|
--- |
|
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: shawgpt-ft |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# shawgpt-ft |
|
|
|
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3151 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 50 |
|
- num_epochs: 15 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.7497 | 1.0 | 4 | 2.6779 | |
|
| 2.6244 | 2.0 | 8 | 2.5849 | |
|
| 2.4713 | 3.0 | 12 | 2.4209 | |
|
| 2.2528 | 4.0 | 16 | 2.2592 | |
|
| 2.1709 | 5.0 | 20 | 2.0030 | |
|
| 1.7641 | 6.0 | 24 | 1.7789 | |
|
| 1.5186 | 7.0 | 28 | 1.5817 | |
|
| 1.4366 | 8.0 | 32 | 1.4485 | |
|
| 1.3282 | 9.0 | 36 | 1.3829 | |
|
| 1.1828 | 10.0 | 40 | 1.3437 | |
|
| 1.2567 | 11.0 | 44 | 1.3216 | |
|
| 1.0748 | 12.0 | 48 | 1.3156 | |
|
| 1.1122 | 13.0 | 52 | 1.3091 | |
|
| 0.9957 | 14.0 | 56 | 1.3154 | |
|
| 1.0336 | 15.0 | 60 | 1.3151 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.13.2 |
|
- Transformers 4.45.2 |
|
- Pytorch 2.5.0+cu124 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.1 |
