Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Example_dp2.x_lmp_gaussian #887

Merged
merged 10 commits into from
Aug 21, 2022
Merged
Show file tree
Hide file tree
Changes from 4 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion doc/troubleshooting/common-errors.md
Original file line number Diff line number Diff line change
Expand Up @@ -28,4 +28,7 @@ Some common reasons are as follows:
2. You may have something wrong in your input files, which causes the process to fail.

## RuntimeError: find too many unsuccessfully terminated jobs.
The ratio of failed jobs is larger than ratio_failure. You can set a high value for ratio_failure or check if there is something wrong with your input files.
The ratio of failed jobs is larger than ratio_failure. You can set a high value for ratio_failure or check if there is something wrong with your input files.

## Dargs: xxx is not allowed in strict mode.
Strict format check has been applied since version 0.10.6. To avoid misleading users, some older-version keys that are already ignored or absorbed into default settings are not allowed to be present. And the expected structure of the dictionary in the param.json also differs from those before versions 0.10.6. This error will occur when format check finds older-fashion keys in the json file. Please try deleting or annotating these keys, or correspondingly modulate the json file. Example files in the newest format could be found in [examples](https://github.com/deepmodeling/dpgen/tree/master/examples).
ziqi-hu marked this conversation as resolved.
Show resolved Hide resolved
3 changes: 3 additions & 0 deletions dpgen/generator/arginfo.py
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@ def basic_args() -> List[Argument]:


def data_args() -> List[Argument]:
doc_init_multi_systems = 'Read init_data_sys as MultiSystems.'
doc_init_data_prefix = 'Prefix of initial data directories.'
doc_init_data_sys = 'Directories of initial data. You may use either absolute or relative path here. Systems will be detected recursively in the directories.'
doc_sys_format = 'Format of initial data.'
Expand All @@ -41,6 +42,8 @@ def data_args() -> List[Argument]:
doc_sys_batch_size = 'Each number is the batch_size for training of corresponding system in sys_configs. If set to auto, batch size will be 32 divided by number of atoms.'

return [
Argument('init_multi_systems', bool, optional=True,
ziqi-hu marked this conversation as resolved.
Show resolved Hide resolved
doc = doc_init_multi_systems),
Argument("init_data_prefix", str, optional=True,
doc=doc_init_data_prefix),
Argument("init_data_sys", list,
Expand Down
110 changes: 110 additions & 0 deletions examples/run/dp2.x-lammps-gaussian/machine.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,110 @@
{
"api_version": "1.0",
"deepmd_version": "2.1.0",
"train" :
{
"command": "dp",
"machine": {
"batch_type": "Lebesgue",
"context_type": "LebesgueContext",
"local_root" : "./",
"remote_profile":{
"email": "[email protected]",
"password": "0415fnmsM.",
"program_id": 10330,
"keep_backup":true,
"input_data":{
"job_type": "indicate",
"log_file": "00*/train.log",
"grouped":true,
"job_name": "dpgen_train_job",
"disk_size": 100,
"scass_type":"c4_m15_1 * NVIDIA T4",
"checkpoint_files":["00*/checkpoint","00*/model.ckpt*"],
"checkpoint_time":30,
"platform": "ali",
"image_name":"LBG_DeePMD-kit_2.1.0_v1",
"on_demand":0
}
}
},
"resources": {
"batch_type": "Lebesgue",
"number_node": 1,
"cpu_per_node": 4,
"gpu_per_node": 1,
"queue_name": "T4_4_15",
"group_size": 1
}
},
"model_devi":
{
"command": "lmp",
"machine": {
"batch_type": "Lebesgue",
"context_type": "LebesgueContext",
"local_root" : "./",
"remote_profile":{
"email": "[email protected]",
"password": "0415fnmsM.",
"program_id": 10330,
"keep_backup":true,
"input_data":{
"job_type": "indicate",
"log_file": "*/model_devi.log",
"grouped":true,
"job_name": "dpgen_model_devi_job",
"disk_size": 200,
"scass_type":"c4_m15_1 * NVIDIA T4",
"platform": "ali",
"image_name":"LBG_DeePMD-kit_2.1.0_v1",
"on_demand":0
}
}
},
"resources": {
"batch_type": "Lebesgue",
"number_node": 1,
"cpu_per_node": 4,
"gpu_per_node": 1,
"queue_name": "T4_4_15",
"group_size": 50
}
},
"fp":
{
"command": "g09 < input > output ||:",
"machine": {
"batch_type": "Lebesgue",
"context_type": "LebesgueContext",
"local_root" : "./",
"remote_profile":{
"email": "[email protected]",
"password": "0415fnmsM.",
"program_id": 10330,
"input_data":{
"api_version":2,
"job_type": "indicate",
"log_file": "task*/fp.log",
"grouped":true,
"job_name": "dpgen_fp_job",
"disk_size": 100,
"scass_type":"c16_m32_cpu",
"platform": "ali",
"image_name":"LBG_Gaussian_09_v2",
"on_demand":0
}
}
},
"resources": {
"batch_type": "Lebesgue",
"source_list": ["/root/g09.sh"],
"number_node": 1,
"cpu_per_node": 16,
"gpu_per_node": 0,
"queue_name": "CPU",
"group_size": 10
}
}
}

143 changes: 143 additions & 0 deletions examples/run/dp2.x-lammps-gaussian/param_C4H16N4_deepmd-kit-2.0.1.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,143 @@
{
"type_map": [
"H",
"C",
"N"
],
"mass_map": [
1,
12,
14
],
"init_data_prefix": "./data/deepmd/",
"init_data_sys": [
"data.000","data.001","data.002","data.003","data.004","data.005"
],
"init_multi_systems": true,
"init_batch_size": ["auto","auto","auto","auto","auto","auto"],
"sys_configs": [
[
"./data/md_sys/data.ch4n2"
]
],
"_comment": " that's all ",
"numb_models": 4,
"sys_format":"lammps/lmp",
"default_training_param": {
"model": {
"type_map": [
"H",
"C",
"N"
],
"descriptor": {
"type": "se_e2_a",
"sel": [
16,
4,
4
],
"rcut_smth": 0.5,
"rcut": 5.0,
"neuron": [
25,
50,
100
],
"resnet_dt": true,
"axis_neuron": 12,
"seed": 1
},
"fitting_net": {
"neuron": [
120,
120,
120
],
"resnet_dt": false,
"seed": 1
}
},
"learning_rate": {
"type": "exp",
"start_lr": 0.001,
"decay_steps": 200
},
"loss": {
"start_pref_f": 1000,
"limit_pref_f": 1,
"start_pref_v": 0.0,
"limit_pref_v": 0.0
},
"training": {
"_set_prefix": "set",
"stop_batch": 20000,
"_batch_size": 1,
"disp_file": "lcurve.out",
"disp_freq": 1000,
"numb_test": 4,
"save_freq": 1000,
"save_ckpt": "model.ckpt",
"disp_training": true,
"time_training": true,
"profiling": false,
"profiling_file": "timeline.json",
"_comment": "that's all"
}
},
"model_devi_dt": 0.002,
"model_devi_skip": 0,
"model_devi_f_trust_lo": 0.02,
"model_devi_f_trust_hi": 1.95,
"model_devi_clean_traj": true,
"model_devi_jobs": [
{
"sys_idx": [
0
],
"temps": [
100
],
"press": [
1
],
"trj_freq": 10,
"nsteps": 2000,
"ensemble": "nvt",
"_idx": "00"
},
{
"sys_idx": [
0
],
"temps": [
100
],
"press": [
1
],
"trj_freq": 10,
"nsteps": 5000,
"ensemble": "nvt",
"_idx": "01"
}

],
"use_clusters": true,
"cluster_cutoff": 5.0,
"cluster_minify": true,
"use_relative": true,
"epsilon": 1.0,
"ratio_failed": 0.20,
"fp_style": "gaussian",
"shuffle_poscar": false,
"fp_task_max": 20,
"fp_task_min": 5,
"fp_pp_path": "./",
"fp_pp_files": [],
"fp_params":{
"keywords": "force B3LYP 6-31g(d,p) nosymm",
"nproc":2 ,
"multiplicity": "auto"
}
}
2 changes: 2 additions & 0 deletions tests/test_check_examples.py
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,7 @@
(run_jdata, p_examples / "run" / "deprecated" / "dp0.12-lammps-siesta" / "dp-lammps-siesta" / "CH4" / "param_CH4.json"),
(run_jdata, p_examples / "run" / "deprecated" / "dp0.12-lammps-vasp" / "Al" / "param_al_all_gpu.json"),
(run_jdata, p_examples / "run" / "deprecated" / "dp0.12-lammps-vasp" / "CH4" / "param_CH4.json"),
(run_jdata, p_examples / "run" / "dp2.x-lammps-gaussian" / "param_C4H16N4_deepmd-kit-2.0.1.json"),
# machines
#(run_mdata, p_examples / "machine" / "DeePMD-kit-2.x" / "lebesgue_v2_machine.json"),
#(run_mdata, p_examples / "machine" / "DeePMD-kit-1.x" / "machine-ali.json"),
Expand All @@ -72,6 +73,7 @@
(run_mdata, p_examples / "CH4-refact-dpdispatcher" / "machine-dpcloudserver.json"),
(run_mdata, p_examples / "run" / "dp2.x-lammps-ABACUS-lcao" / "fcc-al" / "machine.json"),
(run_mdata, p_examples / "run" / "dp2.x-lammps-ABACUS-pw" / "fcc-al" / "machine.json"),
(run_mdata, p_examples / "run" / "dp2.x-lammps-gaussian" / "machine.json"),
#(run_mdata, p_examples / "run" / "dp2.x-gromacs-gaussian" / "machine.json"),
(simplify_mdata, p_examples / "simplify-MAPbI3-scan-lebesgue" / "simplify_example" / "machine.json"),
)
Expand Down