Adding Evaluation Results

README.md

@@ -1,14 +1,130 @@
 ---
+license: cc-by-nc-4.0
 datasets:
 - glaiveai/glaive-code-assistant-v2
 - garage-bAInd/Open-Platypus
 - OpenAssistant/oasst_top1_2023-08-25
 - LDJnr/Capybara
-license: cc-by-nc-4.0
+model-index:
+- name: Mistral-7B-SFT
+  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: 46.5
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Mistral-7B-SFT
+      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: 75.69
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Mistral-7B-SFT
+      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: 51.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Mistral-7B-SFT
+      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: 52.02
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Mistral-7B-SFT
+      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: 72.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Mistral-7B-SFT
+      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: 17.44
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Mistral-7B-SFT
+      name: Open LLM Leaderboard
 ---
 # Model description
 This model serves as a general-purpose assistant. I have trained it to see which datasets work best in fine-tuning language models. 
 # Training
 This model was trained on the datasets shown on the page. 8 TPU V3 were used to do a full fine-tune on this model. 
 
-Early during training, this model suffered exploding gradients, so performance is not guaranteed.
+Early during training, this model suffered exploding gradients, so performance is not guaranteed.
+# [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_Locutusque__Mistral-7B-SFT)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |52.58|
+|AI2 Reasoning Challenge (25-Shot)|46.50|
+|HellaSwag (10-Shot)              |75.69|
+|MMLU (5-Shot)                    |51.04|
+|TruthfulQA (0-shot)              |52.02|
+|Winogrande (5-shot)              |72.77|
+|GSM8k (5-shot)                   |17.44|
+