Fairseq: BART : Is there a tutorial for pre-training BART on your own dataset ?
Thanks!
shamanez
All 7 comments
@myleott ? thanks
orena1
on 22 Jul 2020
Same question here. Appreciate if there is a guide.
jasonwu0731
on 4 Aug 2020
@shamanez @jasonwu0731 I can't confirm everything that I am trying is 100% correct but I think I've pieced together a procedure for (possibly) retraining BART on a new dataset. I'm happy to be proved wrong/improve this. I'd also appreciate FAIR endorsed guidance. The data processing mostly comes from here. I made Gists for preprocessing and training. Let me know if this is helpful or if you have improvements!
tomsherborne
on 6 Aug 2020
Same problem here. It would be great if there is one.
PrettyPrettyMeng
on 7 Aug 2020
@tomsherborne Amazing! Actually I also have taken initial steps. But still, I am not sure about in what percentage that we need to use different pretext denoising tasks.
Let's do this!
shamanez
on 9 Aug 2020
@ngoyal2707 wondering if you can provide us with the details on training BART or comment on @tomsherborne gist if they are good. As it would be good to have the readme in examples folders describing the process.
gurvindersingh
on 22 Aug 2020
yeah, it would be vert useful.
shamanez
on 24 Aug 2020
Related issues
jordiae
路
3Comments
ashim95
路
3Comments
yilegu
路
3Comments
jmatak
路
3Comments
mjpost
路
3Comments
Most helpful comment
@shamanez @jasonwu0731 I can't confirm everything that I am trying is 100% correct but I think I've pieced together a procedure for (possibly) retraining BART on a new dataset. I'm happy to be proved wrong/improve this. I'd also appreciate FAIR endorsed guidance. The data processing mostly comes from here. I made Gists for preprocessing and training. Let me know if this is helpful or if you have improvements!