metadata
license: cc-by-4.0
base_model: deepset/roberta-base-squad2
tags:
- generated_from_trainer
model-index:
- name: RobertaLr1e-8Wd0.02E20
results: []
RobertaLr1e-8Wd0.02E20
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: 3.2435
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9511 | 1.0 | 72 | 3.9642 |
| 2.6869 | 2.0 | 144 | 3.8774 |
| 3.0261 | 3.0 | 216 | 3.7963 |
| 2.659 | 4.0 | 288 | 3.7220 |
| 5.0333 | 5.0 | 360 | 3.6540 |
| 4.4433 | 6.0 | 432 | 3.5911 |
| 4.8192 | 7.0 | 504 | 3.5341 |
| 3.7868 | 8.0 | 576 | 3.4826 |
| 2.4543 | 9.0 | 648 | 3.4379 |
| 2.4081 | 10.0 | 720 | 3.3981 |
| 4.04 | 11.0 | 792 | 3.3631 |
| 3.5419 | 12.0 | 864 | 3.3344 |
| 2.8603 | 13.0 | 936 | 3.3092 |
| 4.191 | 14.0 | 1008 | 3.2884 |
| 3.1615 | 15.0 | 1080 | 3.2721 |
| 2.8836 | 16.0 | 1152 | 3.2593 |
| 4.573 | 17.0 | 1224 | 3.2509 |
| 2.5001 | 18.0 | 1296 | 3.2459 |
| 3.3777 | 19.0 | 1368 | 3.2438 |
| 2.5643 | 20.0 | 1440 | 3.2435 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.4.0
- Datasets 2.20.0
- Tokenizers 0.19.1