Adding Evaluation Results

README.md

@@ -1,5 +1,108 @@
 ---
 license: apache-2.0
+model-index:
+- name: alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2
+  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: 60.32
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2
+      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: 82.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2
+      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: 59.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2
+      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: 42.36
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2
+      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: 76.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2
+      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: 30.1
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2
+      name: Open LLM Leaderboard
 ---
 
 ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2---- 7k steps.
@@ -9,4 +112,17 @@ ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2---- 7k steps.
 ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2---- 7k steps.
 ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2---- 7k steps.
 ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2---- 7k steps.
-ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2---- 7k steps.
+ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2---- 7k steps.
+# [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_ewqr2130__alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |58.67|
+|AI2 Reasoning Challenge (25-Shot)|60.32|
+|HellaSwag (10-Shot)              |82.88|
+|MMLU (5-Shot)                    |59.79|
+|TruthfulQA (0-shot)              |42.36|
+|Winogrande (5-shot)              |76.56|
+|GSM8k (5-shot)                   |30.10|
+