metadata
license: apache-2.0
base_model: makhataei/qa-persian-bert-fa-base-uncased
tags:
- generated_from_trainer
datasets:
- persian_qa
model-index:
- name: qa-persian-bert-fa-base-uncased
results: []
qa-persian-bert-fa-base-uncased
This model is a fine-tuned version of makhataei/qa-persian-bert-fa-base-uncased on the persian_qa dataset. It achieves the following results on the evaluation set:
- Loss: 4.7021
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: 5e-05
- train_batch_size: 14
- eval_batch_size: 14
- 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 |
|---|---|---|---|
| 1.1038 | 1.0 | 644 | 1.9419 |
| 0.8384 | 2.0 | 1288 | 2.3613 |
| 0.5632 | 3.0 | 1932 | 2.3215 |
| 0.2658 | 4.0 | 2576 | 2.9592 |
| 0.1652 | 5.0 | 3220 | 3.2437 |
| 0.1497 | 6.0 | 3864 | 3.7557 |
| 0.0701 | 7.0 | 4508 | 4.0651 |
| 0.0398 | 8.0 | 5152 | 4.5260 |
| 0.0191 | 9.0 | 5796 | 4.7113 |
| 0.013 | 10.0 | 6440 | 4.7021 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0