metadata
license: apache-2.0
tags:
- dpo
base_model:
- CorticalStack/pastiche-crown-clown-7b-dare
dataset:
- jondurbin/truthy-dpo-v0.1
model-index:
- name: pastiche-crown-clown-7b-dare-dpo
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: 72.78
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/pastiche-crown-clown-7b-dare-dpo
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: 89.15
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/pastiche-crown-clown-7b-dare-dpo
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: 64.51
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/pastiche-crown-clown-7b-dare-dpo
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: 78.8
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/pastiche-crown-clown-7b-dare-dpo
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: 84.85
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/pastiche-crown-clown-7b-dare-dpo
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: 68.92
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/pastiche-crown-clown-7b-dare-dpo
name: Open LLM Leaderboard
CorticalStack/pastiche-crown-clown-7b-dare-dpo
CorticalStack/pastiche-crown-clown-7b-dare-dpo is a DPO fine-tuned version of CorticalStack/pastiche-crown-clown-7b-dare using the jondurbin/truthy-dpo-v0.1 dataset.
LoRA
- r: 16
- LoRA alpha: 16
- LoRA dropout: 0.05
Training arguments
- Batch size: 4
- Gradient accumulation steps: 4
- Optimizer: paged_adamw_32bit
- Max steps: 200
- Learning rate: 5e-05
- Learning rate scheduler type: cosine
- Beta: 0.1
- Max prompt length: 1024
- Max length: 1536
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 76.50 |
AI2 Reasoning Challenge (25-Shot) | 72.78 |
HellaSwag (10-Shot) | 89.15 |
MMLU (5-Shot) | 64.51 |
TruthfulQA (0-shot) | 78.80 |
Winogrande (5-shot) | 84.85 |
GSM8k (5-shot) | 68.92 |