***** Test results *****
Thu Sep 22 08:47:08 2022
Task: ner
Model path: bert-base-uncased
Data path: ./data/ud/
Tokenizer: bert-base-uncased
Batch size: 32
Epoch: 8
Learning rate: 2e-05
LR Decay End Factor: 0.3LR Decay End Epoch: 5Sequence length: 96
Training: True
Num Threads: 24
Num Sentences: 0
Max Grad Norm: 0.0
Use GNN: False
Syntax graph style: dep
Use label weights: False
Clip value: 50
              precision    recall  f1-score   support

    CARDINAL     0.7269    0.6307    0.6754       612
        DATE     0.6856    0.7053    0.6953      1045
       EVENT     0.4286    0.4500    0.4390        80
         FAC     0.3454    0.4437    0.3884       151
         GPE     0.8709    0.8574    0.8641      1936
    LANGUAGE     0.5758    0.2468    0.3455        77
         LAW     0.4314    0.3860    0.4074        57
         LOC     0.5829    0.4700    0.5204       217
       MONEY     0.5085    0.4918    0.5000        61
        NORP     0.7023    0.7156    0.7089       422
     ORDINAL     0.8258    0.8596    0.8424       171
         ORG     0.5300    0.5776    0.5528       857
     PERCENT     0.4255    0.5556    0.4819        36
      PERSON     0.7398    0.7841    0.7613      1371
     PRODUCT     0.2975    0.3673    0.3288        98
    QUANTITY     0.3284    0.4151    0.3667        53
        SEP]     0.0000    0.0000    0.0000         0
        TIME     0.5586    0.6682    0.6085       214
 WORK_OF_ART     0.3010    0.2385    0.2661       130

   micro avg     0.6607    0.7024    0.6809      7588
   macro avg     0.5192    0.5191    0.5133      7588
weighted avg     0.6968    0.7024    0.6977      7588

 Special token predictions: 0