In2Lab_WFU_DETECH_ate_span_pubmedbert_v1

This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1159
• Precision: 0.8237
• Recall: 0.8168
• F1: 0.8202

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: 8
• eval_batch_size: 8
• 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: 7
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
No log	1.0	61	0.1541	0.7421	0.6201	0.6757
No log	2.0	122	0.1262	0.7720	0.7468	0.7592
No log	3.0	183	0.1156	0.7987	0.7937	0.7962
No log	4.0	244	0.1134	0.8160	0.7958	0.8058
No log	5.0	305	0.1132	0.8276	0.8050	0.8162
No log	6.0	366	0.1119	0.8306	0.8017	0.8159
No log	7.0	427	0.1159	0.8237	0.8168	0.8202

Framework versions

• Transformers 4.57.6
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.2