Adding Evaluation Results (#1)

- Adding Evaluation Results (f4b059bd62b557f03a08c4360ac3dcdd69ebb5a6)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -12,6 +12,101 @@ base_model:
 - meta-llama/Meta-Llama-3-8B
 datasets:
 - mlabonne/orpo-dpo-mix-40k
+model-index:
+- name: Llama-3-8B-Orpo-v0.1
+  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: 30.0
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Llama-3-8B-Orpo-v0.1
+      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: 13.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Llama-3-8B-Orpo-v0.1
+      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: 3.78
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Llama-3-8B-Orpo-v0.1
+      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: 1.57
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Llama-3-8B-Orpo-v0.1
+      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: 2.73
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Llama-3-8B-Orpo-v0.1
+      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: 14.23
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Llama-3-8B-Orpo-v0.1
+      name: Open LLM Leaderboard
 ---
 
 # dfurman/Llama-3-8B-Orpo-v0.1
@@ -128,4 +223,17 @@ Instructions:
 
 Enjoy! This spicy margarita has a nice balance of sweetness and acidity, with a subtle heat from the jalapeño that builds gradually as you sip."""
 ```
-</details>
+</details>
+# [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_dfurman__Llama-3-8B-Orpo-v0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |11.01|
+|IFEval (0-Shot)    |30.00|
+|BBH (3-Shot)       |13.77|
+|MATH Lvl 5 (4-Shot)| 3.78|
+|GPQA (0-shot)      | 1.57|
+|MuSR (0-shot)      | 2.73|
+|MMLU-PRO (5-shot)  |14.23|
+