Adding Evaluation Results (#1)

- Adding Evaluation Results (bf710b10ffe7c0077d70f8e9780127aa7a461b0f)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: BEE-spoke-data/smol_llama-220M-GQA
 datasets:
 - teknium/openhermes
+base_model: BEE-spoke-data/smol_llama-220M-GQA
 inference:
   parameters:
     do_sample: true
@@ -16,17 +16,114 @@ inference:
     no_repeat_ngram_size: 5
     epsilon_cutoff: 0.0008
 widget:
-  - text: >
-      Below is an instruction that describes a task, paired with an input that
-      provides further context. Write a response that appropriately completes
-      the request.  
-         
-      ### Instruction:  
-        
-      Write an ode to Chipotle burritos. 
-        
-      ### Response:  
-    example_title: burritos
+- text: "Below is an instruction that describes a task, paired with an input that\
+    \ provides further context. Write a response that appropriately completes the\
+    \ request.  \n   \n### Instruction:  \n  \nWrite an ode to Chipotle burritos.\
+    \ \n  \n### Response:  \n"
+  example_title: burritos
+model-index:
+- name: smol_llama-220M-openhermes
+  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: 25.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-openhermes
+      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: 28.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-openhermes
+      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: 26.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-openhermes
+      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: 43.08
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-openhermes
+      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: 52.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-openhermes
+      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: 0.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-openhermes
+      name: Open LLM Leaderboard
 ---
 
 
@@ -87,3 +184,17 @@ Note that **this checkpoint** was fine-tuned on `teknium/openhermes`, which is g
 
 
 ---
+
+# [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_BEE-spoke-data__smol_llama-220M-openhermes)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |29.34|
+|AI2 Reasoning Challenge (25-Shot)|25.17|
+|HellaSwag (10-Shot)              |28.98|
+|MMLU (5-Shot)                    |26.17|
+|TruthfulQA (0-shot)              |43.08|
+|Winogrande (5-shot)              |52.01|
+|GSM8k (5-shot)                   | 0.61|
+