Adding Evaluation Results (#1)

- Adding Evaluation Results (c0ba443a099394617b8c4be45b13f4340084db14)


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:
 - VMware/open-instruct
+base_model: BEE-spoke-data/smol_llama-220M-GQA
 inference:
   parameters:
     do_sample: true
@@ -16,17 +16,114 @@ inference:
     no_repeat_ngram_size: 6
     epsilon_cutoff: 0.0006
 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:  
+- 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-open_instruct
+  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: 25.0
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-open_instruct
+      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: 29.71
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-open_instruct
+      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: 26.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-open_instruct
+      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: 44.06
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-open_instruct
+      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: 50.28
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-open_instruct
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-open_instruct
+      name: Open LLM Leaderboard
 ---
 
 
@@ -83,4 +180,17 @@ Feel free to experiment with the parameters using the model in Python and let us
 
 This was trained on `VMware/open-instruct` so do whatever you want, provided it falls under the base apache-2.0 license :)
 
----
+---
+# [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-open_instruct)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |29.19|
+|AI2 Reasoning Challenge (25-Shot)|25.00|
+|HellaSwag (10-Shot)              |29.71|
+|MMLU (5-Shot)                    |26.11|
+|TruthfulQA (0-shot)              |44.06|
+|Winogrande (5-shot)              |50.28|
+|GSM8k (5-shot)                   | 0.00|
+