|
--- |
|
license: cc-by-4.0 |
|
base_model: deepset/deberta-v3-large-squad2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: deberta-large_vMCQ |
|
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. --> |
|
|
|
# deberta-large_vMCQ |
|
|
|
This model is a fine-tuned version of [deepset/deberta-v3-large-squad2](https://huggingface.co/deepset/deberta-v3-large-squad2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3480 |
|
- Accuracy: 0.9061 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 1 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.5525 | 0.17 | 1000 | 0.4781 | 0.8777 | |
|
| 0.4107 | 0.33 | 2000 | 0.3763 | 0.8924 | |
|
| 0.3733 | 0.5 | 3000 | 0.3605 | 0.8967 | |
|
| 0.39 | 0.67 | 4000 | 0.3378 | 0.9050 | |
|
| 0.3674 | 0.83 | 5000 | 0.3407 | 0.9053 | |
|
| 0.3507 | 1.0 | 6000 | 0.3480 | 0.9061 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.14.1 |
|
|
