update model card README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Loss: 2.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -39,14 +39,16 @@ The following hyperparameters were used during training:
|
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
-
- num_epochs:
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
| 46 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
-
| 3.
|
| 49 |
-
| 2.
|
|
|
|
|
|
|
| 50 |
|
| 51 |
|
| 52 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 2.6443
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 20
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
| 46 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| 3.2125 | 4.35 | 100 | 2.2853 |
|
| 49 |
+
| 2.4165 | 8.7 | 200 | 2.2326 |
|
| 50 |
+
| 2.1551 | 13.04 | 300 | 2.2034 |
|
| 51 |
+
| 2.0115 | 17.39 | 400 | 2.6443 |
|
| 52 |
|
| 53 |
|
| 54 |
### Framework versions
|