|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: t5-small_winobias_finetuned_HBRPOI |
|
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. --> |
|
|
|
# t5-small_winobias_finetuned_HBRPOI |
|
|
|
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3333 |
|
- Accuracy: 0.5 |
|
- Tp: 0.5 |
|
- Tn: 0.0 |
|
- Fp: 0.5 |
|
- Fn: 0.0 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Tp | Tn | Fp | Fn | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---:|:------:|:------:|:---:| |
|
| 0.437 | 0.8 | 20 | 0.3545 | 0.5 | 0.5 | 0.0 | 0.5 | 0.0 | |
|
| 0.3996 | 1.6 | 40 | 0.3565 | 0.5025 | 0.5 | 0.0025 | 0.4975 | 0.0 | |
|
| 0.3844 | 2.4 | 60 | 0.3498 | 0.5 | 0.5 | 0.0 | 0.5 | 0.0 | |
|
| 0.3728 | 3.2 | 80 | 0.3529 | 0.5013 | 0.5 | 0.0013 | 0.4987 | 0.0 | |
|
| 0.3732 | 4.0 | 100 | 0.3482 | 0.5006 | 0.5 | 0.0006 | 0.4994 | 0.0 | |
|
| 0.3798 | 4.8 | 120 | 0.3484 | 0.5 | 0.5 | 0.0 | 0.5 | 0.0 | |
|
| 0.3607 | 5.6 | 140 | 0.3475 | 0.5006 | 0.5 | 0.0006 | 0.4994 | 0.0 | |
|
| 0.3688 | 6.4 | 160 | 0.3456 | 0.5 | 0.5 | 0.0 | 0.5 | 0.0 | |
|
| 0.3597 | 7.2 | 180 | 0.3445 | 0.5006 | 0.5 | 0.0006 | 0.4994 | 0.0 | |
|
| 0.3658 | 8.0 | 200 | 0.3402 | 0.5 | 0.5 | 0.0 | 0.5 | 0.0 | |
|
| 0.3629 | 8.8 | 220 | 0.3362 | 0.5 | 0.5 | 0.0 | 0.5 | 0.0 | |
|
| 0.3393 | 9.6 | 240 | 0.3333 | 0.5 | 0.5 | 0.0 | 0.5 | 0.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
