Skip to content

fix: validate simplify skill templates #1950

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.

Sign up for GitHub

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

Open
njzjz-bot wants to merge 1 commit into
base: master
Choose a base branch
from
Open

fix: validate simplify skill templates #1950

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
10 changes: 6 additions & 4 deletions skills/dpgen-simplify/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -198,6 +198,7 @@ For each stage `train`, `model_devi`, and `fp`, collect or preserve:
- `machine.context_type`
- `machine.local_root`
- `machine.remote_root`
- `resources.batch_type` (use the same backend as `machine.batch_type`)
- `resources.number_node`
- `resources.cpu_per_node`
- `resources.gpu_per_node`
Expand Down Expand Up @@ -234,12 +235,11 @@ Key fields usually include:
- `numb_models`
- `default_training_param`
- `fp_style`
- `shuffle_poscar`
- `fp_task_max`
- `fp_task_min`
- `fp_pp_path`
- `fp_pp_files`
- `fp_params`
- backend support fields such as `fp_pp_path` and `fp_pp_files` only when the
selected FP schema requires them
- `init_pick_number`
- `iter_pick_number`
- `model_devi_f_trust_lo`
Expand All @@ -263,7 +263,7 @@ For each stage, keep the following explicit:

- `command`
- machine or context configuration
- resources
- resources, including the same `batch_type` used by the machine block
- queue or partition if needed
- cpu and gpu counts
- custom scheduler flags
Expand Down Expand Up @@ -316,6 +316,8 @@ Always provide:
- Keep `type_map` ordering consistent with dataset typing.
- If required inputs are missing, stop and ask instead of guessing.
- If `fp_style` is `none`, skip FP-specific prompts and keep FP-specific settings disabled or unset.
- The machine schema still requires an `fp` stage and a string command. Use the
no-op command `true` when `fp_style` is `none`.
- If data is already labeled and the user does not request new labels, enforce `fp_style = "none"` and do not require active FP runtime fields.
- Do not assume outer-shell activation is inherited by stage jobs; for scheduler execution, require explicit `source_list` per stage.
- If the user already has working templates, patch them rather than overwriting them blindly.
Expand Down
47 changes: 25 additions & 22 deletions skills/dpgen-simplify/assets/machine.template.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,46 +4,49 @@
"train": {
"command": "dp",
"machine": {
"batch_type": null,
"context_type": null,
"batch_type": "Shell",
"context_type": "LazyLocalContext",
"local_root": "./",
"remote_root": null
"remote_root": "./"
},
"resources": {
"number_node": null,
"cpu_per_node": null,
"gpu_per_node": null,
"group_size": null
"batch_type": "Shell",
"number_node": 1,
"cpu_per_node": 1,
"gpu_per_node": 0,
"group_size": 1
}
},
"model_devi": {
"command": "dp",
"machine": {
"batch_type": null,
"context_type": null,
"batch_type": "Shell",
"context_type": "LazyLocalContext",
"local_root": "./",
"remote_root": null
"remote_root": "./"
},
"resources": {
"number_node": null,
"cpu_per_node": null,
"gpu_per_node": null,
"group_size": null
"batch_type": "Shell",
"number_node": 1,
"cpu_per_node": 1,
"gpu_per_node": 0,
"group_size": 1
}
},
"fp": {
"command": null,
"command": "true",
"machine": {
"batch_type": null,
"context_type": null,
"batch_type": "Shell",
"context_type": "LazyLocalContext",
"local_root": "./",
"remote_root": null
"remote_root": "./"
},
"resources": {
"number_node": null,
"cpu_per_node": null,
"gpu_per_node": null,
"group_size": null
"batch_type": "Shell",
"number_node": 1,
"cpu_per_node": 1,
"gpu_per_node": 0,
"group_size": 1
}
}
}
17 changes: 10 additions & 7 deletions skills/dpgen-simplify/assets/machine.template.local-shell.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,9 +10,10 @@
"remote_root": "./"
},
"resources": {
"batch_type": "Shell",
"number_node": 1,
"cpu_per_node": null,
"gpu_per_node": null,
"cpu_per_node": 1,
"gpu_per_node": 0,
"group_size": 1
}
},
Expand All @@ -25,24 +26,26 @@
"remote_root": "./"
},
"resources": {
"batch_type": "Shell",
"number_node": 1,
"cpu_per_node": null,
"gpu_per_node": null,
"cpu_per_node": 1,
"gpu_per_node": 0,
"group_size": 1
}
},
"fp": {
"command": null,
"command": "true",
"machine": {
"batch_type": "Shell",
"context_type": "LazyLocalContext",
"local_root": "./",
"remote_root": "./"
},
"resources": {
"batch_type": "Shell",
"number_node": 1,
"cpu_per_node": null,
"gpu_per_node": null,
"cpu_per_node": 1,
"gpu_per_node": 0,
"group_size": 1
}
}
Expand Down
35 changes: 19 additions & 16 deletions skills/dpgen-simplify/assets/machine.template.server-local-slurm.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,13 +7,14 @@
"batch_type": "Slurm",
"context_type": "LocalContext",
"local_root": "./",
"remote_root": null
"remote_root": "./"
},
"resources": {
"number_node": null,
"cpu_per_node": null,
"gpu_per_node": null,
"queue_name": null,
"batch_type": "Slurm",
"number_node": 1,
"cpu_per_node": 1,
"gpu_per_node": 0,
"queue_name": "",
"group_size": 1,
"custom_flags": [],
"source_list": []
Expand All @@ -25,31 +26,33 @@
"batch_type": "Slurm",
"context_type": "LocalContext",
"local_root": "./",
"remote_root": null
"remote_root": "./"
},
"resources": {
"number_node": null,
"cpu_per_node": null,
"gpu_per_node": null,
"queue_name": null,
"batch_type": "Slurm",
"number_node": 1,
"cpu_per_node": 1,
"gpu_per_node": 0,
"queue_name": "",
"group_size": 1,
"custom_flags": [],
"source_list": []
}
},
"fp": {
"command": null,
"command": "true",
"machine": {
"batch_type": "Slurm",
"context_type": "LocalContext",
"local_root": "./",
"remote_root": null
"remote_root": "./"
},
"resources": {
"number_node": null,
"cpu_per_node": null,
"gpu_per_node": null,
"queue_name": null,
"batch_type": "Slurm",
"number_node": 1,
"cpu_per_node": 1,
"gpu_per_node": 0,
"queue_name": "",
"group_size": 1,
"custom_flags": [],
"source_list": []
Expand Down
53 changes: 28 additions & 25 deletions skills/dpgen-simplify/assets/machine.template.ssh-remote-slurm.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,19 +7,20 @@
"batch_type": "Slurm",
"context_type": "SSHContext",
"local_root": "./",
"remote_root": null,
"remote_root": "/path/to/remote/work",
"remote_profile": {
"hostname": null,
"username": null,
"hostname": "cluster.example.com",
"username": "REPLACE_ME",
"port": 22,
"key_filename": null
"key_filename": "/path/to/private/key"
}
},
"resources": {
"number_node": null,
"cpu_per_node": null,
"gpu_per_node": null,
"queue_name": null,
"batch_type": "Slurm",
"number_node": 1,
"cpu_per_node": 1,
"gpu_per_node": 0,
"queue_name": "",
"group_size": 1,
"custom_flags": [],
"source_list": []
Expand All @@ -31,43 +32,45 @@
"batch_type": "Slurm",
"context_type": "SSHContext",
"local_root": "./",
"remote_root": null,
"remote_root": "/path/to/remote/work",
"remote_profile": {
"hostname": null,
"username": null,
"hostname": "cluster.example.com",
"username": "REPLACE_ME",
"port": 22,
"key_filename": null
"key_filename": "/path/to/private/key"
}
},
"resources": {
"number_node": null,
"cpu_per_node": null,
"gpu_per_node": null,
"queue_name": null,
"batch_type": "Slurm",
"number_node": 1,
"cpu_per_node": 1,
"gpu_per_node": 0,
"queue_name": "",
"group_size": 1,
"custom_flags": [],
"source_list": []
}
},
"fp": {
"command": null,
"command": "true",
"machine": {
"batch_type": "Slurm",
"context_type": "SSHContext",
"local_root": "./",
"remote_root": null,
"remote_root": "/path/to/remote/work",
"remote_profile": {
"hostname": null,
"username": null,
"hostname": "cluster.example.com",
"username": "REPLACE_ME",
"port": 22,
"key_filename": null
"key_filename": "/path/to/private/key"
}
},
"resources": {
"number_node": null,
"cpu_per_node": null,
"gpu_per_node": null,
"queue_name": null,
"batch_type": "Slurm",
"number_node": 1,
"cpu_per_node": 1,
"gpu_per_node": 0,
"queue_name": "",
"group_size": 1,
"custom_flags": [],
"source_list": []
Expand Down
4 changes: 1 addition & 3 deletions skills/dpgen-simplify/assets/param.example.qm7.from-official-docs.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@
"pick_data": "/path/to/qm7/deepmd_npy",
"init_data_prefix": "",
"init_data_sys": [],
"sys_configs": [],
"sys_batch_size": [
"auto"
],
Expand Down Expand Up @@ -87,11 +88,8 @@
}
},
"fp_style": "gaussian",
"shuffle_poscar": false,
"fp_task_max": 1000,
"fp_task_min": 10,
"fp_pp_path": "/path/to/fp/support/files",
"fp_pp_files": [],
"fp_params": {
"keywords": "mn15/6-31g** force nosymm scf(maxcyc=512)",
"nproc": 28,
Expand Down
26 changes: 12 additions & 14 deletions skills/dpgen-simplify/assets/param.template.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,24 +1,22 @@
{
"type_map": null,
"mass_map": null,
"pick_data": null,
"sys_configs": null,
"type_map": [
"REPLACE_ME"
],
"mass_map": "auto",
"pick_data": "/path/to/deepmd/data",
"sys_configs": [],
"init_data_prefix": "",
"init_data_sys": [],
"sys_batch_size": [
"auto"
],
"train_backend": null,
"train_backend": "tensorflow",
"labeled": true,
"fp_task_max": null,
"fp_task_min": null,
"model_devi_e_trust_lo": null,
"model_devi_e_trust_hi": null,
"init_pick_number": null,
"iter_pick_number": null,
"model_devi_f_trust_lo": null,
"model_devi_f_trust_hi": null,
"init_pick_number": 100,
"iter_pick_number": 100,
"model_devi_f_trust_lo": 0.1,
"model_devi_f_trust_hi": 0.3,
"numb_models": 4,
"fp_style": "none",
"default_training_param": null
"default_training_param": {}
}
Loading