|
--- |
|
license: apache-2.0 |
|
tags: |
|
- dpo |
|
base_model: |
|
- mistralai/Mistral-7B-v0.1 |
|
dataset: |
|
- mlabonne/distilabel-truthy-dpo-v0.1 |
|
model-index: |
|
- name: mistral-7b-distilabel-truthy-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: 60.92 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-distilabel-truthy-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: 83.64 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-distilabel-truthy-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: 64.18 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-distilabel-truthy-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: 45.12 |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-distilabel-truthy-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: 78.37 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-distilabel-truthy-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: 36.09 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-distilabel-truthy-dpo |
|
name: Open LLM Leaderboard |
|
--- |
|
|
|
# mistral-7b-distilabel-truthy-dpo |
|
|
|
mistral-7b-distilabel-truthy-dpo is a DPO fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) using the [mlabonne/distilabel-truthy-dpo-v0.1](https://huggingface.co/datasets/mlabonne/distilabel-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: 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](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) |
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_CorticalStack__mistral-7b-distilabel-truthy-dpo) |
|
|
|
| Metric |Value| |
|
|---------------------------------|----:| |
|
|Avg. |61.39| |
|
|AI2 Reasoning Challenge (25-Shot)|60.92| |
|
|HellaSwag (10-Shot) |83.64| |
|
|MMLU (5-Shot) |64.18| |
|
|TruthfulQA (0-shot) |45.12| |
|
|Winogrande (5-shot) |78.37| |
|
|GSM8k (5-shot) |36.09| |
|
|
|
|