teacher_electra_small
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -47,14 +47,14 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:-----:|:---------------:|
|
50 |
-
| 0.
|
51 |
-
| 0.
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.3884
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:-----:|:---------------:|
|
50 |
+
| 0.8696 | 0.35 | 3000 | 0.5508 |
|
51 |
+
| 0.5071 | 0.71 | 6000 | 0.4578 |
|
52 |
+
| 0.448 | 1.06 | 9000 | 0.4210 |
|
53 |
+
| 0.4084 | 1.41 | 12000 | 0.4109 |
|
54 |
+
| 0.3878 | 1.77 | 15000 | 0.3913 |
|
55 |
+
| 0.3832 | 2.12 | 18000 | 0.3884 |
|
56 |
+
| 0.3529 | 2.47 | 21000 | 0.3900 |
|
57 |
+
| 0.3492 | 2.83 | 24000 | 0.3884 |
|
58 |
|
59 |
|
60 |
### Framework versions
|