Tushar Roy
commited on
Commit
•
a8ed9ea
1
Parent(s):
1c7b77d
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 21 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Perplexity: 11.0482
|
| 24 |
-
-
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -41,11 +40,10 @@ More information needed
|
|
| 41 |
### Training hyperparameters
|
| 42 |
|
| 43 |
The following hyperparameters were used during training:
|
| 44 |
-
- learning_rate: 2e-05
|
| 45 |
- train_batch_size: 64
|
| 46 |
- eval_batch_size: 64
|
| 47 |
- seed: 42
|
| 48 |
-
- optimizer:
|
| 49 |
- lr_scheduler_type: linear
|
| 50 |
- num_epochs: 3.0
|
| 51 |
|
|
|
|
| 21 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Perplexity: 11.0482
|
|
|
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 40 |
### Training hyperparameters
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
|
|
|
| 43 |
- train_batch_size: 64
|
| 44 |
- eval_batch_size: 64
|
| 45 |
- seed: 42
|
| 46 |
+
- optimizer: AdamW with lr=5e-5
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- num_epochs: 3.0
|
| 49 |
|