<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
my_awesome_qa_model
This model is a fine-tuned version of deepset/roberta-base-squad2 on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 1.6395
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 250 | 0.5410 |
| 0.4883 | 2.0 | 500 | 0.5437 |
| 0.4883 | 3.0 | 750 | 0.5913 |
| 0.226 | 4.0 | 1000 | 0.7683 |
| 0.226 | 5.0 | 1250 | 0.8280 |
| 0.1266 | 6.0 | 1500 | 0.8528 |
| 0.1266 | 7.0 | 1750 | 0.9454 |
| 0.0868 | 8.0 | 2000 | 1.1004 |
| 0.0868 | 9.0 | 2250 | 1.2183 |
| 0.0608 | 10.0 | 2500 | 1.2702 |
| 0.0608 | 11.0 | 2750 | 1.3823 |
| 0.0427 | 12.0 | 3000 | 1.4355 |
| 0.0427 | 13.0 | 3250 | 1.4961 |
| 0.0318 | 14.0 | 3500 | 1.6042 |
| 0.0318 | 15.0 | 3750 | 1.6052 |
| 0.0271 | 16.0 | 4000 | 1.5435 |
| 0.0271 | 17.0 | 4250 | 1.6205 |
| 0.0215 | 18.0 | 4500 | 1.6248 |
| 0.0215 | 19.0 | 4750 | 1.6113 |
| 0.0157 | 20.0 | 5000 | 1.6395 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
