Adding Evaluation Results

README.md

@@ -1,9 +1,112 @@
 ---
+language:
+- en
 license: cc-by-nc-4.0
 datasets:
 - vicgalle/alpaca-gpt4
-language:
-- en
+model-index:
+- name: ShortKingv0.1
+  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: 34.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AtAndDev/ShortKingv0.1
+      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: 54.59
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AtAndDev/ShortKingv0.1
+      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: 25.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AtAndDev/ShortKingv0.1
+      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: 41.64
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AtAndDev/ShortKingv0.1
+      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: 56.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AtAndDev/ShortKingv0.1
+      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: 0.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AtAndDev/ShortKingv0.1
+      name: Open LLM Leaderboard
 ---
 
 ## Model Overview
@@ -36,4 +139,17 @@ This model took `2:31:23` to train in QLoRA on a single  `T4`  GPU.<br>
  - *weight decay*:  `0.001`
  - *optimizer*:  `paged_adamw_32bit`
  - *learning rate schedule*:  `cosine`
- - *warmup ratio (linear)*:  `0.03`
+ - *warmup ratio (linear)*:  `0.03`
+# [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_AtAndDev__ShortKingv0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |35.45|
+|AI2 Reasoning Challenge (25-Shot)|34.22|
+|HellaSwag (10-Shot)              |54.59|
+|MMLU (5-Shot)                    |25.78|
+|TruthfulQA (0-shot)              |41.64|
+|Winogrande (5-shot)              |56.04|
+|GSM8k (5-shot)                   | 0.45|
+