|
--- |
|
library_name: peft |
|
license: mit |
|
base_model: gpt2 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- hatexplain |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: finetuned-gpt2-lora-hatexplain |
|
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. --> |
|
|
|
# finetuned-gpt2-lora-hatexplain |
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the hatexplain dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7617 |
|
- Accuracy: 0.6954 |
|
- Precision: 0.6905 |
|
- Recall: 0.6954 |
|
- F1: 0.6911 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 0.6763 | 1.0 | 1923 | 0.7699 | 0.6629 | 0.6552 | 0.6629 | 0.6429 | |
|
| 0.8192 | 2.0 | 3846 | 0.7648 | 0.6712 | 0.6620 | 0.6712 | 0.6628 | |
|
| 0.7806 | 3.0 | 5769 | 0.7657 | 0.6571 | 0.6682 | 0.6571 | 0.6585 | |
|
| 0.6273 | 4.0 | 7692 | 0.8046 | 0.6769 | 0.6727 | 0.6769 | 0.6740 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.14.0 |
|
- Transformers 4.47.0 |
|
- Pytorch 2.5.1+cu118 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.21.0 |
