Base model: westlake-repl/SaProt_35M_AF2
Task type: Protein-protein Regression
Model Details
Model Description
This model is used to predict TM score give two SA protein pairs.
Model input type
SA sequence pair
Performance
test_loss: 0.0031981547363102436
test_spearman: 0.8464066386222839
test_R2: 0.8718534111976624
test_pearson: 0.9338204860687256
LoRA config
lora_dropout: 0.0
lora_alpha: 16
target_modules: ["query", "key", "value", "intermediate.dense", "output.dense"]
modules_to_save: ["classifier"]
Training config
class: AdamW
betas: (0.9, 0.98)
weight_decay: 0.01
learning rate: 1e-4
epoch: 10
batch size: 4
precision: 16-mixed
- PEFT 0.10.0
- Downloads last month
- 3
Model tree for SaProtHub/Model-Saprot-TM-35M
Base model
westlake-repl/SaProt_35M_AF2