README.md

metadata

license: gemma
library_name: transformers
datasets:
  - jondurbin/gutenberg-dpo-v0.1
model-index:
  - name: gemma-2-Ifable-9B
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 29.84
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ifable/gemma-2-Ifable-9B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 41.03
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ifable/gemma-2-Ifable-9B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 8.91
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ifable/gemma-2-Ifable-9B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 12.19
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ifable/gemma-2-Ifable-9B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 8.52
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ifable/gemma-2-Ifable-9B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 35.85
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ifable/gemma-2-Ifable-9B
          name: Open LLM Leaderboard

ifable/gemma-2-Ifable-9B

This model ranked first on the Creative Writing Benchmark (https://eqbench.com/creative_writing.html) on September 10, 2024

Training and evaluation data

• Gutenberg: https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1
• Carefully curated proprietary creative writing dataset

Training procedure

Training method: SimPO (GitHub - princeton-nlp/SimPO: SimPO: Simple Preference Optimization with a Reference-Free Reward)

It achieves the following results on the evaluation set:

• Loss: 1.0163
• Rewards/chosen: -21.6822
• Rewards/rejected: -47.8754
• Rewards/accuracies: 0.9167
• Rewards/margins: 26.1931
• Logps/rejected: -4.7875
• Logps/chosen: -2.1682
• Logits/rejected: -17.0475
• Logits/chosen: -12.0041

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 8e-07
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen	Sft Loss
1.4444	0.9807	35	1.0163	-21.6822	-47.8754	0.9167	26.1931	-4.7875	-2.1682	-17.0475	-12.0041	0.0184

Framework versions

• Transformers 4.43.4
• Pytorch 2.3.0a0+ebedce2
• Datasets 2.20.0
• Tokenizers 0.19.1

We are looking for product manager and operations managers to build applications through our model, and also open for business cooperation, and also AI engineer to join us, contact with : [email protected]

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	22.73
IFEval (0-Shot)	29.84
BBH (3-Shot)	41.03
MATH Lvl 5 (4-Shot)	8.91
GPQA (0-shot)	12.19
MuSR (0-shot)	8.52
MMLU-PRO (5-shot)	35.85