metadata
base_model: vinai/bartpho-word
tags:
- generated_from_trainer
model-index:
- name: bartpho_queryrewriting
results: []
bartpho_queryrewriting
This model is a fine-tuned version of vinai/bartpho-word on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9354
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: 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: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.8568 | 0.0634 | 100 | 2.0166 |
| 2.0219 | 0.1268 | 200 | 2.0005 |
| 2.0234 | 0.1902 | 300 | 1.9967 |
| 1.9833 | 0.2536 | 400 | 1.9947 |
| 2.0665 | 0.3171 | 500 | 1.9929 |
| 2.047 | 0.3805 | 600 | 1.9898 |
| 1.9644 | 0.4439 | 700 | 1.9765 |
| 1.9494 | 0.5073 | 800 | 1.9556 |
| 1.9489 | 0.5707 | 900 | 1.9532 |
| 1.9747 | 0.6341 | 1000 | 1.9481 |
| 1.936 | 0.6975 | 1100 | 1.9412 |
| 2.032 | 0.7609 | 1200 | 1.9402 |
| 1.94 | 0.8244 | 1300 | 1.9394 |
| 1.9489 | 0.8878 | 1400 | 1.9367 |
| 1.9946 | 0.9512 | 1500 | 1.9354 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1