Adding Evaluation Results

README.md

@@ -10,6 +10,101 @@ widget:
 - messages:
   - role: user
     content: What is your favorite condiment?
+model-index:
+- name: autotrain-llama3-70b-orpo-v2
+  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: 54.06
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abhishek/autotrain-llama3-70b-orpo-v2
+      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: 39.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abhishek/autotrain-llama3-70b-orpo-v2
+      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: 18.73
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abhishek/autotrain-llama3-70b-orpo-v2
+      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: 5.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abhishek/autotrain-llama3-70b-orpo-v2
+      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: 9.95
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abhishek/autotrain-llama3-70b-orpo-v2
+      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: 42.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abhishek/autotrain-llama3-70b-orpo-v2
+      name: Open LLM Leaderboard
 ---
 
 # Model Trained Using AutoTrain
@@ -42,4 +137,17 @@ response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tok
 
 # Model response: "Hello! How can I assist you today?"
 print(response)
-```
+```
+# [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_abhishek__autotrain-llama3-70b-orpo-v2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.48|
+|IFEval (0-Shot)    |54.06|
+|BBH (3-Shot)       |39.88|
+|MATH Lvl 5 (4-Shot)|18.73|
+|GPQA (0-shot)      | 5.82|
+|MuSR (0-shot)      | 9.95|
+|MMLU-PRO (5-shot)  |42.42|
+