Open sbmaruf opened 4 years ago
In refinement iterations, the best model is still selected by the validation metric, but I think in Procrustes update the result will never be decreased. So we should always take the latest updated model after Procrustes update. Related reference: https://github.com/facebookresearch/MUSE/blob/master/unsupervised.py#L179 https://github.com/facebookresearch/MUSE/blob/master/src/trainer.py#L215
Procrustes
@glample @aconneau [log] https://paste.ubuntu.com/p/SJ23FhpWMT/ See in the log. The best model saved whose csls_knn_10 - Precision at k = 1 is 70.133 whereas the best translation model have a score of 78.733
csls_knn_10 - Precision at k = 1
70.133
78.733
In refinement iterations, the best model is still selected by the validation metric, but I think in Procrustes update the result will never be decreased. So we should always take the latest updated model after
Procrustes
update. Related reference: https://github.com/facebookresearch/MUSE/blob/master/unsupervised.py#L179 https://github.com/facebookresearch/MUSE/blob/master/src/trainer.py#L215@glample @aconneau [log] https://paste.ubuntu.com/p/SJ23FhpWMT/ See in the log. The best model saved whose
csls_knn_10 - Precision at k = 1
is70.133
whereas the best translation model have a score of78.733