summaryrefslogtreecommitdiff
path: root/training/dtrain/examples/parallelized/work/out.2.1
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.2.1
parent2a37a7ad1b21ab54701de3b5b44dc4ea55a75307 (diff)
refactoring
Diffstat (limited to 'training/dtrain/examples/parallelized/work/out.2.1')
-rw-r--r--training/dtrain/examples/parallelized/work/out.2.174
1 files changed, 26 insertions, 48 deletions
diff --git a/training/dtrain/examples/parallelized/work/out.2.1 b/training/dtrain/examples/parallelized/work/out.2.1
index 8e4efde9..c54bb1b1 100644
--- a/training/dtrain/examples/parallelized/work/out.2.1
+++ b/training/dtrain/examples/parallelized/work/out.2.1
@@ -1,66 +1,44 @@
- 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 3092904479
-
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.2.0.in'
output 'work/weights.2.1'
weights in 'work/weights.0'
-(a dot represents 10 inputs)
+(a dot per input)
Iteration #1 of 1.
- 3
+ .... 3
WEIGHTS
- Glue = -0.10385
- WordPenalty = +0.038717
- LanguageModel = +0.49413
- LanguageModel_OOV = -0.24887
- PhraseModel_0 = -0.32102
- PhraseModel_1 = +0.34413
- PhraseModel_2 = +0.62366
- PhraseModel_3 = -0.49337
- PhraseModel_4 = -0.77005
- PhraseModel_5 = +0.007
- PhraseModel_6 = -0.05055
- PassThrough = -0.23928
+ Glue = -0.76608
+ WordPenalty = +0.15938
+ LanguageModel = +1.5897
+ LanguageModel_OOV = -0.521
+ PhraseModel_0 = -0.58348
+ PhraseModel_1 = +0.29828
+ PhraseModel_2 = +0.78493
+ PhraseModel_3 = +0.083222
+ PhraseModel_4 = -0.93843
+ PhraseModel_5 = +0.02435
+ PhraseModel_6 = -0.27382
+ PassThrough = -0.55115
---
- 1best avg score: 0.10245 (+0.10245)
- 1best avg model score: -20.384 (-20.384)
- avg # pairs: 1741.7
- avg # rank err: 953.67
- avg # margin viol: 585.33
- k-best loss imp: 100%
- non0 feature count: 12
+ 1best avg score: 0.12881 (+0.12881)
+ 1best avg model score: -9.6731
+ avg # pairs: 2020.3
+ non-0 feature count: 12
avg list sz: 100
- avg f count: 11.977
-(time 0.12 min, 2.3 s/S)
-
-Writing weights file to 'work/weights.2.1' ...
-done
+ avg f count: 12
+(time 0.32 min, 6 s/S)
---
-Best iteration: 1 [SCORE 'stupid_bleu'=0.10245].
-This took 0.11667 min.
+Best iteration: 1 [GOLD = 0.12881].
+This took 0.31667 min.