update model card README.md

README.md

@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # electricidad-base-generator-fake-news
 
-This model is a fine-tuned version of [mrm8488/electricidad-base-generator](https://huggingface.co/mrm8488/electricidad-base-generator) on an Fake_news_train dataset.
+This model is a fine-tuned version of [mrm8488/electricidad-base-generator](https://huggingface.co/mrm8488/electricidad-base-generator) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4223
+- Loss: 0.0067
 - Accuracy: 1.0
 
 ## Model description
@@ -36,8 +36,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 5
-- eval_batch_size: 5
+- train_batch_size: 10
+- eval_batch_size: 10
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -47,11 +47,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4358        | 1.0   | 38   | 0.4223          | 1.0      |
-| 0.4307        | 2.0   | 76   | 0.4223          | 1.0      |
-| 0.4352        | 3.0   | 114  | 0.4223          | 1.0      |
-| 0.4369        | 4.0   | 152  | 0.4223          | 1.0      |
-| 0.4328        | 5.0   | 190  | 0.4223          | 1.0      |
+| 0.1136        | 1.0   | 180  | 0.0852          | 1.0      |
+| 0.0267        | 2.0   | 360  | 0.0219          | 1.0      |
+| 0.0132        | 3.0   | 540  | 0.0108          | 1.0      |
+| 0.0091        | 4.0   | 720  | 0.0075          | 1.0      |
+| 0.0077        | 5.0   | 900  | 0.0067          | 1.0      |
 
 
 ### Framework versions