stage1_config.json

{
    "data_path": "None",
    "pfam_data_path": "None",
    "tb_logger_path": "None",
    "tb_logger_folder": "None",
    "version_name": "None",
    "model_checkpoint_path": "/project/andrewferguson/niksapraljak/Project_ProtARDM/logs/Stage1_final_models/checkpoints/Pretraining_PENCiL_45M/epoch=19-step=116600.ckpt",
    "output_dict_path": "/project/ranganathanr/niksapraljak/BioM3_PDZ/outputs/output_dict.pt",
    "valid_size": 0.2,
    "epochs": 10,
    "acc_grad_batches": 1,
    "batch_size": 80,
    "num_workers": 12,
    "weight_decay": "5e-7",
    "patience": 1,
    "factor": 0.8,
    "temperature": 0.8,
    "seed": 42,
    "num_gpus": 1,
    "precision": "16",
    "dataset_type": "default",
    "model_type": "pfam",
    "fast_dev_run": 0,
    "sequence_keyword": "protein_sequence",
    "id_keyword": "primary_Accession",
    "dataset_source": "swissprot",
    "pfam_data_split_label": "0",
    "base_lr": 0.0016,
    "global_batch_size": 80,
    "lr": 0.0005,
    "seq_model_path": "/project/ranganathanr/niksapraljak/TextDiff_model_weights/Stage_1/pretrained_models/esm2_t33_650M_UR50D.pt",
    "pretrained_seq": true,
    "trainable_seq": true,
    "rep_layer": 33,
    "protein_encoder_embedding": 1280,
    "protein_encoder_lr": 0.0005,
    "pLM_n_layers_to_finetune": 1,
    "text_model_path": "/project/ranganathanr/niksapraljak/TextDiff_model_weights/Stage_1/pretrained_models/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
    "pretrained_text": true,
    "trainable_text": true,
    "text_encoder_embedding": 768,
    "text_encoder_lr": 0.0005,
    "text_max_length": 512,
    "bLM_n_layers_to_finetune": 1,
    "proj_embedding_dim": 512,
    "dropout": 0.1,
    "head_lr": 0.0005,
    "inference_data_path": "/project/ranganathanr/niksapraljak/BioM3_PDZ/data/test_prompts_PDZ_swissprot_pfam_dataset.csv",
    "inference_output_path": "/project/ranganathanr/niksapraljak/BioM3_PDZ/outputs/Stage1_test_prompts_PDZ.pt"
}