salbatarni
/

arabert_baseline_development_task4_fold0

TensorBoard

Safetensors

bert

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

salbatarni commited on Aug 29

Commit

68e0cf2

•

1 Parent(s): 7423a97

End of training

Browse files

Files changed (1) hide show

README.md +17 -22

README.md CHANGED Viewed

@@ -3,20 +3,20 @@ base_model: aubmindlab/bert-base-arabertv02
 tags:
 - generated_from_trainer
 model-index:
-- name: arabert_baseline_development_task3_fold1
   results: []
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
-# arabert_baseline_development_task3_fold1
 This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2282
-- Qwk: 0.0
-- Mse: 0.2300
 ## Model description
@@ -45,23 +45,18 @@ The following hyperparameters were used during training:
 ### Training results
-| Training Loss | Epoch  | Step | Validation Loss | Qwk     | Mse    |
-|:-------------:|:------:|:----:|:---------------:|:-------:|:------:|
-| No log        | 0.6667 | 2    | 2.8377          | 0.0075  | 2.8075 |
-| No log        | 1.3333 | 4    | 0.7850          | -0.0722 | 0.7741 |
-| No log        | 2.0    | 6    | 0.2436          | 0.0     | 0.2359 |
-| No log        | 2.6667 | 8    | 0.2726          | -0.3562 | 0.2744 |
-| No log        | 3.3333 | 10   | 0.2421          | 0.0     | 0.2449 |
-| No log        | 4.0    | 12   | 0.2542          | 0.0     | 0.2555 |
-| No log        | 4.6667 | 14   | 0.2669          | 0.0     | 0.2677 |
-| No log        | 5.3333 | 16   | 0.2579          | 0.0     | 0.2592 |
-| No log        | 6.0    | 18   | 0.2389          | 0.0     | 0.2407 |
-| No log        | 6.6667 | 20   | 0.2143          | 0.0     | 0.2176 |
-| No log        | 7.3333 | 22   | 0.2121          | 0.0     | 0.2162 |
-| No log        | 8.0    | 24   | 0.2173          | 0.0     | 0.2199 |
-| No log        | 8.6667 | 26   | 0.2240          | 0.0     | 0.2258 |
-| No log        | 9.3333 | 28   | 0.2288          | 0.0     | 0.2304 |
-| No log        | 10.0   | 30   | 0.2282          | 0.0     | 0.2300 |
 ### Framework versions

 tags:
 - generated_from_trainer
 model-index:
+- name: arabert_baseline_development_task4_fold0
   results: []
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
+# arabert_baseline_development_task4_fold0
 This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.4483
+- Qwk: 0.6
+- Mse: 0.4483
 ## Model description
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss | Qwk     | Mse    |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
+| No log        | 1.0   | 2    | 3.6202          | -0.0256 | 3.6202 |
+| No log        | 2.0   | 4    | 1.3484          | 0.0667  | 1.3484 |
+| No log        | 3.0   | 6    | 0.4149          | 0.28    | 0.4149 |
+| No log        | 4.0   | 8    | 0.4977          | 0.1765  | 0.4977 |
+| No log        | 5.0   | 10   | 0.6053          | 0.1765  | 0.6053 |
+| No log        | 6.0   | 12   | 0.6080          | 0.25    | 0.6080 |
+| No log        | 7.0   | 14   | 0.5578          | 0.7143  | 0.5578 |
+| No log        | 8.0   | 16   | 0.4912          | 0.6     | 0.4912 |
+| No log        | 9.0   | 18   | 0.4606          | 0.6     | 0.4606 |
+| No log        | 10.0  | 20   | 0.4483          | 0.6     | 0.4483 |
 ### Framework versions