CocoRoF/KoModernBERT-large-V1

KoModernBERT-large-mlm-v23

This model is a fine-tuned version of CocoRoF/KoModernBERT-large-mlm-v22 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.0628

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: 5e-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 32
• total_train_batch_size: 1024
• total_eval_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.98) and epsilon=1e-07 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
70.4372	0.1156	500	2.2211
69.2834	0.2312	1000	2.2037
68.5161	0.3468	1500	2.1771
69.8878	0.4623	2000	2.1396
69.3379	0.5779	2500	2.1180
67.2487	0.6935	3000	2.0976
66.1262	0.8091	3500	2.0809
66.7275	0.9247	4000	2.0628

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.1