Update README.md

README.md

@@ -88,6 +88,18 @@ bpe分词："vocab_size"=30000
 [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
 
+[INFO|trainer.py:1608] 2022-12-05 07:36:13,626 >> ***** Running training *****
+[INFO|trainer.py:1609] 2022-12-05 07:36:13,626 >>   Num examples = 9443
+[INFO|trainer.py:1610] 2022-12-05 07:36:13,626 >>   Num Epochs = 368
+[INFO|trainer.py:1611] 2022-12-05 07:36:13,626 >>   Instantaneous batch size per device = 12
+[INFO|trainer.py:1612] 2022-12-05 07:36:13,626 >>   Total train batch size (w. parallel, distributed & accumulation) = 12
+[INFO|trainer.py:1613] 2022-12-05 07:36:13,626 >>   Gradient Accumulation steps = 1
+[INFO|trainer.py:1614] 2022-12-05 07:36:13,626 >>   Total optimization steps = 289616
+[INFO|trainer.py:1616] 2022-12-05 07:36:13,627 >>   Number of trainable parameters = 124439808
+[INFO|trainer.py:1637] 2022-12-05 07:36:13,628 >>   Continuing training from checkpoint, will skip to saved global_step
+[INFO|trainer.py:1638] 2022-12-05 07:36:13,628 >>   Continuing training from epoch 255
+[INFO|trainer.py:1639] 2022-12-05 07:36:13,628 >>   Continuing training from global step 201000
+
 {'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}
@@ -99,27 +111,29 @@ bpe分词："vocab_size"=30000
 {'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}
+{'loss': 2.7087, 'learning_rate': 4.2642671675598036e-08, 'epoch': 367.85}
+{'train_runtime': 74859.0808, 'train_samples_per_second': 46.421, 'train_steps_per_second': 3.869, 'train_loss': 0.8725239146935282, 'epoch': 368.0}
 ***** train metrics *****
-  epoch                    =       216.0
-  train_loss               =       1.718
-  train_runtime            = 20:04:31.96
+  epoch                    =       368.0
+  train_loss               =      0.8725
+  train_runtime            = 20:47:39.08
   train_samples            =        9443
-  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
+  train_samples_per_second =      46.421
+  train_steps_per_second   =       3.869
+12/06/2022 04:23:55 - INFO - __main__ - *** Evaluate ***
+[INFO|trainer.py:2929] 2022-12-06 04:23:55,953 >> ***** Running Evaluation *****
+[INFO|trainer.py:2931] 2022-12-06 04:23:55,953 >>   Num examples = 283
+[INFO|trainer.py:2934] 2022-12-06 04:23:55,954 >>   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}]}
+[INFO|modelcard.py:449] 2022-12-06 04:24:04,760 >> 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': 0.19599206157122803}]}
 ***** eval metrics *****
-  epoch                   =      216.0
-  eval_accuracy           =     0.2017
-  eval_loss               =     7.4687
-  eval_runtime            = 0:00:07.92
+  epoch                   =      368.0
+  eval_accuracy           =      0.196
+  eval_loss               =     7.9524
+  eval_runtime            = 0:00:07.87
   eval_samples            =        283
-  eval_samples_per_second =     35.695
-  eval_steps_per_second   =      3.027
-  perplexity              =  1752.2686
+  eval_samples_per_second =      35.94
+  eval_steps_per_second   =      3.048
+  perplexity              =  2842.2766
 ```