Rami
/

multi-label-class-classification-on-github-issues

@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [neuralmagic/oBERT-12-upstream-pruned-unstructured-97](https://huggingface.co/neuralmagic/oBERT-12-upstream-pruned-unstructured-97) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1041
-- Micro f1: 0.6590
-- Macro f1: 0.0721
 ## Model description
@@ -47,22 +47,22 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Micro f1 | Macro f1 |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
-| No log        | 1.0   | 49   | 0.2840          | 0.3791   | 0.0172   |
-| No log        | 2.0   | 98   | 0.1717          | 0.3791   | 0.0172   |
-| No log        | 3.0   | 147  | 0.1436          | 0.3796   | 0.0173   |
-| No log        | 4.0   | 196  | 0.1335          | 0.4608   | 0.0299   |
-| No log        | 5.0   | 245  | 0.1250          | 0.5254   | 0.0371   |
-| No log        | 6.0   | 294  | 0.1179          | 0.6312   | 0.0674   |
-| No log        | 7.0   | 343  | 0.1125          | 0.6097   | 0.0549   |
-| No log        | 8.0   | 392  | 0.1089          | 0.6368   | 0.0659   |
-| No log        | 9.0   | 441  | 0.1061          | 0.6562   | 0.0715   |
-| No log        | 10.0  | 490  | 0.1055          | 0.6525   | 0.0706   |
-| 0.1604        | 11.0  | 539  | 0.1030          | 0.6636   | 0.0723   |
-| 0.1604        | 12.0  | 588  | 0.1043          | 0.6526   | 0.0708   |
-| 0.1604        | 13.0  | 637  | 0.1039          | 0.6561   | 0.0709   |
-| 0.1604        | 14.0  | 686  | 0.1050          | 0.6576   | 0.0712   |
-| 0.1604        | 15.0  | 735  | 0.1060          | 0.6530   | 0.0749   |
-| 0.1604        | 16.0  | 784  | 0.1056          | 0.6606   | 0.0827   |
 ### Framework versions

 This model is a fine-tuned version of [neuralmagic/oBERT-12-upstream-pruned-unstructured-97](https://huggingface.co/neuralmagic/oBERT-12-upstream-pruned-unstructured-97) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.1077
+- Micro f1: 0.6520
+- Macro f1: 0.0704
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Micro f1 | Macro f1 |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
+| No log        | 1.0   | 49   | 0.2835          | 0.3791   | 0.0172   |
+| No log        | 2.0   | 98   | 0.1710          | 0.3791   | 0.0172   |
+| No log        | 3.0   | 147  | 0.1433          | 0.3791   | 0.0172   |
+| No log        | 4.0   | 196  | 0.1333          | 0.4540   | 0.0291   |
+| No log        | 5.0   | 245  | 0.1247          | 0.5206   | 0.0352   |
+| No log        | 6.0   | 294  | 0.1173          | 0.6003   | 0.0541   |
+| No log        | 7.0   | 343  | 0.1125          | 0.6315   | 0.0671   |
+| No log        | 8.0   | 392  | 0.1095          | 0.6439   | 0.0699   |
+| No log        | 9.0   | 441  | 0.1072          | 0.6531   | 0.0713   |
+| No log        | 10.0  | 490  | 0.1075          | 0.6397   | 0.0695   |
+| 0.1605        | 11.0  | 539  | 0.1074          | 0.6591   | 0.0711   |
+| 0.1605        | 12.0  | 588  | 0.1043          | 0.6462   | 0.0703   |
+| 0.1605        | 13.0  | 637  | 0.1049          | 0.6541   | 0.0709   |
+| 0.1605        | 14.0  | 686  | 0.1051          | 0.6524   | 0.0713   |
+| 0.1605        | 15.0  | 735  | 0.1061          | 0.6535   | 0.0770   |
+| 0.1605        | 16.0  | 784  | 0.1034          | 0.6511   | 0.0708   |
 ### Framework versions