Adding Evaluation Results (#3)

- Adding Evaluation Results (06df4cb6333dfe20cda841370114db9e80c8c6d4)


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

README.md

@@ -1,58 +1,151 @@
 ---
-base_model: mwitiderrick/open_llama_3b_code_instruct_0.1
+language:
+- en
+license: apache-2.0
+library_name: transformers
+tags:
+- transformers
 datasets:
 - mwitiderrick/AlpacaCode
+base_model: mwitiderrick/open_llama_3b_code_instruct_0.1
 inference: true
 model_type: llama
-prompt_template: |
-  <s>[INST] 
-  {prompt}
-  [/INST]
+prompt_template: "<s>[INST] \n{prompt}\n[/INST]\n"
 created_by: mwitiderrick
-tags:
-- transformers
-license: apache-2.0
-language:
-- en
-library_name: transformers
 pipeline_tag: text-generation
-
 model-index:
-  - name: mwitiderrick/open_llama_3b_instruct_v_0.2
-    results:
-      - task:
-          type: text-generation
-        dataset:
-          name: hellaswag
-          type: hellaswag
-        metrics:
-          - name: hellaswag(0-Shot)
-            type: hellaswag (0-Shot)
-            value: 0.6600
-      - task:
-          type: text-generation
-        dataset:
-          name: winogrande
-          type: winogrande
-        metrics:
-          - name: winogrande(0-Shot)
-            type: winogrande (0-Shot)
-            value: 0.6322
-
-      - task:
-          type: text-generation
-        dataset:
-          name: arc_challenge
-          type: arc_challenge
-        metrics:
-          - name: arc_challenge(0-Shot)
-            type: arc_challenge (0-Shot)
-            value: 0.3447
-        source:
-          name: open_llama_3b_instruct_v_0.2 model card
-          url: https://huggingface.co/mwitiderrick/open_llama_3b_instruct_v_0.2
-
-          
+- name: mwitiderrick/open_llama_3b_instruct_v_0.2
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: hellaswag
+      type: hellaswag
+    metrics:
+    - type: hellaswag (0-Shot)
+      value: 0.66
+      name: hellaswag(0-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: winogrande
+      type: winogrande
+    metrics:
+    - type: winogrande (0-Shot)
+      value: 0.6322
+      name: winogrande(0-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: arc_challenge
+      type: arc_challenge
+    metrics:
+    - type: arc_challenge (0-Shot)
+      value: 0.3447
+      name: arc_challenge(0-Shot)
+    source:
+      url: https://huggingface.co/mwitiderrick/open_llama_3b_instruct_v_0.2
+      name: open_llama_3b_instruct_v_0.2 model card
+  - 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: 40.7
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_glaive_assistant_v0.1
+      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: 67.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_glaive_assistant_v0.1
+      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: 27.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_glaive_assistant_v0.1
+      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: 35.86
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_glaive_assistant_v0.1
+      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: 64.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_glaive_assistant_v0.1
+      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: 1.97
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_glaive_assistant_v0.1
+      name: Open LLM Leaderboard
 ---
 # OpenLLaMA Glaive: An Open Reproduction of LLaMA
 
@@ -122,4 +215,17 @@ def quick_sort(arr):
 |-------------|-------|------|-----:|--------|-----:|---|-----:|
 |arc_challenge|Yaml   |none  |     0|acc     |0.3234|±  |0.0137|
 |             |       |none  |     0|acc_norm|0.3447|±  |0.0139|
-```
+```
+# [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_mwitiderrick__open_llama_3b_glaive_assistant_v0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |39.74|
+|AI2 Reasoning Challenge (25-Shot)|40.70|
+|HellaSwag (10-Shot)              |67.45|
+|MMLU (5-Shot)                    |27.74|
+|TruthfulQA (0-shot)              |35.86|
+|Winogrande (5-shot)              |64.72|
+|GSM8k (5-shot)                   | 1.97|
+