CTEBMSP_ANAT_DISO

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

• Loss: 0.0909
• Anat Precision: 0.7522
• Anat Recall: 0.7147
• Anat F1: 0.7330
• Anat Number: 361
• Diso Precision: 0.8915
• Diso Recall: 0.8919
• Diso F1: 0.8917
• Diso Number: 2645
• Overall Precision: 0.8755
• Overall Recall: 0.8706
• Overall F1: 0.8731
• Overall Accuracy: 0.9873

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: 8e-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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Anat Precision	Anat Recall	Anat F1	Anat Number	Diso Precision	Diso Recall	Diso F1	Diso Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.0592	1.0	2133	0.0506	0.6950	0.4986	0.5806	361	0.8635	0.8609	0.8622	2645	0.8484	0.8174	0.8326	0.9843
0.0323	2.0	4266	0.0583	0.7899	0.6039	0.6845	361	0.8780	0.8817	0.8798	2645	0.8697	0.8483	0.8589	0.9858
0.0201	3.0	6399	0.0580	0.6565	0.7147	0.6844	361	0.8598	0.8764	0.8680	2645	0.8339	0.8570	0.8453	0.9851
0.0121	4.0	8532	0.0758	0.7240	0.6759	0.6991	361	0.8976	0.8752	0.8863	2645	0.8776	0.8513	0.8642	0.9863
0.0078	5.0	10665	0.0814	0.7219	0.7119	0.7169	361	0.8776	0.8975	0.8875	2645	0.8595	0.8752	0.8673	0.9862
0.0031	6.0	12798	0.0974	0.7599	0.6399	0.6947	361	0.8895	0.8915	0.8905	2645	0.8761	0.8613	0.8686	0.9867
0.002	7.0	14931	0.0980	0.7143	0.6787	0.6960	361	0.8813	0.8957	0.8884	2645	0.8624	0.8696	0.8660	0.9860
0.0005	8.0	17064	0.0909	0.7522	0.7147	0.7330	361	0.8915	0.8919	0.8917	2645	0.8755	0.8706	0.8731	0.9873

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2