Adding Evaluation Results

README.md

@@ -1,12 +1,115 @@
 ---
 license: mit
-datasets:
-- neovalle/H4rmony_dpo
 tags:
 - ecology
 - sustainability
 - ecolinguistics
 - dpo
+datasets:
+- neovalle/H4rmony_dpo
+model-index:
+- name: H4rmoniousAnthea
+  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: 65.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=neovalle/H4rmoniousAnthea
+      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: 84.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=neovalle/H4rmoniousAnthea
+      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: 63.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=neovalle/H4rmoniousAnthea
+      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: 55.08
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=neovalle/H4rmoniousAnthea
+      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: 76.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=neovalle/H4rmoniousAnthea
+      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: 12.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=neovalle/H4rmoniousAnthea
+      name: Open LLM Leaderboard
 ---
 
 # Model Details
@@ -56,3 +159,17 @@ Trained using DPO
 # Training Data
 
 H4rmony Dataset - https://huggingface.co/datasets/neovalle/H4rmony_dpo
+
+# [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_neovalle__H4rmoniousAnthea)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |59.76|
+|AI2 Reasoning Challenge (25-Shot)|65.87|
+|HellaSwag (10-Shot)              |84.09|
+|MMLU (5-Shot)                    |63.67|
+|TruthfulQA (0-shot)              |55.08|
+|Winogrande (5-shot)              |76.87|
+|GSM8k (5-shot)                   |12.96|
+