Adding Evaluation Results (#1)

- Adding Evaluation Results (7f542b6e0a014ffb9bc16bf3fbbd19160bc11447)


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

README.md

@@ -1,14 +1,117 @@
 ---
-license: apache-2.0
-datasets:
-- HuggingFaceH4/ultrachat_200k
-- Intel/orca_dpo_pairs
 language:
 - en
-pipeline_tag: text-generation
+license: apache-2.0
 tags:
 - gpt2
 - dpo
+datasets:
+- HuggingFaceH4/ultrachat_200k
+- Intel/orca_dpo_pairs
+pipeline_tag: text-generation
+model-index:
+- name: chat_gpt2_dpo
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 23.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/chat_gpt2_dpo
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 31.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/chat_gpt2_dpo
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 24.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/chat_gpt2_dpo
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 41.26
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/chat_gpt2_dpo
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 49.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/chat_gpt2_dpo
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/chat_gpt2_dpo
+      name: Open LLM Leaderboard
 ---
 This model is a finetuned version of ```Sharathhebbar24/chat_gpt2``` using ```Intel/orca_dpo_pairs``` on DPO
 
@@ -438,4 +541,17 @@ prompt.
     }
 }
 
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Sharathhebbar24__chat_gpt2_dpo)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |28.56|
+|AI2 Reasoning Challenge (25-Shot)|23.98|
+|HellaSwag (10-Shot)              |31.22|
+|MMLU (5-Shot)                    |24.95|
+|TruthfulQA (0-shot)              |41.26|
+|Winogrande (5-shot)              |49.96|
+|GSM8k (5-shot)                   | 0.00|
+