update model card README.md
Browse files
README.md
CHANGED
|
@@ -14,8 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Loss: 0.
|
| 18 |
-
- Roc Auc: 0.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -34,14 +34,14 @@ More information needed
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
-
- learning_rate: 0.
|
| 38 |
- train_batch_size: 2
|
| 39 |
- eval_batch_size: 4
|
| 40 |
- seed: 42
|
| 41 |
- distributed_type: IPU
|
| 42 |
- gradient_accumulation_steps: 39
|
| 43 |
- total_train_batch_size: 2496
|
| 44 |
-
- total_eval_batch_size:
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
|
| 46 |
- lr_scheduler_type: cosine
|
| 47 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.1176
|
| 18 |
+
- Roc Auc: 0.8005
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0001
|
| 38 |
- train_batch_size: 2
|
| 39 |
- eval_batch_size: 4
|
| 40 |
- seed: 42
|
| 41 |
- distributed_type: IPU
|
| 42 |
- gradient_accumulation_steps: 39
|
| 43 |
- total_train_batch_size: 2496
|
| 44 |
+
- total_eval_batch_size: 256
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
|
| 46 |
- lr_scheduler_type: cosine
|
| 47 |
- lr_scheduler_warmup_ratio: 0.1
|