Adding Evaluation Results (#2)

- Adding Evaluation Results (a63c4fe7aee58f375b57f0ea81f67872296a09ec)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,13 +1,108 @@
 ---
-base_model: meta-llama/Meta-Llama-3-8B
-tags:
-- axolotl
-license: llama3
 language:
 - en
+license: llama3
+tags:
+- axolotl
+base_model: meta-llama/Meta-Llama-3-8B
 datasets:
 - BEE-spoke-data/KI-smorgasbord_fw-small
 pipeline_tag: text-generation
+model-index:
+- name: Llama-3-6.3b-v0.1
+  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: 10.44
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pszemraj/Llama-3-6.3b-v0.1
+      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: 18.68
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pszemraj/Llama-3-6.3b-v0.1
+      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: 1.51
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pszemraj/Llama-3-6.3b-v0.1
+      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: 4.47
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pszemraj/Llama-3-6.3b-v0.1
+      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: 6.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pszemraj/Llama-3-6.3b-v0.1
+      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: 20.44
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pszemraj/Llama-3-6.3b-v0.1
+      name: Open LLM Leaderboard
 ---
 
 
@@ -124,4 +219,17 @@ special_tokens:
 | 2.3761        | 0.6006 | 960  | 2.2849          |
 | 2.2448        | 0.8008 | 1280 | 2.2702          |
 
----
+---
+# [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_pszemraj__Llama-3-6.3b-v0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |10.28|
+|IFEval (0-Shot)    |10.44|
+|BBH (3-Shot)       |18.68|
+|MATH Lvl 5 (4-Shot)| 1.51|
+|GPQA (0-shot)      | 4.47|
+|MuSR (0-shot)      | 6.15|
+|MMLU-PRO (5-shot)  |20.44|
+