Adding Evaluation Results (#1)

- Adding Evaluation Results (f7a94cb153e030d7f7a07a525c1c57c4c4a049da)

README.md

@@ -1,12 +1,107 @@
 ---
-license: apache-2.0
 language:
 - en
 - zh
-metrics:
-- accuracy
+license: apache-2.0
 base_model:
 - sthenno/tempesthenno-icy-0130
+metrics:
+- accuracy
+model-index:
+- name: tempesthenno-kto-0205-ckpt80
+  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: 62.18
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-kto-0205-ckpt80
+      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: 50.1
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-kto-0205-ckpt80
+      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: 37.99
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-kto-0205-ckpt80
+      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: 19.69
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-kto-0205-ckpt80
+      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: 19.84
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-kto-0205-ckpt80
+      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: 48.65
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-kto-0205-ckpt80
+      name: Open LLM Leaderboard
 ---
 
 sthenno/tempesthenno-kto-0205-ckpt80
@@ -49,4 +144,17 @@ models:
   - model: sthenno/tempesthenno-icy-0130-01
   - model: sthenno/tempesthenno-icy-0130-02
   - model: sthenno/tempesthenno-icy-0130-03
-```
+```
+# [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-kto-0205-ckpt80-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |39.74|
+|IFEval (0-Shot)    |62.18|
+|BBH (3-Shot)       |50.10|
+|MATH Lvl 5 (4-Shot)|37.99|
+|GPQA (0-shot)      |19.69|
+|MuSR (0-shot)      |19.84|
+|MMLU-PRO (5-shot)  |48.65|
+