Adding Evaluation Results (#2)

- Adding Evaluation Results (8ca1f7fae60d754e1f4c1df005ae096109b3f2bb)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -74,6 +74,109 @@ parameters:
   repetition_penalty: 3.5
   length_penalty: 0.9
 base_model: EleutherAI/gpt-neo-1.3B
+model-index:
+- name: gpt-neo-1.3B-emailgen
+  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: 29.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=postbot/gpt-neo-1.3B-emailgen
+      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: 47.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=postbot/gpt-neo-1.3B-emailgen
+      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: 24.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=postbot/gpt-neo-1.3B-emailgen
+      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: 42.55
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=postbot/gpt-neo-1.3B-emailgen
+      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: 56.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=postbot/gpt-neo-1.3B-emailgen
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=postbot/gpt-neo-1.3B-emailgen
+      name: Open LLM Leaderboard
 ---
 
 
@@ -125,3 +228,17 @@ The following hyperparameters were used during training:
 - Transformers 4.22.2
 - Pytorch 1.10.0+cu113
 - Tokenizers 0.12.1
+
+# [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_postbot__gpt-neo-1.3B-emailgen)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |33.47|
+|AI2 Reasoning Challenge (25-Shot)|29.95|
+|HellaSwag (10-Shot)              |47.95|
+|MMLU (5-Shot)                    |24.11|
+|TruthfulQA (0-shot)              |42.55|
+|Winogrande (5-shot)              |56.27|
+|GSM8k (5-shot)                   | 0.00|
+