You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hey Marco, thank you so much for blowing us all away! Such impressive work.
I've tried fine-tuning and got some interesting results but I feel like I'm going to get even more mind blowing results if I can scale it.
I have some questions about scaling musika:
I want to train a larger version of musika on some more powerful hardware on the cloud (e.g. A100, or RTXA6000). What do you think is the largest number of parameters I can scale to that can still work in terms of inference on a free Colab? For example, can I 5x or 10x the number of parameters on the existing model before pretraining?
Also out of curiosity, how big do you think a model would have to be to be indistinguishable from real music?
Do you think it would be worth it to train a scaled version of the model without also scaling or re-training the autoencoders (I know you mentioned in another issue that you plan to release this eventually. Would you recommend I wait til that happens?)
In the readme you mentioned "You can also increase the number of parameters (capacity) of the model with the --base_channels argument (--base_channels 128 is the default)." How many more parameters would --base_channels 192 have? / How can I calculate final number of parameters and whether that will fit in memory for a free Colab?
Do you support multi-GPU training?
I plan to train from scratch, and then fine-tune. For the fine-tuning, how many iterations do you recommend? I've often found when fine-tuning I quickly reach a plateau after 20-30 epochs and am not sure if I should continue training the next day (on Colab) or wait til I've done 250 epochs.
The text was updated successfully, but these errors were encountered:
Hey Marco, thank you so much for blowing us all away! Such impressive work.
I've tried fine-tuning and got some interesting results but I feel like I'm going to get even more mind blowing results if I can scale it.
I have some questions about scaling musika:
--base_channels 192
have? / How can I calculate final number of parameters and whether that will fit in memory for a free Colab?I plan to train from scratch, and then fine-tune. For the fine-tuning, how many iterations do you recommend? I've often found when fine-tuning I quickly reach a plateau after 20-30 epochs and am not sure if I should continue training the next day (on Colab) or wait til I've done 250 epochs.
The text was updated successfully, but these errors were encountered: