YooSungHyun
YooSungHyun
PLZ, making easily...! nowadays, i`m always using huggingface 😥
@patrickvonplaten plz help!
hi, bro! @sanchit-gandhi ! Lol! you make custom trainer???? 😂 Awesome!! But, I have another very easy way solution....kkk!!! eval and predict loop used SequentialSampler right? so! i only sorted...
THX @sanchit-gandhi i'm already use that `do_stable_layer_norm ` that problem raised too. so, i have to sorted eval, test set...😂 and also, wav2vec2-conformer is not supported that param! do you...
@sanchit-gandhi THX for reply i checked wav2vec2-conformer, that is already do_stable_layer_norm like...! in case, i just pretrained base model and Wav2Vec2ForCTC finetuning. (do_stable_layer_norm is True, group_by_length True) and finally when...
@sanchit-gandhi Hi! that is my company`s private wandb. so i can not share to you but i have one hypothesis, and now testing. confomer has convolution modul, so, conformer output...
@sanchit-gandhi hello! i used 4 kinds of dataset. and 2 datasets have this problem. so, i will filter 'at least 25ms' and 'cnn output lengths / N > labels' i...
i filtered 25ms and feed len(labels) > 0, but eval loss reached NaN on 3~4 epoch...😥 big stress....
@sanchit-gandhi i`m very busy now, so i will reply this comment as soon as possible bro!
and i have this problem on save and load sharded too... https://github.com/pytorch/pytorch/issues/103627 how can i solve it?