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-intermediate-step-1195k-token-2.5T
+  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: 33.53
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T
+      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: 59.38
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T
+      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: 26.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T
+      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: 36.79
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T
+      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: 60.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T
+      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: 1.44
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T
+      name: Open LLM Leaderboard
 ---
 <div align="center">
 
@@ -35,3 +138,17 @@ This collection contains all checkpoints after the 1T fix. Branch name indicates
 | TinyLlama-1.1B-intermediate-step-715k-1.5T |     1.5T     | 53.68     | 35.20 | 58.33      | 29.18 | 51.89 | 59.08 | 71.65 | 51.29 |
 | TinyLlama-1.1B-intermediate-step-955k-2T |     2T     | 54.63     | 33.40 | 56.83      | 28.07 | 54.67 | 63.21 | 70.67 | 51.64 |
 | **TinyLlama-1.1B-intermediate-step-1195k-token-2.5T**  |     **2.5T**     | **58.96**     | **34.40** | **58.72**      | **31.91** | **56.78** | **63.21** | **73.07** | **53.86**|
+
+# [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_TinyLlama__TinyLlama-1.1B-intermediate-step-1195k-token-2.5T)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |36.26|
+|AI2 Reasoning Challenge (25-Shot)|33.53|
+|HellaSwag (10-Shot)              |59.38|
+|MMLU (5-Shot)                    |26.22|
+|TruthfulQA (0-shot)              |36.79|
+|Winogrande (5-shot)              |60.22|
+|GSM8k (5-shot)                   | 1.44|
+