update model card README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -44,18 +48,9 @@ The following hyperparameters were used during training:
|
|
| 44 |
- num_epochs: 3.0
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
-
### Training results
|
| 48 |
-
|
| 49 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
-
| 2.7086 | 1.0 | 157 | 2.4897 |
|
| 52 |
-
| 2.5796 | 2.0 | 314 | 2.4230 |
|
| 53 |
-
| 2.5269 | 3.0 | 471 | 2.4354 |
|
| 54 |
-
|
| 55 |
-
|
| 56 |
### Framework versions
|
| 57 |
|
| 58 |
- Transformers 4.19.4
|
| 59 |
- Pytorch 1.11.0+cu113
|
| 60 |
-
- Datasets 2.3.
|
| 61 |
- Tokenizers 0.12.1
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- eval_loss: 3.1139
|
| 20 |
+
- eval_runtime: 1.8873
|
| 21 |
+
- eval_samples_per_second: 529.866
|
| 22 |
+
- eval_steps_per_second: 8.478
|
| 23 |
+
- step: 0
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 48 |
- num_epochs: 3.0
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
### Framework versions
|
| 52 |
|
| 53 |
- Transformers 4.19.4
|
| 54 |
- Pytorch 1.11.0+cu113
|
| 55 |
+
- Datasets 2.3.1
|
| 56 |
- Tokenizers 0.12.1
|