nominal-groups-recognition-bert-base-spanish-wwm-cased

This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-cased on the ALazcanoG/spanish_nominal_groups_conll2003 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3362
• Body Part Precision: 0.6830
• Body Part Recall: 0.7409
• Body Part F1: 0.7108
• Body Part Number: 413
• Disease Precision: 0.7439
• Disease Recall: 0.7446
• Disease F1: 0.7442
• Disease Number: 975
• Family Member Precision: 0.7941
• Family Member Recall: 0.9
• Family Member F1: 0.8438
• Family Member Number: 30
• Medication Precision: 0.8734
• Medication Recall: 0.7419
• Medication F1: 0.8023
• Medication Number: 93
• Procedure Precision: 0.6190
• Procedure Recall: 0.6270
• Procedure F1: 0.6230
• Procedure Number: 311
• Overall Precision: 0.7144
• Overall Recall: 0.7261
• Overall F1: 0.7202
• Overall Accuracy: 0.9175

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 13
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Body Part Precision	Body Part Recall	Body Part F1	Body Part Number	Disease Precision	Disease Recall	Disease F1	Disease Number	Family Member Precision	Family Member Recall	Family Member F1	Family Member Number	Medication Precision	Medication Recall	Medication F1	Medication Number	Procedure Precision	Procedure Recall	Procedure F1	Procedure Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.4335	1.0	1004	0.3011	0.5944	0.7167	0.6498	413	0.7014	0.7036	0.7025	975	0.8	0.8	0.8000	30	0.7875	0.6774	0.7283	93	0.6007	0.5177	0.5561	311	0.6634	0.6751	0.6692	0.9063
0.2379	2.0	2008	0.2920	0.6995	0.7215	0.7104	413	0.7655	0.7097	0.7366	975	0.75	0.8	0.7742	30	0.7667	0.7419	0.7541	93	0.6094	0.6270	0.6181	311	0.7212	0.7014	0.7112	0.9140
0.1629	3.0	3012	0.3022	0.6674	0.7530	0.7076	413	0.7286	0.7241	0.7263	975	0.8571	0.8	0.8276	30	0.8519	0.7419	0.7931	93	0.5994	0.6495	0.6235	311	0.6975	0.7201	0.7086	0.9170
0.1143	4.0	4016	0.3362	0.6830	0.7409	0.7108	413	0.7439	0.7446	0.7442	975	0.7941	0.9	0.8438	30	0.8734	0.7419	0.8023	93	0.6190	0.6270	0.6230	311	0.7144	0.7261	0.7202	0.9175
0.0861	5.0	5020	0.3643	0.6806	0.7482	0.7128	413	0.7428	0.7436	0.7432	975	0.8182	0.9	0.8571	30	0.8831	0.7312	0.8000	93	0.5928	0.6367	0.6140	311	0.7081	0.7283	0.7181	0.9163

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3