cardiffnlp/mbert-base-tweet-sentiment-ar
This model is a fine-tuned version of bert-base-multilingual-cased on the
cardiffnlp/tweet_sentiment_multilingual (arabic).
Following metrics are computed on the test split of
cardiffnlp/tweet_sentiment_multilingual(arabic).
| eval_f1_micro | eval_recall_micro | eval_precision_micro | eval_f1_macro | eval_recall_macro | eval_precision_macro | eval_accuracy | |
|---|---|---|---|---|---|---|---|
| 0 | 56.09 | 56.09 | 56.09 | 56.29 | 56.09 | 57.36 | 56.09 |
Check the result file here.
