Upload 5 files
Browse files## Training Metrics
**Evaluation Loss**: Converged from 0.543 to 0.502 over 1.8k training steps, demonstrating stable learning progression.
**Evaluation Precision**: Achieved 0.813 precision on the evaluation set, improving consistently from an initial 0.783.
**Evaluation Accuracy**: Reached 0.812 accuracy on the evaluation set, showing steady improvement from 0.778 during training.
**Training Loss**: Decreased from approximately 0.97 to 0.39, indicating effective model optimization throughout the training process.
**Gradient Norm**: Remained within normal ranges (3.0-9.0) throughout training, with final values around 9.0 suggesting continued active learning
- .gitattributes +5 -0
- eval_accuracy.png +3 -0
- eval_loss.png +3 -0
- eval_precision.png +3 -0
- train_grad_norm.png +3 -0
- train_loss.png +3 -0
|
@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
eval_accuracy.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
eval_loss.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
eval_precision.png filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
train_grad_norm.png filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
train_loss.png filter=lfs diff=lfs merge=lfs -text
|
|
Git LFS Details
|
|
Git LFS Details
|
|
Git LFS Details
|
|
Git LFS Details
|
|
Git LFS Details
|