update: eval results

README.md

@@ -2,31 +2,28 @@
 pipeline_tag: text-generation
 inference: false
 license: apache-2.0
-# datasets:
-# metrics:
-# - code_eval
 library_name: transformers
 tags:
 - language
 - granite-3.0
 model-index:
-- name: granite-3.0-3b-a800m-instruct
+- name: granite-3.0-2b-instruct
   results:
   - task:
       type: text-generation
     dataset:
-        type: human-exams
-        name: MMLU
+        type: instruction-following
+        name: IFEval
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 42.49
       veriefied: false
   - task:
       type: text-generation
     dataset:
-        type: human-exams
-        name: MMLU-Pro
+        type: instruction-following
+        name: MT-Bench
     metrics:
     - name: pass@1
       type: pass@1
@@ -40,17 +37,27 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 25.70
       veriefied: false
   - task:
       type: text-generation
     dataset:
-        type: commonsense
-        name: WinoGrande
+        type: human-exams
+        name: MMLU
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 50.16
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: human-exams
+        name: MMLU-Pro
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 20.51
       veriefied: false
   - task:
       type: text-generation
@@ -60,7 +67,7 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 40.80
       veriefied: false
   - task:
       type: text-generation
@@ -70,27 +77,27 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 59.95
       veriefied: false
   - task:
       type: text-generation
     dataset:
         type: commonsense
-        name: PIQA
+        name: Hellaswag
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 71.86
       veriefied: false
   - task:
       type: text-generation
     dataset:
         type: commonsense
-        name: Hellaswag
+        name: WinoGrande
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 67.01
       veriefied: false
   - task:
       type: text-generation
@@ -100,7 +107,7 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 48.00
       veriefied: false
   - task:
       type: text-generation
@@ -110,17 +117,17 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 78.65
       veriefied: false
   - task:
       type: text-generation
     dataset:
         type: reading-comprehension
-        name: SQuAD v2
+        name: SQuAD 2.0
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 6.71
       veriefied: false
   - task:
       type: text-generation
@@ -130,7 +137,7 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 50.94
       veriefied: false
   - task:
       type: text-generation
@@ -140,7 +147,7 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 26.85
       veriefied: false
   - task:
       type: text-generation
@@ -150,17 +157,37 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 37.70
       veriefied: false
   - task:
       type: text-generation
     dataset:
         type: code
-        name: HumanEval
+        name: HumanEvalSynthesis
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 39.63
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: code
+        name: HumanEvalExplain
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 40.85
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: code
+        name: HumanEvalFix
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 35.98
       veriefied: false
   - task:
       type: text-generation
@@ -170,7 +197,7 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 27.40
       veriefied: false     
   - task:
       type: text-generation
@@ -180,7 +207,7 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 47.54
       veriefied: false 
   - task:
       type: text-generation
@@ -190,18 +217,28 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
+      value: 19.86
       veriefied: false   
   - task:
       type: text-generation
     dataset:
         type: multilingual
-        name: MGSM
+        name: PAWS-X (7 langs)
     metrics:
     - name: pass@1
       type: pass@1
-      value: 
-      veriefied: false
+      value: 50.23
+      veriefied: false 
+  - task:
+      type: text-generation
+    dataset:
+        type: multilingual
+        name: MGSM (6 langs)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 28.87
+      veriefied: false 
 ---
 
 <!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png) -->