search

yuhaozhang / tacred-relation

PyTorch implementation of the position-aware attention model for relation extraction
Other
355 stars 97 forks source link

the result is bad #2

Closed SeekPoint closed 5 years ago

SeekPoint commented 5 years ago

Evaluating on dev set... Precision (micro): 100.000% Recall (micro): 0.000% F1 (micro): 0.000% epoch 28: train_loss = 0.757685, dev_loss = 8.513657, dev_f1 = 0.0000 model saved to ./saved_models/00/checkpoint_epoch_28.pt

Evaluating on dev set... Precision (micro): 100.000% Recall (micro): 0.000% F1 (micro): 0.000% epoch 29: train_loss = 0.749475, dev_loss = 8.528827, dev_f1 = 0.0000 model saved to ./saved_models/00/checkpoint_epoch_29.pt

Evaluating on dev set... Precision (micro): 100.000% Recall (micro): 0.000% F1 (micro): 0.000% epoch 30: train_loss = 0.732781, dev_loss = 8.541955, dev_f1 = 0.0000 model saved to ./saved_models/00/checkpoint_epoch_30.pt

Training ended with 30 epochs. $

yuhaozhang commented 5 years ago

Hi @loveJasmine, which data did you run the training on? Note that the data included in this repo is only a sample data with a few examples for debugging purpose, and you should not expect any meaningful results on this sample data.

yuhaozhang commented 5 years ago

Hi @loveJasmine, I am closing this issue if there is no further comment?