KoModernBERT-chp-13

This model is a fine-tuned version of CocoRoF/KoModernBERT-chp-12 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.7189

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-06
• 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
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
22.6033	0.2458	5000	2.8268
22.1713	0.4915	10000	2.7760
22.3855	0.7373	15000	2.7472
21.8066	0.9831	20000	2.7189

Framework versions

• Transformers 4.48.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0