Adding Evaluation Results

README.md

@@ -1,7 +1,102 @@
 ---
 license: apache-2.0
-pipeline_tag: text-generation
 library_name: transformers
+pipeline_tag: text-generation
+model-index:
+- name: zephyr-sft-bnb-4bit-DPO-mtbo-180steps
+  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: 40.87
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbo-180steps
+      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: 21.35
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbo-180steps
+      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: 1.81
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbo-180steps
+      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: 3.47
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbo-180steps
+      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: 6.16
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbo-180steps
+      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: 19.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbo-180steps
+      name: Open LLM Leaderboard
 ---
 TrainOutput(global_step=180, training_loss=0.06880439353962547, metrics={'train_runtime': 1644.0348, 'train_samples_per_second': 1.749, 'train_steps_per_second': 0.109, 'total_flos': 0.0, 'train_loss': 0.06880439353962547, 'epoch': 0.5006954102920723})
 ---
@@ -26,4 +121,17 @@ tags:
 
 This mistral 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)
+[<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_sonthenguyen__zephyr-sft-bnb-4bit-DPO-mtbo-180steps)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |15.51|
+|IFEval (0-Shot)    |40.87|
+|BBH (3-Shot)       |21.35|
+|MATH Lvl 5 (4-Shot)| 1.81|
+|GPQA (0-shot)      | 3.47|
+|MuSR (0-shot)      | 6.16|
+|MMLU-PRO (5-shot)  |19.42|
+