not-gestionable-v2_batch32

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: 0.0032
• Accuracy: 0.9991
• Precision: 0.9991
• Recall: 0.9991
• F1: 0.9991

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: 32
• 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
0.0442	0.5540	400	0.0165	0.9965	0.9965	0.9965	0.9965
0.0126	1.1080	800	0.0171	0.9971	0.9971	0.9971	0.9971
0.0069	1.6620	1200	0.0037	0.9993	0.9993	0.9993	0.9993
0.0032	2.2161	1600	0.0032	0.9991	0.9991	0.9991	0.9991
0.0052	2.7701	2000	0.0047	0.9993	0.9993	0.9993	0.9993
0.0006	3.3241	2400	0.0046	0.9993	0.9993	0.9993	0.9993
0.0015	3.8781	2800	0.0050	0.9991	0.9991	0.9991	0.9991
0.0005	4.4321	3200	0.0044	0.9993	0.9993	0.9993	0.9993
0.0006	4.9861	3600	0.0041	0.9993	0.9993	0.9993	0.9993

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0