diff options
author | Patrick Simianer <p@simianer.de> | 2015-02-26 23:09:15 +0100 |
---|---|---|
committer | Patrick Simianer <p@simianer.de> | 2015-02-26 23:09:15 +0100 |
commit | 0982b8bbb67a42d4b0e084a217e0acd7ddcff243 (patch) | |
tree | ed0c3c8259e9218a3330dec4638da0ec4188e131 /training/dtrain/examples/parallelized/work/out.2.0 | |
parent | 92c4e1558544a367a8266301385892817a4e3426 (diff) |
more fixes
Diffstat (limited to 'training/dtrain/examples/parallelized/work/out.2.0')
-rw-r--r-- | training/dtrain/examples/parallelized/work/out.2.0 | 49 |
1 files changed, 25 insertions, 24 deletions
diff --git a/training/dtrain/examples/parallelized/work/out.2.0 b/training/dtrain/examples/parallelized/work/out.2.0 index 07c85963..2d27fdc6 100644 --- a/training/dtrain/examples/parallelized/work/out.2.0 +++ b/training/dtrain/examples/parallelized/work/out.2.0 @@ -2,42 +2,43 @@ 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 **************************************************************************************************** + Example feature: Shape_S00000_T00000 dtrain Parameters: k 100 N 4 T 1 learning rate 0.0001 - error margin 1 + margin 1 l1 reg 0 decoder conf 'cdec.ini' - input 'work/shard.2.0.in' + input 'work/shard.2.0' output 'work/weights.2.0' -(a dot per input) +(1 dot per processed input) Iteration #1 of 1. - .... 3 + ... 3 WEIGHTS - Glue = -0.2109 - WordPenalty = +0.14922 - LanguageModel = +0.79686 - LanguageModel_OOV = -0.6627 - PhraseModel_0 = +0.37999 - PhraseModel_1 = +0.69213 - PhraseModel_2 = +0.3422 - PhraseModel_3 = +1.1426 - PhraseModel_4 = -0.55413 - PhraseModel_5 = +0 - PhraseModel_6 = +0.0676 - PassThrough = -0.6343 + Glue = -0.0099 + WordPenalty = +0.5556 + LanguageModel = +3.129 + LanguageModel_OOV = +0.1064 + PhraseModel_0 = -0.5801 + PhraseModel_1 = -0.3003 + PhraseModel_2 = +0.1759 + PhraseModel_3 = -0.3496 + PhraseModel_4 = -2.562 + PhraseModel_5 = +0.0102 + PhraseModel_6 = -0.4384 + PassThrough = +0.0809 --- - 1best avg score: 0.072374 (+0.072374) - 1best avg model score: -27.384 - avg # pairs: 2582 - non-0 feature count: 11 + 1best avg score: 9.987 (+9.987) + 1best avg model score: -102.2 + avg # updates: 1862 + non-0 feature count: 850 + avg f count: 144.5 avg list sz: 100 - avg f count: 11.54 -(time 0.32 min, 6 s/S) +(time 0.2 min, 4 s/S) --- -Best iteration: 1 [GOLD = 0.072374]. -This took 0.31667 min. +Best iteration: 1 [GOLD = 9.987]. +This took 0.2 min. |