Adding Evaluation Results

README.md

@@ -1,14 +1,109 @@
 ---
+license: apache-2.0
 library_name: peft
 tags:
 - nlp
 - code
 - instruct
 - llama
+base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 datasets:
 - Intel/orca_dpo_pairs
-base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
-license: apache-2.0
+model-index:
+- name: Llama-3_1-8B-Instruct-orca-ORPO
+  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: 22.73
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=monsterapi/Llama-3_1-8B-Instruct-orca-ORPO
+      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: 1.34
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=monsterapi/Llama-3_1-8B-Instruct-orca-ORPO
+      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=monsterapi/Llama-3_1-8B-Instruct-orca-ORPO
+      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: 0.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=monsterapi/Llama-3_1-8B-Instruct-orca-ORPO
+      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: 3.06
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=monsterapi/Llama-3_1-8B-Instruct-orca-ORPO
+      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: 1.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=monsterapi/Llama-3_1-8B-Instruct-orca-ORPO
+      name: Open LLM Leaderboard
 ---
 
 ### Finetuning Overview:
@@ -37,3 +132,17 @@ This finetuning run was performed using [MonsterAPI](https://monsterapi.ai)'s LL
 - **Data Split:** 90% train 10% validation
 - **Gradient Accumulation Steps:** 16
 
+
+# [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/monsterapi__Llama-3_1-8B-Instruct-orca-ORPO-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 4.83|
+|IFEval (0-Shot)    |22.73|
+|BBH (3-Shot)       | 1.34|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      | 0.00|
+|MuSR (0-shot)      | 3.06|
+|MMLU-PRO (5-shot)  | 1.86|
+