args.json

{
  "data_source": "/scratch/ssd004/datasets/cellxgene/scb_strict/brain/all_counts",
  "save_dir": "./save/cellxgene_census_brain-May19-02-00-2023",
  "load_model": null,
  "n_hvg": null,
  "valid_size_or_ratio": 0.03,
  "vocab_path": "/scratch/ssd004/datasets/cellxgene/scFormer/scformer/tokenizer/default_census_vocab.json",
  "pad_token": "<pad>",
  "input_style": "binned",
  "input_emb_style": "continuous",
  "n_bins": 51,
  "max_seq_len": 1200,
  "training_tasks": "both",
  "mask_ratio": [
    0.25,
    0.5,
    0.75
  ],
  "trunc_by_sample": true,
  "local_rank": 0,
  "batch_size": 32,
  "eval_batch_size": 64,
  "grad_accu_steps": 1,
  "epochs": 6,
  "lr": 0.0001,
  "scheduler_interval": 100,
  "scheduler_factor": 0.99,
  "warmup_ratio_or_step": 10000.0,
  "no_cls": true,
  "no_cce": true,
  "fp16": true,
  "fast_transformer": true,
  "nlayers": 12,
  "nheads": 8,
  "embsize": 512,
  "d_hid": 512,
  "dropout": 0.2,
  "n_layers_cls": 3,
  "log_interval": 6000,
  "save_interval": 18000,
  "mask_value": -1,
  "pad_value": -2,
  "ntoken": 60697,
  "n_cls": 1,
  "MVC": false,
  "DAB": false,
  "cell_emb_style": "cls",
  "pre_norm": false,
  "explicit_zero_prob": false,
  "ecs_threshold": 0.3,
  "mvc_decoder_style": "inner product",
  "use_batch_labels": false,
  "domain_spec_batchnorm": false,
  "pert_pad_id": 2
}