|
---
|
|
base_model: mistralai/Mistral-7B-Instruct-v0.3
|
|
library_name: peft
|
|
license: apache-2.0
|
|
tags:
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: pgd_mistral_8bits_lr0.0002_alpha32_rk8_do0.1_wd1.0e-02
|
|
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. --> |
|
|
|
# pgd_mistral_8bits_lr0.0002_alpha32_rk8_do0.1_wd1.0e-02 |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co./mistralai/Mistral-7B-Instruct-v0.3) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7862 |
|
|
|
## 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: 3 |
|
- eval_batch_size: 3 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 12 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 3.1023 | 0.9778 | 11 | 2.2315 | |
|
| 1.8596 | 1.9556 | 22 | 1.1833 | |
|
| 1.0222 | 2.9333 | 33 | 0.8672 | |
|
| 0.7647 | 4.0 | 45 | 0.8008 | |
|
| 0.7791 | 4.9778 | 56 | 0.7832 | |
|
| 0.763 | 5.9556 | 67 | 0.7755 | |
|
| 0.743 | 6.9333 | 78 | 0.7743 | |
|
| 0.6757 | 8.0 | 90 | 0.7780 | |
|
| 0.721 | 8.9778 | 101 | 0.7850 | |
|
| 0.6752 | 9.7778 | 110 | 0.7862 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.43.4 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
