-
Notifications
You must be signed in to change notification settings - Fork 10
/
Copy pathconfig.yml
228 lines (225 loc) · 7.1 KB
/
config.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
Job:
run_mode: "Training"
#{Training, Predict, Repeat, CV, Hyperparameter, Ensemble, Analysis}
Training:
job_name: "my_train_job"
reprocess: "False"
model: DOS_STO
load_model: "False"
save_model: "True"
model_path: "my_model.pth"
write_output: "True"
parallel: "True"
#seed=0 means random initalization
seed: 0
Predict:
job_name: "my_predict_job"
reprocess: "False"
model_path: "my_model.pth"
write_output: "True"
seed: 0
Repeat:
job_name: "my_repeat_job"
reprocess: "False"
model: DOS_STO
model_path: "my_model.pth"
write_output: "False"
parallel: "True"
seed: 0
###specific options
#number of repeat trials
repeat_trials: 5
CV:
job_name: "my_CV_job"
reprocess: "False"
model: DOS_STO
write_output: "True"
parallel: "True"
seed: 0
###specific options
#number of folds for n-fold CV
cv_folds: 5
Hyperparameter:
job_name: "my_hyperparameter_job"
reprocess: "False"
model: DOS_STO
seed: 0
###specific options
hyper_trials: 200
#number of concurrent trials (can be greater than number of GPUs)
hyper_concurrency: 8
#frequency of checkpointing and update (default: 1)
hyper_iter: 25
#resume a previous hyperparameter optimization run
hyper_resume: "True"
#Verbosity of ray tune output; available: (1, 2, 3)
hyper_verbosity: 1
#Delete processed datasets
hyper_delete_processed: "True"
Ensemble:
job_name: "my_ensemble_job"
reprocess: "False"
save_model: "False"
model_path: "my_model.pth"
write_output: "Partial"
parallel: "True"
seed: 0
###specific options
#List of models to use: (Example: "CGCNN_demo,MPNN_demo,SchNet_demo,MEGNet_demo" or "CGCNN_demo,CGCNN_demo,CGCNN_demo,CGCNN_demo")
ensemble_list: "DOS_STO,DOS_STO,DOS_STO,DOS_STO,DOS_STO"
Processing:
#Whether to use "inmemory" or "large" format for pytorch-geometric dataset. Reccomend inmemory unless the dataset is too large
dataset_type: "inmemory"
#Path to data files
data_path: "/data"
#Path to target file within data_path
target_path: "targets.csv"
#Method of obtaining atom idctionary: available:(provided, default, blank, generated)
dictionary_source: "default"
#Path to atom dictionary file within data_path
dictionary_path: "atom_dict.json"
#Format of data files (limit to those supported by ASE)
data_format: "vasp"
#Print out processing info
verbose: "True"
#graph specific settings
graph_max_radius : 8
graph_max_neighbors : 12
edge_features: "True"
graph_edge_length : 50
#LMBTR specific settings
LMBTR_descriptor: "True"
LMBTR_rcut : 8
LMBTR_grid : 50
LMBTR_sigma : 0.1
#SOAP specific settings
SOAP_descriptor: "True"
SOAP_rcut : 8
SOAP_nmax : 6
SOAP_lmax : 4
SOAP_sigma : 0.4
Training:
#Index of target column in targets.csv
target_index: -1
#Loss functions (from pytorch) examples: l1_loss, mse_loss, binary_cross_entropy
loss: "l1_loss"
features_loss: "True"
#Ratios for train/val/test split out of a total of 1
train_ratio: 0.8
val_ratio: 0.05
test_ratio: 0.15
#Training print out frequency (print per n number of epochs)
verbosity: 5
Models:
DOS_bulk:
model: DOSpredict
dim1: 370
dim2: 370
pre_fc_count: 1
gc_count: 9
batch_norm: "True"
batch_track_stats: "False"
dropout_rate: 0.1
epochs: 800
lr: 0.00034
batch_size: 140
optimizer: "AdamW"
optimizer_args: {"weight_decay":0.1}
scheduler: "ReduceLROnPlateau"
scheduler_args: {"mode":"min", "factor":0.8, "patience":40, "min_lr":0.00001, "threshold":0.0002}
DOS_surf:
model: DOSpredict
dim1: 350
dim2: 270
pre_fc_count: 1
gc_count: 6
batch_norm: "True"
batch_track_stats: "False"
dropout_rate: 0.1
epochs: 800
lr: 0.00057
batch_size: 50
optimizer: "AdamW"
optimizer_args: {"weight_decay":0.01}
scheduler: "ReduceLROnPlateau"
scheduler_args: {"mode":"min", "factor":0.8, "patience":40, "min_lr":0.00001, "threshold":0.0002}
DOS_STO:
model: DOSpredict
dim1: 370
dim2: 370
pre_fc_count: 1
gc_count: 9
batch_norm: "True"
batch_track_stats: "False"
dropout_rate: 0.05
epochs: 2000
lr: 0.00047
batch_size: 180
optimizer: "AdamW"
optimizer_args: {"weight_decay":0.1}
scheduler: "ReduceLROnPlateau"
scheduler_args: {"mode":"min", "factor":0.8, "patience":40, "min_lr":0.00001, "threshold":0.0002}
DOS_STO_SOAP:
model: SOAP_DOS
dim1: 340
fc_count: 4
epochs: 800
lr: 0.001024
batch_size: 70
optimizer: "AdamW"
optimizer_args: {}
scheduler: "ReduceLROnPlateau"
scheduler_args: {"mode":"min", "factor":0.8, "patience":10, "min_lr":0.00001, "threshold":0.0002}
DOS_surf_SOAP:
model: SOAP_DOS
dim1: 300
fc_count: 4
epochs: 800
lr: 0.00078
batch_size: 90
optimizer: "AdamW"
optimizer_args: {}
scheduler: "ReduceLROnPlateau"
scheduler_args: {"mode":"min", "factor":0.8, "patience":10, "min_lr":0.00001, "threshold":0.0002}
DOS_bulk_SOAP:
model: SOAP_DOS
dim1: 390
fc_count: 8
epochs: 800
lr: 0.000157
batch_size: 70
optimizer: "AdamW"
optimizer_args: {}
scheduler: "ReduceLROnPlateau"
scheduler_args: {"mode":"min", "factor":0.8, "patience":10, "min_lr":0.00001, "threshold":0.0002}
DOS_STO_LMBTR:
model: LMBTR_DOS
dim1: 390
fc_count: 9
epochs: 800
lr: 0.000484
batch_size: 50
optimizer: "AdamW"
optimizer_args: {}
scheduler: "ReduceLROnPlateau"
scheduler_args: {"mode":"min", "factor":0.8, "patience":10, "min_lr":0.00001, "threshold":0.0002}
DOS_surf_LMBTR:
model: LMBTR_DOS
dim1: 360
fc_count: 5
epochs: 800
lr: 0.00175
batch_size: 70
optimizer: "AdamW"
optimizer_args: {}
scheduler: "ReduceLROnPlateau"
scheduler_args: {"mode":"min", "factor":0.8, "patience":10, "min_lr":0.00001, "threshold":0.0002}
DOS_dummy:
model: Dummy
epochs: 1
lr: 0.001
batch_size: 64
optimizer: "AdamW"
optimizer_args: {}
scheduler: "ReduceLROnPlateau"
scheduler_args: {"mode":"min", "factor":0.8, "patience":10, "min_lr":0.00001, "threshold":0.0002}