metadata

license: mit
base_model: xlm-roberta-large
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - roc_auc
  - f1
model-index:
  - name: results_RoBERTa
    results: []
datasets:
  - alecmontero/dataset_tweetsmx_areasCPC
language:
  - es
library_name: transformers

results_RoBERTa

This model is a fine-tuned version of xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1365
Roc Auc: 0.8669
Hamming Loss: 0.0454
F1 Score: 0.7761
Accuracy: 0.4712
Precision: 0.7977
Recall: 0.7665

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	0.1904	0.6981	0.0674	0.4749	0.3440	0.7840	0.4297
0.2476	2.0	748	0.1674	0.7439	0.0612	0.5672	0.3802	0.8482	0.5228
0.1597	3.0	1122	0.1512	0.7955	0.0545	0.6516	0.4163	0.8172	0.6218
0.1597	4.0	1496	0.1414	0.8087	0.0511	0.6736	0.4324	0.8251	0.6535
0.1222	5.0	1870	0.1395	0.8344	0.0490	0.7153	0.4378	0.8190	0.7038
0.09	6.0	2244	0.1385	0.8485	0.0477	0.7552	0.4645	0.8182	0.7315
0.0663	7.0	2618	0.1391	0.8544	0.0466	0.7617	0.4712	0.7936	0.7401
0.0663	8.0	2992	0.1365	0.8669	0.0454	0.7761	0.4712	0.7977	0.7665
0.0461	9.0	3366	0.1375	0.8617	0.0460	0.7711	0.4699	0.7956	0.7569
0.0293	10.0	3740	0.1388	0.8636	0.0448	0.7736	0.4926	0.7953	0.7592

Framework versions

Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1