Update README.md

README.md

@@ -1,20 +1,43 @@
 ---
 license: apache-2.0
 tags:
-- generated_from_trainer
+- distigpt2
+- hearthstone
 metrics:
 - bleu
+- dvitel/codebleu
+- exact_match
+- chrf
+datasets:
+- dvitel/hearthstone
 model-index:
 - name: h1
-  results: []
+  results:
+  - task:
+      type: text-generation
+      name: Python Code Synthesis
+    dataset:
+      type: dvitel/hearthstone
+      name: HearthStone
+      split: test
+    metrics:
+      - type: exact_match
+        value: 0.21212121212121213
+        name: Exact Match
+      - type: bleu
+        value: 0.9637468196180485
+        name: BLEU        
+      - type: dvitel/codebleu
+        value: 0.8884667222252154
+        name: CodeBLEU                
+      - type: dvitel/codebleu
+        value: 96.5942286007928
+        name: chrF     
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
 # h1
 
-This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on [hearthstone](https://huggingface.co/datasets/dvitel/hearthstone) dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0890
 - Exact Match: 0.1970
@@ -28,15 +51,24 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+DistilGPT2 applied onto HearthStone dataset with preprocessing of python code to dumped AST. Example:
+```python
+#gold labels
+Module([ClassDef('Innervate', [Name('SpellCard', Load())], [], [FunctionDef('__init__', arguments([], [arg('self', None, None)], None, [], [], None, []), [Expr(Call(Attribute(Call(Name('super', Load()), [], []), '__init__', Load()), [Constant('Innervate', None), Constant(0, None), Attribute(Name('CHARACTER_CLASS', Load()), 'DRUID', Load()), Attribute(Name('CARD_RARITY', Load()), 'FREE', Load())], []))], [], None, None), FunctionDef('use', arguments([], [arg('self', None, None), arg('player', None, None), arg('game', None, None)], None, [], [], None, []), [Expr(Call(Attribute(Call(Name('super', Load()), [], []), 'use', Load()), [Name('player', Load()), Name('game', Load())], [])), If(Compare(Attribute(Name('player', Load()),'mana', Load()), [Lt()], [Constant(8, None)]), [AugAssign(Attribute(Name('player', Load()),'mana', Store()), Add(), Constant(2, None))], [Assign([Attribute(Name('player', Load()),'mana', Store())], Constant(10, None), None)])], [], None, None)], [])], [])
+```
+```python
+#wrong prediction (example of error after training)
+Module([ClassDef('Innervate', [Name('SpellCard', Load())], [], [FunctionDef('__init__', arguments([], [arg('self', None, None)], None, [], [], None, []), [Expr(Call(Attribute(Call(Name('super', Load()), [], []), '__init__', Load()), [Constant('Innervate', None), Constant(0, None), Attribute(Name('CHARACTER_CLASS', Load()), 'DRUID', Load()), Attribute(Name('CARD_RARITY', Load()), 'FREE', Load())], []))], [], None, None), FunctionDef('use', arguments([], [arg('self', None, None), arg('player', None, None), arg('game', None, None)], None, [], [], None, []), [Expr(Call(Attribute(Call(Name('super', Load()), [], []), 'use', Load()), [Name('player', Load()), Name('game', Load())], [])), For(Compare(Attribute(Name('player', Load()),'maxa', Load()), [Lt()], [Constant(10, None)]), [AugAssign(Attribute(Name('player', Load()),'mana', Store()), Add(), Constant(2, None))], Exign([Name(Name('player', Load()),'mana', Store())], Constant(None, None), None)],], [], None, None)], [])], [])
+```
+
 
 ## Intended uses & limitations
 
-More information needed
+HearthStone card code synthesis. 
 
 ## Training and evaluation data
 
-More information needed
+See split of [hearthstone](https://huggingface.co/datasets/dvitel/hearthstone) dataset
 
 ## Training procedure