|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-Instruct-v0.2 |
|
model-index: |
|
- name: mistral-7B-Instruct-prompt |
|
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-7B-Instruct-prompt |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0962 |
|
|
|
## 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: 0.0004 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- training_steps: 2000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.745 | 0.75 | 100 | 0.8404 | |
|
| 0.5396 | 1.5 | 200 | 0.6313 | |
|
| 0.3702 | 2.26 | 300 | 0.4994 | |
|
| 0.3676 | 3.01 | 400 | 0.4106 | |
|
| 0.3623 | 3.76 | 500 | 0.3409 | |
|
| 0.2239 | 4.51 | 600 | 0.2893 | |
|
| 0.1719 | 5.26 | 700 | 0.2405 | |
|
| 0.1971 | 6.02 | 800 | 0.1866 | |
|
| 0.1446 | 6.77 | 900 | 0.1591 | |
|
| 0.1066 | 7.52 | 1000 | 0.1381 | |
|
| 0.0866 | 8.27 | 1100 | 0.1193 | |
|
| 0.0701 | 9.02 | 1200 | 0.1061 | |
|
| 0.0641 | 9.77 | 1300 | 0.1017 | |
|
| 0.0511 | 10.53 | 1400 | 0.0958 | |
|
| 0.0407 | 11.28 | 1500 | 0.0963 | |
|
| 0.0332 | 12.03 | 1600 | 0.0938 | |
|
| 0.0268 | 12.78 | 1700 | 0.0952 | |
|
| 0.0251 | 13.53 | 1800 | 0.0961 | |
|
| 0.023 | 14.29 | 1900 | 0.0961 | |
|
| 0.0219 | 15.04 | 2000 | 0.0962 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.0 |
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
