cardiffnlp/mbert-base-tweet-sentiment-pt

This model is a fine-tuned version of bert-base-multilingual-cased on the cardiffnlp/tweet_sentiment_multilingual (portuguese). Following metrics are computed on the test split of cardiffnlp/tweet_sentiment_multilingual(portuguese).

	eval_f1_micro	eval_recall_micro	eval_precision_micro	eval_f1_macro	eval_recall_macro	eval_precision_macro	eval_accuracy
0	61.26	61.26	61.26	61.31	61.26	61.55	61.26

Check the result file here.