Adding Evaluation Results

README.md

@@ -1,13 +1,115 @@
 ---
-license: other
-license_name: tongyi-qianwen
-license_link: >-
-  https://huggingface.co/Qwen/Qwen1.5-72B/blob/main/LICENSE
 language:
 - en
-pipeline_tag: text-generation
+license: other
 tags:
 - pretrained, dpo
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen1.5-72B/blob/main/LICENSE
+pipeline_tag: text-generation
+model-index:
+- name: SkkuDS-DPO-72B-v3
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 66.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=logicker/SkkuDS-DPO-72B-v3
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 86.11
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=logicker/SkkuDS-DPO-72B-v3
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 77.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=logicker/SkkuDS-DPO-72B-v3
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 59.73
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=logicker/SkkuDS-DPO-72B-v3
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 82.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=logicker/SkkuDS-DPO-72B-v3
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.97
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=logicker/SkkuDS-DPO-72B-v3
+      name: Open LLM Leaderboard
 ---
 
 
@@ -47,3 +149,17 @@ KeyError: 'qwen2'.
   year={2023}
 }
 ```
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_logicker__SkkuDS-DPO-72B-v3)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |72.80|
+|AI2 Reasoning Challenge (25-Shot)|66.04|
+|HellaSwag (10-Shot)              |86.11|
+|MMLU (5-Shot)                    |77.34|
+|TruthfulQA (0-shot)              |59.73|
+|Winogrande (5-shot)              |82.64|
+|GSM8k (5-shot)                   |64.97|
+