|
--- |
|
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-lr2e-05-wd0.1 |
|
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-lr2e-05-wd0.1 |
|
|
|
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: 2.8836 |
|
|
|
## 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: 2e-05 |
|
- 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 | |
|
|:-------------:|:-------:|:----:|:---------------:| |
|
| 3.646 | 0.9231 | 3 | 3.3256 | |
|
| 3.5514 | 1.8462 | 6 | 3.2495 | |
|
| 3.4729 | 2.7692 | 9 | 3.1803 | |
|
| 2.5411 | 4.0 | 13 | 3.1002 | |
|
| 3.3402 | 4.9231 | 16 | 3.0486 | |
|
| 3.2618 | 5.8462 | 19 | 3.0041 | |
|
| 3.2159 | 6.7692 | 22 | 2.9666 | |
|
| 2.3764 | 8.0 | 26 | 2.9273 | |
|
| 3.1368 | 8.9231 | 29 | 2.9059 | |
|
| 3.1173 | 9.8462 | 32 | 2.8916 | |
|
| 3.114 | 10.7692 | 35 | 2.8843 | |
|
| 0.7009 | 11.0769 | 36 | 2.8836 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.13.2 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.5.0+cu124 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.19.1 |
