|
--- |
|
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_lr0.004_alpha32_rk4_do0.2_wd3.0e-03 |
|
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_lr0.004_alpha32_rk4_do0.2_wd3.0e-03 |
|
|
|
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: 4.7590 |
|
|
|
## 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: 0.004 |
|
- 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: 50 |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.1711 | 1.0 | 15 | 1.1259 | |
|
| 2.5313 | 2.0 | 30 | 9.7541 | |
|
| 8.0828 | 3.0 | 45 | 6.5207 | |
|
| 5.9822 | 4.0 | 60 | 5.0761 | |
|
| 4.8191 | 5.0 | 75 | 4.7590 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.42.4 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
