From 1fd45446cdf8e6d517e82f1047417da27cf5f5b4 Mon Sep 17 00:00:00 2001
From: Anyang Peng <137014849+anyangml@users.noreply.github.com>
Date: Mon, 26 May 2025 13:31:54 +0800
Subject: [PATCH 01/14] feat: add rglob by patterns

---
 deepmd/common.py              | 21 +++++++++++++++++++++
 deepmd/pt/entrypoints/main.py |  6 ++++--
 deepmd/utils/data_system.py   | 10 ++++++++--
 3 files changed, 33 insertions(+), 4 deletions(-)

diff --git a/deepmd/common.py b/deepmd/common.py
index c9873a6d94..8ab8722bce 100644
--- a/deepmd/common.py
+++ b/deepmd/common.py
@@ -206,6 +206,27 @@ def expand_sys_str(root_dir: Union[str, Path]) -> list[str]:
         matches.append(str(root_dir))
     return matches
 
+def rglob_sys_str(root_dir: str, patterns: list[str]) -> list[str]:
+    """Recursively iterate over directories taking those that contain `type.raw` file.
+
+    Parameters
+    ----------
+    root_dir : str, Path
+        starting directory
+    patterns : list[str]
+        list of glob patterns to match directories
+
+    Returns
+    -------
+    list[str]
+        list of string pointing to system directories
+    """
+    root_dir = Path(root_dir)
+    matches = []
+    for pattern in patterns:
+        matches.extend([str(d) for d in root_dir.rglob(pattern) if (d / "type.raw").is_file()])
+    return matches
+
 
 def get_np_precision(precision: "_PRECISION") -> np.dtype:
     """Get numpy precision constant from string.
diff --git a/deepmd/pt/entrypoints/main.py b/deepmd/pt/entrypoints/main.py
index 3fe507ecc2..0e248583ec 100644
--- a/deepmd/pt/entrypoints/main.py
+++ b/deepmd/pt/entrypoints/main.py
@@ -114,9 +114,11 @@ def prepare_trainer_input_single(
             validation_dataset_params["systems"] if validation_dataset_params else None
         )
         training_systems = training_dataset_params["systems"]
-        training_systems = process_systems(training_systems)
+        trn_patterns = training_dataset_params.get("rglob_patterns", None)
+        training_systems = process_systems(training_systems, patterns=trn_patterns)
         if validation_systems is not None:
-            validation_systems = process_systems(validation_systems)
+            val_patterns = validation_dataset_params.get("rglob_patterns", None)
+            validation_systems = process_systems(validation_systems, val_patterns)
 
         # stat files
         stat_file_path_single = data_dict_single.get("stat_file", None)
diff --git a/deepmd/utils/data_system.py b/deepmd/utils/data_system.py
index fbc9c1a684..081f0ddf5a 100644
--- a/deepmd/utils/data_system.py
+++ b/deepmd/utils/data_system.py
@@ -16,6 +16,7 @@
 import deepmd.utils.random as dp_random
 from deepmd.common import (
     expand_sys_str,
+    rglob_sys_str,
     make_default_mesh,
 )
 from deepmd.env import (
@@ -730,7 +731,7 @@ def prob_sys_size_ext(keywords, nsystems, nbatch):
     return sys_probs
 
 
-def process_systems(systems: Union[str, list[str]]) -> list[str]:
+def process_systems(systems: Union[str, list[str]], patterns: Optional[list[str]]=None) -> list[str]:
     """Process the user-input systems.
 
     If it is a single directory, search for all the systems in the directory.
@@ -740,6 +741,8 @@ def process_systems(systems: Union[str, list[str]]) -> list[str]:
     ----------
     systems : str or list of str
         The user-input systems
+    patterns : list of str, optional
+        The patterns to match the systems, by default None
 
     Returns
     -------
@@ -747,7 +750,10 @@ def process_systems(systems: Union[str, list[str]]) -> list[str]:
         The valid systems
     """
     if isinstance(systems, str):
-        systems = expand_sys_str(systems)
+        if patterns is None:
+            systems = expand_sys_str(systems)
+        else:
+            systems = rglob_sys_str(systems, patterns)
     elif isinstance(systems, list):
         systems = systems.copy()
     return systems

From b5c6be4765595fed4e0822950e4b9b7c7fab526f Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Mon, 26 May 2025 05:34:23 +0000
Subject: [PATCH 02/14] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 deepmd/common.py            | 5 ++++-
 deepmd/utils/data_system.py | 6 ++++--
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/deepmd/common.py b/deepmd/common.py
index 8ab8722bce..d7cc118ba1 100644
--- a/deepmd/common.py
+++ b/deepmd/common.py
@@ -206,6 +206,7 @@ def expand_sys_str(root_dir: Union[str, Path]) -> list[str]:
         matches.append(str(root_dir))
     return matches
 
+
 def rglob_sys_str(root_dir: str, patterns: list[str]) -> list[str]:
     """Recursively iterate over directories taking those that contain `type.raw` file.
 
@@ -224,7 +225,9 @@ def rglob_sys_str(root_dir: str, patterns: list[str]) -> list[str]:
     root_dir = Path(root_dir)
     matches = []
     for pattern in patterns:
-        matches.extend([str(d) for d in root_dir.rglob(pattern) if (d / "type.raw").is_file()])
+        matches.extend(
+            [str(d) for d in root_dir.rglob(pattern) if (d / "type.raw").is_file()]
+        )
     return matches
 
 
diff --git a/deepmd/utils/data_system.py b/deepmd/utils/data_system.py
index 081f0ddf5a..072eb5b7b4 100644
--- a/deepmd/utils/data_system.py
+++ b/deepmd/utils/data_system.py
@@ -16,8 +16,8 @@
 import deepmd.utils.random as dp_random
 from deepmd.common import (
     expand_sys_str,
-    rglob_sys_str,
     make_default_mesh,
+    rglob_sys_str,
 )
 from deepmd.env import (
     GLOBAL_NP_FLOAT_PRECISION,
@@ -731,7 +731,9 @@ def prob_sys_size_ext(keywords, nsystems, nbatch):
     return sys_probs
 
 
-def process_systems(systems: Union[str, list[str]], patterns: Optional[list[str]]=None) -> list[str]:
+def process_systems(
+    systems: Union[str, list[str]], patterns: Optional[list[str]] = None
+) -> list[str]:
     """Process the user-input systems.
 
     If it is a single directory, search for all the systems in the directory.

From 6f999331fa9b2e0a71b12e50c763979645cea3c2 Mon Sep 17 00:00:00 2001
From: Anyang Peng <137014849+anyangml@users.noreply.github.com>
Date: Mon, 26 May 2025 13:57:23 +0800
Subject: [PATCH 03/14] feat: add argcheck

---
 deepmd/utils/argcheck.py | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/deepmd/utils/argcheck.py b/deepmd/utils/argcheck.py
index 7554abc7e6..126c69b80a 100644
--- a/deepmd/utils/argcheck.py
+++ b/deepmd/utils/argcheck.py
@@ -2886,6 +2886,9 @@ def training_data_args():  # ! added by Ziyao: new specification style for data
         "This key can be provided with a list that specifies the systems, or be provided with a string "
         "by which the prefix of all systems are given and the list of the systems is automatically generated."
     )
+    doc_patterns = (
+        "The customized patterns used in `rglob` to collect all training systems. "
+    )
     doc_batch_size = f'This key can be \n\n\
 - list: the length of which is the same as the {link_sys}. The batch size of each system is given by the elements of the list.\n\n\
 - int: all {link_sys} use the same batch size.\n\n\
@@ -2909,6 +2912,9 @@ def training_data_args():  # ! added by Ziyao: new specification style for data
         Argument(
             "systems", [list[str], str], optional=False, default=".", doc=doc_systems
         ),
+        Argument(
+            "rglob_patterns", [list[str]], optional=True, default=None, doc=doc_patterns
+        ),
         Argument(
             "batch_size",
             [list[int], int, str],
@@ -2955,6 +2961,9 @@ def validation_data_args():  # ! added by Ziyao: new specification style for dat
         "This key can be provided with a list that specifies the systems, or be provided with a string "
         "by which the prefix of all systems are given and the list of the systems is automatically generated."
     )
+    doc_patterns = (
+        "The customized patterns used in `rglob` to collect all validation systems. "
+    )
     doc_batch_size = f'This key can be \n\n\
 - list: the length of which is the same as the {link_sys}. The batch size of each system is given by the elements of the list.\n\n\
 - int: all {link_sys} use the same batch size.\n\n\
@@ -2974,6 +2983,9 @@ def validation_data_args():  # ! added by Ziyao: new specification style for dat
     args = [
         Argument(
             "systems", [list[str], str], optional=False, default=".", doc=doc_systems
+        ),
+         Argument(
+            "rglob_patterns", [list[str]], optional=True, default=None, doc=doc_patterns
         ),
         Argument(
             "batch_size",

From 1aa0ddf9a29fb1333d4c37d951e32df0812980de Mon Sep 17 00:00:00 2001
From: Anyang Peng <137014849+anyangml@users.noreply.github.com>
Date: Mon, 26 May 2025 13:58:15 +0800
Subject: [PATCH 04/14] fix: add duplicates check

---
 deepmd/common.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/deepmd/common.py b/deepmd/common.py
index d7cc118ba1..23b55203d3 100644
--- a/deepmd/common.py
+++ b/deepmd/common.py
@@ -228,7 +228,8 @@ def rglob_sys_str(root_dir: str, patterns: list[str]) -> list[str]:
         matches.extend(
             [str(d) for d in root_dir.rglob(pattern) if (d / "type.raw").is_file()]
         )
-    return matches
+    return list(set(matches))  # remove duplicates
+
 
 
 def get_np_precision(precision: "_PRECISION") -> np.dtype:

From 030143e7a1bac3e49cdbe5cf0faaf985f45e814c Mon Sep 17 00:00:00 2001
From: Anyang Peng <137014849+anyangml@users.noreply.github.com>
Date: Mon, 26 May 2025 14:01:49 +0800
Subject: [PATCH 05/14] doc: add support PT only

---
 deepmd/utils/argcheck.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/deepmd/utils/argcheck.py b/deepmd/utils/argcheck.py
index 126c69b80a..0d6437ab62 100644
--- a/deepmd/utils/argcheck.py
+++ b/deepmd/utils/argcheck.py
@@ -2913,7 +2913,7 @@ def training_data_args():  # ! added by Ziyao: new specification style for data
             "systems", [list[str], str], optional=False, default=".", doc=doc_systems
         ),
         Argument(
-            "rglob_patterns", [list[str]], optional=True, default=None, doc=doc_patterns
+            "rglob_patterns", [list[str]], optional=True, default=None, doc=doc_patterns + doc_only_pt_supported
         ),
         Argument(
             "batch_size",
@@ -2985,7 +2985,7 @@ def validation_data_args():  # ! added by Ziyao: new specification style for dat
             "systems", [list[str], str], optional=False, default=".", doc=doc_systems
         ),
          Argument(
-            "rglob_patterns", [list[str]], optional=True, default=None, doc=doc_patterns
+            "rglob_patterns", [list[str]], optional=True, default=None, doc=doc_patterns + doc_only_pt_supported
         ),
         Argument(
             "batch_size",

From 9b704878fa360069f9d04b2378044c51f855ab25 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Mon, 26 May 2025 06:06:05 +0000
Subject: [PATCH 06/14] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 deepmd/common.py         |  1 -
 deepmd/utils/argcheck.py | 14 +++++++++++---
 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/deepmd/common.py b/deepmd/common.py
index 23b55203d3..3ab936db67 100644
--- a/deepmd/common.py
+++ b/deepmd/common.py
@@ -231,7 +231,6 @@ def rglob_sys_str(root_dir: str, patterns: list[str]) -> list[str]:
     return list(set(matches))  # remove duplicates
 
 
-
 def get_np_precision(precision: "_PRECISION") -> np.dtype:
     """Get numpy precision constant from string.
 
diff --git a/deepmd/utils/argcheck.py b/deepmd/utils/argcheck.py
index 0d6437ab62..0ac2fa8b82 100644
--- a/deepmd/utils/argcheck.py
+++ b/deepmd/utils/argcheck.py
@@ -2913,7 +2913,11 @@ def training_data_args():  # ! added by Ziyao: new specification style for data
             "systems", [list[str], str], optional=False, default=".", doc=doc_systems
         ),
         Argument(
-            "rglob_patterns", [list[str]], optional=True, default=None, doc=doc_patterns + doc_only_pt_supported
+            "rglob_patterns",
+            [list[str]],
+            optional=True,
+            default=None,
+            doc=doc_patterns + doc_only_pt_supported,
         ),
         Argument(
             "batch_size",
@@ -2984,8 +2988,12 @@ def validation_data_args():  # ! added by Ziyao: new specification style for dat
         Argument(
             "systems", [list[str], str], optional=False, default=".", doc=doc_systems
         ),
-         Argument(
-            "rglob_patterns", [list[str]], optional=True, default=None, doc=doc_patterns + doc_only_pt_supported
+        Argument(
+            "rglob_patterns",
+            [list[str]],
+            optional=True,
+            default=None,
+            doc=doc_patterns + doc_only_pt_supported,
         ),
         Argument(
             "batch_size",

From 7c247d5067c7dca4a44573f947663077afc7b8df Mon Sep 17 00:00:00 2001
From: Anyang Peng <137014849+anyangml@users.noreply.github.com>
Date: Tue, 27 May 2025 14:44:22 +0800
Subject: [PATCH 07/14] fix: pass patterns to get_data

---
 deepmd/utils/data_system.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/deepmd/utils/data_system.py b/deepmd/utils/data_system.py
index 072eb5b7b4..07dab35a90 100644
--- a/deepmd/utils/data_system.py
+++ b/deepmd/utils/data_system.py
@@ -785,7 +785,8 @@ def get_data(
         The data system
     """
     systems = jdata["systems"]
-    systems = process_systems(systems)
+    rglob_patterns = jdata.get("rglob_patterns", None)
+    systems = process_systems(systems, patterns=rglob_patterns)
 
     batch_size = jdata["batch_size"]
     sys_probs = jdata.get("sys_probs", None)

From fd59bf9f133ea96304b585a7e920c51461558170 Mon Sep 17 00:00:00 2001
From: Anyang Peng <137014849+anyangml@users.noreply.github.com>
Date: Tue, 3 Jun 2025 12:46:26 +0800
Subject: [PATCH 08/14] feat: add integration test

---
 source/tests/pt/test_training.py | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/source/tests/pt/test_training.py b/source/tests/pt/test_training.py
index ad52c5db16..237fa9e8a6 100644
--- a/source/tests/pt/test_training.py
+++ b/source/tests/pt/test_training.py
@@ -516,5 +516,22 @@ def tearDown(self) -> None:
                 shutil.rmtree(f)
 
 
+class TestCustomizedRGLOB(unittest.TestCase, DPTrainTest):
+    def setUp(self) -> None:
+        input_json = str(Path(__file__).parent / "water/se_atten.json")
+        with open(input_json) as f:
+            self.config = json.load(f)
+        data_file = [str(Path(__file__).parent / "water/data/data_0")]
+        self.config["training"]["training_data"]["rglob_patterns"] = "water/data/data_*"
+        self.config["training"]["training_data"]["systems"] = str(Path(__file__).parent)
+        self.config["training"]["validation_data"]["rglob_patterns"] = "water/data/data_1"
+        self.config["training"]["validation_data"]["systems"] = str(Path(__file__).parent)
+        self.config["model"] = deepcopy(model_dpa1)
+        self.config["training"]["numb_steps"] = 1
+        self.config["training"]["save_freq"] = 1
+
+    def tearDown(self) -> None:
+        DPTrainTest.tearDown(self)
+
 if __name__ == "__main__":
     unittest.main()

From ff52ad294d11166d5fbdff5795010f1ff4249858 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Tue, 3 Jun 2025 04:48:06 +0000
Subject: [PATCH 09/14] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 source/tests/pt/test_training.py | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/source/tests/pt/test_training.py b/source/tests/pt/test_training.py
index 237fa9e8a6..9db43c1b37 100644
--- a/source/tests/pt/test_training.py
+++ b/source/tests/pt/test_training.py
@@ -524,8 +524,12 @@ def setUp(self) -> None:
         data_file = [str(Path(__file__).parent / "water/data/data_0")]
         self.config["training"]["training_data"]["rglob_patterns"] = "water/data/data_*"
         self.config["training"]["training_data"]["systems"] = str(Path(__file__).parent)
-        self.config["training"]["validation_data"]["rglob_patterns"] = "water/data/data_1"
-        self.config["training"]["validation_data"]["systems"] = str(Path(__file__).parent)
+        self.config["training"]["validation_data"]["rglob_patterns"] = (
+            "water/data/data_1"
+        )
+        self.config["training"]["validation_data"]["systems"] = str(
+            Path(__file__).parent
+        )
         self.config["model"] = deepcopy(model_dpa1)
         self.config["training"]["numb_steps"] = 1
         self.config["training"]["save_freq"] = 1
@@ -533,5 +537,6 @@ def setUp(self) -> None:
     def tearDown(self) -> None:
         DPTrainTest.tearDown(self)
 
+
 if __name__ == "__main__":
     unittest.main()

From e621ce205f740effdaaa13be622f8d9e025bdaac Mon Sep 17 00:00:00 2001
From: Anyang Peng <137014849+anyangml@users.noreply.github.com>
Date: Tue, 3 Jun 2025 12:52:32 +0800
Subject: [PATCH 10/14] chore: remove redundant

---
 source/tests/pt/test_training.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/source/tests/pt/test_training.py b/source/tests/pt/test_training.py
index 9db43c1b37..cfc63c7c4b 100644
--- a/source/tests/pt/test_training.py
+++ b/source/tests/pt/test_training.py
@@ -521,7 +521,6 @@ def setUp(self) -> None:
         input_json = str(Path(__file__).parent / "water/se_atten.json")
         with open(input_json) as f:
             self.config = json.load(f)
-        data_file = [str(Path(__file__).parent / "water/data/data_0")]
         self.config["training"]["training_data"]["rglob_patterns"] = "water/data/data_*"
         self.config["training"]["training_data"]["systems"] = str(Path(__file__).parent)
         self.config["training"]["validation_data"]["rglob_patterns"] = (

From fc402537d3a2bac9368e90d6b5e718363c61302c Mon Sep 17 00:00:00 2001
From: Anyang Peng <137014849+anyangml@users.noreply.github.com>
Date: Tue, 3 Jun 2025 13:12:39 +0800
Subject: [PATCH 11/14] fix: update pattern

---
 source/tests/pt/test_training.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/source/tests/pt/test_training.py b/source/tests/pt/test_training.py
index cfc63c7c4b..336e2a7e2e 100644
--- a/source/tests/pt/test_training.py
+++ b/source/tests/pt/test_training.py
@@ -524,7 +524,7 @@ def setUp(self) -> None:
         self.config["training"]["training_data"]["rglob_patterns"] = "water/data/data_*"
         self.config["training"]["training_data"]["systems"] = str(Path(__file__).parent)
         self.config["training"]["validation_data"]["rglob_patterns"] = (
-            "water/data/data_1"
+            "water/*/data_0"
         )
         self.config["training"]["validation_data"]["systems"] = str(
             Path(__file__).parent

From 16fd12d1de088a331bca0446af54a32f9e11ac03 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Tue, 3 Jun 2025 05:14:15 +0000
Subject: [PATCH 12/14] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 source/tests/pt/test_training.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/source/tests/pt/test_training.py b/source/tests/pt/test_training.py
index 336e2a7e2e..30705ee6ab 100644
--- a/source/tests/pt/test_training.py
+++ b/source/tests/pt/test_training.py
@@ -523,9 +523,7 @@ def setUp(self) -> None:
             self.config = json.load(f)
         self.config["training"]["training_data"]["rglob_patterns"] = "water/data/data_*"
         self.config["training"]["training_data"]["systems"] = str(Path(__file__).parent)
-        self.config["training"]["validation_data"]["rglob_patterns"] = (
-            "water/*/data_0"
-        )
+        self.config["training"]["validation_data"]["rglob_patterns"] = "water/*/data_0"
         self.config["training"]["validation_data"]["systems"] = str(
             Path(__file__).parent
         )

From 7f4c958747735641db7c275bb84a2674af50d24d Mon Sep 17 00:00:00 2001
From: Anyang Peng <137014849+anyangml@users.noreply.github.com>
Date: Tue, 3 Jun 2025 14:15:35 +0800
Subject: [PATCH 13/14] fix: UT dtype

---
 source/tests/pt/test_training.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/source/tests/pt/test_training.py b/source/tests/pt/test_training.py
index 30705ee6ab..cf3c010b0b 100644
--- a/source/tests/pt/test_training.py
+++ b/source/tests/pt/test_training.py
@@ -521,9 +521,9 @@ def setUp(self) -> None:
         input_json = str(Path(__file__).parent / "water/se_atten.json")
         with open(input_json) as f:
             self.config = json.load(f)
-        self.config["training"]["training_data"]["rglob_patterns"] = "water/data/data_*"
+        self.config["training"]["training_data"]["rglob_patterns"] = ["water/data/data_*"]
         self.config["training"]["training_data"]["systems"] = str(Path(__file__).parent)
-        self.config["training"]["validation_data"]["rglob_patterns"] = "water/*/data_0"
+        self.config["training"]["validation_data"]["rglob_patterns"] = ["water/*/data_0"]
         self.config["training"]["validation_data"]["systems"] = str(
             Path(__file__).parent
         )

From b8c5db63a4fc39e49c90ef514677650d0c75d682 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Tue, 3 Jun 2025 06:17:16 +0000
Subject: [PATCH 14/14] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 source/tests/pt/test_training.py | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/source/tests/pt/test_training.py b/source/tests/pt/test_training.py
index cf3c010b0b..3df95e4b14 100644
--- a/source/tests/pt/test_training.py
+++ b/source/tests/pt/test_training.py
@@ -521,9 +521,13 @@ def setUp(self) -> None:
         input_json = str(Path(__file__).parent / "water/se_atten.json")
         with open(input_json) as f:
             self.config = json.load(f)
-        self.config["training"]["training_data"]["rglob_patterns"] = ["water/data/data_*"]
+        self.config["training"]["training_data"]["rglob_patterns"] = [
+            "water/data/data_*"
+        ]
         self.config["training"]["training_data"]["systems"] = str(Path(__file__).parent)
-        self.config["training"]["validation_data"]["rglob_patterns"] = ["water/*/data_0"]
+        self.config["training"]["validation_data"]["rglob_patterns"] = [
+            "water/*/data_0"
+        ]
         self.config["training"]["validation_data"]["systems"] = str(
             Path(__file__).parent
         )