xlm-roberta-base-finetuned-pquad-squad-finetuned-PersianQuAD_DeepseekQA_WS_QA-10epochs
This model is a fine-tuned version of Gholamreza/xlm-roberta-base-finetuned-pquad-squad on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0120
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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.635 | 1.0 | 2259 | 0.8399 |
| 0.4712 | 2.0 | 4518 | 0.8221 |
| 0.3627 | 3.0 | 6777 | 0.9052 |
| 0.2624 | 4.0 | 9036 | 1.1555 |
| 0.1988 | 5.0 | 11295 | 1.1706 |
| 0.1622 | 6.0 | 13554 | 1.2554 |
| 0.1391 | 7.0 | 15813 | 1.6088 |
| 0.1078 | 8.0 | 18072 | 1.7671 |
| 0.0696 | 9.0 | 20331 | 1.7681 |
| 0.0666 | 10.0 | 22590 | 2.0120 |
Framework versions
- Transformers 4.56.2
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1