SourceData_NER_v_2-0-3_BioLinkBERT_large

This model is a fine-tuned version of michiyasunaga/BioLinkBERT-large on the source_data dataset. It achieves the following results on the evaluation set:

• Loss: 0.1257
• Accuracy Score: 0.9621
• Precision: 0.8454
• Recall: 0.8684
• F1: 0.8567

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 128
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adafactor
• lr_scheduler_type: linear
• num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Score	Precision	Recall	F1
0.1019	1.0	942	0.1282	0.9590	0.8191	0.8722	0.8448
0.0703	2.0	1884	0.1257	0.9621	0.8454	0.8684	0.8567

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0a0+bfe5ad2
• Datasets 2.10.1
• Tokenizers 0.12.1