shawgpt-ft
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: 1.5055
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: 0.0001
- 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 |
|---|---|---|---|
| 4.6194 | 0.9231 | 3 | 4.0998 |
| 4.3178 | 1.8462 | 6 | 3.8050 |
| 3.9646 | 2.7692 | 9 | 3.5199 |
| 2.716 | 4.0 | 13 | 3.1552 |
| 3.3283 | 4.9231 | 16 | 2.9092 |
| 3.0294 | 5.8462 | 19 | 2.6948 |
| 2.787 | 6.7692 | 22 | 2.5120 |
| 1.9259 | 8.0 | 26 | 2.2909 |
| 2.3663 | 8.9231 | 29 | 2.1413 |
| 2.1511 | 9.8462 | 32 | 1.9888 |
| 1.9999 | 10.7692 | 35 | 1.8699 |
| 1.3764 | 12.0 | 39 | 1.7514 |
| 1.7586 | 12.9231 | 42 | 1.6807 |
| 1.6582 | 13.8462 | 45 | 1.6255 |
| 1.6134 | 14.7692 | 48 | 1.5777 |
| 1.1765 | 16.0 | 52 | 1.5351 |
| 1.5208 | 16.9231 | 55 | 1.5174 |
| 1.4917 | 17.8462 | 58 | 1.5078 |
| 1.0457 | 18.4615 | 60 | 1.5055 |
Framework versions
- PEFT 0.13.2
- 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 Skovbjerg/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ