metadata
library_name: peft
license: mit
base_model: gpt2
tags:
- base_model:adapter:gpt2
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: results
results: []
results
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7737
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3491 | 0.4 | 500 | 1.0980 |
| 0.9806 | 0.8 | 1000 | 0.8535 |
| 0.9117 | 1.2 | 1500 | 0.8104 |
| 0.8753 | 1.6 | 2000 | 0.7913 |
| 0.8527 | 2.0 | 2500 | 0.7803 |
| 0.8426 | 2.4 | 3000 | 0.7756 |
| 0.8376 | 2.8 | 3500 | 0.7737 |
Framework versions
- PEFT 0.16.0
- Transformers 4.54.0
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2