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
Is mT0 suitable / recommended for continued training on mixture of denoising (span corruption, extreme span corruption, prefix LM) tasks similar to UL2? Like below
# span_corruption
{
"text_input": "The <extra_id_0> walks in <extra_id_1> park",
"text_output": "<extra_id_0> cute dog <extra_id_1> the <extra_id_2>"
}
# extreme_span_corruption
{
"text_input": "The <extra_id_0> park",
"text_output": "<extra_id_0> cute dog walks in the <extra_id_1>"
}
# prefix LM
{
"text_input": "The cute <extra_id_0>",
"text_output": "<extra_id_0> dog walks in the park"
}
My domain text is quite different from internet text so I assume span corruption task would help mT0 learn special syntax / semantics of my domain.
The text was updated successfully, but these errors were encountered:
I think that BLOOM might be a good candidate for that. After UL2 training you might want to try instruction tuning like BLOOMZ, FLAN or T0. But a good workaround could be (i) include instruction tuning samples (xp3mt, p3 etc) in the "prefix LM" objective function, (ii) include other objective function like span_corruption and continue UL2 training.
Is mT0 suitable / recommended for continued training on mixture of denoising (span corruption, extreme span corruption, prefix LM) tasks similar to UL2? Like below
My domain text is quite different from internet text so I assume span corruption task would help mT0 learn special syntax / semantics of my domain.
The text was updated successfully, but these errors were encountered: