metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: gpt2-alpaca-instruction-fine-tuning-qlora
results: []
gpt2-alpaca-instruction-fine-tuning-qlora
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8330
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1183 | 0.11 | 1000 | 1.8975 |
| 2.1329 | 0.22 | 2000 | 1.8818 |
| 2.1179 | 0.33 | 3000 | 1.8770 |
| 2.0949 | 0.44 | 4000 | 1.8662 |
| 2.0871 | 0.55 | 5000 | 1.8477 |
| 2.0668 | 0.66 | 6000 | 1.8447 |
| 2.0636 | 0.77 | 7000 | 1.8379 |
| 2.0442 | 0.88 | 8000 | 1.8311 |
| 2.0597 | 0.99 | 9000 | 1.8330 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3