clasificador-sms

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0286
• Accuracy: 0.9964

Model description

Se cree que arroja un acuraccy tan bueno porque las clases están desbalanceadas, como no era el objetivo de la asignatura no se indagado más sobre este problema

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: 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: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0805	1.0	627	0.0328	0.9928
0.0343	2.0	1254	0.0180	0.9964
0.0132	3.0	1881	0.0286	0.9964

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3