update model card README.md
Browse files
README.md
CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 1.
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -49,17 +49,13 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
52 |
-
| 1.
|
53 |
-
| 1.
|
54 |
-
| 1.
|
55 |
-
| 1.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.6871 | 8.0 | 13704 | 1.2018 | 0.62 |
|
60 |
-
| 0.6137 | 9.0 | 15417 | 1.2758 | 0.615 |
|
61 |
-
| 0.55 | 10.0 | 17130 | 1.3500 | 0.595 |
|
62 |
-
| 0.4966 | 11.0 | 18843 | 1.4409 | 0.61 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.3921
|
21 |
+
- Accuracy: 0.544
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
52 |
+
| 1.4555 | 1.0 | 1682 | 1.2794 | 0.504 |
|
53 |
+
| 1.2833 | 2.0 | 3364 | 1.2108 | 0.526 |
|
54 |
+
| 1.1745 | 3.0 | 5046 | 1.2324 | 0.566 |
|
55 |
+
| 1.0688 | 4.0 | 6728 | 1.2353 | 0.548 |
|
56 |
+
| 0.9659 | 5.0 | 8410 | 1.2815 | 0.556 |
|
57 |
+
| 0.8642 | 6.0 | 10092 | 1.3926 | 0.554 |
|
58 |
+
| 0.7652 | 7.0 | 11774 | 1.3921 | 0.544 |
|
|
|
|
|
|
|
|
|
59 |
|
60 |
|
61 |
### Framework versions
|