metadata

tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: biobert-base-cased-v1.2-finetuned-ner
    results: []

biobert-base-cased-v1.2-finetuned-ner

This model is a fine-tuned version of dmis-lab/biobert-base-cased-v1.2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2662
Precision: 0.8204
Recall: 0.8577
F1: 0.8386
Accuracy: 0.9521

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: 3e-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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0189	1.0	680	0.2662	0.8204	0.8577	0.8386	0.9521
0.0141	2.0	1360	0.3010	0.8188	0.8407	0.8296	0.9491
0.0119	3.0	2040	0.3169	0.8316	0.8463	0.8389	0.9517
0.0101	4.0	2720	0.2845	0.8286	0.8588	0.8434	0.9541

Framework versions

Transformers 4.27.2
Pytorch 1.13.0+cu117
Datasets 2.7.1
Tokenizers 0.13.2