Adding Evaluation Results (#1)

- Adding Evaluation Results (049996fc6698ab89ce97d8de8de8978557df4046)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,32 +1,131 @@
 ---
 license: other
-license_name: gemma-terms-of-use
-license_link: https://ai.google.dev/gemma/terms
-base_model: HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
 tags:
 - alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+base_model: HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
 datasets:
 - argilla/dpo-mix-7k
+license_name: gemma-terms-of-use
+license_link: https://ai.google.dev/gemma/terms
 pipeline_tag: text-generation
 model-index:
 - name: zephyr-7b-gemma
   results:
-  # MT-Bench (taken from model card)
-  - task: 
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
       name: MT-Bench
       type: unknown
     metrics:
-       - type: unknown
-         name: score
-         value: 7.81
+    - type: unknown
+      value: 7.81
+      name: score
     source:
       url: https://huggingface.co/spaces/lmsys/mt-bench
+  - 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: 58.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-gemma-v0.1
+      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: 83.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-gemma-v0.1
+      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: 60.68
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-gemma-v0.1
+      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: 52.07
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-gemma-v0.1
+      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: 74.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-gemma-v0.1
+      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: 45.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-gemma-v0.1
+      name: Open LLM Leaderboard
 ---
 
 <img src="https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1/resolve/main/thumbnail.png" alt="Zephyr 7B Gemma Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
@@ -271,3 +370,17 @@ You may also wish to cite the creators of this model as well:
   howpublished = {\url{https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1}}
 }
 ```
+
+# [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_HuggingFaceH4__zephyr-7b-gemma-v0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |62.41|
+|AI2 Reasoning Challenge (25-Shot)|58.45|
+|HellaSwag (10-Shot)              |83.48|
+|MMLU (5-Shot)                    |60.68|
+|TruthfulQA (0-shot)              |52.07|
+|Winogrande (5-shot)              |74.19|
+|GSM8k (5-shot)                   |45.56|
+