shawgpt-finetuned
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: 2.3950
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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.2613 | 1.0 | 4 | 3.9739 |
| 3.7238 | 2.0 | 8 | 3.5186 |
| 3.3449 | 3.0 | 12 | 3.1211 |
| 2.9805 | 4.0 | 16 | 2.8288 |
| 2.7953 | 5.0 | 20 | 2.6280 |
| 2.522 | 6.0 | 24 | 2.4896 |
| 2.4013 | 7.0 | 28 | 2.4092 |
| 2.4103 | 7.6154 | 30 | 2.3950 |
Framework versions
- PEFT 0.14.0
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.1
- Tokenizers 0.21.0
- 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 Jonasbukhave/shawgpt-finetuned
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ