Model save

README.md

@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the emotion dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1218
-- Accuracy: 0.944
+- Loss: 0.1514
+- Accuracy: 0.928
 
 ## Model description
 
@@ -46,19 +46,16 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 7
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 250  | 0.3018          | 0.896    |
-| 0.6433        | 2.0   | 500  | 0.1710          | 0.932    |
-| 0.6433        | 3.0   | 750  | 0.1711          | 0.9315   |
-| 0.1878        | 4.0   | 1000 | 0.1389          | 0.937    |
-| 0.1878        | 5.0   | 1250 | 0.1400          | 0.938    |
-| 0.1453        | 6.0   | 1500 | 0.1290          | 0.941    |
-| 0.1453        | 7.0   | 1750 | 0.1218          | 0.944    |
+| No log        | 1.0   | 250  | 0.3008          | 0.897    |
+| 0.6384        | 2.0   | 500  | 0.1992          | 0.9265   |
+| 0.6384        | 3.0   | 750  | 0.1801          | 0.9245   |
+| 0.1923        | 4.0   | 1000 | 0.1514          | 0.928    |
 
 
 ### Framework versions