End of training

README.md

@@ -4,9 +4,6 @@ license: mit
 base_model: roberta-base
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
-- f1
 model-index:
 - name: cwe-parent-vulnerability-classification-roberta-base
   results: []
@@ -19,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6317
-- Accuracy: 0.4111
-- F1: 0.0069
+- Loss: 0.0746
+- F1 Macro: 0.0
+- Exact Match: 0.0
 
 ## Model description
 
@@ -41,23 +38,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 40
-- eval_batch_size: 40
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 5
-- label_smoothing_factor: 0.1
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 4.5723        | 1.0   | 20   | 4.0892          | 0.2397   | 0.0022 |
-| 4.0579        | 2.0   | 40   | 3.9983          | 0.2397   | 0.0022 |
-| 3.9765        | 3.0   | 60   | 3.9314          | 0.2448   | 0.0025 |
-| 3.9012        | 4.0   | 80   | 3.7501          | 0.3776   | 0.0064 |
-| 3.7555        | 5.0   | 100  | 3.6317          | 0.4111   | 0.0069 |
+| Training Loss | Epoch | Step | Validation Loss | F1 Macro | Exact Match |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|
+| 0.1439        | 1.0   | 25   | 0.1152          | 0.0      | 0.0         |
+| 0.1108        | 2.0   | 50   | 0.0925          | 0.0      | 0.0         |
+| 0.0936        | 3.0   | 75   | 0.0815          | 0.0      | 0.0         |
+| 0.078         | 4.0   | 100  | 0.0762          | 0.0      | 0.0         |
+| 0.0755        | 5.0   | 125  | 0.0746          | 0.0      | 0.0         |
 
 
 ### Framework versions

metrics.json

@@ -1,9 +1,9 @@
 {
-    "eval_loss": 3.6316609382629395,
-    "eval_accuracy": 0.4110824742268041,
-    "eval_f1": 0.006900071113956835,
-    "eval_runtime": 3.6016,
-    "eval_samples_per_second": 215.462,
-    "eval_steps_per_second": 5.553,
+    "eval_loss": 0.07459069043397903,
+    "eval_f1_macro": 0.0,
+    "eval_exact_match": 0.0,
+    "eval_runtime": 0.5137,
+    "eval_samples_per_second": 167.398,
+    "eval_steps_per_second": 5.839,
     "epoch": 5.0
 }