|
--- |
|
library_name: transformers |
|
license: llama3.2 |
|
base_model: Bllossom/llama-3.2-Korean-Bllossom-3B |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: sonigo_style_predict |
|
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. --> |
|
|
|
# sonigo_style_predict |
|
|
|
This model is a fine-tuned version of [Bllossom/llama-3.2-Korean-Bllossom-3B](https://huggingface.co/Bllossom/llama-3.2-Korean-Bllossom-3B) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1488 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 10 |
|
- eval_batch_size: 3 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- 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: 8 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.4074 | 1.0 | 182 | 0.5274 | |
|
| 0.2929 | 2.0 | 364 | 0.3765 | |
|
| 0.2069 | 3.0 | 546 | 0.2395 | |
|
| 0.1576 | 4.0 | 728 | 0.2080 | |
|
| 0.1913 | 5.0 | 910 | 0.2121 | |
|
| 0.1852 | 6.0 | 1092 | 0.1757 | |
|
| 0.079 | 7.0 | 1274 | 0.1601 | |
|
| 0.0992 | 8.0 | 1456 | 0.1488 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
