Adding Evaluation Results

README.md

@@ -1,11 +1,106 @@
 ---
 license: gemma
 library_name: transformers
-pipeline_tag: text-generation
-base_model: google/gemma-2-27b-it
 tags:
 - alignment-handbook
 - generated_from_trainer
+base_model: google/gemma-2-27b-it
+pipeline_tag: text-generation
+model-index:
+- name: gemma-2-27b-it-SimPO-37K
+  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: 24.07
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=AALF/gemma-2-27b-it-SimPO-37K
+      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: 15.31
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=AALF/gemma-2-27b-it-SimPO-37K
+      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: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=AALF/gemma-2-27b-it-SimPO-37K
+      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: 4.03
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=AALF/gemma-2-27b-it-SimPO-37K
+      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: 1.6
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=AALF/gemma-2-27b-it-SimPO-37K
+      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: 10.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=AALF/gemma-2-27b-it-SimPO-37K
+      name: Open LLM Leaderboard
 ---
 
 # gemma-2-27b-it-SimPO-37K Model Card
@@ -77,4 +172,17 @@ UltraFeedback paper:
   journal={arXiv preprint arXiv:2310.01377},
   year={2023}
 }
-```
+```
+# [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/AALF__gemma-2-27b-it-SimPO-37K-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 9.30|
+|IFEval (0-Shot)    |24.07|
+|BBH (3-Shot)       |15.31|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      | 4.03|
+|MuSR (0-shot)      | 1.60|
+|MMLU-PRO (5-shot)  |10.79|
+