Adding Evaluation Results (#1)

- Adding Evaluation Results (576a660d94638e12c4d68a0e7438ce4d6649a56d)


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

README.md

@@ -1,58 +1,157 @@
 ---
-base_model: openlm-research/open_llama_3b
+language:
+- en
+license: apache-2.0
+library_name: transformers
+tags:
+- transformers
 datasets:
 - mwitiderrick/OpenPlatypus
+base_model: openlm-research/open_llama_3b
 inference: true
 model_type: llama
-prompt_template: |
-  ### Instruction:\n
+prompt_template: '### Instruction:\n
+
   {prompt}
+
   ### Response:
+
+  '
 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: 0.4882
-      - task:
-          type: text-generation
-        dataset:
-          name: winogrande
-          type: winogrande
-        metrics:
-          - name: winogrande(0-Shot)
-            type: winogrande (0-Shot)
-            value: 0.6133
-
-      - task:
-          type: text-generation
-        dataset:
-          name: arc_challenge
-          type: arc_challenge
-        metrics:
-          - name: arc_challenge(0-Shot)
-            type: arc_challenge (0-Shot)
-            value: 0.3362
-        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: 0.4882
+      name: hellaswag(0-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: winogrande
+      type: winogrande
+    metrics:
+    - type: winogrande (0-Shot)
+      value: 0.6133
+      name: winogrande(0-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: arc_challenge
+      type: arc_challenge
+    metrics:
+    - type: arc_challenge (0-Shot)
+      value: 0.3362
+      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: 38.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_instruct_v_0.2
+      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: 66.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_instruct_v_0.2
+      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: 25.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_instruct_v_0.2
+      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: 38.16
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_instruct_v_0.2
+      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: 63.46
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_instruct_v_0.2
+      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: 1.59
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_instruct_v_0.2
+      name: Open LLM Leaderboard
 ---
 # OpenLLaMA Instruct: An Open Reproduction of LLaMA
 
@@ -140,4 +239,17 @@ Step 4: Make the gravy
 |          |       |none  |     0|rougeL_max | 45.4592|±  |0.8754|
 |          |       |none  |     0|rougeL_acc |  0.2754|±  |0.0156|
 |          |       |none  |     0|rougeL_diff|-10.0740|±  |0.7807|
-```
+```
+# [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_instruct_v_0.2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |38.97|
+|AI2 Reasoning Challenge (25-Shot)|38.48|
+|HellaSwag (10-Shot)              |66.77|
+|MMLU (5-Shot)                    |25.34|
+|TruthfulQA (0-shot)              |38.16|
+|Winogrande (5-shot)              |63.46|
+|GSM8k (5-shot)                   | 1.59|
+