QNLI
This model is a fine-tuned version of FacebookAI/roberta-large on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.2250
- Accuracy: 0.9451
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: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2269 | 1.0 | 1637 | 0.1639 | 0.9363 |
| 0.1637 | 2.0 | 3274 | 0.1718 | 0.9372 |
| 0.0977 | 3.0 | 4911 | 0.1788 | 0.9425 |
| 0.0672 | 4.0 | 6548 | 0.2250 | 0.9451 |
| 0.0437 | 5.0 | 8185 | 0.2863 | 0.9431 |
| 0.0289 | 6.0 | 9822 | 0.3216 | 0.9438 |
Framework versions
- Transformers 4.43.3
- Pytorch 1.11.0+cu113
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 6
Model tree for du33169/roberta-large-finetuned-GLUE-QNLI
Base model
FacebookAI/roberta-large