Update README.md

README.md

@@ -32,9 +32,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model conducts unstructured magnitude pruning, quantization and distillation at the same time when finetuning on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.41159623861312866
-- Accuracy: 0.9139908256880734
-- Sparsity in transformer block linear layers: 0.8000002260561343
+- Torch loss: 0.4116
+- Torch accuracy: 0.9140
+- OpenVINO accuracy: 0.9106
+- Sparsity in transformer block linear layers: 0.80
 
 ## Setup