metadata

language:
  - en
license: gemma
datasets:
  - openbmb/UltraFeedback
pipeline_tag: text-generation
model-index:
  - name: Gemma-2-9B-It-SPPO-Iter3
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: ENEM Challenge (No Images)
          type: eduagarcia/enem_challenge
          split: train
          args:
            num_few_shot: 3
        metrics:
          - type: acc
            value: 73.48
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BLUEX (No Images)
          type: eduagarcia-temp/BLUEX_without_images
          split: train
          args:
            num_few_shot: 3
        metrics:
          - type: acc
            value: 63
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: OAB Exams
          type: eduagarcia/oab_exams
          split: train
          args:
            num_few_shot: 3
        metrics:
          - type: acc
            value: 52.3
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Assin2 RTE
          type: assin2
          split: test
          args:
            num_few_shot: 15
        metrics:
          - type: f1_macro
            value: 94.36
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Assin2 STS
          type: eduagarcia/portuguese_benchmark
          split: test
          args:
            num_few_shot: 15
        metrics:
          - type: pearson
            value: 78.25
            name: pearson
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: FaQuAD NLI
          type: ruanchaves/faquad-nli
          split: test
          args:
            num_few_shot: 15
        metrics:
          - type: f1_macro
            value: 77.69
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HateBR Binary
          type: ruanchaves/hatebr
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: f1_macro
            value: 87.49
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: PT Hate Speech Binary
          type: hate_speech_portuguese
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: f1_macro
            value: 72.41
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: tweetSentBR
          type: eduagarcia/tweetsentbr_fewshot
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: f1_macro
            value: 69.75
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
          name: Open Portuguese LLM Leaderboard

Self-Play Preference Optimization for Language Model Alignment (https://arxiv.org/abs/2405.00675)

Gemma-2-9B-It-SPPO-Iter3

This model was developed using Self-Play Preference Optimization at iteration 3, based on the google/gemma-2-9b-it architecture as starting point. We utilized the prompt sets from the openbmb/UltraFeedback dataset, splited to 3 parts for 3 iterations by snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset. All responses used are synthetic.

Terms of Use: Terms

Links to Other Models

Model Description

Model type: A 8B parameter GPT-like model fine-tuned on synthetic datasets.
Language(s) (NLP): Primarily English
License: Apache-2.0
Finetuned from model: google/gemma-2-9b-it

AlpacaEval Leaderboard Evaluation Results

Model	LC. Win Rate	Win Rate	Avg. Length
Gemma-2-9B-SPPO Iter1	48.70	40.76	1669
Gemma-2-9B-SPPO Iter2	50.93	44.64	1759
Gemma-2-9B-SPPO Iter3	53.27	47.74	1803

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-07
eta: 1000
per_device_train_batch_size: 8
gradient_accumulation_steps: 1
seed: 42
distributed_type: deepspeed_zero3
num_devices: 8
optimizer: RMSProp
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_train_epochs: 1.0

Citation

@misc{wu2024self,
      title={Self-Play Preference Optimization for Language Model Alignment}, 
      author={Wu, Yue and Sun, Zhiqing and Yuan, Huizhuo and Ji, Kaixuan and Yang, Yiming and Gu, Quanquan},
      year={2024},
      eprint={2405.00675},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

Open Portuguese LLM Leaderboard Evaluation Results

Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard

Metric	Value
Average	74.3
ENEM Challenge (No Images)	73.48
BLUEX (No Images)	63
OAB Exams	52.30
Assin2 RTE	94.36
Assin2 STS	78.25
FaQuAD NLI	77.69
HateBR Binary	87.49
PT Hate Speech Binary	72.41
tweetSentBR	69.75