deberta-large-finetuned-mrpc
This model is a fine-tuned version of microsoft/deberta-large on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5845
- Accuracy: 0.9044
- F1: 0.9307
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: 87
- 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 | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 230 | 0.3173 | 0.8848 | 0.9180 |
| No log | 2.0 | 460 | 0.3501 | 0.8799 | 0.9127 |
| 0.3071 | 3.0 | 690 | 0.5214 | 0.8946 | 0.9239 |
| 0.3071 | 4.0 | 920 | 0.5542 | 0.9118 | 0.9366 |
| 0.0619 | 5.0 | 1150 | 0.5845 | 0.9044 | 0.9307 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.13.3