distilbert-base-uncased-finetuned-mnli
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: 0.5546
- Accuracy: 0.8188
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: 16
- eval_batch_size: 16
- 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 | Accuracy |
|---|---|---|---|---|
| 0.5153 | 1.0 | 24544 | 0.4999 | 0.8029 |
| 0.4194 | 2.0 | 49088 | 0.4788 | 0.8138 |
| 0.3065 | 3.0 | 73632 | 0.5546 | 0.8188 |
| 0.2172 | 4.0 | 98176 | 0.7237 | 0.8142 |
| 0.1784 | 5.0 | 122720 | 0.8463 | 0.8165 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.