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: 2.6867
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 |
|---|---|---|---|
| 4.0832 | 0.9231 | 3 | 4.1794 |
| 3.6615 | 1.8462 | 6 | 3.6643 |
| 3.1631 | 2.7692 | 9 | 3.2256 |
| 2.1013 | 4.0 | 13 | 2.9286 |
| 2.6005 | 4.9231 | 16 | 2.8400 |
| 2.4725 | 5.8462 | 19 | 2.7868 |
| 2.3699 | 6.7692 | 22 | 2.7427 |
| 1.728 | 8.0 | 26 | 2.7016 |
| 2.2633 | 8.9231 | 29 | 2.6882 |
| 1.4946 | 9.2308 | 30 | 2.6867 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.1.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 4
Model tree for pranavGenAI/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ