Adding Evaluation Results

README.md

@@ -1,64 +1,151 @@
 ---
 language:
-  - en
-  - fr
-  - ro
-  - de
-  - multilingual
-widget:
-  - text: 'Translate to German:  My name is Arthur'
-    example_title: Translation
-  - text: >-
-      Please answer to the following question. Who is going to be the next
-      Ballon d'or?
-    example_title: Question Answering
-  - text: >-
-      Q: Can Geoffrey Hinton have a conversation with George Washington? Give
-      the rationale before answering.
-    example_title: Logical reasoning
-  - text: >-
-      Please answer the following question. What is the boiling point of
-      Nitrogen?
-    example_title: Scientific knowledge
-  - text: >-
-      Answer the following yes/no question. Can you write a whole Haiku in a
-      single tweet?
-    example_title: Yes/no question
-  - text: >-
-      Answer the following yes/no question by reasoning step-by-step. Can you
-      write a whole Haiku in a single tweet?
-    example_title: Reasoning task
-  - text: 'Q: ( False or not False or False ) is? A: Let''s think step by step'
-    example_title: Boolean Expressions
-  - text: >-
-      The square root of x is the cube root of y. What is y to the power of 2,
-      if x = 4?
-    example_title: Math reasoning
-  - text: >-
-      Premise:  At my age you will probably have learnt one lesson. Hypothesis: 
-      It's not certain how many lessons you'll learn by your thirties. Does the
-      premise entail the hypothesis?
-    example_title: Premise and hypothesis
-  - text: >-
-      Answer the following question by reasoning step by step. 
-      The cafeteria had 23 apples. If they used 20 for lunch, and bought 6 more, how many apple do they have?
-    example_title: Chain of thought
+- en
+- fr
+- ro
+- de
+- multilingual
+license: apache-2.0
 tags:
-  - text2text-generation
-  - flan-ul2
+- text2text-generation
+- flan-ul2
 datasets:
-  - svakulenk0/qrecc
-  - taskmaster2
-  - djaym7/wiki_dialog
-  - deepmind/code_contests
-  - lambada
-  - gsm8k
-  - aqua_rat
-  - esnli
-  - quasc
-  - qed
-  - c4
-license: apache-2.0
+- svakulenk0/qrecc
+- taskmaster2
+- djaym7/wiki_dialog
+- deepmind/code_contests
+- lambada
+- gsm8k
+- aqua_rat
+- esnli
+- quasc
+- qed
+- c4
+widget:
+- text: 'Translate to German:  My name is Arthur'
+  example_title: Translation
+- text: Please answer to the following question. Who is going to be the next Ballon
+    d'or?
+  example_title: Question Answering
+- text: 'Q: Can Geoffrey Hinton have a conversation with George Washington? Give the
+    rationale before answering.'
+  example_title: Logical reasoning
+- text: Please answer the following question. What is the boiling point of Nitrogen?
+  example_title: Scientific knowledge
+- text: Answer the following yes/no question. Can you write a whole Haiku in a single
+    tweet?
+  example_title: Yes/no question
+- text: Answer the following yes/no question by reasoning step-by-step. Can you write
+    a whole Haiku in a single tweet?
+  example_title: Reasoning task
+- text: 'Q: ( False or not False or False ) is? A: Let''s think step by step'
+  example_title: Boolean Expressions
+- text: The square root of x is the cube root of y. What is y to the power of 2, if
+    x = 4?
+  example_title: Math reasoning
+- text: 'Premise:  At my age you will probably have learnt one lesson. Hypothesis:  It''s
+    not certain how many lessons you''ll learn by your thirties. Does the premise
+    entail the hypothesis?'
+  example_title: Premise and hypothesis
+- text: Answer the following question by reasoning step by step.  The cafeteria had
+    23 apples. If they used 20 for lunch, and bought 6 more, how many apple do they
+    have?
+  example_title: Chain of thought
+model-index:
+- name: flan-ul2
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 23.93
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=google/flan-ul2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 30.02
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=google/flan-ul2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 0.15
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=google/flan-ul2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.03
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=google/flan-ul2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.58
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=google/flan-ul2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 16.59
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=google/flan-ul2
+      name: Open LLM Leaderboard
 ---
 
 
@@ -244,4 +331,17 @@ This model was originally contributed by [Yi Tay](https://www.yitay.net/?author=
 
 # Citation
 
-If you want to cite this work, please consider citing the [blogpost](https://www.yitay.net/blog/flan-ul2-20b) announcing the release of `Flan-UL2`.
+If you want to cite this work, please consider citing the [blogpost](https://www.yitay.net/blog/flan-ul2-20b) announcing the release of `Flan-UL2`.
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_google__flan-ul2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |13.55|
+|IFEval (0-Shot)    |23.93|
+|BBH (3-Shot)       |30.02|
+|MATH Lvl 5 (4-Shot)| 0.15|
+|GPQA (0-shot)      | 5.03|
+|MuSR (0-shot)      | 5.58|
+|MMLU-PRO (5-shot)  |16.59|
+