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: 2.2881
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 |
|---|---|---|---|
| 4.6187 | 0.9231 | 3 | 4.0903 |
| 4.279 | 1.8462 | 6 | 3.7360 |
| 3.8585 | 2.7692 | 9 | 3.3951 |
| 2.6061 | 4.0 | 13 | 3.0000 |
| 3.174 | 4.9231 | 16 | 2.7745 |
| 2.9082 | 5.8462 | 19 | 2.6028 |
| 2.7201 | 6.7692 | 22 | 2.4674 |
| 1.9314 | 8.0 | 26 | 2.3388 |
| 2.4763 | 8.9231 | 29 | 2.2933 |
| 1.6856 | 9.2308 | 30 | 2.2881 |
Framework versions
- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.5.0+cu124
- Datasets 3.0.2
- Tokenizers 0.19.1
- Downloads last month
- 1
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 FrederikKlinkby/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ