Adding Evaluation Results

README.md

@@ -7,16 +7,16 @@ language:
 - vi
 - ms
 - lo
+license: apache-2.0
+tags:
+- multilingual
+- sea
+- sailor
 datasets:
 - cerebras/SlimPajama-627B
 - Skywork/SkyPile-150B
 - allenai/MADLAD-400
 - cc100
-tags:
-- multilingual
-- sea
-- sailor
-license: apache-2.0
 base_model: Qwen/Qwen1.5-4B
 model-index:
 - name: Sailor-4B
@@ -27,117 +27,217 @@ model-index:
       name: XQuAD-Thai
       type: XQuAD-Thai
     metrics:
-    - name: EM (3-Shot)
-      type: EM (3-Shot)
+    - type: EM (3-Shot)
       value: 46.82
-    - name: F1 (3-Shot)
-      type: F1 (3-Shot)
+      name: EM (3-Shot)
+    - type: F1 (3-Shot)
       value: 63.34
+      name: F1 (3-Shot)
   - task:
       type: text-generation
     dataset:
       name: TyDiQA-Indonesian
       type: TyDiQA-Indonesian
     metrics:
-    - name: EM (3-Shot)
-      type: EM (3-Shot)
+    - type: EM (3-Shot)
       value: 53.98
-    - name: F1 (3-Shot)
-      type: F1 (3-Shot)
+      name: EM (3-Shot)
+    - type: F1 (3-Shot)
       value: 73.48
+      name: F1 (3-Shot)
   - task:
       type: text-generation
     dataset:
       name: XQuAD-Vietnamese
       type: XQuAD-Vietnamese
     metrics:
-    - name: EM (3-Shot)
-      type: EM (3-Shot)
+    - type: EM (3-Shot)
       value: 47.65
-    - name: F1 (3-Shot)
-      type: F1 (3-Shot)
+      name: EM (3-Shot)
+    - type: F1 (3-Shot)
       value: 67.09
+      name: F1 (3-Shot)
   - task:
       type: text-generation
     dataset:
       name: XCOPA-Thai
       type: XCOPA-Thai
     metrics:
-    - name: EM (3-Shot)
-      type: EM (3-Shot)
+    - type: EM (3-Shot)
       value: 53.4
+      name: EM (3-Shot)
   - task:
       type: text-generation
     dataset:
       name: XCOPA-Indonesian
       type: XCOPA-Indonesian
     metrics:
-    - name: EM (3-Shot)
-      type: EM (3-Shot)
-      value: 69.20
+    - type: EM (3-Shot)
+      value: 69.2
+      name: EM (3-Shot)
   - task:
       type: text-generation
     dataset:
       name: XCOPA-Vietnamese
       type: XCOPA-Vietnamese
     metrics:
-    - name: EM (3-Shot)
-      type: EM (3-Shot)
-      value: 68.20
+    - type: EM (3-Shot)
+      value: 68.2
+      name: EM (3-Shot)
   - task:
       type: text-generation
     dataset:
       name: M3Exam-Thai
       type: M3Exam-Thai
     metrics:
-    - name: EM (3-Shot)
-      type: EM (3-Shot)
+    - type: EM (3-Shot)
       value: 27.88
+      name: EM (3-Shot)
   - task:
       type: text-generation
     dataset:
       name: M3Exam-Indonesian
       type: M3Exam-Indonesian
     metrics:
-    - name: EM (3-Shot)
-      type: EM (3-Shot)
+    - type: EM (3-Shot)
       value: 31.27
+      name: EM (3-Shot)
   - task:
       type: text-generation
     dataset:
       name: M3Exam-Vietnamese
       type: M3Exam-Vietnamese
     metrics:
-    - name: EM (3-Shot)
-      type: EM (3-Shot)
+    - type: EM (3-Shot)
       value: 40.69
+      name: EM (3-Shot)
   - task:
       type: text-generation
     dataset:
       name: BELEBELE-Thai
       type: BELEBELE-Thai
     metrics:
-    - name: EM (3-Shot)
-      type: EM (3-Shot)
+    - type: EM (3-Shot)
       value: 36.11
+      name: EM (3-Shot)
   - task:
       type: text-generation
     dataset:
       name: BELEBELE-Indonesian
       type: BELEBELE-Indonesian
     metrics:
-    - name: EM (3-Shot)
-      type: EM (3-Shot)
+    - type: EM (3-Shot)
       value: 41.33
+      name: EM (3-Shot)
   - task:
       type: text-generation
     dataset:
       name: BELEBELE-Vietnamese
       type: BELEBELE-Vietnamese
     metrics:
-    - name: EM (3-Shot)
-      type: EM (3-Shot)
+    - type: EM (3-Shot)
       value: 38.89
+      name: EM (3-Shot)
+  - 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: 44.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sail/Sailor-4B
+      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: 69.53
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sail/Sailor-4B
+      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: 38.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sail/Sailor-4B
+      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: 37.02
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sail/Sailor-4B
+      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: 66.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sail/Sailor-4B
+      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: 9.1
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sail/Sailor-4B
+      name: Open LLM Leaderboard
 ---
 
 <div align="center">
@@ -210,4 +310,17 @@ No restrict on the research and the commercial use, but should comply with the [
 
 # Contact Us
 
-If you have any questions, please raise an issue or contact us at [doulx@sea.com](mailto:doulx@sea.com) or [liuqian@sea.com](mailto:liuqian@sea.com).
+If you have any questions, please raise an issue or contact us at [doulx@sea.com](mailto:doulx@sea.com) or [liuqian@sea.com](mailto:liuqian@sea.com).
+# [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_sail__Sailor-4B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |44.19|
+|AI2 Reasoning Challenge (25-Shot)|44.45|
+|HellaSwag (10-Shot)              |69.53|
+|MMLU (5-Shot)                    |38.99|
+|TruthfulQA (0-shot)              |37.02|
+|Winogrande (5-shot)              |66.06|
+|GSM8k (5-shot)                   | 9.10|
+