logo
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Readme
Files and versions

54 lines
1.7 KiB

{
"train_datasets": [
{"name": "coco_cap",
"db": ["/db/pretrain_caption_coco_train_base-cased.db/",
"/db/pretrain_caption_coco_trainval_base-cased.db/"],
"img": ["/img/coco_train2014/", "/img/coco_val2014/"],
"tasks": ["itm", "mlm", "mrfr", "mrckl"],
"mix_ratio": [2, 2, 1, 1]},
{"name": "vg_cap",
"db": ["/db/pretrain_caption_vg_train_base-cased.db/"],
"img": ["/img/vg/"],
"tasks": ["itm", "mlm", "mrfr", "mrckl"],
"mix_ratio": [2, 2, 1, 1]}
],
"val_datasets": [
{"name": "coco_cap",
"db": ["/db/pretrain_caption_coco_val_base-cased.db/"],
"img": ["/img/coco_val2014/"],
"tasks": ["itm", "mlm", "mrfr", "mrckl"]},
{"name": "vg_cap",
"db": ["/db/pretrain_caption_vg_val_base-cased.db/"],
"img": ["/img/vg/"],
"tasks": ["itm", "mlm", "mrfr", "mrckl"]}
],
"model_config": "/src/config/uniter-base.json",
"checkpoint": "/pretrain/bert-base-cased.pt",
"output_dir": "/storage/pretrain/alltask_ot_indomain_base",
"ans2label": "/db/pretrain_ans2label.pkl",
"mrm_prob": 0.15,
"itm_neg_prob": 0.5,
"itm_ot_lambda": 0.1,
"max_txt_len": 60,
"conf_th": 0.2,
"max_bb": 100,
"min_bb": 10,
"num_bb": 36,
"train_batch_size": 10240,
"val_batch_size": 10240,
"gradient_accumulation_steps": 2,
"learning_rate": 5e-05,
"valid_steps": 5000,
"num_train_steps": 200000,
"optim": "adamw",
"decay": "linear",
"dropout": 0.1,
"weight_decay": 0.01,
"grad_norm": 5.0,
"warmup_steps": 10000,
"seed": 42,
"fp16": true,
"pin_mem": true,
"n_workers": 4
}