T1_usingF1_BL

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 base_model: aubmindlab/bert-base-arabertv02-twitter
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: Model4_arabertv2_base_T1_WS_A100_2nd_F1_BL
   results: []
@@ -15,6 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 # Model4_arabertv2_base_T1_WS_A100_2nd_F1_BL
 
 This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02-twitter](https://huggingface.co/aubmindlab/bert-base-arabertv02-twitter) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1605
+- F1 Micro: 0.8413
+- F1 Macro: 0.7546
+- Roc Auc: 0.8981
+- Accuracy: 0.8094
 
 ## Model description
 
@@ -41,6 +49,17 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 20
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Roc Auc | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-------:|:--------:|
+| 0.1692        | 1.0   | 507  | 0.1534          | 0.8371   | 0.7612   | 0.8950  | 0.7947   |
+| 0.0918        | 2.0   | 1014 | 0.1605          | 0.8413   | 0.7546   | 0.8981  | 0.8094   |
+| 0.0537        | 3.0   | 1521 | 0.1786          | 0.8360   | 0.7624   | 0.8990  | 0.8080   |
+| 0.0306        | 4.0   | 2028 | 0.1979          | 0.8347   | 0.7667   | 0.9001  | 0.8073   |
+| 0.0211        | 5.0   | 2535 | 0.2405          | 0.8279   | 0.7651   | 0.8948  | 0.8031   |
+
+
 ### Framework versions
 
 - Transformers 4.48.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e96a0de4361cd05b18ae3d04c47860bca76fbd2bde74883c9b3d9f7841a359
+oid sha256:628faad84eff4e1a3505071c2390f498a99852ba2148d2c325fc791f05ffec97
 size 540815376