Create README.md

README.md

@@ -0,0 +1,23 @@
+---
+datasets:
+- neurae/dnd_style_intents
+language:
+- en
+pipeline_tag: text-classification
+---
+
+This is bert base tuned with optimal lr, lr scheduler and weight decay on dnd-style-intents dataset.
+
+| parametrs     | value    |
+|---------------|----------|
+| learning rate | 1,3e-4   |
+| lr scheduler  | constant |
+| weight decay  | 7e-2     |
+
+Model has next metrics on test data from dataset
+
+| matric   | value |
+|----------|-------|
+| accuracy | 0,978 |
+| Macro F1 | 0,977 |
+| Micro F1 | 0,978 |