============ Initialized logger ============
add_traspose_rels: True
aggregate: pna
aug: False
batch_size: 16
constrained_neg_prob: 0.0
dataset: nell_v3
dropout: 0.1
early_stop: 50
emb_dim: 16
enclosing_sub_graph: True
exp_dir: GNN/experiments/nell_v3_mul
experiment_name: nell_v3_mul
gpu: 1
hop: 3
l2: 0.0001
load_model: False
loss: bce
lr: 0.0005
main_dir: GNN
margin: 10
max_links: 1000000
message: mul
num_epochs: 5
num_gcn_layers: 6
num_neg_samples_per_link: 1
num_workers: 8
optimizer: Adam
residual: False
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 : 16, # Relations : 284
Total number of parameters: 59713
Starting training ...
====================================================================================================
Epoch 1 Training Performance:{'auc': 0.9167109883405882, 'auc_pr': 0.9035948065614264, 'acc': 0.8319709632160068} in 4428.768656015396 s 
Epoch 1 Validation Performance:{'auc': 0.9030697556856706, 'auc_pr': 0.8853484005483674, 'acc': 0.7050243111831442} in 301.1896641254425 s 
Epoch 1 Better models found w.r.t AUC-PR. Saved it!
Epoch 1 with loss: 0.36401489707027995, best validation AUC-PR: 0.8853484005483674, weight_norm: 6.759075164794922 in 4730.009313583374 s 
====================================================================================================
Epoch 2 Training Performance:{'auc': 0.9500038047419033, 'auc_pr': 0.9440941431837335, 'acc': 0.8792472396754712} in 4370.720191955566 s 
Epoch 2 Validation Performance:{'auc': 0.9143347106605829, 'auc_pr': 0.8982370877902763, 'acc': 0.7104267963263101} in 303.20844984054565 s 
Epoch 2 Better models found w.r.t AUC-PR. Saved it!
Epoch 2 with loss: 0.28300491736429495, best validation AUC-PR: 0.8982370877902763, weight_norm: 5.92972469329834 in 4673.974879980087 s 
====================================================================================================
Epoch 3 Training Performance:{'auc': 0.9599800095596908, 'auc_pr': 0.9543669879459881, 'acc': 0.894131641554322} in 4400.674155950546 s 
Epoch 3 Validation Performance:{'auc': 0.9193287258978676, 'auc_pr': 0.8996285681881282, 'acc': 0.7803889789303079} in 299.1571831703186 s 
Epoch 3 Better models found w.r.t AUC-PR. Saved it!
Epoch 3 with loss: 0.25193207337725454, best validation AUC-PR: 0.8996285681881282, weight_norm: 5.3423590660095215 in 4699.877997159958 s 
====================================================================================================
Epoch 4 Training Performance:{'auc': 0.9665677613629857, 'auc_pr': 0.9621286583120274, 'acc': 0.9054779479045935} in 4393.7643411159515 s 
Epoch 4 Validation Performance:{'auc': 0.9245045751840012, 'auc_pr': 0.9149625906645203, 'acc': 0.8392760669908158} in 298.1342396736145 s 
Epoch 4 Better models found w.r.t AUC-PR. Saved it!
Epoch 4 with loss: 0.22972476949052112, best validation AUC-PR: 0.9149625906645203, weight_norm: 4.9148359298706055 in 4691.954957962036 s 
====================================================================================================
Epoch 5 Training Performance:{'auc': 0.970093162014551, 'auc_pr': 0.9662616346113188, 'acc': 0.9112731043738181} in 4381.540847539902 s 
Epoch 5 Validation Performance:{'auc': 0.9223387652971906, 'auc_pr': 0.9088963956980292, 'acc': 0.7695840086439762} in 300.20776438713074 s 
Epoch 5 with loss: 0.21647974141850704, best validation AUC-PR: 0.9149625906645203, weight_norm: 4.604952812194824 in 4681.781101703644 s 
====================================================================================================
