Deepmd plus lammps md simulations

[lanjh09]

I have tried running md simulation of organic molecules in water based on the deepmd train. Howvever, the structure of organiic molecules broke down at the beginning. Could anyone give me some suggestions?

The system contains 3 organic molecules and water as well as a metal ion.
The input is like this:

{
"_comment": " model parameters",
"model": {
"type_map": ["C","H","N","O","U"],
"descriptor" :{
"type": "se_e2_a",
"sel": [46, 92, 46, 46, 46],
"rcut_smth": 0.50,
"rcut": 6.00,
"neuron": [25, 50, 100],
"resnet_dt": false,
"axis_neuron": 16,
"seed": 1,
"_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":  50,
    "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"
},

[njzjz]

Please read the checklist in the documentation to see if anything can be improved. Thanks!