|
--- |
|
base_model: mistralai/Mistral-7B-v0.3 |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: mistral_fine_tuned |
|
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. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](None) |
|
# mistral_fine_tuned |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.7777 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- lr_scheduler_warmup_steps: 0.03 |
|
- training_steps: 100 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.1448 | 0.1 | 10 | 2.6930 | |
|
| 2.5114 | 0.2 | 20 | 2.1804 | |
|
| 1.6951 | 0.3 | 30 | 2.0022 | |
|
| 1.7202 | 0.4 | 40 | 1.9292 | |
|
| 1.7303 | 0.5 | 50 | 1.9083 | |
|
| 1.4861 | 0.6 | 60 | 1.8414 | |
|
| 1.7349 | 0.7 | 70 | 1.7941 | |
|
| 1.6208 | 0.8 | 80 | 1.7469 | |
|
| 1.6669 | 0.9 | 90 | 1.7685 | |
|
| 1.5728 | 1.0 | 100 | 1.7777 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
