diff options
author | Patrick Simianer <p@simianer.de> | 2015-01-23 16:06:11 +0100 |
---|---|---|
committer | Patrick Simianer <p@simianer.de> | 2015-01-23 16:06:11 +0100 |
commit | 5cc49af3caee21a0b745d949431378acb6b62fdc (patch) | |
tree | 23e81b35f6cf1a1c5599f396b598abcdaf39683d /training/dtrain/examples/parallelized/work/out.2.0 | |
parent | 32dea3f24e56ac7c17343457c48f750f16838742 (diff) |
updated parallelized example
Diffstat (limited to 'training/dtrain/examples/parallelized/work/out.2.0')
-rw-r--r-- | training/dtrain/examples/parallelized/work/out.2.0 | 65 |
1 files changed, 65 insertions, 0 deletions
diff --git a/training/dtrain/examples/parallelized/work/out.2.0 b/training/dtrain/examples/parallelized/work/out.2.0 new file mode 100644 index 00000000..ab38c637 --- /dev/null +++ b/training/dtrain/examples/parallelized/work/out.2.0 @@ -0,0 +1,65 @@ + cdec cfg 'cdec.ini' +Loading the LM will be faster if you build a binary file. +Reading ../standard/nc-wmt11.en.srilm.gz +----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100 +**************************************************************************************************** +Seeding random number sequence to 3274281797 + +dtrain +Parameters: + k 100 + N 4 + T 1 + batch 0 + scorer 'stupid_bleu' + sample from 'kbest' + filter 'uniq' + learning rate 0.0001 + gamma 0 + loss margin 1 + faster perceptron 0 + pairs 'XYX' + hi lo 0.1 + pair threshold 0 + select weights 'last' + l1 reg 0 'none' + pclr no + max pairs 4294967295 + repeat 1 + cdec cfg 'cdec.ini' + input '' + output 'work/weights.2.0' +(a dot represents 10 inputs) +Iteration #1 of 1. + 3 +WEIGHTS + Glue = +0.1295 + WordPenalty = +0.12781 + LanguageModel = +1.1825 + LanguageModel_OOV = -0.1667 + PhraseModel_0 = -0.65167 + PhraseModel_1 = -0.044563 + PhraseModel_2 = +0.49706 + PhraseModel_3 = -0.40367 + PhraseModel_4 = -1.3438 + PhraseModel_5 = +0.0435 + PhraseModel_6 = -0.3743 + PassThrough = -0.0307 + --- + 1best avg score: 0.08637 (+0.08637) + 1best avg model score: -42.175 (-42.175) + avg # pairs: 1136.3 + avg # rank err: 720.67 + avg # margin viol: 399.67 + k-best loss imp: 100% + non0 feature count: 12 + avg list sz: 100 + avg f count: 11.487 +(time 0.22 min, 4.3 s/S) + +Writing weights file to 'work/weights.2.0' ... +done + +--- +Best iteration: 1 [SCORE 'stupid_bleu'=0.08637]. +This took 0.21667 min. |