Plant-gob-roberta-base-bne-capitel-ner

Este modelo fue afinado sobre el modelo BSC-LT/roberta-base-bne-capitel-ner sobre conll2002 dataset con un batch_size de 16 logrando la siguiente precisión.

• Loss: 0.1071
• Precision: 0.8628
• Recall: 0.8826
• F1: 0.8726
• Accuracy: 0.9785

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: 16
• eval_batch_size: 16
• seed: 42
• 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	Precision	Recall	F1	Accuracy
0.0681	1.0	521	0.0818	0.8645	0.8842	0.8742	0.9789
0.0313	2.0	1042	0.0841	0.8516	0.8768	0.8640	0.9779
0.0179	3.0	1563	0.0979	0.8584	0.8773	0.8677	0.9781
0.0091	4.0	2084	0.0996	0.8600	0.8819	0.8708	0.9784
0.0068	5.0	2605	0.1071	0.8628	0.8826	0.8726	0.9785

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3