numerous expository enhancements and switch to DeBERTav3

Author: speediedan

lightning_examples/finetuning-scheduler/.meta.yml

@@ -16,5 +16,6 @@ requirements:
   - transformers
   - datasets
   - scikit-learn
+  - sentencepiece
 accelerator:
   - GPU

lightning_examples/finetuning-scheduler/RteBoolqModule_ft_schedule_deberta_base.yaml

@@ -0,0 +1,18 @@
+
+0:
+  params:
+  - model.classifier.bias
+  - model.classifier.weight
+  - model.pooler.dense.bias
+  - model.pooler.dense.weight
+  - model.deberta.encoder.LayerNorm.bias
+  - model.deberta.encoder.LayerNorm.weight
+  - model.deberta.encoder.rel_embeddings.weight
+  - model.deberta.encoder.layer.{0,11}.(output|attention|intermediate).*
+1:
+  params:
+  - model.deberta.embeddings.LayerNorm.bias
+  - model.deberta.embeddings.LayerNorm.weight
+2:
+  params:
+  - model.deberta.embeddings.word_embeddings.weight