README.md

metadata

license: mit
base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: NLP-HIBA_BiomedNLP-BiomedBERT-base-pretrained-model
    results: []

NLP-HIBA_BiomedNLP-BiomedBERT-base-pretrained-model

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

• Loss: 0.2050
• Precision: 0.6079
• Recall: 0.5407
• F1: 0.5723
• Accuracy: 0.9528

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: 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: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	71	0.2223	0.3125	0.1619	0.2133	0.9212
No log	2.0	142	0.1599	0.5228	0.3539	0.4221	0.9446
No log	3.0	213	0.1472	0.5298	0.4385	0.4798	0.9470
No log	4.0	284	0.1441	0.5885	0.4729	0.5244	0.9514
No log	5.0	355	0.1675	0.5654	0.5146	0.5388	0.9491
No log	6.0	426	0.1592	0.5860	0.5082	0.5443	0.9521
No log	7.0	497	0.1634	0.5621	0.5587	0.5604	0.9509
0.1349	8.0	568	0.1897	0.5803	0.5182	0.5475	0.9515
0.1349	9.0	639	0.1880	0.5699	0.5539	0.5618	0.9506
0.1349	10.0	710	0.1939	0.5923	0.5415	0.5657	0.9525
0.1349	11.0	781	0.1988	0.5863	0.5475	0.5662	0.9518
0.1349	12.0	852	0.2050	0.6079	0.5407	0.5723	0.9528

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1