Adding Evaluation Results

This is an automated PR created with https://huggingface.co./spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co./spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,18 +1,18 @@
 ---
 license: mit
-base_model: facebook/bart-large-cnn
 tags:
 - generated_from_trainer
 datasets:
 - xsum
 metrics:
 - rouge
+base_model: facebook/bart-large-cnn
 model-index:
 - name: theus_concepttagger
   results:
   - task:
-      name: Sequence-to-sequence Language Modeling
       type: text2text-generation
+      name: Sequence-to-sequence Language Modeling
     dataset:
       name: xsum
       type: xsum
@@ -20,9 +20,109 @@ model-index:
       split: validation
       args: default
     metrics:
-    - name: Rouge1
-      type: rouge
+    - type: rouge
       value: 34.8663
+      name: Rouge1
+  - 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: 24.57
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=namanpundir/theus_concepttagger
+      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: 25.5
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=namanpundir/theus_concepttagger
+      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: 23.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=namanpundir/theus_concepttagger
+      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: 48.25
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=namanpundir/theus_concepttagger
+      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: 48.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=namanpundir/theus_concepttagger
+      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=namanpundir/theus_concepttagger
+      name: Open LLM Leaderboard
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -77,3 +177,17 @@ The following hyperparameters were used during training:
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
 - Tokenizers 0.13.3
+
+# [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_namanpundir__theus_concepttagger)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |28.29|
+|AI2 Reasoning Challenge (25-Shot)|24.57|
+|HellaSwag (10-Shot)              |25.50|
+|MMLU (5-Shot)                    |23.12|
+|TruthfulQA (0-shot)              |48.25|
+|Winogrande (5-shot)              |48.30|
+|GSM8k (5-shot)                   | 0.00|
+