Adding Evaluation Results

README.md

@@ -1,16 +1,16 @@
 ---
+language:
+- en
 license: apache-2.0
+tags:
+- merge
+- fine-tuned
 datasets:
 - cognitivecomputations/dolphin
 - cognitivecomputations/dolphin-coder
 - ise-uiuc/Magicoder-OSS-Instruct-75K
 - teknium/openhermes
 - migtissera/Synthia-v1.3
-language:
-- en
-tags:
-- merge
-- fine-tuned
 base_model:
 - mistralai/Mistral-7B-Instruct-v0.2
 - ehartford/dolphin-2.2.1-mistral-7b
@@ -26,6 +26,109 @@ base_model:
 - teknium/OpenHermes-2.5-Mistral-7B
 - Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
 - mlabonne/NeuralHermes-2.5-Mistral-7B
+model-index:
+- name: Mistral-7B-Merge-14-v0.3-ft-step-9984
+  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: 62.54
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.3-ft-step-9984
+      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: 82.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.3-ft-step-9984
+      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: 62.92
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.3-ft-step-9984
+      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: 53.7
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.3-ft-step-9984
+      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: 75.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.3-ft-step-9984
+      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: 25.25
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EmbeddedLLM/Mistral-7B-Merge-14-v0.3-ft-step-9984
+      name: Open LLM Leaderboard
 ---
 
 # Model Description
@@ -57,4 +160,17 @@ The model is scheduled to be fine-tuned for 3 epochs on 4 A100s using axolotl.
 
 # Shout-Out to OSS
 
-Thank you to the Open Source AI community for bringing together marvelous code frameworks and datasets.
+Thank you to the Open Source AI community for bringing together marvelous code frameworks and datasets.
+# [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_EmbeddedLLM__Mistral-7B-Merge-14-v0.3-ft-step-9984)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |60.37|
+|AI2 Reasoning Challenge (25-Shot)|62.54|
+|HellaSwag (10-Shot)              |82.18|
+|MMLU (5-Shot)                    |62.92|
+|TruthfulQA (0-shot)              |53.70|
+|Winogrande (5-shot)              |75.61|
+|GSM8k (5-shot)                   |25.25|
+