update model card README.md

README.md

@@ -11,9 +11,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt2_ft_police_articles
 
-This model was trained from scratch on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.6316
+This model is a fine-tuned version of [pdg/gpt2_ft_police_articles](https://huggingface.co/pdg/gpt2_ft_police_articles) on the None dataset.
 
 ## Model description
 
@@ -34,26 +32,14 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
 - train_batch_size: 2
-- eval_batch_size: 20
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 2
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.9126        | 1.0   | 500  | 1.8163          |
-| 1.7955        | 2.0   | 1000 | 1.7321          |
-| 1.6286        | 3.0   | 1500 | 1.6934          |
-| 1.5687        | 4.0   | 2000 | 1.6636          |
-| 1.5136        | 5.0   | 2500 | 1.6465          |
-| 1.4146        | 6.0   | 3000 | 1.6383          |
-| 1.3804        | 7.0   | 3500 | 1.6353          |
-| 1.3458        | 8.0   | 4000 | 1.6316          |
-| 1.287         | 9.0   | 4500 | 1.6415          |
-| 1.3406        | 10.0  | 5000 | 1.6409          |
 
 
 ### Framework versions