Hi,
In Model and Training Details section of your paper, you said that "We use early stopping and select the best model based on the F_0.5 score on the development set.". But to my knowledge, it seems that FairSeq can not do validation based on F_0.5, so my question(clarification) is
In FairSeq, the Early-Stop is only triggered when current learning rate < min-lr ?
after the FairSeq training process finished, the model paramters will be seved as checkpoint_1.pt , checkpoint_2.pt, ......, checkpoint_best.pt, checkpoint_last.pt, then you use the _checkpointbest.pt file directly, or manually select a checkpoint among all *.pt files as "best model" based on the F_0.5 score on development set ?
Yes, after Fairseq training finishes (using the early stopping criteria based on learning rate), the checkpoint that has the highest F0.5 on the development data is selected as the final model.
Hi, In Model and Training Details section of your paper, you said that "We use early stopping and select the best model based on the F_0.5 score on the development set.". But to my knowledge, it seems that FairSeq can not do validation based on F_0.5, so my question(clarification) is
Many thanks