contrast_classifier_bio_bert

This model is a fine-tuned version of dmis-lab/biobert-v1.1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1097
• Accuracy: 0.9857

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0075	1.0	18	0.2757	0.9286
0.0024	2.0	36	0.5377	0.8429
0.0009	3.0	54	0.1979	0.9714
0.0006	4.0	72	0.1630	0.9714
0.0004	5.0	90	0.1114	0.9857
0.0004	6.0	108	0.1033	0.9857
0.0003	7.0	126	0.1036	0.9857
0.0003	8.0	144	0.1067	0.9857
0.0003	9.0	162	0.1095	0.9857
0.0003	10.0	180	0.1094	0.9857
0.0002	11.0	198	0.1096	0.9857
0.0002	12.0	216	0.1097	0.9857

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.0
• Tokenizers 0.15.0