|
--- |
|
license: cc-by-4.0 |
|
base_model: hung200504/bert-covidqa-3 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- covid_qa_deepset |
|
model-index: |
|
- name: bert-covidqa-4 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# bert-covidqa-4 |
|
|
|
This model is a fine-tuned version of [hung200504/bert-covidqa-3](https://huggingface.co/hung200504/bert-covidqa-3) on the covid_qa_deepset dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4380 |
|
|
|
## 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: 3e-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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.4937 | 0.04 | 5 | 0.4384 | |
|
| 0.2678 | 0.09 | 10 | 0.4334 | |
|
| 0.4938 | 0.13 | 15 | 0.4269 | |
|
| 0.2227 | 0.18 | 20 | 0.4598 | |
|
| 0.1708 | 0.22 | 25 | 0.4827 | |
|
| 0.1605 | 0.26 | 30 | 0.5107 | |
|
| 0.4913 | 0.31 | 35 | 0.5024 | |
|
| 0.3042 | 0.35 | 40 | 0.4838 | |
|
| 0.6595 | 0.39 | 45 | 0.4559 | |
|
| 0.4116 | 0.44 | 50 | 0.4385 | |
|
| 0.1758 | 0.48 | 55 | 0.4387 | |
|
| 0.4278 | 0.53 | 60 | 0.4403 | |
|
| 0.3984 | 0.57 | 65 | 0.4300 | |
|
| 0.3893 | 0.61 | 70 | 0.4201 | |
|
| 0.2478 | 0.66 | 75 | 0.4241 | |
|
| 0.2724 | 0.7 | 80 | 0.4258 | |
|
| 0.2483 | 0.75 | 85 | 0.4236 | |
|
| 0.1039 | 0.79 | 90 | 0.4286 | |
|
| 0.2723 | 0.83 | 95 | 0.4344 | |
|
| 0.3411 | 0.88 | 100 | 0.4367 | |
|
| 0.1883 | 0.92 | 105 | 0.4375 | |
|
| 0.5123 | 0.96 | 110 | 0.4380 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
