biobert finetuned ner This model is a fine tuned version of dmis lab/biobert base cased v1.2 on the jnlpba dataset. It achieves the following results on the evaluation set: Loss: 0.5113 Precision: 0.6551 Recall: 0.7646 F1: 0.7056 Accuracy: 0.9108 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: 5 Training results Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy : : : : : : : : : : : : : : : : 0.1815 1.0 2319 0.2706 0.6538 0.7704 0.7073 0.9160 0.1226 2.0 4638 0.3230 0.6524 0.7675 0.7053 0.9118 0.0813 3.0 6957 0.3974 0.6483 0.7611 0.7002 0.9101 0.0521 4.0 9276 0.4529 0.6575 0.7652 0.7073 0.9121 0.0356 5.0 11595 0.5113 0.6551 0.7646 0.7056 0.9108 Framework versions Transformers 4.21.1 Pytorch 1.12.1+cu113 Datasets 2.4.0 Tokenizers 0.12.1
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy