metadata
base_model: gpt2
library_name: peft
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2-lora
results: []
gpt2-lora
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2492
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: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.409 | 0.4737 | 200 | 2.2836 |
| 2.3443 | 0.9473 | 400 | 2.2642 |
| 2.3351 | 1.4210 | 600 | 2.2530 |
| 2.337 | 1.8946 | 800 | 2.2492 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1