|
|
--- |
|
|
library_name: peft |
|
|
license: apache-2.0 |
|
|
base_model: mistralai/Mistral-7B-v0.3 |
|
|
tags: |
|
|
- base_model:adapter:mistralai/Mistral-7B-v0.3 |
|
|
- lora |
|
|
- transformers |
|
|
model-index: |
|
|
- name: Mistral_StereoDetect_Model |
|
|
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_StereoDetect_Model |
|
|
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3143 |
|
|
- Pearson: 0.9660 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 5 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Pearson | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
|
| No log | 1.0 | 190 | 0.2906 | 0.9143 | |
|
|
| No log | 2.0 | 380 | 0.2797 | 0.9360 | |
|
|
| 0.4128 | 3.0 | 570 | 0.2969 | 0.9513 | |
|
|
| 0.4128 | 4.0 | 760 | 0.3159 | 0.9646 | |
|
|
| 0.4128 | 5.0 | 950 | 0.3143 | 0.9660 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.17.1 |
|
|
- Transformers 4.56.0 |
|
|
- Pytorch 2.4.0a0+f70bd71a48.nv24.06 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.22.0 |
