shawgpt-ft-epoch-17
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: 2.6155
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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: 17
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 25.5434 | 0.5714 | 1 | 4.2401 |
| 25.6938 | 1.5714 | 2 | 4.1565 |
| 24.646 | 2.5714 | 3 | 3.9657 |
| 23.5063 | 3.5714 | 4 | 3.7821 |
| 22.2803 | 4.5714 | 5 | 3.6134 |
| 21.3242 | 5.5714 | 6 | 3.4549 |
| 20.3798 | 6.5714 | 7 | 3.3075 |
| 19.658 | 7.5714 | 8 | 3.1749 |
| 18.9316 | 8.5714 | 9 | 3.0579 |
| 18.1952 | 9.5714 | 10 | 2.9563 |
| 17.5537 | 10.5714 | 11 | 2.8690 |
| 17.0554 | 11.5714 | 12 | 2.7957 |
| 16.6773 | 12.5714 | 13 | 2.7354 |
| 16.3041 | 13.5714 | 14 | 2.6879 |
| 15.9872 | 14.5714 | 15 | 2.6520 |
| 15.7942 | 15.5714 | 16 | 2.6279 |
| 10.5046 | 16.5714 | 17 | 2.6155 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0
- Downloads last month
- 15
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 Jonasbukhave/shawgpt-ft-epoch-17
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ