============ Initialized logger ============
add_traspose_rels: True
aggregate: pna
aug: False
batch_size: 64
constrained_neg_prob: 0.0
dataset: nell_v4
dropout: 0.2
early_stop: 50
emb_dim: 32
enclosing_sub_graph: False
exp_dir: GNN/experiments/nell_v4_ln_False_32_0.2_4_gru_lstm
experiment_name: nell_v4_ln_False_32_0.2_4_gru_lstm
gpu: 5
hop: 3
l2: 0.0001
load_model: False
loss: bce
lr: 0.0005
main_dir: GNN
margin: 10
max_links: 1000000
message: gru
num_epochs: 10
num_gcn_layers: 4
num_neg_samples_per_link: 1
num_workers: 8
optimizer: Adam
train_file: train
un_hop: 1
update: lstm
using_jk: False
valid_file: valid
============================================
No existing model found. Initializing new model..
Device: cuda
Input dim : 32, # Relations : 152
Total number of parameters: 145025
Starting training ...
====================================================================================================
Run Time Error! Reduce batch size. Current batch size: 32
No existing model found. Initializing new model..
Device: cuda
Input dim : 32, # Relations : 152
Total number of parameters: 145025
Starting training ...
====================================================================================================
Epoch 1 Training Performance:{'auc': 0.8686786771324058, 'auc_pr': 0.8629141999426512, 'acc': 0.7663662867744501} in 574.1741442680359 s 
Epoch 1 Validation Performance:{'auc': 0.9135964637934989, 'auc_pr': 0.9045061856410443, 'acc': 0.6484018264840182} in 36.60860013961792 s 
Epoch 1 Better models found w.r.t AUC-PR. Saved it!
Epoch 1 with loss: 0.45177897690969, best validation AUC-PR: 0.9045061856410443, weight_norm: 13.32343864440918 in 610.8229598999023 s 
====================================================================================================
Epoch 2 Training Performance:{'auc': 0.9311313088540651, 'auc_pr': 0.9290550039581271, 'acc': 0.8488603233501193} in 571.5330443382263 s 
Epoch 2 Validation Performance:{'auc': 0.9259430839640541, 'auc_pr': 0.9199493113881824, 'acc': 0.7271689497716894} in 36.91341972351074 s 
Epoch 2 Better models found w.r.t AUC-PR. Saved it!
Epoch 2 with loss: 0.334766965801433, best validation AUC-PR: 0.9199493113881824, weight_norm: 12.460060119628906 in 608.4896535873413 s 
====================================================================================================
Epoch 3 Training Performance:{'auc': 0.9423060779827711, 'auc_pr': 0.9393574221613203, 'acc': 0.865491651205937} in 570.633798122406 s 
Epoch 3 Validation Performance:{'auc': 0.9376511644878129, 'auc_pr': 0.9285206869030713, 'acc': 0.7180365296803652} in 35.69383645057678 s 
Epoch 3 Better models found w.r.t AUC-PR. Saved it!
Epoch 3 with loss: 0.3066738830658339, best validation AUC-PR: 0.9285206869030713, weight_norm: 11.693594932556152 in 606.3639168739319 s 
====================================================================================================
Epoch 4 Training Performance:{'auc': 0.9481785327401602, 'auc_pr': 0.9465077227450196, 'acc': 0.877020938245428} in 566.9788229465485 s 
Epoch 4 Validation Performance:{'auc': 0.931949917641417, 'auc_pr': 0.9209165995389751, 'acc': 0.6872146118721462} in 36.79007267951965 s 
Epoch 4 with loss: 0.2904753904726546, best validation AUC-PR: 0.9285206869030713, weight_norm: 10.993420600891113 in 603.7963418960571 s 
====================================================================================================
Epoch 5 Training Performance:{'auc': 0.9540475980906645, 'auc_pr': 0.9519207469750155, 'acc': 0.8863636363636364} in 568.3418548107147 s 
Epoch 5 Validation Performance:{'auc': 0.9432839963720523, 'auc_pr': 0.9359835461722054, 'acc': 0.7756849315068494} in 36.0834686756134 s 
Epoch 5 Better models found w.r.t AUC-PR. Saved it!
Epoch 5 with loss: 0.27316865296560827, best validation AUC-PR: 0.9359835461722054, weight_norm: 10.349580764770508 in 604.4659779071808 s 
====================================================================================================
Epoch 6 Training Performance:{'auc': 0.9567373997833167, 'auc_pr': 0.9538925602389463, 'acc': 0.8894116087993639} in 573.7922079563141 s 
Epoch 6 Validation Performance:{'auc': 0.9419958403703008, 'auc_pr': 0.934211270437483, 'acc': 0.8561643835616438} in 36.13911700248718 s 
Epoch 6 with loss: 0.2652864168256016, best validation AUC-PR: 0.9359835461722054, weight_norm: 9.756217002868652 in 609.9687776565552 s 
====================================================================================================
Epoch 7 Training Performance:{'auc': 0.9591994789937204, 'auc_pr': 0.9573183351798741, 'acc': 0.8940498277232971} in 549.0647683143616 s 
Epoch 7 Validation Performance:{'auc': 0.9386415525114156, 'auc_pr': 0.9278183518900076, 'acc': 0.8378995433789954} in 34.65044140815735 s 
Epoch 7 with loss: 0.25759082022359814, best validation AUC-PR: 0.9359835461722054, weight_norm: 9.20904541015625 in 583.7438235282898 s 
====================================================================================================
Epoch 8 Training Performance:{'auc': 0.9602648942656083, 'auc_pr': 0.9576270843008744, 'acc': 0.8963689371852637} in 545.8382844924927 s 
Epoch 8 Validation Performance:{'auc': 0.9387829434332061, 'auc_pr': 0.9314190065160536, 'acc': 0.851027397260274} in 34.450910806655884 s 
Epoch 8 with loss: 0.25356996182541724, best validation AUC-PR: 0.9359835461722054, weight_norm: 8.70553970336914 in 580.3189566135406 s 
====================================================================================================
Epoch 9 Training Performance:{'auc': 0.9616268650782138, 'auc_pr': 0.9594481483666455, 'acc': 0.8970978001590246} in 546.9438452720642 s 
Epoch 9 Validation Performance:{'auc': 0.9432520693897125, 'auc_pr': 0.9338523982237783, 'acc': 0.8344748858447488} in 34.802486419677734 s 
Epoch 9 with loss: 0.24895519933710664, best validation AUC-PR: 0.9359835461722054, weight_norm: 8.242551803588867 in 581.7778980731964 s 
====================================================================================================
Epoch 10 Training Performance:{'auc': 0.9643851134720741, 'auc_pr': 0.9619922341118221, 'acc': 0.9032600053008216} in 546.0424470901489 s 
Epoch 10 Validation Performance:{'auc': 0.947321782281437, 'auc_pr': 0.9391629299961397, 'acc': 0.8481735159817352} in 35.362237215042114 s 
Epoch 10 Better models found w.r.t AUC-PR. Saved it!
Epoch 10 with loss: 0.2388787780083337, best validation AUC-PR: 0.9391629299961397, weight_norm: 7.816385269165039 in 581.4481036663055 s 
====================================================================================================
============ Initialized logger ============
add_traspose_rels: True
aggregate: pna
aug: False
batch_size: 64
constrained_neg_prob: 0.0
dataset: nell_v4
dropout: 0.2
early_stop: 50
emb_dim: 32
enclosing_sub_graph: False
exp_dir: GNN/experiments/nell_v4_ln_False_32_0.2_4_gru_lstm
experiment_name: nell_v4_ln_False_32_0.2_4_gru_lstm
gpu: 5
hop: 3
l2: 0.0001
load_model: False
loss: bce
lr: 0.0005
main_dir: GNN
margin: 10
max_links: 1000000
message: gru
num_epochs: 10
num_gcn_layers: 4
num_neg_samples_per_link: 1
num_workers: 8
optimizer: Adam
train_file: train
un_hop: 1
update: lstm
using_jk: False
valid_file: valid
============================================
No existing model found. Initializing new model..
Device: cuda
Input dim : 32, # Relations : 152
Total number of parameters: 145025
Starting training ...
====================================================================================================
Run Time Error! Reduce batch size. Current batch size: 32
No existing model found. Initializing new model..
Device: cuda
Input dim : 32, # Relations : 152
Total number of parameters: 145025
Starting training ...
====================================================================================================
