Adding Evaluation Results

README.md

@@ -1,7 +1,5 @@
 ---
 license: other
-license_name: yi-license
-license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
 datasets:
 - ai2_arc
 - unalignment/spicy-3.1
@@ -27,11 +25,116 @@ 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
+license_name: yi-license
+license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
+model-index:
+- name: bagel-34b-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: 68.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-34b-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: 83.72
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-34b-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: 76.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-34b-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: 59.26
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-34b-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: 83.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-34b-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: 46.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-34b-v0.2
+      name: Open LLM Leaderboard
 ---
 
 # A bagel, with everything (except DPO)
@@ -208,4 +311,17 @@ To help me with the OpenAI/compute costs:
 
 - 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-34b-v0.2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.70|
+|AI2 Reasoning Challenge (25-Shot)|68.77|
+|HellaSwag (10-Shot)              |83.72|
+|MMLU (5-Shot)                    |76.45|
+|TruthfulQA (0-shot)              |59.26|
+|Winogrande (5-shot)              |83.82|
+|GSM8k (5-shot)                   |46.17|
+