NER Training

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dslim/distilbert-NER](https://huggingface.co/dslim/distilbert-NER) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0483
-- F1 Score: 0.9453
+- Loss: 0.0514
+- F1 Score: 0.9505
 
 ## Model description
 
@@ -48,16 +48,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | F1 Score |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.1069        | 1.0   | 1534  | 0.0825          | 0.8414   |
-| 0.0553        | 2.0   | 3068  | 0.0587          | 0.8826   |
-| 0.0369        | 3.0   | 4602  | 0.0472          | 0.9125   |
-| 0.018         | 4.0   | 6136  | 0.0465          | 0.9206   |
-| 0.0127        | 5.0   | 7670  | 0.0447          | 0.9351   |
-| 0.0057        | 6.0   | 9204  | 0.0473          | 0.9377   |
-| 0.0045        | 7.0   | 10738 | 0.0465          | 0.9427   |
-| 0.0019        | 8.0   | 12272 | 0.0500          | 0.9409   |
-| 0.0026        | 9.0   | 13806 | 0.0486          | 0.9446   |
-| 0.0015        | 10.0  | 15340 | 0.0483          | 0.9453   |
+| 0.1174        | 1.0   | 1534  | 0.0913          | 0.8434   |
+| 0.0605        | 2.0   | 3068  | 0.0632          | 0.8953   |
+| 0.0394        | 3.0   | 4602  | 0.0514          | 0.9170   |
+| 0.0205        | 4.0   | 6136  | 0.0508          | 0.9291   |
+| 0.0133        | 5.0   | 7670  | 0.0484          | 0.9378   |
+| 0.0066        | 6.0   | 9204  | 0.0500          | 0.9419   |
+| 0.0046        | 7.0   | 10738 | 0.0502          | 0.9475   |
+| 0.002         | 8.0   | 12272 | 0.0503          | 0.9487   |
+| 0.0023        | 9.0   | 13806 | 0.0509          | 0.9492   |
+| 0.0011        | 10.0  | 15340 | 0.0514          | 0.9505   |
 
 
 ### Framework versions