distilbert-base-uncased-finetuned-stsb
This model is a fine-tuned version of distilbert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5389
- Pearson: 0.8738
- Spearmanr: 0.8697
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
|---|---|---|---|---|---|
| 1.1963 | 1.0 | 719 | 0.7779 | 0.8591 | 0.8582 |
| 0.5834 | 2.0 | 1438 | 0.6198 | 0.8684 | 0.8660 |
| 0.2718 | 3.0 | 2157 | 0.5497 | 0.8720 | 0.8684 |
| 0.2302 | 4.0 | 2876 | 0.5389 | 0.8738 | 0.8697 |
| 0.1505 | 5.0 | 3595 | 0.5508 | 0.8718 | 0.8679 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 105
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for hoangthan/distilbert-base-uncased-finetuned-stsb
Base model
distilbert/distilbert-base-uncased