Update README.md

README.md

@@ -76,38 +76,50 @@ bpe分词："vocab_size"=30000
 [INFO|trainer.py:1614] 2022-12-02 19:52:59,024 >>   Total optimization steps = 84996
 [INFO|trainer.py:1616] 2022-12-02 19:52:59,025 >>   Number of trainable parameters = 124439808
 
+[INFO|trainer.py:1608] 2022-12-03 21:44:00,182 >> ***** Running training *****
+[INFO|trainer.py:1609] 2022-12-03 21:44:00,182 >>   Num examples = 9443
+[INFO|trainer.py:1610] 2022-12-03 21:44:00,182 >>   Num Epochs = 216
+[INFO|trainer.py:1611] 2022-12-03 21:44:00,182 >>   Instantaneous batch size per device = 12
+[INFO|trainer.py:1612] 2022-12-03 21:44:00,182 >>   Total train batch size (w. parallel, distributed & accumulation) = 12
+[INFO|trainer.py:1613] 2022-12-03 21:44:00,182 >>   Gradient Accumulation steps = 1
+[INFO|trainer.py:1614] 2022-12-03 21:44:00,182 >>   Total optimization steps = 169992
+[INFO|trainer.py:1616] 2022-12-03 21:44:00,183 >>   Number of trainable parameters = 124439808
+[INFO|trainer.py:1637] 2022-12-03 21:44:00,184 >>   Continuing training from checkpoint, will skip to saved global_step
+[INFO|trainer.py:1638] 2022-12-03 21:44:00,184 >>   Continuing training from epoch 107
+[INFO|trainer.py:1639] 2022-12-03 21:44:00,184 >>   Continuing training from global step 84500
+
 {'loss': 8.0431, 'learning_rate': 4.970998635229893e-05, 'epoch': 0.64}
 {'loss': 7.4867, 'learning_rate': 4.94158548637583e-05, 'epoch': 1.27}
 {'loss': 7.322, 'learning_rate': 4.912172337521766e-05, 'epoch': 1.91}
 ......
+{'loss': 3.901, 'learning_rate': 2.5010882865076008e-05, 'epoch': 108.01}
+{'loss': 3.8959, 'learning_rate': 2.4863817120805686e-05, 'epoch': 108.64}
 ......
-......
-{'loss': 3.8686, 'learning_rate': 9.035719327968376e-07, 'epoch': 106.1}
-{'loss': 3.8685, 'learning_rate': 6.094404442562004e-07, 'epoch': 106.73}
-{'loss': 3.8678, 'learning_rate': 3.1530895571556306e-07, 'epoch': 107.37}
-
-{'train_runtime': 71919.9835, 'train_samples_per_second': 14.18, 'train_steps_per_second': 1.182, 'train_loss': 4.661963973798675, 'epoch': 108.0}
+{'loss': 3.1625, 'learning_rate': 4.6090404254317857e-07, 'epoch': 214.1}
+{'loss': 3.1592, 'learning_rate': 3.1413242976140055e-07, 'epoch': 214.74}
+{'loss': 3.1625, 'learning_rate': 1.6706668549108195e-07, 'epoch': 215.37}
+{'train_runtime': 72271.9602, 'train_samples_per_second': 28.222, 'train_steps_per_second': 2.352, 'train_loss': 1.7180436183842016, 'epoch': 216.0}
 ***** train metrics *****
-  epoch                    =       108.0
-  train_loss               =       4.662
-  train_runtime            = 19:58:39.98
+  epoch                    =       216.0
+  train_loss               =       1.718
+  train_runtime            = 20:04:31.96
   train_samples            =        9443
-  train_samples_per_second =       14.18
-  train_steps_per_second   =       1.182
-12/03/2022 15:51:42 - INFO - __main__ - *** Evaluate ***
-[INFO|trainer.py:2929] 2022-12-03 15:51:42,270 >> ***** Running Evaluation *****
-[INFO|trainer.py:2931] 2022-12-03 15:51:42,270 >>   Num examples = 283
-[INFO|trainer.py:2934] 2022-12-03 15:51:42,270 >>   Batch size = 12
-100%|██████████| 24/24 [00:07<00:00,  3.17it/s]
-[INFO|modelcard.py:449] 2022-12-03 15:51:52,077 >> Dropping the following result as it does not have all the necessary fields:
-{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}, 'metrics': [{'name': 'Accuracy', 'type': 'accuracy', 'value': 0.2100502721055507}]}
+  train_samples_per_second =      28.222
+  train_steps_per_second   =       2.352
+12/04/2022 17:48:35 - INFO - __main__ - *** Evaluate ***
+[INFO|trainer.py:2929] 2022-12-04 17:48:35,460 >> ***** Running Evaluation *****
+[INFO|trainer.py:2931] 2022-12-04 17:48:35,460 >>   Num examples = 283
+[INFO|trainer.py:2934] 2022-12-04 17:48:35,460 >>   Batch size = 12
+100%|██████████| 24/24 [00:07<00:00,  3.20it/s]
+[INFO|modelcard.py:449] 2022-12-04 17:48:45,840 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}, 'metrics': [{'name': 'Accuracy', 'type': 'accuracy', 'value': 0.20171768789804512}]}
 ***** eval metrics *****
-  epoch                   =      108.0
-  eval_accuracy           =     0.2101
-  eval_loss               =      6.889
-  eval_runtime            = 0:00:07.90
+  epoch                   =      216.0
+  eval_accuracy           =     0.2017
+  eval_loss               =     7.4687
+  eval_runtime            = 0:00:07.92
   eval_samples            =        283
-  eval_samples_per_second =      35.79
-  eval_steps_per_second   =      3.035
-  perplexity              =   981.4321
+  eval_samples_per_second =     35.695
+  eval_steps_per_second   =      3.027
+  perplexity              =  1752.2686
 ```