Adding Evaluation Results

README.md

@@ -1,5 +1,108 @@
 ---
 license: apache-2.0
+model-index:
+- name: 7B_ppo_phiRM_2GPU_3e-7step_4000
+  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: 57.25
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
+      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: 80.24
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
+      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: 60.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
+      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: 41.48
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
+      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: 76.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
+      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: 29.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
+      name: Open LLM Leaderboard
 ---
 
 zephre 7B-sft---> PPO-7B
@@ -11,3 +114,17 @@ zephre 7B-sft---> PPO-7B
 zephre 7B-sft---> PPO-7B
 zephre 7B-sft---> PPO-7B
 zephre 7B-sft---> PPO-7B
+
+# [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__7B_ppo_phiRM_2GPU_3e-7step_4000)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |57.46|
+|AI2 Reasoning Challenge (25-Shot)|57.25|
+|HellaSwag (10-Shot)              |80.24|
+|MMLU (5-Shot)                    |60.06|
+|TruthfulQA (0-shot)              |41.48|
+|Winogrande (5-shot)              |76.32|
+|GSM8k (5-shot)                   |29.42|
+