Model-EYFP-650M / README.md
Jiawei Zhang
Upload 5 files
702e9d0 verified
|
raw
history blame
No virus
1.02 kB
metadata
license: mit

Base model: westlake-repl/SaProt_650M_AF2

Dataset: This dataset contains single-site and double-site mutants derived from the wild type EYFP protein. The number of samples for training, validation and test is 26168, 3087 and 3088. All single-site mutants and 80% of double-site mutants for training, 10% of double-site mutants for validation and test respectively. This model was trained by Jia Zheng's lab at Westlake University. The dataset will be released later by this team.

Performance (on test set): 0.95 Spearman's ρ

LoRA config:

  • r: 8
  • lora_dropout: 0.0
  • lora_alpha: 16
  • target_modules: ["query", "key", "value", "intermediate.dense", "output.dense"]
  • modules_to_save: ["classifier"]

Training config:

  • optimizer:
    • class: AdamW
    • betas: (0.9, 0.98)
    • weight_decay: 0.01
  • learning rate: 1e-4
  • epoch: 50
  • batch size: 64
  • precision: 16-mixed