Adding Evaluation Results

README.md

@@ -1,7 +1,4 @@
 ---
-base_model: ehristoforu/Gemma2-9B-it-psy10k
-datasets:
-- jtatman/mental_health_psychology_curated_alpaca
 language:
 - en
 license: apache-2.0
@@ -12,6 +9,104 @@ tags:
 - gemma2
 - trl
 - sft
+base_model: ehristoforu/Gemma2-9B-it-psy10k
+datasets:
+- jtatman/mental_health_psychology_curated_alpaca
+model-index:
+- name: Gemma2-9B-it-psy10k-mental_health
+  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: 58.87
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/Gemma2-9B-it-psy10k-mental_health
+      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: 35.57
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/Gemma2-9B-it-psy10k-mental_health
+      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: 12.16
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/Gemma2-9B-it-psy10k-mental_health
+      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: 11.63
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/Gemma2-9B-it-psy10k-mental_health
+      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: 9.34
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/Gemma2-9B-it-psy10k-mental_health
+      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: 31.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/Gemma2-9B-it-psy10k-mental_health
+      name: Open LLM Leaderboard
 ---
 
 # Uploaded  model
@@ -23,3 +118,17 @@ tags:
 This gemma2 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_ehristoforu__Gemma2-9B-it-psy10k-mental_health)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |26.50|
+|IFEval (0-Shot)    |58.87|
+|BBH (3-Shot)       |35.57|
+|MATH Lvl 5 (4-Shot)|12.16|
+|GPQA (0-shot)      |11.63|
+|MuSR (0-shot)      | 9.34|
+|MMLU-PRO (5-shot)  |31.43|
+