rafaelm47labs's picture
Update README.md
5935390

\n# Spanish News Classification Headlines

SNCH: this model was develop by M47Labs the goal is text classification,the base model use was BETO, it was fine-tuned on 1000 example dataset.

Dataset Sample

Dataset size : 1000

Columns: idTask,task content 1,idTag,tag.

idTask task content 1 idTag tag
3637d9ac-119c-4a8f-899c-339cf5b42ae0 Alcalá de Guadaíra celebra la IV Semana de la Diversidad Sexual con acciones de sensibilización 81b36360-6cbf-4ffa-b558-9ef95c136714 sociedad
d56bab52-0029-45dd-ad90-5c17d4ed4c88 El Archipiélago Chinijo Graciplus se impone en el Trofeo Centro Comercial Rubicón ed198b6d-a5b9-4557-91ff-c0be51707dec deportes
dec70bc5-4932-4fa2-aeac-31a52377be02 Un total de 39 personas padecen ELA actualmente en la provincia 81b36360-6cbf-4ffa-b558-9ef95c136714 sociedad
fb396ba9-fbf1-4495-84d9-5314eb731405 Eurocopa 2021 : Italia vence a Gales y pasa a octavos con su candidatura reforzada ed198b6d-a5b9-4557-91ff-c0be51707dec deportes
bc5a36ca-4e0a-422e-9167-766b41008c01 Resolución de 10 de junio de 2021, del Ayuntamiento de Tarazona de La Mancha (Albacete), referente a la convocatoria para proveer una plaza. 81b36360-6cbf-4ffa-b558-9ef95c136714 sociedad
a87f8703-ce34-47a5-9c1b-e992c7fe60f6 El primer ministro sueco pierde una moción de censura 209ae89e-55b4-41fd-aac0-5400feab479e politica
d80bdaad-0ad5-43a0-850e-c473fd612526 El dólar se dispara tras la reunión de la Fed 11925830-148e-4890-a2bc-da9dc059dc17 economia

Labels:

  • ciencia_tecnologia

  • clickbait

  • cultura

  • deportes

  • economia

  • educacion

  • medio_ambiente

  • opinion

  • politica

  • sociedad

Example of Use

An example on how to use the model in this page can be found in this colab notebook: https://colab.research.google.com/drive/1XsKea6oMyEckye2FePW_XN7Rf8v41Cw_?usp=sharing

Finetune Hyperparameters

  • MAX_LEN = 32

  • TRAIN_BATCH_SIZE = 8

  • VALID_BATCH_SIZE = 4

  • EPOCHS = 5

  • LEARNING_RATE = 1e-05

Train Results

Validation Results

|n_example|epoch|loss|acc| |500|0|2.0770938420295715|24.5| |500|1|1.6953029704093934|50.25| |500|2|1.258900796175003|64.25| |500|3|0.8342628020048142|78.25| |500|4|0.5135736921429634|90.25|

|n_example|epoch|loss|acc| |1000|0|1.916002897115854|36.1997226074896| |1000|1|1.2941598492664295|62.2746185852982| |1000|2|0.8201534710415117|76.97642163661581| |1000|3|0.524806430051615|86.9625520110957| |1000|4|0.30662027455784463|92.64909847434119|

alt text