Adding Evaluation Results (#1)

- Adding Evaluation Results (aa67ceef8c40f0ef131612237d7ff853e18e791e)


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

README.md

@@ -1,13 +1,108 @@
 ---
-base_model: meta-llama/Meta-Llama-3-8B-Instruct
 license: llama3
 tags:
 - axolotl
 - dpo
 - trl
 - generated_from_trainer
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
 datasets:
 - HumanLLMs/humanish-dpo-project
+model-index:
+- name: Humanish-LLama3.1-8B-Instruct
+ results:
+ - task:
+ type: text-generation
+ name: Text Generation
+ dataset:
+ name: IFEval (0-Shot)
+ type: HuggingFaceH4/ifeval
+ args:
+ num_few_shot: 0
+ metrics:
+ - type: inst_level_strict_acc and prompt_level_strict_acc
+ value: 64.98
+ name: strict accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-LLama3.1-8B-Instruct
+ name: Open LLM Leaderboard
+ - task:
+ type: text-generation
+ name: Text Generation
+ dataset:
+ name: BBH (3-Shot)
+ type: BBH
+ args:
+ num_few_shot: 3
+ metrics:
+ - type: acc_norm
+ value: 28.01
+ name: normalized accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-LLama3.1-8B-Instruct
+ name: Open LLM Leaderboard
+ - task:
+ type: text-generation
+ name: Text Generation
+ dataset:
+ name: MATH Lvl 5 (4-Shot)
+ type: hendrycks/competition_math
+ args:
+ num_few_shot: 4
+ metrics:
+ - type: exact_match
+ value: 8.46
+ name: exact match
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-LLama3.1-8B-Instruct
+ name: Open LLM Leaderboard
+ - task:
+ type: text-generation
+ name: Text Generation
+ dataset:
+ name: GPQA (0-shot)
+ type: Idavidrein/gpqa
+ args:
+ num_few_shot: 0
+ metrics:
+ - type: acc_norm
+ value: 0.78
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-LLama3.1-8B-Instruct
+ name: Open LLM Leaderboard
+ - task:
+ type: text-generation
+ name: Text Generation
+ dataset:
+ name: MuSR (0-shot)
+ type: TAUR-Lab/MuSR
+ args:
+ num_few_shot: 0
+ metrics:
+ - type: acc_norm
+ value: 2.0
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-LLama3.1-8B-Instruct
+ name: Open LLM Leaderboard
+ - task:
+ type: text-generation
+ name: Text Generation
+ dataset:
+ name: MMLU-PRO (5-shot)
+ type: TIGER-Lab/MMLU-Pro
+ config: main
+ split: test
+ args:
+ num_few_shot: 5
+ metrics:
+ - type: acc
+ value: 30.02
+ name: accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=HumanLLMs/Humanish-LLama3.1-8B-Instruct
+ name: Open LLM Leaderboard
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -141,4 +236,17 @@ The following hyperparameters were used during training:
 - Transformers 4.45.1
 - Pytorch 2.3.1+cu121
 - Datasets 2.21.0
-- Tokenizers 0.20.0
+- Tokenizers 0.20.0
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_HumanLLMs__Humanish-LLama3.1-8B-Instruct)
+
+| Metric |Value|
+|-------------------|----:|
+|Avg. |22.38|
+|IFEval (0-Shot) |64.98|
+|BBH (3-Shot) |28.01|
+|MATH Lvl 5 (4-Shot)| 8.46|
+|GPQA (0-shot) | 0.78|
+|MuSR (0-shot) | 2.00|
+|MMLU-PRO (5-shot) |30.02|
+