============ Initialized logger ============
add_traspose_rels: True
aggregate: pna
aug: False
batch_size: 4
constrained_neg_prob: 0.0
dataset: fb237_v4
dropout: 0.1
early_stop: 50
emb_dim: 32
enclosing_sub_graph: False
exp_dir: GNN/experiments/fb237_v4_mul
experiment_name: fb237_v4_mul
gpu: 5
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: 5
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 : 32, # Relations : 438
Total number of parameters: 175361
Starting training ...
====================================================================================================
Epoch 1 Training Performance:{'auc': 0.8700657769715159, 'auc_pr': 0.8523873267381179, 'acc': 0.7756865051648715} in 16032.099130153656 s 
Epoch 1 Validation Performance:{'auc': 0.9161198333485225, 'auc_pr': 0.8970122480659746, 'acc': 0.8136933174224343} in 1120.6331956386566 s 
Epoch 1 Better models found w.r.t AUC-PR. Saved it!
Epoch 1 with loss: 0.4496890924284321, best validation AUC-PR: 0.8970122480659746, weight_norm: 7.063918590545654 in 17152.774329423904 s 
====================================================================================================
Epoch 2 Training Performance:{'auc': 0.9409669127529419, 'auc_pr': 0.9229706658865814, 'acc': 0.8765577326030217} in 15841.993093967438 s 
Epoch 2 Validation Performance:{'auc': 0.9460178727052136, 'auc_pr': 0.933134307609229, 'acc': 0.8872315035799523} in 1120.7286312580109 s 
Epoch 2 Better models found w.r.t AUC-PR. Saved it!
Epoch 2 with loss: 0.2959526374083247, best validation AUC-PR: 0.933134307609229, weight_norm: 5.9332380294799805 in 16962.7617559433 s 
====================================================================================================
Epoch 3 Training Performance:{'auc': 0.9540924659692929, 'auc_pr': 0.9390608693135913, 'acc': 0.9012057493658787} in 15990.629873991013 s 
Epoch 3 Validation Performance:{'auc': 0.9520116939411373, 'auc_pr': 0.9372772927183568, 'acc': 0.8990155131264916} in 1141.1713478565216 s 
Epoch 3 Better models found w.r.t AUC-PR. Saved it!
Epoch 3 with loss: 0.2511335145431498, best validation AUC-PR: 0.9372772927183568, weight_norm: 5.310062885284424 in 17131.84466099739 s 
====================================================================================================
Epoch 4 Training Performance:{'auc': 0.9637678496877977, 'auc_pr': 0.9525222373915921, 'acc': 0.915468882108591} in 17630.86172938347 s 
Epoch 4 Validation Performance:{'auc': 0.959454397260781, 'auc_pr': 0.9524082732991147, 'acc': 0.9009546539379475} in 1361.20081615448 s 
Epoch 4 Better models found w.r.t AUC-PR. Saved it!
Epoch 4 with loss: 0.21893587443290707, best validation AUC-PR: 0.9524082732991147, weight_norm: 4.874249458312988 in 18992.120775699615 s 
====================================================================================================
Epoch 5 Training Performance:{'auc': 0.9696620721005549, 'auc_pr': 0.9614882898353375, 'acc': 0.9255413005918465} in 17824.808931350708 s 
Epoch 5 Validation Performance:{'auc': 0.9638706863283987, 'auc_pr': 0.9562574877868469, 'acc': 0.9134844868735084} in 1490.508810043335 s 
Epoch 5 Better models found w.r.t AUC-PR. Saved it!
Epoch 5 with loss: 0.19815475215025902, best validation AUC-PR: 0.9562574877868469, weight_norm: 4.538174152374268 in 19315.403400421143 s 
====================================================================================================
