Upload README.md

README.md

@@ -62,9 +62,21 @@ print(tokenizer.decode(outputs[0]))
 | Reading (eye tracking) | 0.93 |
 | Reading (self-paced) | 0.14 |
 
+### Results (fine-tuning, GLUE)
+
+| Task | Accuracy |
+|------|----------|
+| **BOOLQ** | **63.8** |
+| **MULTIRC** | **58.5** |
+| **RTE** | **61.2** |
+| **WSC** | **63.5** |
+| **MRPC** | **69.6** |
+| **QQP** | **69.6** |
+| **MNLI** | **43.6** |
+
 > Evaluated with [babylm-eval](https://github.com/babylm-org/babylm-eval) on
-> the strict track. Reading scores are correlation coefficients (higher is better
-> for eye tracking, lower is better for self-paced reading).
+> the strict track. Zero-shot tasks measure linguistic knowledge; fine-tuning
+> tasks measure transfer learning to downstream classification.
 
 ## Architecture