README.md

vocabtrimmer/chinese-roberta-wwm-ext.xnli-zh.5

This model is a fine-tuned version of hfl/chinese-roberta-wwm-ext on the xnli (zh). Following metrics are computed on the test split of xnli(zh).

• 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	77.37	77.37	77.37	77.32	77.37	78.06	77.37

• 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	78.71	78.71	78.71	78.71	78.71	79.34	78.71

Check the result file here.