KoModernBERT-large-mlm-v18

This model is a fine-tuned version of CocoRoF/KoModernBERT-large-mlm-v17 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: nan

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: 4
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 32
total_train_batch_size: 1024
total_eval_batch_size: 16
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
84.3345	0.1156	500	nan
82.5464	0.2312	1000	nan
79.8316	0.3468	1500	nan
80.6937	0.4624	2000	nan
78.3035	0.5779	2500	nan
75.2479	0.6935	3000	nan
75.7199	0.8091	3500	nan
74.1576	0.9247	4000	nan