roberta-base-bne-ner

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

• Loss: 0.3159
• Precision: 0.8517
• Recall: 0.8933
• F1: 0.8720
• Accuracy: 0.9384

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: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	280	0.3006	0.7961	0.8563	0.8251	0.9164
0.4008	2.0	560	0.2984	0.7918	0.8622	0.8255	0.9203
0.4008	3.0	840	0.2324	0.8401	0.8563	0.8481	0.9343
0.1014	4.0	1120	0.2394	0.8242	0.8889	0.8553	0.9414
0.1014	5.0	1400	0.2674	0.8469	0.8933	0.8695	0.9371
0.0435	6.0	1680	0.2815	0.8255	0.8830	0.8533	0.9375
0.0435	7.0	1960	0.2713	0.8516	0.8844	0.8677	0.9444
0.0233	8.0	2240	0.2745	0.8541	0.8933	0.8733	0.9437
0.0177	9.0	2520	0.3383	0.8336	0.8978	0.8645	0.9350
0.0177	10.0	2800	0.2858	0.8606	0.8963	0.8781	0.9419
0.013	11.0	3080	0.2956	0.8350	0.8919	0.8625	0.9403
0.013	12.0	3360	0.3097	0.8423	0.9022	0.8712	0.9380
0.0104	13.0	3640	0.3158	0.8443	0.8919	0.8674	0.9380
0.0104	14.0	3920	0.3171	0.8493	0.8933	0.8708	0.9387
0.0088	15.0	4200	0.3159	0.8517	0.8933	0.8720	0.9384

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1