metadata
tags:
- generated_from_trainer
model-index:
- name: electra-qa-3-finetuned-viet-qa
results: []
electra-qa-3-finetuned-viet-qa
This model is a fine-tuned version of NlpHUST/electra-base-vn on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0900
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: 12
- eval_batch_size: 12
- 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 |
|---|---|---|---|
| 1.7588 | 1.0 | 1912 | 1.5902 |
| 1.2695 | 2.0 | 3824 | 1.4278 |
| 0.9466 | 3.0 | 5736 | 1.4897 |
| 0.7172 | 4.0 | 7648 | 1.7142 |
| 0.5232 | 5.0 | 9560 | 1.9696 |
| 0.4025 | 6.0 | 11472 | 2.2235 |
| 0.3104 | 7.0 | 13384 | 2.4544 |
| 0.243 | 8.0 | 15296 | 2.7552 |
| 0.1863 | 9.0 | 17208 | 2.9858 |
| 0.1531 | 10.0 | 19120 | 3.0900 |
Framework versions
- Transformers 4.23.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1