Adding Evaluation Results

README.md

@@ -1,85 +1,185 @@
 ---
+language:
+- en
+license: llama2
 tags:
 - generated_from_trainer
 - finance
 model-index:
 - name: completed-model
   results:
-    - task:
-        type: text-generation
-      dataset:
-        name: ai2_arc
-        type: ai2_arc
-      metrics:
-        - name: AI2 Reasoning Challenge (25-Shot)
-          type: AI2 Reasoning Challenge (25-Shot)
-          value: 71.93
-      source:
-        name: Open LLM Leaderboard
-        url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
-    - task:
-        type: text-generation
-      dataset:
-        name: hellaswag
-        type: hellaswag
-      metrics:
-        - name: HellaSwag (10-shot)
-          type: HellaSwag (10-shot)
-          value: 86.82
-      source:
-        name: Open LLM Leaderboard
-        url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
-    - task:
-        type: text-generation
-      dataset:
-        name: multiple
-        type: miltiple
-      metrics:
-        - name: MMLU (5-shot)
-          type: MMLU (5-shot)
-          value: 70.38
-      source:
-        name: Open LLM Leaderboard
-        url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
-    - task:
-        type: text-generation
-      dataset:
-        name: truthful_qa
-        type: truthful_qa
-      metrics:
-        - name: TruthfulQA (0-shot) 
-          type: TruthfulQA (0-shot) 
-          value: 65.21
-      source:
-        name: Open LLM Leaderboard
-        url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
-    - task:
-        type: text-generation
-      dataset:
-        name: winogrande
-        type: winogrande
-      metrics:
-        - name: Winogrande (5-shot)
-          type: Winogrande (5-shot)
-          value: 83.58
-      source:
-        name: Open LLM Leaderboard
-        url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
-    - task:
-        type: text-generation
-      dataset:
-        name: gsm8k
-        type: gsm8k
-      metrics:
-        - name: GSM8k (5-shot)
-          type: GSM8k (5-shot)
-          value: 61.79
-      source:
-        name: Open LLM Leaderboard
-        url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
-license: llama2
-language:
-- en
+  - task:
+      type: text-generation
+    dataset:
+      name: ai2_arc
+      type: ai2_arc
+    metrics:
+    - type: AI2 Reasoning Challenge (25-Shot)
+      value: 71.93
+      name: AI2 Reasoning Challenge (25-Shot)
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+    dataset:
+      name: hellaswag
+      type: hellaswag
+    metrics:
+    - type: HellaSwag (10-shot)
+      value: 86.82
+      name: HellaSwag (10-shot)
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+    dataset:
+      name: multiple
+      type: miltiple
+    metrics:
+    - type: MMLU (5-shot)
+      value: 70.38
+      name: MMLU (5-shot)
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+    dataset:
+      name: truthful_qa
+      type: truthful_qa
+    metrics:
+    - type: TruthfulQA (0-shot)
+      value: 65.21
+      name: TruthfulQA (0-shot)
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+    dataset:
+      name: winogrande
+      type: winogrande
+    metrics:
+    - type: Winogrande (5-shot)
+      value: 83.58
+      name: Winogrande (5-shot)
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+    dataset:
+      name: gsm8k
+      type: gsm8k
+    metrics:
+    - type: GSM8k (5-shot)
+      value: 61.79
+      name: GSM8k (5-shot)
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+      name: Open LLM Leaderboard
+  - 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: 71.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gradientai/v-alpha-tross
+      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: 86.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gradientai/v-alpha-tross
+      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: 70.38
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gradientai/v-alpha-tross
+      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: 65.21
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gradientai/v-alpha-tross
+      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: 83.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gradientai/v-alpha-tross
+      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: 61.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gradientai/v-alpha-tross
+      name: Open LLM Leaderboard
 ---
 
 **Albatross** is a collection of domain-specific language models for finance applications developed by [Gradient](https://gradient.ai/).
@@ -209,4 +309,17 @@ Gradient is accelerating AI transformation across industries. https://gradient.a
 
 ## Contact Us
 
-Drop an email to [[email protected]](mailto:[email protected])
+Drop an email to [[email protected]](mailto:[email protected])
+# [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_gradientai__v-alpha-tross)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.28|
+|AI2 Reasoning Challenge (25-Shot)|71.93|
+|HellaSwag (10-Shot)              |86.82|
+|MMLU (5-Shot)                    |70.38|
+|TruthfulQA (0-shot)              |65.21|
+|Winogrande (5-shot)              |83.58|
+|GSM8k (5-shot)                   |61.79|
+