Adding Evaluation Results (#1)

- Adding Evaluation Results (1d90c251c7097b2caf307ba8964d7774e6f35cba)


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

README.md

@@ -1,5 +1,4 @@
 ---
-base_model: EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code
 language:
 - en
 license: apache-2.0
@@ -9,6 +8,102 @@ tags:
 - unsloth
 - llama
 - trl
+base_model: EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code
+model-index:
+- name: Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
+  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: 46.33
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
+      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: 26.4
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
+      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: 10.5
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
+      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: 8.28
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
+      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: 5.01
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
+      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: 28.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
+      name: Open LLM Leaderboard
 ---
 
 # Agent LLama with tasks
@@ -330,3 +425,17 @@ Answer the following questions as best you can. You have access to the following
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+# [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_EpistemeAI2__Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.84|
+|IFEval (0-Shot)    |46.33|
+|BBH (3-Shot)       |26.40|
+|MATH Lvl 5 (4-Shot)|10.50|
+|GPQA (0-shot)      | 8.28|
+|MuSR (0-shot)      | 5.01|
+|MMLU-PRO (5-shot)  |28.50|
+