update model card README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the wmt16 dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 1.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -41,8 +41,8 @@ The following hyperparameters were used during training:
|
|
| 41 |
- seed: 42
|
| 42 |
- distributed_type: IPU
|
| 43 |
- gradient_accumulation_steps: 128
|
| 44 |
-
- total_train_batch_size:
|
| 45 |
-
- total_eval_batch_size:
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- num_epochs: 1
|
|
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
-
|
|
| 56 |
|
| 57 |
|
| 58 |
### Framework versions
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the wmt16 dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.9824
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
| 41 |
- seed: 42
|
| 42 |
- distributed_type: IPU
|
| 43 |
- gradient_accumulation_steps: 128
|
| 44 |
+
- total_train_batch_size: 512
|
| 45 |
+
- total_eval_batch_size: 24
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- num_epochs: 1
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
+
| 1.4153 | 1.0 | 1192 | 1.9824 |
|
| 56 |
|
| 57 |
|
| 58 |
### Framework versions
|