Adding Evaluation Results

README.md

@@ -1,24 +1,124 @@
 ---
 language:
 - en
+license: llama2
 library_name: peft
-pipeline_tag: text-generation
 tags:
 - Mistral
-license: llama2
+pipeline_tag: text-generation
 model-index:
 - name: SpeechlessCoder
   results:
   - task:
       type: text-generation
     dataset:
-      type: openai_humaneval
       name: HumanEval
+      type: openai_humaneval
     metrics:
-    - name: pass@1
-      type: pass@1
+    - type: pass@1
       value: 0.0
+      name: pass@1
       verified: false
+  - 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: 61.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/Mistral-7B-OpenOrca-lora-merged
+      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: 83.61
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/Mistral-7B-OpenOrca-lora-merged
+      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: 64.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/Mistral-7B-OpenOrca-lora-merged
+      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: 42.7
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/Mistral-7B-OpenOrca-lora-merged
+      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: 78.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/Mistral-7B-OpenOrca-lora-merged
+      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: 38.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/Mistral-7B-OpenOrca-lora-merged
+      name: Open LLM Leaderboard
 ---
 
 # Mistral-7B-OpenOrca-lora-merged
@@ -95,3 +195,17 @@ The following `bitsandbytes` quantization config was used during training:
 
 
 - PEFT 0.5.0
+
+# [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_uukuguy__Mistral-7B-OpenOrca-lora-merged)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |61.52|
+|AI2 Reasoning Challenge (25-Shot)|61.77|
+|HellaSwag (10-Shot)              |83.61|
+|MMLU (5-Shot)                    |64.34|
+|TruthfulQA (0-shot)              |42.70|
+|Winogrande (5-shot)              |78.53|
+|GSM8k (5-shot)                   |38.13|
+