|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
model-index: |
|
- name: mistral-journal-finetune |
|
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. --> |
|
|
|
# mistral-journal-finetune |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6324 |
|
|
|
## 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: 2.5e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1 |
|
- training_steps: 500 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.9438 | 0.03 | 25 | 1.2268 | |
|
| 1.1449 | 0.06 | 50 | 1.1088 | |
|
| 1.1742 | 0.09 | 75 | 1.0455 | |
|
| 1.0987 | 0.12 | 100 | 0.9922 | |
|
| 1.0298 | 0.15 | 125 | 0.9476 | |
|
| 0.9422 | 0.18 | 150 | 0.9082 | |
|
| 0.934 | 0.21 | 175 | 0.8789 | |
|
| 0.8254 | 0.24 | 200 | 0.8560 | |
|
| 1.045 | 0.27 | 225 | 0.8217 | |
|
| 0.9614 | 0.3 | 250 | 0.7783 | |
|
| 0.8001 | 0.33 | 275 | 0.7525 | |
|
| 0.8299 | 0.36 | 300 | 0.7238 | |
|
| 0.7427 | 0.39 | 325 | 0.7087 | |
|
| 0.7323 | 0.42 | 350 | 0.6973 | |
|
| 0.7501 | 0.45 | 375 | 0.6794 | |
|
| 0.819 | 0.48 | 400 | 0.6692 | |
|
| 0.7871 | 0.51 | 425 | 0.6544 | |
|
| 0.7604 | 0.54 | 450 | 0.6431 | |
|
| 0.6955 | 0.57 | 475 | 0.6356 | |
|
| 0.6919 | 0.6 | 500 | 0.6324 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.2.dev0 |
|
- Transformers 4.37.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
