 frames. , ppl: 9.862719686215542], batch size: 70
+2022-12-12 08:15:54,494 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 08:15:55,254 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.28, over 211138.00 frames. , ppl: 9.779122592522853
+2022-12-12 08:17:39,588 INFO [train.py:421] (7/8) Epoch 6, batch 68200, loss[loss=3.035, over 560.00 frames. , ppl: 20.802768099726627] tot_loss[loss=2.289, over 5464377.34 frames. , ppl: 9.864479547897393], batch size: 70
+2022-12-12 08:19:22,897 INFO [train.py:421] (7/8) Epoch 6, batch 68400, loss[loss=2.288, over 2170.00 frames. , ppl: 9.855032179155263] tot_loss[loss=2.288, over 5516918.53 frames. , ppl: 9.855078980364333], batch size: 70
+2022-12-12 08:21:04,975 INFO [train.py:421] (7/8) Epoch 6, batch 68600, loss[loss=2.302, over 1680.00 frames. , ppl: 9.991528787856119] tot_loss[loss=2.287, over 5551167.99 frames. , ppl: 9.845078034477378], batch size: 70
+2022-12-12 08:22:43,488 INFO [train.py:421] (7/8) Epoch 6, batch 68800, loss[loss=2.634, over 910.00 frames. , ppl: 13.933897802129902] tot_loss[loss=2.288, over 5534312.85 frames. , ppl: 9.854362825315249], batch size: 70
+2022-12-12 08:24:23,648 INFO [train.py:421] (7/8) Epoch 6, batch 69000, loss[loss=2.243, over 2590.00 frames. , ppl: 9.419891639685922] tot_loss[loss=2.287, over 5551134.10 frames. , ppl: 9.849202126602714], batch size: 70
+2022-12-12 08:24:23,649 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 08:24:24,395 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.279, over 211138.00 frames. , ppl: 9.762691245156288
+2022-12-12 08:26:05,592 INFO [train.py:421] (7/8) Epoch 6, batch 69200, loss[loss=2.321, over 2520.00 frames. , ppl: 10.181714908001554] tot_loss[loss=2.287, over 5547317.62 frames. , ppl: 9.848544085885173], batch size: 70
+2022-12-12 08:27:44,996 INFO [train.py:421] (7/8) Epoch 6, batch 69400, loss[loss=2.335, over 2450.00 frames. , ppl: 10.327222424025313] tot_loss[loss=2.288, over 5499542.47 frames. , ppl: 9.859085734845639], batch size: 70
+2022-12-12 08:29:30,567 INFO [train.py:421] (7/8) Epoch 6, batch 69600, loss[loss=2.362, over 1820.00 frames. , ppl: 10.615639058668808] tot_loss[loss=2.29, over 5445460.83 frames. , ppl: 9.87557989418175], batch size: 70
+2022-12-12 08:31:11,122 INFO [train.py:421] (7/8) Epoch 6, batch 69800, loss[loss=2.352, over 2520.00 frames. , ppl: 10.505096355195572] tot_loss[loss=2.29, over 5466389.94 frames. , ppl: 9.878001348916948], batch size: 70
+2022-12-12 08:32:55,421 INFO [train.py:421] (7/8) Epoch 6, batch 70000, loss[loss=2.568, over 1540.00 frames. , ppl: 13.041167862817874] tot_loss[loss=2.291, over 5424710.33 frames. , ppl: 9.887943678266776], batch size: 70
+2022-12-12 08:32:55,421 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 08:32:56,166 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.278, over 211138.00 frames. , ppl: 9.761897999189102
+2022-12-12 08:34:38,124 INFO [train.py:421] (7/8) Epoch 6, batch 70200, loss[loss=2.371, over 1680.00 frames. , ppl: 10.707138242771686] tot_loss[loss=2.292, over 5398638.27 frames. , ppl: 9.890086180708062], batch size: 70
+2022-12-12 08:36:17,126 INFO [train.py:421] (7/8) Epoch 6, batch 70400, loss[loss=2.279, over 3290.00 frames. , ppl: 9.764106064582677] tot_loss[loss=2.292, over 5416522.60 frames. , ppl: 9.89313353191182], batch size: 70
+2022-12-12 08:37:57,456 INFO [train.py:421] (7/8) Epoch 6, batch 70600, loss[loss=2.282, over 3710.00 frames. , ppl: 9.792880369949717] tot_loss[loss=2.292, over 5419468.75 frames. , ppl: 9.892441879802384], batch size: 70
+2022-12-12 08:39:34,985 INFO [train.py:421] (7/8) Epoch 6, batch 70800, loss[loss=2.257, over 3150.00 frames. , ppl: 9.551249054658665] tot_loss[loss=2.292, over 5378827.71 frames. , ppl: 9.899102455773212], batch size: 70
+2022-12-12 08:41:17,310 INFO [train.py:421] (7/8) Epoch 6, batch 71000, loss[loss=2.373, over 1820.00 frames. , ppl: 10.733044292925898] tot_loss[loss=2.292, over 5393605.58 frames. , ppl: 9.89306089223811], batch size: 70
+2022-12-12 08:41:17,311 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 08:41:18,069 INFO [train.py:452] (7/8) Epoch 6, validation: loss=2.278, over 211138.00 frames. , ppl: 9.760633851500042
+2022-12-12 08:42:55,817 INFO [train.py:421] (7/8) Epoch 6, batch 71200, loss[loss=2.42, over 1960.00 frames. , ppl: 11.240689864542736] tot_loss[loss=2.291, over 5442945.87 frames. , ppl: 9.889497349021612], batch size: 70
+2022-12-12 08:44:37,469 INFO [train.py:421] (7/8) Epoch 6, batch 71400, loss[loss=2.212, over 13510.00 frames. , ppl: 9.1341543199662] tot_loss[loss=2.292, over 5445417.70 frames. , ppl: 9.89243693701248], batch size: 70
+2022-12-12 08:46:15,637 INFO [train.py:421] (7/8) Epoch 6, batch 71600, loss[loss=2.292, over 3710.00 frames. , ppl: 9.89937135764125] tot_loss[loss=2.292, over 5417580.19 frames. , ppl: 9.897483827537586], batch size: 70
+2022-12-12 08:47:54,855 INFO [train.py:421] (7/8) Epoch 6, batch 71800, loss[loss=2.93, over 560.00 frames. , ppl: 18.72539516289488] tot_loss[loss=2.293, over 5375393.74 frames. , ppl: 9.909203944411145], batch size: 70
+2022-12-12 08:49:08,173 INFO [train.py:421] (7/8) Epoch 7, batch 0, loss[loss=2.116, over 7140.00 frames. , ppl: 8.29529139952929] tot_loss[loss=2.116, over 7140.00 frames. , ppl: 8.29529139952929], batch size: 70
+2022-12-12 08:50:48,796 INFO [train.py:421] (7/8) Epoch 7, batch 200, loss[loss=2.207, over 3570.00 frames. , ppl: 9.089709903886913] tot_loss[loss=2.278, over 515011.85 frames. , ppl: 9.759194604325065], batch size: 70
+2022-12-12 08:52:29,295 INFO [train.py:421] (7/8) Epoch 7, batch 400, loss[loss=2.26, over 3640.00 frames. , ppl: 9.582740543810266] tot_loss[loss=2.277, over 1001028.45 frames. , ppl: 9.747160545188049], batch size: 70
+2022-12-12 08:54:08,470 INFO [train.py:421] (7/8) Epoch 7, batch 600, loss[loss=2.492, over 980.00 frames. , ppl: 12.089366463515027] tot_loss[loss=2.279, over 1399705.28 frames. , ppl: 9.765029387073694], batch size: 70
+2022-12-12 08:55:44,621 INFO [train.py:421] (7/8) Epoch 7, batch 800, loss[loss=2.616, over 770.00 frames. , ppl: 13.684679017746893] tot_loss[loss=2.277, over 1789003.74 frames. , ppl: 9.746647453273134], batch size: 70
+2022-12-12 08:57:20,593 INFO [train.py:421] (7/8) Epoch 7, batch 1000, loss[loss=2.172, over 4690.00 frames. , ppl: 8.779789218782392] tot_loss[loss=2.278, over 2126278.93 frames. , ppl: 9.754398213220384], batch size: 70
+2022-12-12 08:57:20,594 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 08:57:21,340 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.279, over 211138.00 frames. , ppl: 9.766622303585429
+2022-12-12 08:58:56,585 INFO [train.py:421] (7/8) Epoch 7, batch 1200, loss[loss=2.528, over 840.00 frames. , ppl: 12.53354887180513] tot_loss[loss=2.28, over 2419191.74 frames. , ppl: 9.778584887781602], batch size: 70
+2022-12-12 09:00:32,855 INFO [train.py:421] (7/8) Epoch 7, batch 1400, loss[loss=3.297, over 490.00 frames. , ppl: 27.022180095574267] tot_loss[loss=2.282, over 2662331.33 frames. , ppl: 9.793841561202406], batch size: 70
+2022-12-12 09:02:12,541 INFO [train.py:421] (7/8) Epoch 7, batch 1600, loss[loss=2.39, over 1890.00 frames. , ppl: 10.915121479624133] tot_loss[loss=2.279, over 2945887.75 frames. , ppl: 9.764704401616997], batch size: 70
+2022-12-12 09:03:50,388 INFO [train.py:421] (7/8) Epoch 7, batch 1800, loss[loss=2.334, over 1820.00 frames. , ppl: 10.319799425464385] tot_loss[loss=2.278, over 3191506.63 frames. , ppl: 9.761599135303628], batch size: 70
+2022-12-12 09:05:32,156 INFO [train.py:421] (7/8) Epoch 7, batch 2000, loss[loss=2.329, over 1820.00 frames. , ppl: 10.263869521715765] tot_loss[loss=2.279, over 3416983.66 frames. , ppl: 9.763930379380467], batch size: 70
+2022-12-12 09:05:32,157 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 09:05:32,901 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.279, over 211138.00 frames. , ppl: 9.764543848320063
+2022-12-12 09:07:08,147 INFO [train.py:421] (7/8) Epoch 7, batch 2200, loss[loss=2.203, over 5600.00 frames. , ppl: 9.054628092345324] tot_loss[loss=2.28, over 3584222.41 frames. , ppl: 9.778132164859578], batch size: 70
+2022-12-12 09:08:47,616 INFO [train.py:421] (7/8) Epoch 7, batch 2400, loss[loss=2.337, over 2730.00 frames. , ppl: 10.3525602874678] tot_loss[loss=2.279, over 3780933.85 frames. , ppl: 9.766112396580578], batch size: 70
+2022-12-12 09:10:26,433 INFO [train.py:421] (7/8) Epoch 7, batch 2600, loss[loss=2.423, over 1120.00 frames. , ppl: 11.280412350975281] tot_loss[loss=2.28, over 3929126.20 frames. , ppl: 9.777059618245186], batch size: 70
+2022-12-12 09:12:07,878 INFO [train.py:421] (7/8) Epoch 7, batch 2800, loss[loss=2.153, over 9520.00 frames. , ppl: 8.61250899544913] tot_loss[loss=2.28, over 4070857.64 frames. , ppl: 9.778023491002697], batch size: 70
+2022-12-12 09:13:50,923 INFO [train.py:421] (7/8) Epoch 7, batch 3000, loss[loss=2.47, over 1050.00 frames. , ppl: 11.821982297548786] tot_loss[loss=2.281, over 4185184.54 frames. , ppl: 9.789598586773097], batch size: 70
+2022-12-12 09:13:50,924 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 09:13:51,668 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.277, over 211138.00 frames. , ppl: 9.743588919093323
+2022-12-12 09:15:28,748 INFO [train.py:421] (7/8) Epoch 7, batch 3200, loss[loss=2.273, over 1680.00 frames. , ppl: 9.70590752933341] tot_loss[loss=2.282, over 4307794.85 frames. , ppl: 9.79192329546546], batch size: 70
+2022-12-12 09:17:10,260 INFO [train.py:421] (7/8) Epoch 7, batch 3400, loss[loss=2.574, over 910.00 frames. , ppl: 13.119326978165422] tot_loss[loss=2.282, over 4387681.96 frames. , ppl: 9.79947631579737], batch size: 70
+2022-12-12 09:18:51,746 INFO [train.py:421] (7/8) Epoch 7, batch 3600, loss[loss=2.641, over 630.00 frames. , ppl: 14.029739887814875] tot_loss[loss=2.281, over 4544552.41 frames. , ppl: 9.784691786852449], batch size: 70
+2022-12-12 09:20:35,630 INFO [train.py:421] (7/8) Epoch 7, batch 3800, loss[loss=2.387, over 1960.00 frames. , ppl: 10.881724294427585] tot_loss[loss=2.281, over 4644415.28 frames. , ppl: 9.786588307028223], batch size: 70
+2022-12-12 09:22:13,513 INFO [train.py:421] (7/8) Epoch 7, batch 4000, loss[loss=2.302, over 3640.00 frames. , ppl: 9.993794926291741] tot_loss[loss=2.282, over 4714388.06 frames. , ppl: 9.791515929247375], batch size: 70
+2022-12-12 09:22:13,514 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 09:22:14,273 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.279, over 211138.00 frames. , ppl: 9.764824226068129
+2022-12-12 09:23:52,018 INFO [train.py:421] (7/8) Epoch 7, batch 4200, loss[loss=2.731, over 700.00 frames. , ppl: 15.349915481286695] tot_loss[loss=2.283, over 4751563.02 frames. , ppl: 9.80224763936784], batch size: 70
+2022-12-12 09:25:30,245 INFO [train.py:421] (7/8) Epoch 7, batch 4400, loss[loss=2.423, over 1610.00 frames. , ppl: 11.275640888770052] tot_loss[loss=2.283, over 4817650.17 frames. , ppl: 9.80367559980246], batch size: 70
+2022-12-12 09:27:09,464 INFO [train.py:421] (7/8) Epoch 7, batch 4600, loss[loss=2.194, over 7490.00 frames. , ppl: 8.973260531738893] tot_loss[loss=2.283, over 4870888.56 frames. , ppl: 9.803306440326725], batch size: 70
+2022-12-12 09:28:50,537 INFO [train.py:421] (7/8) Epoch 7, batch 4800, loss[loss=2.246, over 3710.00 frames. , ppl: 9.447341657105472] tot_loss[loss=2.281, over 4971383.09 frames. , ppl: 9.789861587419965], batch size: 70
+2022-12-12 09:30:30,395 INFO [train.py:421] (7/8) Epoch 7, batch 5000, loss[loss=2.298, over 2170.00 frames. , ppl: 9.951732989355426] tot_loss[loss=2.282, over 4982539.44 frames. , ppl: 9.792911709850861], batch size: 70
+2022-12-12 09:30:30,395 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 09:30:31,152 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.279, over 211138.00 frames. , ppl: 9.770388643082995
+2022-12-12 09:32:12,051 INFO [train.py:421] (7/8) Epoch 7, batch 5200, loss[loss=2.556, over 840.00 frames. , ppl: 12.883305507664058] tot_loss[loss=2.282, over 5013342.58 frames. , ppl: 9.79796243664453], batch size: 70
+2022-12-12 09:33:52,020 INFO [train.py:421] (7/8) Epoch 7, batch 5400, loss[loss=3.212, over 490.00 frames. , ppl: 24.834144171962638] tot_loss[loss=2.281, over 5080038.89 frames. , ppl: 9.786992874330721], batch size: 70
+2022-12-12 09:35:30,666 INFO [train.py:421] (7/8) Epoch 7, batch 5600, loss[loss=2.398, over 1190.00 frames. , ppl: 11.001094461093539] tot_loss[loss=2.282, over 5078585.33 frames. , ppl: 9.79476409307745], batch size: 70
+2022-12-12 09:37:13,202 INFO [train.py:421] (7/8) Epoch 7, batch 5800, loss[loss=2.446, over 980.00 frames. , ppl: 11.544565696972171] tot_loss[loss=2.282, over 5119970.35 frames. , ppl: 9.797063406577793], batch size: 70
+2022-12-12 09:38:55,668 INFO [train.py:421] (7/8) Epoch 7, batch 6000, loss[loss=2.198, over 4620.00 frames. , ppl: 9.008089174073413] tot_loss[loss=2.281, over 5208503.55 frames. , ppl: 9.785525258794616], batch size: 70
+2022-12-12 09:38:55,669 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 09:38:56,400 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.279, over 211138.00 frames. , ppl: 9.766977911177703
+2022-12-12 09:40:36,649 INFO [train.py:421] (7/8) Epoch 7, batch 6200, loss[loss=2.529, over 980.00 frames. , ppl: 12.536865815992282] tot_loss[loss=2.281, over 5243905.19 frames. , ppl: 9.783354825259313], batch size: 70
+2022-12-12 09:42:17,028 INFO [train.py:421] (7/8) Epoch 7, batch 6400, loss[loss=2.472, over 980.00 frames. , ppl: 11.844681946578225] tot_loss[loss=2.281, over 5234045.81 frames. , ppl: 9.788725650104515], batch size: 70
+2022-12-12 09:43:57,321 INFO [train.py:421] (7/8) Epoch 7, batch 6600, loss[loss=2.439, over 1260.00 frames. , ppl: 11.465195192258959] tot_loss[loss=2.281, over 5284268.84 frames. , ppl: 9.785044077823983], batch size: 70
+2022-12-12 09:45:38,138 INFO [train.py:421] (7/8) Epoch 7, batch 6800, loss[loss=2.401, over 1890.00 frames. , ppl: 11.035474496666831] tot_loss[loss=2.28, over 5318168.31 frames. , ppl: 9.777839376863621], batch size: 70
+2022-12-12 09:47:22,573 INFO [train.py:421] (7/8) Epoch 7, batch 7000, loss[loss=2.345, over 2310.00 frames. , ppl: 10.429249611575974] tot_loss[loss=2.28, over 5331105.45 frames. , ppl: 9.774229928166704], batch size: 70
+2022-12-12 09:47:22,574 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 09:47:23,332 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.278, over 211138.00 frames. , ppl: 9.761162606501355
+2022-12-12 09:49:03,423 INFO [train.py:421] (7/8) Epoch 7, batch 7200, loss[loss=2.278, over 5530.00 frames. , ppl: 9.755816209883584] tot_loss[loss=2.28, over 5342826.05 frames. , ppl: 9.77854832390492], batch size: 70
+2022-12-12 09:50:43,947 INFO [train.py:421] (7/8) Epoch 7, batch 7400, loss[loss=2.244, over 6790.00 frames. , ppl: 9.433756489023798] tot_loss[loss=2.28, over 5374018.06 frames. , ppl: 9.780837040424313], batch size: 70
+2022-12-12 09:52:24,714 INFO [train.py:421] (7/8) Epoch 7, batch 7600, loss[loss=2.182, over 5040.00 frames. , ppl: 8.864451598052506] tot_loss[loss=2.281, over 5376759.45 frames. , ppl: 9.785303661843642], batch size: 70
+2022-12-12 09:54:01,292 INFO [train.py:421] (7/8) Epoch 7, batch 7800, loss[loss=2.4, over 910.00 frames. , ppl: 11.019140311956374] tot_loss[loss=2.281, over 5403962.97 frames. , ppl: 9.790339298150283], batch size: 70
+2022-12-12 09:55:38,127 INFO [train.py:421] (7/8) Epoch 7, batch 8000, loss[loss=2.215, over 2730.00 frames. , ppl: 9.160318532583652] tot_loss[loss=2.281, over 5433831.57 frames. , ppl: 9.783736756561659], batch size: 70
+2022-12-12 09:55:38,128 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 09:55:38,887 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.279, over 211138.00 frames. , ppl: 9.762243320567698
+2022-12-12 09:57:20,370 INFO [train.py:421] (7/8) Epoch 7, batch 8200, loss[loss=2.249, over 2310.00 frames. , ppl: 9.479498852706657] tot_loss[loss=2.282, over 5381906.70 frames. , ppl: 9.797911406112997], batch size: 70
+2022-12-12 09:59:00,400 INFO [train.py:421] (7/8) Epoch 7, batch 8400, loss[loss=2.244, over 5740.00 frames. , ppl: 9.428808488826908] tot_loss[loss=2.283, over 5361217.05 frames. , ppl: 9.810930468713412], batch size: 70
+2022-12-12 10:00:40,151 INFO [train.py:421] (7/8) Epoch 7, batch 8600, loss[loss=2.274, over 3360.00 frames. , ppl: 9.72034747016154] tot_loss[loss=2.284, over 5343565.38 frames. , ppl: 9.816719372461545], batch size: 70
+2022-12-12 10:02:20,375 INFO [train.py:421] (7/8) Epoch 7, batch 8800, loss[loss=2.228, over 4970.00 frames. , ppl: 9.285378496299582] tot_loss[loss=2.283, over 5386815.25 frames. , ppl: 9.802261824121693], batch size: 70
+2022-12-12 10:04:02,210 INFO [train.py:421] (7/8) Epoch 7, batch 9000, loss[loss=2.401, over 1330.00 frames. , ppl: 11.033403654853142] tot_loss[loss=2.282, over 5421970.82 frames. , ppl: 9.795017613850327], batch size: 70
+2022-12-12 10:04:02,210 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 10:04:02,970 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.278, over 211138.00 frames. , ppl: 9.758306803162158
+2022-12-12 10:05:41,201 INFO [train.py:421] (7/8) Epoch 7, batch 9200, loss[loss=2.202, over 3920.00 frames. , ppl: 9.043619672908239] tot_loss[loss=2.282, over 5420924.70 frames. , ppl: 9.794291524513925], batch size: 70
+2022-12-12 10:07:18,497 INFO [train.py:421] (7/8) Epoch 7, batch 9400, loss[loss=2.181, over 3990.00 frames. , ppl: 8.85137677367792] tot_loss[loss=2.282, over 5432698.27 frames. , ppl: 9.79778857045946], batch size: 70
+2022-12-12 10:08:57,690 INFO [train.py:421] (7/8) Epoch 7, batch 9600, loss[loss=2.382, over 2660.00 frames. , ppl: 10.823959450675416] tot_loss[loss=2.282, over 5400721.10 frames. , ppl: 9.799409844256385], batch size: 70
+2022-12-12 10:10:41,235 INFO [train.py:421] (7/8) Epoch 7, batch 9800, loss[loss=2.249, over 1540.00 frames. , ppl: 9.482863745334237] tot_loss[loss=2.281, over 5430469.44 frames. , ppl: 9.788536909414931], batch size: 70
+2022-12-12 10:12:17,309 INFO [train.py:421] (7/8) Epoch 7, batch 10000, loss[loss=2.171, over 12040.00 frames. , ppl: 8.77127292913329] tot_loss[loss=2.283, over 5379568.69 frames. , ppl: 9.801276884225196], batch size: 70
+2022-12-12 10:12:17,309 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 10:12:18,035 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.277, over 211138.00 frames. , ppl: 9.743937919324686
+2022-12-12 10:13:56,312 INFO [train.py:421] (7/8) Epoch 7, batch 10200, loss[loss=2.206, over 5740.00 frames. , ppl: 9.081264285752889] tot_loss[loss=2.283, over 5379133.99 frames. , ppl: 9.805265428863422], batch size: 70
+2022-12-12 10:15:40,297 INFO [train.py:421] (7/8) Epoch 7, batch 10400, loss[loss=3.268, over 490.00 frames. , ppl: 26.264589101133723] tot_loss[loss=2.282, over 5446858.48 frames. , ppl: 9.792050388377746], batch size: 70
+2022-12-12 10:17:21,282 INFO [train.py:421] (7/8) Epoch 7, batch 10600, loss[loss=2.382, over 1960.00 frames. , ppl: 10.823800926126955] tot_loss[loss=2.283, over 5409647.79 frames. , ppl: 9.8069101654781], batch size: 70
+2022-12-12 10:18:59,591 INFO [train.py:421] (7/8) Epoch 7, batch 10800, loss[loss=2.439, over 1890.00 frames. , ppl: 11.467079199172417] tot_loss[loss=2.283, over 5416597.68 frames. , ppl: 9.80663990735446], batch size: 70
+2022-12-12 10:20:44,637 INFO [train.py:421] (7/8) Epoch 7, batch 11000, loss[loss=2.497, over 1050.00 frames. , ppl: 12.147925757194955] tot_loss[loss=2.281, over 5476098.33 frames. , ppl: 9.78718512635329], batch size: 70
+2022-12-12 10:20:44,638 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 10:20:45,398 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.279, over 211138.00 frames. , ppl: 9.764081387151732
+2022-12-12 10:22:26,516 INFO [train.py:421] (7/8) Epoch 7, batch 11200, loss[loss=2.52, over 840.00 frames. , ppl: 12.425249242131807] tot_loss[loss=2.282, over 5461662.49 frames. , ppl: 9.797724523172057], batch size: 70
+2022-12-12 10:24:09,620 INFO [train.py:421] (7/8) Epoch 7, batch 11400, loss[loss=2.551, over 1120.00 frames. , ppl: 12.82229419598962] tot_loss[loss=2.282, over 5476137.88 frames. , ppl: 9.795642193713725], batch size: 70
+2022-12-12 10:25:51,780 INFO [train.py:421] (7/8) Epoch 7, batch 11600, loss[loss=2.325, over 840.00 frames. , ppl: 10.230586459011265] tot_loss[loss=2.282, over 5511776.11 frames. , ppl: 9.791798497009411], batch size: 70
+2022-12-12 10:27:33,063 INFO [train.py:421] (7/8) Epoch 7, batch 11800, loss[loss=2.212, over 4480.00 frames. , ppl: 9.13439965001628] tot_loss[loss=2.281, over 5502636.77 frames. , ppl: 9.79120081897473], batch size: 70
+2022-12-12 10:29:14,367 INFO [train.py:421] (7/8) Epoch 7, batch 12000, loss[loss=2.27, over 3850.00 frames. , ppl: 9.679174937833862] tot_loss[loss=2.281, over 5516157.35 frames. , ppl: 9.789652153339423], batch size: 70
+2022-12-12 10:29:14,368 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 10:29:15,131 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.279, over 211138.00 frames. , ppl: 9.770513007653056
+2022-12-12 10:30:57,657 INFO [train.py:421] (7/8) Epoch 7, batch 12200, loss[loss=2.402, over 1540.00 frames. , ppl: 11.041043671408413] tot_loss[loss=2.281, over 5529783.92 frames. , ppl: 9.790469701102056], batch size: 70
+2022-12-12 10:32:39,419 INFO [train.py:421] (7/8) Epoch 7, batch 12400, loss[loss=2.308, over 2590.00 frames. , ppl: 10.05465882065721] tot_loss[loss=2.28, over 5573350.82 frames. , ppl: 9.775101254560331], batch size: 70
+2022-12-12 10:34:19,730 INFO [train.py:421] (7/8) Epoch 7, batch 12600, loss[loss=2.41, over 1260.00 frames. , ppl: 11.134930697240446] tot_loss[loss=2.28, over 5544693.42 frames. , ppl: 9.780688382955796], batch size: 70
+2022-12-12 10:35:58,810 INFO [train.py:421] (7/8) Epoch 7, batch 12800, loss[loss=2.412, over 1120.00 frames. , ppl: 11.156856318464333] tot_loss[loss=2.28, over 5538140.08 frames. , ppl: 9.780083434893676], batch size: 70
+2022-12-12 10:37:35,200 INFO [train.py:421] (7/8) Epoch 7, batch 13000, loss[loss=2.909, over 630.00 frames. , ppl: 18.34631736762981] tot_loss[loss=2.28, over 5520842.88 frames. , ppl: 9.779878589314128], batch size: 70
+2022-12-12 10:37:35,200 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 10:37:35,946 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.279, over 211138.00 frames. , ppl: 9.769163881244294
+2022-12-12 10:39:15,583 INFO [train.py:421] (7/8) Epoch 7, batch 13200, loss[loss=2.491, over 910.00 frames. , ppl: 12.072155510260055] tot_loss[loss=2.28, over 5541516.51 frames. , ppl: 9.778501023969126], batch size: 70
+2022-12-12 10:40:55,458 INFO [train.py:421] (7/8) Epoch 7, batch 13400, loss[loss=2.247, over 2240.00 frames. , ppl: 9.455257293167156] tot_loss[loss=2.282, over 5506805.58 frames. , ppl: 9.793732315401092], batch size: 70
+2022-12-12 10:42:34,883 INFO [train.py:421] (7/8) Epoch 7, batch 13600, loss[loss=2.18, over 3150.00 frames. , ppl: 8.841927521622331] tot_loss[loss=2.282, over 5492278.63 frames. , ppl: 9.79775868701485], batch size: 70
+2022-12-12 10:44:12,345 INFO [train.py:421] (7/8) Epoch 7, batch 13800, loss[loss=2.233, over 4690.00 frames. , ppl: 9.330296942787516] tot_loss[loss=2.282, over 5506456.68 frames. , ppl: 9.793777289865876], batch size: 70
+2022-12-12 10:45:49,785 INFO [train.py:421] (7/8) Epoch 7, batch 14000, loss[loss=2.477, over 980.00 frames. , ppl: 11.909278964603134] tot_loss[loss=2.282, over 5490690.32 frames. , ppl: 9.799127952306714], batch size: 70
+2022-12-12 10:45:49,785 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 10:45:50,534 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.282, over 211138.00 frames. , ppl: 9.796524022897163
+2022-12-12 10:47:32,824 INFO [train.py:421] (7/8) Epoch 7, batch 14200, loss[loss=2.345, over 2240.00 frames. , ppl: 10.437621133673337] tot_loss[loss=2.282, over 5490392.17 frames. , ppl: 9.798839531992328], batch size: 70
+2022-12-12 10:49:07,721 INFO [train.py:421] (7/8) Epoch 7, batch 14400, loss[loss=2.72, over 840.00 frames. , ppl: 15.18714571066998] tot_loss[loss=2.282, over 5508877.89 frames. , ppl: 9.799942510766677], batch size: 70
+2022-12-12 10:50:46,722 INFO [train.py:421] (7/8) Epoch 7, batch 14600, loss[loss=2.456, over 840.00 frames. , ppl: 11.660878682993967] tot_loss[loss=2.282, over 5474639.82 frames. , ppl: 9.800455946524822], batch size: 70
+2022-12-12 10:52:28,746 INFO [train.py:421] (7/8) Epoch 7, batch 14800, loss[loss=2.149, over 11760.00 frames. , ppl: 8.580036301186038] tot_loss[loss=2.283, over 5472794.27 frames. , ppl: 9.803615712147224], batch size: 70
+2022-12-12 10:54:11,258 INFO [train.py:421] (7/8) Epoch 7, batch 15000, loss[loss=2.417, over 1120.00 frames. , ppl: 11.216729336703471] tot_loss[loss=2.283, over 5466379.33 frames. , ppl: 9.804860096398135], batch size: 70
+2022-12-12 10:54:11,259 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 10:54:12,021 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.277, over 211138.00 frames. , ppl: 9.747404083511375
+2022-12-12 10:55:53,728 INFO [train.py:421] (7/8) Epoch 7, batch 15200, loss[loss=2.526, over 980.00 frames. , ppl: 12.502825261237337] tot_loss[loss=2.283, over 5474601.55 frames. , ppl: 9.803243751900526], batch size: 70
+2022-12-12 10:57:32,865 INFO [train.py:421] (7/8) Epoch 7, batch 15400, loss[loss=2.317, over 1190.00 frames. , ppl: 10.145436386938075] tot_loss[loss=2.282, over 5517156.89 frames. , ppl: 9.794374821866482], batch size: 70
+2022-12-12 10:59:08,552 INFO [train.py:421] (7/8) Epoch 7, batch 15600, loss[loss=2.747, over 700.00 frames. , ppl: 15.591638758149998] tot_loss[loss=2.283, over 5468299.35 frames. , ppl: 9.807274313056014], batch size: 70
+2022-12-12 11:00:48,237 INFO [train.py:421] (7/8) Epoch 7, batch 15800, loss[loss=2.197, over 4970.00 frames. , ppl: 8.994160622435242] tot_loss[loss=2.283, over 5459791.78 frames. , ppl: 9.810444192315757], batch size: 70
+2022-12-12 11:02:25,864 INFO [train.py:421] (7/8) Epoch 7, batch 16000, loss[loss=2.178, over 4340.00 frames. , ppl: 8.832731604129867] tot_loss[loss=2.284, over 5455234.07 frames. , ppl: 9.81306898532702], batch size: 70
+2022-12-12 11:02:25,864 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 11:02:26,595 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.278, over 211138.00 frames. , ppl: 9.759092535215544
+2022-12-12 11:04:07,743 INFO [train.py:421] (7/8) Epoch 7, batch 16200, loss[loss=2.579, over 770.00 frames. , ppl: 13.190505105192882] tot_loss[loss=2.282, over 5503646.35 frames. , ppl: 9.791364810138962], batch size: 70
+2022-12-12 11:05:46,870 INFO [train.py:421] (7/8) Epoch 7, batch 16400, loss[loss=2.44, over 1400.00 frames. , ppl: 11.472860677650461] tot_loss[loss=2.281, over 5507053.06 frames. , ppl: 9.790169722570573], batch size: 70
+2022-12-12 11:07:27,129 INFO [train.py:421] (7/8) Epoch 7, batch 16600, loss[loss=2.627, over 770.00 frames. , ppl: 13.835387289852381] tot_loss[loss=2.282, over 5482403.63 frames. , ppl: 9.797551231573323], batch size: 70
+2022-12-12 11:09:03,992 INFO [train.py:421] (7/8) Epoch 7, batch 16800, loss[loss=2.175, over 5670.00 frames. , ppl: 8.800144783788262] tot_loss[loss=2.283, over 5458378.60 frames. , ppl: 9.804651022833813], batch size: 70
+2022-12-12 11:10:44,191 INFO [train.py:421] (7/8) Epoch 7, batch 17000, loss[loss=2.29, over 4340.00 frames. , ppl: 9.87814810873214] tot_loss[loss=2.284, over 5444706.45 frames. , ppl: 9.815167083300329], batch size: 70
+2022-12-12 11:10:44,191 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 11:10:44,952 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.278, over 211138.00 frames. , ppl: 9.755632321970248
+2022-12-12 11:12:25,677 INFO [train.py:421] (7/8) Epoch 7, batch 17200, loss[loss=2.191, over 8050.00 frames. , ppl: 8.948616438443484] tot_loss[loss=2.284, over 5459768.21 frames. , ppl: 9.81229829996889], batch size: 70
+2022-12-12 11:14:04,100 INFO [train.py:421] (7/8) Epoch 7, batch 17400, loss[loss=2.306, over 1540.00 frames. , ppl: 10.03566620617779] tot_loss[loss=2.283, over 5488644.72 frames. , ppl: 9.805996245298784], batch size: 70
+2022-12-12 11:15:49,432 INFO [train.py:421] (7/8) Epoch 7, batch 17600, loss[loss=2.896, over 560.00 frames. , ppl: 18.09305753107164] tot_loss[loss=2.283, over 5486028.76 frames. , ppl: 9.808533751044942], batch size: 70
+2022-12-12 11:17:26,212 INFO [train.py:421] (7/8) Epoch 7, batch 17800, loss[loss=2.465, over 1400.00 frames. , ppl: 11.765876365960526] tot_loss[loss=2.284, over 5472659.31 frames. , ppl: 9.817591405407455], batch size: 70
+2022-12-12 11:19:03,111 INFO [train.py:421] (7/8) Epoch 7, batch 18000, loss[loss=2.303, over 2450.00 frames. , ppl: 10.0008810125654] tot_loss[loss=2.284, over 5456600.77 frames. , ppl: 9.820105754523038], batch size: 70
+2022-12-12 11:19:03,111 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 11:19:03,871 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.278, over 211138.00 frames. , ppl: 9.756920371505483
+2022-12-12 11:20:45,120 INFO [train.py:421] (7/8) Epoch 7, batch 18200, loss[loss=2.268, over 3990.00 frames. , ppl: 9.664297548191875] tot_loss[loss=2.285, over 5445678.95 frames. , ppl: 9.825535888270345], batch size: 70
+2022-12-12 11:22:26,378 INFO [train.py:421] (7/8) Epoch 7, batch 18400, loss[loss=2.18, over 6930.00 frames. , ppl: 8.842844366912844] tot_loss[loss=2.284, over 5445118.85 frames. , ppl: 9.819613766777373], batch size: 70
+2022-12-12 11:24:05,729 INFO [train.py:421] (7/8) Epoch 7, batch 18600, loss[loss=2.168, over 4200.00 frames. , ppl: 8.739231577650932] tot_loss[loss=2.285, over 5447765.28 frames. , ppl: 9.822559761532274], batch size: 70
+2022-12-12 11:25:43,136 INFO [train.py:421] (7/8) Epoch 7, batch 18800, loss[loss=2.431, over 1260.00 frames. , ppl: 11.371419295816906] tot_loss[loss=2.286, over 5452980.48 frames. , ppl: 9.831335819241819], batch size: 70
+2022-12-12 11:27:23,642 INFO [train.py:421] (7/8) Epoch 7, batch 19000, loss[loss=2.279, over 2800.00 frames. , ppl: 9.765628564306095] tot_loss[loss=2.285, over 5469020.14 frames. , ppl: 9.826970610293328], batch size: 70
+2022-12-12 11:27:23,642 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 11:27:24,402 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.278, over 211138.00 frames. , ppl: 9.753232844662795
+2022-12-12 11:29:02,269 INFO [train.py:421] (7/8) Epoch 7, batch 19200, loss[loss=2.198, over 4550.00 frames. , ppl: 9.007270329247655] tot_loss[loss=2.284, over 5502839.55 frames. , ppl: 9.813297343421338], batch size: 70
+2022-12-12 11:30:43,914 INFO [train.py:421] (7/8) Epoch 7, batch 19400, loss[loss=2.354, over 2240.00 frames. , ppl: 10.526723815838896] tot_loss[loss=2.284, over 5488119.96 frames. , ppl: 9.812911383220518], batch size: 70
+2022-12-12 11:32:24,646 INFO [train.py:421] (7/8) Epoch 7, batch 19600, loss[loss=2.369, over 1470.00 frames. , ppl: 10.682971392350819] tot_loss[loss=2.284, over 5456314.84 frames. , ppl: 9.820166039645233], batch size: 70
+2022-12-12 11:34:05,672 INFO [train.py:421] (7/8) Epoch 7, batch 19800, loss[loss=2.53, over 1120.00 frames. , ppl: 12.554232410756262] tot_loss[loss=2.284, over 5469603.82 frames. , ppl: 9.817834029702867], batch size: 70
+2022-12-12 11:35:44,818 INFO [train.py:421] (7/8) Epoch 7, batch 20000, loss[loss=2.799, over 630.00 frames. , ppl: 16.427672269752843] tot_loss[loss=2.285, over 5413941.54 frames. , ppl: 9.828257089964517], batch size: 70
+2022-12-12 11:35:44,819 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 11:35:45,578 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.276, over 211138.00 frames. , ppl: 9.73576853706518
+2022-12-12 11:37:27,967 INFO [train.py:421] (7/8) Epoch 7, batch 20200, loss[loss=2.232, over 1820.00 frames. , ppl: 9.314848800243286] tot_loss[loss=2.285, over 5408128.85 frames. , ppl: 9.828679224672408], batch size: 70
+2022-12-12 11:39:05,109 INFO [train.py:421] (7/8) Epoch 7, batch 20400, loss[loss=2.426, over 1400.00 frames. , ppl: 11.313418137695539] tot_loss[loss=2.285, over 5396573.53 frames. , ppl: 9.823084390074978], batch size: 70
+2022-12-12 11:40:47,470 INFO [train.py:421] (7/8) Epoch 7, batch 20600, loss[loss=2.4, over 910.00 frames. , ppl: 11.02169779565496] tot_loss[loss=2.284, over 5414277.62 frames. , ppl: 9.820589849569412], batch size: 70
+2022-12-12 11:42:27,082 INFO [train.py:421] (7/8) Epoch 7, batch 20800, loss[loss=2.319, over 3010.00 frames. , ppl: 10.168513472261168] tot_loss[loss=2.284, over 5408214.44 frames. , ppl: 9.818952705672318], batch size: 70
+2022-12-12 11:44:06,644 INFO [train.py:421] (7/8) Epoch 7, batch 21000, loss[loss=2.245, over 6930.00 frames. , ppl: 9.440917900739628] tot_loss[loss=2.286, over 5364788.05 frames. , ppl: 9.831609104913483], batch size: 70
+2022-12-12 11:44:06,644 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 11:44:07,376 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.277, over 211138.00 frames. , ppl: 9.750929208941372
+2022-12-12 11:45:45,792 INFO [train.py:421] (7/8) Epoch 7, batch 21200, loss[loss=2.511, over 910.00 frames. , ppl: 12.32021903520425] tot_loss[loss=2.285, over 5379619.89 frames. , ppl: 9.829411351364362], batch size: 70
+2022-12-12 11:47:26,538 INFO [train.py:421] (7/8) Epoch 7, batch 21400, loss[loss=2.311, over 2870.00 frames. , ppl: 10.079503460152326] tot_loss[loss=2.286, over 5377559.38 frames. , ppl: 9.832756130045817], batch size: 70
+2022-12-12 11:49:07,974 INFO [train.py:421] (7/8) Epoch 7, batch 21600, loss[loss=2.376, over 1680.00 frames. , ppl: 10.764944363919364] tot_loss[loss=2.285, over 5395583.12 frames. , ppl: 9.822076542342455], batch size: 70
+2022-12-12 11:50:45,615 INFO [train.py:421] (7/8) Epoch 7, batch 21800, loss[loss=2.238, over 3990.00 frames. , ppl: 9.371868085622502] tot_loss[loss=2.284, over 5422996.29 frames. , ppl: 9.812367734007752], batch size: 70
+2022-12-12 11:52:26,437 INFO [train.py:421] (7/8) Epoch 7, batch 22000, loss[loss=2.297, over 1260.00 frames. , ppl: 9.939733193136126] tot_loss[loss=2.284, over 5419668.76 frames. , ppl: 9.816220390807127], batch size: 70
+2022-12-12 11:52:26,438 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 11:52:27,187 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.276, over 211138.00 frames. , ppl: 9.739122243408765
+2022-12-12 11:54:05,002 INFO [train.py:421] (7/8) Epoch 7, batch 22200, loss[loss=2.175, over 6790.00 frames. , ppl: 8.799342230089174] tot_loss[loss=2.286, over 5363144.55 frames. , ppl: 9.833679769580952], batch size: 70
+2022-12-12 11:55:47,111 INFO [train.py:421] (7/8) Epoch 7, batch 22400, loss[loss=2.31, over 2450.00 frames. , ppl: 10.074617407329226] tot_loss[loss=2.285, over 5379437.92 frames. , ppl: 9.828278601100237], batch size: 70
+2022-12-12 11:57:29,556 INFO [train.py:421] (7/8) Epoch 7, batch 22600, loss[loss=2.399, over 2030.00 frames. , ppl: 11.007236891061964] tot_loss[loss=2.285, over 5399672.20 frames. , ppl: 9.826424265490973], batch size: 70
+2022-12-12 11:59:10,045 INFO [train.py:421] (7/8) Epoch 7, batch 22800, loss[loss=2.525, over 1190.00 frames. , ppl: 12.496639447756726] tot_loss[loss=2.283, over 5488390.57 frames. , ppl: 9.804685190122692], batch size: 70
+2022-12-12 12:00:50,387 INFO [train.py:421] (7/8) Epoch 7, batch 23000, loss[loss=4.061, over 350.00 frames. , ppl: 58.01901414049031] tot_loss[loss=2.282, over 5527521.10 frames. , ppl: 9.799072286492432], batch size: 70
+2022-12-12 12:00:50,388 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 12:00:51,133 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.276, over 211138.00 frames. , ppl: 9.741689827028287
+2022-12-12 12:02:30,419 INFO [train.py:421] (7/8) Epoch 7, batch 23200, loss[loss=2.73, over 630.00 frames. , ppl: 15.339267543039282] tot_loss[loss=2.283, over 5495633.90 frames. , ppl: 9.805771814867661], batch size: 70
+2022-12-12 12:04:11,332 INFO [train.py:421] (7/8) Epoch 7, batch 23400, loss[loss=2.349, over 1750.00 frames. , ppl: 10.480234676401368] tot_loss[loss=2.284, over 5447171.57 frames. , ppl: 9.817416777337046], batch size: 70
+2022-12-12 12:05:50,808 INFO [train.py:421] (7/8) Epoch 7, batch 23600, loss[loss=2.239, over 5600.00 frames. , ppl: 9.383347664268825] tot_loss[loss=2.284, over 5430939.46 frames. , ppl: 9.820239174909778], batch size: 70
+2022-12-12 12:07:34,133 INFO [train.py:421] (7/8) Epoch 7, batch 23800, loss[loss=2.384, over 1820.00 frames. , ppl: 10.850897899165684] tot_loss[loss=2.282, over 5528035.58 frames. , ppl: 9.794040417396802], batch size: 70
+2022-12-12 12:09:14,677 INFO [train.py:421] (7/8) Epoch 7, batch 24000, loss[loss=2.262, over 3080.00 frames. , ppl: 9.601823819109072] tot_loss[loss=2.28, over 5579104.07 frames. , ppl: 9.776219741485923], batch size: 70
+2022-12-12 12:09:14,677 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 12:09:15,425 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.277, over 211138.00 frames. , ppl: 9.74665824206101
+2022-12-12 12:10:54,505 INFO [train.py:421] (7/8) Epoch 7, batch 24200, loss[loss=2.223, over 3920.00 frames. , ppl: 9.238027456112114] tot_loss[loss=2.28, over 5589862.68 frames. , ppl: 9.775560548182465], batch size: 70
+2022-12-12 12:12:37,633 INFO [train.py:421] (7/8) Epoch 7, batch 24400, loss[loss=2.335, over 2450.00 frames. , ppl: 10.325938187318036] tot_loss[loss=2.281, over 5557641.98 frames. , ppl: 9.788004683392499], batch size: 70
+2022-12-12 12:14:18,813 INFO [train.py:421] (7/8) Epoch 7, batch 24600, loss[loss=2.172, over 5320.00 frames. , ppl: 8.777234321137568] tot_loss[loss=2.282, over 5523713.16 frames. , ppl: 9.799751365611035], batch size: 70
+2022-12-12 12:15:58,739 INFO [train.py:421] (7/8) Epoch 7, batch 24800, loss[loss=2.262, over 2730.00 frames. , ppl: 9.604839897350212] tot_loss[loss=2.282, over 5532832.20 frames. , ppl: 9.791904127015954], batch size: 70
+2022-12-12 12:17:36,506 INFO [train.py:421] (7/8) Epoch 7, batch 25000, loss[loss=2.12, over 6720.00 frames. , ppl: 8.333238794308444] tot_loss[loss=2.282, over 5534689.27 frames. , ppl: 9.791964625395206], batch size: 70
+2022-12-12 12:17:36,506 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 12:17:37,246 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.276, over 211138.00 frames. , ppl: 9.73495874762003
+2022-12-12 12:19:18,781 INFO [train.py:421] (7/8) Epoch 7, batch 25200, loss[loss=2.151, over 5180.00 frames. , ppl: 8.59742201753109] tot_loss[loss=2.282, over 5523290.55 frames. , ppl: 9.797338930512733], batch size: 70
+2022-12-12 12:20:57,134 INFO [train.py:421] (7/8) Epoch 7, batch 25400, loss[loss=2.268, over 3990.00 frames. , ppl: 9.65723006950081] tot_loss[loss=2.281, over 5552000.27 frames. , ppl: 9.785835551044324], batch size: 70
+2022-12-12 12:22:35,789 INFO [train.py:421] (7/8) Epoch 7, batch 25600, loss[loss=2.608, over 910.00 frames. , ppl: 13.568021295802128] tot_loss[loss=2.281, over 5541185.69 frames. , ppl: 9.790806788378175], batch size: 70
+2022-12-12 12:24:16,861 INFO [train.py:421] (7/8) Epoch 7, batch 25800, loss[loss=2.193, over 3080.00 frames. , ppl: 8.96465497497526] tot_loss[loss=2.281, over 5559654.81 frames. , ppl: 9.785535911701887], batch size: 70
+2022-12-12 12:25:56,647 INFO [train.py:421] (7/8) Epoch 7, batch 26000, loss[loss=2.419, over 1610.00 frames. , ppl: 11.235445975670546] tot_loss[loss=2.28, over 5561079.67 frames. , ppl: 9.78123896360281], batch size: 70
+2022-12-12 12:25:56,647 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 12:25:57,404 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.277, over 211138.00 frames. , ppl: 9.75006332120515
+2022-12-12 12:27:34,576 INFO [train.py:421] (7/8) Epoch 7, batch 26200, loss[loss=2.252, over 6300.00 frames. , ppl: 9.505544976047863] tot_loss[loss=2.279, over 5611673.80 frames. , ppl: 9.762698541926824], batch size: 70
+2022-12-12 12:29:16,204 INFO [train.py:421] (7/8) Epoch 7, batch 26400, loss[loss=2.314, over 4340.00 frames. , ppl: 10.109987690999727] tot_loss[loss=2.28, over 5589623.91 frames. , ppl: 9.773039541494875], batch size: 70
+2022-12-12 12:30:55,037 INFO [train.py:421] (7/8) Epoch 7, batch 26600, loss[loss=2.263, over 2170.00 frames. , ppl: 9.609126401047225] tot_loss[loss=2.281, over 5531691.09 frames. , ppl: 9.791131212928502], batch size: 70
+2022-12-12 12:32:37,087 INFO [train.py:421] (7/8) Epoch 7, batch 26800, loss[loss=2.212, over 5250.00 frames. , ppl: 9.134574341133137] tot_loss[loss=2.281, over 5534267.03 frames. , ppl: 9.78723584240344], batch size: 70
+2022-12-12 12:34:13,502 INFO [train.py:421] (7/8) Epoch 7, batch 27000, loss[loss=2.477, over 910.00 frames. , ppl: 11.908041156838173] tot_loss[loss=2.282, over 5502116.90 frames. , ppl: 9.80101505821011], batch size: 70
+2022-12-12 12:34:13,502 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 12:34:14,248 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.276, over 211138.00 frames. , ppl: 9.741972432318025
+2022-12-12 12:35:56,493 INFO [train.py:421] (7/8) Epoch 7, batch 27200, loss[loss=2.141, over 3290.00 frames. , ppl: 8.509069333065879] tot_loss[loss=2.282, over 5518284.81 frames. , ppl: 9.793941724725865], batch size: 70
+2022-12-12 12:37:39,587 INFO [train.py:421] (7/8) Epoch 7, batch 27400, loss[loss=2.499, over 980.00 frames. , ppl: 12.166722487809885] tot_loss[loss=2.282, over 5524855.87 frames. , ppl: 9.792013384189428], batch size: 70
+2022-12-12 12:39:19,442 INFO [train.py:421] (7/8) Epoch 7, batch 27600, loss[loss=2.435, over 1680.00 frames. , ppl: 11.419943983127682] tot_loss[loss=2.282, over 5513013.12 frames. , ppl: 9.793321957372687], batch size: 70
+2022-12-12 12:41:01,780 INFO [train.py:421] (7/8) Epoch 7, batch 27800, loss[loss=2.151, over 11550.00 frames. , ppl: 8.59701058112999] tot_loss[loss=2.28, over 5557425.25 frames. , ppl: 9.779411667978666], batch size: 70
+2022-12-12 12:42:41,588 INFO [train.py:421] (7/8) Epoch 7, batch 28000, loss[loss=2.174, over 7140.00 frames. , ppl: 8.790346662131753] tot_loss[loss=2.28, over 5568274.22 frames. , ppl: 9.779401723586476], batch size: 70
+2022-12-12 12:42:41,589 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 12:42:42,348 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.277, over 211138.00 frames. , ppl: 9.745110478587499
+2022-12-12 12:44:19,018 INFO [train.py:421] (7/8) Epoch 7, batch 28200, loss[loss=2.173, over 4900.00 frames. , ppl: 8.782918128716977] tot_loss[loss=2.282, over 5508297.74 frames. , ppl: 9.794502744959885], batch size: 70
+2022-12-12 12:45:59,453 INFO [train.py:421] (7/8) Epoch 7, batch 28400, loss[loss=2.333, over 1960.00 frames. , ppl: 10.308943283699158] tot_loss[loss=2.282, over 5536151.05 frames. , ppl: 9.794314265548023], batch size: 70
+2022-12-12 12:47:41,288 INFO [train.py:421] (7/8) Epoch 7, batch 28600, loss[loss=2.413, over 1260.00 frames. , ppl: 11.165722323689499] tot_loss[loss=2.283, over 5486857.07 frames. , ppl: 9.808630931698335], batch size: 70
+2022-12-12 12:49:21,364 INFO [train.py:421] (7/8) Epoch 7, batch 28800, loss[loss=2.391, over 1260.00 frames. , ppl: 10.92864219944394] tot_loss[loss=2.283, over 5510186.83 frames. , ppl: 9.806407135593842], batch size: 70
+2022-12-12 12:50:59,773 INFO [train.py:421] (7/8) Epoch 7, batch 29000, loss[loss=2.644, over 770.00 frames. , ppl: 14.071052862800316] tot_loss[loss=2.283, over 5524758.57 frames. , ppl: 9.805079718816918], batch size: 70
+2022-12-12 12:50:59,773 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 12:51:00,533 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.278, over 211138.00 frames. , ppl: 9.757074891112701
+2022-12-12 12:52:40,868 INFO [train.py:421] (7/8) Epoch 7, batch 29200, loss[loss=2.515, over 910.00 frames. , ppl: 12.363711358215214] tot_loss[loss=2.282, over 5530118.75 frames. , ppl: 9.798682813747037], batch size: 70
+2022-12-12 12:54:23,398 INFO [train.py:421] (7/8) Epoch 7, batch 29400, loss[loss=2.265, over 3570.00 frames. , ppl: 9.631288735874659] tot_loss[loss=2.283, over 5522108.31 frames. , ppl: 9.803756165440298], batch size: 70
+2022-12-12 12:56:02,449 INFO [train.py:421] (7/8) Epoch 7, batch 29600, loss[loss=2.21, over 6930.00 frames. , ppl: 9.1128340179155] tot_loss[loss=2.281, over 5564383.29 frames. , ppl: 9.789672676063013], batch size: 70
+2022-12-12 12:57:39,010 INFO [train.py:421] (7/8) Epoch 7, batch 29800, loss[loss=2.337, over 3010.00 frames. , ppl: 10.352195220559299] tot_loss[loss=2.282, over 5528815.62 frames. , ppl: 9.800627591382659], batch size: 70
+2022-12-12 12:59:14,357 INFO [train.py:421] (7/8) Epoch 7, batch 30000, loss[loss=2.222, over 1680.00 frames. , ppl: 9.223507610115727] tot_loss[loss=2.284, over 5477603.35 frames. , ppl: 9.814619979158541], batch size: 70
+2022-12-12 12:59:14,358 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 12:59:15,118 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.278, over 211138.00 frames. , ppl: 9.757277069995297
+2022-12-12 13:00:54,969 INFO [train.py:421] (7/8) Epoch 7, batch 30200, loss[loss=2.392, over 2030.00 frames. , ppl: 10.93727758688976] tot_loss[loss=2.284, over 5475252.22 frames. , ppl: 9.81984032099664], batch size: 70
+2022-12-12 13:02:35,777 INFO [train.py:421] (7/8) Epoch 7, batch 30400, loss[loss=2.287, over 2520.00 frames. , ppl: 9.84745682652661] tot_loss[loss=2.285, over 5466698.85 frames. , ppl: 9.823429334864061], batch size: 70
+2022-12-12 13:04:16,901 INFO [train.py:421] (7/8) Epoch 7, batch 30600, loss[loss=2.406, over 1400.00 frames. , ppl: 11.090991045681625] tot_loss[loss=2.284, over 5502987.40 frames. , ppl: 9.81578332469945], batch size: 70
+2022-12-12 13:05:54,569 INFO [train.py:421] (7/8) Epoch 7, batch 30800, loss[loss=2.512, over 1330.00 frames. , ppl: 12.328065991868458] tot_loss[loss=2.283, over 5520781.71 frames. , ppl: 9.810224294945304], batch size: 70
+2022-12-12 13:07:37,486 INFO [train.py:421] (7/8) Epoch 7, batch 31000, loss[loss=2.127, over 4900.00 frames. , ppl: 8.391495813427962] tot_loss[loss=2.283, over 5546069.97 frames. , ppl: 9.804518327442297], batch size: 70
+2022-12-12 13:07:37,487 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 13:07:38,249 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.277, over 211138.00 frames. , ppl: 9.74524606034524
+2022-12-12 13:09:21,955 INFO [train.py:421] (7/8) Epoch 7, batch 31200, loss[loss=2.306, over 1890.00 frames. , ppl: 10.035181380551291] tot_loss[loss=2.282, over 5585272.29 frames. , ppl: 9.799908009125927], batch size: 70
+2022-12-12 13:10:57,986 INFO [train.py:421] (7/8) Epoch 7, batch 31400, loss[loss=2.347, over 2800.00 frames. , ppl: 10.453604499287014] tot_loss[loss=2.282, over 5598057.92 frames. , ppl: 9.793946114023521], batch size: 70
+2022-12-12 13:12:37,921 INFO [train.py:421] (7/8) Epoch 7, batch 31600, loss[loss=2.279, over 2450.00 frames. , ppl: 9.76695844712407] tot_loss[loss=2.282, over 5601600.25 frames. , ppl: 9.792567583762885], batch size: 70
+2022-12-12 13:14:17,602 INFO [train.py:421] (7/8) Epoch 7, batch 31800, loss[loss=2.812, over 770.00 frames. , ppl: 16.646648978942896] tot_loss[loss=2.281, over 5627373.12 frames. , ppl: 9.783854381022039], batch size: 70
+2022-12-12 13:15:58,458 INFO [train.py:421] (7/8) Epoch 7, batch 32000, loss[loss=4.131, over 350.00 frames. , ppl: 62.260992147961645] tot_loss[loss=2.281, over 5611875.16 frames. , ppl: 9.788050349345138], batch size: 70
+2022-12-12 13:15:58,459 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 13:15:59,205 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.277, over 211138.00 frames. , ppl: 9.747510843049605
+2022-12-12 13:17:36,126 INFO [train.py:421] (7/8) Epoch 7, batch 32200, loss[loss=2.306, over 2730.00 frames. , ppl: 10.035797238761303] tot_loss[loss=2.282, over 5569142.17 frames. , ppl: 9.799436273621962], batch size: 70
+2022-12-12 13:19:19,500 INFO [train.py:421] (7/8) Epoch 7, batch 32400, loss[loss=2.352, over 1610.00 frames. , ppl: 10.506378439820807] tot_loss[loss=2.282, over 5547872.11 frames. , ppl: 9.800991891598247], batch size: 70
+2022-12-12 13:20:59,452 INFO [train.py:421] (7/8) Epoch 7, batch 32600, loss[loss=2.142, over 6790.00 frames. , ppl: 8.520145672620503] tot_loss[loss=2.283, over 5535585.65 frames. , ppl: 9.8011930770581], batch size: 70
+2022-12-12 13:22:38,745 INFO [train.py:421] (7/8) Epoch 7, batch 32800, loss[loss=2.629, over 910.00 frames. , ppl: 13.860158004261706] tot_loss[loss=2.284, over 5522318.42 frames. , ppl: 9.812092782341763], batch size: 70
+2022-12-12 13:24:19,353 INFO [train.py:421] (7/8) Epoch 7, batch 33000, loss[loss=2.157, over 7140.00 frames. , ppl: 8.648327370339986] tot_loss[loss=2.285, over 5495225.63 frames. , ppl: 9.823302346158874], batch size: 70
+2022-12-12 13:24:19,354 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 13:24:20,117 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.276, over 211138.00 frames. , ppl: 9.737587206525212
+2022-12-12 13:26:00,218 INFO [train.py:421] (7/8) Epoch 7, batch 33200, loss[loss=2.466, over 1120.00 frames. , ppl: 11.780205664513463] tot_loss[loss=2.285, over 5494241.88 frames. , ppl: 9.822468410381038], batch size: 70
+2022-12-12 13:27:39,638 INFO [train.py:421] (7/8) Epoch 7, batch 33400, loss[loss=2.182, over 2660.00 frames. , ppl: 8.861409080073969] tot_loss[loss=2.284, over 5500398.18 frames. , ppl: 9.815821332190884], batch size: 70
+2022-12-12 13:29:21,158 INFO [train.py:421] (7/8) Epoch 7, batch 33600, loss[loss=2.276, over 2520.00 frames. , ppl: 9.737802817059592] tot_loss[loss=2.285, over 5464355.16 frames. , ppl: 9.822639789828594], batch size: 70
+2022-12-12 13:31:03,138 INFO [train.py:421] (7/8) Epoch 7, batch 33800, loss[loss=2.619, over 700.00 frames. , ppl: 13.720660496410531] tot_loss[loss=2.287, over 5427603.26 frames. , ppl: 9.841520384868897], batch size: 70
+2022-12-12 13:32:47,145 INFO [train.py:421] (7/8) Epoch 7, batch 34000, loss[loss=2.493, over 1680.00 frames. , ppl: 12.095156916595453] tot_loss[loss=2.287, over 5431181.70 frames. , ppl: 9.843297685430004], batch size: 70
+2022-12-12 13:32:47,146 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 13:32:47,894 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.277, over 211138.00 frames. , ppl: 9.749546711482623
+2022-12-12 13:34:29,526 INFO [train.py:421] (7/8) Epoch 7, batch 34200, loss[loss=2.373, over 1960.00 frames. , ppl: 10.728274177996104] tot_loss[loss=2.287, over 5419457.55 frames. , ppl: 9.84409448168907], batch size: 70
+2022-12-12 13:36:09,731 INFO [train.py:421] (7/8) Epoch 7, batch 34400, loss[loss=2.204, over 6160.00 frames. , ppl: 9.058701971982247] tot_loss[loss=2.287, over 5433750.15 frames. , ppl: 9.841316528043492], batch size: 70
+2022-12-12 13:37:49,611 INFO [train.py:421] (7/8) Epoch 7, batch 34600, loss[loss=2.352, over 2100.00 frames. , ppl: 10.51117365098608] tot_loss[loss=2.287, over 5425742.27 frames. , ppl: 9.841323772367414], batch size: 70
+2022-12-12 13:39:31,008 INFO [train.py:421] (7/8) Epoch 7, batch 34800, loss[loss=2.343, over 2170.00 frames. , ppl: 10.41239451469506] tot_loss[loss=2.285, over 5459585.50 frames. , ppl: 9.826307350757615], batch size: 70
+2022-12-12 13:41:13,651 INFO [train.py:421] (7/8) Epoch 7, batch 35000, loss[loss=3.008, over 630.00 frames. , ppl: 20.238936011375625] tot_loss[loss=2.285, over 5449019.96 frames. , ppl: 9.829016354829504], batch size: 70
+2022-12-12 13:41:13,651 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 13:41:14,435 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.277, over 211138.00 frames. , ppl: 9.743404328984035
+2022-12-12 13:42:53,065 INFO [train.py:421] (7/8) Epoch 7, batch 35200, loss[loss=2.865, over 560.00 frames. , ppl: 17.553472851572963] tot_loss[loss=2.286, over 5436348.19 frames. , ppl: 9.831264530453117], batch size: 70
+2022-12-12 13:44:36,902 INFO [train.py:421] (7/8) Epoch 7, batch 35400, loss[loss=2.378, over 3080.00 frames. , ppl: 10.784416454807397] tot_loss[loss=2.285, over 5437031.59 frames. , ppl: 9.827339376327597], batch size: 70
+2022-12-12 13:46:17,870 INFO [train.py:421] (7/8) Epoch 7, batch 35600, loss[loss=2.226, over 4620.00 frames. , ppl: 9.259931943658879] tot_loss[loss=2.285, over 5444865.50 frames. , ppl: 9.825983545287183], batch size: 70
+2022-12-12 13:48:00,244 INFO [train.py:421] (7/8) Epoch 7, batch 35800, loss[loss=2.557, over 910.00 frames. , ppl: 12.893703431363338] tot_loss[loss=2.284, over 5445907.59 frames. , ppl: 9.817995337684406], batch size: 70
+2022-12-12 13:49:39,569 INFO [train.py:421] (7/8) Epoch 7, batch 36000, loss[loss=2.521, over 980.00 frames. , ppl: 12.44473674111114] tot_loss[loss=2.285, over 5435593.44 frames. , ppl: 9.824069683661243], batch size: 70
+2022-12-12 13:49:39,569 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 13:49:40,314 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.275, over 211138.00 frames. , ppl: 9.730916571608322
+2022-12-12 13:51:17,496 INFO [train.py:421] (7/8) Epoch 7, batch 36200, loss[loss=2.222, over 3500.00 frames. , ppl: 9.222259911004908] tot_loss[loss=2.284, over 5444301.77 frames. , ppl: 9.81736150090612], batch size: 70
+2022-12-12 13:52:55,998 INFO [train.py:421] (7/8) Epoch 7, batch 36400, loss[loss=2.487, over 1050.00 frames. , ppl: 12.0305423754496] tot_loss[loss=2.283, over 5486458.26 frames. , ppl: 9.80749443173478], batch size: 70
+2022-12-12 13:54:35,737 INFO [train.py:421] (7/8) Epoch 7, batch 36600, loss[loss=2.606, over 840.00 frames. , ppl: 13.547779772898657] tot_loss[loss=2.282, over 5503152.94 frames. , ppl: 9.800552898347824], batch size: 70
+2022-12-12 13:56:13,084 INFO [train.py:421] (7/8) Epoch 7, batch 36800, loss[loss=2.164, over 2450.00 frames. , ppl: 8.707289556103577] tot_loss[loss=2.283, over 5475827.59 frames. , ppl: 9.8071603622891], batch size: 70
+2022-12-12 13:57:51,836 INFO [train.py:421] (7/8) Epoch 7, batch 37000, loss[loss=2.46, over 1120.00 frames. , ppl: 11.705770412824238] tot_loss[loss=2.283, over 5457325.03 frames. , ppl: 9.810670786225002], batch size: 70
+2022-12-12 13:57:51,836 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 13:57:52,594 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.275, over 211138.00 frames. , ppl: 9.730660210790171
+2022-12-12 13:59:32,626 INFO [train.py:421] (7/8) Epoch 7, batch 37200, loss[loss=2.297, over 3990.00 frames. , ppl: 9.942073797850668] tot_loss[loss=2.283, over 5467184.16 frames. , ppl: 9.803863427864865], batch size: 70
+2022-12-12 14:01:13,836 INFO [train.py:421] (7/8) Epoch 7, batch 37400, loss[loss=2.446, over 1330.00 frames. , ppl: 11.539032656781234] tot_loss[loss=2.284, over 5460134.30 frames. , ppl: 9.812818675995794], batch size: 70
+2022-12-12 14:03:00,132 INFO [train.py:421] (7/8) Epoch 7, batch 37600, loss[loss=2.176, over 5600.00 frames. , ppl: 8.810222871301566] tot_loss[loss=2.285, over 5436667.82 frames. , ppl: 9.820795898338659], batch size: 70
+2022-12-12 14:04:41,204 INFO [train.py:421] (7/8) Epoch 7, batch 37800, loss[loss=2.333, over 2870.00 frames. , ppl: 10.311557913231685] tot_loss[loss=2.284, over 5453129.37 frames. , ppl: 9.817380053078265], batch size: 70
+2022-12-12 14:06:18,527 INFO [train.py:421] (7/8) Epoch 7, batch 38000, loss[loss=2.415, over 1960.00 frames. , ppl: 11.190174013676224] tot_loss[loss=2.285, over 5430753.93 frames. , ppl: 9.828119986660791], batch size: 70
+2022-12-12 14:06:18,528 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 14:06:19,290 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.276, over 211138.00 frames. , ppl: 9.735293029761026
+2022-12-12 14:08:00,992 INFO [train.py:421] (7/8) Epoch 7, batch 38200, loss[loss=2.186, over 10150.00 frames. , ppl: 8.900843877158813] tot_loss[loss=2.285, over 5461004.57 frames. , ppl: 9.824614807228837], batch size: 70
+2022-12-12 14:09:41,638 INFO [train.py:421] (7/8) Epoch 7, batch 38400, loss[loss=2.282, over 2310.00 frames. , ppl: 9.791446010101076] tot_loss[loss=2.285, over 5442973.83 frames. , ppl: 9.82930539324544], batch size: 70
+2022-12-12 14:11:19,545 INFO [train.py:421] (7/8) Epoch 7, batch 38600, loss[loss=2.289, over 3710.00 frames. , ppl: 9.869886926210102] tot_loss[loss=2.286, over 5434402.55 frames. , ppl: 9.832864080153373], batch size: 70
+2022-12-12 14:12:58,080 INFO [train.py:421] (7/8) Epoch 7, batch 38800, loss[loss=2.447, over 1750.00 frames. , ppl: 11.557612468376579] tot_loss[loss=2.286, over 5431878.88 frames. , ppl: 9.832141750509777], batch size: 70
+2022-12-12 14:14:39,697 INFO [train.py:421] (7/8) Epoch 7, batch 39000, loss[loss=2.423, over 1540.00 frames. , ppl: 11.276895281443283] tot_loss[loss=2.286, over 5430752.90 frames. , ppl: 9.833716667083621], batch size: 70
+2022-12-12 14:14:39,698 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 14:14:40,458 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.276, over 211138.00 frames. , ppl: 9.733431570068024
+2022-12-12 14:16:18,498 INFO [train.py:421] (7/8) Epoch 7, batch 39200, loss[loss=2.456, over 1540.00 frames. , ppl: 11.661213290295905] tot_loss[loss=2.287, over 5400018.21 frames. , ppl: 9.844203899222947], batch size: 70
+2022-12-12 14:17:57,354 INFO [train.py:421] (7/8) Epoch 7, batch 39400, loss[loss=2.288, over 2100.00 frames. , ppl: 9.86005659525695] tot_loss[loss=2.287, over 5404134.52 frames. , ppl: 9.845106838848709], batch size: 70
+2022-12-12 14:19:39,322 INFO [train.py:421] (7/8) Epoch 7, batch 39600, loss[loss=2.287, over 1960.00 frames. , ppl: 9.848750035614229] tot_loss[loss=2.285, over 5467669.49 frames. , ppl: 9.824740901814248], batch size: 70
+2022-12-12 14:21:22,520 INFO [train.py:421] (7/8) Epoch 7, batch 39800, loss[loss=2.343, over 2660.00 frames. , ppl: 10.408486116819228] tot_loss[loss=2.284, over 5518398.97 frames. , ppl: 9.811203256085681], batch size: 70
+2022-12-12 14:23:03,816 INFO [train.py:421] (7/8) Epoch 7, batch 40000, loss[loss=2.559, over 1330.00 frames. , ppl: 12.920655648967351] tot_loss[loss=2.283, over 5516322.95 frames. , ppl: 9.808932358989846], batch size: 70
+2022-12-12 14:23:03,816 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 14:23:04,577 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.276, over 211138.00 frames. , ppl: 9.732923044306935
+2022-12-12 14:24:40,638 INFO [train.py:421] (7/8) Epoch 7, batch 40200, loss[loss=2.196, over 4060.00 frames. , ppl: 8.984921118173723] tot_loss[loss=2.283, over 5529174.27 frames. , ppl: 9.804862521175224], batch size: 70
+2022-12-12 14:26:24,171 INFO [train.py:421] (7/8) Epoch 7, batch 40400, loss[loss=2.179, over 5110.00 frames. , ppl: 8.839963370205203] tot_loss[loss=2.282, over 5545766.52 frames. , ppl: 9.796324060047866], batch size: 70
+2022-12-12 14:28:05,250 INFO [train.py:421] (7/8) Epoch 7, batch 40600, loss[loss=2.199, over 8330.00 frames. , ppl: 9.018119815951321] tot_loss[loss=2.283, over 5532854.58 frames. , ppl: 9.80415091749698], batch size: 70
+2022-12-12 14:29:48,189 INFO [train.py:421] (7/8) Epoch 7, batch 40800, loss[loss=2.145, over 5810.00 frames. , ppl: 8.545157718741356] tot_loss[loss=2.283, over 5538106.14 frames. , ppl: 9.804763115745217], batch size: 70
+2022-12-12 14:31:28,832 INFO [train.py:421] (7/8) Epoch 7, batch 41000, loss[loss=2.331, over 2170.00 frames. , ppl: 10.284968020215869] tot_loss[loss=2.284, over 5470301.45 frames. , ppl: 9.819653551350553], batch size: 70
+2022-12-12 14:31:28,832 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 14:31:29,592 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.275, over 211138.00 frames. , ppl: 9.72567260083667
+2022-12-12 14:33:15,370 INFO [train.py:421] (7/8) Epoch 7, batch 41200, loss[loss=2.741, over 770.00 frames. , ppl: 15.499606016573319] tot_loss[loss=2.284, over 5491420.41 frames. , ppl: 9.8206286385354], batch size: 70
+2022-12-12 14:34:58,546 INFO [train.py:421] (7/8) Epoch 7, batch 41400, loss[loss=2.519, over 1120.00 frames. , ppl: 12.412050565792033] tot_loss[loss=2.284, over 5509452.21 frames. , ppl: 9.815066787343829], batch size: 70
+2022-12-12 14:36:43,117 INFO [train.py:421] (7/8) Epoch 7, batch 41600, loss[loss=2.356, over 1330.00 frames. , ppl: 10.553889951591323] tot_loss[loss=2.284, over 5538913.97 frames. , ppl: 9.812616389500551], batch size: 70
+2022-12-12 14:38:19,986 INFO [train.py:421] (7/8) Epoch 7, batch 41800, loss[loss=2.563, over 1190.00 frames. , ppl: 12.972878082702131] tot_loss[loss=2.285, over 5469033.21 frames. , ppl: 9.823705390199589], batch size: 70
+2022-12-12 14:39:58,261 INFO [train.py:421] (7/8) Epoch 7, batch 42000, loss[loss=2.277, over 3360.00 frames. , ppl: 9.745322810301632] tot_loss[loss=2.285, over 5454555.93 frames. , ppl: 9.829145467070736], batch size: 70
+2022-12-12 14:39:58,261 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 14:39:59,022 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.275, over 211138.00 frames. , ppl: 9.732604689011115
+2022-12-12 14:41:41,115 INFO [train.py:421] (7/8) Epoch 7, batch 42200, loss[loss=2.531, over 1050.00 frames. , ppl: 12.564240515280511] tot_loss[loss=2.284, over 5493745.56 frames. , ppl: 9.813720859758782], batch size: 70
+2022-12-12 14:43:22,131 INFO [train.py:421] (7/8) Epoch 7, batch 42400, loss[loss=2.296, over 2590.00 frames. , ppl: 9.935364232887599] tot_loss[loss=2.283, over 5523506.25 frames. , ppl: 9.804056733329704], batch size: 70
+2022-12-12 14:45:04,984 INFO [train.py:421] (7/8) Epoch 7, batch 42600, loss[loss=2.176, over 4340.00 frames. , ppl: 8.809976359950236] tot_loss[loss=2.282, over 5564520.37 frames. , ppl: 9.799787370746555], batch size: 70
+2022-12-12 14:46:47,206 INFO [train.py:421] (7/8) Epoch 7, batch 42800, loss[loss=2.362, over 1680.00 frames. , ppl: 10.6163510904467] tot_loss[loss=2.282, over 5584202.70 frames. , ppl: 9.795887709980311], batch size: 70
+2022-12-12 14:48:26,759 INFO [train.py:421] (7/8) Epoch 7, batch 43000, loss[loss=2.21, over 5250.00 frames. , ppl: 9.111642700408954] tot_loss[loss=2.282, over 5570342.30 frames. , ppl: 9.799279606841237], batch size: 70
+2022-12-12 14:48:26,759 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 14:48:27,491 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.274, over 211138.00 frames. , ppl: 9.722768179823841
+2022-12-12 14:50:02,822 INFO [train.py:421] (7/8) Epoch 7, batch 43200, loss[loss=2.499, over 1260.00 frames. , ppl: 12.17502288013903] tot_loss[loss=2.283, over 5551879.14 frames. , ppl: 9.80158270242887], batch size: 70
+2022-12-12 14:51:39,688 INFO [train.py:421] (7/8) Epoch 7, batch 43400, loss[loss=2.153, over 8890.00 frames. , ppl: 8.609883550001534] tot_loss[loss=2.283, over 5550348.14 frames. , ppl: 9.801302974286289], batch size: 70
+2022-12-12 14:53:19,380 INFO [train.py:421] (7/8) Epoch 7, batch 43600, loss[loss=2.405, over 2100.00 frames. , ppl: 11.08101163457437] tot_loss[loss=2.281, over 5558239.91 frames. , ppl: 9.791132221561632], batch size: 70
+2022-12-12 14:54:58,930 INFO [train.py:421] (7/8) Epoch 7, batch 43800, loss[loss=2.365, over 1750.00 frames. , ppl: 10.643854686734723] tot_loss[loss=2.28, over 5591854.73 frames. , ppl: 9.775196083662935], batch size: 70
+2022-12-12 14:56:40,138 INFO [train.py:421] (7/8) Epoch 7, batch 44000, loss[loss=2.209, over 5180.00 frames. , ppl: 9.102793162059765] tot_loss[loss=2.279, over 5613774.73 frames. , ppl: 9.768903048596371], batch size: 70
+2022-12-12 14:56:40,139 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 14:56:40,926 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.276, over 211138.00 frames. , ppl: 9.738247314799137
+2022-12-12 14:58:24,199 INFO [train.py:421] (7/8) Epoch 7, batch 44200, loss[loss=2.169, over 4480.00 frames. , ppl: 8.74739832173827] tot_loss[loss=2.281, over 5564401.31 frames. , ppl: 9.786165274772635], batch size: 70
+2022-12-12 15:00:05,405 INFO [train.py:421] (7/8) Epoch 7, batch 44400, loss[loss=2.229, over 3010.00 frames. , ppl: 9.290670452379622] tot_loss[loss=2.281, over 5580539.73 frames. , ppl: 9.782171029507577], batch size: 70
+2022-12-12 15:01:46,542 INFO [train.py:421] (7/8) Epoch 7, batch 44600, loss[loss=2.458, over 1260.00 frames. , ppl: 11.685899411735239] tot_loss[loss=2.281, over 5558672.96 frames. , ppl: 9.787478976215048], batch size: 70
+2022-12-12 15:03:25,946 INFO [train.py:421] (7/8) Epoch 7, batch 44800, loss[loss=2.214, over 2940.00 frames. , ppl: 9.154022248184303] tot_loss[loss=2.28, over 5616019.81 frames. , ppl: 9.773474993512574], batch size: 70
+2022-12-12 15:05:07,367 INFO [train.py:421] (7/8) Epoch 7, batch 45000, loss[loss=2.222, over 3780.00 frames. , ppl: 9.22302851234215] tot_loss[loss=2.28, over 5584170.02 frames. , ppl: 9.781117528355663], batch size: 70
+2022-12-12 15:05:07,367 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 15:05:08,112 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.276, over 211138.00 frames. , ppl: 9.739091972737263
+2022-12-12 15:06:49,452 INFO [train.py:421] (7/8) Epoch 7, batch 45200, loss[loss=2.229, over 5950.00 frames. , ppl: 9.291975044448881] tot_loss[loss=2.28, over 5591621.80 frames. , ppl: 9.776085089323182], batch size: 70
+2022-12-12 15:08:26,850 INFO [train.py:421] (7/8) Epoch 7, batch 45400, loss[loss=2.164, over 7560.00 frames. , ppl: 8.70809482763333] tot_loss[loss=2.28, over 5590913.15 frames. , ppl: 9.773503830992844], batch size: 70
+2022-12-12 15:10:04,373 INFO [train.py:421] (7/8) Epoch 7, batch 45600, loss[loss=2.318, over 2100.00 frames. , ppl: 10.159796679191796] tot_loss[loss=2.282, over 5519021.18 frames. , ppl: 9.80009524870838], batch size: 70
+2022-12-12 15:11:43,470 INFO [train.py:421] (7/8) Epoch 7, batch 45800, loss[loss=2.551, over 840.00 frames. , ppl: 12.82326876971897] tot_loss[loss=2.283, over 5516564.75 frames. , ppl: 9.805941273195241], batch size: 70
+2022-12-12 15:13:23,822 INFO [train.py:421] (7/8) Epoch 7, batch 46000, loss[loss=2.414, over 2940.00 frames. , ppl: 11.17545704781667] tot_loss[loss=2.283, over 5509512.47 frames. , ppl: 9.809803269772171], batch size: 70
+2022-12-12 15:13:23,823 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 15:13:24,592 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.275, over 211138.00 frames. , ppl: 9.725171677432357
+2022-12-12 15:15:04,842 INFO [train.py:421] (7/8) Epoch 7, batch 46200, loss[loss=2.332, over 1190.00 frames. , ppl: 10.296308861977886] tot_loss[loss=2.284, over 5467078.64 frames. , ppl: 9.816732922919671], batch size: 70
+2022-12-12 15:16:41,452 INFO [train.py:421] (7/8) Epoch 7, batch 46400, loss[loss=2.419, over 3080.00 frames. , ppl: 11.234638739503124] tot_loss[loss=2.285, over 5479972.14 frames. , ppl: 9.825212563305776], batch size: 70
+2022-12-12 15:18:27,480 INFO [train.py:421] (7/8) Epoch 7, batch 46600, loss[loss=2.723, over 700.00 frames. , ppl: 15.223857496984351] tot_loss[loss=2.283, over 5544557.89 frames. , ppl: 9.807423230359625], batch size: 70
+2022-12-12 15:20:06,524 INFO [train.py:421] (7/8) Epoch 7, batch 46800, loss[loss=2.424, over 1050.00 frames. , ppl: 11.29356055496868] tot_loss[loss=2.283, over 5556226.05 frames. , ppl: 9.803166900246248], batch size: 70
+2022-12-12 15:21:46,495 INFO [train.py:421] (7/8) Epoch 7, batch 47000, loss[loss=2.375, over 2380.00 frames. , ppl: 10.751275665188297] tot_loss[loss=2.283, over 5544968.80 frames. , ppl: 9.805307651608993], batch size: 70
+2022-12-12 15:21:46,495 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 15:21:47,256 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.277, over 211138.00 frames. , ppl: 9.746437530099742
+2022-12-12 15:23:25,417 INFO [train.py:421] (7/8) Epoch 7, batch 47200, loss[loss=2.567, over 980.00 frames. , ppl: 13.030056785724403] tot_loss[loss=2.284, over 5538107.51 frames. , ppl: 9.812390965680006], batch size: 70
+2022-12-12 15:25:07,548 INFO [train.py:421] (7/8) Epoch 7, batch 47400, loss[loss=2.687, over 910.00 frames. , ppl: 14.681333053075253] tot_loss[loss=2.284, over 5534212.61 frames. , ppl: 9.813811230948335], batch size: 70
+2022-12-12 15:26:45,396 INFO [train.py:421] (7/8) Epoch 7, batch 47600, loss[loss=2.296, over 2660.00 frames. , ppl: 9.937025883759684] tot_loss[loss=2.283, over 5553759.64 frames. , ppl: 9.809504272560774], batch size: 70
+2022-12-12 15:28:25,600 INFO [train.py:421] (7/8) Epoch 7, batch 47800, loss[loss=2.378, over 2730.00 frames. , ppl: 10.787722351493032] tot_loss[loss=2.284, over 5541213.65 frames. , ppl: 9.811947244168087], batch size: 70
+2022-12-12 15:30:08,468 INFO [train.py:421] (7/8) Epoch 7, batch 48000, loss[loss=2.372, over 1330.00 frames. , ppl: 10.716166406822774] tot_loss[loss=2.282, over 5574743.96 frames. , ppl: 9.7984215170488], batch size: 70
+2022-12-12 15:30:08,468 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 15:30:09,214 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.275, over 211138.00 frames. , ppl: 9.730277122379839
+2022-12-12 15:31:50,594 INFO [train.py:421] (7/8) Epoch 7, batch 48200, loss[loss=2.516, over 770.00 frames. , ppl: 12.375150550487408] tot_loss[loss=2.282, over 5581547.50 frames. , ppl: 9.796445843971727], batch size: 70
+2022-12-12 15:33:31,841 INFO [train.py:421] (7/8) Epoch 7, batch 48400, loss[loss=2.271, over 4340.00 frames. , ppl: 9.686527253564721] tot_loss[loss=2.284, over 5533948.42 frames. , ppl: 9.811286410681394], batch size: 70
+2022-12-12 15:35:15,577 INFO [train.py:421] (7/8) Epoch 7, batch 48600, loss[loss=2.205, over 4760.00 frames. , ppl: 9.066753463901962] tot_loss[loss=2.282, over 5559709.21 frames. , ppl: 9.798689763573819], batch size: 70
+2022-12-12 15:37:00,085 INFO [train.py:421] (7/8) Epoch 7, batch 48800, loss[loss=2.428, over 1470.00 frames. , ppl: 11.333016254642002] tot_loss[loss=2.283, over 5535097.67 frames. , ppl: 9.806034497154371], batch size: 70
+2022-12-12 15:38:39,938 INFO [train.py:421] (7/8) Epoch 7, batch 49000, loss[loss=2.502, over 1260.00 frames. , ppl: 12.20987590814641] tot_loss[loss=2.283, over 5511508.37 frames. , ppl: 9.810206619221274], batch size: 70
+2022-12-12 15:38:39,939 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 15:38:40,684 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.274, over 211138.00 frames. , ppl: 9.71475889319782
+2022-12-12 15:40:19,142 INFO [train.py:421] (7/8) Epoch 7, batch 49200, loss[loss=2.185, over 7560.00 frames. , ppl: 8.893894202982713] tot_loss[loss=2.283, over 5516716.35 frames. , ppl: 9.802331049046284], batch size: 70
+2022-12-12 15:42:00,517 INFO [train.py:421] (7/8) Epoch 7, batch 49400, loss[loss=2.25, over 3150.00 frames. , ppl: 9.48872419365086] tot_loss[loss=2.284, over 5506852.51 frames. , ppl: 9.811666516453608], batch size: 70
+2022-12-12 15:43:37,682 INFO [train.py:421] (7/8) Epoch 7, batch 49600, loss[loss=2.389, over 2170.00 frames. , ppl: 10.904999569399273] tot_loss[loss=2.285, over 5444606.18 frames. , ppl: 9.827769345431006], batch size: 70
+2022-12-12 15:45:24,853 INFO [train.py:421] (7/8) Epoch 7, batch 49800, loss[loss=2.318, over 1470.00 frames. , ppl: 10.150712622089264] tot_loss[loss=2.286, over 5432555.20 frames. , ppl: 9.837063046562372], batch size: 70
+2022-12-12 15:47:06,650 INFO [train.py:421] (7/8) Epoch 7, batch 50000, loss[loss=2.35, over 1960.00 frames. , ppl: 10.482748930920337] tot_loss[loss=2.286, over 5422698.75 frames. , ppl: 9.838516880420615], batch size: 70
+2022-12-12 15:47:06,650 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 15:47:07,406 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.274, over 211138.00 frames. , ppl: 9.714458385768214
+2022-12-12 15:48:44,240 INFO [train.py:421] (7/8) Epoch 7, batch 50200, loss[loss=2.275, over 3290.00 frames. , ppl: 9.732644132579086] tot_loss[loss=2.286, over 5439935.47 frames. , ppl: 9.830666062823918], batch size: 70
+2022-12-12 15:50:22,994 INFO [train.py:421] (7/8) Epoch 7, batch 50400, loss[loss=2.148, over 9800.00 frames. , ppl: 8.56484825049307] tot_loss[loss=2.286, over 5440628.21 frames. , ppl: 9.831696316577005], batch size: 70
+2022-12-12 15:52:02,485 INFO [train.py:421] (7/8) Epoch 7, batch 50600, loss[loss=2.278, over 4340.00 frames. , ppl: 9.757918381195216] tot_loss[loss=2.285, over 5458216.24 frames. , ppl: 9.823092309574507], batch size: 70
+2022-12-12 15:53:41,811 INFO [train.py:421] (7/8) Epoch 7, batch 50800, loss[loss=2.545, over 910.00 frames. , ppl: 12.745118158097462] tot_loss[loss=2.286, over 5425799.74 frames. , ppl: 9.834266087878568], batch size: 70
+2022-12-12 15:55:22,388 INFO [train.py:421] (7/8) Epoch 7, batch 51000, loss[loss=2.763, over 630.00 frames. , ppl: 15.85166383000694] tot_loss[loss=2.285, over 5446815.77 frames. , ppl: 9.82968427299033], batch size: 70
+2022-12-12 15:55:22,388 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 15:55:23,149 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.273, over 211138.00 frames. , ppl: 9.712544846014454
+2022-12-12 15:57:03,534 INFO [train.py:421] (7/8) Epoch 7, batch 51200, loss[loss=2.192, over 4340.00 frames. , ppl: 8.954877005518743] tot_loss[loss=2.285, over 5470536.15 frames. , ppl: 9.821877296554819], batch size: 70
+2022-12-12 15:58:38,232 INFO [train.py:421] (7/8) Epoch 7, batch 51400, loss[loss=2.251, over 7000.00 frames. , ppl: 9.499999188349939] tot_loss[loss=2.285, over 5465722.30 frames. , ppl: 9.82879388082195], batch size: 70
+2022-12-12 16:00:15,722 INFO [train.py:421] (7/8) Epoch 7, batch 51600, loss[loss=2.815, over 700.00 frames. , ppl: 16.70048996202455] tot_loss[loss=2.284, over 5501481.25 frames. , ppl: 9.815013820291224], batch size: 70
+2022-12-12 16:01:57,242 INFO [train.py:421] (7/8) Epoch 7, batch 51800, loss[loss=2.357, over 1890.00 frames. , ppl: 10.55579759318664] tot_loss[loss=2.284, over 5511662.62 frames. , ppl: 9.81394075706658], batch size: 70
+2022-12-12 16:03:36,215 INFO [train.py:421] (7/8) Epoch 7, batch 52000, loss[loss=2.823, over 700.00 frames. , ppl: 16.820904343873725] tot_loss[loss=2.282, over 5555934.64 frames. , ppl: 9.799174953990109], batch size: 70
+2022-12-12 16:03:36,216 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 16:03:36,974 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.274, over 211138.00 frames. , ppl: 9.714971698339436
+2022-12-12 16:05:14,235 INFO [train.py:421] (7/8) Epoch 7, batch 52200, loss[loss=2.526, over 1120.00 frames. , ppl: 12.500908284250444] tot_loss[loss=2.282, over 5559827.80 frames. , ppl: 9.799903658180549], batch size: 70
+2022-12-12 16:06:54,094 INFO [train.py:421] (7/8) Epoch 7, batch 52400, loss[loss=2.3, over 1960.00 frames. , ppl: 9.97675455348854] tot_loss[loss=2.283, over 5519662.15 frames. , ppl: 9.809867158396877], batch size: 70
+2022-12-12 16:08:37,696 INFO [train.py:421] (7/8) Epoch 7, batch 52600, loss[loss=2.553, over 1050.00 frames. , ppl: 12.840576706037083] tot_loss[loss=2.281, over 5594007.05 frames. , ppl: 9.789408187288853], batch size: 70
+2022-12-12 16:10:20,644 INFO [train.py:421] (7/8) Epoch 7, batch 52800, loss[loss=2.196, over 9520.00 frames. , ppl: 8.987312958185056] tot_loss[loss=2.281, over 5572781.30 frames. , ppl: 9.788259531536788], batch size: 70
+2022-12-12 16:12:02,791 INFO [train.py:421] (7/8) Epoch 7, batch 53000, loss[loss=2.469, over 1610.00 frames. , ppl: 11.815462181220905] tot_loss[loss=2.281, over 5575684.68 frames. , ppl: 9.784562821115037], batch size: 70
+2022-12-12 16:12:02,792 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 16:12:03,557 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.273, over 211138.00 frames. , ppl: 9.710289624670212
+2022-12-12 16:13:44,882 INFO [train.py:421] (7/8) Epoch 7, batch 53200, loss[loss=2.504, over 980.00 frames. , ppl: 12.232502885122608] tot_loss[loss=2.28, over 5586563.87 frames. , ppl: 9.77891023358606], batch size: 70
+2022-12-12 16:15:28,466 INFO [train.py:421] (7/8) Epoch 7, batch 53400, loss[loss=2.194, over 6020.00 frames. , ppl: 8.973669997505334] tot_loss[loss=2.281, over 5579580.83 frames. , ppl: 9.784999476382819], batch size: 70
+2022-12-12 16:17:11,417 INFO [train.py:421] (7/8) Epoch 7, batch 53600, loss[loss=2.198, over 7490.00 frames. , ppl: 9.010511734040556] tot_loss[loss=2.28, over 5612122.39 frames. , ppl: 9.7803237772119], batch size: 70
+2022-12-12 16:18:49,869 INFO [train.py:421] (7/8) Epoch 7, batch 53800, loss[loss=2.737, over 700.00 frames. , ppl: 15.442368843840738] tot_loss[loss=2.281, over 5575195.77 frames. , ppl: 9.788853522312019], batch size: 70
+2022-12-12 16:20:30,747 INFO [train.py:421] (7/8) Epoch 7, batch 54000, loss[loss=2.16, over 10360.00 frames. , ppl: 8.666821081062707] tot_loss[loss=2.28, over 5608664.03 frames. , ppl: 9.778087144408659], batch size: 70
+2022-12-12 16:20:30,748 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 16:20:31,473 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.275, over 211138.00 frames. , ppl: 9.730233917866439
+2022-12-12 16:22:14,274 INFO [train.py:421] (7/8) Epoch 7, batch 54200, loss[loss=2.4, over 1750.00 frames. , ppl: 11.023342467697656] tot_loss[loss=2.281, over 5553367.06 frames. , ppl: 9.791269705506883], batch size: 70
+2022-12-12 16:23:57,501 INFO [train.py:421] (7/8) Epoch 7, batch 54400, loss[loss=2.167, over 6790.00 frames. , ppl: 8.729408709525094] tot_loss[loss=2.281, over 5569984.28 frames. , ppl: 9.785793224157189], batch size: 70
+2022-12-12 16:25:40,604 INFO [train.py:421] (7/8) Epoch 7, batch 54600, loss[loss=2.248, over 2590.00 frames. , ppl: 9.466224541322873] tot_loss[loss=2.282, over 5536234.60 frames. , ppl: 9.791913160642645], batch size: 70
+2022-12-12 16:27:23,733 INFO [train.py:421] (7/8) Epoch 7, batch 54800, loss[loss=2.593, over 910.00 frames. , ppl: 13.364572575782528] tot_loss[loss=2.281, over 5566895.30 frames. , ppl: 9.783400095634136], batch size: 70
+2022-12-12 16:29:03,501 INFO [train.py:421] (7/8) Epoch 7, batch 55000, loss[loss=2.282, over 2380.00 frames. , ppl: 9.795878154249985] tot_loss[loss=2.282, over 5536678.33 frames. , ppl: 9.792386618588235], batch size: 70
+2022-12-12 16:29:03,502 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 16:29:04,267 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.276, over 211138.00 frames. , ppl: 9.738142098037239
+2022-12-12 16:30:45,227 INFO [train.py:421] (7/8) Epoch 7, batch 55200, loss[loss=2.839, over 700.00 frames. , ppl: 17.10675992370272] tot_loss[loss=2.282, over 5536308.91 frames. , ppl: 9.794010615981582], batch size: 70
+2022-12-12 16:32:27,222 INFO [train.py:421] (7/8) Epoch 7, batch 55400, loss[loss=2.324, over 1470.00 frames. , ppl: 10.21842546723187] tot_loss[loss=2.282, over 5530595.03 frames. , ppl: 9.793654267430293], batch size: 70
+2022-12-12 16:34:09,959 INFO [train.py:421] (7/8) Epoch 7, batch 55600, loss[loss=2.261, over 3850.00 frames. , ppl: 9.592199179033429] tot_loss[loss=2.282, over 5500151.74 frames. , ppl: 9.799168500094316], batch size: 70
+2022-12-12 16:35:52,325 INFO [train.py:421] (7/8) Epoch 7, batch 55800, loss[loss=2.327, over 2030.00 frames. , ppl: 10.246542962767423] tot_loss[loss=2.283, over 5487965.64 frames. , ppl: 9.806981870472429], batch size: 70
+2022-12-12 16:37:34,623 INFO [train.py:421] (7/8) Epoch 7, batch 56000, loss[loss=2.28, over 3220.00 frames. , ppl: 9.77316031408291] tot_loss[loss=2.283, over 5469993.11 frames. , ppl: 9.80840689234184], batch size: 70
+2022-12-12 16:37:34,623 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 16:37:35,393 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.275, over 211138.00 frames. , ppl: 9.72342008782373
+2022-12-12 16:39:17,250 INFO [train.py:421] (7/8) Epoch 7, batch 56200, loss[loss=2.618, over 840.00 frames. , ppl: 13.714589981666737] tot_loss[loss=2.282, over 5531193.23 frames. , ppl: 9.798079072044581], batch size: 70
+2022-12-12 16:40:58,440 INFO [train.py:421] (7/8) Epoch 7, batch 56400, loss[loss=2.334, over 3290.00 frames. , ppl: 10.323462602733054] tot_loss[loss=2.282, over 5527828.39 frames. , ppl: 9.79453956919253], batch size: 70
+2022-12-12 16:42:37,536 INFO [train.py:421] (7/8) Epoch 7, batch 56600, loss[loss=2.15, over 5250.00 frames. , ppl: 8.586794041027126] tot_loss[loss=2.283, over 5488404.36 frames. , ppl: 9.806302823221197], batch size: 70
+2022-12-12 16:44:14,637 INFO [train.py:421] (7/8) Epoch 7, batch 56800, loss[loss=2.46, over 1540.00 frames. , ppl: 11.703697492318552] tot_loss[loss=2.283, over 5480274.18 frames. , ppl: 9.805781018988439], batch size: 70
+2022-12-12 16:45:52,808 INFO [train.py:421] (7/8) Epoch 7, batch 57000, loss[loss=2.289, over 3220.00 frames. , ppl: 9.861167277779924] tot_loss[loss=2.283, over 5479667.25 frames. , ppl: 9.80967252263692], batch size: 70
+2022-12-12 16:45:52,809 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 16:45:53,554 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.274, over 211138.00 frames. , ppl: 9.720317799677936
+2022-12-12 16:47:33,744 INFO [train.py:421] (7/8) Epoch 7, batch 57200, loss[loss=2.303, over 1960.00 frames. , ppl: 10.0046004428304] tot_loss[loss=2.283, over 5517129.67 frames. , ppl: 9.802002592899886], batch size: 70
+2022-12-12 16:49:17,345 INFO [train.py:421] (7/8) Epoch 7, batch 57400, loss[loss=2.493, over 1960.00 frames. , ppl: 12.093592673670786] tot_loss[loss=2.281, over 5557178.80 frames. , ppl: 9.790868449739042], batch size: 70
+2022-12-12 16:50:58,689 INFO [train.py:421] (7/8) Epoch 7, batch 57600, loss[loss=2.291, over 1820.00 frames. , ppl: 9.884749243661071] tot_loss[loss=2.282, over 5549531.26 frames. , ppl: 9.791853703985693], batch size: 70
+2022-12-12 16:52:38,236 INFO [train.py:421] (7/8) Epoch 7, batch 57800, loss[loss=2.173, over 4480.00 frames. , ppl: 8.787976937517696] tot_loss[loss=2.281, over 5599346.32 frames. , ppl: 9.784851658024186], batch size: 70
+2022-12-12 16:54:19,004 INFO [train.py:421] (7/8) Epoch 7, batch 58000, loss[loss=2.243, over 2800.00 frames. , ppl: 9.423097800780653] tot_loss[loss=2.281, over 5598514.90 frames. , ppl: 9.786234927963987], batch size: 70
+2022-12-12 16:54:19,004 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 16:54:19,765 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.274, over 211138.00 frames. , ppl: 9.714061557664111
+2022-12-12 16:56:00,042 INFO [train.py:421] (7/8) Epoch 7, batch 58200, loss[loss=2.31, over 2450.00 frames. , ppl: 10.076970889210623] tot_loss[loss=2.282, over 5574261.29 frames. , ppl: 9.79641508516333], batch size: 70
+2022-12-12 16:57:41,618 INFO [train.py:421] (7/8) Epoch 7, batch 58400, loss[loss=2.163, over 4200.00 frames. , ppl: 8.701054654177641] tot_loss[loss=2.282, over 5567709.01 frames. , ppl: 9.794894695759275], batch size: 70
+2022-12-12 16:59:24,619 INFO [train.py:421] (7/8) Epoch 7, batch 58600, loss[loss=2.365, over 2030.00 frames. , ppl: 10.646892329951397] tot_loss[loss=2.282, over 5575810.71 frames. , ppl: 9.792458213740593], batch size: 70
+2022-12-12 17:01:06,540 INFO [train.py:421] (7/8) Epoch 7, batch 58800, loss[loss=2.217, over 3220.00 frames. , ppl: 9.182903004452884] tot_loss[loss=2.281, over 5597083.49 frames. , ppl: 9.784971195720926], batch size: 70
+2022-12-12 17:02:51,796 INFO [train.py:421] (7/8) Epoch 7, batch 59000, loss[loss=2.142, over 7070.00 frames. , ppl: 8.516365805576873] tot_loss[loss=2.28, over 5605816.04 frames. , ppl: 9.77931296785419], batch size: 70
+2022-12-12 17:02:51,796 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 17:02:52,548 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.274, over 211138.00 frames. , ppl: 9.716621096251133
+2022-12-12 17:04:37,258 INFO [train.py:421] (7/8) Epoch 7, batch 59200, loss[loss=2.39, over 910.00 frames. , ppl: 10.917203104568422] tot_loss[loss=2.28, over 5588231.51 frames. , ppl: 9.78110851628183], batch size: 70
+2022-12-12 17:06:15,593 INFO [train.py:421] (7/8) Epoch 7, batch 59400, loss[loss=2.316, over 1820.00 frames. , ppl: 10.138624361702366] tot_loss[loss=2.281, over 5551555.41 frames. , ppl: 9.789313394879686], batch size: 70
+2022-12-12 17:07:59,303 INFO [train.py:421] (7/8) Epoch 7, batch 59600, loss[loss=2.232, over 5600.00 frames. , ppl: 9.317246569789907] tot_loss[loss=2.282, over 5525202.73 frames. , ppl: 9.799022432635041], batch size: 70
+2022-12-12 17:09:44,680 INFO [train.py:421] (7/8) Epoch 7, batch 59800, loss[loss=2.238, over 2450.00 frames. , ppl: 9.374716977500704] tot_loss[loss=2.283, over 5515779.71 frames. , ppl: 9.807691986138126], batch size: 70
+2022-12-12 17:11:28,832 INFO [train.py:421] (7/8) Epoch 7, batch 60000, loss[loss=2.333, over 1330.00 frames. , ppl: 10.313846188784703] tot_loss[loss=2.281, over 5568951.74 frames. , ppl: 9.791034163383054], batch size: 70
+2022-12-12 17:11:28,833 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 17:11:29,585 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.274, over 211138.00 frames. , ppl: 9.71337577339601
+2022-12-12 17:13:08,943 INFO [train.py:421] (7/8) Epoch 7, batch 60200, loss[loss=2.23, over 2940.00 frames. , ppl: 9.296571230831663] tot_loss[loss=2.282, over 5543119.21 frames. , ppl: 9.798936872841502], batch size: 70
+2022-12-12 17:14:49,932 INFO [train.py:421] (7/8) Epoch 7, batch 60400, loss[loss=2.811, over 630.00 frames. , ppl: 16.621490384648865] tot_loss[loss=2.283, over 5507726.30 frames. , ppl: 9.81073068889321], batch size: 70
+2022-12-12 17:16:33,758 INFO [train.py:421] (7/8) Epoch 7, batch 60600, loss[loss=2.413, over 2100.00 frames. , ppl: 11.168539119536845] tot_loss[loss=2.284, over 5486268.12 frames. , ppl: 9.81593051832517], batch size: 70
+2022-12-12 17:18:13,221 INFO [train.py:421] (7/8) Epoch 7, batch 60800, loss[loss=2.429, over 2590.00 frames. , ppl: 11.351929668577306] tot_loss[loss=2.284, over 5492796.09 frames. , ppl: 9.814679904044446], batch size: 70
+2022-12-12 17:19:56,254 INFO [train.py:421] (7/8) Epoch 7, batch 61000, loss[loss=3.244, over 490.00 frames. , ppl: 25.63451236114179] tot_loss[loss=2.283, over 5553358.59 frames. , ppl: 9.805291887178427], batch size: 70
+2022-12-12 17:19:56,255 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 17:19:57,004 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.273, over 211138.00 frames. , ppl: 9.70608961125915
+2022-12-12 17:21:39,570 INFO [train.py:421] (7/8) Epoch 7, batch 61200, loss[loss=2.52, over 1610.00 frames. , ppl: 12.424292436402828] tot_loss[loss=2.283, over 5534532.70 frames. , ppl: 9.806882992224542], batch size: 70
+2022-12-12 17:23:24,470 INFO [train.py:421] (7/8) Epoch 7, batch 61400, loss[loss=2.202, over 3500.00 frames. , ppl: 9.045812082752098] tot_loss[loss=2.284, over 5528438.50 frames. , ppl: 9.812936594651141], batch size: 70
+2022-12-12 17:25:04,987 INFO [train.py:421] (7/8) Epoch 7, batch 61600, loss[loss=3.235, over 490.00 frames. , ppl: 25.406809771135897] tot_loss[loss=2.284, over 5521854.30 frames. , ppl: 9.811249631908437], batch size: 70
+2022-12-12 17:26:46,420 INFO [train.py:421] (7/8) Epoch 7, batch 61800, loss[loss=2.554, over 770.00 frames. , ppl: 12.857098919489891] tot_loss[loss=2.283, over 5547151.31 frames. , ppl: 9.802387786839022], batch size: 70
+2022-12-12 17:28:30,622 INFO [train.py:421] (7/8) Epoch 7, batch 62000, loss[loss=3.504, over 420.00 frames. , ppl: 33.254977339998746] tot_loss[loss=2.283, over 5570395.57 frames. , ppl: 9.801964865735126], batch size: 70
+2022-12-12 17:28:30,623 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 17:28:31,386 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.274, over 211138.00 frames. , ppl: 9.71544765103413
+2022-12-12 17:30:11,236 INFO [train.py:421] (7/8) Epoch 7, batch 62200, loss[loss=2.205, over 4270.00 frames. , ppl: 9.070935314287901] tot_loss[loss=2.282, over 5553914.58 frames. , ppl: 9.800142053657693], batch size: 70
+2022-12-12 17:31:56,803 INFO [train.py:421] (7/8) Epoch 7, batch 62400, loss[loss=2.519, over 910.00 frames. , ppl: 12.41482246288164] tot_loss[loss=2.281, over 5572374.09 frames. , ppl: 9.79091016203502], batch size: 70
+2022-12-12 17:33:40,865 INFO [train.py:421] (7/8) Epoch 7, batch 62600, loss[loss=2.328, over 3710.00 frames. , ppl: 10.255148916969013] tot_loss[loss=2.281, over 5576095.00 frames. , ppl: 9.790197162335135], batch size: 70
+2022-12-12 17:35:24,972 INFO [train.py:421] (7/8) Epoch 7, batch 62800, loss[loss=2.273, over 3500.00 frames. , ppl: 9.708085780456999] tot_loss[loss=2.281, over 5589020.54 frames. , ppl: 9.787786448072806], batch size: 70
+2022-12-12 17:37:08,814 INFO [train.py:421] (7/8) Epoch 7, batch 63000, loss[loss=2.37, over 1050.00 frames. , ppl: 10.693085142834688] tot_loss[loss=2.282, over 5556040.32 frames. , ppl: 9.79279557332337], batch size: 70
+2022-12-12 17:37:08,814 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 17:37:09,562 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.274, over 211138.00 frames. , ppl: 9.722217042257858
+2022-12-12 17:38:51,300 INFO [train.py:421] (7/8) Epoch 7, batch 63200, loss[loss=2.475, over 840.00 frames. , ppl: 11.879134651719305] tot_loss[loss=2.281, over 5581390.73 frames. , ppl: 9.790992962910696], batch size: 70
+2022-12-12 17:40:30,766 INFO [train.py:421] (7/8) Epoch 7, batch 63400, loss[loss=2.565, over 980.00 frames. , ppl: 13.004049150083262] tot_loss[loss=2.282, over 5563927.96 frames. , ppl: 9.793595834799925], batch size: 70
+2022-12-12 17:42:12,623 INFO [train.py:421] (7/8) Epoch 7, batch 63600, loss[loss=2.286, over 2310.00 frames. , ppl: 9.839108584985427] tot_loss[loss=2.282, over 5555017.18 frames. , ppl: 9.79729280048316], batch size: 70
+2022-12-12 17:43:53,040 INFO [train.py:421] (7/8) Epoch 7, batch 63800, loss[loss=2.679, over 910.00 frames. , ppl: 14.567762046808129] tot_loss[loss=2.283, over 5531255.10 frames. , ppl: 9.801922653365862], batch size: 70
+2022-12-12 17:45:29,446 INFO [train.py:421] (7/8) Epoch 7, batch 64000, loss[loss=2.384, over 1610.00 frames. , ppl: 10.852292682002334] tot_loss[loss=2.283, over 5512406.33 frames. , ppl: 9.803612670796824], batch size: 70
+2022-12-12 17:45:29,447 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 17:45:30,209 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.274, over 211138.00 frames. , ppl: 9.717427922051451
+2022-12-12 17:47:12,553 INFO [train.py:421] (7/8) Epoch 7, batch 64200, loss[loss=2.351, over 1330.00 frames. , ppl: 10.491114548331325] tot_loss[loss=2.282, over 5566459.47 frames. , ppl: 9.797161026951105], batch size: 70
+2022-12-12 17:48:56,534 INFO [train.py:421] (7/8) Epoch 7, batch 64400, loss[loss=2.222, over 4620.00 frames. , ppl: 9.226256644975667] tot_loss[loss=2.281, over 5589000.96 frames. , ppl: 9.786827743715767], batch size: 70
+2022-12-12 17:50:37,260 INFO [train.py:421] (7/8) Epoch 7, batch 64600, loss[loss=2.171, over 3990.00 frames. , ppl: 8.765283156643076] tot_loss[loss=2.28, over 5578456.74 frames. , ppl: 9.780032331721891], batch size: 70
+2022-12-12 17:52:15,807 INFO [train.py:421] (7/8) Epoch 7, batch 64800, loss[loss=2.557, over 1400.00 frames. , ppl: 12.902102867989774] tot_loss[loss=2.279, over 5625990.48 frames. , ppl: 9.766149747513458], batch size: 70
+2022-12-12 17:53:56,981 INFO [train.py:421] (7/8) Epoch 7, batch 65000, loss[loss=2.299, over 4200.00 frames. , ppl: 9.962060693884347] tot_loss[loss=2.279, over 5625849.78 frames. , ppl: 9.763076148636298], batch size: 70
+2022-12-12 17:53:56,981 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 17:53:57,744 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.275, over 211138.00 frames. , ppl: 9.728521733447238
+2022-12-12 17:55:38,100 INFO [train.py:421] (7/8) Epoch 7, batch 65200, loss[loss=2.177, over 6230.00 frames. , ppl: 8.817292609831718] tot_loss[loss=2.28, over 5582166.83 frames. , ppl: 9.772259323984521], batch size: 70
+2022-12-12 17:57:16,315 INFO [train.py:421] (7/8) Epoch 7, batch 65400, loss[loss=2.473, over 1330.00 frames. , ppl: 11.859970963706584] tot_loss[loss=2.28, over 5530049.44 frames. , ppl: 9.781422749206142], batch size: 70
+2022-12-12 17:58:55,636 INFO [train.py:421] (7/8) Epoch 7, batch 65600, loss[loss=2.308, over 2870.00 frames. , ppl: 10.051745673986927] tot_loss[loss=2.28, over 5529661.84 frames. , ppl: 9.778687527807225], batch size: 70
+2022-12-12 18:00:40,205 INFO [train.py:421] (7/8) Epoch 7, batch 65800, loss[loss=2.249, over 3430.00 frames. , ppl: 9.475382858999456] tot_loss[loss=2.281, over 5533970.34 frames. , ppl: 9.783751350732642], batch size: 70
+2022-12-12 18:02:18,997 INFO [train.py:421] (7/8) Epoch 7, batch 66000, loss[loss=2.261, over 5110.00 frames. , ppl: 9.591938209087198] tot_loss[loss=2.281, over 5513971.65 frames. , ppl: 9.789137838032156], batch size: 70
+2022-12-12 18:02:18,997 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 18:02:19,737 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.275, over 211138.00 frames. , ppl: 9.725315618297568
+2022-12-12 18:04:01,117 INFO [train.py:421] (7/8) Epoch 7, batch 66200, loss[loss=2.377, over 2030.00 frames. , ppl: 10.774576465251494] tot_loss[loss=2.282, over 5505587.32 frames. , ppl: 9.795790909325177], batch size: 70
+2022-12-12 18:05:46,670 INFO [train.py:421] (7/8) Epoch 7, batch 66400, loss[loss=2.381, over 3500.00 frames. , ppl: 10.818124643751911] tot_loss[loss=2.281, over 5530310.99 frames. , ppl: 9.788791683131825], batch size: 70
+2022-12-12 18:07:29,663 INFO [train.py:421] (7/8) Epoch 7, batch 66600, loss[loss=2.316, over 2380.00 frames. , ppl: 10.135134331893454] tot_loss[loss=2.28, over 5566209.02 frames. , ppl: 9.778163938580294], batch size: 70
+2022-12-12 18:09:07,067 INFO [train.py:421] (7/8) Epoch 7, batch 66800, loss[loss=2.245, over 3920.00 frames. , ppl: 9.436978754102219] tot_loss[loss=2.281, over 5516746.94 frames. , ppl: 9.79121333181552], batch size: 70
+2022-12-12 18:10:47,177 INFO [train.py:421] (7/8) Epoch 7, batch 67000, loss[loss=2.404, over 1190.00 frames. , ppl: 11.064880553273873] tot_loss[loss=2.281, over 5515739.15 frames. , ppl: 9.78617725142091], batch size: 70
+2022-12-12 18:10:47,178 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 18:10:47,941 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.274, over 211138.00 frames. , ppl: 9.71459066540528
+2022-12-12 18:12:28,623 INFO [train.py:421] (7/8) Epoch 7, batch 67200, loss[loss=2.321, over 2100.00 frames. , ppl: 10.187999137616682] tot_loss[loss=2.28, over 5547998.44 frames. , ppl: 9.779715606696506], batch size: 70
+2022-12-12 18:14:14,270 INFO [train.py:421] (7/8) Epoch 7, batch 67400, loss[loss=2.284, over 2520.00 frames. , ppl: 9.812612443830142] tot_loss[loss=2.281, over 5536054.66 frames. , ppl: 9.784825952124411], batch size: 70
+2022-12-12 18:15:54,856 INFO [train.py:421] (7/8) Epoch 7, batch 67600, loss[loss=2.173, over 5530.00 frames. , ppl: 8.780534000734438] tot_loss[loss=2.282, over 5498637.22 frames. , ppl: 9.795827142190811], batch size: 70
+2022-12-12 18:17:35,755 INFO [train.py:421] (7/8) Epoch 7, batch 67800, loss[loss=2.205, over 2730.00 frames. , ppl: 9.06853340799805] tot_loss[loss=2.283, over 5497571.87 frames. , ppl: 9.804752268596548], batch size: 70
+2022-12-12 18:19:18,256 INFO [train.py:421] (7/8) Epoch 7, batch 68000, loss[loss=2.627, over 980.00 frames. , ppl: 13.834874365592086] tot_loss[loss=2.282, over 5499918.97 frames. , ppl: 9.799380157893328], batch size: 70
+2022-12-12 18:19:18,257 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 18:19:19,022 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.273, over 211138.00 frames. , ppl: 9.710605812793908
+2022-12-12 18:20:59,032 INFO [train.py:421] (7/8) Epoch 7, batch 68200, loss[loss=2.46, over 1120.00 frames. , ppl: 11.70527795368138] tot_loss[loss=2.282, over 5496937.14 frames. , ppl: 9.796641008182194], batch size: 70
+2022-12-12 18:22:38,125 INFO [train.py:421] (7/8) Epoch 7, batch 68400, loss[loss=2.54, over 840.00 frames. , ppl: 12.675899294411455] tot_loss[loss=2.282, over 5488140.12 frames. , ppl: 9.800414159525218], batch size: 70
+2022-12-12 18:24:19,222 INFO [train.py:421] (7/8) Epoch 7, batch 68600, loss[loss=2.693, over 700.00 frames. , ppl: 14.772901728646373] tot_loss[loss=2.281, over 5528805.49 frames. , ppl: 9.78621089206883], batch size: 70
+2022-12-12 18:25:59,200 INFO [train.py:421] (7/8) Epoch 7, batch 68800, loss[loss=2.146, over 5040.00 frames. , ppl: 8.549583334747641] tot_loss[loss=2.28, over 5561885.36 frames. , ppl: 9.777573490944986], batch size: 70
+2022-12-12 18:27:41,646 INFO [train.py:421] (7/8) Epoch 7, batch 69000, loss[loss=2.344, over 3500.00 frames. , ppl: 10.427842085896774] tot_loss[loss=2.279, over 5621235.91 frames. , ppl: 9.764224833892705], batch size: 70
+2022-12-12 18:27:41,646 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 18:27:42,411 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.273, over 211138.00 frames. , ppl: 9.71098525213279
+2022-12-12 18:29:24,644 INFO [train.py:421] (7/8) Epoch 7, batch 69200, loss[loss=2.338, over 2310.00 frames. , ppl: 10.365054399423158] tot_loss[loss=2.279, over 5592631.43 frames. , ppl: 9.770407569655086], batch size: 70
+2022-12-12 18:31:04,119 INFO [train.py:421] (7/8) Epoch 7, batch 69400, loss[loss=2.245, over 4130.00 frames. , ppl: 9.436236833303143] tot_loss[loss=2.281, over 5552906.34 frames. , ppl: 9.781607228950183], batch size: 70
+2022-12-12 18:32:46,706 INFO [train.py:421] (7/8) Epoch 7, batch 69600, loss[loss=2.229, over 4480.00 frames. , ppl: 9.290428937995834] tot_loss[loss=2.279, over 5595200.87 frames. , ppl: 9.767824599076357], batch size: 70
+2022-12-12 18:34:31,066 INFO [train.py:421] (7/8) Epoch 7, batch 69800, loss[loss=2.126, over 4620.00 frames. , ppl: 8.384256936265302] tot_loss[loss=2.28, over 5582961.44 frames. , ppl: 9.776685909489169], batch size: 70
+2022-12-12 18:36:12,717 INFO [train.py:421] (7/8) Epoch 7, batch 70000, loss[loss=2.591, over 980.00 frames. , ppl: 13.338497414160537] tot_loss[loss=2.281, over 5543777.61 frames. , ppl: 9.787656240801923], batch size: 70
+2022-12-12 18:36:12,717 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 18:36:13,480 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.273, over 211138.00 frames. , ppl: 9.71248878254001
+2022-12-12 18:37:52,860 INFO [train.py:421] (7/8) Epoch 7, batch 70200, loss[loss=2.234, over 5390.00 frames. , ppl: 9.339442333063923] tot_loss[loss=2.28, over 5562826.71 frames. , ppl: 9.781269906304404], batch size: 70
+2022-12-12 18:39:34,549 INFO [train.py:421] (7/8) Epoch 7, batch 70400, loss[loss=2.189, over 3710.00 frames. , ppl: 8.929629881198062] tot_loss[loss=2.281, over 5549379.12 frames. , ppl: 9.785904649097953], batch size: 70
+2022-12-12 18:41:16,485 INFO [train.py:421] (7/8) Epoch 7, batch 70600, loss[loss=2.282, over 3780.00 frames. , ppl: 9.798483177582188] tot_loss[loss=2.28, over 5578357.37 frames. , ppl: 9.779514693597276], batch size: 70
+2022-12-12 18:43:01,219 INFO [train.py:421] (7/8) Epoch 7, batch 70800, loss[loss=2.173, over 12250.00 frames. , ppl: 8.781993604405667] tot_loss[loss=2.28, over 5615683.37 frames. , ppl: 9.77191251222049], batch size: 70
+2022-12-12 18:44:42,650 INFO [train.py:421] (7/8) Epoch 7, batch 71000, loss[loss=2.341, over 1120.00 frames. , ppl: 10.387951036141171] tot_loss[loss=2.279, over 5638983.16 frames. , ppl: 9.766987164467436], batch size: 70
+2022-12-12 18:44:42,650 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 18:44:43,417 INFO [train.py:452] (7/8) Epoch 7, validation: loss=2.273, over 211138.00 frames. , ppl: 9.707774858509012
+2022-12-12 18:46:25,671 INFO [train.py:421] (7/8) Epoch 7, batch 71200, loss[loss=2.314, over 1750.00 frames. , ppl: 10.110299811112984] tot_loss[loss=2.28, over 5578594.51 frames. , ppl: 9.778728379662041], batch size: 70
+2022-12-12 18:48:08,712 INFO [train.py:421] (7/8) Epoch 7, batch 71400, loss[loss=3.67, over 420.00 frames. , ppl: 39.25355097384062] tot_loss[loss=2.28, over 5610254.62 frames. , ppl: 9.77196710234447], batch size: 70
+2022-12-12 18:49:50,984 INFO [train.py:421] (7/8) Epoch 7, batch 71600, loss[loss=2.255, over 7280.00 frames. , ppl: 9.538622607442957] tot_loss[loss=2.28, over 5599899.67 frames. , ppl: 9.773488569053988], batch size: 70
+2022-12-12 18:51:32,658 INFO [train.py:421] (7/8) Epoch 7, batch 71800, loss[loss=3.255, over 490.00 frames. , ppl: 25.912497122346696] tot_loss[loss=2.28, over 5578173.98 frames. , ppl: 9.773636296064833], batch size: 70
+2022-12-12 18:52:47,989 INFO [train.py:421] (7/8) Epoch 8, batch 0, loss[loss=2.247, over 3430.00 frames. , ppl: 9.456859310616846] tot_loss[loss=2.247, over 3430.00 frames. , ppl: 9.456859310616846], batch size: 70
+2022-12-12 18:54:30,707 INFO [train.py:421] (7/8) Epoch 8, batch 200, loss[loss=2.234, over 5530.00 frames. , ppl: 9.339711855916716] tot_loss[loss=2.281, over 518820.49 frames. , ppl: 9.789678317423471], batch size: 70
+2022-12-12 18:56:11,882 INFO [train.py:421] (7/8) Epoch 8, batch 400, loss[loss=2.311, over 1400.00 frames. , ppl: 10.084663448793883] tot_loss[loss=2.287, over 941504.01 frames. , ppl: 9.844950635136374], batch size: 70
+2022-12-12 18:57:54,088 INFO [train.py:421] (7/8) Epoch 8, batch 600, loss[loss=2.195, over 2520.00 frames. , ppl: 8.979560503028404] tot_loss[loss=2.285, over 1326084.06 frames. , ppl: 9.821522404947492], batch size: 70
+2022-12-12 18:59:34,601 INFO [train.py:421] (7/8) Epoch 8, batch 800, loss[loss=2.194, over 3360.00 frames. , ppl: 8.974780527211365] tot_loss[loss=2.28, over 1737939.31 frames. , ppl: 9.773786132746306], batch size: 70
+2022-12-12 19:01:16,012 INFO [train.py:421] (7/8) Epoch 8, batch 1000, loss[loss=2.435, over 1750.00 frames. , ppl: 11.416608674582058] tot_loss[loss=2.279, over 2107449.71 frames. , ppl: 9.762503397770741], batch size: 70
+2022-12-12 19:01:16,013 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 19:01:16,794 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.274, over 211138.00 frames. , ppl: 9.714002609944576
+2022-12-12 19:02:59,996 INFO [train.py:421] (7/8) Epoch 8, batch 1200, loss[loss=2.257, over 3290.00 frames. , ppl: 9.55187424031566] tot_loss[loss=2.276, over 2446681.18 frames. , ppl: 9.742236836301625], batch size: 70
+2022-12-12 19:04:36,354 INFO [train.py:421] (7/8) Epoch 8, batch 1400, loss[loss=2.224, over 6440.00 frames. , ppl: 9.248269983677838] tot_loss[loss=2.277, over 2717616.57 frames. , ppl: 9.749268978861965], batch size: 70
+2022-12-12 19:06:17,642 INFO [train.py:421] (7/8) Epoch 8, batch 1600, loss[loss=2.159, over 4340.00 frames. , ppl: 8.658921266702604] tot_loss[loss=2.277, over 2990806.31 frames. , ppl: 9.748850391197875], batch size: 70
+2022-12-12 19:08:00,659 INFO [train.py:421] (7/8) Epoch 8, batch 1800, loss[loss=2.303, over 1890.00 frames. , ppl: 10.001043345714432] tot_loss[loss=2.277, over 3218138.61 frames. , ppl: 9.749101540504725], batch size: 70
+2022-12-12 19:09:38,930 INFO [train.py:421] (7/8) Epoch 8, batch 2000, loss[loss=2.393, over 1540.00 frames. , ppl: 10.943866306759348] tot_loss[loss=2.276, over 3439712.50 frames. , ppl: 9.74233893943904], batch size: 70
+2022-12-12 19:09:38,931 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 19:09:39,713 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.273, over 211138.00 frames. , ppl: 9.70567014079976
+2022-12-12 19:11:23,706 INFO [train.py:421] (7/8) Epoch 8, batch 2200, loss[loss=2.37, over 1330.00 frames. , ppl: 10.697903633442868] tot_loss[loss=2.277, over 3645745.09 frames. , ppl: 9.748768313540115], batch size: 70
+2022-12-12 19:13:03,010 INFO [train.py:421] (7/8) Epoch 8, batch 2400, loss[loss=2.4, over 1610.00 frames. , ppl: 11.027911243861656] tot_loss[loss=2.279, over 3765563.00 frames. , ppl: 9.763604498419959], batch size: 70
+2022-12-12 19:14:41,152 INFO [train.py:421] (7/8) Epoch 8, batch 2600, loss[loss=2.949, over 630.00 frames. , ppl: 19.088384641686716] tot_loss[loss=2.28, over 3899794.55 frames. , ppl: 9.773748889635291], batch size: 70
+2022-12-12 19:16:22,765 INFO [train.py:421] (7/8) Epoch 8, batch 2800, loss[loss=2.267, over 2800.00 frames. , ppl: 9.654212243093193] tot_loss[loss=2.279, over 4051106.60 frames. , ppl: 9.765561209350425], batch size: 70
+2022-12-12 19:18:01,848 INFO [train.py:421] (7/8) Epoch 8, batch 3000, loss[loss=2.472, over 1190.00 frames. , ppl: 11.843769668813394] tot_loss[loss=2.277, over 4179085.06 frames. , ppl: 9.748339480658966], batch size: 70
+2022-12-12 19:18:01,849 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 19:18:02,632 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.276, over 211138.00 frames. , ppl: 9.739168370327212
+2022-12-12 19:19:44,666 INFO [train.py:421] (7/8) Epoch 8, batch 3200, loss[loss=2.173, over 4130.00 frames. , ppl: 8.784465905265156] tot_loss[loss=2.275, over 4334311.37 frames. , ppl: 9.727564170039043], batch size: 70
+2022-12-12 19:21:28,590 INFO [train.py:421] (7/8) Epoch 8, batch 3400, loss[loss=2.183, over 4480.00 frames. , ppl: 8.876088222598096] tot_loss[loss=2.276, over 4427757.06 frames. , ppl: 9.734224100748184], batch size: 70
+2022-12-12 19:23:11,797 INFO [train.py:421] (7/8) Epoch 8, batch 3600, loss[loss=2.211, over 5460.00 frames. , ppl: 9.126461613586244] tot_loss[loss=2.274, over 4587534.25 frames. , ppl: 9.714790439292244], batch size: 70
+2022-12-12 19:24:50,896 INFO [train.py:421] (7/8) Epoch 8, batch 3800, loss[loss=2.554, over 980.00 frames. , ppl: 12.8556984111538] tot_loss[loss=2.274, over 4649503.22 frames. , ppl: 9.722201072525108], batch size: 70
+2022-12-12 19:26:35,933 INFO [train.py:421] (7/8) Epoch 8, batch 4000, loss[loss=2.272, over 4900.00 frames. , ppl: 9.696422618864036] tot_loss[loss=2.272, over 4800277.10 frames. , ppl: 9.70050965032669], batch size: 70
+2022-12-12 19:26:35,934 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 19:26:36,699 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.273, over 211138.00 frames. , ppl: 9.709655842207155
+2022-12-12 19:28:16,986 INFO [train.py:421] (7/8) Epoch 8, batch 4200, loss[loss=2.37, over 1680.00 frames. , ppl: 10.697032253075959] tot_loss[loss=2.272, over 4862729.67 frames. , ppl: 9.703367676037622], batch size: 70
+2022-12-12 19:29:59,680 INFO [train.py:421] (7/8) Epoch 8, batch 4400, loss[loss=2.211, over 5670.00 frames. , ppl: 9.125209334267733] tot_loss[loss=2.272, over 4895517.99 frames. , ppl: 9.701585489635065], batch size: 70
+2022-12-12 19:31:43,086 INFO [train.py:421] (7/8) Epoch 8, batch 4600, loss[loss=2.306, over 1540.00 frames. , ppl: 10.03261039316974] tot_loss[loss=2.274, over 4919459.60 frames. , ppl: 9.716619419998779], batch size: 70
+2022-12-12 19:33:23,009 INFO [train.py:421] (7/8) Epoch 8, batch 4800, loss[loss=2.546, over 980.00 frames. , ppl: 12.757599490231792] tot_loss[loss=2.274, over 4988724.25 frames. , ppl: 9.71773104245279], batch size: 70
+2022-12-12 19:35:03,747 INFO [train.py:421] (7/8) Epoch 8, batch 5000, loss[loss=2.431, over 1120.00 frames. , ppl: 11.372385507374467] tot_loss[loss=2.275, over 5021404.49 frames. , ppl: 9.724388837350467], batch size: 70
+2022-12-12 19:35:03,747 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 19:35:04,513 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.275, over 211138.00 frames. , ppl: 9.73047586561236
+2022-12-12 19:36:45,802 INFO [train.py:421] (7/8) Epoch 8, batch 5200, loss[loss=2.31, over 3080.00 frames. , ppl: 10.076034049207731] tot_loss[loss=2.275, over 5069995.12 frames. , ppl: 9.724878948153757], batch size: 70
+2022-12-12 19:38:27,931 INFO [train.py:421] (7/8) Epoch 8, batch 5400, loss[loss=2.194, over 4130.00 frames. , ppl: 8.968189286013489] tot_loss[loss=2.275, over 5112261.76 frames. , ppl: 9.724641509912669], batch size: 70
+2022-12-12 19:40:10,533 INFO [train.py:421] (7/8) Epoch 8, batch 5600, loss[loss=2.224, over 5320.00 frames. , ppl: 9.24509208062563] tot_loss[loss=2.275, over 5147133.61 frames. , ppl: 9.726585970564422], batch size: 70
+2022-12-12 19:41:53,333 INFO [train.py:421] (7/8) Epoch 8, batch 5800, loss[loss=2.476, over 980.00 frames. , ppl: 11.892545681239413] tot_loss[loss=2.277, over 5127967.60 frames. , ppl: 9.743864458581932], batch size: 70
+2022-12-12 19:43:36,515 INFO [train.py:421] (7/8) Epoch 8, batch 6000, loss[loss=2.155, over 7630.00 frames. , ppl: 8.629474306919496] tot_loss[loss=2.275, over 5185254.37 frames. , ppl: 9.732325649343014], batch size: 70
+2022-12-12 19:43:36,516 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 19:43:37,249 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.273, over 211138.00 frames. , ppl: 9.709706140891356
+2022-12-12 19:45:21,824 INFO [train.py:421] (7/8) Epoch 8, batch 6200, loss[loss=2.321, over 2590.00 frames. , ppl: 10.186066842161624] tot_loss[loss=2.276, over 5205837.25 frames. , ppl: 9.739600248360436], batch size: 70
+2022-12-12 19:47:05,536 INFO [train.py:421] (7/8) Epoch 8, batch 6400, loss[loss=2.489, over 980.00 frames. , ppl: 12.050031009533805] tot_loss[loss=2.276, over 5238585.69 frames. , ppl: 9.74168378284821], batch size: 70
+2022-12-12 19:48:44,525 INFO [train.py:421] (7/8) Epoch 8, batch 6600, loss[loss=2.394, over 2240.00 frames. , ppl: 10.960123692226814] tot_loss[loss=2.277, over 5275621.87 frames. , ppl: 9.744228618506243], batch size: 70
+2022-12-12 19:50:24,283 INFO [train.py:421] (7/8) Epoch 8, batch 6800, loss[loss=2.296, over 2380.00 frames. , ppl: 9.932468006981797] tot_loss[loss=2.276, over 5305517.55 frames. , ppl: 9.738055096571946], batch size: 70
+2022-12-12 19:52:06,684 INFO [train.py:421] (7/8) Epoch 8, batch 7000, loss[loss=2.348, over 1260.00 frames. , ppl: 10.460808092873023] tot_loss[loss=2.275, over 5356687.98 frames. , ppl: 9.732547186754784], batch size: 70
+2022-12-12 19:52:06,685 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 19:52:07,437 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.272, over 211138.00 frames. , ppl: 9.703498378235237
+2022-12-12 19:53:49,615 INFO [train.py:421] (7/8) Epoch 8, batch 7200, loss[loss=2.18, over 4060.00 frames. , ppl: 8.843418845469197] tot_loss[loss=2.275, over 5404391.76 frames. , ppl: 9.723815798316917], batch size: 70
+2022-12-12 19:55:33,511 INFO [train.py:421] (7/8) Epoch 8, batch 7400, loss[loss=2.272, over 2170.00 frames. , ppl: 9.70329421635089] tot_loss[loss=2.275, over 5404248.97 frames. , ppl: 9.731678139426725], batch size: 70
+2022-12-12 19:57:12,619 INFO [train.py:421] (7/8) Epoch 8, batch 7600, loss[loss=2.232, over 1680.00 frames. , ppl: 9.316768891171016] tot_loss[loss=2.274, over 5429288.54 frames. , ppl: 9.720746528531581], batch size: 70
+2022-12-12 19:58:56,551 INFO [train.py:421] (7/8) Epoch 8, batch 7800, loss[loss=2.154, over 5740.00 frames. , ppl: 8.62332214858999] tot_loss[loss=2.274, over 5470227.58 frames. , ppl: 9.718257104614977], batch size: 70
+2022-12-12 20:00:37,106 INFO [train.py:421] (7/8) Epoch 8, batch 8000, loss[loss=3.025, over 630.00 frames. , ppl: 20.596941813652833] tot_loss[loss=2.273, over 5525940.28 frames. , ppl: 9.708953321415411], batch size: 70
+2022-12-12 20:00:37,107 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 20:00:37,873 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.274, over 211138.00 frames. , ppl: 9.715900618606277
+2022-12-12 20:02:19,423 INFO [train.py:421] (7/8) Epoch 8, batch 8200, loss[loss=2.114, over 8470.00 frames. , ppl: 8.285044085887478] tot_loss[loss=2.275, over 5474137.89 frames. , ppl: 9.72704677314844], batch size: 70
+2022-12-12 20:04:00,791 INFO [train.py:421] (7/8) Epoch 8, batch 8400, loss[loss=2.116, over 4760.00 frames. , ppl: 8.29513936777851] tot_loss[loss=2.276, over 5436254.49 frames. , ppl: 9.737037941613673], batch size: 70
+2022-12-12 20:05:43,616 INFO [train.py:421] (7/8) Epoch 8, batch 8600, loss[loss=2.398, over 1260.00 frames. , ppl: 10.996497438542235] tot_loss[loss=2.277, over 5418148.01 frames. , ppl: 9.745973280666625], batch size: 70
+2022-12-12 20:07:22,555 INFO [train.py:421] (7/8) Epoch 8, batch 8800, loss[loss=2.296, over 4830.00 frames. , ppl: 9.935124048457798] tot_loss[loss=2.278, over 5396491.00 frames. , ppl: 9.752469108075955], batch size: 70
+2022-12-12 20:09:06,512 INFO [train.py:421] (7/8) Epoch 8, batch 9000, loss[loss=2.521, over 1680.00 frames. , ppl: 12.44112028358441] tot_loss[loss=2.277, over 5419091.59 frames. , ppl: 9.747679918481879], batch size: 70
+2022-12-12 20:09:06,512 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 20:09:07,262 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.273, over 211138.00 frames. , ppl: 9.70899192399486
+2022-12-12 20:10:45,555 INFO [train.py:421] (7/8) Epoch 8, batch 9200, loss[loss=2.121, over 4060.00 frames. , ppl: 8.336161202126318] tot_loss[loss=2.277, over 5428813.25 frames. , ppl: 9.744821477734083], batch size: 70
+2022-12-12 20:12:29,544 INFO [train.py:421] (7/8) Epoch 8, batch 9400, loss[loss=2.414, over 1190.00 frames. , ppl: 11.175542426116372] tot_loss[loss=2.276, over 5474848.27 frames. , ppl: 9.736452670326317], batch size: 70
+2022-12-12 20:14:10,750 INFO [train.py:421] (7/8) Epoch 8, batch 9600, loss[loss=2.294, over 3220.00 frames. , ppl: 9.91078474234419] tot_loss[loss=2.277, over 5462375.32 frames. , ppl: 9.745162667737294], batch size: 70
+2022-12-12 20:15:50,131 INFO [train.py:421] (7/8) Epoch 8, batch 9800, loss[loss=2.279, over 2380.00 frames. , ppl: 9.76488709036961] tot_loss[loss=2.277, over 5452176.80 frames. , ppl: 9.746893326505264], batch size: 70
+2022-12-12 20:17:30,564 INFO [train.py:421] (7/8) Epoch 8, batch 10000, loss[loss=2.199, over 3780.00 frames. , ppl: 9.013050943466084] tot_loss[loss=2.277, over 5467651.24 frames. , ppl: 9.751107817080824], batch size: 70
+2022-12-12 20:17:30,565 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 20:17:31,332 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.276, over 211138.00 frames. , ppl: 9.734638884938837
+2022-12-12 20:19:15,342 INFO [train.py:421] (7/8) Epoch 8, batch 10200, loss[loss=2.593, over 840.00 frames. , ppl: 13.365312112440579] tot_loss[loss=2.276, over 5530119.12 frames. , ppl: 9.734677591993513], batch size: 70
+2022-12-12 20:20:52,766 INFO [train.py:421] (7/8) Epoch 8, batch 10400, loss[loss=2.302, over 3220.00 frames. , ppl: 9.99062158971705] tot_loss[loss=2.275, over 5558810.73 frames. , ppl: 9.731146289907246], batch size: 70
+2022-12-12 20:22:35,028 INFO [train.py:421] (7/8) Epoch 8, batch 10600, loss[loss=2.629, over 980.00 frames. , ppl: 13.861790783982894] tot_loss[loss=2.275, over 5544320.59 frames. , ppl: 9.728036241211043], batch size: 70
+2022-12-12 20:24:13,556 INFO [train.py:421] (7/8) Epoch 8, batch 10800, loss[loss=2.338, over 2590.00 frames. , ppl: 10.355708293733379] tot_loss[loss=2.276, over 5521639.58 frames. , ppl: 9.735919383240606], batch size: 70
+2022-12-12 20:25:55,033 INFO [train.py:421] (7/8) Epoch 8, batch 11000, loss[loss=2.254, over 1890.00 frames. , ppl: 9.522433954648035] tot_loss[loss=2.275, over 5516561.06 frames. , ppl: 9.732415315128579], batch size: 70
+2022-12-12 20:25:55,034 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 20:25:55,810 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.273, over 211138.00 frames. , ppl: 9.706705920947643
+2022-12-12 20:27:38,290 INFO [train.py:421] (7/8) Epoch 8, batch 11200, loss[loss=2.329, over 3220.00 frames. , ppl: 10.269511997537965] tot_loss[loss=2.276, over 5494275.90 frames. , ppl: 9.741458202689163], batch size: 70
+2022-12-12 20:29:17,866 INFO [train.py:421] (7/8) Epoch 8, batch 11400, loss[loss=2.238, over 3150.00 frames. , ppl: 9.37502609349496] tot_loss[loss=2.277, over 5477749.65 frames. , ppl: 9.749135074289008], batch size: 70
+2022-12-12 20:30:55,494 INFO [train.py:421] (7/8) Epoch 8, batch 11600, loss[loss=2.393, over 1400.00 frames. , ppl: 10.949093435442574] tot_loss[loss=2.277, over 5497269.27 frames. , ppl: 9.745261468056514], batch size: 70
+2022-12-12 20:32:40,056 INFO [train.py:421] (7/8) Epoch 8, batch 11800, loss[loss=4.008, over 350.00 frames. , ppl: 55.019018710790434] tot_loss[loss=2.275, over 5536780.30 frames. , ppl: 9.732542732706687], batch size: 70
+2022-12-12 20:34:17,576 INFO [train.py:421] (7/8) Epoch 8, batch 12000, loss[loss=2.214, over 4760.00 frames. , ppl: 9.14778757723564] tot_loss[loss=2.277, over 5487010.67 frames. , ppl: 9.747295427859166], batch size: 70
+2022-12-12 20:34:17,576 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 20:34:18,324 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.273, over 211138.00 frames. , ppl: 9.712665599212405
+2022-12-12 20:36:00,925 INFO [train.py:421] (7/8) Epoch 8, batch 12200, loss[loss=2.334, over 1470.00 frames. , ppl: 10.318958973057383] tot_loss[loss=2.277, over 5490910.94 frames. , ppl: 9.746971406752868], batch size: 70
+2022-12-12 20:37:42,049 INFO [train.py:421] (7/8) Epoch 8, batch 12400, loss[loss=2.465, over 980.00 frames. , ppl: 11.761644251483835] tot_loss[loss=2.276, over 5521479.34 frames. , ppl: 9.740697670235196], batch size: 70
+2022-12-12 20:39:22,995 INFO [train.py:421] (7/8) Epoch 8, batch 12600, loss[loss=2.346, over 1680.00 frames. , ppl: 10.443063363432566] tot_loss[loss=2.275, over 5571039.36 frames. , ppl: 9.728529764773063], batch size: 70
+2022-12-12 20:41:03,256 INFO [train.py:421] (7/8) Epoch 8, batch 12800, loss[loss=2.449, over 2030.00 frames. , ppl: 11.576757036199448] tot_loss[loss=2.275, over 5566299.65 frames. , ppl: 9.729092079602681], batch size: 70
+2022-12-12 20:42:44,549 INFO [train.py:421] (7/8) Epoch 8, batch 13000, loss[loss=2.25, over 2100.00 frames. , ppl: 9.484744917960816] tot_loss[loss=2.275, over 5559782.87 frames. , ppl: 9.727398888930797], batch size: 70
+2022-12-12 20:42:44,550 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 20:42:45,301 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.274, over 211138.00 frames. , ppl: 9.722002639478895
+2022-12-12 20:44:28,071 INFO [train.py:421] (7/8) Epoch 8, batch 13200, loss[loss=2.211, over 3150.00 frames. , ppl: 9.129384944358986] tot_loss[loss=2.275, over 5546605.28 frames. , ppl: 9.731973526987295], batch size: 70
+2022-12-12 20:46:10,753 INFO [train.py:421] (7/8) Epoch 8, batch 13400, loss[loss=2.408, over 1540.00 frames. , ppl: 11.114719855759178] tot_loss[loss=2.276, over 5536576.65 frames. , ppl: 9.740878581920134], batch size: 70
+2022-12-12 20:47:53,570 INFO [train.py:421] (7/8) Epoch 8, batch 13600, loss[loss=2.426, over 1120.00 frames. , ppl: 11.309460199208525] tot_loss[loss=2.278, over 5492384.60 frames. , ppl: 9.75886436953377], batch size: 70
+2022-12-12 20:49:37,901 INFO [train.py:421] (7/8) Epoch 8, batch 13800, loss[loss=2.411, over 2380.00 frames. , ppl: 11.149908823131888] tot_loss[loss=2.279, over 5469300.04 frames. , ppl: 9.763781247644602], batch size: 70
+2022-12-12 20:51:19,927 INFO [train.py:421] (7/8) Epoch 8, batch 14000, loss[loss=2.203, over 4620.00 frames. , ppl: 9.056447572327393] tot_loss[loss=2.279, over 5453023.79 frames. , ppl: 9.763523518428302], batch size: 70
+2022-12-12 20:51:19,927 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 20:51:20,692 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.272, over 211138.00 frames. , ppl: 9.699218039613152
+2022-12-12 20:53:03,157 INFO [train.py:421] (7/8) Epoch 8, batch 14200, loss[loss=2.445, over 910.00 frames. , ppl: 11.525300523333497] tot_loss[loss=2.278, over 5494022.52 frames. , ppl: 9.755538423129536], batch size: 70
+2022-12-12 20:54:47,607 INFO [train.py:421] (7/8) Epoch 8, batch 14400, loss[loss=2.452, over 1260.00 frames. , ppl: 11.607740609798444] tot_loss[loss=2.278, over 5479214.35 frames. , ppl: 9.758408507218984], batch size: 70
+2022-12-12 20:56:30,676 INFO [train.py:421] (7/8) Epoch 8, batch 14600, loss[loss=2.267, over 2310.00 frames. , ppl: 9.647424369790565] tot_loss[loss=2.277, over 5549709.66 frames. , ppl: 9.742843077949765], batch size: 70
+2022-12-12 20:58:11,811 INFO [train.py:421] (7/8) Epoch 8, batch 14800, loss[loss=2.281, over 3010.00 frames. , ppl: 9.782336979950058] tot_loss[loss=2.275, over 5578884.49 frames. , ppl: 9.72807257255891], batch size: 70
+2022-12-12 20:59:52,443 INFO [train.py:421] (7/8) Epoch 8, batch 15000, loss[loss=2.243, over 3360.00 frames. , ppl: 9.41980528740485] tot_loss[loss=2.277, over 5500523.90 frames. , ppl: 9.750978090290548], batch size: 70
+2022-12-12 20:59:52,443 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 20:59:53,202 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.272, over 211138.00 frames. , ppl: 9.698958207336654
+2022-12-12 21:01:33,669 INFO [train.py:421] (7/8) Epoch 8, batch 15200, loss[loss=2.5, over 1330.00 frames. , ppl: 12.188555765306118] tot_loss[loss=2.277, over 5492984.86 frames. , ppl: 9.749431240334182], batch size: 70
+2022-12-12 21:03:13,944 INFO [train.py:421] (7/8) Epoch 8, batch 15400, loss[loss=2.32, over 2730.00 frames. , ppl: 10.178563414887952] tot_loss[loss=2.278, over 5479745.24 frames. , ppl: 9.758438778847168], batch size: 70
+2022-12-12 21:04:56,826 INFO [train.py:421] (7/8) Epoch 8, batch 15600, loss[loss=2.415, over 1610.00 frames. , ppl: 11.185180726719533] tot_loss[loss=2.277, over 5496272.39 frames. , ppl: 9.752199159889551], batch size: 70
+2022-12-12 21:06:37,402 INFO [train.py:421] (7/8) Epoch 8, batch 15800, loss[loss=2.2, over 9660.00 frames. , ppl: 9.028610776884797] tot_loss[loss=2.276, over 5551239.01 frames. , ppl: 9.738546792041944], batch size: 70
+2022-12-12 21:08:18,883 INFO [train.py:421] (7/8) Epoch 8, batch 16000, loss[loss=2.269, over 2730.00 frames. , ppl: 9.667461281445654] tot_loss[loss=2.276, over 5560936.28 frames. , ppl: 9.735995251243864], batch size: 70
+2022-12-12 21:08:18,884 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 21:08:19,648 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.273, over 211138.00 frames. , ppl: 9.704328531673617
+2022-12-12 21:09:58,177 INFO [train.py:421] (7/8) Epoch 8, batch 16200, loss[loss=2.147, over 8610.00 frames. , ppl: 8.561443428929433] tot_loss[loss=2.276, over 5552452.50 frames. , ppl: 9.733510387996985], batch size: 70
+2022-12-12 21:11:38,669 INFO [train.py:421] (7/8) Epoch 8, batch 16400, loss[loss=4.89, over 280.00 frames. , ppl: 132.93488804227616] tot_loss[loss=2.277, over 5518363.90 frames. , ppl: 9.747322031058447], batch size: 70
+2022-12-12 21:13:18,891 INFO [train.py:421] (7/8) Epoch 8, batch 16600, loss[loss=2.205, over 3010.00 frames. , ppl: 9.07389630317983] tot_loss[loss=2.276, over 5544948.47 frames. , ppl: 9.741822851531857], batch size: 70
+2022-12-12 21:14:59,022 INFO [train.py:421] (7/8) Epoch 8, batch 16800, loss[loss=2.717, over 700.00 frames. , ppl: 15.1361354470391] tot_loss[loss=2.276, over 5566795.98 frames. , ppl: 9.733159643042368], batch size: 70
+2022-12-12 21:16:43,651 INFO [train.py:421] (7/8) Epoch 8, batch 17000, loss[loss=2.202, over 2800.00 frames. , ppl: 9.044004489130936] tot_loss[loss=2.277, over 5521711.12 frames. , ppl: 9.746920201183917], batch size: 70
+2022-12-12 21:16:43,652 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 21:16:44,419 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.272, over 211138.00 frames. , ppl: 9.701667408509223
+2022-12-12 21:18:25,170 INFO [train.py:421] (7/8) Epoch 8, batch 17200, loss[loss=2.279, over 2310.00 frames. , ppl: 9.76801624236902] tot_loss[loss=2.279, over 5457217.15 frames. , ppl: 9.766603876972342], batch size: 70
+2022-12-12 21:20:08,355 INFO [train.py:421] (7/8) Epoch 8, batch 17400, loss[loss=2.753, over 630.00 frames. , ppl: 15.691780076929978] tot_loss[loss=2.279, over 5434753.00 frames. , ppl: 9.76351118270831], batch size: 70
+2022-12-12 21:21:48,846 INFO [train.py:421] (7/8) Epoch 8, batch 17600, loss[loss=2.31, over 2450.00 frames. , ppl: 10.076310171988569] tot_loss[loss=2.28, over 5402925.26 frames. , ppl: 9.776575415010608], batch size: 70
+2022-12-12 21:23:31,881 INFO [train.py:421] (7/8) Epoch 8, batch 17800, loss[loss=2.261, over 2660.00 frames. , ppl: 9.594479507956859] tot_loss[loss=2.28, over 5431780.80 frames. , ppl: 9.774118814666476], batch size: 70
+2022-12-12 21:25:12,514 INFO [train.py:421] (7/8) Epoch 8, batch 18000, loss[loss=2.44, over 910.00 frames. , ppl: 11.471420565992368] tot_loss[loss=2.28, over 5413730.30 frames. , ppl: 9.776265156826469], batch size: 70
+2022-12-12 21:25:12,514 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 21:25:13,280 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.271, over 211138.00 frames. , ppl: 9.693148970049764
+2022-12-12 21:26:52,973 INFO [train.py:421] (7/8) Epoch 8, batch 18200, loss[loss=2.462, over 770.00 frames. , ppl: 11.724504099780638] tot_loss[loss=2.281, over 5390790.31 frames. , ppl: 9.781970924309949], batch size: 70
+2022-12-12 21:28:32,829 INFO [train.py:421] (7/8) Epoch 8, batch 18400, loss[loss=2.2, over 7280.00 frames. , ppl: 9.02183369743649] tot_loss[loss=2.28, over 5399668.11 frames. , ppl: 9.781042710658262], batch size: 70
+2022-12-12 21:30:13,680 INFO [train.py:421] (7/8) Epoch 8, batch 18600, loss[loss=2.369, over 1050.00 frames. , ppl: 10.681880284403315] tot_loss[loss=2.28, over 5417063.52 frames. , ppl: 9.772598147560277], batch size: 70
+2022-12-12 21:31:51,676 INFO [train.py:421] (7/8) Epoch 8, batch 18800, loss[loss=2.391, over 1120.00 frames. , ppl: 10.923823960142048] tot_loss[loss=2.281, over 5386272.43 frames. , ppl: 9.784514286810294], batch size: 70
+2022-12-12 21:33:32,792 INFO [train.py:421] (7/8) Epoch 8, batch 19000, loss[loss=2.325, over 1820.00 frames. , ppl: 10.229742490203808] tot_loss[loss=2.281, over 5371863.64 frames. , ppl: 9.7863557757118], batch size: 70
+2022-12-12 21:33:32,793 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 21:33:33,556 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.272, over 211138.00 frames. , ppl: 9.703235558989775
+2022-12-12 21:35:14,726 INFO [train.py:421] (7/8) Epoch 8, batch 19200, loss[loss=2.177, over 3150.00 frames. , ppl: 8.817429395174061] tot_loss[loss=2.282, over 5350250.33 frames. , ppl: 9.793683785262994], batch size: 70
+2022-12-12 21:36:52,536 INFO [train.py:421] (7/8) Epoch 8, batch 19400, loss[loss=2.242, over 7350.00 frames. , ppl: 9.413654038308922] tot_loss[loss=2.282, over 5339949.87 frames. , ppl: 9.795451044382352], batch size: 70
+2022-12-12 21:38:36,743 INFO [train.py:421] (7/8) Epoch 8, batch 19600, loss[loss=2.52, over 910.00 frames. , ppl: 12.429372941603035] tot_loss[loss=2.282, over 5344124.75 frames. , ppl: 9.793940568921867], batch size: 70
+2022-12-12 21:40:17,794 INFO [train.py:421] (7/8) Epoch 8, batch 19800, loss[loss=2.374, over 1540.00 frames. , ppl: 10.741903679525864] tot_loss[loss=2.28, over 5375592.47 frames. , ppl: 9.778532031210702], batch size: 70
+2022-12-12 21:42:00,393 INFO [train.py:421] (7/8) Epoch 8, batch 20000, loss[loss=2.143, over 6440.00 frames. , ppl: 8.522438168503943] tot_loss[loss=2.28, over 5364480.47 frames. , ppl: 9.779818171420255], batch size: 70
+2022-12-12 21:42:00,394 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 21:42:01,125 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.272, over 211138.00 frames. , ppl: 9.70147643313627
+2022-12-12 21:43:41,744 INFO [train.py:421] (7/8) Epoch 8, batch 20200, loss[loss=2.258, over 3290.00 frames. , ppl: 9.5627791961237] tot_loss[loss=2.279, over 5398417.69 frames. , ppl: 9.771166223545237], batch size: 70
+2022-12-12 21:45:25,117 INFO [train.py:421] (7/8) Epoch 8, batch 20400, loss[loss=2.161, over 10010.00 frames. , ppl: 8.681492787446986] tot_loss[loss=2.28, over 5391342.03 frames. , ppl: 9.772037325746847], batch size: 70
+2022-12-12 21:47:09,833 INFO [train.py:421] (7/8) Epoch 8, batch 20600, loss[loss=2.112, over 3850.00 frames. , ppl: 8.264352199470965] tot_loss[loss=2.278, over 5436653.62 frames. , ppl: 9.757284110064464], batch size: 70
+2022-12-12 21:48:48,199 INFO [train.py:421] (7/8) Epoch 8, batch 20800, loss[loss=2.181, over 4200.00 frames. , ppl: 8.858734530056886] tot_loss[loss=2.279, over 5394933.95 frames. , ppl: 9.766940175436845], batch size: 70
+2022-12-12 21:50:31,021 INFO [train.py:421] (7/8) Epoch 8, batch 21000, loss[loss=2.164, over 5110.00 frames. , ppl: 8.703527845964018] tot_loss[loss=2.279, over 5386395.17 frames. , ppl: 9.769752083493808], batch size: 70
+2022-12-12 21:50:31,021 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 21:50:31,776 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.272, over 211138.00 frames. , ppl: 9.699197941840623
+2022-12-12 21:52:13,973 INFO [train.py:421] (7/8) Epoch 8, batch 21200, loss[loss=2.323, over 1750.00 frames. , ppl: 10.208685109260427] tot_loss[loss=2.279, over 5379683.58 frames. , ppl: 9.770045251092242], batch size: 70
+2022-12-12 21:53:55,496 INFO [train.py:421] (7/8) Epoch 8, batch 21400, loss[loss=2.228, over 2310.00 frames. , ppl: 9.284014978069496] tot_loss[loss=2.278, over 5409987.42 frames. , ppl: 9.76181600964181], batch size: 70
+2022-12-12 21:55:37,163 INFO [train.py:421] (7/8) Epoch 8, batch 21600, loss[loss=2.195, over 5390.00 frames. , ppl: 8.97787937354918] tot_loss[loss=2.278, over 5432639.55 frames. , ppl: 9.76173743267402], batch size: 70
+2022-12-12 21:57:17,868 INFO [train.py:421] (7/8) Epoch 8, batch 21800, loss[loss=2.539, over 770.00 frames. , ppl: 12.671396700042695] tot_loss[loss=2.276, over 5495733.30 frames. , ppl: 9.7413319834606], batch size: 70
+2022-12-12 21:59:00,466 INFO [train.py:421] (7/8) Epoch 8, batch 22000, loss[loss=2.311, over 1610.00 frames. , ppl: 10.083288220779737] tot_loss[loss=2.276, over 5530779.04 frames. , ppl: 9.733835651334749], batch size: 70
+2022-12-12 21:59:00,467 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 21:59:01,248 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.271, over 211138.00 frames. , ppl: 9.689339266199932
+2022-12-12 22:00:41,755 INFO [train.py:421] (7/8) Epoch 8, batch 22200, loss[loss=2.277, over 1470.00 frames. , ppl: 9.745386742180361] tot_loss[loss=2.278, over 5488885.76 frames. , ppl: 9.754000289051552], batch size: 70
+2022-12-12 22:02:23,816 INFO [train.py:421] (7/8) Epoch 8, batch 22400, loss[loss=2.202, over 6090.00 frames. , ppl: 9.04148325094372] tot_loss[loss=2.278, over 5478703.86 frames. , ppl: 9.76036369668256], batch size: 70
+2022-12-12 22:04:05,302 INFO [train.py:421] (7/8) Epoch 8, batch 22600, loss[loss=2.326, over 1890.00 frames. , ppl: 10.238414924114686] tot_loss[loss=2.278, over 5496928.82 frames. , ppl: 9.759281344071505], batch size: 70
+2022-12-12 22:05:46,666 INFO [train.py:421] (7/8) Epoch 8, batch 22800, loss[loss=2.877, over 560.00 frames. , ppl: 17.759853381847606] tot_loss[loss=2.278, over 5516187.33 frames. , ppl: 9.753768886225084], batch size: 70
+2022-12-12 22:07:29,981 INFO [train.py:421] (7/8) Epoch 8, batch 23000, loss[loss=2.736, over 700.00 frames. , ppl: 15.426685079041356] tot_loss[loss=2.278, over 5493902.94 frames. , ppl: 9.758017116881769], batch size: 70
+2022-12-12 22:07:29,982 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 22:07:30,755 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.272, over 211138.00 frames. , ppl: 9.695581021092998
+2022-12-12 22:09:13,811 INFO [train.py:421] (7/8) Epoch 8, batch 23200, loss[loss=3.329, over 490.00 frames. , ppl: 27.896470609357703] tot_loss[loss=2.277, over 5519043.66 frames. , ppl: 9.74911720306858], batch size: 70
+2022-12-12 22:10:53,394 INFO [train.py:421] (7/8) Epoch 8, batch 23400, loss[loss=2.209, over 5250.00 frames. , ppl: 9.10247804407414] tot_loss[loss=2.278, over 5458513.32 frames. , ppl: 9.761105421264896], batch size: 70
+2022-12-12 22:12:32,786 INFO [train.py:421] (7/8) Epoch 8, batch 23600, loss[loss=2.433, over 1610.00 frames. , ppl: 11.3899118301584] tot_loss[loss=2.278, over 5456381.77 frames. , ppl: 9.761200996675587], batch size: 70
+2022-12-12 22:14:11,813 INFO [train.py:421] (7/8) Epoch 8, batch 23800, loss[loss=2.432, over 1050.00 frames. , ppl: 11.38156012228953] tot_loss[loss=2.279, over 5451087.05 frames. , ppl: 9.763656493296303], batch size: 70
+2022-12-12 22:15:55,042 INFO [train.py:421] (7/8) Epoch 8, batch 24000, loss[loss=2.341, over 1820.00 frames. , ppl: 10.396626413353795] tot_loss[loss=2.28, over 5417498.93 frames. , ppl: 9.772393002450954], batch size: 70
+2022-12-12 22:15:55,042 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 22:15:55,805 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.273, over 211138.00 frames. , ppl: 9.708671477552679
+2022-12-12 22:17:36,360 INFO [train.py:421] (7/8) Epoch 8, batch 24200, loss[loss=2.196, over 5250.00 frames. , ppl: 8.985774099139627] tot_loss[loss=2.279, over 5453794.20 frames. , ppl: 9.76574116773961], batch size: 70
+2022-12-12 22:19:17,619 INFO [train.py:421] (7/8) Epoch 8, batch 24400, loss[loss=2.308, over 3220.00 frames. , ppl: 10.05241398606114] tot_loss[loss=2.278, over 5490649.37 frames. , ppl: 9.755851757939011], batch size: 70
+2022-12-12 22:20:57,983 INFO [train.py:421] (7/8) Epoch 8, batch 24600, loss[loss=2.511, over 1120.00 frames. , ppl: 12.318560275740715] tot_loss[loss=2.278, over 5471616.20 frames. , ppl: 9.760342323491594], batch size: 70
+2022-12-12 22:22:37,694 INFO [train.py:421] (7/8) Epoch 8, batch 24800, loss[loss=2.719, over 630.00 frames. , ppl: 15.170112635112359] tot_loss[loss=2.277, over 5509690.15 frames. , ppl: 9.744682853971698], batch size: 70
+2022-12-12 22:24:20,908 INFO [train.py:421] (7/8) Epoch 8, batch 25000, loss[loss=2.167, over 6510.00 frames. , ppl: 8.729473590524128] tot_loss[loss=2.277, over 5514602.57 frames. , ppl: 9.748773319821135], batch size: 70
+2022-12-12 22:24:20,909 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 22:24:21,639 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.271, over 211138.00 frames. , ppl: 9.690235616742381
+2022-12-12 22:26:02,835 INFO [train.py:421] (7/8) Epoch 8, batch 25200, loss[loss=2.382, over 1680.00 frames. , ppl: 10.824937543142113] tot_loss[loss=2.277, over 5518349.04 frames. , ppl: 9.744053989075558], batch size: 70
+2022-12-12 22:27:41,827 INFO [train.py:421] (7/8) Epoch 8, batch 25400, loss[loss=2.306, over 1890.00 frames. , ppl: 10.034616212330121] tot_loss[loss=2.277, over 5495923.04 frames. , ppl: 9.75206033513147], batch size: 70
+2022-12-12 22:29:21,120 INFO [train.py:421] (7/8) Epoch 8, batch 25600, loss[loss=2.766, over 630.00 frames. , ppl: 15.895489484558267] tot_loss[loss=2.278, over 5447625.59 frames. , ppl: 9.759814951079742], batch size: 70
+2022-12-12 22:31:04,405 INFO [train.py:421] (7/8) Epoch 8, batch 25800, loss[loss=2.492, over 840.00 frames. , ppl: 12.079400709087778] tot_loss[loss=2.278, over 5497855.44 frames. , ppl: 9.754898892427155], batch size: 70
+2022-12-12 22:32:42,660 INFO [train.py:421] (7/8) Epoch 8, batch 26000, loss[loss=2.465, over 1400.00 frames. , ppl: 11.763160088396425] tot_loss[loss=2.277, over 5522288.29 frames. , ppl: 9.742678889764425], batch size: 70
+2022-12-12 22:32:42,661 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 22:32:43,419 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.273, over 211138.00 frames. , ppl: 9.708037800704728
+2022-12-12 22:34:22,026 INFO [train.py:421] (7/8) Epoch 8, batch 26200, loss[loss=2.232, over 3780.00 frames. , ppl: 9.318583032603257] tot_loss[loss=2.276, over 5538760.23 frames. , ppl: 9.738707682633299], batch size: 70
+2022-12-12 22:36:01,430 INFO [train.py:421] (7/8) Epoch 8, batch 26400, loss[loss=2.236, over 4900.00 frames. , ppl: 9.359679356918656] tot_loss[loss=2.277, over 5536454.30 frames. , ppl: 9.745566385208397], batch size: 70
+2022-12-12 22:37:43,187 INFO [train.py:421] (7/8) Epoch 8, batch 26600, loss[loss=2.478, over 770.00 frames. , ppl: 11.918323008570464] tot_loss[loss=2.278, over 5499655.32 frames. , ppl: 9.754117090306792], batch size: 70
+2022-12-12 22:39:21,936 INFO [train.py:421] (7/8) Epoch 8, batch 26800, loss[loss=2.388, over 1890.00 frames. , ppl: 10.886578972307612] tot_loss[loss=2.277, over 5519879.51 frames. , ppl: 9.7456754651643], batch size: 70
+2022-12-12 22:40:59,520 INFO [train.py:421] (7/8) Epoch 8, batch 27000, loss[loss=2.169, over 2940.00 frames. , ppl: 8.749292868905593] tot_loss[loss=2.277, over 5476832.06 frames. , ppl: 9.749081541444998], batch size: 70
+2022-12-12 22:40:59,520 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 22:41:00,266 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.273, over 211138.00 frames. , ppl: 9.710776846115149
+2022-12-12 22:42:40,999 INFO [train.py:421] (7/8) Epoch 8, batch 27200, loss[loss=2.577, over 1120.00 frames. , ppl: 13.162594582609017] tot_loss[loss=2.277, over 5462128.23 frames. , ppl: 9.75169141272952], batch size: 70
+2022-12-12 22:44:23,274 INFO [train.py:421] (7/8) Epoch 8, batch 27400, loss[loss=2.391, over 1750.00 frames. , ppl: 10.921417017946677] tot_loss[loss=2.278, over 5456232.35 frames. , ppl: 9.755836771469845], batch size: 70
+2022-12-12 22:46:01,820 INFO [train.py:421] (7/8) Epoch 8, batch 27600, loss[loss=2.199, over 6650.00 frames. , ppl: 9.019973326142045] tot_loss[loss=2.278, over 5453829.65 frames. , ppl: 9.757219999713149], batch size: 70
+2022-12-12 22:47:40,368 INFO [train.py:421] (7/8) Epoch 8, batch 27800, loss[loss=2.213, over 4690.00 frames. , ppl: 9.140970162440514] tot_loss[loss=2.278, over 5458210.76 frames. , ppl: 9.757263935668417], batch size: 70
+2022-12-12 22:49:20,555 INFO [train.py:421] (7/8) Epoch 8, batch 28000, loss[loss=2.21, over 2940.00 frames. , ppl: 9.111981923651081] tot_loss[loss=2.278, over 5474453.67 frames. , ppl: 9.754162275529037], batch size: 70
+2022-12-12 22:49:20,555 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 22:49:21,297 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.273, over 211138.00 frames. , ppl: 9.709539437680133
+2022-12-12 22:51:00,492 INFO [train.py:421] (7/8) Epoch 8, batch 28200, loss[loss=2.343, over 1750.00 frames. , ppl: 10.409411818694627] tot_loss[loss=2.279, over 5439675.51 frames. , ppl: 9.764414526002662], batch size: 70
+2022-12-12 22:52:39,744 INFO [train.py:421] (7/8) Epoch 8, batch 28400, loss[loss=2.179, over 11130.00 frames. , ppl: 8.835752058007726] tot_loss[loss=2.276, over 5509644.31 frames. , ppl: 9.741140930906061], batch size: 70
+2022-12-12 22:54:17,923 INFO [train.py:421] (7/8) Epoch 8, batch 28600, loss[loss=2.433, over 2100.00 frames. , ppl: 11.39841416455017] tot_loss[loss=2.276, over 5560647.84 frames. , ppl: 9.733514154415175], batch size: 70
+2022-12-12 22:55:59,819 INFO [train.py:421] (7/8) Epoch 8, batch 28800, loss[loss=2.333, over 1680.00 frames. , ppl: 10.313587841628793] tot_loss[loss=2.276, over 5579782.20 frames. , ppl: 9.737495250855114], batch size: 70
+2022-12-12 22:57:42,747 INFO [train.py:421] (7/8) Epoch 8, batch 29000, loss[loss=2.277, over 2380.00 frames. , ppl: 9.749091318106682] tot_loss[loss=2.276, over 5599694.33 frames. , ppl: 9.733174016068645], batch size: 70
+2022-12-12 22:57:42,748 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 22:57:43,506 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.272, over 211138.00 frames. , ppl: 9.696305732449282
+2022-12-12 22:59:22,327 INFO [train.py:421] (7/8) Epoch 8, batch 29200, loss[loss=2.447, over 1540.00 frames. , ppl: 11.55675075126704] tot_loss[loss=2.275, over 5585723.94 frames. , ppl: 9.730065727329045], batch size: 70
+2022-12-12 23:01:03,761 INFO [train.py:421] (7/8) Epoch 8, batch 29400, loss[loss=2.269, over 5810.00 frames. , ppl: 9.665772078553598] tot_loss[loss=2.276, over 5598213.55 frames. , ppl: 9.733284680244353], batch size: 70
+2022-12-12 23:02:44,759 INFO [train.py:421] (7/8) Epoch 8, batch 29600, loss[loss=2.304, over 3010.00 frames. , ppl: 10.01754685687924] tot_loss[loss=2.274, over 5617495.77 frames. , ppl: 9.722877263177363], batch size: 70
+2022-12-12 23:04:24,091 INFO [train.py:421] (7/8) Epoch 8, batch 29800, loss[loss=2.407, over 1610.00 frames. , ppl: 11.104643363761879] tot_loss[loss=2.274, over 5641114.02 frames. , ppl: 9.718421705612592], batch size: 70
+2022-12-12 23:06:04,137 INFO [train.py:421] (7/8) Epoch 8, batch 30000, loss[loss=2.203, over 1400.00 frames. , ppl: 9.054718095896936] tot_loss[loss=2.274, over 5631298.83 frames. , ppl: 9.71772932226183], batch size: 70
+2022-12-12 23:06:04,138 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 23:06:04,900 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.273, over 211138.00 frames. , ppl: 9.705356986317165
+2022-12-12 23:07:46,669 INFO [train.py:421] (7/8) Epoch 8, batch 30200, loss[loss=2.116, over 7770.00 frames. , ppl: 8.295865177370795] tot_loss[loss=2.274, over 5621458.43 frames. , ppl: 9.721521081359509], batch size: 70
+2022-12-12 23:09:28,047 INFO [train.py:421] (7/8) Epoch 8, batch 30400, loss[loss=2.465, over 1120.00 frames. , ppl: 11.760805907324173] tot_loss[loss=2.273, over 5651061.93 frames. , ppl: 9.71034862014515], batch size: 70
+2022-12-12 23:11:07,279 INFO [train.py:421] (7/8) Epoch 8, batch 30600, loss[loss=2.352, over 1750.00 frames. , ppl: 10.506620479835284] tot_loss[loss=2.275, over 5586418.47 frames. , ppl: 9.729533371777936], batch size: 70
+2022-12-12 23:12:43,211 INFO [train.py:421] (7/8) Epoch 8, batch 30800, loss[loss=2.284, over 2240.00 frames. , ppl: 9.81451394338893] tot_loss[loss=2.276, over 5559044.07 frames. , ppl: 9.740959210001355], batch size: 70
+2022-12-12 23:14:23,185 INFO [train.py:421] (7/8) Epoch 8, batch 31000, loss[loss=2.573, over 910.00 frames. , ppl: 13.10303719761338] tot_loss[loss=2.277, over 5541792.27 frames. , ppl: 9.748558694711225], batch size: 70
+2022-12-12 23:14:23,186 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 23:14:23,945 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.272, over 211138.00 frames. , ppl: 9.697824214248042
+2022-12-12 23:16:06,465 INFO [train.py:421] (7/8) Epoch 8, batch 31200, loss[loss=5.134, over 280.00 frames. , ppl: 169.64469645803695] tot_loss[loss=2.278, over 5513294.48 frames. , ppl: 9.756698639516774], batch size: 70
+2022-12-12 23:17:46,228 INFO [train.py:421] (7/8) Epoch 8, batch 31400, loss[loss=2.264, over 3500.00 frames. , ppl: 9.623055466967099] tot_loss[loss=2.278, over 5492269.67 frames. , ppl: 9.756676134515503], batch size: 70
+2022-12-12 23:19:24,626 INFO [train.py:421] (7/8) Epoch 8, batch 31600, loss[loss=2.219, over 5180.00 frames. , ppl: 9.195839294430584] tot_loss[loss=2.277, over 5508513.71 frames. , ppl: 9.747494805356894], batch size: 70
+2022-12-12 23:21:02,586 INFO [train.py:421] (7/8) Epoch 8, batch 31800, loss[loss=2.302, over 1820.00 frames. , ppl: 9.989377286558751] tot_loss[loss=2.277, over 5517212.17 frames. , ppl: 9.751062248923102], batch size: 70
+2022-12-12 23:22:42,624 INFO [train.py:421] (7/8) Epoch 8, batch 32000, loss[loss=2.292, over 1820.00 frames. , ppl: 9.89044726061082] tot_loss[loss=2.277, over 5514610.86 frames. , ppl: 9.744300834466676], batch size: 70
+2022-12-12 23:22:42,625 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 23:22:43,385 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.27, over 211138.00 frames. , ppl: 9.681927833421199
+2022-12-12 23:24:20,888 INFO [train.py:421] (7/8) Epoch 8, batch 32200, loss[loss=2.27, over 4480.00 frames. , ppl: 9.68031994841534] tot_loss[loss=2.277, over 5513654.40 frames. , ppl: 9.744640461711949], batch size: 70
+2022-12-12 23:26:03,838 INFO [train.py:421] (7/8) Epoch 8, batch 32400, loss[loss=2.189, over 3010.00 frames. , ppl: 8.92770773734717] tot_loss[loss=2.276, over 5526884.65 frames. , ppl: 9.736070527360265], batch size: 70
+2022-12-12 23:27:44,857 INFO [train.py:421] (7/8) Epoch 8, batch 32600, loss[loss=2.167, over 8680.00 frames. , ppl: 8.730866360023727] tot_loss[loss=2.276, over 5538378.44 frames. , ppl: 9.734318195320576], batch size: 70
+2022-12-12 23:29:26,645 INFO [train.py:421] (7/8) Epoch 8, batch 32800, loss[loss=2.372, over 1120.00 frames. , ppl: 10.71788222982039] tot_loss[loss=2.276, over 5534969.48 frames. , ppl: 9.734742932834857], batch size: 70
+2022-12-12 23:31:04,175 INFO [train.py:421] (7/8) Epoch 8, batch 33000, loss[loss=2.325, over 910.00 frames. , ppl: 10.229550376951984] tot_loss[loss=2.277, over 5520733.75 frames. , ppl: 9.744019918737537], batch size: 70
+2022-12-12 23:31:04,175 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 23:31:04,954 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.272, over 211138.00 frames. , ppl: 9.70102126639035
+2022-12-12 23:32:46,881 INFO [train.py:421] (7/8) Epoch 8, batch 33200, loss[loss=2.348, over 2030.00 frames. , ppl: 10.46574191938245] tot_loss[loss=2.278, over 5510730.64 frames. , ppl: 9.756737716908049], batch size: 70
+2022-12-12 23:34:29,598 INFO [train.py:421] (7/8) Epoch 8, batch 33400, loss[loss=2.302, over 3220.00 frames. , ppl: 9.991532133739657] tot_loss[loss=2.278, over 5485169.89 frames. , ppl: 9.761582843376223], batch size: 70
+2022-12-12 23:36:09,714 INFO [train.py:421] (7/8) Epoch 8, batch 33600, loss[loss=2.171, over 4970.00 frames. , ppl: 8.763559240270833] tot_loss[loss=2.279, over 5472189.22 frames. , ppl: 9.764388698510562], batch size: 70
+2022-12-12 23:37:51,013 INFO [train.py:421] (7/8) Epoch 8, batch 33800, loss[loss=2.439, over 1400.00 frames. , ppl: 11.458416662095717] tot_loss[loss=2.28, over 5430418.57 frames. , ppl: 9.779916650079027], batch size: 70
+2022-12-12 23:39:28,207 INFO [train.py:421] (7/8) Epoch 8, batch 34000, loss[loss=2.201, over 4200.00 frames. , ppl: 9.033997235083138] tot_loss[loss=2.28, over 5437887.74 frames. , ppl: 9.781378845802939], batch size: 70
+2022-12-12 23:39:28,208 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 23:39:28,937 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.27, over 211138.00 frames. , ppl: 9.680815891149308
+2022-12-12 23:41:01,893 INFO [train.py:421] (7/8) Epoch 8, batch 34200, loss[loss=2.957, over 630.00 frames. , ppl: 19.235517357969368] tot_loss[loss=2.281, over 5416186.34 frames. , ppl: 9.782231497915623], batch size: 70
+2022-12-12 23:42:44,198 INFO [train.py:421] (7/8) Epoch 8, batch 34400, loss[loss=2.201, over 5880.00 frames. , ppl: 9.031101056426776] tot_loss[loss=2.279, over 5452259.97 frames. , ppl: 9.766860466643031], batch size: 70
+2022-12-12 23:44:28,312 INFO [train.py:421] (7/8) Epoch 8, batch 34600, loss[loss=2.972, over 630.00 frames. , ppl: 19.53985619761367] tot_loss[loss=2.279, over 5439195.24 frames. , ppl: 9.769511710958554], batch size: 70
+2022-12-12 23:46:06,947 INFO [train.py:421] (7/8) Epoch 8, batch 34800, loss[loss=2.788, over 630.00 frames. , ppl: 16.250938389292983] tot_loss[loss=2.279, over 5461965.35 frames. , ppl: 9.763154907740928], batch size: 70
+2022-12-12 23:47:51,625 INFO [train.py:421] (7/8) Epoch 8, batch 35000, loss[loss=2.4, over 1890.00 frames. , ppl: 11.02065918092789] tot_loss[loss=2.277, over 5517121.29 frames. , ppl: 9.746976656651006], batch size: 70
+2022-12-12 23:47:51,626 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 23:47:52,385 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.27, over 211138.00 frames. , ppl: 9.680259967903076
+2022-12-12 23:49:30,414 INFO [train.py:421] (7/8) Epoch 8, batch 35200, loss[loss=2.606, over 840.00 frames. , ppl: 13.53854536936881] tot_loss[loss=2.277, over 5495505.23 frames. , ppl: 9.743819562186975], batch size: 70
+2022-12-12 23:51:13,489 INFO [train.py:421] (7/8) Epoch 8, batch 35400, loss[loss=2.431, over 1050.00 frames. , ppl: 11.366575594024265] tot_loss[loss=2.276, over 5519940.01 frames. , ppl: 9.74050437441938], batch size: 70
+2022-12-12 23:52:48,345 INFO [train.py:421] (7/8) Epoch 8, batch 35600, loss[loss=2.198, over 3990.00 frames. , ppl: 9.00963062830539] tot_loss[loss=2.276, over 5510678.78 frames. , ppl: 9.739345196485719], batch size: 70
+2022-12-12 23:54:26,510 INFO [train.py:421] (7/8) Epoch 8, batch 35800, loss[loss=2.201, over 8540.00 frames. , ppl: 9.033758982029836] tot_loss[loss=2.277, over 5489495.88 frames. , ppl: 9.746191012079683], batch size: 70
+2022-12-12 23:56:06,774 INFO [train.py:421] (7/8) Epoch 8, batch 36000, loss[loss=2.215, over 9590.00 frames. , ppl: 9.15742977252543] tot_loss[loss=2.276, over 5522352.49 frames. , ppl: 9.74043476475334], batch size: 70
+2022-12-12 23:56:06,774 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-12 23:56:07,522 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.27, over 211138.00 frames. , ppl: 9.675932595464811
+2022-12-12 23:57:48,185 INFO [train.py:421] (7/8) Epoch 8, batch 36200, loss[loss=2.569, over 770.00 frames. , ppl: 13.053346714110308] tot_loss[loss=2.278, over 5480853.02 frames. , ppl: 9.753944905669531], batch size: 70
+2022-12-12 23:59:26,454 INFO [train.py:421] (7/8) Epoch 8, batch 36400, loss[loss=2.47, over 700.00 frames. , ppl: 11.81801921139545] tot_loss[loss=2.278, over 5483596.98 frames. , ppl: 9.757416473410217], batch size: 70
+2022-12-13 00:01:08,131 INFO [train.py:421] (7/8) Epoch 8, batch 36600, loss[loss=2.487, over 840.00 frames. , ppl: 12.028454387047663] tot_loss[loss=2.278, over 5483009.76 frames. , ppl: 9.757556404711595], batch size: 70
+2022-12-13 00:02:44,811 INFO [train.py:421] (7/8) Epoch 8, batch 36800, loss[loss=2.774, over 630.00 frames. , ppl: 16.021397939317836] tot_loss[loss=2.278, over 5492753.59 frames. , ppl: 9.755894552438633], batch size: 70
+2022-12-13 00:04:22,109 INFO [train.py:421] (7/8) Epoch 8, batch 37000, loss[loss=2.231, over 3080.00 frames. , ppl: 9.305312095869834] tot_loss[loss=2.278, over 5493712.43 frames. , ppl: 9.761363669744382], batch size: 70
+2022-12-13 00:04:22,110 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 00:04:22,851 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.27, over 211138.00 frames. , ppl: 9.678712720778323
+2022-12-13 00:06:04,171 INFO [train.py:421] (7/8) Epoch 8, batch 37200, loss[loss=2.26, over 3080.00 frames. , ppl: 9.586777970609141] tot_loss[loss=2.279, over 5512850.53 frames. , ppl: 9.762049301733672], batch size: 70
+2022-12-13 00:07:45,634 INFO [train.py:421] (7/8) Epoch 8, batch 37400, loss[loss=2.207, over 4760.00 frames. , ppl: 9.084469952622586] tot_loss[loss=2.277, over 5564020.15 frames. , ppl: 9.749282132351235], batch size: 70
+2022-12-13 00:09:28,550 INFO [train.py:421] (7/8) Epoch 8, batch 37600, loss[loss=2.184, over 5740.00 frames. , ppl: 8.881099251309083] tot_loss[loss=2.276, over 5623798.05 frames. , ppl: 9.733535373128605], batch size: 70
+2022-12-13 00:11:11,011 INFO [train.py:421] (7/8) Epoch 8, batch 37800, loss[loss=2.189, over 5180.00 frames. , ppl: 8.92990038296301] tot_loss[loss=2.275, over 5635730.66 frames. , ppl: 9.730174967940341], batch size: 70
+2022-12-13 00:12:52,636 INFO [train.py:421] (7/8) Epoch 8, batch 38000, loss[loss=2.239, over 9310.00 frames. , ppl: 9.38628152626731] tot_loss[loss=2.274, over 5688717.09 frames. , ppl: 9.718335440575952], batch size: 70
+2022-12-13 00:12:52,637 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 00:12:53,370 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.269, over 211138.00 frames. , ppl: 9.666419470350528
+2022-12-13 00:14:31,003 INFO [train.py:421] (7/8) Epoch 8, batch 38200, loss[loss=2.259, over 3640.00 frames. , ppl: 9.573063352535929] tot_loss[loss=2.275, over 5663047.45 frames. , ppl: 9.727960825669783], batch size: 70
+2022-12-13 00:16:13,237 INFO [train.py:421] (7/8) Epoch 8, batch 38400, loss[loss=3.244, over 490.00 frames. , ppl: 25.638191046807282] tot_loss[loss=2.276, over 5629364.92 frames. , ppl: 9.74021462818276], batch size: 70
+2022-12-13 00:17:51,820 INFO [train.py:421] (7/8) Epoch 8, batch 38600, loss[loss=2.553, over 910.00 frames. , ppl: 12.841103105509449] tot_loss[loss=2.276, over 5645512.61 frames. , ppl: 9.736045450432478], batch size: 70
+2022-12-13 00:19:32,518 INFO [train.py:421] (7/8) Epoch 8, batch 38800, loss[loss=2.219, over 2240.00 frames. , ppl: 9.195399932769641] tot_loss[loss=2.277, over 5590774.23 frames. , ppl: 9.745003299980883], batch size: 70
+2022-12-13 00:21:14,872 INFO [train.py:421] (7/8) Epoch 8, batch 39000, loss[loss=2.282, over 2870.00 frames. , ppl: 9.797176178960001] tot_loss[loss=2.275, over 5644674.06 frames. , ppl: 9.731218715475917], batch size: 70
+2022-12-13 00:21:14,873 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 00:21:15,629 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.27, over 211138.00 frames. , ppl: 9.679752787430928
+2022-12-13 00:22:54,861 INFO [train.py:421] (7/8) Epoch 8, batch 39200, loss[loss=2.35, over 1820.00 frames. , ppl: 10.481663007114104] tot_loss[loss=2.275, over 5639402.96 frames. , ppl: 9.728073999076367], batch size: 70
+2022-12-13 00:24:36,588 INFO [train.py:421] (7/8) Epoch 8, batch 39400, loss[loss=2.619, over 840.00 frames. , ppl: 13.717870899635148] tot_loss[loss=2.276, over 5611528.51 frames. , ppl: 9.733108415543235], batch size: 70
+2022-12-13 00:26:21,926 INFO [train.py:421] (7/8) Epoch 8, batch 39600, loss[loss=2.231, over 3360.00 frames. , ppl: 9.312672800788745] tot_loss[loss=2.275, over 5621072.98 frames. , ppl: 9.731225120054741], batch size: 70
+2022-12-13 00:28:01,277 INFO [train.py:421] (7/8) Epoch 8, batch 39800, loss[loss=2.384, over 1540.00 frames. , ppl: 10.849907359992596] tot_loss[loss=2.276, over 5593274.03 frames. , ppl: 9.74060209196849], batch size: 70
+2022-12-13 00:29:43,007 INFO [train.py:421] (7/8) Epoch 8, batch 40000, loss[loss=2.244, over 4130.00 frames. , ppl: 9.42638876242052] tot_loss[loss=2.276, over 5581036.97 frames. , ppl: 9.740866185908216], batch size: 70
+2022-12-13 00:29:43,007 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 00:29:43,770 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.271, over 211138.00 frames. , ppl: 9.689682020856184
+2022-12-13 00:31:23,407 INFO [train.py:421] (7/8) Epoch 8, batch 40200, loss[loss=2.654, over 700.00 frames. , ppl: 14.21013230143046] tot_loss[loss=2.277, over 5548828.51 frames. , ppl: 9.747444152274525], batch size: 70
+2022-12-13 00:33:03,356 INFO [train.py:421] (7/8) Epoch 8, batch 40400, loss[loss=2.459, over 1540.00 frames. , ppl: 11.691799164712739] tot_loss[loss=2.278, over 5506120.42 frames. , ppl: 9.758853922911543], batch size: 70
+2022-12-13 00:34:47,611 INFO [train.py:421] (7/8) Epoch 8, batch 40600, loss[loss=3.473, over 420.00 frames. , ppl: 32.21832346023148] tot_loss[loss=2.278, over 5525304.89 frames. , ppl: 9.759996932406466], batch size: 70
+2022-12-13 00:36:29,496 INFO [train.py:421] (7/8) Epoch 8, batch 40800, loss[loss=2.146, over 9940.00 frames. , ppl: 8.552767142521395] tot_loss[loss=2.279, over 5515122.06 frames. , ppl: 9.763869264955801], batch size: 70
+2022-12-13 00:38:06,222 INFO [train.py:421] (7/8) Epoch 8, batch 41000, loss[loss=2.31, over 1960.00 frames. , ppl: 10.07263333920045] tot_loss[loss=2.278, over 5550258.56 frames. , ppl: 9.755965346684816], batch size: 70
+2022-12-13 00:38:06,222 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 00:38:06,968 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.269, over 211138.00 frames. , ppl: 9.67065241409767
+2022-12-13 00:39:49,707 INFO [train.py:421] (7/8) Epoch 8, batch 41200, loss[loss=2.205, over 4900.00 frames. , ppl: 9.066573670170916] tot_loss[loss=2.277, over 5575906.34 frames. , ppl: 9.745354881591528], batch size: 70
+2022-12-13 00:41:29,187 INFO [train.py:421] (7/8) Epoch 8, batch 41400, loss[loss=2.67, over 770.00 frames. , ppl: 14.436044189359327] tot_loss[loss=2.276, over 5590385.16 frames. , ppl: 9.741806730025862], batch size: 70
+2022-12-13 00:43:12,246 INFO [train.py:421] (7/8) Epoch 8, batch 41600, loss[loss=2.369, over 2380.00 frames. , ppl: 10.689374177657298] tot_loss[loss=2.276, over 5602281.05 frames. , ppl: 9.738934236145154], batch size: 70
+2022-12-13 00:44:46,364 INFO [train.py:421] (7/8) Epoch 8, batch 41800, loss[loss=2.261, over 3080.00 frames. , ppl: 9.593732145844122] tot_loss[loss=2.276, over 5593789.11 frames. , ppl: 9.7387624708129], batch size: 70
+2022-12-13 00:46:26,563 INFO [train.py:421] (7/8) Epoch 8, batch 42000, loss[loss=2.35, over 2170.00 frames. , ppl: 10.48481474256822] tot_loss[loss=2.275, over 5600072.53 frames. , ppl: 9.732244824534716], batch size: 70
+2022-12-13 00:46:26,564 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 00:46:27,308 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.27, over 211138.00 frames. , ppl: 9.675724941707049
+2022-12-13 00:48:05,873 INFO [train.py:421] (7/8) Epoch 8, batch 42200, loss[loss=2.297, over 2030.00 frames. , ppl: 9.944252889517674] tot_loss[loss=2.275, over 5643147.25 frames. , ppl: 9.728723170981969], batch size: 70
+2022-12-13 00:49:47,953 INFO [train.py:421] (7/8) Epoch 8, batch 42400, loss[loss=2.556, over 1610.00 frames. , ppl: 12.879592036651534] tot_loss[loss=2.275, over 5636685.77 frames. , ppl: 9.730039635012114], batch size: 70
+2022-12-13 00:51:28,028 INFO [train.py:421] (7/8) Epoch 8, batch 42600, loss[loss=2.312, over 2310.00 frames. , ppl: 10.090969986595969] tot_loss[loss=2.275, over 5621617.90 frames. , ppl: 9.731759185969848], batch size: 70
+2022-12-13 00:53:10,413 INFO [train.py:421] (7/8) Epoch 8, batch 42800, loss[loss=2.133, over 4690.00 frames. , ppl: 8.444314602906834] tot_loss[loss=2.276, over 5594383.71 frames. , ppl: 9.736238642750589], batch size: 70
+2022-12-13 00:54:50,419 INFO [train.py:421] (7/8) Epoch 8, batch 43000, loss[loss=2.44, over 770.00 frames. , ppl: 11.468862504577126] tot_loss[loss=2.276, over 5592354.55 frames. , ppl: 9.735375383535983], batch size: 70
+2022-12-13 00:54:50,420 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 00:54:51,176 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.27, over 211138.00 frames. , ppl: 9.675021816214633
+2022-12-13 00:56:31,400 INFO [train.py:421] (7/8) Epoch 8, batch 43200, loss[loss=2.594, over 910.00 frames. , ppl: 13.384562515559297] tot_loss[loss=2.275, over 5585932.67 frames. , ppl: 9.731364679359638], batch size: 70
+2022-12-13 00:58:13,083 INFO [train.py:421] (7/8) Epoch 8, batch 43400, loss[loss=2.862, over 630.00 frames. , ppl: 17.490900470275452] tot_loss[loss=2.277, over 5504952.48 frames. , ppl: 9.74582460849225], batch size: 70
+2022-12-13 00:59:53,253 INFO [train.py:421] (7/8) Epoch 8, batch 43600, loss[loss=2.178, over 6930.00 frames. , ppl: 8.824450899556542] tot_loss[loss=2.275, over 5537464.09 frames. , ppl: 9.730583732639305], batch size: 70
+2022-12-13 01:01:34,005 INFO [train.py:421] (7/8) Epoch 8, batch 43800, loss[loss=2.611, over 700.00 frames. , ppl: 13.616162395921748] tot_loss[loss=2.276, over 5519725.26 frames. , ppl: 9.73405545163529], batch size: 70
+2022-12-13 01:03:12,894 INFO [train.py:421] (7/8) Epoch 8, batch 44000, loss[loss=2.64, over 910.00 frames. , ppl: 14.019023098395525] tot_loss[loss=2.275, over 5525609.88 frames. , ppl: 9.732399483046365], batch size: 70
+2022-12-13 01:03:12,894 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 01:03:13,638 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.269, over 211138.00 frames. , ppl: 9.674165532792536
+2022-12-13 01:04:54,834 INFO [train.py:421] (7/8) Epoch 8, batch 44200, loss[loss=2.397, over 910.00 frames. , ppl: 10.985434144696203] tot_loss[loss=2.275, over 5551562.37 frames. , ppl: 9.726245604168316], batch size: 70
+2022-12-13 01:06:33,910 INFO [train.py:421] (7/8) Epoch 8, batch 44400, loss[loss=2.246, over 3640.00 frames. , ppl: 9.45282093193701] tot_loss[loss=2.275, over 5555935.34 frames. , ppl: 9.729365279662947], batch size: 70
+2022-12-13 01:08:12,907 INFO [train.py:421] (7/8) Epoch 8, batch 44600, loss[loss=2.272, over 3080.00 frames. , ppl: 9.70074654531309] tot_loss[loss=2.276, over 5535996.85 frames. , ppl: 9.7329058312176], batch size: 70
+2022-12-13 01:09:58,345 INFO [train.py:421] (7/8) Epoch 8, batch 44800, loss[loss=2.808, over 630.00 frames. , ppl: 16.579671800383366] tot_loss[loss=2.275, over 5551675.35 frames. , ppl: 9.727493777789743], batch size: 70
+2022-12-13 01:11:44,374 INFO [train.py:421] (7/8) Epoch 8, batch 45000, loss[loss=2.396, over 1400.00 frames. , ppl: 10.974852454252174] tot_loss[loss=2.274, over 5585012.56 frames. , ppl: 9.714919739372595], batch size: 70
+2022-12-13 01:11:44,375 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 01:11:45,133 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.269, over 211138.00 frames. , ppl: 9.674410382020383
+2022-12-13 01:13:24,886 INFO [train.py:421] (7/8) Epoch 8, batch 45200, loss[loss=2.406, over 1820.00 frames. , ppl: 11.089983863654444] tot_loss[loss=2.274, over 5558753.98 frames. , ppl: 9.721078361535621], batch size: 70
+2022-12-13 01:15:00,538 INFO [train.py:421] (7/8) Epoch 8, batch 45400, loss[loss=2.167, over 4060.00 frames. , ppl: 8.7327532969181] tot_loss[loss=2.275, over 5538666.65 frames. , ppl: 9.726023547843676], batch size: 70
+2022-12-13 01:16:39,284 INFO [train.py:421] (7/8) Epoch 8, batch 45600, loss[loss=2.337, over 1750.00 frames. , ppl: 10.355154085125047] tot_loss[loss=2.275, over 5543992.52 frames. , ppl: 9.724391045652805], batch size: 70
+2022-12-13 01:18:18,207 INFO [train.py:421] (7/8) Epoch 8, batch 45800, loss[loss=2.347, over 1400.00 frames. , ppl: 10.454727505399468] tot_loss[loss=2.276, over 5512353.58 frames. , ppl: 9.74048487136631], batch size: 70
+2022-12-13 01:19:57,221 INFO [train.py:421] (7/8) Epoch 8, batch 46000, loss[loss=2.498, over 840.00 frames. , ppl: 12.160592801401526] tot_loss[loss=2.275, over 5548181.47 frames. , ppl: 9.72975474224422], batch size: 70
+2022-12-13 01:19:57,221 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 01:19:57,983 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.271, over 211138.00 frames. , ppl: 9.68747512264899
+2022-12-13 01:21:36,883 INFO [train.py:421] (7/8) Epoch 8, batch 46200, loss[loss=2.185, over 6790.00 frames. , ppl: 8.889771929870486] tot_loss[loss=2.276, over 5519908.04 frames. , ppl: 9.734499812964831], batch size: 70
+2022-12-13 01:23:16,620 INFO [train.py:421] (7/8) Epoch 8, batch 46400, loss[loss=2.637, over 1050.00 frames. , ppl: 13.973034585753219] tot_loss[loss=2.276, over 5524488.70 frames. , ppl: 9.74228700678811], batch size: 70
+2022-12-13 01:24:55,149 INFO [train.py:421] (7/8) Epoch 8, batch 46600, loss[loss=2.469, over 1610.00 frames. , ppl: 11.815813359313575] tot_loss[loss=2.277, over 5489544.52 frames. , ppl: 9.751485833313936], batch size: 70
+2022-12-13 01:26:38,480 INFO [train.py:421] (7/8) Epoch 8, batch 46800, loss[loss=2.379, over 1540.00 frames. , ppl: 10.789385942671563] tot_loss[loss=2.278, over 5485664.33 frames. , ppl: 9.756882383413451], batch size: 70
+2022-12-13 01:28:17,303 INFO [train.py:421] (7/8) Epoch 8, batch 47000, loss[loss=2.624, over 770.00 frames. , ppl: 13.796651978370257] tot_loss[loss=2.276, over 5526654.56 frames. , ppl: 9.740060221394552], batch size: 70
+2022-12-13 01:28:17,303 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 01:28:18,064 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.27, over 211138.00 frames. , ppl: 9.67573496626884
+2022-12-13 01:29:59,145 INFO [train.py:421] (7/8) Epoch 8, batch 47200, loss[loss=2.411, over 1050.00 frames. , ppl: 11.145181527075144] tot_loss[loss=2.277, over 5509756.06 frames. , ppl: 9.746912788124813], batch size: 70
+2022-12-13 01:31:41,109 INFO [train.py:421] (7/8) Epoch 8, batch 47400, loss[loss=2.331, over 1750.00 frames. , ppl: 10.291138685239805] tot_loss[loss=2.278, over 5498723.30 frames. , ppl: 9.753115530553844], batch size: 70
+2022-12-13 01:33:21,452 INFO [train.py:421] (7/8) Epoch 8, batch 47600, loss[loss=2.298, over 3920.00 frames. , ppl: 9.954214744476936] tot_loss[loss=2.279, over 5471338.24 frames. , ppl: 9.77001237934888], batch size: 70
+2022-12-13 01:35:04,433 INFO [train.py:421] (7/8) Epoch 8, batch 47800, loss[loss=2.882, over 630.00 frames. , ppl: 17.849599402524213] tot_loss[loss=2.279, over 5484832.28 frames. , ppl: 9.762180542060685], batch size: 70
+2022-12-13 01:36:41,912 INFO [train.py:421] (7/8) Epoch 8, batch 48000, loss[loss=2.464, over 980.00 frames. , ppl: 11.752172133579363] tot_loss[loss=2.278, over 5484667.10 frames. , ppl: 9.759991298641141], batch size: 70
+2022-12-13 01:36:41,913 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 01:36:42,686 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.268, over 211138.00 frames. , ppl: 9.664405251487315
+2022-12-13 01:38:24,558 INFO [train.py:421] (7/8) Epoch 8, batch 48200, loss[loss=2.159, over 5320.00 frames. , ppl: 8.660351292055866] tot_loss[loss=2.278, over 5481790.73 frames. , ppl: 9.76010636470773], batch size: 70
+2022-12-13 01:40:06,223 INFO [train.py:421] (7/8) Epoch 8, batch 48400, loss[loss=2.387, over 3360.00 frames. , ppl: 10.88107076395812] tot_loss[loss=2.279, over 5471425.12 frames. , ppl: 9.765776194582415], batch size: 70
+2022-12-13 01:41:49,538 INFO [train.py:421] (7/8) Epoch 8, batch 48600, loss[loss=2.234, over 2310.00 frames. , ppl: 9.33621262663395] tot_loss[loss=2.278, over 5503622.35 frames. , ppl: 9.758556747268786], batch size: 70
+2022-12-13 01:43:30,069 INFO [train.py:421] (7/8) Epoch 8, batch 48800, loss[loss=2.349, over 1330.00 frames. , ppl: 10.476302171352149] tot_loss[loss=2.279, over 5493604.33 frames. , ppl: 9.764696737487466], batch size: 70
+2022-12-13 01:45:08,312 INFO [train.py:421] (7/8) Epoch 8, batch 49000, loss[loss=2.325, over 2380.00 frames. , ppl: 10.221717167782039] tot_loss[loss=2.281, over 5424339.66 frames. , ppl: 9.784586858815034], batch size: 70
+2022-12-13 01:45:08,312 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 01:45:09,059 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.269, over 211138.00 frames. , ppl: 9.66599885304498
+2022-12-13 01:46:48,495 INFO [train.py:421] (7/8) Epoch 8, batch 49200, loss[loss=2.435, over 1190.00 frames. , ppl: 11.42089651658515] tot_loss[loss=2.281, over 5436102.80 frames. , ppl: 9.783164177457422], batch size: 70
+2022-12-13 01:48:27,304 INFO [train.py:421] (7/8) Epoch 8, batch 49400, loss[loss=2.886, over 630.00 frames. , ppl: 17.92898036175814] tot_loss[loss=2.28, over 5472885.47 frames. , ppl: 9.77237201560249], batch size: 70
+2022-12-13 01:50:08,163 INFO [train.py:421] (7/8) Epoch 8, batch 49600, loss[loss=2.424, over 1330.00 frames. , ppl: 11.288921920259158] tot_loss[loss=2.279, over 5465653.28 frames. , ppl: 9.770885727075033], batch size: 70
+2022-12-13 01:51:45,764 INFO [train.py:421] (7/8) Epoch 8, batch 49800, loss[loss=2.722, over 840.00 frames. , ppl: 15.205382249931388] tot_loss[loss=2.28, over 5431337.96 frames. , ppl: 9.7746893794862], batch size: 70
+2022-12-13 01:53:28,038 INFO [train.py:421] (7/8) Epoch 8, batch 50000, loss[loss=2.234, over 4480.00 frames. , ppl: 9.338235767855297] tot_loss[loss=2.279, over 5484070.83 frames. , ppl: 9.764259241721804], batch size: 70
+2022-12-13 01:53:28,039 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 01:53:28,798 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.267, over 211138.00 frames. , ppl: 9.6543676004614
+2022-12-13 01:55:10,394 INFO [train.py:421] (7/8) Epoch 8, batch 50200, loss[loss=2.255, over 2870.00 frames. , ppl: 9.535311479549188] tot_loss[loss=2.279, over 5487029.22 frames. , ppl: 9.76330106395409], batch size: 70
+2022-12-13 01:56:54,451 INFO [train.py:421] (7/8) Epoch 8, batch 50400, loss[loss=3.297, over 490.00 frames. , ppl: 27.024031417441332] tot_loss[loss=2.279, over 5493967.91 frames. , ppl: 9.765713564503526], batch size: 70
+2022-12-13 01:58:36,243 INFO [train.py:421] (7/8) Epoch 8, batch 50600, loss[loss=2.399, over 1890.00 frames. , ppl: 11.014823995296355] tot_loss[loss=2.277, over 5549436.89 frames. , ppl: 9.747232414154686], batch size: 70
+2022-12-13 02:00:17,758 INFO [train.py:421] (7/8) Epoch 8, batch 50800, loss[loss=2.198, over 3850.00 frames. , ppl: 9.007961219170054] tot_loss[loss=2.279, over 5518226.72 frames. , ppl: 9.763351738335654], batch size: 70
+2022-12-13 02:01:59,730 INFO [train.py:421] (7/8) Epoch 8, batch 51000, loss[loss=2.361, over 1120.00 frames. , ppl: 10.597983145559434] tot_loss[loss=2.278, over 5556601.99 frames. , ppl: 9.756143243561297], batch size: 70
+2022-12-13 02:01:59,730 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 02:02:00,491 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.268, over 211138.00 frames. , ppl: 9.66433230115276
+2022-12-13 02:03:40,185 INFO [train.py:421] (7/8) Epoch 8, batch 51200, loss[loss=2.219, over 2100.00 frames. , ppl: 9.194875319466442] tot_loss[loss=2.277, over 5555434.69 frames. , ppl: 9.752233123770555], batch size: 70
+2022-12-13 02:05:20,067 INFO [train.py:421] (7/8) Epoch 8, batch 51400, loss[loss=2.328, over 1190.00 frames. , ppl: 10.252534122046674] tot_loss[loss=2.278, over 5512103.93 frames. , ppl: 9.75777148249264], batch size: 70
+2022-12-13 02:07:01,076 INFO [train.py:421] (7/8) Epoch 8, batch 51600, loss[loss=2.13, over 11410.00 frames. , ppl: 8.41681507215559] tot_loss[loss=2.278, over 5500201.76 frames. , ppl: 9.756498277202716], batch size: 70
+2022-12-13 02:08:42,083 INFO [train.py:421] (7/8) Epoch 8, batch 51800, loss[loss=2.36, over 1330.00 frames. , ppl: 10.59266280637069] tot_loss[loss=2.277, over 5494626.21 frames. , ppl: 9.752136648158576], batch size: 70
+2022-12-13 02:10:19,803 INFO [train.py:421] (7/8) Epoch 8, batch 52000, loss[loss=2.213, over 3780.00 frames. , ppl: 9.145047984785489] tot_loss[loss=2.276, over 5543191.48 frames. , ppl: 9.737650804344183], batch size: 70
+2022-12-13 02:10:19,804 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 02:10:20,563 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.269, over 211138.00 frames. , ppl: 9.669551784931777
+2022-12-13 02:11:58,347 INFO [train.py:421] (7/8) Epoch 8, batch 52200, loss[loss=2.57, over 1050.00 frames. , ppl: 13.059998858687281] tot_loss[loss=2.276, over 5515726.23 frames. , ppl: 9.740885222401557], batch size: 70
+2022-12-13 02:13:38,891 INFO [train.py:421] (7/8) Epoch 8, batch 52400, loss[loss=2.484, over 840.00 frames. , ppl: 11.985436385323467] tot_loss[loss=2.277, over 5509299.06 frames. , ppl: 9.744023087469731], batch size: 70
+2022-12-13 02:15:21,732 INFO [train.py:421] (7/8) Epoch 8, batch 52600, loss[loss=2.303, over 1820.00 frames. , ppl: 10.001079717287128] tot_loss[loss=2.278, over 5474999.99 frames. , ppl: 9.759779554316118], batch size: 70
+2022-12-13 02:17:02,387 INFO [train.py:421] (7/8) Epoch 8, batch 52800, loss[loss=2.219, over 2170.00 frames. , ppl: 9.201829442648627] tot_loss[loss=2.278, over 5470393.78 frames. , ppl: 9.761570852603306], batch size: 70
+2022-12-13 02:18:40,327 INFO [train.py:421] (7/8) Epoch 8, batch 53000, loss[loss=2.37, over 1890.00 frames. , ppl: 10.69775046172395] tot_loss[loss=2.279, over 5416654.82 frames. , ppl: 9.770529784016725], batch size: 70
+2022-12-13 02:18:40,327 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 02:18:41,091 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.271, over 211138.00 frames. , ppl: 9.68564430928278
+2022-12-13 02:20:19,614 INFO [train.py:421] (7/8) Epoch 8, batch 53200, loss[loss=2.349, over 1260.00 frames. , ppl: 10.478465213996207] tot_loss[loss=2.279, over 5429345.72 frames. , ppl: 9.767725398849132], batch size: 70
+2022-12-13 02:21:58,982 INFO [train.py:421] (7/8) Epoch 8, batch 53400, loss[loss=2.409, over 1120.00 frames. , ppl: 11.123752480698508] tot_loss[loss=2.279, over 5431729.46 frames. , ppl: 9.76526278717725], batch size: 70
+2022-12-13 02:23:40,436 INFO [train.py:421] (7/8) Epoch 8, batch 53600, loss[loss=2.206, over 2800.00 frames. , ppl: 9.078097158273792] tot_loss[loss=2.279, over 5427346.25 frames. , ppl: 9.76558422410375], batch size: 70
+2022-12-13 02:25:20,305 INFO [train.py:421] (7/8) Epoch 8, batch 53800, loss[loss=2.265, over 2450.00 frames. , ppl: 9.628288044620671] tot_loss[loss=2.28, over 5390898.48 frames. , ppl: 9.771829733470822], batch size: 70
+2022-12-13 02:26:59,832 INFO [train.py:421] (7/8) Epoch 8, batch 54000, loss[loss=2.266, over 1960.00 frames. , ppl: 9.638466485472767] tot_loss[loss=2.28, over 5367450.99 frames. , ppl: 9.773124537419562], batch size: 70
+2022-12-13 02:26:59,833 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 02:27:00,592 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.268, over 211138.00 frames. , ppl: 9.66121883652427
+2022-12-13 02:28:44,770 INFO [train.py:421] (7/8) Epoch 8, batch 54200, loss[loss=2.234, over 3850.00 frames. , ppl: 9.341201292520005] tot_loss[loss=2.28, over 5376515.11 frames. , ppl: 9.777186185075793], batch size: 70
+2022-12-13 02:30:23,571 INFO [train.py:421] (7/8) Epoch 8, batch 54400, loss[loss=2.145, over 8400.00 frames. , ppl: 8.545648850382142] tot_loss[loss=2.282, over 5332838.39 frames. , ppl: 9.795272819885556], batch size: 70
+2022-12-13 02:32:02,933 INFO [train.py:421] (7/8) Epoch 8, batch 54600, loss[loss=2.272, over 8470.00 frames. , ppl: 9.700825397305756] tot_loss[loss=2.28, over 5379165.28 frames. , ppl: 9.780642460962703], batch size: 70
+2022-12-13 02:33:42,229 INFO [train.py:421] (7/8) Epoch 8, batch 54800, loss[loss=2.216, over 4760.00 frames. , ppl: 9.173375409582894] tot_loss[loss=2.279, over 5440388.84 frames. , ppl: 9.768607762369323], batch size: 70
+2022-12-13 02:35:25,399 INFO [train.py:421] (7/8) Epoch 8, batch 55000, loss[loss=2.219, over 2450.00 frames. , ppl: 9.20114896868932] tot_loss[loss=2.279, over 5436597.56 frames. , ppl: 9.762649036562497], batch size: 70
+2022-12-13 02:35:25,400 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 02:35:26,159 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.269, over 211138.00 frames. , ppl: 9.668597244433377
+2022-12-13 02:37:08,638 INFO [train.py:421] (7/8) Epoch 8, batch 55200, loss[loss=2.286, over 2870.00 frames. , ppl: 9.833372901830108] tot_loss[loss=2.276, over 5522065.54 frames. , ppl: 9.736833311460785], batch size: 70
+2022-12-13 02:38:47,771 INFO [train.py:421] (7/8) Epoch 8, batch 55400, loss[loss=2.22, over 4760.00 frames. , ppl: 9.21173172424874] tot_loss[loss=2.275, over 5527310.04 frames. , ppl: 9.73176897114508], batch size: 70
+2022-12-13 02:40:28,429 INFO [train.py:421] (7/8) Epoch 8, batch 55600, loss[loss=2.481, over 1750.00 frames. , ppl: 11.948116617355439] tot_loss[loss=2.277, over 5488213.99 frames. , ppl: 9.74330983520655], batch size: 70
+2022-12-13 02:42:10,534 INFO [train.py:421] (7/8) Epoch 8, batch 55800, loss[loss=2.24, over 4760.00 frames. , ppl: 9.391603574758348] tot_loss[loss=2.276, over 5523699.51 frames. , ppl: 9.734316003929106], batch size: 70
+2022-12-13 02:43:52,137 INFO [train.py:421] (7/8) Epoch 8, batch 56000, loss[loss=3.077, over 490.00 frames. , ppl: 21.68453039052722] tot_loss[loss=2.275, over 5562036.54 frames. , ppl: 9.729092090237243], batch size: 70
+2022-12-13 02:43:52,138 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 02:43:52,898 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.27, over 211138.00 frames. , ppl: 9.676379424179105
+2022-12-13 02:45:35,149 INFO [train.py:421] (7/8) Epoch 8, batch 56200, loss[loss=3.546, over 420.00 frames. , ppl: 34.67528525209373] tot_loss[loss=2.275, over 5600394.54 frames. , ppl: 9.72308330922738], batch size: 70
+2022-12-13 02:47:16,352 INFO [train.py:421] (7/8) Epoch 8, batch 56400, loss[loss=2.311, over 2310.00 frames. , ppl: 10.086325380462092] tot_loss[loss=2.274, over 5621253.54 frames. , ppl: 9.718555663522446], batch size: 70
+2022-12-13 02:48:53,786 INFO [train.py:421] (7/8) Epoch 8, batch 56600, loss[loss=2.749, over 630.00 frames. , ppl: 15.621344837355359] tot_loss[loss=2.275, over 5603680.91 frames. , ppl: 9.723152535075288], batch size: 70
+2022-12-13 02:50:34,340 INFO [train.py:421] (7/8) Epoch 8, batch 56800, loss[loss=2.161, over 4620.00 frames. , ppl: 8.678127781456558] tot_loss[loss=2.274, over 5643941.48 frames. , ppl: 9.714919109496241], batch size: 70
+2022-12-13 02:52:17,207 INFO [train.py:421] (7/8) Epoch 8, batch 57000, loss[loss=2.478, over 1120.00 frames. , ppl: 11.920324572290433] tot_loss[loss=2.274, over 5615259.31 frames. , ppl: 9.718944381124588], batch size: 70
+2022-12-13 02:52:17,208 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 02:52:17,969 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.268, over 211138.00 frames. , ppl: 9.66042525657999
+2022-12-13 02:54:00,656 INFO [train.py:421] (7/8) Epoch 8, batch 57200, loss[loss=2.39, over 1890.00 frames. , ppl: 10.91745098224704] tot_loss[loss=2.274, over 5630824.25 frames. , ppl: 9.717356147254916], batch size: 70
+2022-12-13 02:55:44,459 INFO [train.py:421] (7/8) Epoch 8, batch 57400, loss[loss=2.211, over 2660.00 frames. , ppl: 9.12338543457436] tot_loss[loss=2.274, over 5626738.34 frames. , ppl: 9.720950701896495], batch size: 70
+2022-12-13 02:57:27,577 INFO [train.py:421] (7/8) Epoch 8, batch 57600, loss[loss=2.241, over 4480.00 frames. , ppl: 9.404200412161453] tot_loss[loss=2.274, over 5627316.96 frames. , ppl: 9.71683638153298], batch size: 70
+2022-12-13 02:59:04,484 INFO [train.py:421] (7/8) Epoch 8, batch 57800, loss[loss=2.221, over 2450.00 frames. , ppl: 9.213623418978582] tot_loss[loss=2.274, over 5605134.39 frames. , ppl: 9.721119498782672], batch size: 70
+2022-12-13 03:00:43,921 INFO [train.py:421] (7/8) Epoch 8, batch 58000, loss[loss=2.478, over 1260.00 frames. , ppl: 11.914065167983567] tot_loss[loss=2.275, over 5584816.18 frames. , ppl: 9.727520288772679], batch size: 70
+2022-12-13 03:00:43,921 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 03:00:44,670 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.27, over 211138.00 frames. , ppl: 9.679271420376821
+2022-12-13 03:02:24,460 INFO [train.py:421] (7/8) Epoch 8, batch 58200, loss[loss=2.311, over 2100.00 frames. , ppl: 10.08039030761267] tot_loss[loss=2.274, over 5606954.88 frames. , ppl: 9.719974423467368], batch size: 70
+2022-12-13 03:04:02,656 INFO [train.py:421] (7/8) Epoch 8, batch 58400, loss[loss=5.002, over 280.00 frames. , ppl: 148.75868651394583] tot_loss[loss=2.274, over 5623793.22 frames. , ppl: 9.715202881510448], batch size: 70
+2022-12-13 03:05:40,980 INFO [train.py:421] (7/8) Epoch 8, batch 58600, loss[loss=3.304, over 490.00 frames. , ppl: 27.22497351149029] tot_loss[loss=2.274, over 5618971.80 frames. , ppl: 9.717932378923228], batch size: 70
+2022-12-13 03:07:18,317 INFO [train.py:421] (7/8) Epoch 8, batch 58800, loss[loss=2.288, over 3500.00 frames. , ppl: 9.855732764289272] tot_loss[loss=2.275, over 5572065.04 frames. , ppl: 9.730695940724392], batch size: 70
+2022-12-13 03:09:03,641 INFO [train.py:421] (7/8) Epoch 8, batch 59000, loss[loss=2.213, over 6790.00 frames. , ppl: 9.145815893510807] tot_loss[loss=2.276, over 5561810.57 frames. , ppl: 9.734690142548391], batch size: 70
+2022-12-13 03:09:03,641 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 03:09:04,370 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.269, over 211138.00 frames. , ppl: 9.666656969839083
+2022-12-13 03:10:48,155 INFO [train.py:421] (7/8) Epoch 8, batch 59200, loss[loss=2.42, over 910.00 frames. , ppl: 11.250146843476184] tot_loss[loss=2.276, over 5538459.03 frames. , ppl: 9.73611019158585], batch size: 70
+2022-12-13 03:12:28,732 INFO [train.py:421] (7/8) Epoch 8, batch 59400, loss[loss=2.182, over 4620.00 frames. , ppl: 8.86564650180592] tot_loss[loss=2.275, over 5568894.19 frames. , ppl: 9.72989269159655], batch size: 70
+2022-12-13 03:14:12,146 INFO [train.py:421] (7/8) Epoch 8, batch 59600, loss[loss=2.312, over 3780.00 frames. , ppl: 10.09177581900514] tot_loss[loss=2.273, over 5610475.62 frames. , ppl: 9.713242195389922], batch size: 70
+2022-12-13 03:15:48,388 INFO [train.py:421] (7/8) Epoch 8, batch 59800, loss[loss=2.574, over 1260.00 frames. , ppl: 13.121362326193488] tot_loss[loss=2.274, over 5598206.41 frames. , ppl: 9.721201509983462], batch size: 70
+2022-12-13 03:17:30,952 INFO [train.py:421] (7/8) Epoch 8, batch 60000, loss[loss=2.4, over 1050.00 frames. , ppl: 11.020129332380135] tot_loss[loss=2.274, over 5572005.42 frames. , ppl: 9.721123908466335], batch size: 70
+2022-12-13 03:17:30,953 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 03:17:31,713 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.269, over 211138.00 frames. , ppl: 9.674444747320207
+2022-12-13 03:19:10,631 INFO [train.py:421] (7/8) Epoch 8, batch 60200, loss[loss=2.42, over 1750.00 frames. , ppl: 11.243606603320009] tot_loss[loss=2.274, over 5593858.09 frames. , ppl: 9.716240745145695], batch size: 70
+2022-12-13 03:20:51,024 INFO [train.py:421] (7/8) Epoch 8, batch 60400, loss[loss=2.387, over 1260.00 frames. , ppl: 10.88388207456802] tot_loss[loss=2.274, over 5600978.84 frames. , ppl: 9.717358066386822], batch size: 70
+2022-12-13 03:22:28,012 INFO [train.py:421] (7/8) Epoch 8, batch 60600, loss[loss=2.209, over 4410.00 frames. , ppl: 9.109437855416585] tot_loss[loss=2.273, over 5597156.74 frames. , ppl: 9.712860603633999], batch size: 70
+2022-12-13 03:24:04,416 INFO [train.py:421] (7/8) Epoch 8, batch 60800, loss[loss=2.38, over 2030.00 frames. , ppl: 10.800149943629577] tot_loss[loss=2.275, over 5584297.09 frames. , ppl: 9.724154475649017], batch size: 70
+2022-12-13 03:25:46,107 INFO [train.py:421] (7/8) Epoch 8, batch 61000, loss[loss=2.186, over 5250.00 frames. , ppl: 8.897347176074485] tot_loss[loss=2.275, over 5575564.49 frames. , ppl: 9.7271706962064], batch size: 70
+2022-12-13 03:25:46,107 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 03:25:46,839 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.268, over 211138.00 frames. , ppl: 9.66320950762563
+2022-12-13 03:27:25,696 INFO [train.py:421] (7/8) Epoch 8, batch 61200, loss[loss=2.413, over 1260.00 frames. , ppl: 11.16451732079567] tot_loss[loss=2.275, over 5585074.12 frames. , ppl: 9.72786811293107], batch size: 70
+2022-12-13 03:29:02,363 INFO [train.py:421] (7/8) Epoch 8, batch 61400, loss[loss=2.593, over 840.00 frames. , ppl: 13.371353941141873] tot_loss[loss=2.276, over 5559759.46 frames. , ppl: 9.737052249722748], batch size: 70
+2022-12-13 03:30:39,176 INFO [train.py:421] (7/8) Epoch 8, batch 61600, loss[loss=2.38, over 1050.00 frames. , ppl: 10.806141499168813] tot_loss[loss=2.276, over 5537973.61 frames. , ppl: 9.739896955953178], batch size: 70
+2022-12-13 03:32:18,644 INFO [train.py:421] (7/8) Epoch 8, batch 61800, loss[loss=2.335, over 3080.00 frames. , ppl: 10.33206659705966] tot_loss[loss=2.276, over 5536227.51 frames. , ppl: 9.74022484956687], batch size: 70
+2022-12-13 03:33:59,899 INFO [train.py:421] (7/8) Epoch 8, batch 62000, loss[loss=2.384, over 1260.00 frames. , ppl: 10.844962721096683] tot_loss[loss=2.277, over 5514493.35 frames. , ppl: 9.746444835340823], batch size: 70
+2022-12-13 03:33:59,899 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 03:34:00,657 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.267, over 211138.00 frames. , ppl: 9.655050647650823
+2022-12-13 03:35:43,438 INFO [train.py:421] (7/8) Epoch 8, batch 62200, loss[loss=2.484, over 1120.00 frames. , ppl: 11.989175624553807] tot_loss[loss=2.277, over 5513098.47 frames. , ppl: 9.74900579901646], batch size: 70
+2022-12-13 03:37:22,823 INFO [train.py:421] (7/8) Epoch 8, batch 62400, loss[loss=2.176, over 10150.00 frames. , ppl: 8.808711943730867] tot_loss[loss=2.278, over 5491551.08 frames. , ppl: 9.753516959735864], batch size: 70
+2022-12-13 03:39:04,713 INFO [train.py:421] (7/8) Epoch 8, batch 62600, loss[loss=2.184, over 5810.00 frames. , ppl: 8.879033854485613] tot_loss[loss=2.277, over 5530696.02 frames. , ppl: 9.743614904195553], batch size: 70
+2022-12-13 03:40:42,500 INFO [train.py:421] (7/8) Epoch 8, batch 62800, loss[loss=2.241, over 5530.00 frames. , ppl: 9.405649658952571] tot_loss[loss=2.277, over 5544571.73 frames. , ppl: 9.749225687688678], batch size: 70
+2022-12-13 03:42:19,090 INFO [train.py:421] (7/8) Epoch 8, batch 63000, loss[loss=2.495, over 1190.00 frames. , ppl: 12.124370413704133] tot_loss[loss=2.279, over 5476075.76 frames. , ppl: 9.765379627725922], batch size: 70
+2022-12-13 03:42:19,091 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 03:42:19,855 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.268, over 211138.00 frames. , ppl: 9.660179331522313
+2022-12-13 03:44:04,025 INFO [train.py:421] (7/8) Epoch 8, batch 63200, loss[loss=3.023, over 700.00 frames. , ppl: 20.554201239652734] tot_loss[loss=2.28, over 5463013.98 frames. , ppl: 9.773503198097407], batch size: 70
+2022-12-13 03:45:42,070 INFO [train.py:421] (7/8) Epoch 8, batch 63400, loss[loss=2.211, over 3990.00 frames. , ppl: 9.124250752044917] tot_loss[loss=2.279, over 5452901.59 frames. , ppl: 9.771010001658382], batch size: 70
+2022-12-13 03:47:24,377 INFO [train.py:421] (7/8) Epoch 8, batch 63600, loss[loss=2.296, over 2730.00 frames. , ppl: 9.932121805022737] tot_loss[loss=2.279, over 5470155.01 frames. , ppl: 9.769970931302767], batch size: 70
+2022-12-13 03:49:06,228 INFO [train.py:421] (7/8) Epoch 8, batch 63800, loss[loss=2.699, over 910.00 frames. , ppl: 14.858748457922193] tot_loss[loss=2.278, over 5486491.74 frames. , ppl: 9.759208651688729], batch size: 70
+2022-12-13 03:50:46,501 INFO [train.py:421] (7/8) Epoch 8, batch 64000, loss[loss=2.297, over 5040.00 frames. , ppl: 9.94301362134307] tot_loss[loss=2.278, over 5468650.14 frames. , ppl: 9.759527133759759], batch size: 70
+2022-12-13 03:50:46,501 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 03:50:47,232 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.269, over 211138.00 frames. , ppl: 9.672815393681503
+2022-12-13 03:52:29,209 INFO [train.py:421] (7/8) Epoch 8, batch 64200, loss[loss=2.213, over 5110.00 frames. , ppl: 9.141442493158058] tot_loss[loss=2.278, over 5491694.69 frames. , ppl: 9.759114204083993], batch size: 70
+2022-12-13 03:54:10,489 INFO [train.py:421] (7/8) Epoch 8, batch 64400, loss[loss=2.3, over 2520.00 frames. , ppl: 9.974584448195339] tot_loss[loss=2.278, over 5482176.96 frames. , ppl: 9.7618901893987], batch size: 70
+2022-12-13 03:55:52,716 INFO [train.py:421] (7/8) Epoch 8, batch 64600, loss[loss=2.601, over 1400.00 frames. , ppl: 13.472418632064592] tot_loss[loss=2.278, over 5512482.81 frames. , ppl: 9.753305956511067], batch size: 70
+2022-12-13 03:57:33,029 INFO [train.py:421] (7/8) Epoch 8, batch 64800, loss[loss=2.21, over 5880.00 frames. , ppl: 9.115993148569508] tot_loss[loss=2.277, over 5505512.71 frames. , ppl: 9.75160129214367], batch size: 70
+2022-12-13 03:59:15,151 INFO [train.py:421] (7/8) Epoch 8, batch 65000, loss[loss=2.318, over 2450.00 frames. , ppl: 10.154548321016037] tot_loss[loss=2.278, over 5482204.76 frames. , ppl: 9.758039702665036], batch size: 70
+2022-12-13 03:59:15,152 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 03:59:15,897 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.268, over 211138.00 frames. , ppl: 9.65988194214127
+2022-12-13 04:00:56,720 INFO [train.py:421] (7/8) Epoch 8, batch 65200, loss[loss=2.399, over 1050.00 frames. , ppl: 11.00905276470196] tot_loss[loss=2.279, over 5464099.92 frames. , ppl: 9.763297283267578], batch size: 70
+2022-12-13 04:02:38,087 INFO [train.py:421] (7/8) Epoch 8, batch 65400, loss[loss=2.222, over 4270.00 frames. , ppl: 9.221636612014706] tot_loss[loss=2.278, over 5507829.91 frames. , ppl: 9.75503840470741], batch size: 70
+2022-12-13 04:04:12,154 INFO [train.py:421] (7/8) Epoch 8, batch 65600, loss[loss=2.182, over 4900.00 frames. , ppl: 8.862993428710737] tot_loss[loss=2.279, over 5465469.08 frames. , ppl: 9.765836584230147], batch size: 70
+2022-12-13 04:05:51,084 INFO [train.py:421] (7/8) Epoch 8, batch 65800, loss[loss=2.337, over 1750.00 frames. , ppl: 10.350878844011815] tot_loss[loss=2.278, over 5485266.59 frames. , ppl: 9.760924077915469], batch size: 70
+2022-12-13 04:07:30,795 INFO [train.py:421] (7/8) Epoch 8, batch 66000, loss[loss=2.141, over 8820.00 frames. , ppl: 8.50388515679154] tot_loss[loss=2.279, over 5477581.92 frames. , ppl: 9.764665299596539], batch size: 70
+2022-12-13 04:07:30,795 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 04:07:31,525 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.269, over 211138.00 frames. , ppl: 9.665475252994222
+2022-12-13 04:09:13,156 INFO [train.py:421] (7/8) Epoch 8, batch 66200, loss[loss=2.276, over 2450.00 frames. , ppl: 9.736078793528188] tot_loss[loss=2.278, over 5499029.49 frames. , ppl: 9.754142732433518], batch size: 70
+2022-12-13 04:10:50,317 INFO [train.py:421] (7/8) Epoch 8, batch 66400, loss[loss=2.221, over 2450.00 frames. , ppl: 9.215099891147515] tot_loss[loss=2.277, over 5514853.84 frames. , ppl: 9.747426268475447], batch size: 70
+2022-12-13 04:12:32,867 INFO [train.py:421] (7/8) Epoch 8, batch 66600, loss[loss=2.169, over 4200.00 frames. , ppl: 8.750870497095919] tot_loss[loss=2.278, over 5490644.99 frames. , ppl: 9.754083521122096], batch size: 70
+2022-12-13 04:14:11,381 INFO [train.py:421] (7/8) Epoch 8, batch 66800, loss[loss=3.531, over 420.00 frames. , ppl: 34.14958329170099] tot_loss[loss=2.28, over 5459332.58 frames. , ppl: 9.772493140749125], batch size: 70
+2022-12-13 04:15:48,911 INFO [train.py:421] (7/8) Epoch 8, batch 67000, loss[loss=2.223, over 3850.00 frames. , ppl: 9.23476430423233] tot_loss[loss=2.279, over 5487649.91 frames. , ppl: 9.770417988918553], batch size: 70
+2022-12-13 04:15:48,912 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 04:15:49,642 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.267, over 211138.00 frames. , ppl: 9.651940173203029
+2022-12-13 04:17:32,965 INFO [train.py:421] (7/8) Epoch 8, batch 67200, loss[loss=2.433, over 1470.00 frames. , ppl: 11.388095158995519] tot_loss[loss=2.278, over 5522848.79 frames. , ppl: 9.75469494093801], batch size: 70
+2022-12-13 04:19:12,944 INFO [train.py:421] (7/8) Epoch 8, batch 67400, loss[loss=2.373, over 1680.00 frames. , ppl: 10.72476332177042] tot_loss[loss=2.278, over 5509604.51 frames. , ppl: 9.757166649764622], batch size: 70
+2022-12-13 04:20:51,772 INFO [train.py:421] (7/8) Epoch 8, batch 67600, loss[loss=2.323, over 1680.00 frames. , ppl: 10.20955011169138] tot_loss[loss=2.278, over 5488992.14 frames. , ppl: 9.75991489975973], batch size: 70
+2022-12-13 04:22:29,391 INFO [train.py:421] (7/8) Epoch 8, batch 67800, loss[loss=2.397, over 1820.00 frames. , ppl: 10.987296959936055] tot_loss[loss=2.279, over 5484589.92 frames. , ppl: 9.764492992051522], batch size: 70
+2022-12-13 04:24:11,412 INFO [train.py:421] (7/8) Epoch 8, batch 68000, loss[loss=2.33, over 2520.00 frames. , ppl: 10.279981407854235] tot_loss[loss=2.279, over 5492908.41 frames. , ppl: 9.762717603955284], batch size: 70
+2022-12-13 04:24:11,413 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 04:24:12,154 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.269, over 211138.00 frames. , ppl: 9.674181283141165
+2022-12-13 04:25:51,983 INFO [train.py:421] (7/8) Epoch 8, batch 68200, loss[loss=2.339, over 2730.00 frames. , ppl: 10.366293700506166] tot_loss[loss=2.278, over 5499176.64 frames. , ppl: 9.756729271439616], batch size: 70
+2022-12-13 04:27:29,340 INFO [train.py:421] (7/8) Epoch 8, batch 68400, loss[loss=2.26, over 4480.00 frames. , ppl: 9.58092066668981] tot_loss[loss=2.278, over 5486467.95 frames. , ppl: 9.757405040657321], batch size: 70
+2022-12-13 04:29:12,425 INFO [train.py:421] (7/8) Epoch 8, batch 68600, loss[loss=2.304, over 2940.00 frames. , ppl: 10.015522180191924] tot_loss[loss=2.279, over 5465288.14 frames. , ppl: 9.768551427611637], batch size: 70
+2022-12-13 04:30:48,902 INFO [train.py:421] (7/8) Epoch 8, batch 68800, loss[loss=2.379, over 1890.00 frames. , ppl: 10.793225305691728] tot_loss[loss=2.279, over 5455745.97 frames. , ppl: 9.771142775302549], batch size: 70
+2022-12-13 04:32:30,673 INFO [train.py:421] (7/8) Epoch 8, batch 69000, loss[loss=2.508, over 1120.00 frames. , ppl: 12.277699870524186] tot_loss[loss=2.278, over 5502541.85 frames. , ppl: 9.756401449940505], batch size: 70
+2022-12-13 04:32:30,673 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 04:32:31,419 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.265, over 211138.00 frames. , ppl: 9.629115969513046
+2022-12-13 04:34:10,755 INFO [train.py:421] (7/8) Epoch 8, batch 69200, loss[loss=2.338, over 2380.00 frames. , ppl: 10.364225614430925] tot_loss[loss=2.278, over 5488676.38 frames. , ppl: 9.759293553888318], batch size: 70
+2022-12-13 04:35:51,613 INFO [train.py:421] (7/8) Epoch 8, batch 69400, loss[loss=2.215, over 4480.00 frames. , ppl: 9.16382223944153] tot_loss[loss=2.278, over 5492182.77 frames. , ppl: 9.761211615715848], batch size: 70
+2022-12-13 04:37:25,626 INFO [train.py:421] (7/8) Epoch 8, batch 69600, loss[loss=2.253, over 3150.00 frames. , ppl: 9.516463640819111] tot_loss[loss=2.278, over 5484170.39 frames. , ppl: 9.756973218750996], batch size: 70
+2022-12-13 04:39:03,669 INFO [train.py:421] (7/8) Epoch 8, batch 69800, loss[loss=2.271, over 2030.00 frames. , ppl: 9.692604252981893] tot_loss[loss=2.279, over 5488517.08 frames. , ppl: 9.763341213244036], batch size: 70
+2022-12-13 04:40:44,764 INFO [train.py:421] (7/8) Epoch 8, batch 70000, loss[loss=2.307, over 2310.00 frames. , ppl: 10.043700702831721] tot_loss[loss=2.278, over 5505944.42 frames. , ppl: 9.75835995225094], batch size: 70
+2022-12-13 04:40:44,764 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 04:40:45,525 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.267, over 211138.00 frames. , ppl: 9.655207841082497
+2022-12-13 04:42:28,626 INFO [train.py:421] (7/8) Epoch 8, batch 70200, loss[loss=2.507, over 1260.00 frames. , ppl: 12.264076013589563] tot_loss[loss=2.278, over 5509916.67 frames. , ppl: 9.752852263010242], batch size: 70
+2022-12-13 04:44:05,958 INFO [train.py:421] (7/8) Epoch 8, batch 70400, loss[loss=3.202, over 490.00 frames. , ppl: 24.57236748590846] tot_loss[loss=2.278, over 5478603.18 frames. , ppl: 9.761458465724939], batch size: 70
+2022-12-13 04:45:49,716 INFO [train.py:421] (7/8) Epoch 8, batch 70600, loss[loss=2.198, over 6090.00 frames. , ppl: 9.00311348263301] tot_loss[loss=2.277, over 5510952.86 frames. , ppl: 9.751701195066484], batch size: 70
+2022-12-13 04:47:27,338 INFO [train.py:421] (7/8) Epoch 8, batch 70800, loss[loss=2.305, over 2450.00 frames. , ppl: 10.023219352667788] tot_loss[loss=2.279, over 5490667.94 frames. , ppl: 9.763480798070919], batch size: 70
+2022-12-13 04:49:05,281 INFO [train.py:421] (7/8) Epoch 8, batch 71000, loss[loss=2.241, over 2870.00 frames. , ppl: 9.40111988744536] tot_loss[loss=2.279, over 5497976.56 frames. , ppl: 9.769766299598112], batch size: 70
+2022-12-13 04:49:05,282 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 04:49:06,043 INFO [train.py:452] (7/8) Epoch 8, validation: loss=2.268, over 211138.00 frames. , ppl: 9.664858700229336
+2022-12-13 04:50:47,498 INFO [train.py:421] (7/8) Epoch 8, batch 71200, loss[loss=2.251, over 4410.00 frames. , ppl: 9.49303180933652] tot_loss[loss=2.279, over 5497355.48 frames. , ppl: 9.771267726569903], batch size: 70
+2022-12-13 04:52:24,901 INFO [train.py:421] (7/8) Epoch 8, batch 71400, loss[loss=2.306, over 1820.00 frames. , ppl: 10.037297953078237] tot_loss[loss=2.28, over 5473221.46 frames. , ppl: 9.776886717945299], batch size: 70
+2022-12-13 04:54:03,434 INFO [train.py:421] (7/8) Epoch 8, batch 71600, loss[loss=2.254, over 2590.00 frames. , ppl: 9.52398275909254] tot_loss[loss=2.28, over 5461154.83 frames. , ppl: 9.777979593599097], batch size: 70
+2022-12-13 04:55:49,182 INFO [train.py:421] (7/8) Epoch 8, batch 71800, loss[loss=2.127, over 5460.00 frames. , ppl: 8.390369712299384] tot_loss[loss=2.279, over 5482395.51 frames. , ppl: 9.769616684006156], batch size: 70
+2022-12-13 04:57:06,856 INFO [train.py:421] (7/8) Epoch 9, batch 0, loss[loss=3.665, over 420.00 frames. , ppl: 39.0572077514761] tot_loss[loss=3.665, over 420.00 frames. , ppl: 39.0572077514761], batch size: 70
+2022-12-13 04:58:47,672 INFO [train.py:421] (7/8) Epoch 9, batch 200, loss[loss=2.263, over 2310.00 frames. , ppl: 9.60853502702203] tot_loss[loss=2.26, over 544483.53 frames. , ppl: 9.58467712195292], batch size: 70
+2022-12-13 05:00:29,925 INFO [train.py:421] (7/8) Epoch 9, batch 400, loss[loss=2.336, over 1540.00 frames. , ppl: 10.34008922206356] tot_loss[loss=2.265, over 1016535.55 frames. , ppl: 9.628676390469817], batch size: 70
+2022-12-13 05:02:09,653 INFO [train.py:421] (7/8) Epoch 9, batch 600, loss[loss=2.494, over 1120.00 frames. , ppl: 12.114859073696483] tot_loss[loss=2.264, over 1469136.08 frames. , ppl: 9.624368024555176], batch size: 70
+2022-12-13 05:03:48,158 INFO [train.py:421] (7/8) Epoch 9, batch 800, loss[loss=2.124, over 7700.00 frames. , ppl: 8.363753123823571] tot_loss[loss=2.265, over 1860792.45 frames. , ppl: 9.630167438657974], batch size: 70
+2022-12-13 05:05:26,195 INFO [train.py:421] (7/8) Epoch 9, batch 1000, loss[loss=2.335, over 1610.00 frames. , ppl: 10.329379105471185] tot_loss[loss=2.266, over 2210218.32 frames. , ppl: 9.641342275835711], batch size: 70
+2022-12-13 05:05:26,196 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 05:05:26,939 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.268, over 211138.00 frames. , ppl: 9.664010468014997
+2022-12-13 05:07:07,628 INFO [train.py:421] (7/8) Epoch 9, batch 1200, loss[loss=2.51, over 910.00 frames. , ppl: 12.305400166835526] tot_loss[loss=2.266, over 2544383.99 frames. , ppl: 9.639453190615065], batch size: 70
+2022-12-13 05:08:50,642 INFO [train.py:421] (7/8) Epoch 9, batch 1400, loss[loss=2.671, over 770.00 frames. , ppl: 14.459603804806678] tot_loss[loss=2.266, over 2825045.58 frames. , ppl: 9.641208370353931], batch size: 70
+2022-12-13 05:10:29,016 INFO [train.py:421] (7/8) Epoch 9, batch 1600, loss[loss=2.382, over 2100.00 frames. , ppl: 10.82370115761498] tot_loss[loss=2.267, over 3071448.74 frames. , ppl: 9.654793389992276], batch size: 70
+2022-12-13 05:12:07,732 INFO [train.py:421] (7/8) Epoch 9, batch 1800, loss[loss=2.193, over 5810.00 frames. , ppl: 8.958748733094044] tot_loss[loss=2.269, over 3278495.47 frames. , ppl: 9.668015026958903], batch size: 70
+2022-12-13 05:13:46,772 INFO [train.py:421] (7/8) Epoch 9, batch 2000, loss[loss=2.368, over 1890.00 frames. , ppl: 10.672398156102277] tot_loss[loss=2.268, over 3526905.65 frames. , ppl: 9.656462326607302], batch size: 70
+2022-12-13 05:13:46,773 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 05:13:47,536 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.269, over 211138.00 frames. , ppl: 9.667164894955036
+2022-12-13 05:15:30,257 INFO [train.py:421] (7/8) Epoch 9, batch 2200, loss[loss=2.279, over 2240.00 frames. , ppl: 9.770434734217922] tot_loss[loss=2.268, over 3726164.45 frames. , ppl: 9.658826699473188], batch size: 70
+2022-12-13 05:17:11,208 INFO [train.py:421] (7/8) Epoch 9, batch 2400, loss[loss=2.211, over 4270.00 frames. , ppl: 9.129017060408367] tot_loss[loss=2.269, over 3861519.58 frames. , ppl: 9.672037651214568], batch size: 70
+2022-12-13 05:18:52,166 INFO [train.py:421] (7/8) Epoch 9, batch 2600, loss[loss=2.312, over 3640.00 frames. , ppl: 10.092426438886855] tot_loss[loss=2.268, over 4023580.77 frames. , ppl: 9.66375826057798], batch size: 70
+2022-12-13 05:20:30,385 INFO [train.py:421] (7/8) Epoch 9, batch 2800, loss[loss=2.254, over 4130.00 frames. , ppl: 9.524592766592194] tot_loss[loss=2.268, over 4176197.81 frames. , ppl: 9.663397291250782], batch size: 70
+2022-12-13 05:22:11,119 INFO [train.py:421] (7/8) Epoch 9, batch 3000, loss[loss=2.24, over 4130.00 frames. , ppl: 9.389010450021752] tot_loss[loss=2.267, over 4318604.80 frames. , ppl: 9.651088617152551], batch size: 70
+2022-12-13 05:22:11,119 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 05:22:11,878 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.268, over 211138.00 frames. , ppl: 9.65743883465414
+2022-12-13 05:23:52,012 INFO [train.py:421] (7/8) Epoch 9, batch 3200, loss[loss=2.164, over 4550.00 frames. , ppl: 8.702613377911288] tot_loss[loss=2.268, over 4451464.22 frames. , ppl: 9.656252332812196], batch size: 70
+2022-12-13 05:25:30,714 INFO [train.py:421] (7/8) Epoch 9, batch 3400, loss[loss=2.396, over 980.00 frames. , ppl: 10.979779841823783] tot_loss[loss=2.269, over 4524193.33 frames. , ppl: 9.666589952479843], batch size: 70
+2022-12-13 05:27:10,002 INFO [train.py:421] (7/8) Epoch 9, batch 3600, loss[loss=2.349, over 1610.00 frames. , ppl: 10.475446103102982] tot_loss[loss=2.269, over 4608541.70 frames. , ppl: 9.670666127142425], batch size: 70
+2022-12-13 05:28:50,469 INFO [train.py:421] (7/8) Epoch 9, batch 3800, loss[loss=2.402, over 1470.00 frames. , ppl: 11.043721893100555] tot_loss[loss=2.268, over 4710176.90 frames. , ppl: 9.664048594295895], batch size: 70
+2022-12-13 05:30:30,356 INFO [train.py:421] (7/8) Epoch 9, batch 4000, loss[loss=2.292, over 3150.00 frames. , ppl: 9.89442602873462] tot_loss[loss=2.268, over 4818901.67 frames. , ppl: 9.65751844473072], batch size: 70
+2022-12-13 05:30:30,357 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 05:30:31,100 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.269, over 211138.00 frames. , ppl: 9.671714518344173
+2022-12-13 05:32:07,771 INFO [train.py:421] (7/8) Epoch 9, batch 4200, loss[loss=2.362, over 1400.00 frames. , ppl: 10.610705990473686] tot_loss[loss=2.267, over 4903032.10 frames. , ppl: 9.64998254562034], batch size: 70
+2022-12-13 05:33:45,393 INFO [train.py:421] (7/8) Epoch 9, batch 4400, loss[loss=2.31, over 2100.00 frames. , ppl: 10.06956757736753] tot_loss[loss=2.268, over 4939960.32 frames. , ppl: 9.65952919866371], batch size: 70
+2022-12-13 05:35:25,480 INFO [train.py:421] (7/8) Epoch 9, batch 4600, loss[loss=2.377, over 1960.00 frames. , ppl: 10.773625931653585] tot_loss[loss=2.268, over 5002821.29 frames. , ppl: 9.661322125744874], batch size: 70
+2022-12-13 05:37:03,952 INFO [train.py:421] (7/8) Epoch 9, batch 4800, loss[loss=2.208, over 2730.00 frames. , ppl: 9.097432691345015] tot_loss[loss=2.268, over 5052596.06 frames. , ppl: 9.664630381299892], batch size: 70
+2022-12-13 05:38:46,307 INFO [train.py:421] (7/8) Epoch 9, batch 5000, loss[loss=2.243, over 3150.00 frames. , ppl: 9.418321330861724] tot_loss[loss=2.269, over 5091730.00 frames. , ppl: 9.668181480939074], batch size: 70
+2022-12-13 05:38:46,308 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 05:38:47,053 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.268, over 211138.00 frames. , ppl: 9.655562250208732
+2022-12-13 05:40:30,507 INFO [train.py:421] (7/8) Epoch 9, batch 5200, loss[loss=2.148, over 5950.00 frames. , ppl: 8.570098965667317] tot_loss[loss=2.269, over 5154520.73 frames. , ppl: 9.666072537497822], batch size: 70
+2022-12-13 05:42:13,841 INFO [train.py:421] (7/8) Epoch 9, batch 5400, loss[loss=2.166, over 5530.00 frames. , ppl: 8.720305873433928] tot_loss[loss=2.268, over 5196691.85 frames. , ppl: 9.661042973537208], batch size: 70
+2022-12-13 05:43:55,319 INFO [train.py:421] (7/8) Epoch 9, batch 5600, loss[loss=2.562, over 910.00 frames. , ppl: 12.964262948899552] tot_loss[loss=2.268, over 5243411.22 frames. , ppl: 9.65716988834162], batch size: 70
+2022-12-13 05:45:33,975 INFO [train.py:421] (7/8) Epoch 9, batch 5800, loss[loss=2.387, over 1470.00 frames. , ppl: 10.878212453050766] tot_loss[loss=2.266, over 5316734.87 frames. , ppl: 9.643620197393515], batch size: 70
+2022-12-13 05:47:17,486 INFO [train.py:421] (7/8) Epoch 9, batch 6000, loss[loss=2.308, over 1890.00 frames. , ppl: 10.049990788357091] tot_loss[loss=2.266, over 5344118.34 frames. , ppl: 9.642812897969423], batch size: 70
+2022-12-13 05:47:17,487 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 05:47:18,250 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.269, over 211138.00 frames. , ppl: 9.66698032189641
+2022-12-13 05:48:59,184 INFO [train.py:421] (7/8) Epoch 9, batch 6200, loss[loss=2.261, over 5810.00 frames. , ppl: 9.596801014099308] tot_loss[loss=2.267, over 5348006.07 frames. , ppl: 9.647685331867802], batch size: 70
+2022-12-13 05:50:38,217 INFO [train.py:421] (7/8) Epoch 9, batch 6400, loss[loss=2.239, over 1890.00 frames. , ppl: 9.385513561324341] tot_loss[loss=2.268, over 5356346.60 frames. , ppl: 9.659319762706934], batch size: 70
+2022-12-13 05:52:22,372 INFO [train.py:421] (7/8) Epoch 9, batch 6600, loss[loss=3.047, over 560.00 frames. , ppl: 21.058952954832098] tot_loss[loss=2.267, over 5388752.31 frames. , ppl: 9.648813760363812], batch size: 70
+2022-12-13 05:54:01,402 INFO [train.py:421] (7/8) Epoch 9, batch 6800, loss[loss=2.321, over 2660.00 frames. , ppl: 10.185205760298311] tot_loss[loss=2.266, over 5415354.98 frames. , ppl: 9.64340939911157], batch size: 70
+2022-12-13 05:55:37,137 INFO [train.py:421] (7/8) Epoch 9, batch 7000, loss[loss=2.158, over 8890.00 frames. , ppl: 8.653216811327676] tot_loss[loss=2.267, over 5409219.34 frames. , ppl: 9.651808084147953], batch size: 70
+2022-12-13 05:55:37,138 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 05:55:37,868 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.271, over 211138.00 frames. , ppl: 9.689801055644402
+2022-12-13 05:57:20,762 INFO [train.py:421] (7/8) Epoch 9, batch 7200, loss[loss=2.212, over 3150.00 frames. , ppl: 9.131626809630019] tot_loss[loss=2.267, over 5421620.69 frames. , ppl: 9.64948749506611], batch size: 70
+2022-12-13 05:59:03,231 INFO [train.py:421] (7/8) Epoch 9, batch 7400, loss[loss=2.281, over 2170.00 frames. , ppl: 9.781860771686445] tot_loss[loss=2.266, over 5449562.88 frames. , ppl: 9.643478398872507], batch size: 70
+2022-12-13 06:00:38,578 INFO [train.py:421] (7/8) Epoch 9, batch 7600, loss[loss=2.161, over 4270.00 frames. , ppl: 8.679715307924797] tot_loss[loss=2.268, over 5433331.50 frames. , ppl: 9.657685628721952], batch size: 70
+2022-12-13 06:02:16,061 INFO [train.py:421] (7/8) Epoch 9, batch 7800, loss[loss=2.468, over 1190.00 frames. , ppl: 11.799916575739145] tot_loss[loss=2.269, over 5414380.76 frames. , ppl: 9.665507916761493], batch size: 70
+2022-12-13 06:03:55,048 INFO [train.py:421] (7/8) Epoch 9, batch 8000, loss[loss=2.128, over 5180.00 frames. , ppl: 8.399197142513488] tot_loss[loss=2.27, over 5394842.94 frames. , ppl: 9.676133569352501], batch size: 70
+2022-12-13 06:03:55,049 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 06:03:55,778 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.27, over 211138.00 frames. , ppl: 9.677170017837494
+2022-12-13 06:05:34,734 INFO [train.py:421] (7/8) Epoch 9, batch 8200, loss[loss=2.364, over 1330.00 frames. , ppl: 10.637688302322047] tot_loss[loss=2.27, over 5396023.72 frames. , ppl: 9.681172860116462], batch size: 70
+2022-12-13 06:07:15,120 INFO [train.py:421] (7/8) Epoch 9, batch 8400, loss[loss=2.209, over 3640.00 frames. , ppl: 9.10570315849617] tot_loss[loss=2.269, over 5456522.02 frames. , ppl: 9.665893366728186], batch size: 70
+2022-12-13 06:08:56,774 INFO [train.py:421] (7/8) Epoch 9, batch 8600, loss[loss=3.073, over 490.00 frames. , ppl: 21.599226321843087] tot_loss[loss=2.268, over 5507018.95 frames. , ppl: 9.662438629822732], batch size: 70
+2022-12-13 06:10:33,932 INFO [train.py:421] (7/8) Epoch 9, batch 8800, loss[loss=2.377, over 1820.00 frames. , ppl: 10.775500323866595] tot_loss[loss=2.269, over 5509235.87 frames. , ppl: 9.669040623368435], batch size: 70
+2022-12-13 06:12:16,353 INFO [train.py:421] (7/8) Epoch 9, batch 9000, loss[loss=2.329, over 2100.00 frames. , ppl: 10.26969056607733] tot_loss[loss=2.27, over 5505432.29 frames. , ppl: 9.678474899605941], batch size: 70
+2022-12-13 06:12:16,354 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 06:12:17,100 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.269, over 211138.00 frames. , ppl: 9.667984785319996
+2022-12-13 06:13:54,675 INFO [train.py:421] (7/8) Epoch 9, batch 9200, loss[loss=2.454, over 1680.00 frames. , ppl: 11.633918628620547] tot_loss[loss=2.27, over 5491255.61 frames. , ppl: 9.684079008091313], batch size: 70
+2022-12-13 06:15:37,228 INFO [train.py:421] (7/8) Epoch 9, batch 9400, loss[loss=2.374, over 840.00 frames. , ppl: 10.736349542145637] tot_loss[loss=2.271, over 5472116.87 frames. , ppl: 9.687845290097323], batch size: 70
+2022-12-13 06:17:15,206 INFO [train.py:421] (7/8) Epoch 9, batch 9600, loss[loss=2.571, over 840.00 frames. , ppl: 13.083263547729553] tot_loss[loss=2.271, over 5457329.59 frames. , ppl: 9.688480459582726], batch size: 70
+2022-12-13 06:18:55,628 INFO [train.py:421] (7/8) Epoch 9, batch 9800, loss[loss=2.335, over 3710.00 frames. , ppl: 10.329235889015209] tot_loss[loss=2.273, over 5418751.31 frames. , ppl: 9.705356496608339], batch size: 70
+2022-12-13 06:20:37,101 INFO [train.py:421] (7/8) Epoch 9, batch 10000, loss[loss=2.404, over 1610.00 frames. , ppl: 11.062216005863458] tot_loss[loss=2.274, over 5371712.17 frames. , ppl: 9.72041334031089], batch size: 70
+2022-12-13 06:20:37,102 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 06:20:37,859 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.268, over 211138.00 frames. , ppl: 9.658802552803898
+2022-12-13 06:22:19,989 INFO [train.py:421] (7/8) Epoch 9, batch 10200, loss[loss=2.527, over 770.00 frames. , ppl: 12.516541610442372] tot_loss[loss=2.273, over 5426313.48 frames. , ppl: 9.70529891297983], batch size: 70
+2022-12-13 06:23:58,846 INFO [train.py:421] (7/8) Epoch 9, batch 10400, loss[loss=2.596, over 770.00 frames. , ppl: 13.404367398137014] tot_loss[loss=2.274, over 5414247.79 frames. , ppl: 9.713576449676255], batch size: 70
+2022-12-13 06:25:43,276 INFO [train.py:421] (7/8) Epoch 9, batch 10600, loss[loss=2.209, over 3220.00 frames. , ppl: 9.109786007742217] tot_loss[loss=2.274, over 5401027.32 frames. , ppl: 9.715881079510154], batch size: 70
+2022-12-13 06:27:26,722 INFO [train.py:421] (7/8) Epoch 9, batch 10800, loss[loss=2.339, over 2660.00 frames. , ppl: 10.366285893812602] tot_loss[loss=2.272, over 5470323.70 frames. , ppl: 9.696995425366088], batch size: 70
+2022-12-13 06:29:05,718 INFO [train.py:421] (7/8) Epoch 9, batch 11000, loss[loss=2.713, over 630.00 frames. , ppl: 15.06851898197348] tot_loss[loss=2.272, over 5448630.17 frames. , ppl: 9.699881013554537], batch size: 70
+2022-12-13 06:29:05,718 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 06:29:06,467 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.269, over 211138.00 frames. , ppl: 9.671750305558916
+2022-12-13 06:30:49,635 INFO [train.py:421] (7/8) Epoch 9, batch 11200, loss[loss=2.252, over 3080.00 frames. , ppl: 9.510923029225868] tot_loss[loss=2.272, over 5495790.73 frames. , ppl: 9.695997124890988], batch size: 70
+2022-12-13 06:32:30,898 INFO [train.py:421] (7/8) Epoch 9, batch 11400, loss[loss=2.236, over 3290.00 frames. , ppl: 9.357996428751543] tot_loss[loss=2.272, over 5497168.15 frames. , ppl: 9.696976551103186], batch size: 70
+2022-12-13 06:34:12,400 INFO [train.py:421] (7/8) Epoch 9, batch 11600, loss[loss=2.125, over 8330.00 frames. , ppl: 8.374717556672502] tot_loss[loss=2.27, over 5546916.33 frames. , ppl: 9.683060252761338], batch size: 70
+2022-12-13 06:35:50,660 INFO [train.py:421] (7/8) Epoch 9, batch 11800, loss[loss=2.415, over 1540.00 frames. , ppl: 11.194664681491467] tot_loss[loss=2.271, over 5528071.15 frames. , ppl: 9.693805495797859], batch size: 70
+2022-12-13 06:37:30,263 INFO [train.py:421] (7/8) Epoch 9, batch 12000, loss[loss=2.34, over 2380.00 frames. , ppl: 10.378149639845665] tot_loss[loss=2.271, over 5510014.98 frames. , ppl: 9.693458652653606], batch size: 70
+2022-12-13 06:37:30,264 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 06:37:31,009 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.267, over 211138.00 frames. , ppl: 9.655009206172396
+2022-12-13 06:39:10,545 INFO [train.py:421] (7/8) Epoch 9, batch 12200, loss[loss=2.249, over 3780.00 frames. , ppl: 9.481266992638592] tot_loss[loss=2.271, over 5515970.01 frames. , ppl: 9.691841083022092], batch size: 70
+2022-12-13 06:40:53,685 INFO [train.py:421] (7/8) Epoch 9, batch 12400, loss[loss=2.239, over 5600.00 frames. , ppl: 9.381397366417609] tot_loss[loss=2.272, over 5513146.12 frames. , ppl: 9.696122899090383], batch size: 70
+2022-12-13 06:42:37,745 INFO [train.py:421] (7/8) Epoch 9, batch 12600, loss[loss=2.844, over 630.00 frames. , ppl: 17.190895659638826] tot_loss[loss=2.273, over 5477624.49 frames. , ppl: 9.70453484621674], batch size: 70
+2022-12-13 06:44:16,097 INFO [train.py:421] (7/8) Epoch 9, batch 12800, loss[loss=2.397, over 2030.00 frames. , ppl: 10.989239998876883] tot_loss[loss=2.273, over 5437466.25 frames. , ppl: 9.712685771071422], batch size: 70
+2022-12-13 06:45:55,154 INFO [train.py:421] (7/8) Epoch 9, batch 13000, loss[loss=2.342, over 2100.00 frames. , ppl: 10.39731278323799] tot_loss[loss=2.274, over 5411142.51 frames. , ppl: 9.718423674823446], batch size: 70
+2022-12-13 06:45:55,154 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 06:45:55,900 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.268, over 211138.00 frames. , ppl: 9.66105725550274
+2022-12-13 06:47:36,600 INFO [train.py:421] (7/8) Epoch 9, batch 13200, loss[loss=2.311, over 3080.00 frames. , ppl: 10.08941141676528] tot_loss[loss=2.273, over 5445626.75 frames. , ppl: 9.712655328184868], batch size: 70
+2022-12-13 06:49:17,403 INFO [train.py:421] (7/8) Epoch 9, batch 13400, loss[loss=2.23, over 4550.00 frames. , ppl: 9.29822948539835] tot_loss[loss=2.274, over 5444942.45 frames. , ppl: 9.7172328098717], batch size: 70
+2022-12-13 06:50:56,808 INFO [train.py:421] (7/8) Epoch 9, batch 13600, loss[loss=2.357, over 2590.00 frames. , ppl: 10.563805298305654] tot_loss[loss=2.272, over 5484463.70 frames. , ppl: 9.697653177404938], batch size: 70
+2022-12-13 06:52:32,853 INFO [train.py:421] (7/8) Epoch 9, batch 13800, loss[loss=2.332, over 1960.00 frames. , ppl: 10.299568497965533] tot_loss[loss=2.272, over 5490687.25 frames. , ppl: 9.702441147745153], batch size: 70
+2022-12-13 06:54:17,172 INFO [train.py:421] (7/8) Epoch 9, batch 14000, loss[loss=2.298, over 3220.00 frames. , ppl: 9.949942600078664] tot_loss[loss=2.272, over 5516054.93 frames. , ppl: 9.701277797015846], batch size: 70
+2022-12-13 06:54:17,172 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 06:54:17,916 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.27, over 211138.00 frames. , ppl: 9.675671954910115
+2022-12-13 06:55:57,101 INFO [train.py:421] (7/8) Epoch 9, batch 14200, loss[loss=2.439, over 1330.00 frames. , ppl: 11.467290163607068] tot_loss[loss=2.271, over 5542979.50 frames. , ppl: 9.693618066848195], batch size: 70
+2022-12-13 06:57:38,459 INFO [train.py:421] (7/8) Epoch 9, batch 14400, loss[loss=2.224, over 1470.00 frames. , ppl: 9.241521650947568] tot_loss[loss=2.272, over 5510448.12 frames. , ppl: 9.702435647447308], batch size: 70
+2022-12-13 06:59:18,407 INFO [train.py:421] (7/8) Epoch 9, batch 14600, loss[loss=2.124, over 5390.00 frames. , ppl: 8.367810998521914] tot_loss[loss=2.272, over 5538979.18 frames. , ppl: 9.6968691246746], batch size: 70
+2022-12-13 07:00:59,401 INFO [train.py:421] (7/8) Epoch 9, batch 14800, loss[loss=2.389, over 2380.00 frames. , ppl: 10.903383657213668] tot_loss[loss=2.272, over 5513029.82 frames. , ppl: 9.698902026510922], batch size: 70
+2022-12-13 07:02:36,609 INFO [train.py:421] (7/8) Epoch 9, batch 15000, loss[loss=2.27, over 7630.00 frames. , ppl: 9.678773473173454] tot_loss[loss=2.271, over 5557241.53 frames. , ppl: 9.692634279357419], batch size: 70
+2022-12-13 07:02:36,609 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 07:02:37,339 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.268, over 211138.00 frames. , ppl: 9.661317502370732
+2022-12-13 07:04:17,421 INFO [train.py:421] (7/8) Epoch 9, batch 15200, loss[loss=2.512, over 1120.00 frames. , ppl: 12.326306922584667] tot_loss[loss=2.271, over 5571098.47 frames. , ppl: 9.687302941710408], batch size: 70
+2022-12-13 07:05:53,692 INFO [train.py:421] (7/8) Epoch 9, batch 15400, loss[loss=2.318, over 2170.00 frames. , ppl: 10.156749002311106] tot_loss[loss=2.272, over 5527287.64 frames. , ppl: 9.697480603167419], batch size: 70
+2022-12-13 07:07:28,840 INFO [train.py:421] (7/8) Epoch 9, batch 15600, loss[loss=2.145, over 8820.00 frames. , ppl: 8.542304548320743] tot_loss[loss=2.271, over 5516317.11 frames. , ppl: 9.693451293889511], batch size: 70
+2022-12-13 07:09:10,483 INFO [train.py:421] (7/8) Epoch 9, batch 15800, loss[loss=2.353, over 2310.00 frames. , ppl: 10.514240434943211] tot_loss[loss=2.272, over 5496321.95 frames. , ppl: 9.695401124268464], batch size: 70
+2022-12-13 07:10:50,271 INFO [train.py:421] (7/8) Epoch 9, batch 16000, loss[loss=2.177, over 10570.00 frames. , ppl: 8.823201368995475] tot_loss[loss=2.271, over 5539658.38 frames. , ppl: 9.687355698593187], batch size: 70
+2022-12-13 07:10:50,271 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 07:10:51,000 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.268, over 211138.00 frames. , ppl: 9.65729732776054
+2022-12-13 07:12:29,303 INFO [train.py:421] (7/8) Epoch 9, batch 16200, loss[loss=2.166, over 8190.00 frames. , ppl: 8.719264218681388] tot_loss[loss=2.27, over 5584857.02 frames. , ppl: 9.676622907805413], batch size: 70
+2022-12-13 07:14:07,486 INFO [train.py:421] (7/8) Epoch 9, batch 16400, loss[loss=2.183, over 6440.00 frames. , ppl: 8.875015884778716] tot_loss[loss=2.272, over 5535688.81 frames. , ppl: 9.694739231912648], batch size: 70
+2022-12-13 07:15:49,897 INFO [train.py:421] (7/8) Epoch 9, batch 16600, loss[loss=2.222, over 4270.00 frames. , ppl: 9.22579020251529] tot_loss[loss=2.271, over 5549218.49 frames. , ppl: 9.690236504489294], batch size: 70
+2022-12-13 07:17:30,242 INFO [train.py:421] (7/8) Epoch 9, batch 16800, loss[loss=2.39, over 1190.00 frames. , ppl: 10.916573918088028] tot_loss[loss=2.271, over 5550159.10 frames. , ppl: 9.692398093081504], batch size: 70
+2022-12-13 07:19:11,498 INFO [train.py:421] (7/8) Epoch 9, batch 17000, loss[loss=2.389, over 1120.00 frames. , ppl: 10.898353380066776] tot_loss[loss=2.271, over 5558430.33 frames. , ppl: 9.688987017955844], batch size: 70
+2022-12-13 07:19:11,499 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 07:19:12,256 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.27, over 211138.00 frames. , ppl: 9.679668259935742
+2022-12-13 07:20:56,017 INFO [train.py:421] (7/8) Epoch 9, batch 17200, loss[loss=2.365, over 1610.00 frames. , ppl: 10.64634168962832] tot_loss[loss=2.271, over 5555651.42 frames. , ppl: 9.686916502478773], batch size: 70
+2022-12-13 07:22:38,914 INFO [train.py:421] (7/8) Epoch 9, batch 17400, loss[loss=2.234, over 3570.00 frames. , ppl: 9.335980225336593] tot_loss[loss=2.272, over 5502583.11 frames. , ppl: 9.703382027585645], batch size: 70
+2022-12-13 07:24:16,739 INFO [train.py:421] (7/8) Epoch 9, batch 17600, loss[loss=2.165, over 3710.00 frames. , ppl: 8.717346765975199] tot_loss[loss=2.273, over 5504120.56 frames. , ppl: 9.703864273380155], batch size: 70
+2022-12-13 07:25:57,037 INFO [train.py:421] (7/8) Epoch 9, batch 17800, loss[loss=2.217, over 3850.00 frames. , ppl: 9.176565939454003] tot_loss[loss=2.273, over 5468720.01 frames. , ppl: 9.707547895813258], batch size: 70
+2022-12-13 07:27:36,348 INFO [train.py:421] (7/8) Epoch 9, batch 18000, loss[loss=2.219, over 1820.00 frames. , ppl: 9.195201032984968] tot_loss[loss=2.272, over 5504855.19 frames. , ppl: 9.69573603050372], batch size: 70
+2022-12-13 07:27:36,349 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 07:27:37,108 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.635843748058024
+2022-12-13 07:29:17,365 INFO [train.py:421] (7/8) Epoch 9, batch 18200, loss[loss=2.541, over 1470.00 frames. , ppl: 12.691556148006349] tot_loss[loss=2.271, over 5543711.58 frames. , ppl: 9.687504414871857], batch size: 70
+2022-12-13 07:30:55,921 INFO [train.py:421] (7/8) Epoch 9, batch 18400, loss[loss=2.253, over 3010.00 frames. , ppl: 9.518618730450672] tot_loss[loss=2.271, over 5574175.54 frames. , ppl: 9.687358302459506], batch size: 70
+2022-12-13 07:32:36,192 INFO [train.py:421] (7/8) Epoch 9, batch 18600, loss[loss=2.204, over 4340.00 frames. , ppl: 9.061029590160864] tot_loss[loss=2.272, over 5537958.96 frames. , ppl: 9.697885723058192], batch size: 70
+2022-12-13 07:34:20,275 INFO [train.py:421] (7/8) Epoch 9, batch 18800, loss[loss=2.452, over 980.00 frames. , ppl: 11.610296561001746] tot_loss[loss=2.272, over 5545408.32 frames. , ppl: 9.699334710120977], batch size: 70
+2022-12-13 07:36:01,309 INFO [train.py:421] (7/8) Epoch 9, batch 19000, loss[loss=2.446, over 1120.00 frames. , ppl: 11.546885078817663] tot_loss[loss=2.272, over 5561325.20 frames. , ppl: 9.695785941954872], batch size: 70
+2022-12-13 07:36:01,309 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 07:36:02,070 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.267, over 211138.00 frames. , ppl: 9.654813433317269
+2022-12-13 07:37:39,896 INFO [train.py:421] (7/8) Epoch 9, batch 19200, loss[loss=2.752, over 840.00 frames. , ppl: 15.668955110112536] tot_loss[loss=2.272, over 5578605.29 frames. , ppl: 9.695460880776617], batch size: 70
+2022-12-13 07:39:21,550 INFO [train.py:421] (7/8) Epoch 9, batch 19400, loss[loss=2.673, over 840.00 frames. , ppl: 14.487523323148272] tot_loss[loss=2.272, over 5567638.60 frames. , ppl: 9.694439565436026], batch size: 70
+2022-12-13 07:41:01,750 INFO [train.py:421] (7/8) Epoch 9, batch 19600, loss[loss=2.333, over 2940.00 frames. , ppl: 10.31216087896442] tot_loss[loss=2.272, over 5576426.41 frames. , ppl: 9.697971169373671], batch size: 70
+2022-12-13 07:42:40,800 INFO [train.py:421] (7/8) Epoch 9, batch 19800, loss[loss=2.435, over 1190.00 frames. , ppl: 11.413094272506244] tot_loss[loss=2.274, over 5527723.60 frames. , ppl: 9.718526763715932], batch size: 70
+2022-12-13 07:44:22,225 INFO [train.py:421] (7/8) Epoch 9, batch 20000, loss[loss=2.503, over 840.00 frames. , ppl: 12.22167519285017] tot_loss[loss=2.275, over 5494069.14 frames. , ppl: 9.72442891288848], batch size: 70
+2022-12-13 07:44:22,225 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 07:44:22,986 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.269, over 211138.00 frames. , ppl: 9.671224962542615
+2022-12-13 07:46:03,952 INFO [train.py:421] (7/8) Epoch 9, batch 20200, loss[loss=2.23, over 3010.00 frames. , ppl: 9.299919786558378] tot_loss[loss=2.274, over 5518566.08 frames. , ppl: 9.713747467469867], batch size: 70
+2022-12-13 07:47:42,245 INFO [train.py:421] (7/8) Epoch 9, batch 20400, loss[loss=3.503, over 420.00 frames. , ppl: 33.21458141649369] tot_loss[loss=2.274, over 5498753.58 frames. , ppl: 9.713817220841133], batch size: 70
+2022-12-13 07:49:23,898 INFO [train.py:421] (7/8) Epoch 9, batch 20600, loss[loss=2.182, over 5880.00 frames. , ppl: 8.86193248601369] tot_loss[loss=2.275, over 5471654.81 frames. , ppl: 9.726113669076632], batch size: 70
+2022-12-13 07:51:06,184 INFO [train.py:421] (7/8) Epoch 9, batch 20800, loss[loss=2.344, over 1820.00 frames. , ppl: 10.420736914432995] tot_loss[loss=2.275, over 5452595.03 frames. , ppl: 9.73218140299105], batch size: 70
+2022-12-13 07:52:48,695 INFO [train.py:421] (7/8) Epoch 9, batch 21000, loss[loss=4.076, over 350.00 frames. , ppl: 58.880126757678866] tot_loss[loss=2.274, over 5470173.24 frames. , ppl: 9.721002055314218], batch size: 70
+2022-12-13 07:52:48,695 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 07:52:49,455 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.267, over 211138.00 frames. , ppl: 9.652867352648064
+2022-12-13 07:54:33,301 INFO [train.py:421] (7/8) Epoch 9, batch 21200, loss[loss=2.425, over 1260.00 frames. , ppl: 11.298888054009074] tot_loss[loss=2.276, over 5423115.79 frames. , ppl: 9.733189812198987], batch size: 70
+2022-12-13 07:56:15,662 INFO [train.py:421] (7/8) Epoch 9, batch 21400, loss[loss=2.391, over 840.00 frames. , ppl: 10.929105954912407] tot_loss[loss=2.276, over 5411869.08 frames. , ppl: 9.739031207612149], batch size: 70
+2022-12-13 07:57:54,061 INFO [train.py:421] (7/8) Epoch 9, batch 21600, loss[loss=3.555, over 420.00 frames. , ppl: 34.98199159043058] tot_loss[loss=2.275, over 5409870.70 frames. , ppl: 9.731835778116077], batch size: 70
+2022-12-13 07:59:33,286 INFO [train.py:421] (7/8) Epoch 9, batch 21800, loss[loss=2.261, over 4130.00 frames. , ppl: 9.59439807497421] tot_loss[loss=2.276, over 5434015.37 frames. , ppl: 9.733490208507147], batch size: 70
+2022-12-13 08:01:12,352 INFO [train.py:421] (7/8) Epoch 9, batch 22000, loss[loss=2.368, over 1890.00 frames. , ppl: 10.672899980602647] tot_loss[loss=2.277, over 5372944.14 frames. , ppl: 9.748636735448583], batch size: 70
+2022-12-13 08:01:12,353 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 08:01:13,114 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.268, over 211138.00 frames. , ppl: 9.65536646613963
+2022-12-13 08:02:53,719 INFO [train.py:421] (7/8) Epoch 9, batch 22200, loss[loss=2.166, over 8680.00 frames. , ppl: 8.719956063412896] tot_loss[loss=2.276, over 5416547.44 frames. , ppl: 9.735283497855544], batch size: 70
+2022-12-13 08:04:32,687 INFO [train.py:421] (7/8) Epoch 9, batch 22400, loss[loss=2.636, over 840.00 frames. , ppl: 13.95803741736018] tot_loss[loss=2.277, over 5370808.19 frames. , ppl: 9.74613691749988], batch size: 70
+2022-12-13 08:06:15,183 INFO [train.py:421] (7/8) Epoch 9, batch 22600, loss[loss=2.483, over 1400.00 frames. , ppl: 11.982450012774844] tot_loss[loss=2.275, over 5433026.52 frames. , ppl: 9.728775645131993], batch size: 70
+2022-12-13 08:07:55,315 INFO [train.py:421] (7/8) Epoch 9, batch 22800, loss[loss=2.407, over 1330.00 frames. , ppl: 11.100302118537133] tot_loss[loss=2.276, over 5405211.14 frames. , ppl: 9.739777189156095], batch size: 70
+2022-12-13 08:09:36,095 INFO [train.py:421] (7/8) Epoch 9, batch 23000, loss[loss=2.44, over 980.00 frames. , ppl: 11.47416349842237] tot_loss[loss=2.276, over 5405971.14 frames. , ppl: 9.738287593269382], batch size: 70
+2022-12-13 08:09:36,096 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 08:09:36,839 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.639090273243687
+2022-12-13 08:11:16,458 INFO [train.py:421] (7/8) Epoch 9, batch 23200, loss[loss=2.184, over 4900.00 frames. , ppl: 8.885019261436286] tot_loss[loss=2.276, over 5380578.19 frames. , ppl: 9.74177332542353], batch size: 70
+2022-12-13 08:12:57,319 INFO [train.py:421] (7/8) Epoch 9, batch 23400, loss[loss=2.337, over 2520.00 frames. , ppl: 10.349055583190653] tot_loss[loss=2.275, over 5401076.13 frames. , ppl: 9.730103742447353], batch size: 70
+2022-12-13 08:14:44,681 INFO [train.py:421] (7/8) Epoch 9, batch 23600, loss[loss=2.451, over 1610.00 frames. , ppl: 11.604480787155543] tot_loss[loss=2.275, over 5390386.59 frames. , ppl: 9.73254446077638], batch size: 70
+2022-12-13 08:16:23,460 INFO [train.py:421] (7/8) Epoch 9, batch 23800, loss[loss=2.836, over 560.00 frames. , ppl: 17.052245785282686] tot_loss[loss=2.276, over 5379940.55 frames. , ppl: 9.737748351317325], batch size: 70
+2022-12-13 08:18:03,866 INFO [train.py:421] (7/8) Epoch 9, batch 24000, loss[loss=2.348, over 1890.00 frames. , ppl: 10.464699134760197] tot_loss[loss=2.277, over 5373775.32 frames. , ppl: 9.743993243864335], batch size: 70
+2022-12-13 08:18:03,866 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 08:18:04,611 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.267, over 211138.00 frames. , ppl: 9.650770254134942
+2022-12-13 08:19:39,211 INFO [train.py:421] (7/8) Epoch 9, batch 24200, loss[loss=2.413, over 1330.00 frames. , ppl: 11.167384810342572] tot_loss[loss=2.277, over 5360653.41 frames. , ppl: 9.749678892515673], batch size: 70
+2022-12-13 08:21:19,435 INFO [train.py:421] (7/8) Epoch 9, batch 24400, loss[loss=2.455, over 1050.00 frames. , ppl: 11.641719928779612] tot_loss[loss=2.277, over 5391242.48 frames. , ppl: 9.744945553790274], batch size: 70
+2022-12-13 08:23:01,207 INFO [train.py:421] (7/8) Epoch 9, batch 24600, loss[loss=2.28, over 3220.00 frames. , ppl: 9.7788172756088] tot_loss[loss=2.276, over 5416347.47 frames. , ppl: 9.737497278250933], batch size: 70
+2022-12-13 08:24:43,333 INFO [train.py:421] (7/8) Epoch 9, batch 24800, loss[loss=2.215, over 3500.00 frames. , ppl: 9.162095476142776] tot_loss[loss=2.275, over 5437071.97 frames. , ppl: 9.729883400459274], batch size: 70
+2022-12-13 08:26:25,431 INFO [train.py:421] (7/8) Epoch 9, batch 25000, loss[loss=2.151, over 3150.00 frames. , ppl: 8.590453312275972] tot_loss[loss=2.275, over 5442361.61 frames. , ppl: 9.72992467775269], batch size: 70
+2022-12-13 08:26:25,432 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 08:26:26,196 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.640315849779926
+2022-12-13 08:28:06,142 INFO [train.py:421] (7/8) Epoch 9, batch 25200, loss[loss=2.155, over 11270.00 frames. , ppl: 8.623919438072742] tot_loss[loss=2.275, over 5462177.06 frames. , ppl: 9.72474575485367], batch size: 70
+2022-12-13 08:29:44,793 INFO [train.py:421] (7/8) Epoch 9, batch 25400, loss[loss=2.494, over 1050.00 frames. , ppl: 12.112250214892097] tot_loss[loss=2.275, over 5455124.59 frames. , ppl: 9.726336335201484], batch size: 70
+2022-12-13 08:31:25,709 INFO [train.py:421] (7/8) Epoch 9, batch 25600, loss[loss=2.19, over 6230.00 frames. , ppl: 8.931991174554103] tot_loss[loss=2.274, over 5490367.84 frames. , ppl: 9.717703974780017], batch size: 70
+2022-12-13 08:33:08,240 INFO [train.py:421] (7/8) Epoch 9, batch 25800, loss[loss=2.449, over 1540.00 frames. , ppl: 11.581086803965574] tot_loss[loss=2.274, over 5487913.83 frames. , ppl: 9.718871831686382], batch size: 70
+2022-12-13 08:34:47,566 INFO [train.py:421] (7/8) Epoch 9, batch 26000, loss[loss=2.413, over 1330.00 frames. , ppl: 11.169094586227017] tot_loss[loss=2.275, over 5464521.33 frames. , ppl: 9.724672556030823], batch size: 70
+2022-12-13 08:34:47,566 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 08:34:48,310 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.645219714400634
+2022-12-13 08:36:28,485 INFO [train.py:421] (7/8) Epoch 9, batch 26200, loss[loss=2.377, over 1960.00 frames. , ppl: 10.77772780158477] tot_loss[loss=2.274, over 5480761.77 frames. , ppl: 9.721696678485696], batch size: 70
+2022-12-13 08:38:06,094 INFO [train.py:421] (7/8) Epoch 9, batch 26400, loss[loss=2.43, over 1400.00 frames. , ppl: 11.363036643951752] tot_loss[loss=2.275, over 5467121.02 frames. , ppl: 9.72944938559015], batch size: 70
+2022-12-13 08:39:46,922 INFO [train.py:421] (7/8) Epoch 9, batch 26600, loss[loss=2.202, over 7140.00 frames. , ppl: 9.045933331811822] tot_loss[loss=2.275, over 5454860.87 frames. , ppl: 9.729734758544407], batch size: 70
+2022-12-13 08:41:30,300 INFO [train.py:421] (7/8) Epoch 9, batch 26800, loss[loss=2.152, over 4340.00 frames. , ppl: 8.606265283806241] tot_loss[loss=2.275, over 5456818.19 frames. , ppl: 9.7303502969631], batch size: 70
+2022-12-13 08:43:11,278 INFO [train.py:421] (7/8) Epoch 9, batch 27000, loss[loss=2.393, over 1330.00 frames. , ppl: 10.948403169567332] tot_loss[loss=2.276, over 5476175.40 frames. , ppl: 9.73428891441448], batch size: 70
+2022-12-13 08:43:11,278 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 08:43:12,039 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.267, over 211138.00 frames. , ppl: 9.652885925719394
+2022-12-13 08:44:53,160 INFO [train.py:421] (7/8) Epoch 9, batch 27200, loss[loss=2.299, over 1890.00 frames. , ppl: 9.962253723034118] tot_loss[loss=2.276, over 5445509.83 frames. , ppl: 9.74043524655645], batch size: 70
+2022-12-13 08:46:33,216 INFO [train.py:421] (7/8) Epoch 9, batch 27400, loss[loss=2.436, over 1190.00 frames. , ppl: 11.425759511692357] tot_loss[loss=2.278, over 5395766.20 frames. , ppl: 9.754630788657337], batch size: 70
+2022-12-13 08:48:13,490 INFO [train.py:421] (7/8) Epoch 9, batch 27600, loss[loss=2.33, over 2030.00 frames. , ppl: 10.28159804363716] tot_loss[loss=2.278, over 5361387.60 frames. , ppl: 9.761802003283153], batch size: 70
+2022-12-13 08:49:50,164 INFO [train.py:421] (7/8) Epoch 9, batch 27800, loss[loss=2.317, over 2450.00 frames. , ppl: 10.147239014328248] tot_loss[loss=2.278, over 5381547.23 frames. , ppl: 9.754800555937734], batch size: 70
+2022-12-13 08:51:34,722 INFO [train.py:421] (7/8) Epoch 9, batch 28000, loss[loss=2.384, over 1820.00 frames. , ppl: 10.850996878660881] tot_loss[loss=2.277, over 5426501.73 frames. , ppl: 9.743123706102642], batch size: 70
+2022-12-13 08:51:34,723 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 08:51:35,469 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.631405082310689
+2022-12-13 08:53:13,314 INFO [train.py:421] (7/8) Epoch 9, batch 28200, loss[loss=2.239, over 4830.00 frames. , ppl: 9.387252370814831] tot_loss[loss=2.276, over 5450673.09 frames. , ppl: 9.74061526321534], batch size: 70
+2022-12-13 08:54:53,462 INFO [train.py:421] (7/8) Epoch 9, batch 28400, loss[loss=2.152, over 2940.00 frames. , ppl: 8.605625882599064] tot_loss[loss=2.276, over 5450179.34 frames. , ppl: 9.741906685122235], batch size: 70
+2022-12-13 08:56:32,713 INFO [train.py:421] (7/8) Epoch 9, batch 28600, loss[loss=2.25, over 5110.00 frames. , ppl: 9.487463862751067] tot_loss[loss=2.275, over 5504782.79 frames. , ppl: 9.731790528976417], batch size: 70
+2022-12-13 08:58:14,687 INFO [train.py:421] (7/8) Epoch 9, batch 28800, loss[loss=2.159, over 7000.00 frames. , ppl: 8.658410065328937] tot_loss[loss=2.276, over 5494849.42 frames. , ppl: 9.73663681521849], batch size: 70
+2022-12-13 08:59:57,441 INFO [train.py:421] (7/8) Epoch 9, batch 29000, loss[loss=2.191, over 3360.00 frames. , ppl: 8.940475850298505] tot_loss[loss=2.276, over 5474278.50 frames. , ppl: 9.73722281256185], batch size: 70
+2022-12-13 08:59:57,441 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 08:59:58,199 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.267, over 211138.00 frames. , ppl: 9.650904523356159
+2022-12-13 09:01:42,270 INFO [train.py:421] (7/8) Epoch 9, batch 29200, loss[loss=2.193, over 4410.00 frames. , ppl: 8.963003475831261] tot_loss[loss=2.273, over 5543351.04 frames. , ppl: 9.712949284534147], batch size: 70
+2022-12-13 09:03:21,216 INFO [train.py:421] (7/8) Epoch 9, batch 29400, loss[loss=2.138, over 7350.00 frames. , ppl: 8.483352676652238] tot_loss[loss=2.274, over 5514794.20 frames. , ppl: 9.717399393536729], batch size: 70
+2022-12-13 09:05:00,161 INFO [train.py:421] (7/8) Epoch 9, batch 29600, loss[loss=2.198, over 4060.00 frames. , ppl: 9.003179892851417] tot_loss[loss=2.273, over 5500378.81 frames. , ppl: 9.712533795269893], batch size: 70
+2022-12-13 09:06:41,422 INFO [train.py:421] (7/8) Epoch 9, batch 29800, loss[loss=2.321, over 1680.00 frames. , ppl: 10.187902606971674] tot_loss[loss=2.275, over 5473662.95 frames. , ppl: 9.724988283811964], batch size: 70
+2022-12-13 09:08:24,044 INFO [train.py:421] (7/8) Epoch 9, batch 30000, loss[loss=2.408, over 1400.00 frames. , ppl: 11.1165798535388] tot_loss[loss=2.274, over 5528789.29 frames. , ppl: 9.715519776998851], batch size: 70
+2022-12-13 09:08:24,044 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 09:08:24,805 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.637924764691014
+2022-12-13 09:10:04,499 INFO [train.py:421] (7/8) Epoch 9, batch 30200, loss[loss=2.281, over 1750.00 frames. , ppl: 9.789381424166837] tot_loss[loss=2.273, over 5535669.15 frames. , ppl: 9.710413930571733], batch size: 70
+2022-12-13 09:11:45,359 INFO [train.py:421] (7/8) Epoch 9, batch 30400, loss[loss=2.297, over 2030.00 frames. , ppl: 9.943501855830227] tot_loss[loss=2.273, over 5573876.35 frames. , ppl: 9.707285742362517], batch size: 70
+2022-12-13 09:13:24,107 INFO [train.py:421] (7/8) Epoch 9, batch 30600, loss[loss=2.283, over 2380.00 frames. , ppl: 9.804580103452913] tot_loss[loss=2.273, over 5569432.03 frames. , ppl: 9.703774547065455], batch size: 70
+2022-12-13 09:15:01,163 INFO [train.py:421] (7/8) Epoch 9, batch 30800, loss[loss=2.216, over 3010.00 frames. , ppl: 9.170602356700426] tot_loss[loss=2.274, over 5527602.33 frames. , ppl: 9.713686368454542], batch size: 70
+2022-12-13 09:16:34,884 INFO [train.py:421] (7/8) Epoch 9, batch 31000, loss[loss=2.449, over 1610.00 frames. , ppl: 11.572721177043608] tot_loss[loss=2.275, over 5467352.84 frames. , ppl: 9.72635822514321], batch size: 70
+2022-12-13 09:16:34,885 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 09:16:35,648 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.268, over 211138.00 frames. , ppl: 9.66225130295525
+2022-12-13 09:18:16,658 INFO [train.py:421] (7/8) Epoch 9, batch 31200, loss[loss=2.532, over 770.00 frames. , ppl: 12.57490406526726] tot_loss[loss=2.275, over 5441832.34 frames. , ppl: 9.732315386062185], batch size: 70
+2022-12-13 09:19:54,596 INFO [train.py:421] (7/8) Epoch 9, batch 31400, loss[loss=2.5, over 1050.00 frames. , ppl: 12.184102990075674] tot_loss[loss=2.275, over 5452735.70 frames. , ppl: 9.72371069507647], batch size: 70
+2022-12-13 09:21:34,365 INFO [train.py:421] (7/8) Epoch 9, batch 31600, loss[loss=2.547, over 700.00 frames. , ppl: 12.768827332300548] tot_loss[loss=2.275, over 5450210.35 frames. , ppl: 9.727467463960057], batch size: 70
+2022-12-13 09:23:15,092 INFO [train.py:421] (7/8) Epoch 9, batch 31800, loss[loss=2.556, over 980.00 frames. , ppl: 12.889524400415901] tot_loss[loss=2.274, over 5472299.01 frames. , ppl: 9.722074470558596], batch size: 70
+2022-12-13 09:24:55,718 INFO [train.py:421] (7/8) Epoch 9, batch 32000, loss[loss=2.275, over 2590.00 frames. , ppl: 9.729683443581344] tot_loss[loss=2.274, over 5493523.65 frames. , ppl: 9.713778441899587], batch size: 70
+2022-12-13 09:24:55,719 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 09:24:56,478 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.268, over 211138.00 frames. , ppl: 9.664727097772253
+2022-12-13 09:26:38,798 INFO [train.py:421] (7/8) Epoch 9, batch 32200, loss[loss=3.522, over 420.00 frames. , ppl: 33.85810576255502] tot_loss[loss=2.273, over 5492282.71 frames. , ppl: 9.711870568022512], batch size: 70
+2022-12-13 09:28:15,352 INFO [train.py:421] (7/8) Epoch 9, batch 32400, loss[loss=2.274, over 3220.00 frames. , ppl: 9.722262009492447] tot_loss[loss=2.273, over 5488752.02 frames. , ppl: 9.710171674416806], batch size: 70
+2022-12-13 09:29:54,356 INFO [train.py:421] (7/8) Epoch 9, batch 32600, loss[loss=2.349, over 1890.00 frames. , ppl: 10.477413554499426] tot_loss[loss=2.274, over 5445705.89 frames. , ppl: 9.721248507003413], batch size: 70
+2022-12-13 09:31:30,580 INFO [train.py:421] (7/8) Epoch 9, batch 32800, loss[loss=2.513, over 910.00 frames. , ppl: 12.338759442935915] tot_loss[loss=2.273, over 5472734.88 frames. , ppl: 9.71266437067306], batch size: 70
+2022-12-13 09:33:11,510 INFO [train.py:421] (7/8) Epoch 9, batch 33000, loss[loss=2.155, over 4060.00 frames. , ppl: 8.624850001040736] tot_loss[loss=2.273, over 5484541.93 frames. , ppl: 9.709667063476147], batch size: 70
+2022-12-13 09:33:11,511 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 09:33:12,263 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.644468844695679
+2022-12-13 09:34:49,445 INFO [train.py:421] (7/8) Epoch 9, batch 33200, loss[loss=2.406, over 1120.00 frames. , ppl: 11.088525322741715] tot_loss[loss=2.273, over 5471966.86 frames. , ppl: 9.710295576446292], batch size: 70
+2022-12-13 09:36:29,258 INFO [train.py:421] (7/8) Epoch 9, batch 33400, loss[loss=2.168, over 5810.00 frames. , ppl: 8.742507141066756] tot_loss[loss=2.273, over 5485721.91 frames. , ppl: 9.709215537184507], batch size: 70
+2022-12-13 09:38:10,170 INFO [train.py:421] (7/8) Epoch 9, batch 33600, loss[loss=2.273, over 3640.00 frames. , ppl: 9.712746642595935] tot_loss[loss=2.275, over 5444248.58 frames. , ppl: 9.724132183488072], batch size: 70
+2022-12-13 09:39:46,992 INFO [train.py:421] (7/8) Epoch 9, batch 33800, loss[loss=2.356, over 1470.00 frames. , ppl: 10.544113423960763] tot_loss[loss=2.275, over 5435413.56 frames. , ppl: 9.727543520655338], batch size: 70
+2022-12-13 09:41:27,524 INFO [train.py:421] (7/8) Epoch 9, batch 34000, loss[loss=2.188, over 3710.00 frames. , ppl: 8.917160984595766] tot_loss[loss=2.276, over 5410221.29 frames. , ppl: 9.737387815330413], batch size: 70
+2022-12-13 09:41:27,525 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 09:41:28,282 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.268, over 211138.00 frames. , ppl: 9.6631322756689
+2022-12-13 09:43:09,917 INFO [train.py:421] (7/8) Epoch 9, batch 34200, loss[loss=2.192, over 4830.00 frames. , ppl: 8.952616954614383] tot_loss[loss=2.276, over 5423999.12 frames. , ppl: 9.735529550386909], batch size: 70
+2022-12-13 09:44:49,464 INFO [train.py:421] (7/8) Epoch 9, batch 34400, loss[loss=2.177, over 7840.00 frames. , ppl: 8.81929042599504] tot_loss[loss=2.276, over 5414179.18 frames. , ppl: 9.733811643968924], batch size: 70
+2022-12-13 09:46:28,569 INFO [train.py:421] (7/8) Epoch 9, batch 34600, loss[loss=2.626, over 910.00 frames. , ppl: 13.818799552332662] tot_loss[loss=2.276, over 5405629.38 frames. , ppl: 9.736529473962182], batch size: 70
+2022-12-13 09:48:11,553 INFO [train.py:421] (7/8) Epoch 9, batch 34800, loss[loss=2.424, over 1050.00 frames. , ppl: 11.288903131929645] tot_loss[loss=2.275, over 5433824.56 frames. , ppl: 9.729924855917163], batch size: 70
+2022-12-13 09:49:50,488 INFO [train.py:421] (7/8) Epoch 9, batch 35000, loss[loss=2.187, over 4410.00 frames. , ppl: 8.904915060854014] tot_loss[loss=2.275, over 5433536.91 frames. , ppl: 9.729543150744025], batch size: 70
+2022-12-13 09:49:50,489 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 09:49:51,240 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.644501676179262
+2022-12-13 09:51:35,363 INFO [train.py:421] (7/8) Epoch 9, batch 35200, loss[loss=2.471, over 1260.00 frames. , ppl: 11.829948673969657] tot_loss[loss=2.275, over 5452846.31 frames. , ppl: 9.723799332488845], batch size: 70
+2022-12-13 09:53:15,453 INFO [train.py:421] (7/8) Epoch 9, batch 35400, loss[loss=2.15, over 3360.00 frames. , ppl: 8.588646846497937] tot_loss[loss=2.276, over 5389644.21 frames. , ppl: 9.738689731090831], batch size: 70
+2022-12-13 09:54:55,420 INFO [train.py:421] (7/8) Epoch 9, batch 35600, loss[loss=2.184, over 3150.00 frames. , ppl: 8.879833990831738] tot_loss[loss=2.275, over 5421950.11 frames. , ppl: 9.725587680404686], batch size: 70
+2022-12-13 09:56:35,187 INFO [train.py:421] (7/8) Epoch 9, batch 35800, loss[loss=2.272, over 6930.00 frames. , ppl: 9.697741637422192] tot_loss[loss=2.275, over 5417248.17 frames. , ppl: 9.730578377994082], batch size: 70
+2022-12-13 09:58:16,596 INFO [train.py:421] (7/8) Epoch 9, batch 36000, loss[loss=3.023, over 560.00 frames. , ppl: 20.54551635857391] tot_loss[loss=2.274, over 5469379.99 frames. , ppl: 9.719902687671171], batch size: 70
+2022-12-13 09:58:16,596 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 09:58:17,362 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.267, over 211138.00 frames. , ppl: 9.647108567176648
+2022-12-13 09:59:55,818 INFO [train.py:421] (7/8) Epoch 9, batch 36200, loss[loss=2.392, over 1960.00 frames. , ppl: 10.933519422969152] tot_loss[loss=2.274, over 5478696.96 frames. , ppl: 9.715584136245141], batch size: 70
+2022-12-13 10:01:36,713 INFO [train.py:421] (7/8) Epoch 9, batch 36400, loss[loss=2.213, over 4200.00 frames. , ppl: 9.147286370440899] tot_loss[loss=2.274, over 5483785.23 frames. , ppl: 9.7141513129317], batch size: 70
+2022-12-13 10:03:20,897 INFO [train.py:421] (7/8) Epoch 9, batch 36600, loss[loss=2.316, over 1890.00 frames. , ppl: 10.139784078157906] tot_loss[loss=2.274, over 5483046.91 frames. , ppl: 9.716855503701664], batch size: 70
+2022-12-13 10:05:04,602 INFO [train.py:421] (7/8) Epoch 9, batch 36800, loss[loss=2.214, over 3010.00 frames. , ppl: 9.154644822246183] tot_loss[loss=2.275, over 5490311.66 frames. , ppl: 9.725469902124672], batch size: 70
+2022-12-13 10:06:43,623 INFO [train.py:421] (7/8) Epoch 9, batch 37000, loss[loss=2.345, over 2800.00 frames. , ppl: 10.434595528557029] tot_loss[loss=2.274, over 5524430.74 frames. , ppl: 9.713628039936307], batch size: 70
+2022-12-13 10:06:43,623 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 10:06:44,368 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.267, over 211138.00 frames. , ppl: 9.65039602425002
+2022-12-13 10:08:24,181 INFO [train.py:421] (7/8) Epoch 9, batch 37200, loss[loss=2.31, over 1400.00 frames. , ppl: 10.076789639520765] tot_loss[loss=2.275, over 5481076.34 frames. , ppl: 9.728999927450799], batch size: 70
+2022-12-13 10:10:01,429 INFO [train.py:421] (7/8) Epoch 9, batch 37400, loss[loss=2.199, over 4130.00 frames. , ppl: 9.012376171372999] tot_loss[loss=2.275, over 5488060.42 frames. , ppl: 9.723200791682027], batch size: 70
+2022-12-13 10:11:39,959 INFO [train.py:421] (7/8) Epoch 9, batch 37600, loss[loss=2.469, over 1120.00 frames. , ppl: 11.808687025492205] tot_loss[loss=2.275, over 5452321.24 frames. , ppl: 9.729716925750651], batch size: 70
+2022-12-13 10:13:18,222 INFO [train.py:421] (7/8) Epoch 9, batch 37800, loss[loss=2.444, over 1470.00 frames. , ppl: 11.519248112180296] tot_loss[loss=2.275, over 5453311.68 frames. , ppl: 9.731087158841166], batch size: 70
+2022-12-13 10:14:59,566 INFO [train.py:421] (7/8) Epoch 9, batch 38000, loss[loss=2.434, over 1400.00 frames. , ppl: 11.408610454464752] tot_loss[loss=2.275, over 5456105.52 frames. , ppl: 9.730032334033954], batch size: 70
+2022-12-13 10:14:59,567 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 10:15:00,328 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.637123113571448
+2022-12-13 10:16:42,063 INFO [train.py:421] (7/8) Epoch 9, batch 38200, loss[loss=2.251, over 2800.00 frames. , ppl: 9.499185467690642] tot_loss[loss=2.275, over 5462349.76 frames. , ppl: 9.726746258937204], batch size: 70
+2022-12-13 10:18:21,503 INFO [train.py:421] (7/8) Epoch 9, batch 38400, loss[loss=2.26, over 4760.00 frames. , ppl: 9.582453361341242] tot_loss[loss=2.275, over 5457157.55 frames. , ppl: 9.725261828183466], batch size: 70
+2022-12-13 10:20:03,169 INFO [train.py:421] (7/8) Epoch 9, batch 38600, loss[loss=2.32, over 2870.00 frames. , ppl: 10.178300553903822] tot_loss[loss=2.275, over 5472680.70 frames. , ppl: 9.731008916603974], batch size: 70
+2022-12-13 10:21:45,084 INFO [train.py:421] (7/8) Epoch 9, batch 38800, loss[loss=2.386, over 2170.00 frames. , ppl: 10.871500567169134] tot_loss[loss=2.274, over 5519656.53 frames. , ppl: 9.717414324034019], batch size: 70
+2022-12-13 10:23:26,885 INFO [train.py:421] (7/8) Epoch 9, batch 39000, loss[loss=2.258, over 2800.00 frames. , ppl: 9.566395484858058] tot_loss[loss=2.274, over 5525344.73 frames. , ppl: 9.71374037117698], batch size: 70
+2022-12-13 10:23:26,886 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 10:23:27,632 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.267, over 211138.00 frames. , ppl: 9.646513174570288
+2022-12-13 10:25:07,540 INFO [train.py:421] (7/8) Epoch 9, batch 39200, loss[loss=2.329, over 3570.00 frames. , ppl: 10.267905447818352] tot_loss[loss=2.274, over 5510971.31 frames. , ppl: 9.717850537531104], batch size: 70
+2022-12-13 10:26:46,253 INFO [train.py:421] (7/8) Epoch 9, batch 39400, loss[loss=2.262, over 4270.00 frames. , ppl: 9.59977185689417] tot_loss[loss=2.274, over 5516603.94 frames. , ppl: 9.714128735324174], batch size: 70
+2022-12-13 10:28:27,588 INFO [train.py:421] (7/8) Epoch 9, batch 39600, loss[loss=2.097, over 7070.00 frames. , ppl: 8.140492562385155] tot_loss[loss=2.273, over 5512136.87 frames. , ppl: 9.711855913245868], batch size: 70
+2022-12-13 10:30:04,680 INFO [train.py:421] (7/8) Epoch 9, batch 39800, loss[loss=2.266, over 4270.00 frames. , ppl: 9.639270869787698] tot_loss[loss=2.274, over 5475731.57 frames. , ppl: 9.721417515118338], batch size: 70
+2022-12-13 10:31:44,861 INFO [train.py:421] (7/8) Epoch 9, batch 40000, loss[loss=2.26, over 1680.00 frames. , ppl: 9.579520794583525] tot_loss[loss=2.273, over 5515329.34 frames. , ppl: 9.70799716098959], batch size: 70
+2022-12-13 10:31:44,862 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 10:31:45,622 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.267, over 211138.00 frames. , ppl: 9.648730734417011
+2022-12-13 10:33:26,259 INFO [train.py:421] (7/8) Epoch 9, batch 40200, loss[loss=2.215, over 3150.00 frames. , ppl: 9.158271207566964] tot_loss[loss=2.273, over 5507256.75 frames. , ppl: 9.711484066080486], batch size: 70
+2022-12-13 10:35:02,356 INFO [train.py:421] (7/8) Epoch 9, batch 40400, loss[loss=2.297, over 2800.00 frames. , ppl: 9.944128211607124] tot_loss[loss=2.274, over 5506674.20 frames. , ppl: 9.716054985132683], batch size: 70
+2022-12-13 10:36:42,737 INFO [train.py:421] (7/8) Epoch 9, batch 40600, loss[loss=2.218, over 4270.00 frames. , ppl: 9.191922134707587] tot_loss[loss=2.274, over 5505995.97 frames. , ppl: 9.717188619680341], batch size: 70
+2022-12-13 10:38:21,196 INFO [train.py:421] (7/8) Epoch 9, batch 40800, loss[loss=2.233, over 6090.00 frames. , ppl: 9.329690503842675] tot_loss[loss=2.275, over 5480362.02 frames. , ppl: 9.728053199354415], batch size: 70
+2022-12-13 10:39:58,028 INFO [train.py:421] (7/8) Epoch 9, batch 41000, loss[loss=2.274, over 2800.00 frames. , ppl: 9.71398786341075] tot_loss[loss=2.276, over 5452235.06 frames. , ppl: 9.735825805979331], batch size: 70
+2022-12-13 10:39:58,029 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 10:39:58,774 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.268, over 211138.00 frames. , ppl: 9.663169461348792
+2022-12-13 10:41:39,551 INFO [train.py:421] (7/8) Epoch 9, batch 41200, loss[loss=2.59, over 980.00 frames. , ppl: 13.335719735905892] tot_loss[loss=2.275, over 5497889.81 frames. , ppl: 9.727760676913553], batch size: 70
+2022-12-13 10:43:16,339 INFO [train.py:421] (7/8) Epoch 9, batch 41400, loss[loss=2.22, over 3150.00 frames. , ppl: 9.208578347329714] tot_loss[loss=2.277, over 5454506.54 frames. , ppl: 9.744591614915851], batch size: 70
+2022-12-13 10:44:58,190 INFO [train.py:421] (7/8) Epoch 9, batch 41600, loss[loss=2.246, over 9730.00 frames. , ppl: 9.448248549004875] tot_loss[loss=2.276, over 5488146.91 frames. , ppl: 9.736348858507165], batch size: 70
+2022-12-13 10:46:39,492 INFO [train.py:421] (7/8) Epoch 9, batch 41800, loss[loss=2.334, over 1400.00 frames. , ppl: 10.32328326685462] tot_loss[loss=2.277, over 5432300.06 frames. , ppl: 9.744312371413677], batch size: 70
+2022-12-13 10:48:20,323 INFO [train.py:421] (7/8) Epoch 9, batch 42000, loss[loss=2.652, over 700.00 frames. , ppl: 14.188547545871094] tot_loss[loss=2.275, over 5486506.55 frames. , ppl: 9.726021506021382], batch size: 70
+2022-12-13 10:48:20,324 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 10:48:21,082 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.635082199742264
+2022-12-13 10:50:03,520 INFO [train.py:421] (7/8) Epoch 9, batch 42200, loss[loss=2.358, over 2100.00 frames. , ppl: 10.574307829819828] tot_loss[loss=2.274, over 5485368.60 frames. , ppl: 9.720784978157436], batch size: 70
+2022-12-13 10:51:44,294 INFO [train.py:421] (7/8) Epoch 9, batch 42400, loss[loss=2.208, over 6370.00 frames. , ppl: 9.100341794254039] tot_loss[loss=2.274, over 5488783.30 frames. , ppl: 9.713344778602382], batch size: 70
+2022-12-13 10:53:20,410 INFO [train.py:421] (7/8) Epoch 9, batch 42600, loss[loss=2.315, over 1960.00 frames. , ppl: 10.125727076509856] tot_loss[loss=2.275, over 5420808.43 frames. , ppl: 9.731629242017778], batch size: 70
+2022-12-13 10:54:59,731 INFO [train.py:421] (7/8) Epoch 9, batch 42800, loss[loss=2.419, over 1260.00 frames. , ppl: 11.233908924580073] tot_loss[loss=2.276, over 5396518.87 frames. , ppl: 9.73908891051934], batch size: 70
+2022-12-13 10:56:37,378 INFO [train.py:421] (7/8) Epoch 9, batch 43000, loss[loss=2.551, over 1120.00 frames. , ppl: 12.816076743616403] tot_loss[loss=2.275, over 5408729.44 frames. , ppl: 9.731332313951661], batch size: 70
+2022-12-13 10:56:37,379 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 10:56:38,138 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.269, over 211138.00 frames. , ppl: 9.668268114386317
+2022-12-13 10:58:19,721 INFO [train.py:421] (7/8) Epoch 9, batch 43200, loss[loss=2.309, over 3150.00 frames. , ppl: 10.064822051130049] tot_loss[loss=2.275, over 5434332.60 frames. , ppl: 9.725627426273904], batch size: 70
+2022-12-13 11:00:01,372 INFO [train.py:421] (7/8) Epoch 9, batch 43400, loss[loss=3.224, over 490.00 frames. , ppl: 25.130267923384242] tot_loss[loss=2.275, over 5415733.02 frames. , ppl: 9.73147829926499], batch size: 70
+2022-12-13 11:01:45,159 INFO [train.py:421] (7/8) Epoch 9, batch 43600, loss[loss=2.471, over 1120.00 frames. , ppl: 11.839804936550362] tot_loss[loss=2.274, over 5449519.27 frames. , ppl: 9.721001654773811], batch size: 70
+2022-12-13 11:03:26,871 INFO [train.py:421] (7/8) Epoch 9, batch 43800, loss[loss=2.252, over 3080.00 frames. , ppl: 9.5058069530411] tot_loss[loss=2.274, over 5464821.93 frames. , ppl: 9.717476491259744], batch size: 70
+2022-12-13 11:05:05,109 INFO [train.py:421] (7/8) Epoch 9, batch 44000, loss[loss=2.299, over 3640.00 frames. , ppl: 9.961894097886733] tot_loss[loss=2.275, over 5433849.73 frames. , ppl: 9.727943015938587], batch size: 70
+2022-12-13 11:05:05,110 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 11:05:05,859 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.264, over 211138.00 frames. , ppl: 9.623468208814646
+2022-12-13 11:06:45,154 INFO [train.py:421] (7/8) Epoch 9, batch 44200, loss[loss=2.198, over 6160.00 frames. , ppl: 9.008509038866567] tot_loss[loss=2.276, over 5416044.90 frames. , ppl: 9.73579439397588], batch size: 70
+2022-12-13 11:08:25,118 INFO [train.py:421] (7/8) Epoch 9, batch 44400, loss[loss=2.288, over 3360.00 frames. , ppl: 9.85056030922188] tot_loss[loss=2.275, over 5431786.45 frames. , ppl: 9.730599073829753], batch size: 70
+2022-12-13 11:10:01,990 INFO [train.py:421] (7/8) Epoch 9, batch 44600, loss[loss=2.239, over 2940.00 frames. , ppl: 9.388142700761698] tot_loss[loss=2.275, over 5433381.05 frames. , ppl: 9.732227533473294], batch size: 70
+2022-12-13 11:11:38,150 INFO [train.py:421] (7/8) Epoch 9, batch 44800, loss[loss=2.398, over 1470.00 frames. , ppl: 11.000394280146645] tot_loss[loss=2.277, over 5386846.72 frames. , ppl: 9.742627887419674], batch size: 70
+2022-12-13 11:13:19,790 INFO [train.py:421] (7/8) Epoch 9, batch 45000, loss[loss=2.407, over 1470.00 frames. , ppl: 11.100565362766016] tot_loss[loss=2.275, over 5432055.95 frames. , ppl: 9.73222531868792], batch size: 70
+2022-12-13 11:13:19,790 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 11:13:20,550 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.267, over 211138.00 frames. , ppl: 9.648610776092447
+2022-12-13 11:15:01,467 INFO [train.py:421] (7/8) Epoch 9, batch 45200, loss[loss=2.289, over 1610.00 frames. , ppl: 9.869294855260875] tot_loss[loss=2.274, over 5463458.18 frames. , ppl: 9.71648229463611], batch size: 70
+2022-12-13 11:16:44,207 INFO [train.py:421] (7/8) Epoch 9, batch 45400, loss[loss=2.343, over 2800.00 frames. , ppl: 10.41328738834569] tot_loss[loss=2.274, over 5442444.27 frames. , ppl: 9.722166318728943], batch size: 70
+2022-12-13 11:18:27,658 INFO [train.py:421] (7/8) Epoch 9, batch 45600, loss[loss=2.17, over 3990.00 frames. , ppl: 8.757252595401466] tot_loss[loss=2.275, over 5398238.77 frames. , ppl: 9.731504790206785], batch size: 70
+2022-12-13 11:20:08,208 INFO [train.py:421] (7/8) Epoch 9, batch 45800, loss[loss=2.222, over 3780.00 frames. , ppl: 9.227776208144485] tot_loss[loss=2.274, over 5455688.95 frames. , ppl: 9.713622265111532], batch size: 70
+2022-12-13 11:21:46,360 INFO [train.py:421] (7/8) Epoch 9, batch 46000, loss[loss=3.518, over 420.00 frames. , ppl: 33.72867381204152] tot_loss[loss=2.273, over 5467257.14 frames. , ppl: 9.708219851201568], batch size: 70
+2022-12-13 11:21:46,360 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 11:21:47,106 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.636034857644312
+2022-12-13 11:23:26,557 INFO [train.py:421] (7/8) Epoch 9, batch 46200, loss[loss=2.996, over 560.00 frames. , ppl: 20.015082590408063] tot_loss[loss=2.273, over 5472236.35 frames. , ppl: 9.708915655408354], batch size: 70
+2022-12-13 11:25:07,646 INFO [train.py:421] (7/8) Epoch 9, batch 46400, loss[loss=2.211, over 9660.00 frames. , ppl: 9.124244246687365] tot_loss[loss=2.273, over 5463352.80 frames. , ppl: 9.70912914706193], batch size: 70
+2022-12-13 11:26:44,519 INFO [train.py:421] (7/8) Epoch 9, batch 46600, loss[loss=2.24, over 2380.00 frames. , ppl: 9.392110332402247] tot_loss[loss=2.273, over 5466457.56 frames. , ppl: 9.709693037123658], batch size: 70
+2022-12-13 11:28:29,187 INFO [train.py:421] (7/8) Epoch 9, batch 46800, loss[loss=2.299, over 3500.00 frames. , ppl: 9.96259531658316] tot_loss[loss=2.271, over 5519802.36 frames. , ppl: 9.691009584840149], batch size: 70
+2022-12-13 11:30:14,120 INFO [train.py:421] (7/8) Epoch 9, batch 47000, loss[loss=2.504, over 1120.00 frames. , ppl: 12.236558883464733] tot_loss[loss=2.271, over 5545620.48 frames. , ppl: 9.687981380030724], batch size: 70
+2022-12-13 11:30:14,120 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 11:30:14,868 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.63486544043961
+2022-12-13 11:31:58,223 INFO [train.py:421] (7/8) Epoch 9, batch 47200, loss[loss=2.518, over 1120.00 frames. , ppl: 12.401803233170108] tot_loss[loss=2.27, over 5572381.53 frames. , ppl: 9.677184648773075], batch size: 70
+2022-12-13 11:33:39,675 INFO [train.py:421] (7/8) Epoch 9, batch 47400, loss[loss=2.375, over 1540.00 frames. , ppl: 10.753743964026436] tot_loss[loss=2.27, over 5582104.57 frames. , ppl: 9.681496067119786], batch size: 70
+2022-12-13 11:35:21,988 INFO [train.py:421] (7/8) Epoch 9, batch 47600, loss[loss=2.189, over 7420.00 frames. , ppl: 8.925242582535914] tot_loss[loss=2.271, over 5556634.22 frames. , ppl: 9.692645175120349], batch size: 70
+2022-12-13 11:37:01,536 INFO [train.py:421] (7/8) Epoch 9, batch 47800, loss[loss=2.368, over 1960.00 frames. , ppl: 10.675039006256899] tot_loss[loss=2.271, over 5562042.70 frames. , ppl: 9.688175053206047], batch size: 70
+2022-12-13 11:38:43,295 INFO [train.py:421] (7/8) Epoch 9, batch 48000, loss[loss=2.359, over 2380.00 frames. , ppl: 10.578349087322568] tot_loss[loss=2.271, over 5542438.06 frames. , ppl: 9.690084839602994], batch size: 70
+2022-12-13 11:38:43,296 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 11:38:44,056 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.627387380087804
+2022-12-13 11:40:21,735 INFO [train.py:421] (7/8) Epoch 9, batch 48200, loss[loss=2.508, over 1120.00 frames. , ppl: 12.28102164058834] tot_loss[loss=2.272, over 5542361.05 frames. , ppl: 9.696090694479027], batch size: 70
+2022-12-13 11:42:04,579 INFO [train.py:421] (7/8) Epoch 9, batch 48400, loss[loss=2.308, over 1820.00 frames. , ppl: 10.05499762132954] tot_loss[loss=2.27, over 5595302.46 frames. , ppl: 9.681873215749937], batch size: 70
+2022-12-13 11:43:45,263 INFO [train.py:421] (7/8) Epoch 9, batch 48600, loss[loss=2.265, over 3080.00 frames. , ppl: 9.635273029234197] tot_loss[loss=2.271, over 5558334.17 frames. , ppl: 9.693073818100967], batch size: 70
+2022-12-13 11:45:22,567 INFO [train.py:421] (7/8) Epoch 9, batch 48800, loss[loss=2.108, over 10290.00 frames. , ppl: 8.229302601114743] tot_loss[loss=2.272, over 5568590.78 frames. , ppl: 9.698464334859985], batch size: 70
+2022-12-13 11:47:02,921 INFO [train.py:421] (7/8) Epoch 9, batch 49000, loss[loss=2.409, over 2520.00 frames. , ppl: 11.12772903144172] tot_loss[loss=2.271, over 5593905.58 frames. , ppl: 9.692432623120716], batch size: 70
+2022-12-13 11:47:02,921 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 11:47:03,679 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.644904227803092
+2022-12-13 11:48:42,690 INFO [train.py:421] (7/8) Epoch 9, batch 49200, loss[loss=2.383, over 1050.00 frames. , ppl: 10.836574031700197] tot_loss[loss=2.271, over 5598870.63 frames. , ppl: 9.689162094935178], batch size: 70
+2022-12-13 11:50:20,798 INFO [train.py:421] (7/8) Epoch 9, batch 49400, loss[loss=2.265, over 4550.00 frames. , ppl: 9.634875086493166] tot_loss[loss=2.272, over 5595943.05 frames. , ppl: 9.694251601130606], batch size: 70
+2022-12-13 11:52:05,014 INFO [train.py:421] (7/8) Epoch 9, batch 49600, loss[loss=2.186, over 4410.00 frames. , ppl: 8.899436756470015] tot_loss[loss=2.272, over 5585681.60 frames. , ppl: 9.695600225502934], batch size: 70
+2022-12-13 11:53:47,508 INFO [train.py:421] (7/8) Epoch 9, batch 49800, loss[loss=2.482, over 1610.00 frames. , ppl: 11.969824016913103] tot_loss[loss=2.272, over 5588377.60 frames. , ppl: 9.697156649095117], batch size: 70
+2022-12-13 11:55:28,994 INFO [train.py:421] (7/8) Epoch 9, batch 50000, loss[loss=2.862, over 630.00 frames. , ppl: 17.490120999504825] tot_loss[loss=2.271, over 5617815.84 frames. , ppl: 9.68750326815328], batch size: 70
+2022-12-13 11:55:28,995 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 11:55:29,755 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.643979240614769
+2022-12-13 11:57:09,485 INFO [train.py:421] (7/8) Epoch 9, batch 50200, loss[loss=2.393, over 1470.00 frames. , ppl: 10.944781744344292] tot_loss[loss=2.271, over 5604809.84 frames. , ppl: 9.6911603803467], batch size: 70
+2022-12-13 11:58:51,091 INFO [train.py:421] (7/8) Epoch 9, batch 50400, loss[loss=2.22, over 4480.00 frames. , ppl: 9.210845058559567] tot_loss[loss=2.272, over 5581564.13 frames. , ppl: 9.694462597269819], batch size: 70
+2022-12-13 12:00:30,171 INFO [train.py:421] (7/8) Epoch 9, batch 50600, loss[loss=2.516, over 1190.00 frames. , ppl: 12.373807205319968] tot_loss[loss=2.272, over 5570787.48 frames. , ppl: 9.696121222466314], batch size: 70
+2022-12-13 12:02:07,594 INFO [train.py:421] (7/8) Epoch 9, batch 50800, loss[loss=2.343, over 2520.00 frames. , ppl: 10.411080859766924] tot_loss[loss=2.272, over 5542933.06 frames. , ppl: 9.700408850329262], batch size: 70
+2022-12-13 12:03:46,556 INFO [train.py:421] (7/8) Epoch 9, batch 51000, loss[loss=2.389, over 2310.00 frames. , ppl: 10.90267274010717] tot_loss[loss=2.271, over 5566263.43 frames. , ppl: 9.687727974572455], batch size: 70
+2022-12-13 12:03:46,556 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 12:03:47,301 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.639113099787668
+2022-12-13 12:05:25,877 INFO [train.py:421] (7/8) Epoch 9, batch 51200, loss[loss=2.361, over 1540.00 frames. , ppl: 10.60656535585141] tot_loss[loss=2.271, over 5559529.13 frames. , ppl: 9.686924576203296], batch size: 70
+2022-12-13 12:07:04,785 INFO [train.py:421] (7/8) Epoch 9, batch 51400, loss[loss=2.219, over 3990.00 frames. , ppl: 9.197733183710616] tot_loss[loss=2.271, over 5565705.56 frames. , ppl: 9.685876841638034], batch size: 70
+2022-12-13 12:08:46,932 INFO [train.py:421] (7/8) Epoch 9, batch 51600, loss[loss=2.199, over 2730.00 frames. , ppl: 9.014217786887238] tot_loss[loss=2.271, over 5548344.87 frames. , ppl: 9.69079381813227], batch size: 70
+2022-12-13 12:10:24,705 INFO [train.py:421] (7/8) Epoch 9, batch 51800, loss[loss=3.92, over 350.00 frames. , ppl: 50.406316265605696] tot_loss[loss=2.271, over 5563520.92 frames. , ppl: 9.6862881092886], batch size: 70
+2022-12-13 12:12:05,997 INFO [train.py:421] (7/8) Epoch 9, batch 52000, loss[loss=2.147, over 10850.00 frames. , ppl: 8.55977198649673] tot_loss[loss=2.271, over 5524903.57 frames. , ppl: 9.69342032600654], batch size: 70
+2022-12-13 12:12:05,998 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 12:12:06,730 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.267, over 211138.00 frames. , ppl: 9.646610262463758
+2022-12-13 12:13:45,408 INFO [train.py:421] (7/8) Epoch 9, batch 52200, loss[loss=2.277, over 2730.00 frames. , ppl: 9.74879945802025] tot_loss[loss=2.273, over 5477294.45 frames. , ppl: 9.706039100086532], batch size: 70
+2022-12-13 12:15:24,544 INFO [train.py:421] (7/8) Epoch 9, batch 52400, loss[loss=2.163, over 5390.00 frames. , ppl: 8.69366322213916] tot_loss[loss=2.272, over 5510183.71 frames. , ppl: 9.69584656107752], batch size: 70
+2022-12-13 12:17:07,158 INFO [train.py:421] (7/8) Epoch 9, batch 52600, loss[loss=2.263, over 2310.00 frames. , ppl: 9.608222254279848] tot_loss[loss=2.271, over 5522679.99 frames. , ppl: 9.691853232199188], batch size: 70
+2022-12-13 12:18:50,845 INFO [train.py:421] (7/8) Epoch 9, batch 52800, loss[loss=2.428, over 770.00 frames. , ppl: 11.340604359473057] tot_loss[loss=2.272, over 5510395.40 frames. , ppl: 9.696572806423516], batch size: 70
+2022-12-13 12:20:28,993 INFO [train.py:421] (7/8) Epoch 9, batch 53000, loss[loss=2.27, over 2870.00 frames. , ppl: 9.683402996879716] tot_loss[loss=2.272, over 5493132.34 frames. , ppl: 9.699262686084083], batch size: 70
+2022-12-13 12:20:28,994 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 12:20:29,752 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.642737499169275
+2022-12-13 12:22:10,640 INFO [train.py:421] (7/8) Epoch 9, batch 53200, loss[loss=2.589, over 840.00 frames. , ppl: 13.313488167651649] tot_loss[loss=2.273, over 5457122.21 frames. , ppl: 9.711481652976238], batch size: 70
+2022-12-13 12:23:51,913 INFO [train.py:421] (7/8) Epoch 9, batch 53400, loss[loss=2.31, over 1330.00 frames. , ppl: 10.075632693797479] tot_loss[loss=2.273, over 5455005.96 frames. , ppl: 9.712820560832311], batch size: 70
+2022-12-13 12:25:35,115 INFO [train.py:421] (7/8) Epoch 9, batch 53600, loss[loss=2.143, over 8960.00 frames. , ppl: 8.520863996944534] tot_loss[loss=2.273, over 5464581.93 frames. , ppl: 9.709879187375398], batch size: 70
+2022-12-13 12:27:15,425 INFO [train.py:421] (7/8) Epoch 9, batch 53800, loss[loss=2.227, over 2940.00 frames. , ppl: 9.276605702591612] tot_loss[loss=2.273, over 5466604.67 frames. , ppl: 9.709515071959409], batch size: 70
+2022-12-13 12:28:55,778 INFO [train.py:421] (7/8) Epoch 9, batch 54000, loss[loss=2.226, over 4060.00 frames. , ppl: 9.261873286628651] tot_loss[loss=2.272, over 5495611.80 frames. , ppl: 9.700150495909797], batch size: 70
+2022-12-13 12:28:55,779 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 12:28:56,510 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.633422404126998
+2022-12-13 12:30:35,815 INFO [train.py:421] (7/8) Epoch 9, batch 54200, loss[loss=2.298, over 2870.00 frames. , ppl: 9.959192815549496] tot_loss[loss=2.273, over 5477250.48 frames. , ppl: 9.707388474361226], batch size: 70
+2022-12-13 12:32:16,552 INFO [train.py:421] (7/8) Epoch 9, batch 54400, loss[loss=2.405, over 1190.00 frames. , ppl: 11.075693650844466] tot_loss[loss=2.273, over 5500993.54 frames. , ppl: 9.71107252932392], batch size: 70
+2022-12-13 12:33:55,486 INFO [train.py:421] (7/8) Epoch 9, batch 54600, loss[loss=2.534, over 840.00 frames. , ppl: 12.603341729777329] tot_loss[loss=2.273, over 5488562.59 frames. , ppl: 9.711922720371977], batch size: 70
+2022-12-13 12:35:38,809 INFO [train.py:421] (7/8) Epoch 9, batch 54800, loss[loss=2.235, over 4060.00 frames. , ppl: 9.350620683588698] tot_loss[loss=2.273, over 5495922.48 frames. , ppl: 9.709469204058957], batch size: 70
+2022-12-13 12:37:17,707 INFO [train.py:421] (7/8) Epoch 9, batch 55000, loss[loss=2.267, over 2170.00 frames. , ppl: 9.650434962711802] tot_loss[loss=2.273, over 5502395.77 frames. , ppl: 9.710226692825097], batch size: 70
+2022-12-13 12:37:17,707 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 12:37:18,465 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.64445171527035
+2022-12-13 12:39:02,246 INFO [train.py:421] (7/8) Epoch 9, batch 55200, loss[loss=2.397, over 1680.00 frames. , ppl: 10.9904707857208] tot_loss[loss=2.273, over 5505582.20 frames. , ppl: 9.712738867701988], batch size: 70
+2022-12-13 12:40:39,118 INFO [train.py:421] (7/8) Epoch 9, batch 55400, loss[loss=2.255, over 2870.00 frames. , ppl: 9.532813511588746] tot_loss[loss=2.273, over 5520233.13 frames. , ppl: 9.70756545728343], batch size: 70
+2022-12-13 12:42:18,509 INFO [train.py:421] (7/8) Epoch 9, batch 55600, loss[loss=2.516, over 1120.00 frames. , ppl: 12.380308395557837] tot_loss[loss=2.273, over 5491132.98 frames. , ppl: 9.706078175228527], batch size: 70
+2022-12-13 12:43:58,845 INFO [train.py:421] (7/8) Epoch 9, batch 55800, loss[loss=2.439, over 2030.00 frames. , ppl: 11.458587680813897] tot_loss[loss=2.272, over 5518402.92 frames. , ppl: 9.697757670951216], batch size: 70
+2022-12-13 12:45:38,588 INFO [train.py:421] (7/8) Epoch 9, batch 56000, loss[loss=2.288, over 2870.00 frames. , ppl: 9.852039300598742] tot_loss[loss=2.272, over 5539202.93 frames. , ppl: 9.695097269252056], batch size: 70
+2022-12-13 12:45:38,589 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 12:45:39,335 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.264, over 211138.00 frames. , ppl: 9.625552251361995
+2022-12-13 12:47:19,624 INFO [train.py:421] (7/8) Epoch 9, batch 56200, loss[loss=2.265, over 3430.00 frames. , ppl: 9.633324563108673] tot_loss[loss=2.271, over 5567025.60 frames. , ppl: 9.69079418191512], batch size: 70
+2022-12-13 12:48:56,816 INFO [train.py:421] (7/8) Epoch 9, batch 56400, loss[loss=2.552, over 980.00 frames. , ppl: 12.836301789308994] tot_loss[loss=2.271, over 5564188.24 frames. , ppl: 9.688557163624305], batch size: 70
+2022-12-13 12:50:35,595 INFO [train.py:421] (7/8) Epoch 9, batch 56600, loss[loss=2.435, over 1330.00 frames. , ppl: 11.417778628430016] tot_loss[loss=2.272, over 5538356.35 frames. , ppl: 9.695661417011973], batch size: 70
+2022-12-13 12:52:13,282 INFO [train.py:421] (7/8) Epoch 9, batch 56800, loss[loss=3.651, over 420.00 frames. , ppl: 38.52376579110324] tot_loss[loss=2.272, over 5500977.37 frames. , ppl: 9.69962821990591], batch size: 70
+2022-12-13 12:53:52,634 INFO [train.py:421] (7/8) Epoch 9, batch 57000, loss[loss=2.486, over 1400.00 frames. , ppl: 12.007871527541274] tot_loss[loss=2.272, over 5514133.60 frames. , ppl: 9.700293420353036], batch size: 70
+2022-12-13 12:53:52,634 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 12:53:53,394 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.636780791774152
+2022-12-13 12:55:34,866 INFO [train.py:421] (7/8) Epoch 9, batch 57200, loss[loss=2.232, over 2310.00 frames. , ppl: 9.316268442986807] tot_loss[loss=2.274, over 5467894.42 frames. , ppl: 9.713671143217791], batch size: 70
+2022-12-13 12:57:12,828 INFO [train.py:421] (7/8) Epoch 9, batch 57400, loss[loss=2.402, over 1610.00 frames. , ppl: 11.044351906550926] tot_loss[loss=2.273, over 5463204.45 frames. , ppl: 9.711148977389403], batch size: 70
+2022-12-13 12:58:55,750 INFO [train.py:421] (7/8) Epoch 9, batch 57600, loss[loss=2.389, over 1050.00 frames. , ppl: 10.90248653195254] tot_loss[loss=2.274, over 5436534.10 frames. , ppl: 9.717217693423043], batch size: 70
+2022-12-13 13:00:36,169 INFO [train.py:421] (7/8) Epoch 9, batch 57800, loss[loss=2.172, over 11410.00 frames. , ppl: 8.774697195966889] tot_loss[loss=2.273, over 5444679.26 frames. , ppl: 9.710630692797498], batch size: 70
+2022-12-13 13:02:18,863 INFO [train.py:421] (7/8) Epoch 9, batch 58000, loss[loss=2.434, over 1540.00 frames. , ppl: 11.403232465964964] tot_loss[loss=2.272, over 5487301.69 frames. , ppl: 9.700205630743762], batch size: 70
+2022-12-13 13:02:18,864 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 13:02:19,612 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.635025157347723
+2022-12-13 13:04:04,621 INFO [train.py:421] (7/8) Epoch 9, batch 58200, loss[loss=2.341, over 1260.00 frames. , ppl: 10.390720255387802] tot_loss[loss=2.271, over 5505290.49 frames. , ppl: 9.691946083820195], batch size: 70
+2022-12-13 13:05:43,766 INFO [train.py:421] (7/8) Epoch 9, batch 58400, loss[loss=2.297, over 2590.00 frames. , ppl: 9.945693962514765] tot_loss[loss=2.27, over 5523925.19 frames. , ppl: 9.68406808872539], batch size: 70
+2022-12-13 13:07:23,478 INFO [train.py:421] (7/8) Epoch 9, batch 58600, loss[loss=2.307, over 2870.00 frames. , ppl: 10.039342903944526] tot_loss[loss=2.271, over 5511960.71 frames. , ppl: 9.6932645932602], batch size: 70
+2022-12-13 13:09:02,106 INFO [train.py:421] (7/8) Epoch 9, batch 58800, loss[loss=2.348, over 1260.00 frames. , ppl: 10.465203359660787] tot_loss[loss=2.271, over 5516451.32 frames. , ppl: 9.6911300466218], batch size: 70
+2022-12-13 13:10:46,533 INFO [train.py:421] (7/8) Epoch 9, batch 59000, loss[loss=2.355, over 1750.00 frames. , ppl: 10.533275501206084] tot_loss[loss=2.272, over 5521897.39 frames. , ppl: 9.697936842570684], batch size: 70
+2022-12-13 13:10:46,534 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 13:10:47,278 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.634386305600566
+2022-12-13 13:12:26,045 INFO [train.py:421] (7/8) Epoch 9, batch 59200, loss[loss=2.257, over 2870.00 frames. , ppl: 9.556905591075047] tot_loss[loss=2.272, over 5509008.82 frames. , ppl: 9.69395054503254], batch size: 70
+2022-12-13 13:14:06,376 INFO [train.py:421] (7/8) Epoch 9, batch 59400, loss[loss=2.31, over 2450.00 frames. , ppl: 10.076611405470352] tot_loss[loss=2.271, over 5499299.74 frames. , ppl: 9.692969755404187], batch size: 70
+2022-12-13 13:15:48,494 INFO [train.py:421] (7/8) Epoch 9, batch 59600, loss[loss=2.236, over 3220.00 frames. , ppl: 9.352826997559953] tot_loss[loss=2.271, over 5503565.21 frames. , ppl: 9.693333329062483], batch size: 70
+2022-12-13 13:17:26,950 INFO [train.py:421] (7/8) Epoch 9, batch 59800, loss[loss=2.274, over 1610.00 frames. , ppl: 9.714934626233001] tot_loss[loss=2.273, over 5467268.21 frames. , ppl: 9.706481966573453], batch size: 70
+2022-12-13 13:19:05,928 INFO [train.py:421] (7/8) Epoch 9, batch 60000, loss[loss=2.311, over 2380.00 frames. , ppl: 10.086952715166404] tot_loss[loss=2.273, over 5459612.24 frames. , ppl: 9.705311910410622], batch size: 70
+2022-12-13 13:19:05,929 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 13:19:06,687 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.63870508346662
+2022-12-13 13:20:45,794 INFO [train.py:421] (7/8) Epoch 9, batch 60200, loss[loss=2.279, over 3080.00 frames. , ppl: 9.769830280996233] tot_loss[loss=2.272, over 5475857.04 frames. , ppl: 9.70204097504237], batch size: 70
+2022-12-13 13:22:24,272 INFO [train.py:421] (7/8) Epoch 9, batch 60400, loss[loss=2.138, over 4340.00 frames. , ppl: 8.479982306765084] tot_loss[loss=2.272, over 5452205.23 frames. , ppl: 9.70203092506229], batch size: 70
+2022-12-13 13:24:05,150 INFO [train.py:421] (7/8) Epoch 9, batch 60600, loss[loss=2.167, over 3010.00 frames. , ppl: 8.7303090336842] tot_loss[loss=2.272, over 5464748.45 frames. , ppl: 9.695719582369561], batch size: 70
+2022-12-13 13:25:47,348 INFO [train.py:421] (7/8) Epoch 9, batch 60800, loss[loss=2.313, over 2940.00 frames. , ppl: 10.109714815871728] tot_loss[loss=2.271, over 5496982.88 frames. , ppl: 9.689879909241956], batch size: 70
+2022-12-13 13:27:25,583 INFO [train.py:421] (7/8) Epoch 9, batch 61000, loss[loss=2.302, over 2730.00 frames. , ppl: 9.994558203497972] tot_loss[loss=2.272, over 5468604.85 frames. , ppl: 9.698511034064017], batch size: 70
+2022-12-13 13:27:25,584 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 13:27:26,343 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.267, over 211138.00 frames. , ppl: 9.648386572270214
+2022-12-13 13:29:06,971 INFO [train.py:421] (7/8) Epoch 9, batch 61200, loss[loss=2.227, over 6510.00 frames. , ppl: 9.269305515424685] tot_loss[loss=2.272, over 5467026.20 frames. , ppl: 9.700667519698976], batch size: 70
+2022-12-13 13:30:44,602 INFO [train.py:421] (7/8) Epoch 9, batch 61400, loss[loss=2.245, over 6020.00 frames. , ppl: 9.43695272945495] tot_loss[loss=2.274, over 5418181.49 frames. , ppl: 9.71837694123351], batch size: 70
+2022-12-13 13:32:23,424 INFO [train.py:421] (7/8) Epoch 9, batch 61600, loss[loss=4.117, over 350.00 frames. , ppl: 61.38739923117468] tot_loss[loss=2.274, over 5416869.96 frames. , ppl: 9.715623394180502], batch size: 70
+2022-12-13 13:34:08,412 INFO [train.py:421] (7/8) Epoch 9, batch 61800, loss[loss=2.284, over 2730.00 frames. , ppl: 9.811646915650332] tot_loss[loss=2.274, over 5428974.75 frames. , ppl: 9.719467633673014], batch size: 70
+2022-12-13 13:35:49,228 INFO [train.py:421] (7/8) Epoch 9, batch 62000, loss[loss=2.604, over 700.00 frames. , ppl: 13.522039911887427] tot_loss[loss=2.274, over 5449168.43 frames. , ppl: 9.720183830413145], batch size: 70
+2022-12-13 13:35:49,229 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 13:35:49,993 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.263, over 211138.00 frames. , ppl: 9.615221936937656
+2022-12-13 13:37:32,300 INFO [train.py:421] (7/8) Epoch 9, batch 62200, loss[loss=2.648, over 700.00 frames. , ppl: 14.128773810646875] tot_loss[loss=2.274, over 5462335.59 frames. , ppl: 9.713687876416714], batch size: 70
+2022-12-13 13:39:16,071 INFO [train.py:421] (7/8) Epoch 9, batch 62400, loss[loss=2.143, over 5460.00 frames. , ppl: 8.522666485618506] tot_loss[loss=2.273, over 5504814.29 frames. , ppl: 9.707569244419826], batch size: 70
+2022-12-13 13:40:53,822 INFO [train.py:421] (7/8) Epoch 9, batch 62600, loss[loss=2.571, over 980.00 frames. , ppl: 13.07518395934662] tot_loss[loss=2.273, over 5496211.77 frames. , ppl: 9.710592445369512], batch size: 70
+2022-12-13 13:42:33,900 INFO [train.py:421] (7/8) Epoch 9, batch 62800, loss[loss=3.082, over 560.00 frames. , ppl: 21.805210623443866] tot_loss[loss=2.272, over 5487286.72 frames. , ppl: 9.70306433546219], batch size: 70
+2022-12-13 13:44:11,463 INFO [train.py:421] (7/8) Epoch 9, batch 63000, loss[loss=2.454, over 1330.00 frames. , ppl: 11.634052458635173] tot_loss[loss=2.273, over 5463065.91 frames. , ppl: 9.706889935545822], batch size: 70
+2022-12-13 13:44:11,464 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 13:44:12,223 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.266, over 211138.00 frames. , ppl: 9.639786507154147
+2022-12-13 13:45:47,947 INFO [train.py:421] (7/8) Epoch 9, batch 63200, loss[loss=3.246, over 490.00 frames. , ppl: 25.689114527999138] tot_loss[loss=2.273, over 5458038.27 frames. , ppl: 9.711890119252772], batch size: 70
+2022-12-13 13:47:29,990 INFO [train.py:421] (7/8) Epoch 9, batch 63400, loss[loss=2.25, over 3290.00 frames. , ppl: 9.492099165679772] tot_loss[loss=2.272, over 5465678.58 frames. , ppl: 9.700995188458434], batch size: 70
+2022-12-13 13:49:09,473 INFO [train.py:421] (7/8) Epoch 9, batch 63600, loss[loss=2.165, over 1260.00 frames. , ppl: 8.715281758505132] tot_loss[loss=2.271, over 5495902.17 frames. , ppl: 9.690664930958258], batch size: 70
+2022-12-13 13:50:48,805 INFO [train.py:421] (7/8) Epoch 9, batch 63800, loss[loss=2.228, over 5250.00 frames. , ppl: 9.283374149450816] tot_loss[loss=2.271, over 5518267.13 frames. , ppl: 9.68554074226221], batch size: 70
+2022-12-13 13:52:29,001 INFO [train.py:421] (7/8) Epoch 9, batch 64000, loss[loss=2.457, over 1120.00 frames. , ppl: 11.675544319036486] tot_loss[loss=2.27, over 5541439.13 frames. , ppl: 9.6803916884227], batch size: 70
+2022-12-13 13:52:29,001 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 13:52:29,747 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.627401629350286
+2022-12-13 13:54:05,565 INFO [train.py:421] (7/8) Epoch 9, batch 64200, loss[loss=2.515, over 840.00 frames. , ppl: 12.368547683410311] tot_loss[loss=2.271, over 5525914.65 frames. , ppl: 9.692826725657223], batch size: 70
+2022-12-13 13:55:48,758 INFO [train.py:421] (7/8) Epoch 9, batch 64400, loss[loss=2.199, over 2520.00 frames. , ppl: 9.017525141541423] tot_loss[loss=2.271, over 5532127.74 frames. , ppl: 9.690238834809293], batch size: 70
+2022-12-13 13:57:26,853 INFO [train.py:421] (7/8) Epoch 9, batch 64600, loss[loss=2.487, over 770.00 frames. , ppl: 12.026885106249885] tot_loss[loss=2.272, over 5503973.93 frames. , ppl: 9.698731889027583], batch size: 70
+2022-12-13 13:59:05,998 INFO [train.py:421] (7/8) Epoch 9, batch 64800, loss[loss=2.211, over 4480.00 frames. , ppl: 9.127632278352038] tot_loss[loss=2.273, over 5466613.72 frames. , ppl: 9.708639010024717], batch size: 70
+2022-12-13 14:00:44,198 INFO [train.py:421] (7/8) Epoch 9, batch 65000, loss[loss=2.215, over 4900.00 frames. , ppl: 9.157790982013633] tot_loss[loss=2.274, over 5455182.67 frames. , ppl: 9.71452786474677], batch size: 70
+2022-12-13 14:00:44,199 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 14:00:44,934 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.633545025291745
+2022-12-13 14:02:29,168 INFO [train.py:421] (7/8) Epoch 9, batch 65200, loss[loss=2.676, over 700.00 frames. , ppl: 14.52848982746928] tot_loss[loss=2.273, over 5495868.95 frames. , ppl: 9.70397471094015], batch size: 70
+2022-12-13 14:04:10,422 INFO [train.py:421] (7/8) Epoch 9, batch 65400, loss[loss=2.324, over 2870.00 frames. , ppl: 10.219863713382084] tot_loss[loss=2.271, over 5536082.01 frames. , ppl: 9.692369030520544], batch size: 70
+2022-12-13 14:05:48,253 INFO [train.py:421] (7/8) Epoch 9, batch 65600, loss[loss=2.244, over 3290.00 frames. , ppl: 9.433823780630094] tot_loss[loss=2.271, over 5553761.58 frames. , ppl: 9.685269582630964], batch size: 70
+2022-12-13 14:07:28,832 INFO [train.py:421] (7/8) Epoch 9, batch 65800, loss[loss=2.21, over 4690.00 frames. , ppl: 9.116821910753266] tot_loss[loss=2.272, over 5536839.36 frames. , ppl: 9.693977883593371], batch size: 70
+2022-12-13 14:09:11,364 INFO [train.py:421] (7/8) Epoch 9, batch 66000, loss[loss=2.275, over 2100.00 frames. , ppl: 9.723943429680267] tot_loss[loss=2.272, over 5522394.43 frames. , ppl: 9.69476813877421], batch size: 70
+2022-12-13 14:09:11,364 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 14:09:12,123 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.633080213783197
+2022-12-13 14:10:51,441 INFO [train.py:421] (7/8) Epoch 9, batch 66200, loss[loss=2.253, over 2590.00 frames. , ppl: 9.517321935571365] tot_loss[loss=2.27, over 5553903.53 frames. , ppl: 9.681637769680806], batch size: 70
+2022-12-13 14:12:30,194 INFO [train.py:421] (7/8) Epoch 9, batch 66400, loss[loss=2.577, over 770.00 frames. , ppl: 13.158662254866451] tot_loss[loss=2.27, over 5559666.43 frames. , ppl: 9.679656173900227], batch size: 70
+2022-12-13 14:14:07,586 INFO [train.py:421] (7/8) Epoch 9, batch 66600, loss[loss=2.27, over 2730.00 frames. , ppl: 9.674783328642913] tot_loss[loss=2.271, over 5519304.13 frames. , ppl: 9.690286557089777], batch size: 70
+2022-12-13 14:15:45,372 INFO [train.py:421] (7/8) Epoch 9, batch 66800, loss[loss=2.463, over 980.00 frames. , ppl: 11.7356391298116] tot_loss[loss=2.272, over 5528944.29 frames. , ppl: 9.69552368428992], batch size: 70
+2022-12-13 14:17:23,669 INFO [train.py:421] (7/8) Epoch 9, batch 67000, loss[loss=3.673, over 420.00 frames. , ppl: 39.36486437904046] tot_loss[loss=2.272, over 5501390.71 frames. , ppl: 9.7031781112111], batch size: 70
+2022-12-13 14:17:23,670 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 14:17:24,429 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.635444426828531
+2022-12-13 14:19:04,965 INFO [train.py:421] (7/8) Epoch 9, batch 67200, loss[loss=2.347, over 1680.00 frames. , ppl: 10.45250409463472] tot_loss[loss=2.272, over 5516474.98 frames. , ppl: 9.699126365762366], batch size: 70
+2022-12-13 14:20:42,270 INFO [train.py:421] (7/8) Epoch 9, batch 67400, loss[loss=2.378, over 1820.00 frames. , ppl: 10.785866364745143] tot_loss[loss=2.272, over 5517351.01 frames. , ppl: 9.701651523246438], batch size: 70
+2022-12-13 14:22:19,562 INFO [train.py:421] (7/8) Epoch 9, batch 67600, loss[loss=2.338, over 1750.00 frames. , ppl: 10.361229118083322] tot_loss[loss=2.273, over 5489711.33 frames. , ppl: 9.708939490096192], batch size: 70
+2022-12-13 14:23:58,430 INFO [train.py:421] (7/8) Epoch 9, batch 67800, loss[loss=2.313, over 3010.00 frames. , ppl: 10.10670766902477] tot_loss[loss=2.273, over 5503094.79 frames. , ppl: 9.713290218356558], batch size: 70
+2022-12-13 14:25:36,735 INFO [train.py:421] (7/8) Epoch 9, batch 68000, loss[loss=2.539, over 1190.00 frames. , ppl: 12.66160022021923] tot_loss[loss=2.273, over 5512138.73 frames. , ppl: 9.711550500194452], batch size: 70
+2022-12-13 14:25:36,736 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 14:25:37,495 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.264, over 211138.00 frames. , ppl: 9.621968490265408
+2022-12-13 14:27:17,468 INFO [train.py:421] (7/8) Epoch 9, batch 68200, loss[loss=2.211, over 4970.00 frames. , ppl: 9.126455704987931] tot_loss[loss=2.273, over 5519885.49 frames. , ppl: 9.70709409953414], batch size: 70
+2022-12-13 14:28:57,912 INFO [train.py:421] (7/8) Epoch 9, batch 68400, loss[loss=2.544, over 840.00 frames. , ppl: 12.729310378809036] tot_loss[loss=2.273, over 5525431.72 frames. , ppl: 9.707806211550935], batch size: 70
+2022-12-13 14:30:42,246 INFO [train.py:421] (7/8) Epoch 9, batch 68600, loss[loss=2.305, over 2870.00 frames. , ppl: 10.025507220849818] tot_loss[loss=2.273, over 5542647.44 frames. , ppl: 9.703932994113023], batch size: 70
+2022-12-13 14:32:21,734 INFO [train.py:421] (7/8) Epoch 9, batch 68800, loss[loss=2.391, over 1400.00 frames. , ppl: 10.920019933846687] tot_loss[loss=2.273, over 5522590.07 frames. , ppl: 9.710412770105442], batch size: 70
+2022-12-13 14:34:01,339 INFO [train.py:421] (7/8) Epoch 9, batch 69000, loss[loss=2.386, over 1400.00 frames. , ppl: 10.866511129695683] tot_loss[loss=2.274, over 5488420.73 frames. , ppl: 9.719383479240584], batch size: 70
+2022-12-13 14:34:01,340 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 14:34:02,096 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.634126784178106
+2022-12-13 14:35:35,881 INFO [train.py:421] (7/8) Epoch 9, batch 69200, loss[loss=2.421, over 1120.00 frames. , ppl: 11.262005046635883] tot_loss[loss=2.273, over 5505014.88 frames. , ppl: 9.710190584232176], batch size: 70
+2022-12-13 14:37:12,959 INFO [train.py:421] (7/8) Epoch 9, batch 69400, loss[loss=2.311, over 2520.00 frames. , ppl: 10.080164129517538] tot_loss[loss=2.273, over 5530486.76 frames. , ppl: 9.706821644868182], batch size: 70
+2022-12-13 14:38:55,420 INFO [train.py:421] (7/8) Epoch 9, batch 69600, loss[loss=2.217, over 2240.00 frames. , ppl: 9.181661764576276] tot_loss[loss=2.273, over 5526738.75 frames. , ppl: 9.712254226701777], batch size: 70
+2022-12-13 14:40:38,306 INFO [train.py:421] (7/8) Epoch 9, batch 69800, loss[loss=2.365, over 2030.00 frames. , ppl: 10.642913396074658] tot_loss[loss=2.274, over 5482158.03 frames. , ppl: 9.720663148016222], batch size: 70
+2022-12-13 14:42:20,435 INFO [train.py:421] (7/8) Epoch 9, batch 70000, loss[loss=2.294, over 2590.00 frames. , ppl: 9.912449334035639] tot_loss[loss=2.274, over 5483870.24 frames. , ppl: 9.718450538671283], batch size: 70
+2022-12-13 14:42:20,436 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 14:42:21,216 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.265, over 211138.00 frames. , ppl: 9.632411551904289
+2022-12-13 14:44:01,646 INFO [train.py:421] (7/8) Epoch 9, batch 70200, loss[loss=2.342, over 3010.00 frames. , ppl: 10.406858478503144] tot_loss[loss=2.275, over 5485544.04 frames. , ppl: 9.723365833255887], batch size: 70
+2022-12-13 14:45:43,983 INFO [train.py:421] (7/8) Epoch 9, batch 70400, loss[loss=2.149, over 4410.00 frames. , ppl: 8.572107996672626] tot_loss[loss=2.274, over 5508307.86 frames. , ppl: 9.721598271216392], batch size: 70
+2022-12-13 14:47:24,088 INFO [train.py:421] (7/8) Epoch 9, batch 70600, loss[loss=2.222, over 5180.00 frames. , ppl: 9.226877099330373] tot_loss[loss=2.274, over 5545800.96 frames. , ppl: 9.713492631567183], batch size: 70
+2022-12-13 14:49:06,612 INFO [train.py:421] (7/8) Epoch 9, batch 70800, loss[loss=3.094, over 560.00 frames. , ppl: 22.070637174575534] tot_loss[loss=2.273, over 5561101.71 frames. , ppl: 9.708402726989872], batch size: 70
+2022-12-13 14:50:45,767 INFO [train.py:421] (7/8) Epoch 9, batch 71000, loss[loss=2.417, over 1680.00 frames. , ppl: 11.215109198628479] tot_loss[loss=2.274, over 5536942.72 frames. , ppl: 9.714806746233856], batch size: 70
+2022-12-13 14:50:45,767 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 14:50:46,533 INFO [train.py:452] (7/8) Epoch 9, validation: loss=2.264, over 211138.00 frames. , ppl: 9.622304589200576
+2022-12-13 14:52:28,174 INFO [train.py:421] (7/8) Epoch 9, batch 71200, loss[loss=3.349, over 490.00 frames. , ppl: 28.464259698188474] tot_loss[loss=2.274, over 5521923.31 frames. , ppl: 9.716136584500594], batch size: 70
+2022-12-13 14:54:10,838 INFO [train.py:421] (7/8) Epoch 9, batch 71400, loss[loss=2.309, over 1470.00 frames. , ppl: 10.06294782015499] tot_loss[loss=2.275, over 5497599.91 frames. , ppl: 9.726249178302215], batch size: 70
+2022-12-13 14:55:50,276 INFO [train.py:421] (7/8) Epoch 9, batch 71600, loss[loss=2.221, over 2870.00 frames. , ppl: 9.216735735191024] tot_loss[loss=2.275, over 5455915.11 frames. , ppl: 9.73250238375246], batch size: 70
+2022-12-13 14:57:34,041 INFO [train.py:421] (7/8) Epoch 9, batch 71800, loss[loss=2.197, over 1610.00 frames. , ppl: 9.000200200804715] tot_loss[loss=2.276, over 5429544.19 frames. , ppl: 9.738909616687575], batch size: 70
+2022-12-13 14:58:47,405 INFO [train.py:421] (7/8) Epoch 10, batch 0, loss[loss=2.393, over 1820.00 frames. , ppl: 10.945313094251405] tot_loss[loss=2.393, over 1820.00 frames. , ppl: 10.945313094251405], batch size: 70
+2022-12-13 15:00:28,720 INFO [train.py:421] (7/8) Epoch 10, batch 200, loss[loss=2.281, over 3150.00 frames. , ppl: 9.789480969474146] tot_loss[loss=2.263, over 520791.71 frames. , ppl: 9.614854390332212], batch size: 70
+2022-12-13 15:02:15,468 INFO [train.py:421] (7/8) Epoch 10, batch 400, loss[loss=2.135, over 4200.00 frames. , ppl: 8.459007224111165] tot_loss[loss=2.262, over 996220.71 frames. , ppl: 9.605650644851972], batch size: 70
+2022-12-13 15:03:56,690 INFO [train.py:421] (7/8) Epoch 10, batch 600, loss[loss=2.269, over 2310.00 frames. , ppl: 9.671977484879477] tot_loss[loss=2.261, over 1429494.97 frames. , ppl: 9.594290489105855], batch size: 70
+2022-12-13 15:05:40,251 INFO [train.py:421] (7/8) Epoch 10, batch 800, loss[loss=2.836, over 700.00 frames. , ppl: 17.04066725124496] tot_loss[loss=2.261, over 1813005.40 frames. , ppl: 9.596045333106744], batch size: 70
+2022-12-13 15:07:21,188 INFO [train.py:421] (7/8) Epoch 10, batch 1000, loss[loss=2.57, over 700.00 frames. , ppl: 13.072012030280762] tot_loss[loss=2.259, over 2188572.97 frames. , ppl: 9.573372237552078], batch size: 70
+2022-12-13 15:07:21,188 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 15:07:21,948 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.266, over 211138.00 frames. , ppl: 9.636474138823111
+2022-12-13 15:09:07,573 INFO [train.py:421] (7/8) Epoch 10, batch 1200, loss[loss=2.194, over 7700.00 frames. , ppl: 8.97325446925599] tot_loss[loss=2.262, over 2483506.13 frames. , ppl: 9.600231204332312], batch size: 70
+2022-12-13 15:10:54,475 INFO [train.py:421] (7/8) Epoch 10, batch 1400, loss[loss=2.208, over 4410.00 frames. , ppl: 9.094244743219654] tot_loss[loss=2.264, over 2759360.62 frames. , ppl: 9.618084796984531], batch size: 70
+2022-12-13 15:12:36,517 INFO [train.py:421] (7/8) Epoch 10, batch 1600, loss[loss=2.365, over 1470.00 frames. , ppl: 10.640117181269934] tot_loss[loss=2.264, over 3021085.75 frames. , ppl: 9.624264908400539], batch size: 70
+2022-12-13 15:14:19,426 INFO [train.py:421] (7/8) Epoch 10, batch 1800, loss[loss=2.469, over 910.00 frames. , ppl: 11.80900225665896] tot_loss[loss=2.265, over 3233173.73 frames. , ppl: 9.635190804935554], batch size: 70
+2022-12-13 15:16:01,289 INFO [train.py:421] (7/8) Epoch 10, batch 2000, loss[loss=2.344, over 980.00 frames. , ppl: 10.427640289486282] tot_loss[loss=2.267, over 3422563.12 frames. , ppl: 9.64714927839262], batch size: 70
+2022-12-13 15:16:01,290 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 15:16:02,057 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.265, over 211138.00 frames. , ppl: 9.634249414308712
+2022-12-13 15:17:44,578 INFO [train.py:421] (7/8) Epoch 10, batch 2200, loss[loss=2.825, over 700.00 frames. , ppl: 16.86931520080386] tot_loss[loss=2.266, over 3624108.00 frames. , ppl: 9.645071854315672], batch size: 70
+2022-12-13 15:19:27,892 INFO [train.py:421] (7/8) Epoch 10, batch 2400, loss[loss=2.168, over 8330.00 frames. , ppl: 8.737169937103] tot_loss[loss=2.268, over 3754837.66 frames. , ppl: 9.658014195035719], batch size: 70
+2022-12-13 15:21:09,697 INFO [train.py:421] (7/8) Epoch 10, batch 2600, loss[loss=2.179, over 6020.00 frames. , ppl: 8.840388104537315] tot_loss[loss=2.268, over 3905206.09 frames. , ppl: 9.657229978677115], batch size: 70
+2022-12-13 15:22:53,437 INFO [train.py:421] (7/8) Epoch 10, batch 2800, loss[loss=2.483, over 1120.00 frames. , ppl: 11.977953572169868] tot_loss[loss=2.265, over 4109301.85 frames. , ppl: 9.632358571838846], batch size: 70
+2022-12-13 15:24:36,434 INFO [train.py:421] (7/8) Epoch 10, batch 3000, loss[loss=2.397, over 1190.00 frames. , ppl: 10.986185890644414] tot_loss[loss=2.266, over 4235988.21 frames. , ppl: 9.636967053519081], batch size: 70
+2022-12-13 15:24:36,435 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 15:24:37,197 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.624782969170553
+2022-12-13 15:26:21,717 INFO [train.py:421] (7/8) Epoch 10, batch 3200, loss[loss=1.975, over 3290.00 frames. , ppl: 7.2075502323805845] tot_loss[loss=2.266, over 4337388.71 frames. , ppl: 9.642878186393407], batch size: 70
+2022-12-13 15:28:06,755 INFO [train.py:421] (7/8) Epoch 10, batch 3400, loss[loss=2.231, over 4550.00 frames. , ppl: 9.31085268147655] tot_loss[loss=2.267, over 4409157.04 frames. , ppl: 9.654380252744287], batch size: 70
+2022-12-13 15:29:50,699 INFO [train.py:421] (7/8) Epoch 10, batch 3600, loss[loss=2.236, over 4200.00 frames. , ppl: 9.353875815309648] tot_loss[loss=2.267, over 4522419.18 frames. , ppl: 9.645998420553319], batch size: 70
+2022-12-13 15:31:33,969 INFO [train.py:421] (7/8) Epoch 10, batch 3800, loss[loss=2.421, over 2170.00 frames. , ppl: 11.260968325244857] tot_loss[loss=2.267, over 4597516.50 frames. , ppl: 9.651057153595248], batch size: 70
+2022-12-13 15:33:14,209 INFO [train.py:421] (7/8) Epoch 10, batch 4000, loss[loss=2.428, over 1610.00 frames. , ppl: 11.330866728436932] tot_loss[loss=2.268, over 4648240.00 frames. , ppl: 9.664421949536756], batch size: 70
+2022-12-13 15:33:14,209 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 15:33:14,973 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.266, over 211138.00 frames. , ppl: 9.6403101424268
+2022-12-13 15:34:56,310 INFO [train.py:421] (7/8) Epoch 10, batch 4200, loss[loss=2.238, over 5040.00 frames. , ppl: 9.375659719720428] tot_loss[loss=2.267, over 4770937.75 frames. , ppl: 9.647313683625002], batch size: 70
+2022-12-13 15:36:36,712 INFO [train.py:421] (7/8) Epoch 10, batch 4400, loss[loss=2.355, over 1610.00 frames. , ppl: 10.541691732881874] tot_loss[loss=2.265, over 4902853.53 frames. , ppl: 9.62696525486247], batch size: 70
+2022-12-13 15:38:18,551 INFO [train.py:421] (7/8) Epoch 10, batch 4600, loss[loss=2.255, over 1680.00 frames. , ppl: 9.53389608677019] tot_loss[loss=2.265, over 4948112.51 frames. , ppl: 9.627274671797542], batch size: 70
+2022-12-13 15:39:59,357 INFO [train.py:421] (7/8) Epoch 10, batch 4800, loss[loss=2.578, over 1050.00 frames. , ppl: 13.170092262101875] tot_loss[loss=2.265, over 4986487.29 frames. , ppl: 9.635263817591055], batch size: 70
+2022-12-13 15:41:41,308 INFO [train.py:421] (7/8) Epoch 10, batch 5000, loss[loss=2.308, over 1540.00 frames. , ppl: 10.051274737976579] tot_loss[loss=2.266, over 5041109.69 frames. , ppl: 9.63692869958233], batch size: 70
+2022-12-13 15:41:41,309 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 15:41:42,117 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.265, over 211138.00 frames. , ppl: 9.634593072176935
+2022-12-13 15:43:26,471 INFO [train.py:421] (7/8) Epoch 10, batch 5200, loss[loss=2.27, over 3430.00 frames. , ppl: 9.683123570699777] tot_loss[loss=2.265, over 5117921.97 frames. , ppl: 9.627563286715537], batch size: 70
+2022-12-13 15:45:06,995 INFO [train.py:421] (7/8) Epoch 10, batch 5400, loss[loss=2.36, over 1330.00 frames. , ppl: 10.59324420856354] tot_loss[loss=2.265, over 5149321.70 frames. , ppl: 9.62742125979824], batch size: 70
+2022-12-13 15:46:49,887 INFO [train.py:421] (7/8) Epoch 10, batch 5600, loss[loss=2.243, over 3430.00 frames. , ppl: 9.42135305724256] tot_loss[loss=2.265, over 5192596.15 frames. , ppl: 9.628338760765274], batch size: 70
+2022-12-13 15:48:31,067 INFO [train.py:421] (7/8) Epoch 10, batch 5800, loss[loss=2.383, over 1680.00 frames. , ppl: 10.840197915369457] tot_loss[loss=2.265, over 5251780.46 frames. , ppl: 9.628124971342025], batch size: 70
+2022-12-13 15:50:14,250 INFO [train.py:421] (7/8) Epoch 10, batch 6000, loss[loss=2.56, over 770.00 frames. , ppl: 12.929358238634656] tot_loss[loss=2.263, over 5324243.21 frames. , ppl: 9.61498349151365], batch size: 70
+2022-12-13 15:50:14,250 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 15:50:14,999 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.622741820215266
+2022-12-13 15:51:54,468 INFO [train.py:421] (7/8) Epoch 10, batch 6200, loss[loss=2.318, over 2870.00 frames. , ppl: 10.152828544780043] tot_loss[loss=2.264, over 5316760.76 frames. , ppl: 9.623300235746406], batch size: 70
+2022-12-13 15:53:34,775 INFO [train.py:421] (7/8) Epoch 10, batch 6400, loss[loss=2.164, over 4270.00 frames. , ppl: 8.707367732526219] tot_loss[loss=2.264, over 5321831.68 frames. , ppl: 9.622224913405265], batch size: 70
+2022-12-13 15:55:17,563 INFO [train.py:421] (7/8) Epoch 10, batch 6600, loss[loss=2.384, over 1470.00 frames. , ppl: 10.84404777360147] tot_loss[loss=2.265, over 5320295.80 frames. , ppl: 9.63358636924172], batch size: 70
+2022-12-13 15:56:56,906 INFO [train.py:421] (7/8) Epoch 10, batch 6800, loss[loss=2.319, over 1540.00 frames. , ppl: 10.168164826935326] tot_loss[loss=2.266, over 5295757.16 frames. , ppl: 9.644711792205587], batch size: 70
+2022-12-13 15:58:42,412 INFO [train.py:421] (7/8) Epoch 10, batch 7000, loss[loss=2.296, over 2030.00 frames. , ppl: 9.932224042473406] tot_loss[loss=2.267, over 5285790.37 frames. , ppl: 9.650369461793748], batch size: 70
+2022-12-13 15:58:42,413 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 15:58:43,176 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.266, over 211138.00 frames. , ppl: 9.637175889263702
+2022-12-13 16:00:25,417 INFO [train.py:421] (7/8) Epoch 10, batch 7200, loss[loss=2.817, over 700.00 frames. , ppl: 16.71918304063382] tot_loss[loss=2.268, over 5286035.70 frames. , ppl: 9.661037094767398], batch size: 70
+2022-12-13 16:02:05,001 INFO [train.py:421] (7/8) Epoch 10, batch 7400, loss[loss=2.114, over 3150.00 frames. , ppl: 8.278056063740184] tot_loss[loss=2.27, over 5267871.79 frames. , ppl: 9.67564340373744], batch size: 70
+2022-12-13 16:03:46,148 INFO [train.py:421] (7/8) Epoch 10, batch 7600, loss[loss=2.264, over 1680.00 frames. , ppl: 9.6255708615799] tot_loss[loss=2.27, over 5256159.84 frames. , ppl: 9.679786344465777], batch size: 70
+2022-12-13 16:05:27,151 INFO [train.py:421] (7/8) Epoch 10, batch 7800, loss[loss=2.811, over 630.00 frames. , ppl: 16.62315874947217] tot_loss[loss=2.269, over 5283419.27 frames. , ppl: 9.66909177494684], batch size: 70
+2022-12-13 16:07:06,114 INFO [train.py:421] (7/8) Epoch 10, batch 8000, loss[loss=2.154, over 6650.00 frames. , ppl: 8.622067659791911] tot_loss[loss=2.271, over 5252436.53 frames. , ppl: 9.686086139727074], batch size: 70
+2022-12-13 16:07:06,115 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 16:07:06,898 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.623687560464123
+2022-12-13 16:08:45,827 INFO [train.py:421] (7/8) Epoch 10, batch 8200, loss[loss=2.345, over 1680.00 frames. , ppl: 10.43497766185515] tot_loss[loss=2.271, over 5252818.72 frames. , ppl: 9.689449987623632], batch size: 70
+2022-12-13 16:10:28,729 INFO [train.py:421] (7/8) Epoch 10, batch 8400, loss[loss=2.38, over 1120.00 frames. , ppl: 10.809869881628678] tot_loss[loss=2.269, over 5323045.57 frames. , ppl: 9.66541359609726], batch size: 70
+2022-12-13 16:12:10,319 INFO [train.py:421] (7/8) Epoch 10, batch 8600, loss[loss=2.487, over 980.00 frames. , ppl: 12.022384876809435] tot_loss[loss=2.266, over 5394941.65 frames. , ppl: 9.64536503631396], batch size: 70
+2022-12-13 16:13:50,371 INFO [train.py:421] (7/8) Epoch 10, batch 8800, loss[loss=2.168, over 4970.00 frames. , ppl: 8.744028130553334] tot_loss[loss=2.265, over 5453557.49 frames. , ppl: 9.631582747909524], batch size: 70
+2022-12-13 16:15:29,984 INFO [train.py:421] (7/8) Epoch 10, batch 9000, loss[loss=2.473, over 1540.00 frames. , ppl: 11.852798308345761] tot_loss[loss=2.265, over 5455542.60 frames. , ppl: 9.628690003633322], batch size: 70
+2022-12-13 16:15:29,984 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 16:15:30,747 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.265, over 211138.00 frames. , ppl: 9.634809825352011
+2022-12-13 16:17:11,734 INFO [train.py:421] (7/8) Epoch 10, batch 9200, loss[loss=2.355, over 1540.00 frames. , ppl: 10.542354422696993] tot_loss[loss=2.266, over 5439012.37 frames. , ppl: 9.64069703337374], batch size: 70
+2022-12-13 16:18:52,528 INFO [train.py:421] (7/8) Epoch 10, batch 9400, loss[loss=2.322, over 1960.00 frames. , ppl: 10.194692861471296] tot_loss[loss=2.267, over 5415900.19 frames. , ppl: 9.653343670264807], batch size: 70
+2022-12-13 16:20:35,315 INFO [train.py:421] (7/8) Epoch 10, batch 9600, loss[loss=2.17, over 3710.00 frames. , ppl: 8.755029890176072] tot_loss[loss=2.269, over 5366394.89 frames. , ppl: 9.671377926172992], batch size: 70
+2022-12-13 16:22:23,363 INFO [train.py:421] (7/8) Epoch 10, batch 9800, loss[loss=2.22, over 2940.00 frames. , ppl: 9.203945288991422] tot_loss[loss=2.268, over 5420017.80 frames. , ppl: 9.662380341184813], batch size: 70
+2022-12-13 16:24:04,271 INFO [train.py:421] (7/8) Epoch 10, batch 10000, loss[loss=2.189, over 5880.00 frames. , ppl: 8.922598119204935] tot_loss[loss=2.268, over 5440410.75 frames. , ppl: 9.658764378728021], batch size: 70
+2022-12-13 16:24:04,271 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 16:24:05,013 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.621310567860883
+2022-12-13 16:25:47,066 INFO [train.py:421] (7/8) Epoch 10, batch 10200, loss[loss=2.374, over 2940.00 frames. , ppl: 10.741503981476828] tot_loss[loss=2.27, over 5401708.42 frames. , ppl: 9.677889572573482], batch size: 70
+2022-12-13 16:27:29,193 INFO [train.py:421] (7/8) Epoch 10, batch 10400, loss[loss=2.364, over 1400.00 frames. , ppl: 10.63316349061717] tot_loss[loss=2.269, over 5435534.83 frames. , ppl: 9.66821325733586], batch size: 70
+2022-12-13 16:29:09,732 INFO [train.py:421] (7/8) Epoch 10, batch 10600, loss[loss=2.223, over 3640.00 frames. , ppl: 9.230886653420171] tot_loss[loss=2.27, over 5422589.73 frames. , ppl: 9.683695414394395], batch size: 70
+2022-12-13 16:30:51,418 INFO [train.py:421] (7/8) Epoch 10, batch 10800, loss[loss=2.248, over 3290.00 frames. , ppl: 9.465519374735562] tot_loss[loss=2.271, over 5389844.98 frames. , ppl: 9.691539501792352], batch size: 70
+2022-12-13 16:32:33,734 INFO [train.py:421] (7/8) Epoch 10, batch 11000, loss[loss=2.337, over 2100.00 frames. , ppl: 10.348956523926672] tot_loss[loss=2.272, over 5365978.56 frames. , ppl: 9.699543171057496], batch size: 70
+2022-12-13 16:32:33,735 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 16:32:34,520 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.60629313197587
+2022-12-13 16:34:15,548 INFO [train.py:421] (7/8) Epoch 10, batch 11200, loss[loss=2.504, over 1400.00 frames. , ppl: 12.22849438408136] tot_loss[loss=2.271, over 5381132.51 frames. , ppl: 9.690878783725827], batch size: 70
+2022-12-13 16:35:59,435 INFO [train.py:421] (7/8) Epoch 10, batch 11400, loss[loss=2.215, over 4130.00 frames. , ppl: 9.156855014655878] tot_loss[loss=2.269, over 5435010.97 frames. , ppl: 9.674101093961475], batch size: 70
+2022-12-13 16:37:41,301 INFO [train.py:421] (7/8) Epoch 10, batch 11600, loss[loss=3.003, over 560.00 frames. , ppl: 20.137636087959415] tot_loss[loss=2.269, over 5430566.06 frames. , ppl: 9.67285729461192], batch size: 70
+2022-12-13 16:39:23,732 INFO [train.py:421] (7/8) Epoch 10, batch 11800, loss[loss=2.308, over 2800.00 frames. , ppl: 10.058835986733401] tot_loss[loss=2.268, over 5468279.34 frames. , ppl: 9.66379044589641], batch size: 70
+2022-12-13 16:41:07,320 INFO [train.py:421] (7/8) Epoch 10, batch 12000, loss[loss=2.472, over 1400.00 frames. , ppl: 11.84644015400329] tot_loss[loss=2.269, over 5464943.63 frames. , ppl: 9.669854250772781], batch size: 70
+2022-12-13 16:41:07,320 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 16:41:08,102 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.625352801927015
+2022-12-13 16:42:53,923 INFO [train.py:421] (7/8) Epoch 10, batch 12200, loss[loss=2.314, over 1750.00 frames. , ppl: 10.118860798144892] tot_loss[loss=2.27, over 5448957.45 frames. , ppl: 9.674804654158505], batch size: 70
+2022-12-13 16:44:34,117 INFO [train.py:421] (7/8) Epoch 10, batch 12400, loss[loss=2.375, over 1260.00 frames. , ppl: 10.746031464663666] tot_loss[loss=2.269, over 5465288.68 frames. , ppl: 9.67364791552815], batch size: 70
+2022-12-13 16:46:16,871 INFO [train.py:421] (7/8) Epoch 10, batch 12600, loss[loss=2.303, over 3570.00 frames. , ppl: 10.009079660165817] tot_loss[loss=2.269, over 5468103.95 frames. , ppl: 9.673235316339412], batch size: 70
+2022-12-13 16:47:56,483 INFO [train.py:421] (7/8) Epoch 10, batch 12800, loss[loss=2.281, over 2660.00 frames. , ppl: 9.784996046204965] tot_loss[loss=2.27, over 5416886.84 frames. , ppl: 9.68095655233403], batch size: 70
+2022-12-13 16:49:37,745 INFO [train.py:421] (7/8) Epoch 10, batch 13000, loss[loss=2.256, over 2170.00 frames. , ppl: 9.546828903666029] tot_loss[loss=2.27, over 5435021.49 frames. , ppl: 9.676993088242833], batch size: 70
+2022-12-13 16:49:37,746 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 16:49:38,513 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.265, over 211138.00 frames. , ppl: 9.634478993517094
+2022-12-13 16:51:20,369 INFO [train.py:421] (7/8) Epoch 10, batch 13200, loss[loss=2.517, over 770.00 frames. , ppl: 12.392939811802085] tot_loss[loss=2.269, over 5454881.07 frames. , ppl: 9.672427370646378], batch size: 70
+2022-12-13 16:53:01,610 INFO [train.py:421] (7/8) Epoch 10, batch 13400, loss[loss=2.22, over 1540.00 frames. , ppl: 9.211738940159398] tot_loss[loss=2.27, over 5445495.27 frames. , ppl: 9.676784527615297], batch size: 70
+2022-12-13 16:54:46,216 INFO [train.py:421] (7/8) Epoch 10, batch 13600, loss[loss=2.207, over 3990.00 frames. , ppl: 9.0921517413314] tot_loss[loss=2.269, over 5454695.63 frames. , ppl: 9.67236993175055], batch size: 70
+2022-12-13 16:56:30,070 INFO [train.py:421] (7/8) Epoch 10, batch 13800, loss[loss=2.455, over 1050.00 frames. , ppl: 11.648486370360711] tot_loss[loss=2.27, over 5454951.31 frames. , ppl: 9.67498756162726], batch size: 70
+2022-12-13 16:58:09,139 INFO [train.py:421] (7/8) Epoch 10, batch 14000, loss[loss=2.76, over 840.00 frames. , ppl: 15.802215417237239] tot_loss[loss=2.269, over 5465777.40 frames. , ppl: 9.671081909177342], batch size: 70
+2022-12-13 16:58:09,140 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 16:58:09,934 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.266, over 211138.00 frames. , ppl: 9.641104923874973
+2022-12-13 16:59:47,674 INFO [train.py:421] (7/8) Epoch 10, batch 14200, loss[loss=2.508, over 1470.00 frames. , ppl: 12.280844574111446] tot_loss[loss=2.271, over 5428031.61 frames. , ppl: 9.68506046393841], batch size: 70
+2022-12-13 17:01:29,028 INFO [train.py:421] (7/8) Epoch 10, batch 14400, loss[loss=2.323, over 3710.00 frames. , ppl: 10.201364431217247] tot_loss[loss=2.269, over 5475095.36 frames. , ppl: 9.669488566709985], batch size: 70
+2022-12-13 17:03:10,008 INFO [train.py:421] (7/8) Epoch 10, batch 14600, loss[loss=2.109, over 6440.00 frames. , ppl: 8.237853228491904] tot_loss[loss=2.27, over 5463874.87 frames. , ppl: 9.674702951052694], batch size: 70
+2022-12-13 17:04:50,614 INFO [train.py:421] (7/8) Epoch 10, batch 14800, loss[loss=2.424, over 1190.00 frames. , ppl: 11.286727505329706] tot_loss[loss=2.27, over 5462556.00 frames. , ppl: 9.675543777781334], batch size: 70
+2022-12-13 17:06:32,746 INFO [train.py:421] (7/8) Epoch 10, batch 15000, loss[loss=2.341, over 1750.00 frames. , ppl: 10.39170127704462] tot_loss[loss=2.269, over 5468099.83 frames. , ppl: 9.670579674934961], batch size: 70
+2022-12-13 17:06:32,746 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 17:06:33,530 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.265, over 211138.00 frames. , ppl: 9.634267951557288
+2022-12-13 17:08:12,493 INFO [train.py:421] (7/8) Epoch 10, batch 15200, loss[loss=2.481, over 1050.00 frames. , ppl: 11.95161422023904] tot_loss[loss=2.268, over 5492908.95 frames. , ppl: 9.663912039258378], batch size: 70
+2022-12-13 17:09:58,750 INFO [train.py:421] (7/8) Epoch 10, batch 15400, loss[loss=2.319, over 3080.00 frames. , ppl: 10.169741473800364] tot_loss[loss=2.269, over 5478981.81 frames. , ppl: 9.668333384370436], batch size: 70
+2022-12-13 17:11:43,377 INFO [train.py:421] (7/8) Epoch 10, batch 15600, loss[loss=2.525, over 980.00 frames. , ppl: 12.491508297415368] tot_loss[loss=2.267, over 5518673.59 frames. , ppl: 9.652877429268065], batch size: 70
+2022-12-13 17:13:24,533 INFO [train.py:421] (7/8) Epoch 10, batch 15800, loss[loss=2.415, over 2100.00 frames. , ppl: 11.190246494908939] tot_loss[loss=2.266, over 5591389.86 frames. , ppl: 9.638182490448337], batch size: 70
+2022-12-13 17:15:07,632 INFO [train.py:421] (7/8) Epoch 10, batch 16000, loss[loss=2.404, over 1750.00 frames. , ppl: 11.072756512924927] tot_loss[loss=2.266, over 5589597.16 frames. , ppl: 9.637894535031597], batch size: 70
+2022-12-13 17:15:07,633 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 17:15:08,400 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.61156377960389
+2022-12-13 17:16:51,513 INFO [train.py:421] (7/8) Epoch 10, batch 16200, loss[loss=2.16, over 6090.00 frames. , ppl: 8.674450925741748] tot_loss[loss=2.263, over 5644966.52 frames. , ppl: 9.612579881359643], batch size: 70
+2022-12-13 17:18:33,686 INFO [train.py:421] (7/8) Epoch 10, batch 16400, loss[loss=2.264, over 3710.00 frames. , ppl: 9.621172703241664] tot_loss[loss=2.265, over 5580368.77 frames. , ppl: 9.631962318385366], batch size: 70
+2022-12-13 17:20:17,177 INFO [train.py:421] (7/8) Epoch 10, batch 16600, loss[loss=2.25, over 1890.00 frames. , ppl: 9.483513435622243] tot_loss[loss=2.265, over 5579329.71 frames. , ppl: 9.633437375172864], batch size: 70
+2022-12-13 17:21:59,444 INFO [train.py:421] (7/8) Epoch 10, batch 16800, loss[loss=2.795, over 700.00 frames. , ppl: 16.355262891445516] tot_loss[loss=2.266, over 5556447.69 frames. , ppl: 9.638758972662618], batch size: 70
+2022-12-13 17:23:43,871 INFO [train.py:421] (7/8) Epoch 10, batch 17000, loss[loss=2.595, over 840.00 frames. , ppl: 13.396817866428636] tot_loss[loss=2.267, over 5553717.68 frames. , ppl: 9.649307270012612], batch size: 70
+2022-12-13 17:23:43,872 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 17:23:44,636 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.265, over 211138.00 frames. , ppl: 9.629349702040027
+2022-12-13 17:25:25,466 INFO [train.py:421] (7/8) Epoch 10, batch 17200, loss[loss=2.251, over 2590.00 frames. , ppl: 9.500298897820846] tot_loss[loss=2.268, over 5503131.82 frames. , ppl: 9.664325718056249], batch size: 70
+2022-12-13 17:27:07,628 INFO [train.py:421] (7/8) Epoch 10, batch 17400, loss[loss=2.503, over 840.00 frames. , ppl: 12.21655051267785] tot_loss[loss=2.269, over 5458973.76 frames. , ppl: 9.672205929164267], batch size: 70
+2022-12-13 17:28:48,492 INFO [train.py:421] (7/8) Epoch 10, batch 17600, loss[loss=2.252, over 6300.00 frames. , ppl: 9.506470350056988] tot_loss[loss=2.269, over 5472095.77 frames. , ppl: 9.67084918718323], batch size: 70
+2022-12-13 17:30:34,237 INFO [train.py:421] (7/8) Epoch 10, batch 17800, loss[loss=2.347, over 2310.00 frames. , ppl: 10.449681112466594] tot_loss[loss=2.27, over 5453450.81 frames. , ppl: 9.68279967269817], batch size: 70
+2022-12-13 17:32:15,322 INFO [train.py:421] (7/8) Epoch 10, batch 18000, loss[loss=2.203, over 3850.00 frames. , ppl: 9.054794893893156] tot_loss[loss=2.27, over 5458620.51 frames. , ppl: 9.682102688547594], batch size: 70
+2022-12-13 17:32:15,322 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 17:32:16,072 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.622539580598964
+2022-12-13 17:33:56,552 INFO [train.py:421] (7/8) Epoch 10, batch 18200, loss[loss=2.322, over 1890.00 frames. , ppl: 10.19332309658098] tot_loss[loss=2.268, over 5522237.02 frames. , ppl: 9.660664409126301], batch size: 70
+2022-12-13 17:35:35,512 INFO [train.py:421] (7/8) Epoch 10, batch 18400, loss[loss=2.239, over 3570.00 frames. , ppl: 9.387199339198029] tot_loss[loss=2.27, over 5474202.41 frames. , ppl: 9.675181108423844], batch size: 70
+2022-12-13 17:37:19,304 INFO [train.py:421] (7/8) Epoch 10, batch 18600, loss[loss=2.387, over 1960.00 frames. , ppl: 10.87926308582474] tot_loss[loss=2.269, over 5473329.86 frames. , ppl: 9.667499711640675], batch size: 70
+2022-12-13 17:39:02,831 INFO [train.py:421] (7/8) Epoch 10, batch 18800, loss[loss=2.417, over 1750.00 frames. , ppl: 11.215554599179095] tot_loss[loss=2.269, over 5484680.95 frames. , ppl: 9.666894874747525], batch size: 70
+2022-12-13 17:40:48,048 INFO [train.py:421] (7/8) Epoch 10, batch 19000, loss[loss=2.391, over 1680.00 frames. , ppl: 10.925698128956782] tot_loss[loss=2.269, over 5472722.00 frames. , ppl: 9.665593839613994], batch size: 70
+2022-12-13 17:40:48,048 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 17:40:48,813 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.265, over 211138.00 frames. , ppl: 9.63137799747174
+2022-12-13 17:42:30,792 INFO [train.py:421] (7/8) Epoch 10, batch 19200, loss[loss=2.201, over 6020.00 frames. , ppl: 9.030357344031236] tot_loss[loss=2.268, over 5487732.49 frames. , ppl: 9.662076750393647], batch size: 70
+2022-12-13 17:44:15,187 INFO [train.py:421] (7/8) Epoch 10, batch 19400, loss[loss=2.223, over 2380.00 frames. , ppl: 9.233714545499184] tot_loss[loss=2.268, over 5505202.37 frames. , ppl: 9.661990827847497], batch size: 70
+2022-12-13 17:45:57,131 INFO [train.py:421] (7/8) Epoch 10, batch 19600, loss[loss=2.49, over 1330.00 frames. , ppl: 12.056408028866207] tot_loss[loss=2.268, over 5501277.44 frames. , ppl: 9.664202912173089], batch size: 70
+2022-12-13 17:47:36,296 INFO [train.py:421] (7/8) Epoch 10, batch 19800, loss[loss=2.425, over 1330.00 frames. , ppl: 11.296766015333766] tot_loss[loss=2.27, over 5467839.73 frames. , ppl: 9.676652733032197], batch size: 70
+2022-12-13 17:49:20,607 INFO [train.py:421] (7/8) Epoch 10, batch 20000, loss[loss=2.146, over 4340.00 frames. , ppl: 8.54799946291785] tot_loss[loss=2.269, over 5506249.01 frames. , ppl: 9.670936439948697], batch size: 70
+2022-12-13 17:49:20,608 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 17:49:21,384 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.266, over 211138.00 frames. , ppl: 9.641742794080622
+2022-12-13 17:51:06,013 INFO [train.py:421] (7/8) Epoch 10, batch 20200, loss[loss=2.272, over 2730.00 frames. , ppl: 9.700394336099908] tot_loss[loss=2.27, over 5504546.07 frames. , ppl: 9.675233437065591], batch size: 70
+2022-12-13 17:52:43,990 INFO [train.py:421] (7/8) Epoch 10, batch 20400, loss[loss=2.196, over 4410.00 frames. , ppl: 8.986221823049428] tot_loss[loss=2.269, over 5481717.87 frames. , ppl: 9.669982704729449], batch size: 70
+2022-12-13 17:54:27,190 INFO [train.py:421] (7/8) Epoch 10, batch 20600, loss[loss=2.349, over 1190.00 frames. , ppl: 10.477209110581551] tot_loss[loss=2.269, over 5500530.07 frames. , ppl: 9.66500977982869], batch size: 70
+2022-12-13 17:56:10,935 INFO [train.py:421] (7/8) Epoch 10, batch 20800, loss[loss=2.343, over 1820.00 frames. , ppl: 10.41358227213643] tot_loss[loss=2.268, over 5482747.48 frames. , ppl: 9.664658284303586], batch size: 70
+2022-12-13 17:57:56,885 INFO [train.py:421] (7/8) Epoch 10, batch 21000, loss[loss=2.196, over 3500.00 frames. , ppl: 8.992490030549414] tot_loss[loss=2.268, over 5501657.51 frames. , ppl: 9.655821312671726], batch size: 70
+2022-12-13 17:57:56,885 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 17:57:57,648 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.622576610069983
+2022-12-13 17:59:39,846 INFO [train.py:421] (7/8) Epoch 10, batch 21200, loss[loss=2.15, over 5390.00 frames. , ppl: 8.587941770029607] tot_loss[loss=2.267, over 5531434.77 frames. , ppl: 9.65441293997558], batch size: 70
+2022-12-13 18:01:19,793 INFO [train.py:421] (7/8) Epoch 10, batch 21400, loss[loss=2.132, over 4480.00 frames. , ppl: 8.430262178141597] tot_loss[loss=2.267, over 5548642.51 frames. , ppl: 9.647588158521133], batch size: 70
+2022-12-13 18:03:00,310 INFO [train.py:421] (7/8) Epoch 10, batch 21600, loss[loss=2.381, over 1610.00 frames. , ppl: 10.813215002566896] tot_loss[loss=2.268, over 5508304.41 frames. , ppl: 9.655367959283202], batch size: 70
+2022-12-13 18:04:42,566 INFO [train.py:421] (7/8) Epoch 10, batch 21800, loss[loss=2.268, over 4550.00 frames. , ppl: 9.66308972476289] tot_loss[loss=2.267, over 5504107.29 frames. , ppl: 9.653502039632508], batch size: 70
+2022-12-13 18:06:24,589 INFO [train.py:421] (7/8) Epoch 10, batch 22000, loss[loss=2.725, over 770.00 frames. , ppl: 15.250281480688084] tot_loss[loss=2.266, over 5528853.98 frames. , ppl: 9.644468965437033], batch size: 70
+2022-12-13 18:06:24,590 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 18:06:25,356 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.620783692748795
+2022-12-13 18:08:04,750 INFO [train.py:421] (7/8) Epoch 10, batch 22200, loss[loss=2.364, over 3010.00 frames. , ppl: 10.633443705683066] tot_loss[loss=2.268, over 5463752.93 frames. , ppl: 9.65944484247374], batch size: 70
+2022-12-13 18:09:43,514 INFO [train.py:421] (7/8) Epoch 10, batch 22400, loss[loss=2.258, over 4410.00 frames. , ppl: 9.567181499796225] tot_loss[loss=2.269, over 5434678.80 frames. , ppl: 9.665231688807296], batch size: 70
+2022-12-13 18:11:22,901 INFO [train.py:421] (7/8) Epoch 10, batch 22600, loss[loss=2.347, over 2800.00 frames. , ppl: 10.450168776955914] tot_loss[loss=2.268, over 5442058.18 frames. , ppl: 9.662028280946931], batch size: 70
+2022-12-13 18:13:02,880 INFO [train.py:421] (7/8) Epoch 10, batch 22800, loss[loss=2.177, over 4270.00 frames. , ppl: 8.818506244211134] tot_loss[loss=2.269, over 5451948.95 frames. , ppl: 9.665596344217393], batch size: 70
+2022-12-13 18:14:48,431 INFO [train.py:421] (7/8) Epoch 10, batch 23000, loss[loss=2.443, over 1120.00 frames. , ppl: 11.507475524254263] tot_loss[loss=2.267, over 5509577.12 frames. , ppl: 9.648448950706895], batch size: 70
+2022-12-13 18:14:48,431 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 18:14:49,200 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.624770148321595
+2022-12-13 18:16:34,755 INFO [train.py:421] (7/8) Epoch 10, batch 23200, loss[loss=2.23, over 3640.00 frames. , ppl: 9.297146148716523] tot_loss[loss=2.266, over 5519137.36 frames. , ppl: 9.644885079724132], batch size: 70
+2022-12-13 18:18:16,614 INFO [train.py:421] (7/8) Epoch 10, batch 23400, loss[loss=2.328, over 1820.00 frames. , ppl: 10.262055022413396] tot_loss[loss=2.268, over 5501953.21 frames. , ppl: 9.656456250077426], batch size: 70
+2022-12-13 18:19:54,584 INFO [train.py:421] (7/8) Epoch 10, batch 23600, loss[loss=2.246, over 4550.00 frames. , ppl: 9.445585777549757] tot_loss[loss=2.268, over 5484901.17 frames. , ppl: 9.659460833955857], batch size: 70
+2022-12-13 18:21:36,229 INFO [train.py:421] (7/8) Epoch 10, batch 23800, loss[loss=2.231, over 3850.00 frames. , ppl: 9.313307560850857] tot_loss[loss=2.268, over 5486012.73 frames. , ppl: 9.662807657994685], batch size: 70
+2022-12-13 18:23:16,494 INFO [train.py:421] (7/8) Epoch 10, batch 24000, loss[loss=2.338, over 2030.00 frames. , ppl: 10.359154906694913] tot_loss[loss=2.27, over 5460250.24 frames. , ppl: 9.675218963719502], batch size: 70
+2022-12-13 18:23:16,494 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 18:23:17,301 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.265, over 211138.00 frames. , ppl: 9.631834173341721
+2022-12-13 18:24:57,920 INFO [train.py:421] (7/8) Epoch 10, batch 24200, loss[loss=2.316, over 2450.00 frames. , ppl: 10.138657857292644] tot_loss[loss=2.269, over 5475776.50 frames. , ppl: 9.66890999922457], batch size: 70
+2022-12-13 18:26:41,699 INFO [train.py:421] (7/8) Epoch 10, batch 24400, loss[loss=2.256, over 1890.00 frames. , ppl: 9.541987351961167] tot_loss[loss=2.269, over 5457436.79 frames. , ppl: 9.671990577202113], batch size: 70
+2022-12-13 18:28:25,422 INFO [train.py:421] (7/8) Epoch 10, batch 24600, loss[loss=2.364, over 1610.00 frames. , ppl: 10.637193516463395] tot_loss[loss=2.268, over 5468845.67 frames. , ppl: 9.66295078596492], batch size: 70
+2022-12-13 18:30:06,364 INFO [train.py:421] (7/8) Epoch 10, batch 24800, loss[loss=2.228, over 5110.00 frames. , ppl: 9.28123186484537] tot_loss[loss=2.269, over 5434826.24 frames. , ppl: 9.673305958604878], batch size: 70
+2022-12-13 18:31:48,362 INFO [train.py:421] (7/8) Epoch 10, batch 25000, loss[loss=2.426, over 910.00 frames. , ppl: 11.309384724372785] tot_loss[loss=2.268, over 5481737.98 frames. , ppl: 9.664288592550305], batch size: 70
+2022-12-13 18:31:48,363 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 18:31:49,120 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.617161851458512
+2022-12-13 18:33:31,040 INFO [train.py:421] (7/8) Epoch 10, batch 25200, loss[loss=2.458, over 1120.00 frames. , ppl: 11.687002738109022] tot_loss[loss=2.269, over 5452836.75 frames. , ppl: 9.672573890099118], batch size: 70
+2022-12-13 18:35:13,476 INFO [train.py:421] (7/8) Epoch 10, batch 25400, loss[loss=2.613, over 1190.00 frames. , ppl: 13.643863590310422] tot_loss[loss=2.27, over 5433788.71 frames. , ppl: 9.677046353850637], batch size: 70
+2022-12-13 18:36:55,984 INFO [train.py:421] (7/8) Epoch 10, batch 25600, loss[loss=2.179, over 5040.00 frames. , ppl: 8.840766711075954] tot_loss[loss=2.268, over 5477453.83 frames. , ppl: 9.663015373235872], batch size: 70
+2022-12-13 18:38:38,921 INFO [train.py:421] (7/8) Epoch 10, batch 25800, loss[loss=2.41, over 1330.00 frames. , ppl: 11.13645731177348] tot_loss[loss=2.267, over 5511130.27 frames. , ppl: 9.653345831279289], batch size: 70
+2022-12-13 18:40:24,876 INFO [train.py:421] (7/8) Epoch 10, batch 26000, loss[loss=2.458, over 1330.00 frames. , ppl: 11.676317777025098] tot_loss[loss=2.267, over 5534298.94 frames. , ppl: 9.648791390727528], batch size: 70
+2022-12-13 18:40:24,876 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 18:40:25,675 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.266, over 211138.00 frames. , ppl: 9.637863426039562
+2022-12-13 18:42:06,980 INFO [train.py:421] (7/8) Epoch 10, batch 26200, loss[loss=2.114, over 5040.00 frames. , ppl: 8.278987705431941] tot_loss[loss=2.266, over 5590691.79 frames. , ppl: 9.63831512120812], batch size: 70
+2022-12-13 18:43:50,151 INFO [train.py:421] (7/8) Epoch 10, batch 26400, loss[loss=2.164, over 6370.00 frames. , ppl: 8.70931801542097] tot_loss[loss=2.268, over 5548649.37 frames. , ppl: 9.657193903857053], batch size: 70
+2022-12-13 18:45:37,768 INFO [train.py:421] (7/8) Epoch 10, batch 26600, loss[loss=2.476, over 1120.00 frames. , ppl: 11.895921795436099] tot_loss[loss=2.266, over 5611971.12 frames. , ppl: 9.639770175207158], batch size: 70
+2022-12-13 18:47:19,961 INFO [train.py:421] (7/8) Epoch 10, batch 26800, loss[loss=2.586, over 910.00 frames. , ppl: 13.281721381203495] tot_loss[loss=2.267, over 5564600.88 frames. , ppl: 9.651846342358123], batch size: 70
+2022-12-13 18:49:02,367 INFO [train.py:421] (7/8) Epoch 10, batch 27000, loss[loss=2.358, over 3360.00 frames. , ppl: 10.570152855836627] tot_loss[loss=2.267, over 5553002.31 frames. , ppl: 9.649210661410798], batch size: 70
+2022-12-13 18:49:02,368 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 18:49:03,131 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.621924342548795
+2022-12-13 18:50:45,267 INFO [train.py:421] (7/8) Epoch 10, batch 27200, loss[loss=2.117, over 3850.00 frames. , ppl: 8.305518307114097] tot_loss[loss=2.268, over 5513967.71 frames. , ppl: 9.657748478964328], batch size: 70
+2022-12-13 18:52:26,330 INFO [train.py:421] (7/8) Epoch 10, batch 27400, loss[loss=2.229, over 3640.00 frames. , ppl: 9.293905373582312] tot_loss[loss=2.268, over 5514321.22 frames. , ppl: 9.659162448106454], batch size: 70
+2022-12-13 18:54:07,432 INFO [train.py:421] (7/8) Epoch 10, batch 27600, loss[loss=2.391, over 1540.00 frames. , ppl: 10.922888186797355] tot_loss[loss=2.269, over 5484886.10 frames. , ppl: 9.670336083224955], batch size: 70
+2022-12-13 18:55:51,711 INFO [train.py:421] (7/8) Epoch 10, batch 27800, loss[loss=2.227, over 4200.00 frames. , ppl: 9.276257207827364] tot_loss[loss=2.269, over 5489238.33 frames. , ppl: 9.672734405111406], batch size: 70
+2022-12-13 18:57:33,166 INFO [train.py:421] (7/8) Epoch 10, batch 28000, loss[loss=2.324, over 2310.00 frames. , ppl: 10.21813418780344] tot_loss[loss=2.268, over 5493117.28 frames. , ppl: 9.663387398578738], batch size: 70
+2022-12-13 18:57:33,166 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 18:57:33,931 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.617768243976228
+2022-12-13 18:59:13,886 INFO [train.py:421] (7/8) Epoch 10, batch 28200, loss[loss=2.387, over 1190.00 frames. , ppl: 10.881988210620483] tot_loss[loss=2.268, over 5522430.06 frames. , ppl: 9.655822017004178], batch size: 70
+2022-12-13 19:00:57,580 INFO [train.py:421] (7/8) Epoch 10, batch 28400, loss[loss=2.457, over 1400.00 frames. , ppl: 11.665007410347744] tot_loss[loss=2.268, over 5496139.43 frames. , ppl: 9.664173217406649], batch size: 70
+2022-12-13 19:02:36,587 INFO [train.py:421] (7/8) Epoch 10, batch 28600, loss[loss=2.212, over 3780.00 frames. , ppl: 9.136690486962804] tot_loss[loss=2.269, over 5481899.12 frames. , ppl: 9.673352903010416], batch size: 70
+2022-12-13 19:04:16,639 INFO [train.py:421] (7/8) Epoch 10, batch 28800, loss[loss=2.22, over 3290.00 frames. , ppl: 9.203772655231681] tot_loss[loss=2.27, over 5473932.60 frames. , ppl: 9.678471858432985], batch size: 70
+2022-12-13 19:06:00,419 INFO [train.py:421] (7/8) Epoch 10, batch 29000, loss[loss=2.168, over 7140.00 frames. , ppl: 8.742058907425198] tot_loss[loss=2.27, over 5498295.82 frames. , ppl: 9.675454349669844], batch size: 70
+2022-12-13 19:06:00,420 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 19:06:01,145 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.614629935321982
+2022-12-13 19:07:42,004 INFO [train.py:421] (7/8) Epoch 10, batch 29200, loss[loss=2.296, over 2030.00 frames. , ppl: 9.933609773066552] tot_loss[loss=2.27, over 5475683.37 frames. , ppl: 9.678086883317775], batch size: 70
+2022-12-13 19:09:24,501 INFO [train.py:421] (7/8) Epoch 10, batch 29400, loss[loss=2.19, over 4200.00 frames. , ppl: 8.935312838615896] tot_loss[loss=2.269, over 5507236.83 frames. , ppl: 9.665078834296683], batch size: 70
+2022-12-13 19:11:08,697 INFO [train.py:421] (7/8) Epoch 10, batch 29600, loss[loss=2.283, over 2730.00 frames. , ppl: 9.80697300860536] tot_loss[loss=2.269, over 5461596.77 frames. , ppl: 9.67294379874287], batch size: 70
+2022-12-13 19:12:55,140 INFO [train.py:421] (7/8) Epoch 10, batch 29800, loss[loss=2.474, over 1050.00 frames. , ppl: 11.87163315243006] tot_loss[loss=2.268, over 5530392.80 frames. , ppl: 9.658960982769997], batch size: 70
+2022-12-13 19:14:36,422 INFO [train.py:421] (7/8) Epoch 10, batch 30000, loss[loss=2.218, over 2800.00 frames. , ppl: 9.191732542547511] tot_loss[loss=2.268, over 5559519.37 frames. , ppl: 9.657587677429877], batch size: 70
+2022-12-13 19:14:36,423 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 19:14:37,217 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.266, over 211138.00 frames. , ppl: 9.638813505699115
+2022-12-13 19:16:16,761 INFO [train.py:421] (7/8) Epoch 10, batch 30200, loss[loss=2.27, over 4340.00 frames. , ppl: 9.681580806503806] tot_loss[loss=2.268, over 5529345.46 frames. , ppl: 9.663265637286228], batch size: 70
+2022-12-13 19:18:02,136 INFO [train.py:421] (7/8) Epoch 10, batch 30400, loss[loss=2.559, over 1050.00 frames. , ppl: 12.91759105038794] tot_loss[loss=2.268, over 5528383.43 frames. , ppl: 9.659792310536501], batch size: 70
+2022-12-13 19:19:43,255 INFO [train.py:421] (7/8) Epoch 10, batch 30600, loss[loss=2.267, over 2730.00 frames. , ppl: 9.653628021932937] tot_loss[loss=2.269, over 5504785.38 frames. , ppl: 9.66895243826829], batch size: 70
+2022-12-13 19:21:25,052 INFO [train.py:421] (7/8) Epoch 10, batch 30800, loss[loss=3.06, over 560.00 frames. , ppl: 21.3285650973933] tot_loss[loss=2.269, over 5492128.06 frames. , ppl: 9.66893542676216], batch size: 70
+2022-12-13 19:23:07,034 INFO [train.py:421] (7/8) Epoch 10, batch 31000, loss[loss=2.448, over 910.00 frames. , ppl: 11.569748101986841] tot_loss[loss=2.27, over 5462632.37 frames. , ppl: 9.67721406564316], batch size: 70
+2022-12-13 19:23:07,034 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 19:23:07,797 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.624022295019808
+2022-12-13 19:24:49,278 INFO [train.py:421] (7/8) Epoch 10, batch 31200, loss[loss=2.824, over 630.00 frames. , ppl: 16.837474749901354] tot_loss[loss=2.27, over 5456091.24 frames. , ppl: 9.68363054409008], batch size: 70
+2022-12-13 19:26:30,794 INFO [train.py:421] (7/8) Epoch 10, batch 31400, loss[loss=2.187, over 11270.00 frames. , ppl: 8.907455181658335] tot_loss[loss=2.27, over 5463128.11 frames. , ppl: 9.682081139985076], batch size: 70
+2022-12-13 19:28:10,487 INFO [train.py:421] (7/8) Epoch 10, batch 31600, loss[loss=2.302, over 2590.00 frames. , ppl: 9.994716721632365] tot_loss[loss=2.269, over 5485210.14 frames. , ppl: 9.672943683383972], batch size: 70
+2022-12-13 19:29:51,154 INFO [train.py:421] (7/8) Epoch 10, batch 31800, loss[loss=2.501, over 1260.00 frames. , ppl: 12.188996538057383] tot_loss[loss=2.27, over 5450898.01 frames. , ppl: 9.675479766322693], batch size: 70
+2022-12-13 19:31:35,514 INFO [train.py:421] (7/8) Epoch 10, batch 32000, loss[loss=2.275, over 2240.00 frames. , ppl: 9.72908960895468] tot_loss[loss=2.27, over 5423611.27 frames. , ppl: 9.68421516568966], batch size: 70
+2022-12-13 19:31:35,514 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 19:31:36,277 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.616229561960207
+2022-12-13 19:33:19,166 INFO [train.py:421] (7/8) Epoch 10, batch 32200, loss[loss=2.31, over 2240.00 frames. , ppl: 10.072698268207267] tot_loss[loss=2.271, over 5402445.62 frames. , ppl: 9.691773501793248], batch size: 70
+2022-12-13 19:35:01,661 INFO [train.py:421] (7/8) Epoch 10, batch 32400, loss[loss=2.311, over 2450.00 frames. , ppl: 10.081775947557274] tot_loss[loss=2.271, over 5457110.56 frames. , ppl: 9.68589000115159], batch size: 70
+2022-12-13 19:36:43,496 INFO [train.py:421] (7/8) Epoch 10, batch 32600, loss[loss=2.27, over 3710.00 frames. , ppl: 9.68198519296484] tot_loss[loss=2.269, over 5458403.39 frames. , ppl: 9.673953937640409], batch size: 70
+2022-12-13 19:38:26,634 INFO [train.py:421] (7/8) Epoch 10, batch 32800, loss[loss=2.325, over 2940.00 frames. , ppl: 10.222974699894849] tot_loss[loss=2.268, over 5498224.51 frames. , ppl: 9.65905498483643], batch size: 70
+2022-12-13 19:40:07,395 INFO [train.py:421] (7/8) Epoch 10, batch 33000, loss[loss=2.577, over 770.00 frames. , ppl: 13.157275084431372] tot_loss[loss=2.268, over 5496499.17 frames. , ppl: 9.664285074614188], batch size: 70
+2022-12-13 19:40:07,396 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 19:40:08,159 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.611626373467763
+2022-12-13 19:41:48,438 INFO [train.py:421] (7/8) Epoch 10, batch 33200, loss[loss=2.238, over 2380.00 frames. , ppl: 9.376634777341014] tot_loss[loss=2.268, over 5510488.27 frames. , ppl: 9.656840433138125], batch size: 70
+2022-12-13 19:43:28,469 INFO [train.py:421] (7/8) Epoch 10, batch 33400, loss[loss=2.311, over 3220.00 frames. , ppl: 10.087316493485654] tot_loss[loss=2.27, over 5430933.23 frames. , ppl: 9.680916447934234], batch size: 70
+2022-12-13 19:45:11,013 INFO [train.py:421] (7/8) Epoch 10, batch 33600, loss[loss=2.88, over 630.00 frames. , ppl: 17.815982561454863] tot_loss[loss=2.27, over 5445536.31 frames. , ppl: 9.682754375484642], batch size: 70
+2022-12-13 19:46:54,751 INFO [train.py:421] (7/8) Epoch 10, batch 33800, loss[loss=2.224, over 3290.00 frames. , ppl: 9.24123519342163] tot_loss[loss=2.269, over 5481458.25 frames. , ppl: 9.667536409569978], batch size: 70
+2022-12-13 19:48:42,877 INFO [train.py:421] (7/8) Epoch 10, batch 34000, loss[loss=2.391, over 1260.00 frames. , ppl: 10.92849185372166] tot_loss[loss=2.268, over 5488701.98 frames. , ppl: 9.664393190530648], batch size: 70
+2022-12-13 19:48:42,878 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 19:48:43,659 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.612292169791925
+2022-12-13 19:50:27,173 INFO [train.py:421] (7/8) Epoch 10, batch 34200, loss[loss=2.288, over 3850.00 frames. , ppl: 9.851393087688251] tot_loss[loss=2.269, over 5460822.66 frames. , ppl: 9.669359816672133], batch size: 70
+2022-12-13 19:52:08,998 INFO [train.py:421] (7/8) Epoch 10, batch 34400, loss[loss=2.266, over 2380.00 frames. , ppl: 9.645326934238687] tot_loss[loss=2.269, over 5478806.87 frames. , ppl: 9.669482391125639], batch size: 70
+2022-12-13 19:53:50,217 INFO [train.py:421] (7/8) Epoch 10, batch 34600, loss[loss=2.313, over 3430.00 frames. , ppl: 10.102394444664771] tot_loss[loss=2.269, over 5463250.81 frames. , ppl: 9.671172608038654], batch size: 70
+2022-12-13 19:55:28,953 INFO [train.py:421] (7/8) Epoch 10, batch 34800, loss[loss=2.133, over 6860.00 frames. , ppl: 8.439069087446518] tot_loss[loss=2.269, over 5468494.32 frames. , ppl: 9.669630336238749], batch size: 70
+2022-12-13 19:57:12,613 INFO [train.py:421] (7/8) Epoch 10, batch 35000, loss[loss=3.613, over 420.00 frames. , ppl: 37.09200977422227] tot_loss[loss=2.269, over 5481425.34 frames. , ppl: 9.665274736401514], batch size: 70
+2022-12-13 19:57:12,614 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 19:57:13,388 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.616518490872702
+2022-12-13 19:58:57,910 INFO [train.py:421] (7/8) Epoch 10, batch 35200, loss[loss=2.374, over 2030.00 frames. , ppl: 10.737732098681533] tot_loss[loss=2.268, over 5472536.53 frames. , ppl: 9.663597211694421], batch size: 70
+2022-12-13 20:00:39,614 INFO [train.py:421] (7/8) Epoch 10, batch 35400, loss[loss=2.184, over 3500.00 frames. , ppl: 8.878717199504791] tot_loss[loss=2.27, over 5417032.19 frames. , ppl: 9.683034060729318], batch size: 70
+2022-12-13 20:02:22,805 INFO [train.py:421] (7/8) Epoch 10, batch 35600, loss[loss=2.224, over 4550.00 frames. , ppl: 9.24079260189948] tot_loss[loss=2.27, over 5455891.13 frames. , ppl: 9.676132073459502], batch size: 70
+2022-12-13 20:04:05,805 INFO [train.py:421] (7/8) Epoch 10, batch 35800, loss[loss=2.605, over 1190.00 frames. , ppl: 13.530772255913563] tot_loss[loss=2.269, over 5461215.36 frames. , ppl: 9.670294799952224], batch size: 70
+2022-12-13 20:05:47,839 INFO [train.py:421] (7/8) Epoch 10, batch 36000, loss[loss=2.216, over 4550.00 frames. , ppl: 9.172419165985955] tot_loss[loss=2.269, over 5483345.53 frames. , ppl: 9.668679599865303], batch size: 70
+2022-12-13 20:05:47,840 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 20:05:48,581 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.601890816854365
+2022-12-13 20:07:33,623 INFO [train.py:421] (7/8) Epoch 10, batch 36200, loss[loss=2.407, over 1400.00 frames. , ppl: 11.10217974045473] tot_loss[loss=2.266, over 5582151.72 frames. , ppl: 9.643550210491634], batch size: 70
+2022-12-13 20:09:17,749 INFO [train.py:421] (7/8) Epoch 10, batch 36400, loss[loss=2.225, over 4130.00 frames. , ppl: 9.249567041439912] tot_loss[loss=2.267, over 5572629.49 frames. , ppl: 9.647662911111041], batch size: 70
+2022-12-13 20:11:03,410 INFO [train.py:421] (7/8) Epoch 10, batch 36600, loss[loss=2.383, over 1750.00 frames. , ppl: 10.832281373459015] tot_loss[loss=2.267, over 5548172.92 frames. , ppl: 9.647779238767656], batch size: 70
+2022-12-13 20:12:48,784 INFO [train.py:421] (7/8) Epoch 10, batch 36800, loss[loss=2.244, over 2940.00 frames. , ppl: 9.430835320955739] tot_loss[loss=2.267, over 5535855.31 frames. , ppl: 9.647738556633573], batch size: 70
+2022-12-13 20:14:30,489 INFO [train.py:421] (7/8) Epoch 10, batch 37000, loss[loss=2.335, over 2170.00 frames. , ppl: 10.32999545672677] tot_loss[loss=2.267, over 5526421.21 frames. , ppl: 9.650939854788168], batch size: 70
+2022-12-13 20:14:30,490 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 20:14:31,281 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.600985586014557
+2022-12-13 20:16:16,938 INFO [train.py:421] (7/8) Epoch 10, batch 37200, loss[loss=2.785, over 840.00 frames. , ppl: 16.19332444822544] tot_loss[loss=2.267, over 5546345.10 frames. , ppl: 9.650801304082094], batch size: 70
+2022-12-13 20:17:58,387 INFO [train.py:421] (7/8) Epoch 10, batch 37400, loss[loss=2.139, over 8680.00 frames. , ppl: 8.486818031482903] tot_loss[loss=2.266, over 5574039.00 frames. , ppl: 9.643278573963373], batch size: 70
+2022-12-13 20:19:44,289 INFO [train.py:421] (7/8) Epoch 10, batch 37600, loss[loss=2.226, over 6510.00 frames. , ppl: 9.26545606250435] tot_loss[loss=2.265, over 5610913.45 frames. , ppl: 9.635217139200634], batch size: 70
+2022-12-13 20:21:26,457 INFO [train.py:421] (7/8) Epoch 10, batch 37800, loss[loss=2.3, over 2170.00 frames. , ppl: 9.974445045429977] tot_loss[loss=2.266, over 5604022.15 frames. , ppl: 9.639375097143592], batch size: 70
+2022-12-13 20:23:05,380 INFO [train.py:421] (7/8) Epoch 10, batch 38000, loss[loss=2.345, over 2030.00 frames. , ppl: 10.43599894882522] tot_loss[loss=2.266, over 5610997.03 frames. , ppl: 9.63698283125678], batch size: 70
+2022-12-13 20:23:05,380 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 20:23:06,141 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.261, over 211138.00 frames. , ppl: 9.589634108742406
+2022-12-13 20:24:47,954 INFO [train.py:421] (7/8) Epoch 10, batch 38200, loss[loss=2.608, over 1120.00 frames. , ppl: 13.573678304401128] tot_loss[loss=2.267, over 5563583.10 frames. , ppl: 9.652664012270026], batch size: 70
+2022-12-13 20:26:26,943 INFO [train.py:421] (7/8) Epoch 10, batch 38400, loss[loss=2.242, over 3430.00 frames. , ppl: 9.41255764003244] tot_loss[loss=2.268, over 5539882.45 frames. , ppl: 9.656148764165405], batch size: 70
+2022-12-13 20:28:07,272 INFO [train.py:421] (7/8) Epoch 10, batch 38600, loss[loss=2.376, over 1680.00 frames. , ppl: 10.758766831767751] tot_loss[loss=2.268, over 5534488.05 frames. , ppl: 9.661267599871408], batch size: 70
+2022-12-13 20:29:50,051 INFO [train.py:421] (7/8) Epoch 10, batch 38800, loss[loss=2.246, over 4060.00 frames. , ppl: 9.4521652511374] tot_loss[loss=2.269, over 5500145.34 frames. , ppl: 9.672062167034126], batch size: 70
+2022-12-13 20:31:30,516 INFO [train.py:421] (7/8) Epoch 10, batch 39000, loss[loss=2.222, over 7630.00 frames. , ppl: 9.221914580833964] tot_loss[loss=2.27, over 5476735.31 frames. , ppl: 9.678623698371496], batch size: 70
+2022-12-13 20:31:30,516 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 20:31:31,277 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.59960729794989
+2022-12-13 20:33:11,829 INFO [train.py:421] (7/8) Epoch 10, batch 39200, loss[loss=2.579, over 840.00 frames. , ppl: 13.181412876100607] tot_loss[loss=2.27, over 5464440.60 frames. , ppl: 9.681755422077465], batch size: 70
+2022-12-13 20:34:51,232 INFO [train.py:421] (7/8) Epoch 10, batch 39400, loss[loss=2.27, over 3290.00 frames. , ppl: 9.677802920851654] tot_loss[loss=2.27, over 5439644.44 frames. , ppl: 9.68369678515584], batch size: 70
+2022-12-13 20:36:33,969 INFO [train.py:421] (7/8) Epoch 10, batch 39600, loss[loss=2.35, over 3360.00 frames. , ppl: 10.485274115211272] tot_loss[loss=2.271, over 5456472.64 frames. , ppl: 9.68613164573859], batch size: 70
+2022-12-13 20:38:17,863 INFO [train.py:421] (7/8) Epoch 10, batch 39800, loss[loss=2.431, over 1610.00 frames. , ppl: 11.368099614136597] tot_loss[loss=2.271, over 5469320.10 frames. , ppl: 9.688252114733364], batch size: 70
+2022-12-13 20:40:01,100 INFO [train.py:421] (7/8) Epoch 10, batch 40000, loss[loss=2.185, over 6160.00 frames. , ppl: 8.892512900695731] tot_loss[loss=2.27, over 5511172.87 frames. , ppl: 9.677197280458712], batch size: 70
+2022-12-13 20:40:01,101 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 20:40:01,849 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.261, over 211138.00 frames. , ppl: 9.595198105641067
+2022-12-13 20:41:45,210 INFO [train.py:421] (7/8) Epoch 10, batch 40200, loss[loss=3.551, over 420.00 frames. , ppl: 34.838976748364665] tot_loss[loss=2.268, over 5560046.49 frames. , ppl: 9.661764064407107], batch size: 70
+2022-12-13 20:43:28,823 INFO [train.py:421] (7/8) Epoch 10, batch 40400, loss[loss=2.591, over 840.00 frames. , ppl: 13.348948791136085] tot_loss[loss=2.268, over 5590840.88 frames. , ppl: 9.65598924873157], batch size: 70
+2022-12-13 20:45:07,758 INFO [train.py:421] (7/8) Epoch 10, batch 40600, loss[loss=3.733, over 420.00 frames. , ppl: 41.808572395629454] tot_loss[loss=2.269, over 5552485.46 frames. , ppl: 9.66587070331569], batch size: 70
+2022-12-13 20:46:47,452 INFO [train.py:421] (7/8) Epoch 10, batch 40800, loss[loss=2.174, over 3640.00 frames. , ppl: 8.792831445042491] tot_loss[loss=2.27, over 5482196.41 frames. , ppl: 9.678632970577702], batch size: 70
+2022-12-13 20:48:25,962 INFO [train.py:421] (7/8) Epoch 10, batch 41000, loss[loss=2.227, over 5670.00 frames. , ppl: 9.269303197950281] tot_loss[loss=2.27, over 5473458.04 frames. , ppl: 9.681517774639962], batch size: 70
+2022-12-13 20:48:25,963 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 20:48:26,717 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.60531213793815
+2022-12-13 20:50:09,273 INFO [train.py:421] (7/8) Epoch 10, batch 41200, loss[loss=2.194, over 4970.00 frames. , ppl: 8.966746093264241] tot_loss[loss=2.271, over 5447323.13 frames. , ppl: 9.687053588768217], batch size: 70
+2022-12-13 20:51:52,025 INFO [train.py:421] (7/8) Epoch 10, batch 41400, loss[loss=2.336, over 2030.00 frames. , ppl: 10.33953878986596] tot_loss[loss=2.272, over 5401936.10 frames. , ppl: 9.698557978427418], batch size: 70
+2022-12-13 20:53:33,182 INFO [train.py:421] (7/8) Epoch 10, batch 41600, loss[loss=2.199, over 3220.00 frames. , ppl: 9.012475311080376] tot_loss[loss=2.272, over 5410295.09 frames. , ppl: 9.69829123175631], batch size: 70
+2022-12-13 20:55:14,354 INFO [train.py:421] (7/8) Epoch 10, batch 41800, loss[loss=2.508, over 1260.00 frames. , ppl: 12.281206953354928] tot_loss[loss=2.272, over 5398858.86 frames. , ppl: 9.701166574250442], batch size: 70
+2022-12-13 20:56:55,445 INFO [train.py:421] (7/8) Epoch 10, batch 42000, loss[loss=2.294, over 2730.00 frames. , ppl: 9.91259490595747] tot_loss[loss=2.272, over 5385595.15 frames. , ppl: 9.700433999647048], batch size: 70
+2022-12-13 20:56:55,445 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 20:56:56,194 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.599615822834881
+2022-12-13 20:58:38,511 INFO [train.py:421] (7/8) Epoch 10, batch 42200, loss[loss=2.347, over 1820.00 frames. , ppl: 10.450038268413953] tot_loss[loss=2.27, over 5436327.86 frames. , ppl: 9.678634757151002], batch size: 70
+2022-12-13 21:00:23,425 INFO [train.py:421] (7/8) Epoch 10, batch 42400, loss[loss=2.415, over 2240.00 frames. , ppl: 11.19235423143874] tot_loss[loss=2.27, over 5434636.62 frames. , ppl: 9.682453000896826], batch size: 70
+2022-12-13 21:02:03,404 INFO [train.py:421] (7/8) Epoch 10, batch 42600, loss[loss=2.201, over 6300.00 frames. , ppl: 9.034207991600258] tot_loss[loss=2.27, over 5455681.99 frames. , ppl: 9.678738689836777], batch size: 70
+2022-12-13 21:03:47,715 INFO [train.py:421] (7/8) Epoch 10, batch 42800, loss[loss=2.188, over 1680.00 frames. , ppl: 8.920310940046763] tot_loss[loss=2.271, over 5436020.96 frames. , ppl: 9.687328625957619], batch size: 70
+2022-12-13 21:05:29,127 INFO [train.py:421] (7/8) Epoch 10, batch 43000, loss[loss=2.16, over 4060.00 frames. , ppl: 8.67413030792775] tot_loss[loss=2.271, over 5440009.07 frames. , ppl: 9.68814354000665], batch size: 70
+2022-12-13 21:05:29,127 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 21:05:29,892 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.605019280876657
+2022-12-13 21:07:11,584 INFO [train.py:421] (7/8) Epoch 10, batch 43200, loss[loss=2.241, over 2870.00 frames. , ppl: 9.401006327946394] tot_loss[loss=2.269, over 5478546.90 frames. , ppl: 9.66641476359559], batch size: 70
+2022-12-13 21:08:55,575 INFO [train.py:421] (7/8) Epoch 10, batch 43400, loss[loss=2.223, over 6300.00 frames. , ppl: 9.236019927752661] tot_loss[loss=2.268, over 5518424.38 frames. , ppl: 9.664683397858262], batch size: 70
+2022-12-13 21:10:37,370 INFO [train.py:421] (7/8) Epoch 10, batch 43600, loss[loss=3.483, over 420.00 frames. , ppl: 32.545429734845214] tot_loss[loss=2.269, over 5489886.87 frames. , ppl: 9.672841387858629], batch size: 70
+2022-12-13 21:12:19,477 INFO [train.py:421] (7/8) Epoch 10, batch 43800, loss[loss=2.328, over 2450.00 frames. , ppl: 10.26189478918143] tot_loss[loss=2.269, over 5504910.91 frames. , ppl: 9.66647883289995], batch size: 70
+2022-12-13 21:13:59,360 INFO [train.py:421] (7/8) Epoch 10, batch 44000, loss[loss=2.395, over 1190.00 frames. , ppl: 10.964614466204463] tot_loss[loss=2.269, over 5483481.38 frames. , ppl: 9.672211534081672], batch size: 70
+2022-12-13 21:13:59,361 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 21:14:00,109 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.620145785284024
+2022-12-13 21:15:38,898 INFO [train.py:421] (7/8) Epoch 10, batch 44200, loss[loss=2.265, over 2100.00 frames. , ppl: 9.633664392613298] tot_loss[loss=2.27, over 5446139.88 frames. , ppl: 9.680283068735015], batch size: 70
+2022-12-13 21:17:20,615 INFO [train.py:421] (7/8) Epoch 10, batch 44400, loss[loss=2.197, over 3920.00 frames. , ppl: 8.99811854944838] tot_loss[loss=2.27, over 5440924.35 frames. , ppl: 9.683852494705649], batch size: 70
+2022-12-13 21:19:00,966 INFO [train.py:421] (7/8) Epoch 10, batch 44600, loss[loss=2.166, over 4900.00 frames. , ppl: 8.722534047769193] tot_loss[loss=2.27, over 5430258.71 frames. , ppl: 9.681660511728733], batch size: 70
+2022-12-13 21:20:45,706 INFO [train.py:421] (7/8) Epoch 10, batch 44800, loss[loss=2.309, over 2100.00 frames. , ppl: 10.066243445648672] tot_loss[loss=2.269, over 5487607.85 frames. , ppl: 9.667025516695263], batch size: 70
+2022-12-13 21:22:25,935 INFO [train.py:421] (7/8) Epoch 10, batch 45000, loss[loss=2.213, over 2450.00 frames. , ppl: 9.140625281263182] tot_loss[loss=2.269, over 5482376.96 frames. , ppl: 9.670057434328525], batch size: 70
+2022-12-13 21:22:25,935 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 21:22:26,698 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.598352801576091
+2022-12-13 21:24:05,953 INFO [train.py:421] (7/8) Epoch 10, batch 45200, loss[loss=2.239, over 4060.00 frames. , ppl: 9.379291468455104] tot_loss[loss=2.27, over 5457267.61 frames. , ppl: 9.679688044972309], batch size: 70
+2022-12-13 21:25:48,543 INFO [train.py:421] (7/8) Epoch 10, batch 45400, loss[loss=2.241, over 4970.00 frames. , ppl: 9.4050640306078] tot_loss[loss=2.271, over 5438470.78 frames. , ppl: 9.684535750806681], batch size: 70
+2022-12-13 21:27:30,578 INFO [train.py:421] (7/8) Epoch 10, batch 45600, loss[loss=2.392, over 980.00 frames. , ppl: 10.932054121013405] tot_loss[loss=2.27, over 5448116.33 frames. , ppl: 9.681522705826264], batch size: 70
+2022-12-13 21:29:13,847 INFO [train.py:421] (7/8) Epoch 10, batch 45800, loss[loss=2.185, over 5180.00 frames. , ppl: 8.886696818260663] tot_loss[loss=2.271, over 5446172.21 frames. , ppl: 9.687298586961875], batch size: 70
+2022-12-13 21:30:58,417 INFO [train.py:421] (7/8) Epoch 10, batch 46000, loss[loss=2.118, over 7000.00 frames. , ppl: 8.313082649111715] tot_loss[loss=2.271, over 5477174.69 frames. , ppl: 9.685957609563413], batch size: 70
+2022-12-13 21:30:58,417 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 21:30:59,139 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.603299281294177
+2022-12-13 21:32:38,609 INFO [train.py:421] (7/8) Epoch 10, batch 46200, loss[loss=2.43, over 1960.00 frames. , ppl: 11.363709543790227] tot_loss[loss=2.271, over 5462917.67 frames. , ppl: 9.693814716242969], batch size: 70
+2022-12-13 21:34:24,217 INFO [train.py:421] (7/8) Epoch 10, batch 46400, loss[loss=2.831, over 700.00 frames. , ppl: 16.961203794696832] tot_loss[loss=2.272, over 5447141.95 frames. , ppl: 9.701830411458898], batch size: 70
+2022-12-13 21:36:10,344 INFO [train.py:421] (7/8) Epoch 10, batch 46600, loss[loss=2.358, over 3430.00 frames. , ppl: 10.568070834715504] tot_loss[loss=2.271, over 5475193.12 frames. , ppl: 9.693484487330073], batch size: 70
+2022-12-13 21:37:49,343 INFO [train.py:421] (7/8) Epoch 10, batch 46800, loss[loss=2.468, over 1400.00 frames. , ppl: 11.796983810388994] tot_loss[loss=2.272, over 5455479.27 frames. , ppl: 9.697858233231043], batch size: 70
+2022-12-13 21:39:32,507 INFO [train.py:421] (7/8) Epoch 10, batch 47000, loss[loss=2.383, over 1610.00 frames. , ppl: 10.838251272233384] tot_loss[loss=2.27, over 5460208.17 frames. , ppl: 9.68258250609922], batch size: 70
+2022-12-13 21:39:32,507 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 21:39:33,262 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.62268485087924
+2022-12-13 21:41:16,054 INFO [train.py:421] (7/8) Epoch 10, batch 47200, loss[loss=2.354, over 1260.00 frames. , ppl: 10.528724425299181] tot_loss[loss=2.272, over 5434507.81 frames. , ppl: 9.694788512417837], batch size: 70
+2022-12-13 21:42:58,726 INFO [train.py:421] (7/8) Epoch 10, batch 47400, loss[loss=2.21, over 4550.00 frames. , ppl: 9.11647163262799] tot_loss[loss=2.272, over 5406813.37 frames. , ppl: 9.698917627734904], batch size: 70
+2022-12-13 21:44:41,591 INFO [train.py:421] (7/8) Epoch 10, batch 47600, loss[loss=2.204, over 4900.00 frames. , ppl: 9.058112040468949] tot_loss[loss=2.273, over 5369050.85 frames. , ppl: 9.707755042866783], batch size: 70
+2022-12-13 21:46:26,632 INFO [train.py:421] (7/8) Epoch 10, batch 47800, loss[loss=2.212, over 3780.00 frames. , ppl: 9.137698460165787] tot_loss[loss=2.272, over 5384046.07 frames. , ppl: 9.700535262968915], batch size: 70
+2022-12-13 21:48:08,393 INFO [train.py:421] (7/8) Epoch 10, batch 48000, loss[loss=2.316, over 3360.00 frames. , ppl: 10.13215994592368] tot_loss[loss=2.271, over 5449972.35 frames. , ppl: 9.687778935313595], batch size: 70
+2022-12-13 21:48:08,394 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 21:48:09,144 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.621020070987242
+2022-12-13 21:49:55,426 INFO [train.py:421] (7/8) Epoch 10, batch 48200, loss[loss=2.463, over 1050.00 frames. , ppl: 11.734994197260349] tot_loss[loss=2.271, over 5465107.82 frames. , ppl: 9.690455591340271], batch size: 70
+2022-12-13 21:51:37,488 INFO [train.py:421] (7/8) Epoch 10, batch 48400, loss[loss=2.368, over 1890.00 frames. , ppl: 10.680910307126766] tot_loss[loss=2.271, over 5491256.22 frames. , ppl: 9.688843327307378], batch size: 70
+2022-12-13 21:53:19,230 INFO [train.py:421] (7/8) Epoch 10, batch 48600, loss[loss=2.663, over 910.00 frames. , ppl: 14.343960821950136] tot_loss[loss=2.271, over 5463814.11 frames. , ppl: 9.693758494967522], batch size: 70
+2022-12-13 21:55:03,403 INFO [train.py:421] (7/8) Epoch 10, batch 48800, loss[loss=2.385, over 1680.00 frames. , ppl: 10.85458064144315] tot_loss[loss=2.271, over 5479156.84 frames. , ppl: 9.688893157637356], batch size: 70
+2022-12-13 21:56:44,858 INFO [train.py:421] (7/8) Epoch 10, batch 49000, loss[loss=2.682, over 700.00 frames. , ppl: 14.60887855786491] tot_loss[loss=2.27, over 5519724.21 frames. , ppl: 9.680368501455787], batch size: 70
+2022-12-13 21:56:44,858 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 21:56:45,606 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.608761699260915
+2022-12-13 21:58:25,273 INFO [train.py:421] (7/8) Epoch 10, batch 49200, loss[loss=2.271, over 2730.00 frames. , ppl: 9.686330308412021] tot_loss[loss=2.271, over 5489578.31 frames. , ppl: 9.685764694553015], batch size: 70
+2022-12-13 22:00:03,878 INFO [train.py:421] (7/8) Epoch 10, batch 49400, loss[loss=2.594, over 840.00 frames. , ppl: 13.37947099505518] tot_loss[loss=2.271, over 5454421.46 frames. , ppl: 9.69170442276858], batch size: 70
+2022-12-13 22:01:44,548 INFO [train.py:421] (7/8) Epoch 10, batch 49600, loss[loss=2.357, over 1820.00 frames. , ppl: 10.555375532171526] tot_loss[loss=2.272, over 5423731.42 frames. , ppl: 9.699375780766275], batch size: 70
+2022-12-13 22:03:22,305 INFO [train.py:421] (7/8) Epoch 10, batch 49800, loss[loss=2.29, over 2940.00 frames. , ppl: 9.87927033135837] tot_loss[loss=2.273, over 5417986.19 frames. , ppl: 9.708595493167191], batch size: 70
+2022-12-13 22:05:00,313 INFO [train.py:421] (7/8) Epoch 10, batch 50000, loss[loss=2.473, over 1400.00 frames. , ppl: 11.857667196195857] tot_loss[loss=2.271, over 5456079.49 frames. , ppl: 9.693852693982867], batch size: 70
+2022-12-13 22:05:00,313 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 22:05:01,070 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.608694857576053
+2022-12-13 22:06:42,910 INFO [train.py:421] (7/8) Epoch 10, batch 50200, loss[loss=2.168, over 5810.00 frames. , ppl: 8.742418973477296] tot_loss[loss=2.271, over 5482189.33 frames. , ppl: 9.689679962622883], batch size: 70
+2022-12-13 22:08:19,153 INFO [train.py:421] (7/8) Epoch 10, batch 50400, loss[loss=2.415, over 1190.00 frames. , ppl: 11.190999540378264] tot_loss[loss=2.272, over 5453613.22 frames. , ppl: 9.700595381099609], batch size: 70
+2022-12-13 22:10:01,734 INFO [train.py:421] (7/8) Epoch 10, batch 50600, loss[loss=2.191, over 3920.00 frames. , ppl: 8.941926483381833] tot_loss[loss=2.27, over 5531535.73 frames. , ppl: 9.675312113197924], batch size: 70
+2022-12-13 22:11:42,226 INFO [train.py:421] (7/8) Epoch 10, batch 50800, loss[loss=2.193, over 3570.00 frames. , ppl: 8.965304845772268] tot_loss[loss=2.271, over 5482462.92 frames. , ppl: 9.687923304159714], batch size: 70
+2022-12-13 22:13:22,635 INFO [train.py:421] (7/8) Epoch 10, batch 51000, loss[loss=2.158, over 7070.00 frames. , ppl: 8.653265939004763] tot_loss[loss=2.271, over 5467231.68 frames. , ppl: 9.688452007425093], batch size: 70
+2022-12-13 22:13:22,636 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 22:13:23,385 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.617215941256719
+2022-12-13 22:15:05,603 INFO [train.py:421] (7/8) Epoch 10, batch 51200, loss[loss=2.137, over 10710.00 frames. , ppl: 8.473943156655006] tot_loss[loss=2.271, over 5473239.17 frames. , ppl: 9.68429501447115], batch size: 70
+2022-12-13 22:16:46,784 INFO [train.py:421] (7/8) Epoch 10, batch 51400, loss[loss=2.275, over 2170.00 frames. , ppl: 9.732354779276141] tot_loss[loss=2.27, over 5468583.91 frames. , ppl: 9.679348779618833], batch size: 70
+2022-12-13 22:18:32,940 INFO [train.py:421] (7/8) Epoch 10, batch 51600, loss[loss=2.461, over 840.00 frames. , ppl: 11.712974250802516] tot_loss[loss=2.269, over 5506874.75 frames. , ppl: 9.66661721433919], batch size: 70
+2022-12-13 22:20:11,646 INFO [train.py:421] (7/8) Epoch 10, batch 51800, loss[loss=2.395, over 1050.00 frames. , ppl: 10.966333970669526] tot_loss[loss=2.27, over 5455884.75 frames. , ppl: 9.677185800669237], batch size: 70
+2022-12-13 22:21:49,902 INFO [train.py:421] (7/8) Epoch 10, batch 52000, loss[loss=2.62, over 840.00 frames. , ppl: 13.739365752864625] tot_loss[loss=2.269, over 5486962.60 frames. , ppl: 9.673161275651994], batch size: 70
+2022-12-13 22:21:49,903 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 22:21:50,672 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.599999450495101
+2022-12-13 22:23:31,996 INFO [train.py:421] (7/8) Epoch 10, batch 52200, loss[loss=2.17, over 5040.00 frames. , ppl: 8.759782303557348] tot_loss[loss=2.269, over 5504057.03 frames. , ppl: 9.665877341821421], batch size: 70
+2022-12-13 22:25:13,144 INFO [train.py:421] (7/8) Epoch 10, batch 52400, loss[loss=2.354, over 2590.00 frames. , ppl: 10.529068210430587] tot_loss[loss=2.268, over 5508660.89 frames. , ppl: 9.663920733890782], batch size: 70
+2022-12-13 22:26:53,089 INFO [train.py:421] (7/8) Epoch 10, batch 52600, loss[loss=2.547, over 1190.00 frames. , ppl: 12.772850184205106] tot_loss[loss=2.268, over 5525002.90 frames. , ppl: 9.664851508969475], batch size: 70
+2022-12-13 22:28:32,259 INFO [train.py:421] (7/8) Epoch 10, batch 52800, loss[loss=2.469, over 1540.00 frames. , ppl: 11.807097749191328] tot_loss[loss=2.269, over 5480751.25 frames. , ppl: 9.672148512645764], batch size: 70
+2022-12-13 22:30:12,637 INFO [train.py:421] (7/8) Epoch 10, batch 53000, loss[loss=2.378, over 1680.00 frames. , ppl: 10.779316532320221] tot_loss[loss=2.269, over 5476524.71 frames. , ppl: 9.671101399631842], batch size: 70
+2022-12-13 22:30:12,638 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 22:30:13,403 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.621981307382367
+2022-12-13 22:31:58,568 INFO [train.py:421] (7/8) Epoch 10, batch 53200, loss[loss=2.457, over 980.00 frames. , ppl: 11.665393917763685] tot_loss[loss=2.269, over 5463357.44 frames. , ppl: 9.67354161520831], batch size: 70
+2022-12-13 22:33:42,495 INFO [train.py:421] (7/8) Epoch 10, batch 53400, loss[loss=2.206, over 5950.00 frames. , ppl: 9.079587438134133] tot_loss[loss=2.269, over 5453584.12 frames. , ppl: 9.672857617774481], batch size: 70
+2022-12-13 22:35:23,717 INFO [train.py:421] (7/8) Epoch 10, batch 53600, loss[loss=2.611, over 840.00 frames. , ppl: 13.61452410999241] tot_loss[loss=2.271, over 5414852.08 frames. , ppl: 9.686428215596363], batch size: 70
+2022-12-13 22:37:03,240 INFO [train.py:421] (7/8) Epoch 10, batch 53800, loss[loss=2.477, over 1260.00 frames. , ppl: 11.899825635365508] tot_loss[loss=2.271, over 5429497.56 frames. , ppl: 9.685379713349281], batch size: 70
+2022-12-13 22:38:45,589 INFO [train.py:421] (7/8) Epoch 10, batch 54000, loss[loss=2.148, over 6160.00 frames. , ppl: 8.56366688209388] tot_loss[loss=2.269, over 5482711.46 frames. , ppl: 9.672381172416378], batch size: 70
+2022-12-13 22:38:45,589 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 22:38:46,336 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.606318724465547
+2022-12-13 22:40:29,332 INFO [train.py:421] (7/8) Epoch 10, batch 54200, loss[loss=2.295, over 2660.00 frames. , ppl: 9.92598901303586] tot_loss[loss=2.269, over 5486561.76 frames. , ppl: 9.67384075217048], batch size: 70
+2022-12-13 22:42:07,629 INFO [train.py:421] (7/8) Epoch 10, batch 54400, loss[loss=2.19, over 7700.00 frames. , ppl: 8.935822807862976] tot_loss[loss=2.271, over 5470430.99 frames. , ppl: 9.685578489930572], batch size: 70
+2022-12-13 22:43:49,798 INFO [train.py:421] (7/8) Epoch 10, batch 54600, loss[loss=2.394, over 1610.00 frames. , ppl: 10.957898922668655] tot_loss[loss=2.271, over 5473043.41 frames. , ppl: 9.687228732920124], batch size: 70
+2022-12-13 22:45:29,932 INFO [train.py:421] (7/8) Epoch 10, batch 54800, loss[loss=3.308, over 490.00 frames. , ppl: 27.324972846489015] tot_loss[loss=2.271, over 5459663.87 frames. , ppl: 9.69226868338243], batch size: 70
+2022-12-13 22:47:09,473 INFO [train.py:421] (7/8) Epoch 10, batch 55000, loss[loss=2.6, over 700.00 frames. , ppl: 13.465362872631212] tot_loss[loss=2.271, over 5462514.43 frames. , ppl: 9.689163855401215], batch size: 70
+2022-12-13 22:47:09,473 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 22:47:10,233 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.265, over 211138.00 frames. , ppl: 9.6300680375108
+2022-12-13 22:48:52,900 INFO [train.py:421] (7/8) Epoch 10, batch 55200, loss[loss=2.355, over 910.00 frames. , ppl: 10.536045959593482] tot_loss[loss=2.271, over 5466310.05 frames. , ppl: 9.68903349656519], batch size: 70
+2022-12-13 22:50:33,381 INFO [train.py:421] (7/8) Epoch 10, batch 55400, loss[loss=2.394, over 1540.00 frames. , ppl: 10.96079874726666] tot_loss[loss=2.271, over 5452170.22 frames. , ppl: 9.6929787456716], batch size: 70
+2022-12-13 22:52:12,072 INFO [train.py:421] (7/8) Epoch 10, batch 55600, loss[loss=2.421, over 2310.00 frames. , ppl: 11.258308986670242] tot_loss[loss=2.272, over 5445141.48 frames. , ppl: 9.697208206984593], batch size: 70
+2022-12-13 22:53:51,922 INFO [train.py:421] (7/8) Epoch 10, batch 55800, loss[loss=2.212, over 4900.00 frames. , ppl: 9.133761824454856] tot_loss[loss=2.271, over 5457322.41 frames. , ppl: 9.692765591865953], batch size: 70
+2022-12-13 22:55:32,376 INFO [train.py:421] (7/8) Epoch 10, batch 56000, loss[loss=2.443, over 1750.00 frames. , ppl: 11.5026289528555] tot_loss[loss=2.271, over 5474699.32 frames. , ppl: 9.685831023721711], batch size: 70
+2022-12-13 22:55:32,377 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 22:55:33,125 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.602260323357212
+2022-12-13 22:57:14,363 INFO [train.py:421] (7/8) Epoch 10, batch 56200, loss[loss=2.329, over 2730.00 frames. , ppl: 10.26707711489005] tot_loss[loss=2.271, over 5458868.22 frames. , ppl: 9.693497463493262], batch size: 70
+2022-12-13 22:58:56,443 INFO [train.py:421] (7/8) Epoch 10, batch 56400, loss[loss=2.189, over 4270.00 frames. , ppl: 8.921905061942049] tot_loss[loss=2.27, over 5510907.88 frames. , ppl: 9.683600345758132], batch size: 70
+2022-12-13 23:00:37,874 INFO [train.py:421] (7/8) Epoch 10, batch 56600, loss[loss=2.353, over 2520.00 frames. , ppl: 10.516639865407072] tot_loss[loss=2.271, over 5485601.02 frames. , ppl: 9.691681480519703], batch size: 70
+2022-12-13 23:02:17,339 INFO [train.py:421] (7/8) Epoch 10, batch 56800, loss[loss=2.343, over 2240.00 frames. , ppl: 10.415207006659129] tot_loss[loss=2.271, over 5482876.55 frames. , ppl: 9.693203478974235], batch size: 70
+2022-12-13 23:03:57,913 INFO [train.py:421] (7/8) Epoch 10, batch 57000, loss[loss=2.414, over 910.00 frames. , ppl: 11.17620805656335] tot_loss[loss=2.271, over 5464951.54 frames. , ppl: 9.689910103120376], batch size: 70
+2022-12-13 23:03:57,913 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 23:03:58,673 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.264, over 211138.00 frames. , ppl: 9.62573033470701
+2022-12-13 23:05:40,823 INFO [train.py:421] (7/8) Epoch 10, batch 57200, loss[loss=2.217, over 5460.00 frames. , ppl: 9.176196833750605] tot_loss[loss=2.272, over 5421344.43 frames. , ppl: 9.700702777166969], batch size: 70
+2022-12-13 23:07:18,395 INFO [train.py:421] (7/8) Epoch 10, batch 57400, loss[loss=2.321, over 3150.00 frames. , ppl: 10.185589500950828] tot_loss[loss=2.271, over 5456754.22 frames. , ppl: 9.684865682832625], batch size: 70
+2022-12-13 23:08:53,701 INFO [train.py:421] (7/8) Epoch 10, batch 57600, loss[loss=2.458, over 1260.00 frames. , ppl: 11.681036733268938] tot_loss[loss=2.271, over 5451936.40 frames. , ppl: 9.692567005885378], batch size: 70
+2022-12-13 23:10:36,335 INFO [train.py:421] (7/8) Epoch 10, batch 57800, loss[loss=2.286, over 2310.00 frames. , ppl: 9.834642268348036] tot_loss[loss=2.272, over 5445713.73 frames. , ppl: 9.696044295476323], batch size: 70
+2022-12-13 23:12:20,211 INFO [train.py:421] (7/8) Epoch 10, batch 58000, loss[loss=2.156, over 4970.00 frames. , ppl: 8.637821232367385] tot_loss[loss=2.271, over 5468164.47 frames. , ppl: 9.691388723212844], batch size: 70
+2022-12-13 23:12:20,211 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 23:12:20,972 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.609582325499408
+2022-12-13 23:14:05,388 INFO [train.py:421] (7/8) Epoch 10, batch 58200, loss[loss=2.144, over 5110.00 frames. , ppl: 8.534113153860659] tot_loss[loss=2.27, over 5496454.87 frames. , ppl: 9.68361398596861], batch size: 70
+2022-12-13 23:15:40,222 INFO [train.py:421] (7/8) Epoch 10, batch 58400, loss[loss=2.197, over 4130.00 frames. , ppl: 8.993753199741363] tot_loss[loss=2.269, over 5489130.11 frames. , ppl: 9.67446962349504], batch size: 70
+2022-12-13 23:17:18,338 INFO [train.py:421] (7/8) Epoch 10, batch 58600, loss[loss=3.387, over 490.00 frames. , ppl: 29.56560306710497] tot_loss[loss=2.269, over 5504661.45 frames. , ppl: 9.674350522199529], batch size: 70
+2022-12-13 23:18:57,520 INFO [train.py:421] (7/8) Epoch 10, batch 58800, loss[loss=2.404, over 1190.00 frames. , ppl: 11.063300695273158] tot_loss[loss=2.268, over 5540865.12 frames. , ppl: 9.661654881208765], batch size: 70
+2022-12-13 23:20:40,942 INFO [train.py:421] (7/8) Epoch 10, batch 59000, loss[loss=2.804, over 630.00 frames. , ppl: 16.509857009229123] tot_loss[loss=2.268, over 5550503.19 frames. , ppl: 9.659243582975733], batch size: 70
+2022-12-13 23:20:40,943 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 23:20:41,703 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.606206402379026
+2022-12-13 23:22:20,235 INFO [train.py:421] (7/8) Epoch 10, batch 59200, loss[loss=2.255, over 2520.00 frames. , ppl: 9.538022947906404] tot_loss[loss=2.269, over 5526483.83 frames. , ppl: 9.667446307112368], batch size: 70
+2022-12-13 23:24:00,411 INFO [train.py:421] (7/8) Epoch 10, batch 59400, loss[loss=2.301, over 2100.00 frames. , ppl: 9.981854819492751] tot_loss[loss=2.269, over 5520924.04 frames. , ppl: 9.665701012065425], batch size: 70
+2022-12-13 23:25:41,350 INFO [train.py:421] (7/8) Epoch 10, batch 59600, loss[loss=2.486, over 1400.00 frames. , ppl: 12.012470846668739] tot_loss[loss=2.269, over 5530229.50 frames. , ppl: 9.666618451528997], batch size: 70
+2022-12-13 23:27:19,479 INFO [train.py:421] (7/8) Epoch 10, batch 59800, loss[loss=2.38, over 1820.00 frames. , ppl: 10.803381676320189] tot_loss[loss=2.269, over 5533165.98 frames. , ppl: 9.669420183566697], batch size: 70
+2022-12-13 23:28:53,388 INFO [train.py:421] (7/8) Epoch 10, batch 60000, loss[loss=2.213, over 4830.00 frames. , ppl: 9.140005075159438] tot_loss[loss=2.27, over 5490706.67 frames. , ppl: 9.683422800019073], batch size: 70
+2022-12-13 23:28:53,388 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 23:28:54,130 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.612700490778435
+2022-12-13 23:30:35,176 INFO [train.py:421] (7/8) Epoch 10, batch 60200, loss[loss=2.255, over 3500.00 frames. , ppl: 9.538972184549582] tot_loss[loss=2.269, over 5538687.08 frames. , ppl: 9.66831083700845], batch size: 70
+2022-12-13 23:32:13,583 INFO [train.py:421] (7/8) Epoch 10, batch 60400, loss[loss=2.237, over 3780.00 frames. , ppl: 9.365250040941902] tot_loss[loss=2.268, over 5567530.80 frames. , ppl: 9.657907134831735], batch size: 70
+2022-12-13 23:33:56,149 INFO [train.py:421] (7/8) Epoch 10, batch 60600, loss[loss=2.604, over 840.00 frames. , ppl: 13.514430247112676] tot_loss[loss=2.267, over 5613721.49 frames. , ppl: 9.649222599664487], batch size: 70
+2022-12-13 23:35:35,542 INFO [train.py:421] (7/8) Epoch 10, batch 60800, loss[loss=2.277, over 1400.00 frames. , ppl: 9.748749502665099] tot_loss[loss=2.267, over 5621605.73 frames. , ppl: 9.646475106894268], batch size: 70
+2022-12-13 23:37:16,238 INFO [train.py:421] (7/8) Epoch 10, batch 61000, loss[loss=2.184, over 3710.00 frames. , ppl: 8.88577073481145] tot_loss[loss=2.267, over 5596943.44 frames. , ppl: 9.652289727428345], batch size: 70
+2022-12-13 23:37:16,238 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 23:37:16,983 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.60258010007721
+2022-12-13 23:38:59,953 INFO [train.py:421] (7/8) Epoch 10, batch 61200, loss[loss=3.325, over 490.00 frames. , ppl: 27.79949727395079] tot_loss[loss=2.266, over 5653251.47 frames. , ppl: 9.636691946771846], batch size: 70
+2022-12-13 23:40:40,176 INFO [train.py:421] (7/8) Epoch 10, batch 61400, loss[loss=2.331, over 2520.00 frames. , ppl: 10.290657416027674] tot_loss[loss=2.267, over 5584174.39 frames. , ppl: 9.65463457024963], batch size: 70
+2022-12-13 23:42:19,009 INFO [train.py:421] (7/8) Epoch 10, batch 61600, loss[loss=2.251, over 3010.00 frames. , ppl: 9.501761214711946] tot_loss[loss=2.268, over 5573009.04 frames. , ppl: 9.658131754066744], batch size: 70
+2022-12-13 23:44:03,604 INFO [train.py:421] (7/8) Epoch 10, batch 61800, loss[loss=2.145, over 5810.00 frames. , ppl: 8.545394710891095] tot_loss[loss=2.268, over 5557736.24 frames. , ppl: 9.660120409165614], batch size: 70
+2022-12-13 23:45:42,347 INFO [train.py:421] (7/8) Epoch 10, batch 62000, loss[loss=2.255, over 2100.00 frames. , ppl: 9.533151834382695] tot_loss[loss=2.266, over 5598222.39 frames. , ppl: 9.645578487231859], batch size: 70
+2022-12-13 23:45:42,347 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 23:45:43,104 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.61007587277309
+2022-12-13 23:47:24,546 INFO [train.py:421] (7/8) Epoch 10, batch 62200, loss[loss=2.211, over 3850.00 frames. , ppl: 9.128109087115302] tot_loss[loss=2.265, over 5616097.77 frames. , ppl: 9.633625165082282], batch size: 70
+2022-12-13 23:49:09,221 INFO [train.py:421] (7/8) Epoch 10, batch 62400, loss[loss=2.196, over 3570.00 frames. , ppl: 8.990086519663377] tot_loss[loss=2.266, over 5589040.97 frames. , ppl: 9.64451694061729], batch size: 70
+2022-12-13 23:50:45,970 INFO [train.py:421] (7/8) Epoch 10, batch 62600, loss[loss=2.416, over 1540.00 frames. , ppl: 11.202081927641652] tot_loss[loss=2.267, over 5573921.20 frames. , ppl: 9.650082163872577], batch size: 70
+2022-12-13 23:52:24,486 INFO [train.py:421] (7/8) Epoch 10, batch 62800, loss[loss=2.494, over 910.00 frames. , ppl: 12.10566516364101] tot_loss[loss=2.268, over 5534293.65 frames. , ppl: 9.660455555194444], batch size: 70
+2022-12-13 23:54:03,435 INFO [train.py:421] (7/8) Epoch 10, batch 63000, loss[loss=2.678, over 630.00 frames. , ppl: 14.557382609660252] tot_loss[loss=2.269, over 5515076.95 frames. , ppl: 9.665859438180068], batch size: 70
+2022-12-13 23:54:03,435 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-13 23:54:04,195 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.606716838640049
+2022-12-13 23:55:42,812 INFO [train.py:421] (7/8) Epoch 10, batch 63200, loss[loss=2.355, over 2100.00 frames. , ppl: 10.53942268461243] tot_loss[loss=2.269, over 5515425.35 frames. , ppl: 9.666185552537515], batch size: 70
+2022-12-13 23:57:21,549 INFO [train.py:421] (7/8) Epoch 10, batch 63400, loss[loss=2.25, over 1890.00 frames. , ppl: 9.484941930767551] tot_loss[loss=2.268, over 5517489.90 frames. , ppl: 9.660785073655587], batch size: 70
+2022-12-13 23:59:00,636 INFO [train.py:421] (7/8) Epoch 10, batch 63600, loss[loss=2.279, over 3430.00 frames. , ppl: 9.76331576010102] tot_loss[loss=2.27, over 5454123.31 frames. , ppl: 9.681482021367525], batch size: 70
+2022-12-14 00:00:37,637 INFO [train.py:421] (7/8) Epoch 10, batch 63800, loss[loss=2.53, over 980.00 frames. , ppl: 12.549077313771042] tot_loss[loss=2.269, over 5485854.10 frames. , ppl: 9.666434259445628], batch size: 70
+2022-12-14 00:02:18,825 INFO [train.py:421] (7/8) Epoch 10, batch 64000, loss[loss=2.209, over 3850.00 frames. , ppl: 9.109535599366485] tot_loss[loss=2.268, over 5515593.07 frames. , ppl: 9.658304989321373], batch size: 70
+2022-12-14 00:02:18,826 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 00:02:19,585 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.616598196927988
+2022-12-14 00:03:57,270 INFO [train.py:421] (7/8) Epoch 10, batch 64200, loss[loss=2.355, over 1820.00 frames. , ppl: 10.54180547602143] tot_loss[loss=2.268, over 5528987.97 frames. , ppl: 9.659438801938427], batch size: 70
+2022-12-14 00:05:36,744 INFO [train.py:421] (7/8) Epoch 10, batch 64400, loss[loss=2.479, over 1190.00 frames. , ppl: 11.925365052801428] tot_loss[loss=2.268, over 5533601.33 frames. , ppl: 9.659664926986016], batch size: 70
+2022-12-14 00:07:12,123 INFO [train.py:421] (7/8) Epoch 10, batch 64600, loss[loss=2.272, over 2520.00 frames. , ppl: 9.70230301203624] tot_loss[loss=2.268, over 5529222.37 frames. , ppl: 9.65847987691602], batch size: 70
+2022-12-14 00:08:51,349 INFO [train.py:421] (7/8) Epoch 10, batch 64800, loss[loss=2.353, over 1680.00 frames. , ppl: 10.513131480734248] tot_loss[loss=2.269, over 5512883.02 frames. , ppl: 9.669578062343755], batch size: 70
+2022-12-14 00:10:28,829 INFO [train.py:421] (7/8) Epoch 10, batch 65000, loss[loss=2.195, over 4970.00 frames. , ppl: 8.980238207865986] tot_loss[loss=2.27, over 5469653.32 frames. , ppl: 9.682866279082877], batch size: 70
+2022-12-14 00:10:28,829 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 00:10:29,560 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.599982400051333
+2022-12-14 00:12:08,439 INFO [train.py:421] (7/8) Epoch 10, batch 65200, loss[loss=2.166, over 3150.00 frames. , ppl: 8.72532885704593] tot_loss[loss=2.271, over 5454052.69 frames. , ppl: 9.691601430774172], batch size: 70
+2022-12-14 00:13:46,655 INFO [train.py:421] (7/8) Epoch 10, batch 65400, loss[loss=2.362, over 1610.00 frames. , ppl: 10.613788494757564] tot_loss[loss=2.271, over 5460747.91 frames. , ppl: 9.68462327061495], batch size: 70
+2022-12-14 00:15:25,096 INFO [train.py:421] (7/8) Epoch 10, batch 65600, loss[loss=2.221, over 4340.00 frames. , ppl: 9.214681995426238] tot_loss[loss=2.27, over 5452406.54 frames. , ppl: 9.682218933789764], batch size: 70
+2022-12-14 00:17:06,086 INFO [train.py:421] (7/8) Epoch 10, batch 65800, loss[loss=2.224, over 2730.00 frames. , ppl: 9.248045888634095] tot_loss[loss=2.27, over 5461494.99 frames. , ppl: 9.68357865116692], batch size: 70
+2022-12-14 00:18:46,951 INFO [train.py:421] (7/8) Epoch 10, batch 66000, loss[loss=2.135, over 4270.00 frames. , ppl: 8.454422654817126] tot_loss[loss=2.271, over 5428187.90 frames. , ppl: 9.690972419569155], batch size: 70
+2022-12-14 00:18:46,952 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 00:18:47,681 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.599644239172868
+2022-12-14 00:20:26,482 INFO [train.py:421] (7/8) Epoch 10, batch 66200, loss[loss=2.878, over 630.00 frames. , ppl: 17.783641912925894] tot_loss[loss=2.271, over 5407469.04 frames. , ppl: 9.690802282410145], batch size: 70
+2022-12-14 00:22:05,234 INFO [train.py:421] (7/8) Epoch 10, batch 66400, loss[loss=2.157, over 8400.00 frames. , ppl: 8.644870556773995] tot_loss[loss=2.271, over 5403384.29 frames. , ppl: 9.690890393203054], batch size: 70
+2022-12-14 00:23:48,625 INFO [train.py:421] (7/8) Epoch 10, batch 66600, loss[loss=2.473, over 980.00 frames. , ppl: 11.85803881756567] tot_loss[loss=2.27, over 5448618.40 frames. , ppl: 9.678799779630268], batch size: 70
+2022-12-14 00:25:27,836 INFO [train.py:421] (7/8) Epoch 10, batch 66800, loss[loss=2.388, over 3290.00 frames. , ppl: 10.886677292187079] tot_loss[loss=2.272, over 5392691.91 frames. , ppl: 9.697089063305844], batch size: 70
+2022-12-14 00:27:09,561 INFO [train.py:421] (7/8) Epoch 10, batch 67000, loss[loss=2.516, over 770.00 frames. , ppl: 12.376810402269841] tot_loss[loss=2.273, over 5376785.58 frames. , ppl: 9.70722013025639], batch size: 70
+2022-12-14 00:27:09,562 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 00:27:10,333 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.608690591101315
+2022-12-14 00:28:53,508 INFO [train.py:421] (7/8) Epoch 10, batch 67200, loss[loss=2.358, over 2030.00 frames. , ppl: 10.571317475686419] tot_loss[loss=2.274, over 5363055.64 frames. , ppl: 9.714130948903835], batch size: 70
+2022-12-14 00:30:34,766 INFO [train.py:421] (7/8) Epoch 10, batch 67400, loss[loss=2.508, over 1400.00 frames. , ppl: 12.283327868202033] tot_loss[loss=2.272, over 5391597.40 frames. , ppl: 9.698560696033347], batch size: 70
+2022-12-14 00:32:15,546 INFO [train.py:421] (7/8) Epoch 10, batch 67600, loss[loss=2.262, over 1890.00 frames. , ppl: 9.600992956793972] tot_loss[loss=2.271, over 5432847.77 frames. , ppl: 9.685415751258484], batch size: 70
+2022-12-14 00:33:55,294 INFO [train.py:421] (7/8) Epoch 10, batch 67800, loss[loss=2.252, over 4200.00 frames. , ppl: 9.5086323629817] tot_loss[loss=2.271, over 5420589.83 frames. , ppl: 9.68491208202862], batch size: 70
+2022-12-14 00:35:36,607 INFO [train.py:421] (7/8) Epoch 10, batch 68000, loss[loss=2.386, over 2170.00 frames. , ppl: 10.867342747335458] tot_loss[loss=2.271, over 5425737.49 frames. , ppl: 9.684532030989452], batch size: 70
+2022-12-14 00:35:36,608 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 00:35:37,368 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.606830588577454
+2022-12-14 00:37:17,020 INFO [train.py:421] (7/8) Epoch 10, batch 68200, loss[loss=2.187, over 5180.00 frames. , ppl: 8.906469716004976] tot_loss[loss=2.271, over 5392562.53 frames. , ppl: 9.686968605159384], batch size: 70
+2022-12-14 00:38:58,133 INFO [train.py:421] (7/8) Epoch 10, batch 68400, loss[loss=2.528, over 700.00 frames. , ppl: 12.532826890476846] tot_loss[loss=2.272, over 5386670.06 frames. , ppl: 9.698793155080667], batch size: 70
+2022-12-14 00:40:37,857 INFO [train.py:421] (7/8) Epoch 10, batch 68600, loss[loss=2.293, over 4410.00 frames. , ppl: 9.903525473211477] tot_loss[loss=2.272, over 5384533.55 frames. , ppl: 9.696429706645878], batch size: 70
+2022-12-14 00:42:17,523 INFO [train.py:421] (7/8) Epoch 10, batch 68800, loss[loss=2.435, over 1050.00 frames. , ppl: 11.420499287687077] tot_loss[loss=2.272, over 5392316.01 frames. , ppl: 9.69450364947349], batch size: 70
+2022-12-14 00:44:01,116 INFO [train.py:421] (7/8) Epoch 10, batch 69000, loss[loss=2.192, over 10220.00 frames. , ppl: 8.956358273598319] tot_loss[loss=2.271, over 5415501.14 frames. , ppl: 9.684690990676394], batch size: 70
+2022-12-14 00:44:01,116 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 00:44:01,845 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.60023105535575
+2022-12-14 00:45:40,105 INFO [train.py:421] (7/8) Epoch 10, batch 69200, loss[loss=2.241, over 2590.00 frames. , ppl: 9.399691264498292] tot_loss[loss=2.272, over 5378350.08 frames. , ppl: 9.694721645814349], batch size: 70
+2022-12-14 00:47:14,231 INFO [train.py:421] (7/8) Epoch 10, batch 69400, loss[loss=2.328, over 1820.00 frames. , ppl: 10.256960170247103] tot_loss[loss=2.271, over 5392344.21 frames. , ppl: 9.691827212551354], batch size: 70
+2022-12-14 00:48:53,975 INFO [train.py:421] (7/8) Epoch 10, batch 69600, loss[loss=2.906, over 630.00 frames. , ppl: 18.290694172844365] tot_loss[loss=2.27, over 5416063.73 frames. , ppl: 9.683544248026694], batch size: 70
+2022-12-14 00:50:33,922 INFO [train.py:421] (7/8) Epoch 10, batch 69800, loss[loss=2.243, over 4830.00 frames. , ppl: 9.42391301101034] tot_loss[loss=2.268, over 5474913.22 frames. , ppl: 9.66362840386447], batch size: 70
+2022-12-14 00:52:14,677 INFO [train.py:421] (7/8) Epoch 10, batch 70000, loss[loss=2.438, over 1750.00 frames. , ppl: 11.446990322498728] tot_loss[loss=2.268, over 5489099.60 frames. , ppl: 9.663610296412482], batch size: 70
+2022-12-14 00:52:14,677 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 00:52:15,422 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.262, over 211138.00 frames. , ppl: 9.601824022965605
+2022-12-14 00:53:54,453 INFO [train.py:421] (7/8) Epoch 10, batch 70200, loss[loss=2.245, over 1750.00 frames. , ppl: 9.440465603438877] tot_loss[loss=2.27, over 5425077.85 frames. , ppl: 9.680530936567866], batch size: 70
+2022-12-14 00:55:36,203 INFO [train.py:421] (7/8) Epoch 10, batch 70400, loss[loss=2.337, over 840.00 frames. , ppl: 10.352460068257534] tot_loss[loss=2.271, over 5401130.44 frames. , ppl: 9.685808539814841], batch size: 70
+2022-12-14 00:57:16,765 INFO [train.py:421] (7/8) Epoch 10, batch 70600, loss[loss=2.418, over 1190.00 frames. , ppl: 11.222855147365722] tot_loss[loss=2.27, over 5389938.33 frames. , ppl: 9.680869003778387], batch size: 70
+2022-12-14 00:58:55,100 INFO [train.py:421] (7/8) Epoch 10, batch 70800, loss[loss=2.458, over 1890.00 frames. , ppl: 11.67698152180706] tot_loss[loss=2.27, over 5406170.01 frames. , ppl: 9.678999784734126], batch size: 70
+2022-12-14 01:00:36,976 INFO [train.py:421] (7/8) Epoch 10, batch 71000, loss[loss=2.316, over 1540.00 frames. , ppl: 10.134332405359196] tot_loss[loss=2.27, over 5403085.80 frames. , ppl: 9.675416444594097], batch size: 70
+2022-12-14 01:00:36,977 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 01:00:37,735 INFO [train.py:452] (7/8) Epoch 10, validation: loss=2.263, over 211138.00 frames. , ppl: 9.609851142052824
+2022-12-14 01:02:17,479 INFO [train.py:421] (7/8) Epoch 10, batch 71200, loss[loss=2.571, over 840.00 frames. , ppl: 13.074220368007717] tot_loss[loss=2.269, over 5411296.64 frames. , ppl: 9.670166052142665], batch size: 70
+2022-12-14 01:03:55,204 INFO [train.py:421] (7/8) Epoch 10, batch 71400, loss[loss=2.374, over 1820.00 frames. , ppl: 10.743853728367029] tot_loss[loss=2.269, over 5432045.32 frames. , ppl: 9.670247986140323], batch size: 70
+2022-12-14 01:05:31,344 INFO [train.py:421] (7/8) Epoch 10, batch 71600, loss[loss=2.255, over 4970.00 frames. , ppl: 9.535360010668072] tot_loss[loss=2.269, over 5433885.15 frames. , ppl: 9.673831110777193], batch size: 70
+2022-12-14 01:07:12,760 INFO [train.py:421] (7/8) Epoch 10, batch 71800, loss[loss=2.234, over 3570.00 frames. , ppl: 9.33485405484197] tot_loss[loss=2.27, over 5429570.42 frames. , ppl: 9.681023328593088], batch size: 70
+2022-12-14 01:08:27,263 INFO [train.py:421] (7/8) Epoch 11, batch 0, loss[loss=2.461, over 840.00 frames. , ppl: 11.71980526979706] tot_loss[loss=2.461, over 840.00 frames. , ppl: 11.71980526979706], batch size: 70
+2022-12-14 01:10:06,170 INFO [train.py:421] (7/8) Epoch 11, batch 200, loss[loss=2.38, over 1330.00 frames. , ppl: 10.804049244318637] tot_loss[loss=2.276, over 488521.08 frames. , ppl: 9.742320572044381], batch size: 70
+2022-12-14 01:11:46,162 INFO [train.py:421] (7/8) Epoch 11, batch 400, loss[loss=2.191, over 10290.00 frames. , ppl: 8.945963242092024] tot_loss[loss=2.265, over 976054.55 frames. , ppl: 9.632753410317912], batch size: 70
+2022-12-14 01:13:23,774 INFO [train.py:421] (7/8) Epoch 11, batch 600, loss[loss=2.293, over 1680.00 frames. , ppl: 9.905250331054336] tot_loss[loss=2.269, over 1356520.57 frames. , ppl: 9.669192300978949], batch size: 70
+2022-12-14 01:15:02,880 INFO [train.py:421] (7/8) Epoch 11, batch 800, loss[loss=2.257, over 2030.00 frames. , ppl: 9.5584444742357] tot_loss[loss=2.263, over 1775526.31 frames. , ppl: 9.607177420190288], batch size: 70
+2022-12-14 01:16:43,480 INFO [train.py:421] (7/8) Epoch 11, batch 1000, loss[loss=2.281, over 2520.00 frames. , ppl: 9.784501910506316] tot_loss[loss=2.26, over 2147143.26 frames. , ppl: 9.584493957595525], batch size: 70
+2022-12-14 01:16:43,480 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 01:16:44,237 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.264, over 211138.00 frames. , ppl: 9.619912276163067
+2022-12-14 01:18:27,842 INFO [train.py:421] (7/8) Epoch 11, batch 1200, loss[loss=2.228, over 4270.00 frames. , ppl: 9.285128932327032] tot_loss[loss=2.263, over 2442472.79 frames. , ppl: 9.611676380486317], batch size: 70
+2022-12-14 01:20:08,992 INFO [train.py:421] (7/8) Epoch 11, batch 1400, loss[loss=2.234, over 5810.00 frames. , ppl: 9.334736070631411] tot_loss[loss=2.262, over 2749753.83 frames. , ppl: 9.60691097964534], batch size: 70
+2022-12-14 01:21:47,211 INFO [train.py:421] (7/8) Epoch 11, batch 1600, loss[loss=2.223, over 5740.00 frames. , ppl: 9.235298391881164] tot_loss[loss=2.261, over 3026752.37 frames. , ppl: 9.589019066148209], batch size: 70
+2022-12-14 01:23:27,107 INFO [train.py:421] (7/8) Epoch 11, batch 1800, loss[loss=2.589, over 770.00 frames. , ppl: 13.313506459752176] tot_loss[loss=2.261, over 3274412.48 frames. , ppl: 9.590149777458848], batch size: 70
+2022-12-14 01:25:04,643 INFO [train.py:421] (7/8) Epoch 11, batch 2000, loss[loss=2.474, over 1400.00 frames. , ppl: 11.866454520453281] tot_loss[loss=2.258, over 3518185.28 frames. , ppl: 9.568483492985278], batch size: 70
+2022-12-14 01:25:04,644 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 01:25:05,404 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.264, over 211138.00 frames. , ppl: 9.623191889826966
+2022-12-14 01:26:47,629 INFO [train.py:421] (7/8) Epoch 11, batch 2200, loss[loss=2.174, over 6510.00 frames. , ppl: 8.797223091588451] tot_loss[loss=2.258, over 3710628.70 frames. , ppl: 9.566619065709324], batch size: 70
+2022-12-14 01:28:26,721 INFO [train.py:421] (7/8) Epoch 11, batch 2400, loss[loss=2.318, over 3990.00 frames. , ppl: 10.153062615784474] tot_loss[loss=2.26, over 3860883.75 frames. , ppl: 9.582208297969423], batch size: 70
+2022-12-14 01:30:12,133 INFO [train.py:421] (7/8) Epoch 11, batch 2600, loss[loss=2.4, over 1610.00 frames. , ppl: 11.02737947355046] tot_loss[loss=2.261, over 4007346.67 frames. , ppl: 9.589251394288418], batch size: 70
+2022-12-14 01:31:49,623 INFO [train.py:421] (7/8) Epoch 11, batch 2800, loss[loss=2.424, over 1120.00 frames. , ppl: 11.29279742249511] tot_loss[loss=2.261, over 4145881.38 frames. , ppl: 9.590169732275749], batch size: 70
+2022-12-14 01:33:29,897 INFO [train.py:421] (7/8) Epoch 11, batch 3000, loss[loss=2.185, over 4620.00 frames. , ppl: 8.893037815197468] tot_loss[loss=2.261, over 4258915.43 frames. , ppl: 9.594837036369572], batch size: 70
+2022-12-14 01:33:29,898 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 01:33:30,660 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.263, over 211138.00 frames. , ppl: 9.612494194035516
+2022-12-14 01:35:15,620 INFO [train.py:421] (7/8) Epoch 11, batch 3200, loss[loss=2.247, over 2520.00 frames. , ppl: 9.455510809716024] tot_loss[loss=2.262, over 4379046.90 frames. , ppl: 9.601656300703668], batch size: 70
+2022-12-14 01:36:56,902 INFO [train.py:421] (7/8) Epoch 11, batch 3400, loss[loss=2.288, over 2730.00 frames. , ppl: 9.853719037467773] tot_loss[loss=2.26, over 4537802.59 frames. , ppl: 9.584404705647934], batch size: 70
+2022-12-14 01:38:36,971 INFO [train.py:421] (7/8) Epoch 11, batch 3600, loss[loss=2.292, over 1750.00 frames. , ppl: 9.89128451969065] tot_loss[loss=2.261, over 4604821.20 frames. , ppl: 9.59053526790349], batch size: 70
+2022-12-14 01:40:18,034 INFO [train.py:421] (7/8) Epoch 11, batch 3800, loss[loss=2.375, over 2170.00 frames. , ppl: 10.749327182736428] tot_loss[loss=2.261, over 4711671.81 frames. , ppl: 9.589381868284532], batch size: 70
+2022-12-14 01:42:00,374 INFO [train.py:421] (7/8) Epoch 11, batch 4000, loss[loss=2.246, over 2450.00 frames. , ppl: 9.447744806775537] tot_loss[loss=2.26, over 4801578.89 frames. , ppl: 9.585938453987886], batch size: 70
+2022-12-14 01:42:00,375 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 01:42:01,137 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.606853338726559
+2022-12-14 01:43:42,448 INFO [train.py:421] (7/8) Epoch 11, batch 4200, loss[loss=2.249, over 2590.00 frames. , ppl: 9.477731656157813] tot_loss[loss=2.262, over 4847988.22 frames. , ppl: 9.59823469146145], batch size: 70
+2022-12-14 01:45:19,905 INFO [train.py:421] (7/8) Epoch 11, batch 4400, loss[loss=2.318, over 1750.00 frames. , ppl: 10.150997602383303] tot_loss[loss=2.262, over 4893332.19 frames. , ppl: 9.6028758658223], batch size: 70
+2022-12-14 01:46:59,748 INFO [train.py:421] (7/8) Epoch 11, batch 4600, loss[loss=2.383, over 1890.00 frames. , ppl: 10.837786898188215] tot_loss[loss=2.262, over 4970694.90 frames. , ppl: 9.601361964398409], batch size: 70
+2022-12-14 01:48:42,458 INFO [train.py:421] (7/8) Epoch 11, batch 4800, loss[loss=2.387, over 2100.00 frames. , ppl: 10.875886425865646] tot_loss[loss=2.262, over 5020918.61 frames. , ppl: 9.598462168184245], batch size: 70
+2022-12-14 01:50:23,265 INFO [train.py:421] (7/8) Epoch 11, batch 5000, loss[loss=2.41, over 1190.00 frames. , ppl: 11.137729874257426] tot_loss[loss=2.262, over 5036635.07 frames. , ppl: 9.603809485435026], batch size: 70
+2022-12-14 01:50:23,266 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 01:50:24,027 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.263, over 211138.00 frames. , ppl: 9.615150780970064
+2022-12-14 01:52:05,453 INFO [train.py:421] (7/8) Epoch 11, batch 5200, loss[loss=2.297, over 2450.00 frames. , ppl: 9.941571706657971] tot_loss[loss=2.262, over 5079606.27 frames. , ppl: 9.604444193353428], batch size: 70
+2022-12-14 01:53:46,206 INFO [train.py:421] (7/8) Epoch 11, batch 5400, loss[loss=2.395, over 1540.00 frames. , ppl: 10.971859233760197] tot_loss[loss=2.263, over 5117936.39 frames. , ppl: 9.609019730674763], batch size: 70
+2022-12-14 01:55:25,272 INFO [train.py:421] (7/8) Epoch 11, batch 5600, loss[loss=2.578, over 770.00 frames. , ppl: 13.174005971751027] tot_loss[loss=2.263, over 5162795.42 frames. , ppl: 9.608477940909232], batch size: 70
+2022-12-14 01:57:09,550 INFO [train.py:421] (7/8) Epoch 11, batch 5800, loss[loss=2.452, over 1820.00 frames. , ppl: 11.606489461296322] tot_loss[loss=2.261, over 5237131.43 frames. , ppl: 9.591881633710557], batch size: 70
+2022-12-14 01:58:49,592 INFO [train.py:421] (7/8) Epoch 11, batch 6000, loss[loss=2.291, over 3780.00 frames. , ppl: 9.880138883549465] tot_loss[loss=2.26, over 5286707.57 frames. , ppl: 9.585206604801373], batch size: 70
+2022-12-14 01:58:49,592 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 01:58:50,322 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.606113986457235
+2022-12-14 02:00:27,434 INFO [train.py:421] (7/8) Epoch 11, batch 6200, loss[loss=2.27, over 2310.00 frames. , ppl: 9.67503848861141] tot_loss[loss=2.26, over 5302865.40 frames. , ppl: 9.584839162557252], batch size: 70
+2022-12-14 02:02:09,159 INFO [train.py:421] (7/8) Epoch 11, batch 6400, loss[loss=2.336, over 1330.00 frames. , ppl: 10.339778460570983] tot_loss[loss=2.262, over 5277439.55 frames. , ppl: 9.601161207359402], batch size: 70
+2022-12-14 02:03:48,307 INFO [train.py:421] (7/8) Epoch 11, batch 6600, loss[loss=2.267, over 2520.00 frames. , ppl: 9.64894151756858] tot_loss[loss=2.262, over 5270271.30 frames. , ppl: 9.60498537256165], batch size: 70
+2022-12-14 02:05:25,883 INFO [train.py:421] (7/8) Epoch 11, batch 6800, loss[loss=2.262, over 2380.00 frames. , ppl: 9.603718882345637] tot_loss[loss=2.263, over 5276990.85 frames. , ppl: 9.609545634124942], batch size: 70
+2022-12-14 02:07:09,116 INFO [train.py:421] (7/8) Epoch 11, batch 7000, loss[loss=2.227, over 5110.00 frames. , ppl: 9.27408830239312] tot_loss[loss=2.262, over 5319245.39 frames. , ppl: 9.602582870056857], batch size: 70
+2022-12-14 02:07:09,116 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 02:07:09,879 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.263, over 211138.00 frames. , ppl: 9.616433092260849
+2022-12-14 02:08:51,381 INFO [train.py:421] (7/8) Epoch 11, batch 7200, loss[loss=2.753, over 700.00 frames. , ppl: 15.690943055941982] tot_loss[loss=2.262, over 5322631.89 frames. , ppl: 9.604857756639086], batch size: 70
+2022-12-14 02:10:28,063 INFO [train.py:421] (7/8) Epoch 11, batch 7400, loss[loss=2.642, over 840.00 frames. , ppl: 14.04789582716139] tot_loss[loss=2.263, over 5353428.98 frames. , ppl: 9.608308042909366], batch size: 70
+2022-12-14 02:12:08,227 INFO [train.py:421] (7/8) Epoch 11, batch 7600, loss[loss=2.346, over 1750.00 frames. , ppl: 10.440448068790033] tot_loss[loss=2.263, over 5356802.37 frames. , ppl: 9.611564543213278], batch size: 70
+2022-12-14 02:13:46,077 INFO [train.py:421] (7/8) Epoch 11, batch 7800, loss[loss=2.414, over 1610.00 frames. , ppl: 11.178905138991425] tot_loss[loss=2.264, over 5338952.44 frames. , ppl: 9.6222453125823], batch size: 70
+2022-12-14 02:15:21,894 INFO [train.py:421] (7/8) Epoch 11, batch 8000, loss[loss=2.334, over 1750.00 frames. , ppl: 10.318936967966648] tot_loss[loss=2.266, over 5325991.34 frames. , ppl: 9.639230164574293], batch size: 70
+2022-12-14 02:15:21,895 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 02:15:22,633 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.595916733986652
+2022-12-14 02:17:02,600 INFO [train.py:421] (7/8) Epoch 11, batch 8200, loss[loss=2.381, over 1470.00 frames. , ppl: 10.817253209229088] tot_loss[loss=2.266, over 5325468.09 frames. , ppl: 9.640613219182704], batch size: 70
+2022-12-14 02:18:44,667 INFO [train.py:421] (7/8) Epoch 11, batch 8400, loss[loss=2.375, over 2940.00 frames. , ppl: 10.750588233481391] tot_loss[loss=2.265, over 5379214.58 frames. , ppl: 9.632037875574833], batch size: 70
+2022-12-14 02:20:24,717 INFO [train.py:421] (7/8) Epoch 11, batch 8600, loss[loss=2.631, over 700.00 frames. , ppl: 13.88707810618418] tot_loss[loss=2.266, over 5368275.68 frames. , ppl: 9.6379810941033], batch size: 70
+2022-12-14 02:22:03,174 INFO [train.py:421] (7/8) Epoch 11, batch 8800, loss[loss=2.375, over 1680.00 frames. , ppl: 10.749764935627317] tot_loss[loss=2.265, over 5405881.85 frames. , ppl: 9.631077146020399], batch size: 70
+2022-12-14 02:23:44,981 INFO [train.py:421] (7/8) Epoch 11, batch 9000, loss[loss=2.159, over 6020.00 frames. , ppl: 8.661124306016417] tot_loss[loss=2.263, over 5476531.97 frames. , ppl: 9.607967342222116], batch size: 70
+2022-12-14 02:23:44,982 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 02:23:45,723 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.263, over 211138.00 frames. , ppl: 9.615415483833607
+2022-12-14 02:25:22,463 INFO [train.py:421] (7/8) Epoch 11, batch 9200, loss[loss=2.252, over 3710.00 frames. , ppl: 9.510759819042718] tot_loss[loss=2.264, over 5452746.42 frames. , ppl: 9.622977860922475], batch size: 70
+2022-12-14 02:27:01,802 INFO [train.py:421] (7/8) Epoch 11, batch 9400, loss[loss=2.348, over 1470.00 frames. , ppl: 10.463790973257975] tot_loss[loss=2.264, over 5450852.95 frames. , ppl: 9.626123068673074], batch size: 70
+2022-12-14 02:28:45,756 INFO [train.py:421] (7/8) Epoch 11, batch 9600, loss[loss=2.168, over 4130.00 frames. , ppl: 8.736742902569695] tot_loss[loss=2.264, over 5491223.35 frames. , ppl: 9.617168800157874], batch size: 70
+2022-12-14 02:30:24,405 INFO [train.py:421] (7/8) Epoch 11, batch 9800, loss[loss=2.643, over 770.00 frames. , ppl: 14.048629660386869] tot_loss[loss=2.264, over 5465891.10 frames. , ppl: 9.623132678733086], batch size: 70
+2022-12-14 02:32:06,052 INFO [train.py:421] (7/8) Epoch 11, batch 10000, loss[loss=2.313, over 2100.00 frames. , ppl: 10.104715864402673] tot_loss[loss=2.264, over 5479057.67 frames. , ppl: 9.617397254934955], batch size: 70
+2022-12-14 02:32:06,053 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 02:32:06,813 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.263, over 211138.00 frames. , ppl: 9.607311196929732
+2022-12-14 02:33:49,150 INFO [train.py:421] (7/8) Epoch 11, batch 10200, loss[loss=2.473, over 1750.00 frames. , ppl: 11.85204325166001] tot_loss[loss=2.264, over 5478866.06 frames. , ppl: 9.625441625657128], batch size: 70
+2022-12-14 02:35:28,713 INFO [train.py:421] (7/8) Epoch 11, batch 10400, loss[loss=2.748, over 630.00 frames. , ppl: 15.613752368381979] tot_loss[loss=2.263, over 5524520.83 frames. , ppl: 9.614365395773032], batch size: 70
+2022-12-14 02:37:09,002 INFO [train.py:421] (7/8) Epoch 11, batch 10600, loss[loss=2.649, over 840.00 frames. , ppl: 14.134478804099938] tot_loss[loss=2.264, over 5500601.41 frames. , ppl: 9.618213622049279], batch size: 70
+2022-12-14 02:38:52,736 INFO [train.py:421] (7/8) Epoch 11, batch 10800, loss[loss=2.3, over 1820.00 frames. , ppl: 9.971319612606619] tot_loss[loss=2.263, over 5528388.31 frames. , ppl: 9.612279617673977], batch size: 70
+2022-12-14 02:40:34,255 INFO [train.py:421] (7/8) Epoch 11, batch 11000, loss[loss=2.349, over 3010.00 frames. , ppl: 10.47168713513855] tot_loss[loss=2.264, over 5511778.40 frames. , ppl: 9.62357931631764], batch size: 70
+2022-12-14 02:40:34,255 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 02:40:35,016 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.604206151775301
+2022-12-14 02:42:14,889 INFO [train.py:421] (7/8) Epoch 11, batch 11200, loss[loss=2.31, over 2170.00 frames. , ppl: 10.070345984494582] tot_loss[loss=2.265, over 5518615.55 frames. , ppl: 9.629478086022099], batch size: 70
+2022-12-14 02:43:54,232 INFO [train.py:421] (7/8) Epoch 11, batch 11400, loss[loss=2.232, over 5040.00 frames. , ppl: 9.322853631787119] tot_loss[loss=2.265, over 5502129.89 frames. , ppl: 9.628177064896517], batch size: 70
+2022-12-14 02:45:34,728 INFO [train.py:421] (7/8) Epoch 11, batch 11600, loss[loss=2.638, over 980.00 frames. , ppl: 13.990825950563828] tot_loss[loss=2.264, over 5525821.74 frames. , ppl: 9.621034050748746], batch size: 70
+2022-12-14 02:47:16,924 INFO [train.py:421] (7/8) Epoch 11, batch 11800, loss[loss=2.157, over 3150.00 frames. , ppl: 8.642750872299501] tot_loss[loss=2.264, over 5526118.38 frames. , ppl: 9.623463908000351], batch size: 70
+2022-12-14 02:48:54,560 INFO [train.py:421] (7/8) Epoch 11, batch 12000, loss[loss=2.402, over 1330.00 frames. , ppl: 11.046827666014696] tot_loss[loss=2.265, over 5508269.53 frames. , ppl: 9.632248775661552], batch size: 70
+2022-12-14 02:48:54,561 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 02:48:55,303 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.264, over 211138.00 frames. , ppl: 9.621384617486425
+2022-12-14 02:50:34,275 INFO [train.py:421] (7/8) Epoch 11, batch 12200, loss[loss=2.237, over 3570.00 frames. , ppl: 9.368075602132489] tot_loss[loss=2.265, over 5519669.07 frames. , ppl: 9.631396526380467], batch size: 70
+2022-12-14 02:52:10,841 INFO [train.py:421] (7/8) Epoch 11, batch 12400, loss[loss=2.225, over 2450.00 frames. , ppl: 9.251529996939086] tot_loss[loss=2.266, over 5489717.35 frames. , ppl: 9.642467841594108], batch size: 70
+2022-12-14 02:53:50,842 INFO [train.py:421] (7/8) Epoch 11, batch 12600, loss[loss=2.287, over 1960.00 frames. , ppl: 9.848642079961492] tot_loss[loss=2.266, over 5483824.62 frames. , ppl: 9.638920007384481], batch size: 70
+2022-12-14 02:55:29,958 INFO [train.py:421] (7/8) Epoch 11, batch 12800, loss[loss=2.185, over 3290.00 frames. , ppl: 8.8898144080657] tot_loss[loss=2.265, over 5509674.85 frames. , ppl: 9.635337854405126], batch size: 70
+2022-12-14 02:57:14,315 INFO [train.py:421] (7/8) Epoch 11, batch 13000, loss[loss=3.113, over 560.00 frames. , ppl: 22.48050893444905] tot_loss[loss=2.265, over 5535493.91 frames. , ppl: 9.63032592686794], batch size: 70
+2022-12-14 02:57:14,315 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 02:57:15,076 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.593847627631558
+2022-12-14 02:58:53,992 INFO [train.py:421] (7/8) Epoch 11, batch 13200, loss[loss=2.381, over 2030.00 frames. , ppl: 10.820967876754006] tot_loss[loss=2.265, over 5504273.32 frames. , ppl: 9.633802258033825], batch size: 70
+2022-12-14 03:00:37,503 INFO [train.py:421] (7/8) Epoch 11, batch 13400, loss[loss=2.39, over 2030.00 frames. , ppl: 10.909269478039016] tot_loss[loss=2.263, over 5549946.97 frames. , ppl: 9.613973746444074], batch size: 70
+2022-12-14 03:02:16,670 INFO [train.py:421] (7/8) Epoch 11, batch 13600, loss[loss=2.409, over 1190.00 frames. , ppl: 11.123343555253665] tot_loss[loss=2.263, over 5538376.61 frames. , ppl: 9.616184615408915], batch size: 70
+2022-12-14 03:03:48,775 INFO [train.py:421] (7/8) Epoch 11, batch 13800, loss[loss=2.179, over 3640.00 frames. , ppl: 8.8388646860065] tot_loss[loss=2.264, over 5525332.01 frames. , ppl: 9.61965681636239], batch size: 70
+2022-12-14 03:05:29,098 INFO [train.py:421] (7/8) Epoch 11, batch 14000, loss[loss=2.437, over 1610.00 frames. , ppl: 11.439808143187593] tot_loss[loss=2.263, over 5530264.82 frames. , ppl: 9.616676384068894], batch size: 70
+2022-12-14 03:05:29,098 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 03:05:29,843 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.264, over 211138.00 frames. , ppl: 9.617450808382541
+2022-12-14 03:07:07,757 INFO [train.py:421] (7/8) Epoch 11, batch 14200, loss[loss=2.459, over 910.00 frames. , ppl: 11.69751400979733] tot_loss[loss=2.263, over 5522966.30 frames. , ppl: 9.614948908166824], batch size: 70
+2022-12-14 03:08:46,879 INFO [train.py:421] (7/8) Epoch 11, batch 14400, loss[loss=2.281, over 1540.00 frames. , ppl: 9.782132706367781] tot_loss[loss=2.265, over 5501876.17 frames. , ppl: 9.629045435661638], batch size: 70
+2022-12-14 03:10:30,194 INFO [train.py:421] (7/8) Epoch 11, batch 14600, loss[loss=3.616, over 420.00 frames. , ppl: 37.180872361830005] tot_loss[loss=2.266, over 5458050.04 frames. , ppl: 9.639103797063665], batch size: 70
+2022-12-14 03:12:09,169 INFO [train.py:421] (7/8) Epoch 11, batch 14800, loss[loss=2.327, over 1960.00 frames. , ppl: 10.248343179541157] tot_loss[loss=2.266, over 5488115.75 frames. , ppl: 9.639618174910824], batch size: 70
+2022-12-14 03:13:48,750 INFO [train.py:421] (7/8) Epoch 11, batch 15000, loss[loss=2.888, over 700.00 frames. , ppl: 17.966285353976605] tot_loss[loss=2.267, over 5436067.07 frames. , ppl: 9.646224081958572], batch size: 70
+2022-12-14 03:13:48,751 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 03:13:49,508 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.603182730483441
+2022-12-14 03:15:28,744 INFO [train.py:421] (7/8) Epoch 11, batch 15200, loss[loss=2.695, over 700.00 frames. , ppl: 14.802312408582152] tot_loss[loss=2.268, over 5406557.60 frames. , ppl: 9.657590828538977], batch size: 70
+2022-12-14 03:17:08,552 INFO [train.py:421] (7/8) Epoch 11, batch 15400, loss[loss=2.979, over 560.00 frames. , ppl: 19.67387129983972] tot_loss[loss=2.268, over 5407478.15 frames. , ppl: 9.658078329807395], batch size: 70
+2022-12-14 03:18:44,460 INFO [train.py:421] (7/8) Epoch 11, batch 15600, loss[loss=2.345, over 910.00 frames. , ppl: 10.435816864488638] tot_loss[loss=2.268, over 5415957.36 frames. , ppl: 9.65549781057179], batch size: 70
+2022-12-14 03:20:25,763 INFO [train.py:421] (7/8) Epoch 11, batch 15800, loss[loss=2.188, over 3290.00 frames. , ppl: 8.91348503105408] tot_loss[loss=2.268, over 5394338.20 frames. , ppl: 9.66477388270996], batch size: 70
+2022-12-14 03:22:04,991 INFO [train.py:421] (7/8) Epoch 11, batch 16000, loss[loss=2.295, over 3430.00 frames. , ppl: 9.925125766924499] tot_loss[loss=2.268, over 5409851.77 frames. , ppl: 9.65837899415382], batch size: 70
+2022-12-14 03:22:04,992 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 03:22:05,752 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.263, over 211138.00 frames. , ppl: 9.608784453983127
+2022-12-14 03:23:48,824 INFO [train.py:421] (7/8) Epoch 11, batch 16200, loss[loss=2.309, over 1750.00 frames. , ppl: 10.06179316902455] tot_loss[loss=2.269, over 5360761.38 frames. , ppl: 9.670254351004557], batch size: 70
+2022-12-14 03:25:29,634 INFO [train.py:421] (7/8) Epoch 11, batch 16400, loss[loss=2.257, over 1470.00 frames. , ppl: 9.555655941648912] tot_loss[loss=2.269, over 5358441.21 frames. , ppl: 9.672576773709263], batch size: 70
+2022-12-14 03:27:08,122 INFO [train.py:421] (7/8) Epoch 11, batch 16600, loss[loss=2.178, over 4270.00 frames. , ppl: 8.832546410932808] tot_loss[loss=2.269, over 5364586.16 frames. , ppl: 9.669276583468536], batch size: 70
+2022-12-14 03:28:48,331 INFO [train.py:421] (7/8) Epoch 11, batch 16800, loss[loss=2.385, over 2660.00 frames. , ppl: 10.863505127113543] tot_loss[loss=2.271, over 5335608.08 frames. , ppl: 9.68528209278916], batch size: 70
+2022-12-14 03:30:30,498 INFO [train.py:421] (7/8) Epoch 11, batch 17000, loss[loss=2.552, over 1470.00 frames. , ppl: 12.838130006088205] tot_loss[loss=2.269, over 5365833.87 frames. , ppl: 9.67295210931279], batch size: 70
+2022-12-14 03:30:30,498 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 03:30:31,251 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.599325980992132
+2022-12-14 03:32:09,722 INFO [train.py:421] (7/8) Epoch 11, batch 17200, loss[loss=2.25, over 5390.00 frames. , ppl: 9.485628586180388] tot_loss[loss=2.27, over 5340979.30 frames. , ppl: 9.680137623350012], batch size: 70
+2022-12-14 03:33:49,129 INFO [train.py:421] (7/8) Epoch 11, batch 17400, loss[loss=2.302, over 1820.00 frames. , ppl: 9.991446471704034] tot_loss[loss=2.27, over 5367298.78 frames. , ppl: 9.677221022311347], batch size: 70
+2022-12-14 03:35:31,005 INFO [train.py:421] (7/8) Epoch 11, batch 17600, loss[loss=2.148, over 8120.00 frames. , ppl: 8.57129627948047] tot_loss[loss=2.269, over 5392084.10 frames. , ppl: 9.667586161535473], batch size: 70
+2022-12-14 03:37:07,957 INFO [train.py:421] (7/8) Epoch 11, batch 17800, loss[loss=2.399, over 1750.00 frames. , ppl: 11.013977836893064] tot_loss[loss=2.269, over 5398189.30 frames. , ppl: 9.667069429616896], batch size: 70
+2022-12-14 03:38:46,523 INFO [train.py:421] (7/8) Epoch 11, batch 18000, loss[loss=2.528, over 1050.00 frames. , ppl: 12.532426212428419] tot_loss[loss=2.268, over 5415502.97 frames. , ppl: 9.662135062120816], batch size: 70
+2022-12-14 03:38:46,524 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 03:38:47,290 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.263, over 211138.00 frames. , ppl: 9.611424367463018
+2022-12-14 03:40:27,912 INFO [train.py:421] (7/8) Epoch 11, batch 18200, loss[loss=2.395, over 1820.00 frames. , ppl: 10.972538691342578] tot_loss[loss=2.268, over 5432481.75 frames. , ppl: 9.664140773740113], batch size: 70
+2022-12-14 03:42:05,025 INFO [train.py:421] (7/8) Epoch 11, batch 18400, loss[loss=2.264, over 2660.00 frames. , ppl: 9.624791832181474] tot_loss[loss=2.27, over 5393990.46 frames. , ppl: 9.67499583640231], batch size: 70
+2022-12-14 03:43:44,910 INFO [train.py:421] (7/8) Epoch 11, batch 18600, loss[loss=2.442, over 1400.00 frames. , ppl: 11.492161720372836] tot_loss[loss=2.27, over 5377382.91 frames. , ppl: 9.68065515761119], batch size: 70
+2022-12-14 03:45:24,656 INFO [train.py:421] (7/8) Epoch 11, batch 18800, loss[loss=2.152, over 5740.00 frames. , ppl: 8.6033310382622] tot_loss[loss=2.269, over 5407146.86 frames. , ppl: 9.671326530323691], batch size: 70
+2022-12-14 03:47:03,770 INFO [train.py:421] (7/8) Epoch 11, batch 19000, loss[loss=2.512, over 1050.00 frames. , ppl: 12.327349850569345] tot_loss[loss=2.269, over 5411433.78 frames. , ppl: 9.671078181155785], batch size: 70
+2022-12-14 03:47:03,771 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 03:47:04,530 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.604402319978165
+2022-12-14 03:48:43,946 INFO [train.py:421] (7/8) Epoch 11, batch 19200, loss[loss=2.304, over 2170.00 frames. , ppl: 10.010440338595291] tot_loss[loss=2.269, over 5404999.05 frames. , ppl: 9.669182467704925], batch size: 70
+2022-12-14 03:50:21,981 INFO [train.py:421] (7/8) Epoch 11, batch 19400, loss[loss=2.256, over 3360.00 frames. , ppl: 9.549495517961411] tot_loss[loss=2.268, over 5435250.85 frames. , ppl: 9.659844364255648], batch size: 70
+2022-12-14 03:52:05,992 INFO [train.py:421] (7/8) Epoch 11, batch 19600, loss[loss=2.311, over 1890.00 frames. , ppl: 10.083829568999041] tot_loss[loss=2.268, over 5424822.58 frames. , ppl: 9.662097350331212], batch size: 70
+2022-12-14 03:53:44,118 INFO [train.py:421] (7/8) Epoch 11, batch 19800, loss[loss=2.587, over 770.00 frames. , ppl: 13.296122020171536] tot_loss[loss=2.269, over 5420277.08 frames. , ppl: 9.665134546688444], batch size: 70
+2022-12-14 03:55:25,013 INFO [train.py:421] (7/8) Epoch 11, batch 20000, loss[loss=2.849, over 700.00 frames. , ppl: 17.272305016991087] tot_loss[loss=2.269, over 5411829.39 frames. , ppl: 9.670180811955928], batch size: 70
+2022-12-14 03:55:25,013 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 03:55:25,775 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.263, over 211138.00 frames. , ppl: 9.61202043965363
+2022-12-14 03:57:05,992 INFO [train.py:421] (7/8) Epoch 11, batch 20200, loss[loss=2.272, over 2030.00 frames. , ppl: 9.702319348093587] tot_loss[loss=2.268, over 5430080.96 frames. , ppl: 9.662442709457851], batch size: 70
+2022-12-14 03:58:46,599 INFO [train.py:421] (7/8) Epoch 11, batch 20400, loss[loss=2.348, over 1680.00 frames. , ppl: 10.468976692680767] tot_loss[loss=2.268, over 5421817.71 frames. , ppl: 9.66416734785308], batch size: 70
+2022-12-14 04:00:28,916 INFO [train.py:421] (7/8) Epoch 11, batch 20600, loss[loss=2.078, over 9030.00 frames. , ppl: 7.985349038828998] tot_loss[loss=2.267, over 5468911.01 frames. , ppl: 9.647018614002887], batch size: 70
+2022-12-14 04:02:14,438 INFO [train.py:421] (7/8) Epoch 11, batch 20800, loss[loss=2.311, over 3010.00 frames. , ppl: 10.081312514860517] tot_loss[loss=2.266, over 5485173.43 frames. , ppl: 9.636542146795378], batch size: 70
+2022-12-14 04:03:51,808 INFO [train.py:421] (7/8) Epoch 11, batch 21000, loss[loss=2.266, over 2240.00 frames. , ppl: 9.638557730156503] tot_loss[loss=2.265, over 5514909.08 frames. , ppl: 9.627425969503728], batch size: 70
+2022-12-14 04:03:51,809 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 04:03:52,554 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.59960729794989
+2022-12-14 04:05:34,809 INFO [train.py:421] (7/8) Epoch 11, batch 21200, loss[loss=2.471, over 1120.00 frames. , ppl: 11.828400394698638] tot_loss[loss=2.264, over 5522041.59 frames. , ppl: 9.623367361724368], batch size: 70
+2022-12-14 04:07:12,358 INFO [train.py:421] (7/8) Epoch 11, batch 21400, loss[loss=2.307, over 1190.00 frames. , ppl: 10.048254090334412] tot_loss[loss=2.264, over 5525673.81 frames. , ppl: 9.618675192207126], batch size: 70
+2022-12-14 04:08:53,877 INFO [train.py:421] (7/8) Epoch 11, batch 21600, loss[loss=2.415, over 840.00 frames. , ppl: 11.185460025023255] tot_loss[loss=2.263, over 5564687.09 frames. , ppl: 9.610586021831681], batch size: 70
+2022-12-14 04:10:28,569 INFO [train.py:421] (7/8) Epoch 11, batch 21800, loss[loss=2.243, over 3150.00 frames. , ppl: 9.417316950349168] tot_loss[loss=2.263, over 5579252.53 frames. , ppl: 9.60905529735287], batch size: 70
+2022-12-14 04:12:08,370 INFO [train.py:421] (7/8) Epoch 11, batch 22000, loss[loss=4.108, over 350.00 frames. , ppl: 60.82005418173159] tot_loss[loss=2.262, over 5578131.53 frames. , ppl: 9.606753232409135], batch size: 70
+2022-12-14 04:12:08,371 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 04:12:09,131 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.59981047643547
+2022-12-14 04:13:46,451 INFO [train.py:421] (7/8) Epoch 11, batch 22200, loss[loss=2.23, over 3220.00 frames. , ppl: 9.301603930930852] tot_loss[loss=2.262, over 5576817.50 frames. , ppl: 9.605468818820524], batch size: 70
+2022-12-14 04:15:26,608 INFO [train.py:421] (7/8) Epoch 11, batch 22400, loss[loss=2.621, over 1120.00 frames. , ppl: 13.749939975781697] tot_loss[loss=2.262, over 5580340.15 frames. , ppl: 9.602061080254577], batch size: 70
+2022-12-14 04:17:04,241 INFO [train.py:421] (7/8) Epoch 11, batch 22600, loss[loss=2.802, over 630.00 frames. , ppl: 16.481391376361486] tot_loss[loss=2.262, over 5572746.76 frames. , ppl: 9.599925623639795], batch size: 70
+2022-12-14 04:18:46,596 INFO [train.py:421] (7/8) Epoch 11, batch 22800, loss[loss=2.195, over 3920.00 frames. , ppl: 8.979415843836623] tot_loss[loss=2.262, over 5540040.38 frames. , ppl: 9.606942141561207], batch size: 70
+2022-12-14 04:20:26,434 INFO [train.py:421] (7/8) Epoch 11, batch 23000, loss[loss=2.185, over 6160.00 frames. , ppl: 8.891037009050352] tot_loss[loss=2.262, over 5568815.60 frames. , ppl: 9.600613222977788], batch size: 70
+2022-12-14 04:20:26,435 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 04:20:27,166 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.589605722035854
+2022-12-14 04:22:05,160 INFO [train.py:421] (7/8) Epoch 11, batch 23200, loss[loss=2.412, over 2590.00 frames. , ppl: 11.153164559284525] tot_loss[loss=2.262, over 5565515.40 frames. , ppl: 9.597551783377725], batch size: 70
+2022-12-14 04:23:43,567 INFO [train.py:421] (7/8) Epoch 11, batch 23400, loss[loss=2.313, over 2800.00 frames. , ppl: 10.103868318976257] tot_loss[loss=2.264, over 5505877.70 frames. , ppl: 9.620281919150264], batch size: 70
+2022-12-14 04:25:27,497 INFO [train.py:421] (7/8) Epoch 11, batch 23600, loss[loss=2.178, over 8330.00 frames. , ppl: 8.82687014837029] tot_loss[loss=2.265, over 5481549.47 frames. , ppl: 9.629387685671364], batch size: 70
+2022-12-14 04:27:09,129 INFO [train.py:421] (7/8) Epoch 11, batch 23800, loss[loss=2.231, over 3290.00 frames. , ppl: 9.304938972452682] tot_loss[loss=2.264, over 5489391.56 frames. , ppl: 9.62041872850653], batch size: 70
+2022-12-14 04:28:49,641 INFO [train.py:421] (7/8) Epoch 11, batch 24000, loss[loss=2.443, over 1330.00 frames. , ppl: 11.50283098036137] tot_loss[loss=2.263, over 5511932.64 frames. , ppl: 9.614774994196429], batch size: 70
+2022-12-14 04:28:49,641 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 04:28:50,387 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.589086260144834
+2022-12-14 04:30:27,488 INFO [train.py:421] (7/8) Epoch 11, batch 24200, loss[loss=2.205, over 4130.00 frames. , ppl: 9.072807139701291] tot_loss[loss=2.263, over 5508861.09 frames. , ppl: 9.61483418335859], batch size: 70
+2022-12-14 04:32:06,790 INFO [train.py:421] (7/8) Epoch 11, batch 24400, loss[loss=2.885, over 630.00 frames. , ppl: 17.90606686509623] tot_loss[loss=2.263, over 5517088.46 frames. , ppl: 9.613217655363984], batch size: 70
+2022-12-14 04:33:49,456 INFO [train.py:421] (7/8) Epoch 11, batch 24600, loss[loss=2.525, over 980.00 frames. , ppl: 12.491729245909859] tot_loss[loss=2.263, over 5531654.91 frames. , ppl: 9.615546423415331], batch size: 70
+2022-12-14 04:35:31,657 INFO [train.py:421] (7/8) Epoch 11, batch 24800, loss[loss=4.003, over 350.00 frames. , ppl: 54.771844177237114] tot_loss[loss=2.262, over 5569603.04 frames. , ppl: 9.60623180475092], batch size: 70
+2022-12-14 04:37:15,800 INFO [train.py:421] (7/8) Epoch 11, batch 25000, loss[loss=2.404, over 1610.00 frames. , ppl: 11.071422467982595] tot_loss[loss=2.261, over 5620132.84 frames. , ppl: 9.593766518364665], batch size: 70
+2022-12-14 04:37:15,801 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 04:37:16,563 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.606207824169385
+2022-12-14 04:38:53,653 INFO [train.py:421] (7/8) Epoch 11, batch 25200, loss[loss=2.245, over 4830.00 frames. , ppl: 9.442881191361534] tot_loss[loss=2.261, over 5621432.17 frames. , ppl: 9.590423422998096], batch size: 70
+2022-12-14 04:40:34,681 INFO [train.py:421] (7/8) Epoch 11, batch 25400, loss[loss=2.45, over 1330.00 frames. , ppl: 11.586228214046027] tot_loss[loss=2.262, over 5609311.89 frames. , ppl: 9.598169427862155], batch size: 70
+2022-12-14 04:42:13,997 INFO [train.py:421] (7/8) Epoch 11, batch 25600, loss[loss=2.337, over 1680.00 frames. , ppl: 10.354118091843526] tot_loss[loss=2.26, over 5638697.55 frames. , ppl: 9.586716848394747], batch size: 70
+2022-12-14 04:43:56,172 INFO [train.py:421] (7/8) Epoch 11, batch 25800, loss[loss=2.173, over 4690.00 frames. , ppl: 8.782032642634123] tot_loss[loss=2.26, over 5653419.01 frames. , ppl: 9.58360453459549], batch size: 70
+2022-12-14 04:45:33,981 INFO [train.py:421] (7/8) Epoch 11, batch 26000, loss[loss=2.276, over 2800.00 frames. , ppl: 9.738486624654573] tot_loss[loss=2.261, over 5618307.97 frames. , ppl: 9.596657888122774], batch size: 70
+2022-12-14 04:45:33,981 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 04:45:34,741 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.263, over 211138.00 frames. , ppl: 9.612918174211162
+2022-12-14 04:47:14,143 INFO [train.py:421] (7/8) Epoch 11, batch 26200, loss[loss=2.957, over 560.00 frames. , ppl: 19.248929414112617] tot_loss[loss=2.263, over 5576722.17 frames. , ppl: 9.613613279071933], batch size: 70
+2022-12-14 04:48:55,148 INFO [train.py:421] (7/8) Epoch 11, batch 26400, loss[loss=2.233, over 5250.00 frames. , ppl: 9.324076151464158] tot_loss[loss=2.263, over 5580332.83 frames. , ppl: 9.608780182731158], batch size: 70
+2022-12-14 04:50:33,171 INFO [train.py:421] (7/8) Epoch 11, batch 26600, loss[loss=2.222, over 3780.00 frames. , ppl: 9.229023121643108] tot_loss[loss=2.263, over 5562038.58 frames. , ppl: 9.613145467152481], batch size: 70
+2022-12-14 04:52:12,405 INFO [train.py:421] (7/8) Epoch 11, batch 26800, loss[loss=4.101, over 350.00 frames. , ppl: 60.41740370461545] tot_loss[loss=2.263, over 5560013.42 frames. , ppl: 9.615057646234991], batch size: 70
+2022-12-14 04:53:51,714 INFO [train.py:421] (7/8) Epoch 11, batch 27000, loss[loss=2.17, over 4620.00 frames. , ppl: 8.755939496448896] tot_loss[loss=2.263, over 5587743.45 frames. , ppl: 9.608564484518189], batch size: 70
+2022-12-14 04:53:51,714 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 04:53:52,445 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.594008084573185
+2022-12-14 04:55:35,157 INFO [train.py:421] (7/8) Epoch 11, batch 27200, loss[loss=2.246, over 5180.00 frames. , ppl: 9.450172967369726] tot_loss[loss=2.264, over 5543675.07 frames. , ppl: 9.621744058274263], batch size: 70
+2022-12-14 04:57:14,464 INFO [train.py:421] (7/8) Epoch 11, batch 27400, loss[loss=2.854, over 630.00 frames. , ppl: 17.36258506771503] tot_loss[loss=2.266, over 5503845.16 frames. , ppl: 9.639166142704001], batch size: 70
+2022-12-14 04:58:50,882 INFO [train.py:421] (7/8) Epoch 11, batch 27600, loss[loss=2.202, over 5040.00 frames. , ppl: 9.044485357187718] tot_loss[loss=2.266, over 5504944.07 frames. , ppl: 9.641131630953941], batch size: 70
+2022-12-14 05:00:29,827 INFO [train.py:421] (7/8) Epoch 11, batch 27800, loss[loss=2.174, over 4060.00 frames. , ppl: 8.795328025066377] tot_loss[loss=2.268, over 5450566.86 frames. , ppl: 9.661079797370371], batch size: 70
+2022-12-14 05:02:14,477 INFO [train.py:421] (7/8) Epoch 11, batch 28000, loss[loss=2.417, over 1400.00 frames. , ppl: 11.217623283685029] tot_loss[loss=2.27, over 5417968.97 frames. , ppl: 9.676506183003761], batch size: 70
+2022-12-14 05:02:14,477 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 05:02:15,236 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.594497991840212
+2022-12-14 05:04:00,710 INFO [train.py:421] (7/8) Epoch 11, batch 28200, loss[loss=2.182, over 7630.00 frames. , ppl: 8.865634707678717] tot_loss[loss=2.268, over 5462012.85 frames. , ppl: 9.661879597598098], batch size: 70
+2022-12-14 05:05:42,754 INFO [train.py:421] (7/8) Epoch 11, batch 28400, loss[loss=2.289, over 1890.00 frames. , ppl: 9.865674070125877] tot_loss[loss=2.267, over 5504732.29 frames. , ppl: 9.650085484033733], batch size: 70
+2022-12-14 05:07:20,250 INFO [train.py:421] (7/8) Epoch 11, batch 28600, loss[loss=2.279, over 1610.00 frames. , ppl: 9.768105026402278] tot_loss[loss=2.267, over 5500410.20 frames. , ppl: 9.650584277786752], batch size: 70
+2022-12-14 05:09:04,635 INFO [train.py:421] (7/8) Epoch 11, batch 28800, loss[loss=2.348, over 1680.00 frames. , ppl: 10.46975262041113] tot_loss[loss=2.267, over 5491255.50 frames. , ppl: 9.654501510469673], batch size: 70
+2022-12-14 05:10:45,351 INFO [train.py:421] (7/8) Epoch 11, batch 29000, loss[loss=2.549, over 1050.00 frames. , ppl: 12.795682897481706] tot_loss[loss=2.267, over 5501936.98 frames. , ppl: 9.649873216948771], batch size: 70
+2022-12-14 05:10:45,351 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 05:10:46,097 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.587935312328966
+2022-12-14 05:12:24,279 INFO [train.py:421] (7/8) Epoch 11, batch 29200, loss[loss=2.233, over 2240.00 frames. , ppl: 9.332354812023894] tot_loss[loss=2.268, over 5474974.36 frames. , ppl: 9.656523202105634], batch size: 70
+2022-12-14 05:14:04,311 INFO [train.py:421] (7/8) Epoch 11, batch 29400, loss[loss=2.334, over 3220.00 frames. , ppl: 10.315185218404324] tot_loss[loss=2.268, over 5449856.46 frames. , ppl: 9.66051269393387], batch size: 70
+2022-12-14 05:15:46,582 INFO [train.py:421] (7/8) Epoch 11, batch 29600, loss[loss=2.2, over 5810.00 frames. , ppl: 9.020994472405128] tot_loss[loss=2.266, over 5485379.56 frames. , ppl: 9.644133662958303], batch size: 70
+2022-12-14 05:17:28,206 INFO [train.py:421] (7/8) Epoch 11, batch 29800, loss[loss=2.378, over 1260.00 frames. , ppl: 10.779527485635667] tot_loss[loss=2.265, over 5517039.70 frames. , ppl: 9.635603746451697], batch size: 70
+2022-12-14 05:19:07,020 INFO [train.py:421] (7/8) Epoch 11, batch 30000, loss[loss=2.754, over 910.00 frames. , ppl: 15.701968045147376] tot_loss[loss=2.266, over 5491152.20 frames. , ppl: 9.64204261830618], batch size: 70
+2022-12-14 05:19:07,021 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 05:19:07,779 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.263, over 211138.00 frames. , ppl: 9.613103137864265
+2022-12-14 05:20:48,056 INFO [train.py:421] (7/8) Epoch 11, batch 30200, loss[loss=2.189, over 6720.00 frames. , ppl: 8.927289142586902] tot_loss[loss=2.267, over 5471792.14 frames. , ppl: 9.646370366882994], batch size: 70
+2022-12-14 05:22:30,470 INFO [train.py:421] (7/8) Epoch 11, batch 30400, loss[loss=2.259, over 3360.00 frames. , ppl: 9.5753898934982] tot_loss[loss=2.267, over 5450050.57 frames. , ppl: 9.651143843913072], batch size: 70
+2022-12-14 05:24:12,369 INFO [train.py:421] (7/8) Epoch 11, batch 30600, loss[loss=2.104, over 6440.00 frames. , ppl: 8.20053852021328] tot_loss[loss=2.267, over 5435732.80 frames. , ppl: 9.651774861989228], batch size: 70
+2022-12-14 05:25:49,459 INFO [train.py:421] (7/8) Epoch 11, batch 30800, loss[loss=2.55, over 980.00 frames. , ppl: 12.807186737107576] tot_loss[loss=2.267, over 5446396.91 frames. , ppl: 9.647060718844966], batch size: 70
+2022-12-14 05:27:28,455 INFO [train.py:421] (7/8) Epoch 11, batch 31000, loss[loss=2.247, over 1750.00 frames. , ppl: 9.462691570968165] tot_loss[loss=2.266, over 5458842.48 frames. , ppl: 9.643002951882876], batch size: 70
+2022-12-14 05:27:28,455 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 05:27:29,214 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.263, over 211138.00 frames. , ppl: 9.613066144848931
+2022-12-14 05:29:07,428 INFO [train.py:421] (7/8) Epoch 11, batch 31200, loss[loss=2.471, over 1260.00 frames. , ppl: 11.829499411446388] tot_loss[loss=2.266, over 5519240.29 frames. , ppl: 9.636393520178594], batch size: 70
+2022-12-14 05:30:46,537 INFO [train.py:421] (7/8) Epoch 11, batch 31400, loss[loss=2.436, over 1470.00 frames. , ppl: 11.426013683124422] tot_loss[loss=2.265, over 5537235.20 frames. , ppl: 9.630108667461467], batch size: 70
+2022-12-14 05:32:28,444 INFO [train.py:421] (7/8) Epoch 11, batch 31600, loss[loss=2.457, over 2450.00 frames. , ppl: 11.673254710710633] tot_loss[loss=2.265, over 5540852.88 frames. , ppl: 9.630236881872616], batch size: 70
+2022-12-14 05:34:09,690 INFO [train.py:421] (7/8) Epoch 11, batch 31800, loss[loss=2.223, over 1680.00 frames. , ppl: 9.23138300291991] tot_loss[loss=2.263, over 5563030.30 frames. , ppl: 9.616161002787216], batch size: 70
+2022-12-14 05:35:44,348 INFO [train.py:421] (7/8) Epoch 11, batch 32000, loss[loss=2.186, over 4060.00 frames. , ppl: 8.89649625499742] tot_loss[loss=2.265, over 5541151.09 frames. , ppl: 9.629231968375105], batch size: 70
+2022-12-14 05:35:44,349 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 05:35:45,109 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.604530257921299
+2022-12-14 05:37:24,335 INFO [train.py:421] (7/8) Epoch 11, batch 32200, loss[loss=2.188, over 5040.00 frames. , ppl: 8.920309643731208] tot_loss[loss=2.266, over 5494841.31 frames. , ppl: 9.64390864388014], batch size: 70
+2022-12-14 05:39:05,742 INFO [train.py:421] (7/8) Epoch 11, batch 32400, loss[loss=2.657, over 770.00 frames. , ppl: 14.248512495217488] tot_loss[loss=2.265, over 5517813.28 frames. , ppl: 9.6332964487098], batch size: 70
+2022-12-14 05:40:47,685 INFO [train.py:421] (7/8) Epoch 11, batch 32600, loss[loss=2.172, over 4200.00 frames. , ppl: 8.776398476825062] tot_loss[loss=2.264, over 5569550.58 frames. , ppl: 9.620766323993356], batch size: 70
+2022-12-14 05:42:26,788 INFO [train.py:421] (7/8) Epoch 11, batch 32800, loss[loss=2.471, over 1050.00 frames. , ppl: 11.833920805111381] tot_loss[loss=2.263, over 5572045.27 frames. , ppl: 9.616685992496441], batch size: 70
+2022-12-14 05:44:07,639 INFO [train.py:421] (7/8) Epoch 11, batch 33000, loss[loss=2.715, over 630.00 frames. , ppl: 15.106801162546216] tot_loss[loss=2.264, over 5564858.90 frames. , ppl: 9.625515234712214], batch size: 70
+2022-12-14 05:44:07,640 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 05:44:08,396 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.259, over 211138.00 frames. , ppl: 9.5747582284789
+2022-12-14 05:45:47,675 INFO [train.py:421] (7/8) Epoch 11, batch 33200, loss[loss=2.297, over 1750.00 frames. , ppl: 9.94099237971509] tot_loss[loss=2.266, over 5512126.68 frames. , ppl: 9.638865367344222], batch size: 70
+2022-12-14 05:47:26,447 INFO [train.py:421] (7/8) Epoch 11, batch 33400, loss[loss=2.51, over 910.00 frames. , ppl: 12.301373152650985] tot_loss[loss=2.266, over 5523991.53 frames. , ppl: 9.638497012882382], batch size: 70
+2022-12-14 05:49:07,563 INFO [train.py:421] (7/8) Epoch 11, batch 33600, loss[loss=2.655, over 700.00 frames. , ppl: 14.219871897737718] tot_loss[loss=2.264, over 5554897.52 frames. , ppl: 9.626287788917516], batch size: 70
+2022-12-14 05:50:49,688 INFO [train.py:421] (7/8) Epoch 11, batch 33800, loss[loss=2.318, over 2730.00 frames. , ppl: 10.151361306500622] tot_loss[loss=2.266, over 5529687.21 frames. , ppl: 9.63621832882682], batch size: 70
+2022-12-14 05:52:29,251 INFO [train.py:421] (7/8) Epoch 11, batch 34000, loss[loss=2.229, over 4620.00 frames. , ppl: 9.292637967225406] tot_loss[loss=2.265, over 5529252.16 frames. , ppl: 9.633415997208758], batch size: 70
+2022-12-14 05:52:29,251 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 05:52:30,011 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.580360386976093
+2022-12-14 05:54:12,839 INFO [train.py:421] (7/8) Epoch 11, batch 34200, loss[loss=2.243, over 2870.00 frames. , ppl: 9.41912119459241] tot_loss[loss=2.265, over 5513672.21 frames. , ppl: 9.628480026277188], batch size: 70
+2022-12-14 05:55:56,811 INFO [train.py:421] (7/8) Epoch 11, batch 34400, loss[loss=2.136, over 7000.00 frames. , ppl: 8.464744882686656] tot_loss[loss=2.264, over 5544093.16 frames. , ppl: 9.620490938746428], batch size: 70
+2022-12-14 05:57:35,021 INFO [train.py:421] (7/8) Epoch 11, batch 34600, loss[loss=2.139, over 2870.00 frames. , ppl: 8.488151029659912] tot_loss[loss=2.264, over 5534836.20 frames. , ppl: 9.619765671427377], batch size: 70
+2022-12-14 05:59:12,270 INFO [train.py:421] (7/8) Epoch 11, batch 34800, loss[loss=2.373, over 1610.00 frames. , ppl: 10.733143824961823] tot_loss[loss=2.264, over 5515244.51 frames. , ppl: 9.625884741781702], batch size: 70
+2022-12-14 06:00:51,154 INFO [train.py:421] (7/8) Epoch 11, batch 35000, loss[loss=2.207, over 2240.00 frames. , ppl: 9.085362510079088] tot_loss[loss=2.264, over 5530133.26 frames. , ppl: 9.624369116859246], batch size: 70
+2022-12-14 06:00:51,155 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 06:00:51,940 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.259, over 211138.00 frames. , ppl: 9.571281208986392
+2022-12-14 06:02:35,355 INFO [train.py:421] (7/8) Epoch 11, batch 35200, loss[loss=2.54, over 910.00 frames. , ppl: 12.677397422736988] tot_loss[loss=2.265, over 5533472.89 frames. , ppl: 9.627345983610239], batch size: 70
+2022-12-14 06:04:14,599 INFO [train.py:421] (7/8) Epoch 11, batch 35400, loss[loss=2.42, over 1610.00 frames. , ppl: 11.250919807407069] tot_loss[loss=2.266, over 5486154.44 frames. , ppl: 9.638899138928522], batch size: 70
+2022-12-14 06:05:56,230 INFO [train.py:421] (7/8) Epoch 11, batch 35600, loss[loss=2.592, over 980.00 frames. , ppl: 13.363096442118577] tot_loss[loss=2.266, over 5496627.81 frames. , ppl: 9.63804538378104], batch size: 70
+2022-12-14 06:07:32,112 INFO [train.py:421] (7/8) Epoch 11, batch 35800, loss[loss=2.247, over 2450.00 frames. , ppl: 9.456150137380028] tot_loss[loss=2.267, over 5443974.36 frames. , ppl: 9.651967844254468], batch size: 70
+2022-12-14 06:09:12,203 INFO [train.py:421] (7/8) Epoch 11, batch 36000, loss[loss=2.209, over 2940.00 frames. , ppl: 9.104584711342662] tot_loss[loss=2.267, over 5450181.25 frames. , ppl: 9.653394517670142], batch size: 70
+2022-12-14 06:09:12,203 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 06:09:12,963 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.593320836541546
+2022-12-14 06:10:52,350 INFO [train.py:421] (7/8) Epoch 11, batch 36200, loss[loss=2.305, over 2170.00 frames. , ppl: 10.01970687709468] tot_loss[loss=2.268, over 5429986.19 frames. , ppl: 9.660180995809203], batch size: 70
+2022-12-14 06:12:34,283 INFO [train.py:421] (7/8) Epoch 11, batch 36400, loss[loss=3.307, over 490.00 frames. , ppl: 27.300083153082543] tot_loss[loss=2.268, over 5448599.31 frames. , ppl: 9.659436019867488], batch size: 70
+2022-12-14 06:14:15,796 INFO [train.py:421] (7/8) Epoch 11, batch 36600, loss[loss=2.419, over 1960.00 frames. , ppl: 11.236562957469715] tot_loss[loss=2.269, over 5407888.56 frames. , ppl: 9.67285390554196], batch size: 70
+2022-12-14 06:15:56,235 INFO [train.py:421] (7/8) Epoch 11, batch 36800, loss[loss=2.779, over 700.00 frames. , ppl: 16.10184405506865] tot_loss[loss=2.27, over 5378714.35 frames. , ppl: 9.678469052916673], batch size: 70
+2022-12-14 06:17:38,558 INFO [train.py:421] (7/8) Epoch 11, batch 37000, loss[loss=2.52, over 1120.00 frames. , ppl: 12.433099117327927] tot_loss[loss=2.271, over 5374207.70 frames. , ppl: 9.684387248780569], batch size: 70
+2022-12-14 06:17:38,559 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 06:17:39,307 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.585279151337225
+2022-12-14 06:19:19,620 INFO [train.py:421] (7/8) Epoch 11, batch 37200, loss[loss=2.296, over 2940.00 frames. , ppl: 9.939066287727561] tot_loss[loss=2.271, over 5389931.23 frames. , ppl: 9.68620302259293], batch size: 70
+2022-12-14 06:21:00,622 INFO [train.py:421] (7/8) Epoch 11, batch 37400, loss[loss=2.447, over 1120.00 frames. , ppl: 11.556642656403266] tot_loss[loss=2.269, over 5435278.40 frames. , ppl: 9.673049792361084], batch size: 70
+2022-12-14 06:22:44,801 INFO [train.py:421] (7/8) Epoch 11, batch 37600, loss[loss=2.239, over 3430.00 frames. , ppl: 9.385010118343445] tot_loss[loss=2.268, over 5491799.09 frames. , ppl: 9.657348761870253], batch size: 70
+2022-12-14 06:24:22,293 INFO [train.py:421] (7/8) Epoch 11, batch 37800, loss[loss=2.161, over 3990.00 frames. , ppl: 8.68286142613121] tot_loss[loss=2.268, over 5498001.27 frames. , ppl: 9.661687544213283], batch size: 70
+2022-12-14 06:26:03,855 INFO [train.py:421] (7/8) Epoch 11, batch 38000, loss[loss=2.179, over 6300.00 frames. , ppl: 8.835126547224682] tot_loss[loss=2.268, over 5493819.77 frames. , ppl: 9.65703150635327], batch size: 70
+2022-12-14 06:26:03,856 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 06:26:04,620 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.584332929905047
+2022-12-14 06:27:46,875 INFO [train.py:421] (7/8) Epoch 11, batch 38200, loss[loss=2.343, over 3010.00 frames. , ppl: 10.413915846892172] tot_loss[loss=2.266, over 5531202.34 frames. , ppl: 9.643358498462975], batch size: 70
+2022-12-14 06:29:24,551 INFO [train.py:421] (7/8) Epoch 11, batch 38400, loss[loss=2.266, over 2730.00 frames. , ppl: 9.636964951092414] tot_loss[loss=2.268, over 5466619.19 frames. , ppl: 9.662312985614392], batch size: 70
+2022-12-14 06:31:03,606 INFO [train.py:421] (7/8) Epoch 11, batch 38600, loss[loss=2.107, over 7070.00 frames. , ppl: 8.219424127875362] tot_loss[loss=2.268, over 5468461.25 frames. , ppl: 9.664849934282937], batch size: 70
+2022-12-14 06:32:43,279 INFO [train.py:421] (7/8) Epoch 11, batch 38800, loss[loss=2.736, over 770.00 frames. , ppl: 15.426324351843865] tot_loss[loss=2.268, over 5491127.25 frames. , ppl: 9.655406871706615], batch size: 70
+2022-12-14 06:34:25,406 INFO [train.py:421] (7/8) Epoch 11, batch 39000, loss[loss=2.255, over 4900.00 frames. , ppl: 9.537946594858138] tot_loss[loss=2.267, over 5478314.32 frames. , ppl: 9.654218678834141], batch size: 70
+2022-12-14 06:34:25,406 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 06:34:26,137 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.58167067609052
+2022-12-14 06:36:07,569 INFO [train.py:421] (7/8) Epoch 11, batch 39200, loss[loss=2.186, over 10920.00 frames. , ppl: 8.901922934135818] tot_loss[loss=2.266, over 5532943.08 frames. , ppl: 9.639452221069735], batch size: 70
+2022-12-14 06:37:47,056 INFO [train.py:421] (7/8) Epoch 11, batch 39400, loss[loss=2.195, over 4620.00 frames. , ppl: 8.98155465119872] tot_loss[loss=2.266, over 5541321.55 frames. , ppl: 9.641311492186906], batch size: 70
+2022-12-14 06:39:24,956 INFO [train.py:421] (7/8) Epoch 11, batch 39600, loss[loss=2.194, over 5530.00 frames. , ppl: 8.9679816862724] tot_loss[loss=2.265, over 5567270.25 frames. , ppl: 9.633491316335647], batch size: 70
+2022-12-14 06:41:07,682 INFO [train.py:421] (7/8) Epoch 11, batch 39800, loss[loss=2.393, over 2030.00 frames. , ppl: 10.941182349700666] tot_loss[loss=2.263, over 5639789.80 frames. , ppl: 9.613724267989117], batch size: 70
+2022-12-14 06:42:42,717 INFO [train.py:421] (7/8) Epoch 11, batch 40000, loss[loss=2.485, over 840.00 frames. , ppl: 12.004237580044043] tot_loss[loss=2.266, over 5573097.08 frames. , ppl: 9.637810300236163], batch size: 70
+2022-12-14 06:42:42,718 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 06:42:43,479 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.58547067678701
+2022-12-14 06:44:22,147 INFO [train.py:421] (7/8) Epoch 11, batch 40200, loss[loss=2.264, over 2380.00 frames. , ppl: 9.622506320283177] tot_loss[loss=2.266, over 5540559.21 frames. , ppl: 9.643498036397634], batch size: 70
+2022-12-14 06:46:07,000 INFO [train.py:421] (7/8) Epoch 11, batch 40400, loss[loss=2.383, over 3290.00 frames. , ppl: 10.834305284339932] tot_loss[loss=2.263, over 5653896.08 frames. , ppl: 9.615162935554292], batch size: 70
+2022-12-14 06:47:50,939 INFO [train.py:421] (7/8) Epoch 11, batch 40600, loss[loss=2.32, over 1610.00 frames. , ppl: 10.171315841241336] tot_loss[loss=2.264, over 5659621.06 frames. , ppl: 9.618195583782791], batch size: 70
+2022-12-14 06:49:30,456 INFO [train.py:421] (7/8) Epoch 11, batch 40800, loss[loss=2.194, over 7070.00 frames. , ppl: 8.967206167410843] tot_loss[loss=2.264, over 5645495.23 frames. , ppl: 9.620626227480512], batch size: 70
+2022-12-14 06:51:11,967 INFO [train.py:421] (7/8) Epoch 11, batch 41000, loss[loss=2.389, over 1540.00 frames. , ppl: 10.903053001786501] tot_loss[loss=2.265, over 5613597.69 frames. , ppl: 9.628336470629048], batch size: 70
+2022-12-14 06:51:11,968 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 06:51:12,725 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.258, over 211138.00 frames. , ppl: 9.567495329829377
+2022-12-14 06:52:55,089 INFO [train.py:421] (7/8) Epoch 11, batch 41200, loss[loss=2.614, over 770.00 frames. , ppl: 13.652532724462045] tot_loss[loss=2.263, over 5654155.18 frames. , ppl: 9.614275042056752], batch size: 70
+2022-12-14 06:54:38,130 INFO [train.py:421] (7/8) Epoch 11, batch 41400, loss[loss=2.577, over 1120.00 frames. , ppl: 13.154508741900166] tot_loss[loss=2.263, over 5646741.02 frames. , ppl: 9.616379917225316], batch size: 70
+2022-12-14 06:56:20,581 INFO [train.py:421] (7/8) Epoch 11, batch 41600, loss[loss=2.454, over 1050.00 frames. , ppl: 11.633740096082903] tot_loss[loss=2.264, over 5622313.31 frames. , ppl: 9.621849384498775], batch size: 70
+2022-12-14 06:58:01,898 INFO [train.py:421] (7/8) Epoch 11, batch 41800, loss[loss=2.345, over 2380.00 frames. , ppl: 10.435037070389487] tot_loss[loss=2.265, over 5593432.47 frames. , ppl: 9.629372045704233], batch size: 70
+2022-12-14 06:59:44,360 INFO [train.py:421] (7/8) Epoch 11, batch 42000, loss[loss=2.285, over 2170.00 frames. , ppl: 9.830541278851378] tot_loss[loss=2.264, over 5633869.02 frames. , ppl: 9.619735932606355], batch size: 70
+2022-12-14 06:59:44,360 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 06:59:45,115 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.592491660652186
+2022-12-14 07:01:25,039 INFO [train.py:421] (7/8) Epoch 11, batch 42200, loss[loss=2.353, over 1190.00 frames. , ppl: 10.512893508104295] tot_loss[loss=2.264, over 5600196.44 frames. , ppl: 9.620862302834313], batch size: 70
+2022-12-14 07:03:05,978 INFO [train.py:421] (7/8) Epoch 11, batch 42400, loss[loss=2.331, over 4060.00 frames. , ppl: 10.286456280670246] tot_loss[loss=2.262, over 5654016.29 frames. , ppl: 9.60458852318524], batch size: 70
+2022-12-14 07:04:49,209 INFO [train.py:421] (7/8) Epoch 11, batch 42600, loss[loss=3.05, over 560.00 frames. , ppl: 21.10626048973914] tot_loss[loss=2.262, over 5668377.15 frames. , ppl: 9.60510334074817], batch size: 70
+2022-12-14 07:06:29,114 INFO [train.py:421] (7/8) Epoch 11, batch 42800, loss[loss=2.202, over 3850.00 frames. , ppl: 9.040194612559764] tot_loss[loss=2.263, over 5633993.42 frames. , ppl: 9.614263338796796], batch size: 70
+2022-12-14 07:08:09,300 INFO [train.py:421] (7/8) Epoch 11, batch 43000, loss[loss=2.254, over 3850.00 frames. , ppl: 9.52539648879121] tot_loss[loss=2.263, over 5632562.22 frames. , ppl: 9.613961086142934], batch size: 70
+2022-12-14 07:08:09,300 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 07:08:10,045 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.259, over 211138.00 frames. , ppl: 9.569812285675939
+2022-12-14 07:09:48,762 INFO [train.py:421] (7/8) Epoch 11, batch 43200, loss[loss=2.158, over 4970.00 frames. , ppl: 8.655489062707781] tot_loss[loss=2.263, over 5629792.54 frames. , ppl: 9.60991969737953], batch size: 70
+2022-12-14 07:11:27,393 INFO [train.py:421] (7/8) Epoch 11, batch 43400, loss[loss=2.449, over 1260.00 frames. , ppl: 11.573962730151148] tot_loss[loss=2.264, over 5599417.53 frames. , ppl: 9.625104876276476], batch size: 70
+2022-12-14 07:13:07,442 INFO [train.py:421] (7/8) Epoch 11, batch 43600, loss[loss=2.209, over 5530.00 frames. , ppl: 9.109248672888334] tot_loss[loss=2.265, over 5571435.98 frames. , ppl: 9.632512307554425], batch size: 70
+2022-12-14 07:14:45,265 INFO [train.py:421] (7/8) Epoch 11, batch 43800, loss[loss=2.178, over 7490.00 frames. , ppl: 8.82489418665513] tot_loss[loss=2.265, over 5544394.30 frames. , ppl: 9.632377827031519], batch size: 70
+2022-12-14 07:16:27,746 INFO [train.py:421] (7/8) Epoch 11, batch 44000, loss[loss=2.35, over 1400.00 frames. , ppl: 10.487731279702764] tot_loss[loss=2.264, over 5546427.95 frames. , ppl: 9.62543652772439], batch size: 70
+2022-12-14 07:16:27,747 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 07:16:28,507 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.259, over 211138.00 frames. , ppl: 9.577322170162937
+2022-12-14 07:18:06,699 INFO [train.py:421] (7/8) Epoch 11, batch 44200, loss[loss=2.19, over 7490.00 frames. , ppl: 8.9342317788836] tot_loss[loss=2.266, over 5487875.61 frames. , ppl: 9.638223119859028], batch size: 70
+2022-12-14 07:19:47,741 INFO [train.py:421] (7/8) Epoch 11, batch 44400, loss[loss=2.374, over 1610.00 frames. , ppl: 10.738724603915744] tot_loss[loss=2.266, over 5473858.62 frames. , ppl: 9.64457913331242], batch size: 70
+2022-12-14 07:21:28,931 INFO [train.py:421] (7/8) Epoch 11, batch 44600, loss[loss=2.294, over 2730.00 frames. , ppl: 9.917695201527843] tot_loss[loss=2.267, over 5450466.98 frames. , ppl: 9.650223050434674], batch size: 70
+2022-12-14 07:23:10,233 INFO [train.py:421] (7/8) Epoch 11, batch 44800, loss[loss=2.263, over 2240.00 frames. , ppl: 9.609875089130306] tot_loss[loss=2.267, over 5439456.50 frames. , ppl: 9.654648057175233], batch size: 70
+2022-12-14 07:24:47,374 INFO [train.py:421] (7/8) Epoch 11, batch 45000, loss[loss=2.448, over 1820.00 frames. , ppl: 11.560877151185661] tot_loss[loss=2.268, over 5428016.79 frames. , ppl: 9.656382822726671], batch size: 70
+2022-12-14 07:24:47,374 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 07:24:48,135 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.587963694090844
+2022-12-14 07:26:33,406 INFO [train.py:421] (7/8) Epoch 11, batch 45200, loss[loss=2.634, over 700.00 frames. , ppl: 13.929717168503045] tot_loss[loss=2.266, over 5454640.24 frames. , ppl: 9.644837930492463], batch size: 70
+2022-12-14 07:28:14,104 INFO [train.py:421] (7/8) Epoch 11, batch 45400, loss[loss=2.244, over 3010.00 frames. , ppl: 9.428861015558066] tot_loss[loss=2.267, over 5460015.12 frames. , ppl: 9.648450860747717], batch size: 70
+2022-12-14 07:29:58,385 INFO [train.py:421] (7/8) Epoch 11, batch 45600, loss[loss=2.213, over 4270.00 frames. , ppl: 9.13910687552912] tot_loss[loss=2.266, over 5487597.21 frames. , ppl: 9.637402565608205], batch size: 70
+2022-12-14 07:31:41,340 INFO [train.py:421] (7/8) Epoch 11, batch 45800, loss[loss=2.604, over 770.00 frames. , ppl: 13.514691632378407] tot_loss[loss=2.265, over 5506467.95 frames. , ppl: 9.633522225461899], batch size: 70
+2022-12-14 07:33:22,392 INFO [train.py:421] (7/8) Epoch 11, batch 46000, loss[loss=2.179, over 8680.00 frames. , ppl: 8.838799512446416] tot_loss[loss=2.266, over 5513801.51 frames. , ppl: 9.639084012041955], batch size: 70
+2022-12-14 07:33:22,393 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 07:33:23,121 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.604798933149176
+2022-12-14 07:35:07,462 INFO [train.py:421] (7/8) Epoch 11, batch 46200, loss[loss=2.214, over 3290.00 frames. , ppl: 9.155326839407515] tot_loss[loss=2.265, over 5537626.94 frames. , ppl: 9.63147024734323], batch size: 70
+2022-12-14 07:36:50,561 INFO [train.py:421] (7/8) Epoch 11, batch 46400, loss[loss=2.775, over 700.00 frames. , ppl: 16.03271540795047] tot_loss[loss=2.263, over 5599357.34 frames. , ppl: 9.615954237391843], batch size: 70
+2022-12-14 07:38:31,817 INFO [train.py:421] (7/8) Epoch 11, batch 46600, loss[loss=2.188, over 4200.00 frames. , ppl: 8.916642343560886] tot_loss[loss=2.264, over 5568725.00 frames. , ppl: 9.616891154366707], batch size: 70
+2022-12-14 07:40:11,795 INFO [train.py:421] (7/8) Epoch 11, batch 46800, loss[loss=2.169, over 4480.00 frames. , ppl: 8.75140538720609] tot_loss[loss=2.263, over 5572307.70 frames. , ppl: 9.616125501097954], batch size: 70
+2022-12-14 07:41:53,120 INFO [train.py:421] (7/8) Epoch 11, batch 47000, loss[loss=2.173, over 12530.00 frames. , ppl: 8.78134098352732] tot_loss[loss=2.263, over 5600832.08 frames. , ppl: 9.610927983611267], batch size: 70
+2022-12-14 07:41:53,121 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 07:41:53,854 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.593797929123168
+2022-12-14 07:43:37,130 INFO [train.py:421] (7/8) Epoch 11, batch 47200, loss[loss=2.523, over 1400.00 frames. , ppl: 12.462575453739086] tot_loss[loss=2.263, over 5584607.06 frames. , ppl: 9.614977977005974], batch size: 70
+2022-12-14 07:45:10,243 INFO [train.py:421] (7/8) Epoch 11, batch 47400, loss[loss=3, over 560.00 frames. , ppl: 20.08957412109178] tot_loss[loss=2.265, over 5565898.14 frames. , ppl: 9.629371539452926], batch size: 70
+2022-12-14 07:46:47,937 INFO [train.py:421] (7/8) Epoch 11, batch 47600, loss[loss=2.3, over 2730.00 frames. , ppl: 9.97822929307949] tot_loss[loss=2.265, over 5555590.87 frames. , ppl: 9.634131881356412], batch size: 70
+2022-12-14 07:48:29,965 INFO [train.py:421] (7/8) Epoch 11, batch 47800, loss[loss=2.237, over 2940.00 frames. , ppl: 9.36304664402933] tot_loss[loss=2.266, over 5539928.00 frames. , ppl: 9.642759159313082], batch size: 70
+2022-12-14 07:50:08,692 INFO [train.py:421] (7/8) Epoch 11, batch 48000, loss[loss=2.199, over 3430.00 frames. , ppl: 9.015495841388418] tot_loss[loss=2.265, over 5557059.48 frames. , ppl: 9.633745763261446], batch size: 70
+2022-12-14 07:50:08,692 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 07:50:09,455 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.597875482483978
+2022-12-14 07:51:49,511 INFO [train.py:421] (7/8) Epoch 11, batch 48200, loss[loss=2.169, over 7980.00 frames. , ppl: 8.748704765338237] tot_loss[loss=2.265, over 5549032.80 frames. , ppl: 9.634850383296937], batch size: 70
+2022-12-14 07:53:28,411 INFO [train.py:421] (7/8) Epoch 11, batch 48400, loss[loss=2.313, over 3290.00 frames. , ppl: 10.103837090832766] tot_loss[loss=2.265, over 5545820.63 frames. , ppl: 9.634825085643536], batch size: 70
+2022-12-14 07:55:09,689 INFO [train.py:421] (7/8) Epoch 11, batch 48600, loss[loss=2.202, over 11410.00 frames. , ppl: 9.039922993491569] tot_loss[loss=2.265, over 5548126.12 frames. , ppl: 9.629711737763264], batch size: 70
+2022-12-14 07:56:48,791 INFO [train.py:421] (7/8) Epoch 11, batch 48800, loss[loss=2.316, over 1260.00 frames. , ppl: 10.130987964423246] tot_loss[loss=2.266, over 5522471.13 frames. , ppl: 9.637866150929035], batch size: 70
+2022-12-14 07:58:30,715 INFO [train.py:421] (7/8) Epoch 11, batch 49000, loss[loss=2.231, over 2800.00 frames. , ppl: 9.306000006060104] tot_loss[loss=2.266, over 5536070.78 frames. , ppl: 9.637046826064573], batch size: 70
+2022-12-14 07:58:30,716 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 07:58:31,475 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.595209466935325
+2022-12-14 08:00:11,581 INFO [train.py:421] (7/8) Epoch 11, batch 49200, loss[loss=2.295, over 3150.00 frames. , ppl: 9.924814462466417] tot_loss[loss=2.267, over 5476641.40 frames. , ppl: 9.650471499380274], batch size: 70
+2022-12-14 08:01:52,650 INFO [train.py:421] (7/8) Epoch 11, batch 49400, loss[loss=2.38, over 1190.00 frames. , ppl: 10.802222719321918] tot_loss[loss=2.266, over 5495824.85 frames. , ppl: 9.643940942675812], batch size: 70
+2022-12-14 08:03:32,888 INFO [train.py:421] (7/8) Epoch 11, batch 49600, loss[loss=2.693, over 770.00 frames. , ppl: 14.781988869532054] tot_loss[loss=2.267, over 5478241.97 frames. , ppl: 9.65051672913732], batch size: 70
+2022-12-14 08:05:11,616 INFO [train.py:421] (7/8) Epoch 11, batch 49800, loss[loss=2.282, over 1890.00 frames. , ppl: 9.796288667630712] tot_loss[loss=2.267, over 5503715.43 frames. , ppl: 9.647737316216315], batch size: 70
+2022-12-14 08:06:50,134 INFO [train.py:421] (7/8) Epoch 11, batch 50000, loss[loss=2.348, over 1400.00 frames. , ppl: 10.463139300574976] tot_loss[loss=2.266, over 5500221.10 frames. , ppl: 9.645179633896584], batch size: 70
+2022-12-14 08:06:50,134 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 08:06:50,881 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.581751511481997
+2022-12-14 08:08:32,386 INFO [train.py:421] (7/8) Epoch 11, batch 50200, loss[loss=2.428, over 1400.00 frames. , ppl: 11.340075801363936] tot_loss[loss=2.266, over 5516215.64 frames. , ppl: 9.643747152103561], batch size: 70
+2022-12-14 08:10:12,767 INFO [train.py:421] (7/8) Epoch 11, batch 50400, loss[loss=2.231, over 2030.00 frames. , ppl: 9.309823021372313] tot_loss[loss=2.265, over 5560457.83 frames. , ppl: 9.627737882965226], batch size: 70
+2022-12-14 08:11:48,475 INFO [train.py:421] (7/8) Epoch 11, batch 50600, loss[loss=2.183, over 7560.00 frames. , ppl: 8.87589359479543] tot_loss[loss=2.264, over 5556732.45 frames. , ppl: 9.621141497854248], batch size: 70
+2022-12-14 08:13:30,528 INFO [train.py:421] (7/8) Epoch 11, batch 50800, loss[loss=2.46, over 1610.00 frames. , ppl: 11.709367579241487] tot_loss[loss=2.264, over 5532744.31 frames. , ppl: 9.62489366619627], batch size: 70
+2022-12-14 08:15:09,636 INFO [train.py:421] (7/8) Epoch 11, batch 51000, loss[loss=2.811, over 840.00 frames. , ppl: 16.623825498074986] tot_loss[loss=2.265, over 5539734.07 frames. , ppl: 9.627235813127488], batch size: 70
+2022-12-14 08:15:09,637 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 08:15:10,400 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.599885781441973
+2022-12-14 08:16:50,481 INFO [train.py:421] (7/8) Epoch 11, batch 51200, loss[loss=2.235, over 3150.00 frames. , ppl: 9.349192945272407] tot_loss[loss=2.263, over 5576932.62 frames. , ppl: 9.614454867389766], batch size: 70
+2022-12-14 08:18:32,234 INFO [train.py:421] (7/8) Epoch 11, batch 51400, loss[loss=2.377, over 1960.00 frames. , ppl: 10.772273301262667] tot_loss[loss=2.262, over 5615029.68 frames. , ppl: 9.604227422103007], batch size: 70
+2022-12-14 08:20:10,263 INFO [train.py:421] (7/8) Epoch 11, batch 51600, loss[loss=2.316, over 2170.00 frames. , ppl: 10.133822496195373] tot_loss[loss=2.263, over 5603711.29 frames. , ppl: 9.611066274047388], batch size: 70
+2022-12-14 08:21:49,056 INFO [train.py:421] (7/8) Epoch 11, batch 51800, loss[loss=2.335, over 1260.00 frames. , ppl: 10.33435746412323] tot_loss[loss=2.264, over 5549437.55 frames. , ppl: 9.622569277078162], batch size: 70
+2022-12-14 08:23:27,666 INFO [train.py:421] (7/8) Epoch 11, batch 52000, loss[loss=2.162, over 11760.00 frames. , ppl: 8.692598636376813] tot_loss[loss=2.264, over 5566161.99 frames. , ppl: 9.619643374353782], batch size: 70
+2022-12-14 08:23:27,666 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 08:23:28,401 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.587526624273279
+2022-12-14 08:25:07,219 INFO [train.py:421] (7/8) Epoch 11, batch 52200, loss[loss=2.21, over 6020.00 frames. , ppl: 9.114978823061264] tot_loss[loss=2.265, over 5552967.91 frames. , ppl: 9.63148902467577], batch size: 70
+2022-12-14 08:26:45,635 INFO [train.py:421] (7/8) Epoch 11, batch 52400, loss[loss=2.28, over 2380.00 frames. , ppl: 9.775614994273583] tot_loss[loss=2.266, over 5526062.43 frames. , ppl: 9.639126848013905], batch size: 70
+2022-12-14 08:28:22,606 INFO [train.py:421] (7/8) Epoch 11, batch 52600, loss[loss=2.165, over 3920.00 frames. , ppl: 8.718544925896563] tot_loss[loss=2.265, over 5529501.36 frames. , ppl: 9.632579980784392], batch size: 70
+2022-12-14 08:30:00,815 INFO [train.py:421] (7/8) Epoch 11, batch 52800, loss[loss=2.157, over 9170.00 frames. , ppl: 8.641009646947413] tot_loss[loss=2.264, over 5557142.73 frames. , ppl: 9.625338897921663], batch size: 70
+2022-12-14 08:31:42,278 INFO [train.py:421] (7/8) Epoch 11, batch 53000, loss[loss=2.256, over 910.00 frames. , ppl: 9.545998174833338] tot_loss[loss=2.264, over 5569878.08 frames. , ppl: 9.625331686446705], batch size: 70
+2022-12-14 08:31:42,279 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 08:31:43,029 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.581084994414798
+2022-12-14 08:33:24,616 INFO [train.py:421] (7/8) Epoch 11, batch 53200, loss[loss=2.158, over 9170.00 frames. , ppl: 8.654088605729573] tot_loss[loss=2.264, over 5578638.32 frames. , ppl: 9.618864183689727], batch size: 70
+2022-12-14 08:35:06,682 INFO [train.py:421] (7/8) Epoch 11, batch 53400, loss[loss=2.39, over 840.00 frames. , ppl: 10.916581943490469] tot_loss[loss=2.264, over 5553925.74 frames. , ppl: 9.617641558767312], batch size: 70
+2022-12-14 08:36:47,442 INFO [train.py:421] (7/8) Epoch 11, batch 53600, loss[loss=2.133, over 3710.00 frames. , ppl: 8.438309277506928] tot_loss[loss=2.263, over 5555895.97 frames. , ppl: 9.616007005069285], batch size: 70
+2022-12-14 08:38:27,755 INFO [train.py:421] (7/8) Epoch 11, batch 53800, loss[loss=2.271, over 1470.00 frames. , ppl: 9.685089441666886] tot_loss[loss=2.265, over 5491122.58 frames. , ppl: 9.635408775025082], batch size: 70
+2022-12-14 08:40:09,518 INFO [train.py:421] (7/8) Epoch 11, batch 54000, loss[loss=2.319, over 2590.00 frames. , ppl: 10.164857738948577] tot_loss[loss=2.265, over 5521803.36 frames. , ppl: 9.632486741560026], batch size: 70
+2022-12-14 08:40:09,518 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 08:40:10,265 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.59367723381749
+2022-12-14 08:41:46,162 INFO [train.py:421] (7/8) Epoch 11, batch 54200, loss[loss=2.454, over 1190.00 frames. , ppl: 11.637695981725347] tot_loss[loss=2.266, over 5492994.83 frames. , ppl: 9.641177814923097], batch size: 70
+2022-12-14 08:43:25,449 INFO [train.py:421] (7/8) Epoch 11, batch 54400, loss[loss=2.118, over 5040.00 frames. , ppl: 8.314940903937277] tot_loss[loss=2.265, over 5489987.52 frames. , ppl: 9.630694858373914], batch size: 70
+2022-12-14 08:45:04,356 INFO [train.py:421] (7/8) Epoch 11, batch 54600, loss[loss=2.258, over 3920.00 frames. , ppl: 9.56561573033571] tot_loss[loss=2.266, over 5474502.44 frames. , ppl: 9.638898930585004], batch size: 70
+2022-12-14 08:46:40,893 INFO [train.py:421] (7/8) Epoch 11, batch 54800, loss[loss=2.354, over 1330.00 frames. , ppl: 10.526811978834022] tot_loss[loss=2.266, over 5493604.91 frames. , ppl: 9.637538965359743], batch size: 70
+2022-12-14 08:48:23,511 INFO [train.py:421] (7/8) Epoch 11, batch 55000, loss[loss=2.273, over 2730.00 frames. , ppl: 9.713326884246507] tot_loss[loss=2.265, over 5499156.65 frames. , ppl: 9.635697401795484], batch size: 70
+2022-12-14 08:48:23,512 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 08:48:24,275 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.600448456413142
+2022-12-14 08:50:04,127 INFO [train.py:421] (7/8) Epoch 11, batch 55200, loss[loss=2.389, over 1680.00 frames. , ppl: 10.902275496047736] tot_loss[loss=2.265, over 5508852.45 frames. , ppl: 9.631322350483003], batch size: 70
+2022-12-14 08:51:43,844 INFO [train.py:421] (7/8) Epoch 11, batch 55400, loss[loss=2.356, over 2520.00 frames. , ppl: 10.545507169894371] tot_loss[loss=2.266, over 5486757.41 frames. , ppl: 9.638318687517977], batch size: 70
+2022-12-14 08:53:24,621 INFO [train.py:421] (7/8) Epoch 11, batch 55600, loss[loss=2.613, over 840.00 frames. , ppl: 13.642810207126512] tot_loss[loss=2.264, over 5515990.44 frames. , ppl: 9.62433914702611], batch size: 70
+2022-12-14 08:55:02,630 INFO [train.py:421] (7/8) Epoch 11, batch 55800, loss[loss=2.755, over 770.00 frames. , ppl: 15.714006210775143] tot_loss[loss=2.266, over 5484336.35 frames. , ppl: 9.63735731728292], batch size: 70
+2022-12-14 08:56:44,632 INFO [train.py:421] (7/8) Epoch 11, batch 56000, loss[loss=2.124, over 8190.00 frames. , ppl: 8.360668396932436] tot_loss[loss=2.266, over 5467084.58 frames. , ppl: 9.642230387758056], batch size: 70
+2022-12-14 08:56:44,632 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 08:56:45,361 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.589785979049779
+2022-12-14 08:58:29,521 INFO [train.py:421] (7/8) Epoch 11, batch 56200, loss[loss=2.365, over 1330.00 frames. , ppl: 10.64788433027091] tot_loss[loss=2.265, over 5474345.80 frames. , ppl: 9.635691775960488], batch size: 70
+2022-12-14 09:00:08,807 INFO [train.py:421] (7/8) Epoch 11, batch 56400, loss[loss=2.303, over 2100.00 frames. , ppl: 10.00734559102924] tot_loss[loss=2.264, over 5507938.92 frames. , ppl: 9.625539054153219], batch size: 70
+2022-12-14 09:01:50,868 INFO [train.py:421] (7/8) Epoch 11, batch 56600, loss[loss=2.203, over 5250.00 frames. , ppl: 9.053900728052161] tot_loss[loss=2.264, over 5542466.01 frames. , ppl: 9.623429246015226], batch size: 70
+2022-12-14 09:03:29,224 INFO [train.py:421] (7/8) Epoch 11, batch 56800, loss[loss=2.241, over 4200.00 frames. , ppl: 9.398701313353712] tot_loss[loss=2.266, over 5489484.32 frames. , ppl: 9.638335600845203], batch size: 70
+2022-12-14 09:05:09,670 INFO [train.py:421] (7/8) Epoch 11, batch 57000, loss[loss=2.635, over 840.00 frames. , ppl: 13.947015350320582] tot_loss[loss=2.267, over 5452612.04 frames. , ppl: 9.653381144054066], batch size: 70
+2022-12-14 09:05:09,671 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 09:05:10,417 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.587563519007391
+2022-12-14 09:06:48,016 INFO [train.py:421] (7/8) Epoch 11, batch 57200, loss[loss=2.166, over 4970.00 frames. , ppl: 8.720009123604246] tot_loss[loss=2.268, over 5448514.07 frames. , ppl: 9.65744292131872], batch size: 70
+2022-12-14 09:08:32,496 INFO [train.py:421] (7/8) Epoch 11, batch 57400, loss[loss=2.283, over 4200.00 frames. , ppl: 9.801756618931254] tot_loss[loss=2.267, over 5484013.16 frames. , ppl: 9.650310020367478], batch size: 70
+2022-12-14 09:10:14,445 INFO [train.py:421] (7/8) Epoch 11, batch 57600, loss[loss=2.268, over 2240.00 frames. , ppl: 9.655565921038448] tot_loss[loss=2.267, over 5494124.48 frames. , ppl: 9.647105400062145], batch size: 70
+2022-12-14 09:11:54,087 INFO [train.py:421] (7/8) Epoch 11, batch 57800, loss[loss=2.43, over 1540.00 frames. , ppl: 11.358606207499502] tot_loss[loss=2.268, over 5473714.94 frames. , ppl: 9.657585536377715], batch size: 70
+2022-12-14 09:13:32,715 INFO [train.py:421] (7/8) Epoch 11, batch 58000, loss[loss=2.227, over 2800.00 frames. , ppl: 9.26744196645228] tot_loss[loss=2.269, over 5418165.14 frames. , ppl: 9.671638886731476], batch size: 70
+2022-12-14 09:13:32,716 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 09:13:33,485 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.579467110769087
+2022-12-14 09:15:15,196 INFO [train.py:421] (7/8) Epoch 11, batch 58200, loss[loss=2.276, over 3010.00 frames. , ppl: 9.738971706411618] tot_loss[loss=2.269, over 5422937.53 frames. , ppl: 9.667016959862782], batch size: 70
+2022-12-14 09:16:56,044 INFO [train.py:421] (7/8) Epoch 11, batch 58400, loss[loss=2.11, over 6160.00 frames. , ppl: 8.252286213660929] tot_loss[loss=2.267, over 5467465.75 frames. , ppl: 9.647644294183605], batch size: 70
+2022-12-14 09:18:34,149 INFO [train.py:421] (7/8) Epoch 11, batch 58600, loss[loss=2.611, over 840.00 frames. , ppl: 13.60874815306177] tot_loss[loss=2.267, over 5427624.20 frames. , ppl: 9.649825436801246], batch size: 70
+2022-12-14 09:20:16,254 INFO [train.py:421] (7/8) Epoch 11, batch 58800, loss[loss=2.645, over 910.00 frames. , ppl: 14.090008931806565] tot_loss[loss=2.267, over 5426140.24 frames. , ppl: 9.655049667434277], batch size: 70
+2022-12-14 09:21:58,266 INFO [train.py:421] (7/8) Epoch 11, batch 59000, loss[loss=2.799, over 700.00 frames. , ppl: 16.425518748992026] tot_loss[loss=2.267, over 5423197.19 frames. , ppl: 9.65440509467485], batch size: 70
+2022-12-14 09:21:58,266 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 09:21:59,025 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.585608293732157
+2022-12-14 09:23:40,364 INFO [train.py:421] (7/8) Epoch 11, batch 59200, loss[loss=2.463, over 840.00 frames. , ppl: 11.741233345197772] tot_loss[loss=2.268, over 5417613.50 frames. , ppl: 9.659147003244122], batch size: 70
+2022-12-14 09:25:21,847 INFO [train.py:421] (7/8) Epoch 11, batch 59400, loss[loss=2.203, over 4270.00 frames. , ppl: 9.053550655959556] tot_loss[loss=2.267, over 5418642.80 frames. , ppl: 9.654507843257152], batch size: 70
+2022-12-14 09:27:00,560 INFO [train.py:421] (7/8) Epoch 11, batch 59600, loss[loss=2.18, over 3010.00 frames. , ppl: 8.843510658849095] tot_loss[loss=2.266, over 5442332.71 frames. , ppl: 9.643429654706637], batch size: 70
+2022-12-14 09:28:41,378 INFO [train.py:421] (7/8) Epoch 11, batch 59800, loss[loss=2.18, over 4200.00 frames. , ppl: 8.850373680552154] tot_loss[loss=2.267, over 5411631.06 frames. , ppl: 9.65442866968986], batch size: 70
+2022-12-14 09:30:19,023 INFO [train.py:421] (7/8) Epoch 11, batch 60000, loss[loss=2.196, over 3500.00 frames. , ppl: 8.990181986720584] tot_loss[loss=2.268, over 5423003.39 frames. , ppl: 9.655408405381262], batch size: 70
+2022-12-14 09:30:19,024 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 09:30:19,782 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.259, over 211138.00 frames. , ppl: 9.57757590873942
+2022-12-14 09:32:01,997 INFO [train.py:421] (7/8) Epoch 11, batch 60200, loss[loss=2.459, over 1120.00 frames. , ppl: 11.697947100997657] tot_loss[loss=2.268, over 5431112.28 frames. , ppl: 9.658273288190944], batch size: 70
+2022-12-14 09:33:42,588 INFO [train.py:421] (7/8) Epoch 11, batch 60400, loss[loss=2.377, over 1680.00 frames. , ppl: 10.77373351421187] tot_loss[loss=2.267, over 5449293.26 frames. , ppl: 9.65253707817507], batch size: 70
+2022-12-14 09:35:24,853 INFO [train.py:421] (7/8) Epoch 11, batch 60600, loss[loss=2.238, over 3710.00 frames. , ppl: 9.374826154208272] tot_loss[loss=2.266, over 5500619.40 frames. , ppl: 9.640537976621689], batch size: 70
+2022-12-14 09:37:07,335 INFO [train.py:421] (7/8) Epoch 11, batch 60800, loss[loss=2.334, over 1890.00 frames. , ppl: 10.319318304776576] tot_loss[loss=2.266, over 5513960.73 frames. , ppl: 9.638998323145481], batch size: 70
+2022-12-14 09:38:49,724 INFO [train.py:421] (7/8) Epoch 11, batch 61000, loss[loss=2.304, over 2590.00 frames. , ppl: 10.017540400628256] tot_loss[loss=2.266, over 5527876.65 frames. , ppl: 9.63673158310196], batch size: 70
+2022-12-14 09:38:49,725 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 09:38:50,484 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.587292487923966
+2022-12-14 09:40:29,806 INFO [train.py:421] (7/8) Epoch 11, batch 61200, loss[loss=2.16, over 3150.00 frames. , ppl: 8.670574493673247] tot_loss[loss=2.266, over 5492822.14 frames. , ppl: 9.641966653992668], batch size: 70
+2022-12-14 09:42:09,351 INFO [train.py:421] (7/8) Epoch 11, batch 61400, loss[loss=2.313, over 2660.00 frames. , ppl: 10.10336932148686] tot_loss[loss=2.266, over 5494464.29 frames. , ppl: 9.643644900081782], batch size: 70
+2022-12-14 09:43:48,639 INFO [train.py:421] (7/8) Epoch 11, batch 61600, loss[loss=2.122, over 4550.00 frames. , ppl: 8.345275497541335] tot_loss[loss=2.266, over 5481013.22 frames. , ppl: 9.642575909038435], batch size: 70
+2022-12-14 09:45:23,761 INFO [train.py:421] (7/8) Epoch 11, batch 61800, loss[loss=2.28, over 2800.00 frames. , ppl: 9.772197503905725] tot_loss[loss=2.266, over 5481292.41 frames. , ppl: 9.636945364650332], batch size: 70
+2022-12-14 09:47:03,483 INFO [train.py:421] (7/8) Epoch 11, batch 62000, loss[loss=2.289, over 1750.00 frames. , ppl: 9.862051367609673] tot_loss[loss=2.266, over 5485308.74 frames. , ppl: 9.636722057827757], batch size: 70
+2022-12-14 09:47:03,483 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 09:47:04,244 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.582718752746382
+2022-12-14 09:48:44,735 INFO [train.py:421] (7/8) Epoch 11, batch 62200, loss[loss=2.36, over 3920.00 frames. , ppl: 10.591265960405147] tot_loss[loss=2.266, over 5466980.51 frames. , ppl: 9.642265099702778], batch size: 70
+2022-12-14 09:50:24,715 INFO [train.py:421] (7/8) Epoch 11, batch 62400, loss[loss=2.372, over 1260.00 frames. , ppl: 10.721415057476824] tot_loss[loss=2.266, over 5456073.93 frames. , ppl: 9.639172235814609], batch size: 70
+2022-12-14 09:52:03,659 INFO [train.py:421] (7/8) Epoch 11, batch 62600, loss[loss=2.32, over 2660.00 frames. , ppl: 10.174636558563696] tot_loss[loss=2.267, over 5411261.48 frames. , ppl: 9.650336069139144], batch size: 70
+2022-12-14 09:53:42,469 INFO [train.py:421] (7/8) Epoch 11, batch 62800, loss[loss=2.485, over 980.00 frames. , ppl: 12.000783015079039] tot_loss[loss=2.267, over 5433399.87 frames. , ppl: 9.64865965476909], batch size: 70
+2022-12-14 09:55:20,750 INFO [train.py:421] (7/8) Epoch 11, batch 63000, loss[loss=2.423, over 980.00 frames. , ppl: 11.283284752411609] tot_loss[loss=2.266, over 5455934.46 frames. , ppl: 9.641328126554685], batch size: 70
+2022-12-14 09:55:20,750 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 09:55:21,511 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.60109500498798
+2022-12-14 09:57:02,142 INFO [train.py:421] (7/8) Epoch 11, batch 63200, loss[loss=2.489, over 910.00 frames. , ppl: 12.050559131790044] tot_loss[loss=2.266, over 5436232.86 frames. , ppl: 9.639927825519788], batch size: 70
+2022-12-14 09:58:42,040 INFO [train.py:421] (7/8) Epoch 11, batch 63400, loss[loss=2.404, over 1330.00 frames. , ppl: 11.065397664087733] tot_loss[loss=2.266, over 5454300.14 frames. , ppl: 9.641520987082279], batch size: 70
+2022-12-14 10:00:19,152 INFO [train.py:421] (7/8) Epoch 11, batch 63600, loss[loss=2.32, over 2520.00 frames. , ppl: 10.180174241594965] tot_loss[loss=2.267, over 5414551.77 frames. , ppl: 9.65354488751949], batch size: 70
+2022-12-14 10:02:00,368 INFO [train.py:421] (7/8) Epoch 11, batch 63800, loss[loss=2.185, over 9030.00 frames. , ppl: 8.889837860166997] tot_loss[loss=2.265, over 5505542.09 frames. , ppl: 9.632853231175721], batch size: 70
+2022-12-14 10:03:38,199 INFO [train.py:421] (7/8) Epoch 11, batch 64000, loss[loss=2.25, over 3780.00 frames. , ppl: 9.49202142342324] tot_loss[loss=2.264, over 5518855.75 frames. , ppl: 9.623309727750321], batch size: 70
+2022-12-14 10:03:38,200 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 10:03:38,952 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.263, over 211138.00 frames. , ppl: 9.61195926586509
+2022-12-14 10:05:19,749 INFO [train.py:421] (7/8) Epoch 11, batch 64200, loss[loss=2.256, over 2100.00 frames. , ppl: 9.547262056973592] tot_loss[loss=2.266, over 5477572.55 frames. , ppl: 9.640218886457433], batch size: 70
+2022-12-14 10:07:02,735 INFO [train.py:421] (7/8) Epoch 11, batch 64400, loss[loss=2.733, over 630.00 frames. , ppl: 15.385733403958474] tot_loss[loss=2.265, over 5545843.76 frames. , ppl: 9.626585771730644], batch size: 70
+2022-12-14 10:08:42,848 INFO [train.py:421] (7/8) Epoch 11, batch 64600, loss[loss=2.287, over 2520.00 frames. , ppl: 9.848704781332918] tot_loss[loss=2.263, over 5574867.17 frames. , ppl: 9.615859613872926], batch size: 70
+2022-12-14 10:10:23,651 INFO [train.py:421] (7/8) Epoch 11, batch 64800, loss[loss=2.186, over 3920.00 frames. , ppl: 8.897637428625153] tot_loss[loss=2.264, over 5548018.74 frames. , ppl: 9.6210851991454], batch size: 70
+2022-12-14 10:12:04,659 INFO [train.py:421] (7/8) Epoch 11, batch 65000, loss[loss=2.438, over 1540.00 frames. , ppl: 11.451237782876555] tot_loss[loss=2.264, over 5535434.48 frames. , ppl: 9.620145609876742], batch size: 70
+2022-12-14 10:12:04,660 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 10:12:05,419 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.588153854062595
+2022-12-14 10:13:48,134 INFO [train.py:421] (7/8) Epoch 11, batch 65200, loss[loss=2.318, over 2800.00 frames. , ppl: 10.159698644052297] tot_loss[loss=2.265, over 5533396.82 frames. , ppl: 9.626556243469254], batch size: 70
+2022-12-14 10:15:30,903 INFO [train.py:421] (7/8) Epoch 11, batch 65400, loss[loss=3.454, over 490.00 frames. , ppl: 31.632829258788714] tot_loss[loss=2.263, over 5561424.76 frames. , ppl: 9.614100409890309], batch size: 70
+2022-12-14 10:17:13,921 INFO [train.py:421] (7/8) Epoch 11, batch 65600, loss[loss=2.173, over 2940.00 frames. , ppl: 8.78159520095936] tot_loss[loss=2.263, over 5596568.53 frames. , ppl: 9.609362157064762], batch size: 70
+2022-12-14 10:18:52,818 INFO [train.py:421] (7/8) Epoch 11, batch 65800, loss[loss=2.435, over 980.00 frames. , ppl: 11.4136324985882] tot_loss[loss=2.263, over 5566139.17 frames. , ppl: 9.614160665919176], batch size: 70
+2022-12-14 10:20:34,422 INFO [train.py:421] (7/8) Epoch 11, batch 66000, loss[loss=2.236, over 4900.00 frames. , ppl: 9.357829093015411] tot_loss[loss=2.263, over 5586215.88 frames. , ppl: 9.608802373261314], batch size: 70
+2022-12-14 10:20:34,423 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 10:20:35,171 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.583815172113377
+2022-12-14 10:22:18,349 INFO [train.py:421] (7/8) Epoch 11, batch 66200, loss[loss=2.329, over 1330.00 frames. , ppl: 10.26508555053519] tot_loss[loss=2.263, over 5576410.44 frames. , ppl: 9.608206199922726], batch size: 70
+2022-12-14 10:24:06,434 INFO [train.py:421] (7/8) Epoch 11, batch 66400, loss[loss=2.288, over 2030.00 frames. , ppl: 9.850349880798838] tot_loss[loss=2.264, over 5520207.77 frames. , ppl: 9.620578558924965], batch size: 70
+2022-12-14 10:25:47,258 INFO [train.py:421] (7/8) Epoch 11, batch 66600, loss[loss=2.623, over 770.00 frames. , ppl: 13.776410969554867] tot_loss[loss=2.264, over 5501923.02 frames. , ppl: 9.623830360989654], batch size: 70
+2022-12-14 10:27:31,530 INFO [train.py:421] (7/8) Epoch 11, batch 66800, loss[loss=2.414, over 1540.00 frames. , ppl: 11.181707838658498] tot_loss[loss=2.264, over 5505483.62 frames. , ppl: 9.624504847717015], batch size: 70
+2022-12-14 10:29:12,954 INFO [train.py:421] (7/8) Epoch 11, batch 67000, loss[loss=2.539, over 840.00 frames. , ppl: 12.669858696976256] tot_loss[loss=2.264, over 5519014.09 frames. , ppl: 9.625107972746788], batch size: 70
+2022-12-14 10:29:12,954 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 10:29:13,717 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.262, over 211138.00 frames. , ppl: 9.59918248410303
+2022-12-14 10:30:53,826 INFO [train.py:421] (7/8) Epoch 11, batch 67200, loss[loss=2.187, over 4130.00 frames. , ppl: 8.906778561437084] tot_loss[loss=2.266, over 5501111.01 frames. , ppl: 9.63735068796002], batch size: 70
+2022-12-14 10:32:32,049 INFO [train.py:421] (7/8) Epoch 11, batch 67400, loss[loss=2.247, over 6090.00 frames. , ppl: 9.46096193394294] tot_loss[loss=2.265, over 5516790.39 frames. , ppl: 9.628914963347839], batch size: 70
+2022-12-14 10:34:15,946 INFO [train.py:421] (7/8) Epoch 11, batch 67600, loss[loss=2.183, over 1330.00 frames. , ppl: 8.87506709648717] tot_loss[loss=2.266, over 5480542.69 frames. , ppl: 9.638931912817993], batch size: 70
+2022-12-14 10:35:56,743 INFO [train.py:421] (7/8) Epoch 11, batch 67800, loss[loss=2.23, over 3920.00 frames. , ppl: 9.304513837324098] tot_loss[loss=2.266, over 5460522.17 frames. , ppl: 9.642895384346721], batch size: 70
+2022-12-14 10:37:37,872 INFO [train.py:421] (7/8) Epoch 11, batch 68000, loss[loss=2.197, over 5040.00 frames. , ppl: 8.99866403148827] tot_loss[loss=2.267, over 5440448.29 frames. , ppl: 9.649106006202201], batch size: 70
+2022-12-14 10:37:37,873 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 10:37:38,622 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.26, over 211138.00 frames. , ppl: 9.586750448742256
+2022-12-14 10:39:17,212 INFO [train.py:421] (7/8) Epoch 11, batch 68200, loss[loss=2.286, over 2660.00 frames. , ppl: 9.83564234044528] tot_loss[loss=2.268, over 5421831.11 frames. , ppl: 9.657631235628644], batch size: 70
+2022-12-14 10:40:56,990 INFO [train.py:421] (7/8) Epoch 11, batch 68400, loss[loss=3.037, over 560.00 frames. , ppl: 20.835243331375025] tot_loss[loss=2.268, over 5404640.74 frames. , ppl: 9.663583882060445], batch size: 70
+2022-12-14 10:42:35,926 INFO [train.py:421] (7/8) Epoch 11, batch 68600, loss[loss=2.664, over 840.00 frames. , ppl: 14.347891426174721] tot_loss[loss=2.269, over 5386502.87 frames. , ppl: 9.667116029746731], batch size: 70
+2022-12-14 10:44:17,967 INFO [train.py:421] (7/8) Epoch 11, batch 68800, loss[loss=2.58, over 910.00 frames. , ppl: 13.202645669426042] tot_loss[loss=2.269, over 5411949.26 frames. , ppl: 9.667425378159303], batch size: 70
+2022-12-14 10:46:02,172 INFO [train.py:421] (7/8) Epoch 11, batch 69000, loss[loss=2.964, over 560.00 frames. , ppl: 19.379515647660593] tot_loss[loss=2.271, over 5354455.02 frames. , ppl: 9.686085562867172], batch size: 70
+2022-12-14 10:46:02,173 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 10:46:02,935 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.261, over 211138.00 frames. , ppl: 9.590407678839963
+2022-12-14 10:47:43,636 INFO [train.py:421] (7/8) Epoch 11, batch 69200, loss[loss=2.265, over 2240.00 frames. , ppl: 9.63463798891113] tot_loss[loss=2.271, over 5343558.30 frames. , ppl: 9.690472196752912], batch size: 70
+2022-12-14 10:49:26,939 INFO [train.py:421] (7/8) Epoch 11, batch 69400, loss[loss=2.232, over 4690.00 frames. , ppl: 9.318084882457883] tot_loss[loss=2.27, over 5405655.85 frames. , ppl: 9.676882840546394], batch size: 70
+2022-12-14 10:51:09,338 INFO [train.py:421] (7/8) Epoch 11, batch 69600, loss[loss=2.201, over 5740.00 frames. , ppl: 9.035506726383025] tot_loss[loss=2.27, over 5389041.16 frames. , ppl: 9.680851319562299], batch size: 70
+2022-12-14 10:52:54,747 INFO [train.py:421] (7/8) Epoch 11, batch 69800, loss[loss=2.356, over 1610.00 frames. , ppl: 10.5498058643424] tot_loss[loss=2.269, over 5419847.22 frames. , ppl: 9.672066810365164], batch size: 70
+2022-12-14 10:54:39,566 INFO [train.py:421] (7/8) Epoch 11, batch 70000, loss[loss=2.132, over 5390.00 frames. , ppl: 8.429111385791309] tot_loss[loss=2.27, over 5399730.88 frames. , ppl: 9.677639834671329], batch size: 70
+2022-12-14 10:54:39,567 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 10:54:40,301 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.259, over 211138.00 frames. , ppl: 9.575361947313867
+2022-12-14 10:56:19,536 INFO [train.py:421] (7/8) Epoch 11, batch 70200, loss[loss=2.446, over 1750.00 frames. , ppl: 11.544192280854956] tot_loss[loss=2.27, over 5397827.58 frames. , ppl: 9.682158420577858], batch size: 70
+2022-12-14 10:58:03,425 INFO [train.py:421] (7/8) Epoch 11, batch 70400, loss[loss=2.865, over 560.00 frames. , ppl: 17.553771309677177] tot_loss[loss=2.27, over 5414961.38 frames. , ppl: 9.67730812533178], batch size: 70
+2022-12-14 10:59:41,682 INFO [train.py:421] (7/8) Epoch 11, batch 70600, loss[loss=2.237, over 2870.00 frames. , ppl: 9.366466484887315] tot_loss[loss=2.27, over 5390153.78 frames. , ppl: 9.683334345129031], batch size: 70
+2022-12-14 11:01:20,613 INFO [train.py:421] (7/8) Epoch 11, batch 70800, loss[loss=2.138, over 3920.00 frames. , ppl: 8.482286604291366] tot_loss[loss=2.27, over 5381284.91 frames. , ppl: 9.682208811337182], batch size: 70
+2022-12-14 11:03:04,093 INFO [train.py:421] (7/8) Epoch 11, batch 71000, loss[loss=2.681, over 770.00 frames. , ppl: 14.604428834104457] tot_loss[loss=2.272, over 5337184.10 frames. , ppl: 9.702692857260345], batch size: 70
+2022-12-14 11:03:04,094 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 11:03:04,885 INFO [train.py:452] (7/8) Epoch 11, validation: loss=2.259, over 211138.00 frames. , ppl: 9.57697205031597
+2022-12-14 11:04:44,373 INFO [train.py:421] (7/8) Epoch 11, batch 71200, loss[loss=2.244, over 3920.00 frames. , ppl: 9.428129155791105] tot_loss[loss=2.273, over 5323970.40 frames. , ppl: 9.709584482135147], batch size: 70
+2022-12-14 11:06:25,522 INFO [train.py:421] (7/8) Epoch 11, batch 71400, loss[loss=4.025, over 350.00 frames. , ppl: 56.001906913798045] tot_loss[loss=2.272, over 5342211.92 frames. , ppl: 9.703530024061715], batch size: 70
+2022-12-14 11:08:07,115 INFO [train.py:421] (7/8) Epoch 11, batch 71600, loss[loss=2.298, over 1890.00 frames. , ppl: 9.95797192856516] tot_loss[loss=2.272, over 5353416.47 frames. , ppl: 9.70050104087822], batch size: 70
+2022-12-14 11:09:48,361 INFO [train.py:421] (7/8) Epoch 11, batch 71800, loss[loss=2.481, over 840.00 frames. , ppl: 11.949492002299413] tot_loss[loss=2.273, over 5320364.62 frames. , ppl: 9.706580222924245], batch size: 70
+2022-12-14 11:11:04,453 INFO [train.py:421] (7/8) Epoch 12, batch 0, loss[loss=2.289, over 3570.00 frames. , ppl: 9.866412948656327] tot_loss[loss=2.289, over 3570.00 frames. , ppl: 9.866412948656327], batch size: 70
+2022-12-14 11:12:45,933 INFO [train.py:421] (7/8) Epoch 12, batch 200, loss[loss=2.323, over 2590.00 frames. , ppl: 10.208844390256044] tot_loss[loss=2.261, over 513351.21 frames. , ppl: 9.59226444332147], batch size: 70
+2022-12-14 11:14:25,216 INFO [train.py:421] (7/8) Epoch 12, batch 400, loss[loss=2.237, over 2450.00 frames. , ppl: 9.364885185773895] tot_loss[loss=2.268, over 936348.70 frames. , ppl: 9.655731331923308], batch size: 70
+2022-12-14 11:16:08,525 INFO [train.py:421] (7/8) Epoch 12, batch 600, loss[loss=2.352, over 2380.00 frames. , ppl: 10.510294852534857] tot_loss[loss=2.258, over 1406650.62 frames. , ppl: 9.567781090457935], batch size: 70
+2022-12-14 11:17:49,310 INFO [train.py:421] (7/8) Epoch 12, batch 800, loss[loss=2.175, over 5670.00 frames. , ppl: 8.798600443946148] tot_loss[loss=2.256, over 1787828.55 frames. , ppl: 9.549241236860773], batch size: 70
+2022-12-14 11:19:30,205 INFO [train.py:421] (7/8) Epoch 12, batch 1000, loss[loss=4.088, over 350.00 frames. , ppl: 59.60145380754547] tot_loss[loss=2.259, over 2118753.50 frames. , ppl: 9.574094734323287], batch size: 70
+2022-12-14 11:19:30,206 INFO [train.py:441] (7/8) Computing validation loss
+2022-12-14 11:19:30,968 INFO [train.py:452] (7/8) Epoch 12, validation: loss=2.26, over 211138.00 frames. , ppl: 9.584870576501038
+2022-12-14 11:21:11,007 INFO [train.py:421] (7/8) Epoch 12, batch 1200, loss[loss=2.249, over 2520.00 frames. , ppl: 9.479573325692227] tot_loss[loss=2.254, over 2503664.11 frames. , ppl: 9.527502710197126], batch size: 70