metadata
license: apache-2.0
tags:
- dpo
base_model:
- mistralai/Mistral-7B-v0.1
dataset:
- CorticalStack/tak-stack-dpo
model-index:
- name: mistral-7b-tak-stack-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: 61.18
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-tak-stack-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: 83.98
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-tak-stack-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: 64.32
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-tak-stack-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: 43.8
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-tak-stack-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: 79.32
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-tak-stack-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: 38.59
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-tak-stack-dpo
name: Open LLM Leaderboard
mistral-7b-tak-stack-dpo
mistral-7b-tak-stack-dpo is a DPO fine-tuned version of mistralai/Mistral-7B-v0.1 using the CorticalStack/tak-stack-dpo dataset.
LoRA
- r: 32
- LoRA alpha: 32
- LoRA dropout: 0.05
Training arguments
- Batch size: 4
- Gradient accumulation steps: 4
- Optimizer: paged_adamw_32bit
- Max steps: 100
- 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. | 61.86 |
| AI2 Reasoning Challenge (25-Shot) | 61.18 |
| HellaSwag (10-Shot) | 83.98 |
| MMLU (5-Shot) | 64.32 |
| TruthfulQA (0-shot) | 43.80 |
| Winogrande (5-shot) | 79.32 |
| GSM8k (5-shot) | 38.59 |