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: 1.4276
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: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|
| 4.2131 | 1.0 | 4 | 3.7758 |
| 3.4606 | 2.0 | 8 | 3.1119 |
| 2.8976 | 3.0 | 12 | 2.6217 |
| 2.4209 | 4.0 | 16 | 2.3240 |
| 2.2093 | 5.0 | 20 | 1.9847 |
| 1.7278 | 6.0 | 24 | 1.7438 |
| 1.4981 | 7.0 | 28 | 1.5861 |
| 1.444 | 8.0 | 32 | 1.4874 |
| 1.368 | 9.0 | 36 | 1.4439 |
| 1.2514 | 10.0 | 40 | 1.4276 |
Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for santoshmds21/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ