metadata
license: apache-2.0
base_model: makhataei/qa-persian-bert-fa-base-uncased
tags:
- generated_from_trainer
datasets:
- parsinlu_reading_comprehension
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 parsinlu_reading_comprehension dataset. It achieves the following results on the evaluation set:
- Loss: 5.4907
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: 0.0005
- 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 |
|---|---|---|---|
| 5.4237 | 1.0 | 86 | 5.4907 |
| 5.4024 | 2.0 | 172 | 5.4907 |
| 5.4299 | 3.0 | 258 | 5.4907 |
| 5.432 | 4.0 | 344 | 5.4907 |
| 5.4115 | 5.0 | 430 | 5.4907 |
| 5.3933 | 6.0 | 516 | 5.4907 |
| 5.4077 | 7.0 | 602 | 5.4907 |
| 5.3919 | 8.0 | 688 | 5.4907 |
| 5.4018 | 9.0 | 774 | 5.4907 |
| 5.4428 | 10.0 | 860 | 5.4907 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0