Adding Evaluation Results

README.md

@@ -5,6 +5,105 @@ datasets:
 - vicgalle/configurable-system-prompt-multitask
 base_model:
 - Qwen/Qwen2.5-0.5B-Instruct
+model-index:
+- name: Qwen2.5-0.5B-Instruct-CrashCourse-dropout
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 29.49
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FQwen2.5-0.5B-Instruct-CrashCourse-dropout
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 7.23
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FQwen2.5-0.5B-Instruct-CrashCourse-dropout
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 0.08
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FQwen2.5-0.5B-Instruct-CrashCourse-dropout
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 1.79
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FQwen2.5-0.5B-Instruct-CrashCourse-dropout
+      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: 1.11
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FQwen2.5-0.5B-Instruct-CrashCourse-dropout
+      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: 6.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FQwen2.5-0.5B-Instruct-CrashCourse-dropout
+      name: Open LLM Leaderboard
 ---
 # Qwen2.5-0.5B-Instruct-CrashCourse-dropout
 
@@ -39,3 +138,18 @@ Users should be aware that this model, like all AI models, may reflect biases pr
 ## Additional Information
 
 For more details on the base model, please refer to the Qwen/Qwen2.5-0.5B-Instruct model card. For information about the datasets used in fine-tuning, check the respective dataset cards on the Hugging Face Hub.
+
+# [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/agentlans__Qwen2.5-0.5B-Instruct-CrashCourse-dropout-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=agentlans%2FQwen2.5-0.5B-Instruct-CrashCourse-dropout&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |     7.74|
+|IFEval (0-Shot)    |    29.49|
+|BBH (3-Shot)       |     7.23|
+|MATH Lvl 5 (4-Shot)|     0.08|
+|GPQA (0-shot)      |     1.79|
+|MuSR (0-shot)      |     1.11|
+|MMLU-PRO (5-shot)  |     6.76|
+