metadata
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: []
sonigo_style_predict
This model is a fine-tuned version of 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