Adding Evaluation Results (#1)

- Adding Evaluation Results (0a72867b13c251d04acb956ef610c19c7c128c73)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,11 +1,114 @@
 ---
-library_name: peft
-base_model: meta-llama/Llama-2-7b-hf
+language:
+- en
 license: apache-2.0
+library_name: peft
 datasets:
 - squad_v2
-language:
-- en
+base_model: meta-llama/Llama-2-7b-hf
+model-index:
+- name: belal-finetuned-llama2-v1.0
+  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: 52.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abdulrahman-nuzha/belal-finetuned-llama2-v1.0
+      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: 77.75
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abdulrahman-nuzha/belal-finetuned-llama2-v1.0
+      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: 43.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abdulrahman-nuzha/belal-finetuned-llama2-v1.0
+      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: 39.09
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abdulrahman-nuzha/belal-finetuned-llama2-v1.0
+      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: 74.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abdulrahman-nuzha/belal-finetuned-llama2-v1.0
+      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: 10.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abdulrahman-nuzha/belal-finetuned-llama2-v1.0
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -206,4 +309,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ### Framework versions
 
-- PEFT 0.7.2.dev0
+- PEFT 0.7.2.dev0
+# [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_abdulrahman-nuzha__belal-finetuned-llama2-v1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |49.70|
+|AI2 Reasoning Challenge (25-Shot)|52.82|
+|HellaSwag (10-Shot)              |77.75|
+|MMLU (5-Shot)                    |43.51|
+|TruthfulQA (0-shot)              |39.09|
+|Winogrande (5-shot)              |74.35|
+|GSM8k (5-shot)                   |10.69|
+