distilbert-base-uncased-finetuned
This model is a fine-tuned version of distilbert-base-uncased on the clinc_oos dataset. It achieves the following results on the evaluation set:
- Loss: 0.7734
- Accuracy: 0.9184
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: 48
- eval_batch_size: 48
- 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 |
|---|---|---|---|---|
| 4.2955 | 1.0 | 318 | 3.2914 | 0.7452 |
| 2.6342 | 2.0 | 636 | 1.8815 | 0.8313 |
| 1.5504 | 3.0 | 954 | 1.1547 | 0.8952 |
| 1.0151 | 4.0 | 1272 | 0.8580 | 0.9113 |
| 0.7936 | 5.0 | 1590 | 0.7734 | 0.9184 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.10.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1
- Downloads last month
- 3
Dataset used to train roscoyoon/distilbert-base-uncased-finetuned
Evaluation results
- Accuracy on clinc_oosself-reported0.918