|
|
--- |
|
|
license: cc-by-4.0 |
|
|
base_model: deepset/deberta-v3-base-squad2 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: FYP_sq2_mrqa |
|
|
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_sq2_mrqa |
|
|
|
|
|
This model is a fine-tuned version of [deepset/deberta-v3-base-squad2](https://huggingface.co/deepset/deberta-v3-base-squad2) on [MRQA](https://huggingface.co/datasets/mrqa) dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.0805 |
|
|
|
|
|
## 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-06 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 1 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 3.2667 | 0.14 | 4000 | 2.6882 | |
|
|
| 2.4457 | 0.27 | 8000 | 2.3556 | |
|
|
| 2.2012 | 0.41 | 12000 | 2.1995 | |
|
|
| 2.0871 | 0.55 | 16000 | 2.1129 | |
|
|
| 2.0249 | 0.68 | 20000 | 2.1128 | |
|
|
| 1.9939 | 0.82 | 24000 | 2.0941 | |
|
|
| 1.9658 | 0.95 | 28000 | 2.0805 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.39.3 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
