Gestionabilidad-v2_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: 0.0034
• Accuracy: 0.9994
• Precision: 0.9994
• Recall: 0.9994
• F1: 0.9994

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
0.0229	0.5330	500	0.0098	0.9977	0.9977	0.9977	0.9977
0.0118	1.0661	1000	0.0068	0.9986	0.9986	0.9986	0.9986
0.0042	1.5991	1500	0.0067	0.9988	0.9988	0.9988	0.9988
0.0041	2.1322	2000	0.0052	0.9991	0.9991	0.9991	0.9991
0.0033	2.6652	2500	0.0055	0.9989	0.9989	0.9989	0.9989
0.0014	3.1983	3000	0.0052	0.9992	0.9992	0.9992	0.9992
0.0005	3.7313	3500	0.0036	0.9993	0.9993	0.9993	0.9993
0.0009	4.2644	4000	0.0040	0.9993	0.9993	0.9993	0.9993
0.0003	4.7974	4500	0.0034	0.9994	0.9994	0.9994	0.9994

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0