ctrl

ctrl copied to clipboard

Fine-tuning on Colab

4

I am trying to fine-tune the model in Google Colab in a [Python 3 / GPU] runtime type. After launching the training, it suddenly stops, indicating "^C" though I haven't...

manueltonneau

Out of memory when fine-tuning

9

Thank you for this important contribution! I am trying to fine-tune your full model on a V100 with 16GB memory. Even when setting batch size to 1 in the patch,...

orenmelamud

Thank you very much.

guotong1988

Hi, I'm wondering if there is a way to change the personal pronouns of the output - I'm trying to see if I can avoid the first person POV, but...

qdx45

I'm hoping to add some domain-specific knowledge to the Q&A control code, using text that is not in a Q&A format. Seems like that would be best accomplished by not...

umhau

Hi, I found several interesting machine translation examples in the paper. I wonder if the translation result is also yielded by greedy sampling with a penalty of 1.2? Will the...

MichaelZhouwang

Hi! First off, thanks a lot for making and sharing this model. Second, is there a license that can be applied to the pre-trained model itself? Thanks, Josh

MobiusLooper

Hello, for pre-training the model, what kind of training curriculum did you use? Did the model see the training records control code by control code sequentially or did you feed...

v1nc3nt27

Lower memory

1

finance is helpful

wieldmore

Hi, thanks for the excellent work and the repo. I am trying to reproduce source attribution results and they are way off compared to the examples shown (latest code as...

sipity19