Gestionabilidad-v4_batch32

This model is a fine-tuned version of M4rt0no/Gestionabilidad-v3_batch32 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5671
• Accuracy: 0.8731
• Precision: 0.8726
• Recall: 0.8731
• F1: 0.8691

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: 16
• 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
0.083	0.7220	400	0.6704	0.8660	0.8641	0.8660	0.8628
0.1806	1.4440	800	0.5671	0.8731	0.8726	0.8731	0.8691
0.1207	2.1661	1200	0.6259	0.8800	0.8783	0.8800	0.8782
0.0571	2.8881	1600	0.7081	0.8702	0.8711	0.8702	0.8706
0.0303	3.6101	2000	0.7597	0.8734	0.8734	0.8734	0.8734
0.0199	4.3321	2400	0.7955	0.8818	0.8803	0.8818	0.8803

Framework versions

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