README.md

metadata

license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - roc_auc
  - f1
model-index:
  - name: results
    results: []
datasets:
  - alecmontero/dataset_tweetsmx_areasCPC
language:
  - es
library_name: transformers

results

This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1516
• Roc Auc: 0.8130
• Hamming Loss: 0.0509
• F1 Score: 0.6969
• Accuracy: 0.4418
• Precision: 0.8279
• Recall: 0.6583

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Roc Auc	Hamming Loss	F1 Score	Accuracy	Precision	Recall
No log	1.0	374	0.2285	0.6386	0.0822	0.3390	0.2731	0.8932	0.3080
0.2678	2.0	748	0.1870	0.7175	0.0679	0.5123	0.3481	0.7842	0.4679
0.1722	3.0	1122	0.1727	0.7839	0.0607	0.6116	0.3949	0.7611	0.6096
0.1722	4.0	1496	0.1577	0.7865	0.0545	0.6408	0.4137	0.8178	0.6096
0.1236	5.0	1870	0.1537	0.8055	0.0523	0.6798	0.4230	0.8250	0.6423
0.0847	6.0	2244	0.1570	0.8069	0.0541	0.6695	0.4297	0.7839	0.6503
0.063	7.0	2618	0.1516	0.8130	0.0509	0.6969	0.4418	0.8279	0.6583
0.063	8.0	2992	0.1531	0.8147	0.0512	0.6856	0.4458	0.7982	0.6622
0.0465	9.0	3366	0.1526	0.8427	0.0489	0.7544	0.4565	0.8190	0.7174
0.0349	10.0	3740	0.1534	0.8349	0.0498	0.7414	0.4431	0.8212	0.7023

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1