biobert-v1.1-BC2GM-NCBI-BC5CDR-IOBES

This model is a fine-tuned version of sujeongh/biobert-v1.1-BC2GM-NCBI-IOBES on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3932
• Precision: 0.8824
• Recall: 0.1339
• F1: 0.2326

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
0.4535	1.0	1	0.4246	0.0	0.0	0.0
0.4535	2.0	2	0.4094	0.25	0.0045	0.0088
0.4535	3.0	3	0.4015	0.6	0.0268	0.0513
0.4535	4.0	4	0.3960	0.8182	0.0804	0.1463
0.4535	5.0	5	0.3932	0.8824	0.1339	0.2326

Framework versions

• Transformers 4.28.1
• Pytorch 2.3.1+cu121
• Datasets 2.19.1
• Tokenizers 0.13.3