update test data

tests/auto/phonons/test_flows.py

@@ -946,16 +946,16 @@ def test_complete_dft_vs_ml_benchmark_workflow_nep(
         pre_database_dir=test_dir / "fitting" / "ref_files",
         benchmark_structures=[structure],
         fit_kwargs_list=[{
-            "generation": 100,
-            "batch": 100,
+            "generation": 1000,
+            "batch": 1,
             }]
     )
 
     # automatically use fake VASP and write POTCAR.spec during the test
     mock_vasp(ref_paths4_mpid, fake_run_vasp_kwargs4_mpid)
 
     # mock nep
-    ref_paths_nep = {"machine_learning_fit": "LiCl"}
+    ref_paths_nep = {"machine_learning_fit": "LiCl_complete_dft_vs_ml_benchmark_workflow"}
     fake_run_nep_kwargs = {
         "machine_learning_fit": {"nep_settings": ["generation", "batch", "type_weight"], "check_nep_inputs": True}}
     mock_nep(ref_paths_nep, fake_run_nep_kwargs)
@@ -970,7 +970,7 @@ def test_complete_dft_vs_ml_benchmark_workflow_nep(
     assert complete_workflow_nep.jobs[5].name == "complete_benchmark_mp-22905"
     assert responses[complete_workflow_nep.jobs[-1].output.uuid][1].output["metrics"][0][0][
                "benchmark_phonon_rmse"] == pytest.approx(
-        1.2588388619302524
+        3.8951576702856716
     )
 
 def test_complete_dft_vs_ml_benchmark_workflow_mace(

tests/conftest.py

@@ -136,7 +136,7 @@ def memory_jobstore():
 
 @pytest.fixture(scope="session")
 def nep_test_dir(test_dir):
-    return test_dir / "nep"
+    return test_dir / "fitting" / "NEP"
 
 @pytest.fixture
 def mock_nep(monkeypatch, nep_test_dir):

tests/fitting/common/test_flows.py

@@ -269,7 +269,7 @@ def test_mlip_fit_maker_nep(
         **{"generation": 100, "batch": 100},
     )
 
-    ref_paths_nep = {"machine_learning_fit": "LiCl"}
+    ref_paths_nep = {"machine_learning_fit": "LiCl_mlipfitmaker"}
     fake_run_nep_kwargs = {
         "machine_learning_fit": {"nep_settings": ["generation", "batch", "type_weight"], "check_nep_inputs": True}}
     mock_nep(ref_paths_nep, fake_run_nep_kwargs)

tests/test_data/fitting/NEP/LiCl_complete_dft_vs_ml_benchmark_workflow/inputs/nep.in

@@ -0,0 +1,19 @@
+version  4
+type  2 Cl Li
+type_weight  1.0 1.0
+model_type   0
+prediction  0
+cutoff  6 5
+n_max  4 4
+basis_size  8 8
+l_max  4 2 1
+neuron   80
+lambda_1  0
+lambda_e  1.0
+lambda_f  1.0
+lambda_v  0.1
+force_delta  0
+batch  1
+population  60
+generation  1000
+zbl  2

tests/test_data/fitting/NEP/LiCl_complete_dft_vs_ml_benchmark_workflow/outputs/energy_test.out

@@ -0,0 +1,6 @@
+-3.78179 -3.80685
+-3.78275 -3.8187
+-3.78292 -3.81927
+-3.78319 -3.81107
+-3.78292 -3.81927
+-3.77989 -3.77989

tests/test_data/fitting/NEP/LiCl_complete_dft_vs_ml_benchmark_workflow/outputs/energy_train.out

@@ -0,0 +1,8 @@
+-3.78292 -3.81927
+-3.78292 -3.81927
+-3.78292 -3.81927
+-3.78292 -3.81927
+-3.78275 -3.8187
+-3.78319 -3.81107
+-3.78179 -3.80685
+-3.77989 -3.77989

tests/test_data/fitting/NEP/LiCl_complete_dft_vs_ml_benchmark_workflow/outputs/loss.out

@@ -0,0 +1,10 @@
+100     0.03622    0.00000    0.03390    0.00000      0.00207      0.00248      0.01718      0.02292      0.17095      
+200     0.08109    0.00000    0.03197    0.00000      0.01452      0.34597      0.18150      0.41054      0.80414      
+300     0.03263    0.00000    0.03012    0.00000      0.00249      0.00021      0.01719      0.02097      0.17423      
+400     0.07128    0.00000    0.02896    0.00000      0.01396      0.28364      0.03058      0.01597      0.15819      
+500     0.03029    0.00000    0.02810    0.00000      0.00213      0.00058      0.01510      0.11608      0.11391      
+600     0.07390    0.00000    0.02719    0.00000      0.01381      0.32894      0.03168      0.02064      0.17143      
+700     0.02790    0.00000    0.02643    0.00000      0.00145      0.00016      0.00817      0.03671      0.11751      
+800     0.06863    0.00000    0.02585    0.00000      0.01729      0.25491      0.02933      0.02017      0.14767      
+900     0.02613    0.00000    0.02501    0.00000      0.00062      0.00498      0.01616      0.02158      0.16808      
+1000    0.07058    0.00000    0.02493    0.00000      0.01457      0.31079      0.02983      0.01799      0.16420