search

plkmo / BERT-Relation-Extraction

PyTorch implementation for "Matching the Blanks: Distributional Similarity for Relation Learning" paper
Apache License 2.0
565 stars 132 forks source link

zero f1 #7

Closed xiongjun19 closed 4 years ago

xiongjun19 commented 4 years ago

Hi, plkmo ! I have managed to run the main_task script using follow command: python main_task.py --train_data ./data/finetune/SemEval2010_task8_all_data/SemEval2010_task8_training/TRAIN_FILE.TXT --test_data ./data/finetune/SemEval2010_task8_all_data/SemEval2010_task8_testing_keys/TEST_FILE_FULL.TXT --use_pretrained_blanks 0 --model_no 0 but always got zero f1 in about 20 ecpos, you can see the detail in following:

Epoch finished, took 29.90 seconds. Losses at Epoch 20: 2.6830234 Train accuracy at Epoch 20: 0.1756250 Test f1 at Epoch 20: 0.0000000

plkmo commented 4 years ago

What is the other arguments used for main_task.py? Can you try running with default arguments?