metadata
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: []
finetuned-gpt2-lora-hatexplain
This model is a fine-tuned version of 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