roberta-base-finetuned-squad8000
This model is a fine-tuned version of roberta-base on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 0.8537
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8461 | 1.0 | 6063 | 0.8284 |
| 0.6586 | 2.0 | 12126 | 0.8036 |
| 0.5178 | 3.0 | 18189 | 0.8537 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3