MistahCase
commited on
Commit
•
db0fea8
1
Parent(s):
80e021a
Update README.md
Browse files
README.md
CHANGED
@@ -12,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# distilroberta-base-testingSB
|
14 |
|
15 |
-
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Loss: 1.
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -42,10 +42,14 @@ The following hyperparameters were used during training:
|
|
42 |
- num_epochs: 3.0
|
43 |
|
44 |
### Training results
|
|
|
|
|
|
|
|
|
45 |
|
46 |
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
|:-------------:|:-----:|:----:|:---------------:|
|
48 |
-
|
|
49 |
| 1.3179 | 2.0 | 2922 | 1.3314 |
|
50 |
| 1.1931 | 3.0 | 4383 | 1.2530 |
|
51 |
|
12 |
|
13 |
# distilroberta-base-testingSB
|
14 |
|
15 |
+
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on a company specific, Danish dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.0403
|
18 |
|
19 |
## Model description
|
20 |
|
42 |
- num_epochs: 3.0
|
43 |
|
44 |
### Training results
|
45 |
+
Epoch Training Loss Validation Loss
|
46 |
+
1 0.988500 1.056376
|
47 |
+
2 0.996300 1.027803
|
48 |
+
3 0.990300 1.040270
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 0.98850 | 1.0 | 1461 | 1.5211 |
|
53 |
| 1.3179 | 2.0 | 2922 | 1.3314 |
|
54 |
| 1.1931 | 3.0 | 4383 | 1.2530 |
|
55 |
|