KoModernBERT-base-mlm-v04-retry-model-chp11

This model is a fine-tuned version of CocoRoF/KoModernBERT-base-mlm-v04-retry-model-chp10 on the miracl-corpus dataset. It achieves the following results on the evaluation set:

• Loss: 1.6514

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: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 64
• total_train_batch_size: 2048
• total_eval_batch_size: 32
• 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
112.1792	0.1413	100	1.7653
110.9146	0.2826	200	1.7264
109.9796	0.4239	300	1.7024
107.8193	0.5651	400	1.6842
106.8794	0.7064	500	1.6747
106.3015	0.8477	600	1.6712
106.583	0.9890	700	1.6514

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0