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: 1.9051
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 |
|---|---|---|---|
| 4.5943 | 0.9231 | 3 | 3.9664 |
| 4.0507 | 1.8462 | 6 | 3.4400 |
| 3.4751 | 2.7692 | 9 | 2.9919 |
| 2.2716 | 4.0 | 13 | 2.5826 |
| 2.7038 | 4.9231 | 16 | 2.3385 |
| 2.3949 | 5.8462 | 19 | 2.1511 |
| 2.1602 | 6.7692 | 22 | 2.0036 |
| 1.5554 | 8.0 | 26 | 1.9689 |
| 2.0291 | 8.9231 | 29 | 1.9142 |
| 1.3949 | 9.2308 | 30 | 1.9051 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 10
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 jnwulff/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ