|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ |
|
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 the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.7929 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 3.921 | 0.9892 | 69 | 3.1268 | |
|
| 2.7734 | 1.9928 | 139 | 2.7793 | |
|
| 2.5538 | 2.9964 | 209 | 2.7026 | |
|
| 2.4648 | 4.0 | 279 | 2.7008 | |
|
| 2.4164 | 4.9892 | 348 | 2.7113 | |
|
| 2.3266 | 5.9928 | 418 | 2.6972 | |
|
| 2.2489 | 6.9964 | 488 | 2.7195 | |
|
| 2.1813 | 8.0 | 558 | 2.7573 | |
|
| 2.2002 | 8.9892 | 627 | 2.7826 | |
|
| 2.0955 | 9.8925 | 690 | 2.7929 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
