Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
-license: apache-2.0
 language:
-  - en
+- en
+license: apache-2.0
 tags:
-  - sft
+- sft
 pipeline_tag: text-generation
 widget:
-  - text: <|prompter|>What is a meme, and what's the history behind this word?<|endoftext|><|assistant|>
-  - text: <|prompter|>What's the Earth total population<|endoftext|><|assistant|>
-  - text: <|prompter|>Write a story about future of AI development<|endoftext|><|assistant|>
+- text: <|prompter|>What is a meme, and what's the history behind this word?<|endoftext|><|assistant|>
+- text: <|prompter|>What's the Earth total population<|endoftext|><|assistant|>
+- text: <|prompter|>Write a story about future of AI development<|endoftext|><|assistant|>
+model-index:
+- name: oasst-sft-4-pythia-12b-epoch-3.5
+  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: 45.73
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
+      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: 68.59
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
+      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: 26.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
+      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: 37.81
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
+      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: 65.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
+      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: 3.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
+      name: Open LLM Leaderboard
 ---
 
 # Open-Assistant SFT-4 12B Model
@@ -136,4 +239,17 @@ zero config:
   "train_micro_batch_size_per_gpu": "auto",
   "wall_clock_breakdown": false
 }
-```
+```
+# [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_OpenAssistant__oasst-sft-4-pythia-12b-epoch-3.5)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |41.31|
+|AI2 Reasoning Challenge (25-Shot)|45.73|
+|HellaSwag (10-Shot)              |68.59|
+|MMLU (5-Shot)                    |26.82|
+|TruthfulQA (0-shot)              |37.81|
+|Winogrande (5-shot)              |65.90|
+|GSM8k (5-shot)                   | 3.03|
+