|
|
--- |
|
|
metrics: |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: aha_class |
|
|
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. --> |
|
|
|
|
|
# aha_class |
|
|
|
|
|
This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0885 |
|
|
- F1: 0.9580 |
|
|
- Roc Auc: 0.9679 |
|
|
- Accuracy: 0.9391 |
|
|
|
|
|
## 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: 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: 15 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| |
|
|
| No log | 1.0 | 42 | 0.1723 | 0.95 | 0.9635 | 0.9217 | |
|
|
| No log | 2.0 | 84 | 0.1160 | 0.9576 | 0.9659 | 0.9391 | |
|
|
| No log | 3.0 | 126 | 0.1064 | 0.9492 | 0.9595 | 0.9304 | |
|
|
| No log | 4.0 | 168 | 0.0974 | 0.9540 | 0.9657 | 0.9304 | |
|
|
| No log | 5.0 | 210 | 0.0968 | 0.9580 | 0.9679 | 0.9304 | |
|
|
| No log | 6.0 | 252 | 0.0885 | 0.9580 | 0.9679 | 0.9391 | |
|
|
| No log | 7.0 | 294 | 0.1005 | 0.9580 | 0.9679 | 0.9391 | |
|
|
| No log | 8.0 | 336 | 0.0921 | 0.9664 | 0.9743 | 0.9478 | |
|
|
| No log | 9.0 | 378 | 0.1055 | 0.9580 | 0.9679 | 0.9391 | |
|
|
| No log | 10.0 | 420 | 0.0988 | 0.9664 | 0.9743 | 0.9478 | |
|
|
| No log | 11.0 | 462 | 0.0993 | 0.9664 | 0.9743 | 0.9478 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.42.3 |
|
|
- Pytorch 2.3.0+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.19.1 |
