update model card README.md

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: neuralsentry/starencoder-git-commits-mlm
+license: apache-2.0
+base_model: neuralsentry/distilbert-git-commits-mlm
 tags:
 - generated_from_trainer
 metrics:
@@ -17,14 +18,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # starencoder-vulnfix-classification
 
-This model is a fine-tuned version of [neuralsentry/starencoder-git-commits-mlm](https://huggingface.co/neuralsentry/starencoder-git-commits-mlm) on the None dataset.
+This model is a fine-tuned version of [neuralsentry/distilbert-git-commits-mlm](https://huggingface.co/neuralsentry/distilbert-git-commits-mlm) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2327
-- Accuracy: 0.9274
-- Precision: 0.9691
-- Recall: 0.9199
-- F1: 0.9438
-- Roc Auc: 0.9310
+- Loss: 0.2247
+- Accuracy: 0.9087
+- Precision: 0.9401
+- Recall: 0.9210
+- F1: 0.9304
+- Roc Auc: 0.9027
 
 ## Model description
 
@@ -44,8 +45,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 128
-- eval_batch_size: 128
+- train_batch_size: 256
+- eval_batch_size: 256
 - seed: 420
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -55,7 +56,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Roc Auc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-------:|
-| 0.2872        | 1.57  | 66   | 0.2017          | 0.9177   | 0.9439    | 0.9312 | 0.9375 | 0.9111  |
+| 0.36          | 1.57  | 33   | 0.2265          | 0.9124   | 0.9315    | 0.9368 | 0.9342 | 0.9006  |
 
 
 ### Framework versions