Adding Evaluation Results

README.md

@@ -25,11 +25,114 @@ datasets:
 - Intel/orca_dpo_pairs
 - unalignment/toxic-dpo-v0.1
 - jondurbin/truthy-dpo-v0.1
-- allenai/ultrafeedback_binarized_cleaned 
+- allenai/ultrafeedback_binarized_cleaned
 - Squish42/bluemoon-fandom-1-1-rp-cleaned
 - LDJnr/Capybara
 - JULIELab/EmoBank
 - kingbri/PIPPA-shareGPT
+model-index:
+- name: bagel-8x7b-v0.2
+  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: 68.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-8x7b-v0.2
+      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: 86.32
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-8x7b-v0.2
+      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: 70.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-8x7b-v0.2
+      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: 60.03
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-8x7b-v0.2
+      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: 81.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-8x7b-v0.2
+      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: 4.7
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-8x7b-v0.2
+      name: Open LLM Leaderboard
 ---
 
 # A bagel, with everything (except DPO)
@@ -433,4 +536,17 @@ I am not a lawyer, so I can't help determine if this is actually commercially vi
 - If the dataset was released under a permissive license, but actually includes OpenAI generated data, does that ToS supersede the license?
 - Does the dataset fall completely under fair use anyways, since the model isn't really capable of reproducing the entire training set verbatim?
 
-Use your best judgement and seek legal advice if you are concerned about the terms.  In any case, by using this model, you agree to completely indemnify me.
+Use your best judgement and seek legal advice if you are concerned about the terms.  In any case, by using this model, you agree to completely indemnify me.
+# [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-8x7b-v0.2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |61.83|
+|AI2 Reasoning Challenge (25-Shot)|68.26|
+|HellaSwag (10-Shot)              |86.32|
+|MMLU (5-Shot)                    |70.40|
+|TruthfulQA (0-shot)              |60.03|
+|Winogrande (5-shot)              |81.29|
+|GSM8k (5-shot)                   | 4.70|
+