biomedical-roberta-finetuned-iomed_task

This model is a fine-tuned version of PlanTL-GOB-ES/roberta-base-biomedical-es on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0582
• Precision: 0.2269
• Recall: 0.4283
• F1: 0.2966
• Accuracy: 0.7695

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: 2.1e-06
• train_batch_size: 4
• eval_batch_size: 4
• 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
1.2536	2.0	1520	1.2135	0.1082	0.2685	0.1542	0.7422
1.0249	4.0	3040	1.0510	0.1448	0.3244	0.2002	0.7650
0.9	6.0	4560	1.0098	0.1587	0.3512	0.2186	0.7694
0.8002	8.0	6080	1.0143	0.1835	0.3795	0.2474	0.7664
0.7195	10.0	7600	1.0173	0.2007	0.4055	0.2685	0.7691
0.693	12.0	9120	1.0218	0.1991	0.4079	0.2676	0.7683
0.6139	14.0	10640	1.0394	0.2063	0.4071	0.2738	0.7672
0.616	16.0	12160	1.0376	0.2141	0.4142	0.2823	0.7695
0.5911	18.0	13680	1.0491	0.2240	0.4268	0.2938	0.7697
0.6042	20.0	15200	1.0582	0.2269	0.4283	0.2966	0.7695

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3