Adding Evaluation Results

README.md

@@ -43,6 +43,109 @@ datasets:
 - WhiteRabbitNeo/WRN-Chapter-1
 - WhiteRabbitNeo/WRN-Chapter-2
 - winogrande
+model-index:
+- name: bagel-dpo-7b-v0.5
+  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: 66.3
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-dpo-7b-v0.5
+      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: 84.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-dpo-7b-v0.5
+      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: 65.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-dpo-7b-v0.5
+      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: 62.41
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-dpo-7b-v0.5
+      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: 81.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-dpo-7b-v0.5
+      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: 53.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-dpo-7b-v0.5
+      name: Open LLM Leaderboard
 ---
 
 # A bagel, with everything
@@ -803,4 +906,17 @@ For assistance with the VM join the [Massed Compute Discord Server](https://disc
 
 - https://bmc.link/jondurbin
 - ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
-- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
+- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
+# [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_jondurbin__bagel-dpo-7b-v0.5)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.84|
+|AI2 Reasoning Challenge (25-Shot)|66.30|
+|HellaSwag (10-Shot)              |84.22|
+|MMLU (5-Shot)                    |65.27|
+|TruthfulQA (0-shot)              |62.41|
+|Winogrande (5-shot)              |81.45|
+|GSM8k (5-shot)                   |53.37|
+