koelectra

This model is a fine-tuned version of monologg/koelectra-small-v3-discriminator on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5279
• Accuracy: 0.7425

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	100	0.6898	0.5925
No log	2.0	200	0.6713	0.6425
No log	3.0	300	0.6305	0.69
No log	4.0	400	0.5867	0.715
0.6422	5.0	500	0.5630	0.7075
0.6422	6.0	600	0.5326	0.745
0.6422	7.0	700	0.5395	0.745
0.6422	8.0	800	0.5281	0.7425
0.6422	9.0	900	0.5445	0.7275
0.4493	10.0	1000	0.5279	0.7425

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2