Gestionabilidad-v1_batch64

This model is a fine-tuned version of dccuchile/tulio-chilean-spanish-bert on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0249
• Accuracy: 0.9942
• Precision: 0.9942
• Recall: 0.9942
• F1: 0.9942

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: 64
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.0625	0.2737	500	0.0508	0.9898	0.9898	0.9898	0.9898
0.0426	0.5473	1000	0.0349	0.9910	0.9910	0.9910	0.9910
0.0338	0.8210	1500	0.0308	0.9923	0.9923	0.9923	0.9923
0.0336	1.0947	2000	0.0319	0.9931	0.9932	0.9931	0.9931
0.0271	1.3684	2500	0.0304	0.9933	0.9933	0.9933	0.9933
0.0255	1.6420	3000	0.0326	0.9927	0.9928	0.9927	0.9927
0.0242	1.9157	3500	0.0277	0.9936	0.9936	0.9936	0.9936
0.0191	2.1894	4000	0.0285	0.9942	0.9942	0.9942	0.9942
0.0189	2.4631	4500	0.0249	0.9942	0.9942	0.9942	0.9942
0.0166	2.7367	5000	0.0262	0.9946	0.9946	0.9946	0.9946
0.0155	3.0104	5500	0.0273	0.9943	0.9943	0.9943	0.9943
0.0097	3.2841	6000	0.0313	0.9943	0.9943	0.9943	0.9943
0.0074	3.5577	6500	0.0353	0.9940	0.9940	0.9940	0.9940
0.0095	3.8314	7000	0.0338	0.9942	0.9942	0.9942	0.9942
0.006	4.1051	7500	0.0379	0.9939	0.9939	0.9939	0.9939
0.004	4.3788	8000	0.0380	0.9938	0.9938	0.9938	0.9938
0.0048	4.6524	8500	0.0373	0.9939	0.9939	0.9939	0.9939
0.0032	4.9261	9000	0.0394	0.9939	0.9939	0.9939	0.9939

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0