metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: openai-community/gpt2
datasets:
- emotion
metrics:
- accuracy
model-index:
- name: emotion-gpt2-lora
results: []
emotion-gpt2-lora
This model is a fine-tuned version of openai-community/gpt2 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.1445
- Accuracy: 0.9315
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 250 | 0.3155 | 0.8815 |
| 0.6098 | 2.0 | 500 | 0.1879 | 0.926 |
| 0.6098 | 3.0 | 750 | 0.1576 | 0.934 |
| 0.1844 | 4.0 | 1000 | 0.1445 | 0.9315 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1