Adding Evaluation Results (#1)

- Adding Evaluation Results (11a22fd68633a525926143b21bc9d58bc42e77f5)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,11 +1,106 @@
 ---
-base_model: mistralai/Mistral-Nemo-Instruct-2407
 license: apache-2.0
 tags:
 - axolotl
 - dpo
 - trl
 - generated_from_trainer
+base_model: mistralai/Mistral-Nemo-Instruct-2407
+model-index:
+- name: Humanish-Mistral-Nemo-Instruct-2407
+  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: 54.51
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-Mistral-Nemo-Instruct-2407
+      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: 32.71
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-Mistral-Nemo-Instruct-2407
+      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: 7.63
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-Mistral-Nemo-Instruct-2407
+      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: 5.03
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-Mistral-Nemo-Instruct-2407
+      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: 9.4
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-Mistral-Nemo-Instruct-2407
+      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: 28.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-Mistral-Nemo-Instruct-2407
+      name: Open LLM Leaderboard
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -141,4 +236,17 @@ The following hyperparameters were used during training:
 - Transformers 4.45.1
 - Pytorch 2.3.1+cu121
 - Datasets 2.21.0
-- Tokenizers 0.20.0
+- Tokenizers 0.20.0
+# [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_HumanLLMs__Humanish-Mistral-Nemo-Instruct-2407)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.88|
+|IFEval (0-Shot)    |54.51|
+|BBH (3-Shot)       |32.71|
+|MATH Lvl 5 (4-Shot)| 7.63|
+|GPQA (0-shot)      | 5.03|
+|MuSR (0-shot)      | 9.40|
+|MMLU-PRO (5-shot)  |28.01|
+