This is a version of the dccuchile/bert-base-spanish-wwm-cased model fine-tuned on Spanish chitchat and question messages data.
The input of the model is a syntetic dataset, and the output is the probability of each one.
Epoch Training Loss Validation Loss Accuracy Precision Recall F1 1 0.000010 0.000020 0.9900 0.9910 0.9920 0.9915 2 0.000001 0.000005 0.9990 0.9991 0.9992 0.9991 3 0.000000 0.000000 1.0000 1.0000 1.0000 1.0000
The model can be used as follows: