Yepes_5e-05_29_03

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

• Loss: 0.1549
• Precision: 0.5725
• Recall: 0.4261
• F1: 0.4886
• Accuracy: 0.9781

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.4799	5.0	25	0.1950	0.0	0.0	0.0	0.9697
0.1703	10.0	50	0.1385	0.0	0.0	0.0	0.9697
0.0981	15.0	75	0.1336	0.3361	0.2273	0.2712	0.9740
0.0594	20.0	100	0.1192	0.4150	0.3466	0.3777	0.9757
0.0318	25.0	125	0.1293	0.5039	0.3693	0.4262	0.9775
0.0177	30.0	150	0.1303	0.5123	0.4716	0.4911	0.9767
0.0114	35.0	175	0.1363	0.5411	0.4489	0.4907	0.9773
0.0074	40.0	200	0.1459	0.5455	0.4773	0.5091	0.9774
0.0058	45.0	225	0.1442	0.5190	0.4659	0.4910	0.9767
0.0044	50.0	250	0.1549	0.5725	0.4261	0.4886	0.9781

Framework versions

• Transformers 4.27.4
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2