metadata
license: cc-by-4.0
base_model: deepset/roberta-base-squad2
tags:
- generated_from_trainer
model-index:
- name: RobertaLr4.736874483017473e-06Wd0.009579411474848759E20
results: []
RobertaLr4.736874483017473e-06Wd0.009579411474848759E20
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: 0.1592
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: 4.736874483017473e-06
- 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.427 | 1.0 | 541 | 0.2540 |
| 0.1727 | 2.0 | 1082 | 0.2023 |
| 0.0003 | 3.0 | 1623 | 0.1707 |
| 0.0013 | 4.0 | 2164 | 0.1500 |
| 0.0 | 5.0 | 2705 | 0.1500 |
| 0.0006 | 6.0 | 3246 | 0.1682 |
| 0.0508 | 7.0 | 3787 | 0.1603 |
| 0.0038 | 8.0 | 4328 | 0.1417 |
| 0.7646 | 9.0 | 4869 | 0.1419 |
| 0.0 | 10.0 | 5410 | 0.1465 |
| 0.0001 | 11.0 | 5951 | 0.1470 |
| 0.0027 | 12.0 | 6492 | 0.1636 |
| 0.0 | 13.0 | 7033 | 0.1579 |
| 0.0 | 14.0 | 7574 | 0.1606 |
| 0.0001 | 15.0 | 8115 | 0.1647 |
| 0.0008 | 16.0 | 8656 | 0.1574 |
| 0.0 | 17.0 | 9197 | 0.1604 |
| 0.0 | 18.0 | 9738 | 0.1687 |
| 0.0 | 19.0 | 10279 | 0.1580 |
| 0.0 | 20.0 | 10820 | 0.1592 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.5.1
- Datasets 2.19.1
- Tokenizers 0.19.1