metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: openai-community/gpt2
datasets:
- financial_phrasebank
metrics:
- accuracy
model-index:
- name: gpt2-sentiment_analysis
results: []
gpt2-sentiment_analysis
This model is a fine-tuned version of openai-community/gpt2 on the financial_phrasebank dataset. It achieves the following results on the evaluation set:
- Loss: 0.7017
- Accuracy: {'accuracy': 0.8941548183254344}
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: 0.0006
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 224 | 0.4513 | {'accuracy': 0.8515007898894155} |
| No log | 2.0 | 448 | 0.3301 | {'accuracy': 0.8862559241706162} |
| 0.2776 | 3.0 | 672 | 0.3686 | {'accuracy': 0.8862559241706162} |
| 0.2776 | 4.0 | 896 | 0.3920 | {'accuracy': 0.8767772511848341} |
| 0.198 | 5.0 | 1120 | 0.3815 | {'accuracy': 0.8925750394944708} |
| 0.198 | 6.0 | 1344 | 0.5228 | {'accuracy': 0.8720379146919431} |
| 0.1346 | 7.0 | 1568 | 0.5616 | {'accuracy': 0.8846761453396524} |
| 0.1346 | 8.0 | 1792 | 0.5480 | {'accuracy': 0.9020537124802528} |
| 0.0823 | 9.0 | 2016 | 0.6681 | {'accuracy': 0.8957345971563981} |
| 0.0823 | 10.0 | 2240 | 0.7017 | {'accuracy': 0.8941548183254344} |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1