Adding Evaluation Results

README.md

@@ -1,9 +1,9 @@
 ---
+language:
+- en
 license: apache-2.0
 datasets:
 - HuggingFaceTB/cosmopedia
-language:
-- en
 inference:
   parameters:
     temperature: 0.6
@@ -11,15 +11,118 @@ inference:
     top_k: 50
     repetition_penalty: 1.2
 widget:
-  - text: 'Photosynthesis is'
-    example_title: Textbook
-    group: Completion
-  - text: '<s> [INST]  How to take care of plants? [/INST] '
-    example_title: Wikihow
-    group: Completion
-  - text: '<s> [INST] Generate a story about a flying cat [/INST] '
-    example_title: Story
-    group: Completion
+- text: Photosynthesis is
+  example_title: Textbook
+  group: Completion
+- text: '<s> [INST]  How to take care of plants? [/INST] '
+  example_title: Wikihow
+  group: Completion
+- text: '<s> [INST] Generate a story about a flying cat [/INST] '
+  example_title: Story
+  group: Completion
+model-index:
+- name: cosmo-1b
+  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: 38.57
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceTB/cosmo-1b
+      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: 55.13
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceTB/cosmo-1b
+      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: 26.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceTB/cosmo-1b
+      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: 38.15
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceTB/cosmo-1b
+      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: 55.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceTB/cosmo-1b
+      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: 5.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceTB/cosmo-1b
+      name: Open LLM Leaderboard
 ---
 
 # Model Summary
@@ -107,3 +210,17 @@ This is a small 1.8B model trained on synthetic data, so it might hallucinate, g
 The training loss:
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61c141342aac764ce1654e43/rJobY7F6tqTAvIox1ZGKR.png)
+
+# [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_HuggingFaceTB__cosmo-1b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |36.59|
+|AI2 Reasoning Challenge (25-Shot)|38.57|
+|HellaSwag (10-Shot)              |55.13|
+|MMLU (5-Shot)                    |26.69|
+|TruthfulQA (0-shot)              |38.15|
+|Winogrande (5-shot)              |55.49|
+|GSM8k (5-shot)                   | 5.53|
+