metadata
library_name: transformers
license: apache-2.0
base_model: CocoRoF/KoModernBERT-chp-01
tags:
- generated_from_trainer
model-index:
- name: KoModernBERT-chp-02
results: []
KoModernBERT-chp-02
This model is a fine-tuned version of CocoRoF/KoModernBERT-chp-01 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1608
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 512
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 17.4659 | 0.0904 | 5000 | 2.2019 |
| 17.5275 | 0.1808 | 10000 | 2.1976 |
| 17.7839 | 0.2712 | 15000 | 2.1957 |
| 17.1639 | 0.3616 | 20000 | 2.1879 |
| 17.4977 | 0.4520 | 25000 | 2.1829 |
| 17.001 | 0.5424 | 30000 | 2.1814 |
| 17.4017 | 0.6329 | 35000 | 2.1747 |
| 17.0944 | 0.7233 | 40000 | 2.1722 |
| 17.46 | 0.8137 | 45000 | 2.1676 |
| 17.0978 | 0.9041 | 50000 | 2.1674 |
| 17.1695 | 0.9945 | 55000 | 2.1608 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0