Adding Evaluation Results

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- princeton-nlp/Llama-3-Instruct-8B-SimPO
-- UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
+license: llama3
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: llama3
+base_model:
+- princeton-nlp/Llama-3-Instruct-8B-SimPO
+- UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
 pipeline_tag: text-generation
+model-index:
+- name: Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
+  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: 42.71
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
+      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: 28.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
+      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: 9.37
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
+      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: 5.37
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
+      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: 9.54
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
+      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: 29.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
+      name: Open LLM Leaderboard
 ---
 # Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
 
@@ -63,3 +158,17 @@ parameters:
 dtype: bfloat16
 
 ```
+
+# [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_grimjim__Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.74|
+|IFEval (0-Shot)    |42.71|
+|BBH (3-Shot)       |28.26|
+|MATH Lvl 5 (4-Shot)| 9.37|
+|GPQA (0-shot)      | 5.37|
+|MuSR (0-shot)      | 9.54|
+|MMLU-PRO (5-shot)  |29.17|
+