Adding Evaluation Results

README.md

@@ -1,19 +1,114 @@
 ---
-license: apache-2.0
-datasets:
-- nvidia/HelpSteer2
 language:
 - en
 - zh
-metrics:
-- accuracy
-base_model:
-- sthenno/tempesthenno-14b-nuslerp-0111
-- sthenno/tempesthenno-hs2-rm
+license: apache-2.0
 tags:
 - RLHF
 - PPO
 - custom-research
+base_model:
+- sthenno/tempesthenno-14b-nuslerp-0111
+- sthenno/tempesthenno-hs2-rm
+datasets:
+- nvidia/HelpSteer2
+metrics:
+- accuracy
+model-index:
+- name: tempesthenno-ppo-ckpt40
+  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: 79.23
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-ppo-ckpt40
+      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: 50.57
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-ppo-ckpt40
+      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: 34.21
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-ppo-ckpt40
+      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: 17.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-ppo-ckpt40
+      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: 14.56
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-ppo-ckpt40
+      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: 47.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-ppo-ckpt40
+      name: Open LLM Leaderboard
 ---
 # tempesthenno--nuslerp (BASE MODEL)
 
@@ -122,4 +217,17 @@ slices:
           weight: 0.60
           nuslerp_flatten: true
 
-```
+```
+# [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/sthenno__tempesthenno-ppo-ckpt40-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |40.55|
+|IFEval (0-Shot)    |79.23|
+|BBH (3-Shot)       |50.57|
+|MATH Lvl 5 (4-Shot)|34.21|
+|GPQA (0-shot)      |17.00|
+|MuSR (0-shot)      |14.56|
+|MMLU-PRO (5-shot)  |47.69|
+