Adding Evaluation Results

README.md

@@ -1,10 +1,113 @@
 ---
+language:
+- en
 license: apache-2.0
 datasets:
 - cerebras/SlimPajama-627B
 - bigcode/starcoderdata
-language:
-- en
+model-index:
+- name: TinyLlama-1.1B-step-50K-105b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 25.85
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PY007/TinyLlama-1.1B-step-50K-105b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 44.1
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PY007/TinyLlama-1.1B-step-50K-105b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 26.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PY007/TinyLlama-1.1B-step-50K-105b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 39.51
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PY007/TinyLlama-1.1B-step-50K-105b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 54.38
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PY007/TinyLlama-1.1B-step-50K-105b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 0.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PY007/TinyLlama-1.1B-step-50K-105b
+      name: Open LLM Leaderboard
 ---
 <div align="center">
 
@@ -67,4 +170,17 @@ sequences = pipeline(
 )
 for seq in sequences:
     print(f"Result: {seq['generated_text']}")
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_PY007__TinyLlama-1.1B-step-50K-105b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |31.86|
+|AI2 Reasoning Challenge (25-Shot)|25.85|
+|HellaSwag (10-Shot)              |44.10|
+|MMLU (5-Shot)                    |26.78|
+|TruthfulQA (0-shot)              |39.51|
+|Winogrande (5-shot)              |54.38|
+|GSM8k (5-shot)                   | 0.53|
+