Adding Evaluation Results

README.md

@@ -3,6 +3,109 @@ license: apache-2.0
 datasets:
 - databricks/databricks-dolly-15k
 - lucasmccabe-lmi/CodeAlpaca-20k
+model-index:
+- name: Instruct_Yi-6B_Dolly_CodeAlpaca
+  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: 53.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HenryJJ/Instruct_Yi-6B_Dolly_CodeAlpaca
+      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: 75.3
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HenryJJ/Instruct_Yi-6B_Dolly_CodeAlpaca
+      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: 63.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HenryJJ/Instruct_Yi-6B_Dolly_CodeAlpaca
+      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: 41.42
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HenryJJ/Instruct_Yi-6B_Dolly_CodeAlpaca
+      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: 75.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HenryJJ/Instruct_Yi-6B_Dolly_CodeAlpaca
+      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: 28.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HenryJJ/Instruct_Yi-6B_Dolly_CodeAlpaca
+      name: Open LLM Leaderboard
 ---
 
 
@@ -39,4 +142,17 @@ Fully opensourced at: https://github.com/hengjiUSTC/learn-llm/blob/main/trl_fine
 
 ```
 python3 trl_finetune.py --config configs/yi_6b-large.yml
-```
+```
+# [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_HenryJJ__Instruct_Yi-6B_Dolly_CodeAlpaca)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |56.11|
+|AI2 Reasoning Challenge (25-Shot)|53.16|
+|HellaSwag (10-Shot)              |75.30|
+|MMLU (5-Shot)                    |63.06|
+|TruthfulQA (0-shot)              |41.42|
+|Winogrande (5-shot)              |75.37|
+|GSM8k (5-shot)                   |28.35|
+