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: 0.5838
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 |
|---|---|---|---|
| 1.3788 | 1.0 | 134 | 1.1852 |
| 1.1719 | 2.0 | 268 | 1.0125 |
| 1.0327 | 3.0 | 402 | 0.8912 |
| 0.9163 | 4.0 | 536 | 0.8010 |
| 0.8256 | 5.0 | 670 | 0.7345 |
| 0.7605 | 6.0 | 804 | 0.6839 |
| 0.7048 | 7.0 | 938 | 0.6426 |
| 0.6641 | 8.0 | 1072 | 0.6137 |
| 0.636 | 9.0 | 1206 | 0.5929 |
| 0.6089 | 10.0 | 1340 | 0.5838 |
Framework versions
- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.19.1
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for vignesh2404/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ