qa_bert-base-multilingual-cased-finetuned-squad
This model is a fine-tuned version of salti/bert-base-multilingual-cased-finetuned-squad on the subjqa dataset. It achieves the following results on the evaluation set:
- Loss: 1.8327
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-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 |
|---|---|---|---|
| 2.6495 | 1.0 | 81 | 2.3399 |
| 1.8855 | 2.0 | 162 | 2.0887 |
| 1.7301 | 3.0 | 243 | 1.9716 |
| 1.668 | 4.0 | 324 | 1.9215 |
| 1.6121 | 5.0 | 405 | 1.8922 |
| 1.5587 | 6.0 | 486 | 1.8767 |
| 1.5236 | 7.0 | 567 | 1.8614 |
| 1.4978 | 8.0 | 648 | 1.8464 |
| 1.4769 | 9.0 | 729 | 1.8434 |
| 1.4612 | 10.0 | 810 | 1.8364 |
| 1.4215 | 11.0 | 891 | 1.8357 |
| 1.4132 | 12.0 | 972 | 1.8330 |
| 1.394 | 13.0 | 1053 | 1.8325 |
| 1.3798 | 14.0 | 1134 | 1.8348 |
| 1.3786 | 15.0 | 1215 | 1.8326 |
| 1.3668 | 16.0 | 1296 | 1.8339 |
| 1.3545 | 17.0 | 1377 | 1.8338 |
| 1.3581 | 18.0 | 1458 | 1.8323 |
| 1.3449 | 19.0 | 1539 | 1.8324 |
| 1.3443 | 20.0 | 1620 | 1.8327 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
- Downloads last month
- 8