amritpuhan
commited on
Commit
•
f63090e
1
Parent(s):
90f7e68
End of training
Browse files
README.md
CHANGED
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the swag dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
-
- Accuracy: 0.
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -46,18 +46,22 @@ The following hyperparameters were used during training:
|
|
46 |
- seed: 42
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
49 |
-
- num_epochs:
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch | Step
|
54 |
-
|
55 |
-
| 1.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
|
|
|
|
|
|
|
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the swag dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.6557
|
24 |
+
- Accuracy: 0.7483
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
46 |
- seed: 42
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 10
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
55 |
+
| 1.0316 | 1.0 | 1150 | 0.8202 | 0.6860 |
|
56 |
+
| 0.9261 | 2.0 | 2300 | 0.7423 | 0.7144 |
|
57 |
+
| 0.8862 | 3.0 | 3450 | 0.7114 | 0.7268 |
|
58 |
+
| 0.8612 | 4.0 | 4600 | 0.6924 | 0.7347 |
|
59 |
+
| 0.8637 | 5.0 | 5750 | 0.6819 | 0.7393 |
|
60 |
+
| 0.8541 | 6.0 | 6900 | 0.6691 | 0.7441 |
|
61 |
+
| 0.8369 | 7.0 | 8050 | 0.6635 | 0.7464 |
|
62 |
+
| 0.8349 | 8.0 | 9200 | 0.6591 | 0.7475 |
|
63 |
+
| 0.8302 | 9.0 | 10350 | 0.6572 | 0.7483 |
|
64 |
+
| 0.8333 | 10.0 | 11500 | 0.6557 | 0.7483 |
|
65 |
|
66 |
|
67 |
### Framework versions
|