roberta-base-finetuned-squad_roberta_5
This model is a fine-tuned version of roberta-base on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 1.1045
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 |
|---|---|---|---|
| 0.9063 | 1.0 | 5536 | 0.8850 |
| 0.6938 | 2.0 | 11072 | 0.8703 |
| 0.5392 | 3.0 | 16608 | 0.9224 |
| 0.4317 | 4.0 | 22144 | 1.0132 |
| 0.351 | 5.0 | 27680 | 1.1045 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- -