metadata
license: apache-2.0
base_model: makhataei/qa-persian-albert-fa-zwnj-base-v2
tags:
- generated_from_trainer
datasets:
- pquad
model-index:
- name: qa-persian-albert-fa-zwnj-base-v2
results: []
qa-persian-albert-fa-zwnj-base-v2
This model is a fine-tuned version of makhataei/qa-persian-albert-fa-zwnj-base-v2 on the pquad dataset. It achieves the following results on the evaluation set:
- Loss: 1.4440
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: 0.0001
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5731 | 0.12 | 500 | 1.6899 |
| 1.4759 | 0.25 | 1000 | 1.4951 |
| 1.3844 | 0.38 | 1500 | 1.5161 |
| 1.3116 | 0.5 | 2000 | 1.3618 |
| 1.3055 | 0.62 | 2500 | 1.3795 |
| 1.2364 | 0.75 | 3000 | 1.3386 |
| 1.2189 | 0.88 | 3500 | 1.3131 |
| 1.1737 | 1.0 | 4000 | 1.2202 |
| 1.0047 | 1.12 | 4500 | 1.2268 |
| 0.9573 | 1.25 | 5000 | 1.3119 |
| 0.978 | 1.38 | 5500 | 1.1918 |
| 0.9655 | 1.5 | 6000 | 1.1896 |
| 0.9505 | 1.62 | 6500 | 1.1730 |
| 0.9379 | 1.75 | 7000 | 1.1215 |
| 0.9237 | 1.88 | 7500 | 1.0691 |
| 0.8911 | 2.0 | 8000 | 1.0819 |
| 0.6874 | 2.12 | 8500 | 1.1670 |
| 0.6919 | 2.25 | 9000 | 1.1506 |
| 0.7118 | 2.38 | 9500 | 1.1352 |
| 0.7062 | 2.5 | 10000 | 1.1762 |
| 0.7077 | 2.62 | 10500 | 1.1072 |
| 0.7055 | 2.75 | 11000 | 1.0788 |
| 0.6869 | 2.88 | 11500 | 1.0863 |
| 0.6707 | 3.0 | 12000 | 1.0167 |
| 0.4597 | 3.12 | 12500 | 1.2769 |
| 0.4652 | 3.25 | 13000 | 1.1891 |
| 0.4673 | 3.38 | 13500 | 1.1466 |
| 0.4644 | 3.5 | 14000 | 1.1818 |
| 0.4701 | 3.62 | 14500 | 1.1939 |
| 0.4765 | 3.75 | 15000 | 1.1518 |
| 0.4537 | 3.88 | 15500 | 1.1528 |
| 0.4164 | 4.0 | 16000 | 1.2239 |
| 0.2465 | 4.12 | 16500 | 1.4501 |
| 0.2495 | 4.25 | 17000 | 1.3717 |
| 0.263 | 4.38 | 17500 | 1.4030 |
| 0.2423 | 4.5 | 18000 | 1.4249 |
| 0.2297 | 4.62 | 18500 | 1.4387 |
| 0.227 | 4.75 | 19000 | 1.4600 |
| 0.239 | 4.88 | 19500 | 1.4452 |
| 0.2307 | 5.0 | 20000 | 1.4440 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0