How to set training_data/systems and validation_data/systems if I set set_size=some exact number when I prepare the data?

[Lihuigao21]

For example, I run MD for 5000 steps and I want to 1000 steps of them to be validation_data, so I set set_size=1000. Then I get set.000 to set.004. Then how can I set training_data/systems and validation_data/systems in input.json? If I delete all the "validation_data" part , I find that the lcurve.out will miss some rows. Thanks for helping me.

I know that if I set set_size=1000 then it is default to regard set.004 as validation_data. But how to let deepmd use this "default" without do harm to lcurve.out?

My input.json:
`{
"_comment": " model parameters",
"model": {
"type_map": ["Ti", "O", "H.66", "H1.33", "H"],
"descriptor" :{
"type": "se_e2_a",
"sel": [40,70,10,15,15],
"rcut_smth": 0.50,
"rcut": 6.00,
"neuron": [25, 50, 100],
"resnet_dt": false,
"axis_neuron": 16,
"seed": 983,
"_comment": " that's all"
},
"fitting_net" : {
"neuron": [240, 240, 240],
"resnet_dt": true,
"seed": 1,
"_comment": " that's all"
},
"_comment": " that's all"
},

"learning_rate" :{
"type":		"exp",
"decay_steps":	5000,
"start_lr":	0.001,	
"stop_lr":	3.51e-8,
"_comment":	"that's all"
},

"loss" :{
"type":		"ener",
"start_pref_e":	0.02,
"limit_pref_e":	1,
"start_pref_f":	1000,
"limit_pref_f":	1,
"start_pref_v":	0,
"limit_pref_v":	0,
"_comment":	" that's all"
},

"training" : {
"training_data": {
    "systems":		["t=300/", "t=100/", "t=500/", "t=100ts/", "t=300ts/", "t=500ts/", "t=100dis/", "t=300dis/", "t=500dis/"],
    "batch_size":	"auto",
    "_comment":		"that's all"
},

"numb_steps":	1000000,
"seed":		10,
"disp_file":	"lcurve.out",
"disp_freq":	100,
"save_freq":	1000,
"_comment":	"that's all"
},    

"_comment":		"that's all"

}
`

[wanghan-iapcm]

split the training and validation sets in different folders and refer them by training_data and validation_data.

[Lihuigao21]

Great idea, I will have a try.