Loss parameters for downstream tasks
wenjiajia123 opened this issue Β· comments
wenjiajia123 commented
Hi, I got bad results when training on moment retraival without loading pretrained model, I wonder that are the hyperparameters in 'qvhl_pretrain.sh' correct? π
b_loss_coef=10 g_loss_coef=0 eos_coef=0.1 f_loss_coef=10 s_loss_intra_coef=0 s_loss_inter_coef=0
Kevin commented
Hi, this setting is not the optimal result. Please refer our paper or checkpoint config for parameters. :)
wenjiajia123 commented
Thamk u! I have found that. π