Adding Evaluation Results

README.md

@@ -1,10 +1,113 @@
 ---
-license: llama2
-datasets:
-- YeungNLP/firefly-pretrain-dataset
 language:
 - zh
 - en
+license: llama2
+datasets:
+- YeungNLP/firefly-pretrain-dataset
+model-index:
+- name: 20231206094523-pretrain-Llama-2-13b-hf-76000
+  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: 31.06
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zyh3826/20231206094523-pretrain-Llama-2-13b-hf-76000
+      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: 52.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zyh3826/20231206094523-pretrain-Llama-2-13b-hf-76000
+      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: 24.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zyh3826/20231206094523-pretrain-Llama-2-13b-hf-76000
+      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: 44.71
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zyh3826/20231206094523-pretrain-Llama-2-13b-hf-76000
+      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: 61.25
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zyh3826/20231206094523-pretrain-Llama-2-13b-hf-76000
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zyh3826/20231206094523-pretrain-Llama-2-13b-hf-76000
+      name: Open LLM Leaderboard
 ---
 
 # Model Details
@@ -20,4 +123,17 @@ Please see the Responsible Use Guide available at https://ai.meta.com/llama/resp
 # License Disclaimer:
 This model is bound by the license & usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.
 
-全参数继续预训练中文llama2-13B，取76000步ckpt测试，其他细节待补充
+全参数继续预训练中文llama2-13B，取76000步ckpt测试，其他细节待补充
+# [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_zyh3826__20231206094523-pretrain-Llama-2-13b-hf-76000)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |35.58|
+|AI2 Reasoning Challenge (25-Shot)|31.06|
+|HellaSwag (10-Shot)              |52.03|
+|MMLU (5-Shot)                    |24.43|
+|TruthfulQA (0-shot)              |44.71|
+|Winogrande (5-shot)              |61.25|
+|GSM8k (5-shot)                   | 0.00|
+