Early stop

[tareksakakini]

Hello Mr. Ling,

Thank you for this work.

I'm having the following issue and was wondering if you might know the reason. I'm running the following command:

./word2vec -train Corpus.txt -output vectors.bin -type 2 -size 300 -window 5 -negative 10 -nce 0 -hs 0 -sample 1e-4 -threads 8 -binary 1 -iter 5 -cap 0

And it's stopping here: Alpha: 0.047280 Progress: 5.44% Words/thread/sec: 19.99k.

I had no such issues with lower dimensions (100,200) or when training with -type 3

Thank you

[wlin12]

Hi,

It seems that the gradients got too high at some point, try setting -cap 1, this will cap the gradients.

Wang Ling

On Feb 4, 2016, at 6:37 PM, Tarek Sakakini notifications@github.com wrote:

Hello Mr. Ling,

Thank you for this work.

I'm having the following issue and was wondering if you might know the reason. I'm running the following command:

./word2vec -train Corpus.txt -output vectors.bin -type 2 -size 300 -window 5 -negative 10 -nce 0 -hs 0 -sample 1e-4 -threads 8 -binary 1 -iter 5 -cap 0

And it's stopping here: Alpha: 0.047280 Progress: 5.44% Words/thread/sec: 19.99k.

I had no such issues with lower dimensions (100,200) or when training with -type 3

Thank you

—
Reply to this email directly or view it on GitHub #2.

[tareksakakini]

Thank you. For now decreasing the initial step size alpha seems to be working. If it didn't work I'll try using a cap of 1.