Closed felixgao closed 3 weeks ago
I did some debugging it seems that all of my examples are returning False
in the metrics. I feel this should somehow still works because the task is trying to figure out what is the correct prompt to use to do a task.
You could increase the num_candidates
value so it tries more then 10 times.
class MIPRO(Teleprompter):
def __init__(
self,
metric,
prompt_model=None,
task_model=None,
teacher_settings={},
num_candidates=10,
init_temperature=1.0,
verbose=False,
track_stats=True,
view_data_batch_size=10,
):
However the best option might be to give it at least one sample that also has a label.
@felixgao Did you end up finding a solution? Also blocked on this when trying to fit a classifier using DSPY
Probably fixed now in DSPy 2.5 with the MIPROv2 updates? Closing but feel free to re-open.
Trying to run MIPRO for my signature and it failed with the exception.
relevant code