|
--- |
|
license: cc-by-4.0 |
|
base_model: kxx-kkk/FYP_sq2_mrqa_adqa_synqa |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: FYP_qa_final |
|
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. --> |
|
|
|
# FYP_qa_final |
|
|
|
This model is a fine-tuned version of [kxx-kkk/FYP_sq2_mrqa_adqa_synqa](https://huggingface.co./kxx-kkk/FYP_sq2_mrqa_adqa_synqa) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.5802 |
|
|
|
## 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: 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: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.7511 | 0.48 | 300 | 2.9918 | |
|
| 2.538 | 0.96 | 600 | 2.8853 | |
|
| 2.428 | 1.44 | 900 | 2.6102 | |
|
| 2.408 | 1.92 | 1200 | 2.5302 | |
|
| 2.3025 | 2.4 | 1500 | 2.5252 | |
|
| 2.2878 | 2.88 | 1800 | 2.5802 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
