# `vocabtrimmer/roberta-base.xnli-en.5`
This model is a fine-tuned version of [roberta-base](https://huggingface.co./roberta-base) on the 
[xnli](https://huggingface.co./datasets/xnli) (en).
Following metrics are computed on the `test` split of 
[xnli](https://huggingface.co./datasets/xnli)(en). 

* Evaluation on test split
 
|    |   eval_f1_micro |   eval_recall_micro |   eval_precision_micro |   eval_f1_macro |   eval_recall_macro |   eval_precision_macro |   eval_accuracy |
|---:|----------------:|--------------------:|-----------------------:|----------------:|--------------------:|-----------------------:|----------------:|
|  0 |           88.06 |               88.06 |                  88.06 |           88.06 |               88.06 |                  88.09 |           88.06 |

* Evaluation on validation split
 
|    |   eval_f1_micro |   eval_recall_micro |   eval_precision_micro |   eval_f1_macro |   eval_recall_macro |   eval_precision_macro |   eval_accuracy |
|---:|----------------:|--------------------:|-----------------------:|----------------:|--------------------:|-----------------------:|----------------:|
|  0 |           88.51 |               88.51 |                  88.51 |           88.51 |               88.51 |                  88.54 |           88.51 |


Check the result file [here](https://huggingface.co./vocabtrimmer/roberta-base.xnli-en.5/raw/main/eval.json).