bio_bert_ft – AI Model by ericntay | AlphaNeural AI

You can deploy this model and start earning money today!

ericntay/
bio_bert_ft

like

0

token-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

bio_bert_ft

This model is a fine-tuned version of dmis-lab/biobert-v1.1 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0747
F1: 0.8621

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: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.0879	1.0	170	0.0400	0.8312
0.0211	2.0	340	0.0454	0.8413
0.0105	3.0	510	0.0503	0.8603
0.0045	4.0	680	0.0497	0.8496
0.0028	5.0	850	0.0759	0.8387
0.0019	6.0	1020	0.0654	0.8598
0.0011	7.0	1190	0.0667	0.8654
0.0005	8.0	1360	0.0702	0.8621
0.0003	9.0	1530	0.0739	0.8596
0.0002	10.0	1700	0.0747	0.8621

Framework versions

Transformers 4.20.1
Pytorch 1.11.0+cu113
Datasets 2.3.2
Tokenizers 0.12.1