Adding Evaluation Results

README.md

@@ -1,5 +1,108 @@
 ---
 license: llama2
+model-index:
+- name: llama2-13b-ft-openllm-leaderboard-v1
+  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: 59.64
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zyh3826/llama2-13b-ft-openllm-leaderboard-v1
+      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: 83.14
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zyh3826/llama2-13b-ft-openllm-leaderboard-v1
+      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: 60.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zyh3826/llama2-13b-ft-openllm-leaderboard-v1
+      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: 40.72
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zyh3826/llama2-13b-ft-openllm-leaderboard-v1
+      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: 77.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zyh3826/llama2-13b-ft-openllm-leaderboard-v1
+      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: 1.36
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zyh3826/llama2-13b-ft-openllm-leaderboard-v1
+      name: Open LLM Leaderboard
 ---
 finetue LLAMA2-13B myself
 20231024-172733
@@ -15,4 +118,17 @@ Llama2 and fine-tuned variants are a new technology that carries risks with use.
 Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/
 
 # 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.
+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.
+# [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__llama2-13b-ft-openllm-leaderboard-v1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |53.86|
+|AI2 Reasoning Challenge (25-Shot)|59.64|
+|HellaSwag (10-Shot)              |83.14|
+|MMLU (5-Shot)                    |60.93|
+|TruthfulQA (0-shot)              |40.72|
+|Winogrande (5-shot)              |77.35|
+|GSM8k (5-shot)                   | 1.36|
+