Closed weka511 closed 1 year ago
This is on even the first call after resume, before weights have been updated!
Loaded ./data\dummy.npz eta=0.04929739848256657, loss 2.3568230232668697, k=5, width=2 C:\Users\Weka\nlp\word2vec2.py:177: UserWarning: Calculated tau 70382 exceeds N 1000 warn(f'Calculated tau {tau} exceeds N {N}') There are 216626 groups. Initial Loss=4.86660994e+00
Trace what is happening from baseline (k-2)
./word2vec2.py train --vocabulary gatsby.npz --examples gatsby.csv --save gatsby --plot gatsby --show --freq 100 --dimension 128 --N 50000 --eta 0.01
Uniform doesn't appear to be very successful.
This is an artifact:
I resumed: ./word2vec2.py train --resume --load train-k2 --save train-k2-a --plot train-k2-a --eta 0.001 --N 100000
loss appears to have doubled from around 0.5 to around 1.0.