Adding Evaluation Results (#1)

- Adding Evaluation Results (ef0c79a8d9c4c84e353ba2921e5d85a71a1aa14a)


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

README.md

@@ -1,9 +1,9 @@
 ---
 license: apache-2.0
-base_model: mistralai/Mistral-7B-v0.3
 tags:
 - generated_from_trainer
 - axolotl
+base_model: mistralai/Mistral-7B-v0.3
 datasets:
 - cognitivecomputations/Dolphin-2.9
 - teknium/OpenHermes-2.5
@@ -13,6 +13,101 @@ datasets:
 - microsoft/orca-math-word-problems-200k
 - Locutusque/function-calling-chatml
 - internlm/Agent-FLAN
+model-index:
+- name: dolphin-2.9.3-mistral-7B-32k
+  results:
+  - 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: 41.26
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-7B-32k
+      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: 26.91
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-7B-32k
+      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: 4.83
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-7B-32k
+      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: 4.7
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-7B-32k
+      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: 17.93
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-7B-32k
+      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: 20.23
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-7B-32k
+      name: Open LLM Leaderboard
 ---
 
 # Dolphin 2.9.3 Mistral 7b v0.3 32k 🐬
@@ -177,3 +272,17 @@ tokens:
   - "<|im_start|>"
 
 ```
+
+# [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/details_cognitivecomputations__dolphin-2.9.3-mistral-7B-32k)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |19.31|
+|IFEval (0-Shot)    |41.26|
+|BBH (3-Shot)       |26.91|
+|MATH Lvl 5 (4-Shot)| 4.83|
+|GPQA (0-shot)      | 4.70|
+|MuSR (0-shot)      |17.93|
+|MMLU-PRO (5-shot)  |20.23|
+