|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
datasets: |
|
- generator |
|
model-index: |
|
- name: sexed-mistral-7b-sft-lora-v3 |
|
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. --> |
|
|
|
# sexed-mistral-7b-sft-lora-v3 |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2857 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-------:|:----:|:---------------:| |
|
| 0.4906 | 0.9902 | 38 | 0.4776 | |
|
| 0.3966 | 1.9805 | 76 | 0.4122 | |
|
| 0.3648 | 2.9967 | 115 | 0.3658 | |
|
| 0.3405 | 3.9870 | 153 | 0.3372 | |
|
| 0.3153 | 4.9772 | 191 | 0.3180 | |
|
| 0.2996 | 5.9935 | 230 | 0.3043 | |
|
| 0.2987 | 6.9837 | 268 | 0.2969 | |
|
| 0.2888 | 8.0 | 307 | 0.2923 | |
|
| 0.2899 | 8.9902 | 345 | 0.2898 | |
|
| 0.2873 | 9.9805 | 383 | 0.2883 | |
|
| 0.2831 | 10.9967 | 422 | 0.2872 | |
|
| 0.2773 | 11.9870 | 460 | 0.2866 | |
|
| 0.2814 | 12.9772 | 498 | 0.2862 | |
|
| 0.2781 | 13.9935 | 537 | 0.2860 | |
|
| 0.2845 | 14.9837 | 575 | 0.2858 | |
|
| 0.29 | 16.0 | 614 | 0.2858 | |
|
| 0.2799 | 16.9902 | 652 | 0.2857 | |
|
| 0.2825 | 17.9805 | 690 | 0.2857 | |
|
| 0.2829 | 18.9967 | 729 | 0.2857 | |
|
| 0.2801 | 19.8046 | 760 | 0.2857 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |