update model card README.md
Browse files
README.md
CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the swag dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Accuracy: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -44,8 +44,8 @@ The following hyperparameters were used during training:
|
|
44 |
- seed: 42
|
45 |
- distributed_type: IPU
|
46 |
- gradient_accumulation_steps: 16
|
47 |
-
- total_train_batch_size:
|
48 |
-
- total_eval_batch_size:
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
- num_epochs: 3
|
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the swag dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.5093
|
22 |
+
- Accuracy: 0.8302
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
44 |
- seed: 42
|
45 |
- distributed_type: IPU
|
46 |
- gradient_accumulation_steps: 16
|
47 |
+
- total_train_batch_size: 32
|
48 |
+
- total_eval_batch_size: 10
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
- num_epochs: 3
|
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
58 |
+
| 0.9911 | 1.0 | 2298 | 0.5308 | 0.7929 |
|
59 |
+
| 0.3024 | 2.0 | 4596 | 0.4780 | 0.8161 |
|
60 |
+
| 0.0785 | 3.0 | 6894 | 0.5093 | 0.8302 |
|
61 |
|
62 |
|
63 |
### Framework versions
|