Adding Evaluation Results

README.md

@@ -1,13 +1,7 @@
 ---
-license: apache-2.0
-datasets:
-- stanfordnlp/SHP
-- Anthropic/hh-rlhf
-- OpenAssistant/oasst1
 language:
 - en
-metrics:
-- accuracy
+license: apache-2.0
 tags:
 - human feedback
 - rlhf
@@ -17,6 +11,115 @@ tags:
 - halos
 - dpo
 - rl
+datasets:
+- stanfordnlp/SHP
+- Anthropic/hh-rlhf
+- OpenAssistant/oasst1
+metrics:
+- accuracy
+model-index:
+- name: archangel_sft-kto_llama13b
+  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: 56.14
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ContextualAI/archangel_sft-kto_llama13b
+      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: 80.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ContextualAI/archangel_sft-kto_llama13b
+      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: 47.84
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ContextualAI/archangel_sft-kto_llama13b
+      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: 39.42
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ContextualAI/archangel_sft-kto_llama13b
+      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: 76.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ContextualAI/archangel_sft-kto_llama13b
+      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: 16.83
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ContextualAI/archangel_sft-kto_llama13b
+      name: Open LLM Leaderboard
 ---
 
 ![halos](https://gist.github.com/assets/29318529/fe2d8391-dbd1-4b7e-9dc4-7cb97e55bc06)
@@ -54,4 +157,17 @@ If you find this repo or the technical paper useful in your research, please fee
   note = {https://github.com/ContextualAI/HALOs/blob/main/assets/report.pdf},
   year = {2023},
 }
-```
+```
+# [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_ContextualAI__archangel_sft-kto_llama13b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |52.87|
+|AI2 Reasoning Challenge (25-Shot)|56.14|
+|HellaSwag (10-Shot)              |80.80|
+|MMLU (5-Shot)                    |47.84|
+|TruthfulQA (0-shot)              |39.42|
+|Winogrande (5-shot)              |76.16|
+|GSM8k (5-shot)                   |16.83|
+