AlexanderHolmes0
commited on
Commit
•
360f4d1
1
Parent(s):
24806fb
End of training
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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Training results
|
49 |
|
@@ -53,7 +53,8 @@ The following hyperparameters were used during training:
|
|
53 |
| 0.6949 | 2.0 | 540 | 0.6968 | 0.6960 |
|
54 |
| 0.6949 | 3.0 | 810 | 0.7038 | 0.6750 |
|
55 |
| 0.5696 | 4.0 | 1080 | 0.7185 | 0.6674 |
|
56 |
-
| 0.5696 | 5.0 | 1350 | 0.
|
|
|
57 |
|
58 |
|
59 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.6531
|
21 |
+
- Accuracy: 0.7206
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 6
|
47 |
|
48 |
### Training results
|
49 |
|
|
|
53 |
| 0.6949 | 2.0 | 540 | 0.6968 | 0.6960 |
|
54 |
| 0.6949 | 3.0 | 810 | 0.7038 | 0.6750 |
|
55 |
| 0.5696 | 4.0 | 1080 | 0.7185 | 0.6674 |
|
56 |
+
| 0.5696 | 5.0 | 1350 | 0.7136 | 0.6607 |
|
57 |
+
| 0.49 | 6.0 | 1620 | 0.6531 | 0.7206 |
|
58 |
|
59 |
|
60 |
### Framework versions
|