metadata

license: apache-2.0
base_model: bert-base-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - recall
  - precision
model-index:
  - name: biobert-biocause-trainer
    results: []

biobert-biocause-trainer

This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1681
Accuracy: 0.9485
F1: 0.9040
Recall: 0.9511
Precision: 0.8614

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Recall	Precision
0.6094	0.16	50	0.5106	0.7701	0.6246	0.7492	0.5355
0.5744	0.32	100	0.4291	0.8132	0.6898	0.8139	0.5986
0.5282	0.48	150	0.3735	0.7963	0.6995	0.9290	0.5610
0.4704	0.64	200	0.4850	0.8965	0.7724	0.6877	0.8808
0.4809	0.8	250	0.2955	0.9074	0.8192	0.8218	0.8166
0.3985	0.96	300	0.2699	0.8829	0.8014	0.9259	0.7064
0.347	1.13	350	0.2695	0.9275	0.8587	0.8628	0.8547
0.3729	1.29	400	0.2227	0.9320	0.8723	0.9101	0.8374
0.4059	1.45	450	0.2130	0.9420	0.8894	0.9132	0.8668
0.3023	1.61	500	0.1996	0.9477	0.8989	0.9117	0.8865
0.2676	1.77	550	0.1814	0.9521	0.9074	0.9196	0.8955
0.4202	1.93	600	0.1702	0.9452	0.8987	0.9511	0.8517

Framework versions

Transformers 4.37.2
Pytorch 2.3.1
Datasets 2.19.1
Tokenizers 0.15.1