correct Tasksource rows to heterogeneous-split probes

README.md

@@ -31,8 +31,8 @@ It is LateOn (~149M parameters) fine-tuned on 512k real decisions covering three
 
 | Benchmark (1k examples each, same samples for every model) | v0 |
 |---|---|
-| Tasksource, unseen tasks | 58.9% |
-| Tasksource, unseen test tasks | 53.0% |
+| Tasksource, unseen tasks (all three judgment types) | 46.8% |
+| Tasksource, unseen test tasks (all three judgment types) | 49.7% |
 | Typed Decisions | 42.6% |
 | AG News | 73.8% |
 | Emotion | 49.0% |