daor95/APAU_II-3

roberta-base-bne-ner

This model is a fine-tuned version of PlanTL-GOB-ES/roberta-base-bne on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0820
• Loc Precision: 0.8585
• Loc Recall: 0.8973
• Loc F1: 0.8775
• Loc Number: 974
• Misc Precision: 0.6777
• Misc Recall: 0.5955
• Misc F1: 0.6340
• Misc Number: 445
• Org Precision: 0.8713
• Org Recall: 0.8944
• Org F1: 0.8827
• Org Number: 1666
• Per Precision: 0.9539
• Per Recall: 0.9688
• Per F1: 0.9613
• Per Number: 1218
• Overall Precision: 0.8744
• Overall Recall: 0.8852
• Overall F1: 0.8798
• Overall Accuracy: 0.9821

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Loc Precision	Loc Recall	Loc F1	Loc Number	Misc Precision	Misc Recall	Misc F1	Misc Number	Org Precision	Org Recall	Org F1	Org Number	Per Precision	Per Recall	Per F1	Per Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.0648	1.0	261	0.0851	0.7593	0.9035	0.8251	974	0.6593	0.5393	0.5933	445	0.8331	0.8211	0.8271	1666	0.9512	0.9598	0.9555	1218	0.8323	0.8499	0.8410	0.9782
0.0329	2.0	522	0.0794	0.8669	0.8563	0.8616	974	0.6691	0.6090	0.6376	445	0.8461	0.9142	0.8788	1666	0.9570	0.9507	0.9539	1218	0.8650	0.8799	0.8724	0.9810
0.0191	3.0	783	0.0820	0.8585	0.8973	0.8775	974	0.6777	0.5955	0.6340	445	0.8713	0.8944	0.8827	1666	0.9539	0.9688	0.9613	1218	0.8744	0.8852	0.8798	0.9821
0.0108	4.0	1044	0.1017	0.8292	0.8676	0.8480	974	0.6324	0.6225	0.6274	445	0.8689	0.8752	0.8720	1666	0.9614	0.9606	0.9610	1218	0.8617	0.8715	0.8666	0.9805
0.0063	5.0	1305	0.1042	0.8621	0.8665	0.8643	974	0.6512	0.6292	0.64	445	0.8576	0.8932	0.8750	1666	0.9670	0.9622	0.9646	1218	0.8687	0.8794	0.8740	0.9812

Framework versions

• Transformers 4.51.3
• Pytorch 2.5.1+cu121
• Datasets 3.6.0
• Tokenizers 0.21.1