Commit
·
e923c5c
1
Parent(s):
39f4ff6
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,15 +11,13 @@ model-index:
|
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
-
# bert-base-uncased-finetuned-semeval2020-task4a
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the ComVE dataset which was part of SemEval 2020 Task 4.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 0.2782
|
| 19 |
- Accuracy: 0.9040
|
| 20 |
|
| 21 |
-
## Training procedure
|
| 22 |
-
|
| 23 |
### Training hyperparameters
|
| 24 |
|
| 25 |
The following hyperparameters were used during training:
|
|
@@ -38,7 +36,6 @@ The following hyperparameters were used during training:
|
|
| 38 |
| No log | 1.0 | 344 | 0.2700 | 0.8940 |
|
| 39 |
| 0.349 | 2.0 | 688 | 0.2782 | 0.9040 |
|
| 40 |
|
| 41 |
-
|
| 42 |
### Framework versions
|
| 43 |
|
| 44 |
- Transformers 4.12.3
|
|
|
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
+
# bert-base-uncased-finetuned-semeval2020-task4a
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the ComVE dataset which was part of SemEval 2020 Task 4.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 0.2782
|
| 19 |
- Accuracy: 0.9040
|
| 20 |
|
|
|
|
|
|
|
| 21 |
### Training hyperparameters
|
| 22 |
|
| 23 |
The following hyperparameters were used during training:
|
|
|
|
| 36 |
| No log | 1.0 | 344 | 0.2700 | 0.8940 |
|
| 37 |
| 0.349 | 2.0 | 688 | 0.2782 | 0.9040 |
|
| 38 |
|
|
|
|
| 39 |
### Framework versions
|
| 40 |
|
| 41 |
- Transformers 4.12.3
|