<!-- 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. -->
mdeberta_Quran_qa
This model is a fine-tuned version of timpal0l/mdeberta-v3-base-squad2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.6248
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: 8
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 89 | 2.2395 |
| No log | 2.0 | 178 | 2.3282 |
| No log | 3.0 | 267 | 2.4226 |
| No log | 4.0 | 356 | 2.6551 |
| No log | 5.0 | 445 | 2.9332 |
| 1.0317 | 6.0 | 534 | 3.2124 |
| 1.0317 | 7.0 | 623 | 3.2915 |
| 1.0317 | 8.0 | 712 | 3.5401 |
| 1.0317 | 9.0 | 801 | 3.6132 |
| 1.0317 | 10.0 | 890 | 3.6248 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
