Soroush javdan

Thanks for your reply This the result that i got after finetuning . epoch loss Peplexity Entl_b Bleu_b 0 3.8042 44.8887 -0.1415 0.4747 1 3.7168 41.1305 -0.1400 0.5077 3 3.6794...

`python MAML.py --cuda --model trs --batch_size 16 --use_sgd --lr 0.01 --meta_lr 0.0003 --meta_batch_size 16 --meta_optimizer adam --pretrain_emb --weight_sharing --emb_dim 300 --hidden_dim 300 --fix_dialnum_train --pointer_gen --save_path save/paml/ ` This was the...

I checked other baselines and the results was quite strange! for this command `python main.py --cuda --model trs --pretrain_emb --weight_sharing --label_smoothing --noam --emb_dim 300 --hidden_dim 300 --pointer_gen --save_path save/no_persona/ `...

Hi kuassivi , thank your for your great library . I changed what you asked for .

@susheel17 Thanks for your response , i added grade dependency .

Same here !! I have so many labeled data on their website, but unfortunately, I cannot have access to them !!

Does anyone know how we could access to our data !?