shawgpt-finetuned-lr0.0002-wd0.001
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: 1.4875
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: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.5944 | 0.9231 | 3 | 3.9735 |
| 4.0559 | 1.8462 | 6 | 3.4489 |
| 3.475 | 2.7692 | 9 | 2.9840 |
| 2.2434 | 4.0 | 13 | 2.5324 |
| 2.6219 | 4.9231 | 16 | 2.2569 |
| 2.2616 | 5.8462 | 19 | 2.0276 |
| 1.96 | 6.7692 | 22 | 1.8151 |
| 1.3396 | 8.0 | 26 | 1.6637 |
| 1.6532 | 8.9231 | 29 | 1.5778 |
| 1.5344 | 9.8462 | 32 | 1.5191 |
| 1.5103 | 10.7692 | 35 | 1.4905 |
| 0.2698 | 11.0769 | 36 | 1.4875 |
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
- 0
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-finetuned-lr0.0002-wd0.001
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ