shawgpt-ft-epoch15
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: 1.5885
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: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.6183 | 0.9231 | 3 | 4.0882 |
| 4.2715 | 1.8462 | 6 | 3.7222 |
| 3.8304 | 2.7692 | 9 | 3.3585 |
| 2.5639 | 4.0 | 13 | 2.9241 |
| 3.0708 | 4.9231 | 16 | 2.6518 |
| 2.7369 | 5.8462 | 19 | 2.4187 |
| 2.4602 | 6.7692 | 22 | 2.2188 |
| 1.678 | 8.0 | 26 | 1.9874 |
| 2.0312 | 8.9231 | 29 | 1.8634 |
| 1.8743 | 9.8462 | 32 | 1.7719 |
| 1.8014 | 10.7692 | 35 | 1.7017 |
| 1.2676 | 12.0 | 39 | 1.6337 |
| 1.6596 | 12.9231 | 42 | 1.6020 |
| 1.3657 | 13.8462 | 45 | 1.5885 |
Framework versions
- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- 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-epoch15
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ