Adding Evaluation Results (#1)

- Adding Evaluation Results (5a9bcbc28f71a9932b5d15cea27211d73c6db2a9)


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

README.md

@@ -1,4 +1,5 @@
 ---
+license: llama3
 library_name: transformers
 tags:
 - experimental
@@ -8,7 +9,109 @@ datasets:
 - jondurbin/gutenberg-dpo-v0.1
 - jondurbin/truthy-dpo-v0.1
 - flammenai/FlameMix-DPO-v1
-license: llama3
+model-index:
+- name: llama-3-sauce-v2-8B
+  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: 65.61
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/llama-3-sauce-v2-8B
+      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: 83.11
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/llama-3-sauce-v2-8B
+      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: 67.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/llama-3-sauce-v2-8B
+      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: 56.39
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/llama-3-sauce-v2-8B
+      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: 76.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/llama-3-sauce-v2-8B
+      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: 72.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/llama-3-sauce-v2-8B
+      name: Open LLM Leaderboard
 ---
 
 # llama-3-sauce-v2-8B
@@ -143,4 +246,17 @@ dpo_trainer = DPOTrainer(
 )
 # Fine-tune model with DPO
 dpo_trainer.train()
-```
+```
+# [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_nbeerbower__llama-3-sauce-v2-8B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.38|
+|AI2 Reasoning Challenge (25-Shot)|65.61|
+|HellaSwag (10-Shot)              |83.11|
+|MMLU (5-Shot)                    |67.98|
+|TruthfulQA (0-shot)              |56.39|
+|Winogrande (5-shot)              |76.72|
+|GSM8k (5-shot)                   |72.48|
+