summaryrefslogtreecommitdiff
path: root/training/dtrain/examples/parallelized/work/out.3.0
diff options
context:
space:
mode:
authorPatrick Simianer <p@simianer.de>2015-02-26 13:26:37 +0100
committerPatrick Simianer <p@simianer.de>2015-02-26 13:26:37 +0100
commit4223261682388944fe1b1cf31b9d51d88f9ad53b (patch)
treedaf072c310d60b0386587bde5e554312f193b3b2 /training/dtrain/examples/parallelized/work/out.3.0
parent2a37a7ad1b21ab54701de3b5b44dc4ea55a75307 (diff)
refactoring
Diffstat (limited to 'training/dtrain/examples/parallelized/work/out.3.0')
-rw-r--r--training/dtrain/examples/parallelized/work/out.3.074
1 files changed, 26 insertions, 48 deletions
diff --git a/training/dtrain/examples/parallelized/work/out.3.0 b/training/dtrain/examples/parallelized/work/out.3.0
index 3c074f04..fa499523 100644
--- a/training/dtrain/examples/parallelized/work/out.3.0
+++ b/training/dtrain/examples/parallelized/work/out.3.0
@@ -1,65 +1,43 @@
- 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 316107185
-
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 ''
+ error margin 1
+ l1 reg 0
+ decoder conf 'cdec.ini'
+ input 'work/shard.3.0.in'
output 'work/weights.3.0'
-(a dot represents 10 inputs)
+(a dot per input)
Iteration #1 of 1.
- 1
+ .. 1
WEIGHTS
- Glue = +0.046
- WordPenalty = +0.17328
- LanguageModel = +1.1667
- LanguageModel_OOV = +0.066
- PhraseModel_0 = -1.1694
- PhraseModel_1 = -0.9883
- PhraseModel_2 = +0.036205
- PhraseModel_3 = -0.77387
- PhraseModel_4 = -1.5019
- PhraseModel_5 = +0.024
- PhraseModel_6 = -0.514
- PassThrough = +0.031
+ Glue = -0.09
+ WordPenalty = +0.32442
+ LanguageModel = +2.5769
+ LanguageModel_OOV = -0.009
+ PhraseModel_0 = -0.58972
+ PhraseModel_1 = +0.063691
+ PhraseModel_2 = +0.5366
+ PhraseModel_3 = +0.12867
+ PhraseModel_4 = -1.9801
+ PhraseModel_5 = +0.018
+ PhraseModel_6 = -0.486
+ PassThrough = -0.09
---
- 1best avg score: 0.032916 (+0.032916)
- 1best avg model score: 0 (+0)
- avg # pairs: 900
- avg # rank err: 900
- avg # margin viol: 0
- k-best loss imp: 100%
- non0 feature count: 12
+ 1best avg score: 0.034204 (+0.034204)
+ 1best avg model score: 0
+ avg # pairs: 1700
+ non-0 feature count: 12
avg list sz: 100
- avg f count: 11.72
-(time 0.23 min, 14 s/S)
-
-Writing weights file to 'work/weights.3.0' ...
-done
+ avg f count: 10.8
+(time 0.1 min, 6 s/S)
---
-Best iteration: 1 [SCORE 'stupid_bleu'=0.032916].
-This took 0.23333 min.
+Best iteration: 1 [GOLD = 0.034204].
+This took 0.1 min.