| --- |
| license: mit |
| --- |
| |
| **Base model:** [westlake-repl/SaProt_650M_AF2](https://huggingface.co/westlake-repl/SaProt_650M_AF2) |
|
|
| **Task type:** protein-level regression |
|
|
| **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. |
|
|
| **Model input type:** Amino acid sequence |
|
|
| **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 |
