shawgpt-ft-new
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3160
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: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.5927 | 0.9231 | 3 | 3.9679 |
| 4.0376 | 1.8462 | 6 | 3.4219 |
| 3.4208 | 2.7692 | 9 | 2.9201 |
| 2.1751 | 4.0 | 13 | 2.4252 |
| 2.47 | 4.9231 | 16 | 2.1059 |
| 2.0327 | 5.8462 | 19 | 1.8209 |
| 1.7364 | 6.7692 | 22 | 1.6435 |
| 1.1738 | 8.0 | 26 | 1.4568 |
| 1.4144 | 8.9231 | 29 | 1.3998 |
| 1.3386 | 9.8462 | 32 | 1.3745 |
| 1.3338 | 10.7692 | 35 | 1.3571 |
| 0.9492 | 12.0 | 39 | 1.3395 |
| 1.2699 | 12.9231 | 42 | 1.3300 |
| 1.2263 | 13.8462 | 45 | 1.3237 |
| 1.2285 | 14.7692 | 48 | 1.3207 |
| 0.9198 | 16.0 | 52 | 1.3178 |
| 1.1982 | 16.9231 | 55 | 1.3167 |
| 1.1828 | 17.8462 | 58 | 1.3162 |
| 0.8346 | 18.4615 | 60 | 1.3160 |
Framework versions
- PEFT 0.13.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for AndreasHansenAU/shawgpt-ft-new
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ