RobertaLr1e-8Wd0.01
This model is a fine-tuned version of deepset/roberta-base-squad2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9040
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: 1e-08
- 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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.3277 | 1.0 | 72 | 4.3899 |
| 3.0377 | 2.0 | 144 | 4.2966 |
| 3.7413 | 3.0 | 216 | 4.2134 |
| 2.8379 | 4.0 | 288 | 4.1416 |
| 3.8044 | 5.0 | 360 | 4.0798 |
| 3.788 | 6.0 | 432 | 4.0279 |
| 4.4786 | 7.0 | 504 | 3.9849 |
| 4.2643 | 8.0 | 576 | 3.9515 |
| 3.3807 | 9.0 | 648 | 3.9273 |
| 5.0268 | 10.0 | 720 | 3.9121 |
| 2.4943 | 11.0 | 792 | 3.9052 |
| 3.1589 | 12.0 | 864 | 3.9040 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.4.0
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 1