Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,34 +1,32 @@
 ---
+language:
+- en
+license: mit
 tags:
 - generated_from_trainer
-license: mit
+base_model: mistralai/Mistral-7B-v0.1
 datasets:
 - HuggingFaceH4/ultrachat_200k
 - HuggingFaceH4/ultrafeedback_binarized
-language:
-- en
-base_model: mistralai/Mistral-7B-v0.1
 widget:
-  - example_title: Pirate!
-    messages:
-      - role: system
-        content: You are a pirate chatbot who always responds with Arr!
-      - role: user
-        content: "There's a llama on my lawn, how can I get rid of him?"
-    output:
-      text: >-
-        Arr! 'Tis a puzzlin' matter, me hearty! A llama on yer lawn be a rare
-        sight, but I've got a plan that might help ye get rid of 'im. Ye'll need
-        to gather some carrots and hay, and then lure the llama away with the
-        promise of a tasty treat. Once he's gone, ye can clean up yer lawn and
-        enjoy the peace and quiet once again. But beware, me hearty, for there
-        may be more llamas where that one came from! Arr!
+- example_title: Pirate!
+  messages:
+  - role: system
+    content: You are a pirate chatbot who always responds with Arr!
+  - role: user
+    content: There's a llama on my lawn, how can I get rid of him?
+  output:
+    text: Arr! 'Tis a puzzlin' matter, me hearty! A llama on yer lawn be a rare sight,
+      but I've got a plan that might help ye get rid of 'im. Ye'll need to gather
+      some carrots and hay, and then lure the llama away with the promise of a tasty
+      treat. Once he's gone, ye can clean up yer lawn and enjoy the peace and quiet
+      once again. But beware, me hearty, for there may be more llamas where that one
+      came from! Arr!
 pipeline_tag: text-generation
 model-index:
 - name: zephyr-7b-beta
   results:
-  # AI2 Reasoning Challenge (25-Shot)
-  - task: 
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -39,15 +37,13 @@ model-index:
       args:
         num_few_shot: 25
     metrics:
-       - type: acc_norm
-         name: normalized accuracy
-         value: 62.03071672354948
+    - type: acc_norm
+      value: 62.03071672354948
+      name: normalized accuracy
     source:
-      name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # HellaSwag (10-shot)
-  - task: 
+      name: Open LLM Leaderboard
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -57,15 +53,13 @@ model-index:
       args:
         num_few_shot: 10
     metrics:
-       - type: acc_norm
-         name: normalized accuracy
-         value: 84.35570603465445
+    - type: acc_norm
+      value: 84.35570603465445
+      name: normalized accuracy
     source:
-      name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # DROP (3-shot)
-  - task: 
+      name: Open LLM Leaderboard
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -75,15 +69,13 @@ model-index:
       args:
         num_few_shot: 3
     metrics:
-       - type: f1
-         name: f1 score
-         value: 9.662437080536909
+    - type: f1
+      value: 9.66243708053691
+      name: f1 score
     source:
-      name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # TruthfulQA (0-shot)
-  - task: 
+      name: Open LLM Leaderboard
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -94,14 +86,12 @@ model-index:
       args:
         num_few_shot: 0
     metrics:
-       - type: mc2
-         value: 57.44916942762855
+    - type: mc2
+      value: 57.44916942762855
     source:
-      name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # GSM8k (5-shot)
-  - task: 
+      name: Open LLM Leaderboard
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -112,15 +102,13 @@ model-index:
       args:
         num_few_shot: 5
     metrics:
-       - type: acc
-         name: accuracy
-         value: 12.736921910538287
+    - type: acc
+      value: 12.736921910538287
+      name: accuracy
     source:
-      name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # MMLU (5-Shot)
-  - task: 
+      name: Open LLM Leaderboard
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -131,15 +119,13 @@ model-index:
       args:
         num_few_shot: 5
     metrics:
-       - type: acc
-         name: accuracy
-         value: 61.07
+    - type: acc
+      value: 61.07
+      name: accuracy
     source:
-      name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # Winogrande (5-shot)
-  - task: 
+      name: Open LLM Leaderboard
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -150,40 +136,128 @@ model-index:
       args:
         num_few_shot: 5
     metrics:
-       - type: acc
-         name: accuracy
-         value: 77.74269928966061
+    - type: acc
+      value: 77.7426992896606
+      name: accuracy
     source:
-      name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # AlpacaEval (taken from model card)
-  - task: 
+      name: Open LLM Leaderboard
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
       name: AlpacaEval
       type: tatsu-lab/alpaca_eval
     metrics:
-       - type: unknown
-         name: win rate
-         value: 0.9060
+    - type: unknown
+      value: 0.906
+      name: win rate
     source:
       url: https://tatsu-lab.github.io/alpaca_eval/
-
-  # 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: 7.34
+    - type: unknown
+      value: 7.34
+      name: score
     source:
       url: https://huggingface.co/spaces/lmsys/mt-bench
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 49.5
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 21.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 2.72
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.37
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 7.73
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 19.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+      name: Open LLM Leaderboard
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -441,4 +515,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 | TruthfulQA (0-shot)   | 57.45   |
 | Winogrande (5-shot)   | 77.74   |
 | GSM8K (5-shot)        | 12.74        |
-| DROP (3-shot)         | 9.66         |
+| DROP (3-shot)         | 9.66         |
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/HuggingFaceH4__zephyr-7b-beta-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |17.77|
+|IFEval (0-Shot)    |49.50|
+|BBH (3-Shot)       |21.49|
+|MATH Lvl 5 (4-Shot)| 2.72|
+|GPQA (0-shot)      | 5.37|
+|MuSR (0-shot)      | 7.73|
+|MMLU-PRO (5-shot)  |19.79|
+