joey234
/

roberta-base-mnli-negnli

Text Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

joey234 commited on Oct 14, 2022

Commit

f25ee9d

•

1 Parent(s): 9478f0e

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 # roberta2-base-mnli-negnli
-This model is a fine-tuned version of [sileod/roberta-base-mnli](https://huggingface.co/sileod/roberta-base-mnli) on the MNLI subset containing negation.
 It achieves the following results on the evaluation set:
 - Loss: 0.8397
 - Accuracy: 0.8400

 # roberta2-base-mnli-negnli
+This model is a fine-tuned version of [sileod/roberta-base-mnli](https://huggingface.co/sileod/roberta-base-mnli) on the GLUE MNLI dataset and the [MNLI subset in NegNLI](https://github.com/mosharafhossain/negation-and-nli/tree/master/data/new_benchmarks/processed_for_run/MNLI).
 It achieves the following results on the evaluation set:
 - Loss: 0.8397
 - Accuracy: 0.8400