update model card README.md

README.md

@@ -1,5 +1,4 @@
 ---
-license: mit
 tags:
 - generated_from_trainer
 model-index:
@@ -12,9 +11,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt2-wikitext2
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
+This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.1103
+- Loss: 5.5247
 
 ## Model description
 
@@ -34,20 +33,27 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
+- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 10.0
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 6.5575        | 1.0   | 2249 | 6.4694          |
-| 6.1905        | 2.0   | 4498 | 6.2004          |
-| 6.0149        | 3.0   | 6747 | 6.1103          |
+| 5.9217        | 1.0   | 563  | 5.9554          |
+| 5.7636        | 2.0   | 1126 | 5.8439          |
+| 5.6343        | 3.0   | 1689 | 5.7501          |
+| 5.536         | 4.0   | 2252 | 5.6839          |
+| 5.4445        | 5.0   | 2815 | 5.6307          |
+| 5.3763        | 6.0   | 3378 | 5.5920          |
+| 5.3048        | 7.0   | 3941 | 5.5625          |
+| 5.2132        | 8.0   | 4504 | 5.5434          |
+| 5.174         | 9.0   | 5067 | 5.5299          |
+| 5.1527        | 10.0  | 5630 | 5.5247          |
 
 
 ### Framework versions