Adding Evaluation Results (#6)

- Adding Evaluation Results (3d39250b94894dab101a7aa73428a160aabe2a92)


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

README.md

@@ -1,11 +1,114 @@
 ---
-license: apache-2.0
-datasets:
-- 64bits/lima_vicuna_format
 language:
 - en
+license: apache-2.0
 library_name: transformers
+datasets:
+- 64bits/lima_vicuna_format
 pipeline_tag: text-generation
+model-index:
+- name: Bean-3B
+  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: 40.36
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Bean-3B
+      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: 72.0
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Bean-3B
+      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: 26.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Bean-3B
+      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: 36.11
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Bean-3B
+      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: 65.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Bean-3B
+      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: 0.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Bean-3B
+      name: Open LLM Leaderboard
 ---
 
 <a href="https://www.buymeacoffee.com/acrastt" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
@@ -34,3 +137,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 | TruthfulQA (0-shot)   | 36.11   |
 | Winogrande (5-shot)   | 65.67   |
 | GSM8K (5-shot)        | 0.53        |
+
+# [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_acrastt__Bean-3B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |40.18|
+|AI2 Reasoning Challenge (25-Shot)|40.36|
+|HellaSwag (10-Shot)              |72.00|
+|MMLU (5-Shot)                    |26.43|
+|TruthfulQA (0-shot)              |36.11|
+|Winogrande (5-shot)              |65.67|
+|GSM8k (5-shot)                   | 0.53|
+