Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
-library_name: peft
 license: llama2
+library_name: peft
 datasets:
 - tonytan48/TempReason
 - tasksource/tracie
 - tasksource/bigbench
 - time_dial
+model-index:
+- name: vicuna-7b-v1.5-lora-temporal-without-mctaco-1
+  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: 49.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Charlie911/vicuna-7b-v1.5-lora-temporal-without-mctaco-1
+      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: 75.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Charlie911/vicuna-7b-v1.5-lora-temporal-without-mctaco-1
+      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: 47.47
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Charlie911/vicuna-7b-v1.5-lora-temporal-without-mctaco-1
+      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: 39.95
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Charlie911/vicuna-7b-v1.5-lora-temporal-without-mctaco-1
+      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: 71.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Charlie911/vicuna-7b-v1.5-lora-temporal-without-mctaco-1
+      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: 11.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Charlie911/vicuna-7b-v1.5-lora-temporal-without-mctaco-1
+      name: Open LLM Leaderboard
 ---
 ## Training procedure
 
@@ -24,4 +127,17 @@ The following `bitsandbytes` quantization config was used during training:
 ### Framework versions
 
 
-- PEFT 0.5.0
+- PEFT 0.5.0
+# [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_Charlie911__vicuna-7b-v1.5-lora-temporal-without-mctaco-1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |49.35|
+|AI2 Reasoning Challenge (25-Shot)|49.49|
+|HellaSwag (10-Shot)              |75.93|
+|MMLU (5-Shot)                    |47.47|
+|TruthfulQA (0-shot)              |39.95|
+|Winogrande (5-shot)              |71.35|
+|GSM8k (5-shot)                   |11.90|
+