Adding Evaluation Results (#1)

- Adding Evaluation Results (72a333261b744af72dcf144e2698eb3d01b98ad6)


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

README.md

@@ -1,12 +1,107 @@
 ---
-library_name: transformers
-license: apache-2.0
 language:
 - en
+license: apache-2.0
+library_name: transformers
 tags:
 - smollm2
 - smollm2-360m
 - distillation
+model-index:
+- name: d-SmolLM2-360M
+  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: 20.97
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=aloobun/d-SmolLM2-360M
+      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: 4.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=aloobun/d-SmolLM2-360M
+      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: 0.23
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=aloobun/d-SmolLM2-360M
+      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: 0.45
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=aloobun/d-SmolLM2-360M
+      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: 7.76
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=aloobun/d-SmolLM2-360M
+      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: 1.88
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=aloobun/d-SmolLM2-360M
+      name: Open LLM Leaderboard
 ---
 
 This is a distillation experiment with SmolLM2-1.7B as teacher and SmolLM2-360M as student model.
@@ -132,4 +227,17 @@ Well, it didn’t work as well as I hoped, will try again.
 | - leaderboard_math_intermediate_algebra_hard|      2|none  |     4|exact_match|↑  |0.0000|±  |0.0000|
 | - leaderboard_math_num_theory_hard          |      2|none  |     4|exact_match|↑  |0.0065|±  |0.0065|
 | - leaderboard_math_prealgebra_hard          |      2|none  |     4|exact_match|↑  |0.0104|±  |0.0073|
-| - leaderboard_math_precalculus_hard         |      2|none  |     4|exact_match|↑  |0.0000|±  |0.0000|
+| - leaderboard_math_precalculus_hard         |      2|none  |     4|exact_match|↑  |0.0000|±  |0.0000|
+# [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_aloobun__d-SmolLM2-360M)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 6.01|
+|IFEval (0-Shot)    |20.97|
+|BBH (3-Shot)       | 4.76|
+|MATH Lvl 5 (4-Shot)| 0.23|
+|GPQA (0-shot)      | 0.45|
+|MuSR (0-shot)      | 7.76|
+|MMLU-PRO (5-shot)  | 1.88|
+