Hi Oscar,
Two possible suggestions:
Could it be you picked an overly aggressive learning rate? (I’m a beginner so this suggestion could be way off)
To find the learning rate automatically…
lrn_rate = learner.lr_find()
print(lrn_rate.valley) # plug this value into your learner
Second suggestion: perhaps your callback method for unfreezing is where the problem is (can’t see where it is defined). Would it be better to use fastai fine_tune to rule that out?
- In the forums: "fine_tune" vs. "fit_one_cycle" - #6 by muellerzr
- In the example: Computer vision intro – fastai
Paul