# `cardiffnlp/xlm-roberta-base-tweet-sentiment-ar`
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the 
[cardiffnlp/tweet_sentiment_multilingual](https://huggingface.co/datasets/cardiffnlp/tweet_sentiment_multilingual) (arabic).
Following metrics are computed on the `test` split of 
[cardiffnlp/tweet_sentiment_multilingual](https://huggingface.co/datasets/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 |           66.21 |               66.21 |                  66.21 |           66.33 |               66.21 |                  66.51 |           66.21 |

Check the result file [here](https://huggingface.co/cardiffnlp/xlm-roberta-base-tweet-sentiment-ar/raw/main/eval.json).