Adding Evaluation Results

README.md

@@ -5,6 +5,109 @@ datasets:
 - ise-uiuc/Magicoder-Evol-Instruct-110K
 - tatsu-lab/alpaca
 - garage-bAInd/Open-Platypus
+model-index:
+- name: AIRIC-The-Mistral
+  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: 59.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericpolewski/AIRIC-The-Mistral
+      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: 82.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericpolewski/AIRIC-The-Mistral
+      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: 60.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericpolewski/AIRIC-The-Mistral
+      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: 48.24
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericpolewski/AIRIC-The-Mistral
+      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: 76.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericpolewski/AIRIC-The-Mistral
+      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: 30.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericpolewski/AIRIC-The-Mistral
+      name: Open LLM Leaderboard
 ---
 
 This is Mistral-v0.1 and a combination of the AIRIC dataset sprinkled into the other datasets listed. Trained for 3 epochs at rank 128 until loss hit about 1.37. I noticed some "it's important to remembers" in there that I may try to scrub out but otherwise the model wasn't intentionally censored.
@@ -20,3 +123,17 @@ This is an instruct model trained in the Alpaca format.
 5-bit exl2 available at https://huggingface.co/ericpolewski/AIRIC-The-Mistral-5.0bpw-exl2
 
 8-bit exl2 available at https://huggingface.co/ericpolewski/AIRIC-The-Mistral-8.0bpw-exl2
+
+# [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_ericpolewski__AIRIC-The-Mistral)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |59.95|
+|AI2 Reasoning Challenge (25-Shot)|59.98|
+|HellaSwag (10-Shot)              |82.98|
+|MMLU (5-Shot)                    |60.67|
+|TruthfulQA (0-shot)              |48.24|
+|Winogrande (5-shot)              |76.95|
+|GSM8k (5-shot)                   |30.86|
+