clasificador-tweets

This model is a fine-tuned version of mrm8488/electricidad-base-discriminator on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0622
• Accuracy: 0.7021

Model description

En este apartado habría que describir en detalle el modelo

Intended uses & limitations

En este apartado sería necesario explicar para qué se puede usar el modelo y cuáles son sus limitaciones

Training and evaluation data

Aquí habría que aportar información sobre el entrenamiento y la evaluación del modelo

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: Use 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	23	1.7633	0.3404
No log	2.0	46	1.6195	0.5106
No log	3.0	69	1.4145	0.5319
No log	4.0	92	1.2612	0.6170
No log	5.0	115	1.1615	0.6383
No log	6.0	138	1.0982	0.6383
No log	7.0	161	1.1311	0.6809
No log	8.0	184	1.0435	0.7021
No log	9.0	207	1.0331	0.7234
No log	10.0	230	1.0622	0.7021

Framework versions

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