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: 0.0068
-- Accuracy: 0.0126
-- F1: 0.0126
-- Bleu4: 0.0363
+- Loss: 0.0001
+- Accuracy: 0.0211
+- F1: 0.0211
+- Bleu4: 0.1608
 
 ## Model description
 
@@ -39,8 +39,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -50,11 +50,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Bleu4  |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|
-| 2.6008        | 1.0   | 687  | 0.0221          | 0.0173   | 0.0173 | 0.1220 |
-| 0.0455        | 2.0   | 1374 | 0.0171          | 0.0233   | 0.0233 | 0.1751 |
-| 0.0199        | 3.0   | 2061 | 0.0163          | 0.0154   | 0.0154 | 0.0993 |
-| 0.0119        | 4.0   | 2748 | 0.0068          | 0.0198   | 0.0198 | 0.1486 |
-| 0.0086        | 5.0   | 3435 | 0.0068          | 0.0126   | 0.0126 | 0.0363 |
+| 0.0908        | 1.0   | 1373 | 0.0184          | 0.0257   | 0.0257 | 0.1931 |
+| 0.0169        | 2.0   | 2746 | 0.0007          | 0.0207   | 0.0207 | 0.1567 |
+| 0.0033        | 3.0   | 4119 | 0.0058          | 0.0138   | 0.0138 | 0.0759 |
+| 0.0025        | 4.0   | 5492 | 0.0001          | 0.0211   | 0.0211 | 0.1608 |
 
 
 ### Framework versions