aha_classification

This model is a fine-tuned version of monologg/kobigbird-bert-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1156
• F1: 0.9617
• Roc Auc: 0.9682
• Accuracy: 0.9478

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
No log	1.0	42	0.3257	0.8718	0.8998	0.8522
No log	2.0	84	0.1861	0.9451	0.9573	0.9217
No log	3.0	126	0.1474	0.9492	0.9595	0.9304
No log	4.0	168	0.1156	0.9617	0.9682	0.9478
No log	5.0	210	0.1185	0.9536	0.9637	0.9391
No log	6.0	252	0.1133	0.9492	0.9595	0.9304
No log	7.0	294	0.1098	0.9580	0.9679	0.9391
No log	8.0	336	0.1084	0.9536	0.9637	0.9391
No log	9.0	378	0.1167	0.9536	0.9637	0.9391

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1