Adding Evaluation Results

README.md

@@ -1,4 +1,7 @@
 ---
+language:
+- en
+license: apache-2.0
 datasets:
 - ehartford/dolphin
 - jondurbin/airoboros-2.2.1
@@ -7,9 +10,109 @@ datasets:
 - ise-uiuc/Magicoder-OSS-Instruct-75K
 - ise-uiuc/Magicoder-Evol-Instruct-110K
 - LDJnr/Capybara
-language:
-- en
-license: apache-2.0
+model-index:
+- name: UNA-dolphin-2.6-mistral-7b-dpo-laser
+  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: 67.15
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-dolphin-2.6-mistral-7b-dpo-laser
+      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: 86.31
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-dolphin-2.6-mistral-7b-dpo-laser
+      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: 63.36
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-dolphin-2.6-mistral-7b-dpo-laser
+      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: 64.15
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-dolphin-2.6-mistral-7b-dpo-laser
+      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: 79.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-dolphin-2.6-mistral-7b-dpo-laser
+      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: 44.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-dolphin-2.6-mistral-7b-dpo-laser
+      name: Open LLM Leaderboard
 ---
 
 UNA Dolphin 2.6 Mistral 7b 🐬
@@ -74,3 +177,17 @@ Please give ideas and a detailed plan about how to assemble and train an army of
 - And HUGE thanks to @winglian and the Axolotl contributors for making the best training framework!
 - [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
 
+
+# [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_fblgit__UNA-dolphin-2.6-mistral-7b-dpo-laser)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.43|
+|AI2 Reasoning Challenge (25-Shot)|67.15|
+|HellaSwag (10-Shot)              |86.31|
+|MMLU (5-Shot)                    |63.36|
+|TruthfulQA (0-shot)              |64.15|
+|Winogrande (5-shot)              |79.24|
+|GSM8k (5-shot)                   |44.35|
+