update model card README.md

README.md

@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0002
-- Accuracy: 0.0215
-- F1: 0.0215
-- Bleu4: 0.1640
+- Loss: 14.6482
+- Accuracy: 0.0
+- F1: 0.0
+- Bleu4: 0.0592
 
 ## Model description
 
@@ -44,22 +44,21 @@ 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: 5
+- num_epochs: 100
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Bleu4  |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|
-| 0.1044        | 1.0   | 1373 | 0.0185          | 0.0146   | 0.0146 | 0.0889 |
-| 0.0129        | 2.0   | 2746 | 0.0070          | 0.0243   | 0.0243 | 0.1871 |
-| 0.0031        | 3.0   | 4119 | 0.0003          | 0.0215   | 0.0215 | 0.1640 |
-| 0.002         | 4.0   | 5492 | 0.0003          | 0.0215   | 0.0215 | 0.1640 |
-| 0.0011        | 5.0   | 6865 | 0.0002          | 0.0215   | 0.0215 | 0.1640 |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1  | Bleu4  |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---:|:------:|
+| No log        | 1.0   | 1    | 16.4835         | 0.0      | 0.0 | 0.1118 |
+| No log        | 2.0   | 2    | 15.8217         | 0.0      | 0.0 | 0.0940 |
+| No log        | 3.0   | 3    | 15.2096         | 0.0      | 0.0 | 0.0648 |
+| No log        | 4.0   | 4    | 14.6482         | 0.0      | 0.0 | 0.0592 |
 
 
 ### Framework versions
 
 - Transformers 4.25.1
-- Pytorch 1.13.0+cu117
+- Pytorch 1.13.0
 - Datasets 2.7.1
 - Tokenizers 0.13.2