shawgpt-ft
This model is a fine-tuned version of hugging-quants/Meta-Llama-3.1-8B-Instruct-GPTQ-INT4 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0354
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- 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
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.8384 | 0.9231 | 3 | 3.2747 |
| 3.666 | 1.8462 | 6 | 3.1189 |
| 3.4422 | 2.7692 | 9 | 2.9378 |
| 2.3978 | 4.0 | 13 | 2.6971 |
| 2.9756 | 4.9231 | 16 | 2.5165 |
| 2.7288 | 5.8462 | 19 | 2.3571 |
| 2.5339 | 6.7692 | 22 | 2.2220 |
| 1.796 | 8.0 | 26 | 2.0908 |
| 2.2918 | 8.9231 | 29 | 2.0411 |
| 1.6171 | 9.2308 | 30 | 2.0354 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 10