summaryrefslogtreecommitdiff
path: root/training/dtrain/examples/parallelized/work/out.0.0
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.0.0
parent2a37a7ad1b21ab54701de3b5b44dc4ea55a75307 (diff)
refactoring
Diffstat (limited to 'training/dtrain/examples/parallelized/work/out.0.0')
-rw-r--r--training/dtrain/examples/parallelized/work/out.0.074
1 files changed, 26 insertions, 48 deletions
diff --git a/training/dtrain/examples/parallelized/work/out.0.0 b/training/dtrain/examples/parallelized/work/out.0.0
index 9154c906..77749404 100644
--- a/training/dtrain/examples/parallelized/work/out.0.0
+++ b/training/dtrain/examples/parallelized/work/out.0.0
@@ -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 4087834873
-
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.0.0.in'
output 'work/weights.0.0'
-(a dot represents 10 inputs)
+(a dot per input)
Iteration #1 of 1.
- 3
+ .... 3
WEIGHTS
- Glue = +0.257
- WordPenalty = +0.026926
- LanguageModel = +0.67342
- LanguageModel_OOV = -0.046
- PhraseModel_0 = +0.25329
- PhraseModel_1 = +0.20036
- PhraseModel_2 = +0.00060731
- PhraseModel_3 = +0.65578
- PhraseModel_4 = +0.47916
- PhraseModel_5 = +0.004
- PhraseModel_6 = +0.1829
- PassThrough = -0.082
+ Glue = +0.3404
+ WordPenalty = -0.017632
+ LanguageModel = +0.72958
+ LanguageModel_OOV = -0.235
+ PhraseModel_0 = -0.43721
+ PhraseModel_1 = +1.01
+ PhraseModel_2 = +1.3525
+ PhraseModel_3 = -0.25541
+ PhraseModel_4 = -0.78115
+ PhraseModel_5 = +0
+ PhraseModel_6 = -0.3681
+ PassThrough = -0.3304
---
- 1best avg score: 0.04518 (+0.04518)
- 1best avg model score: 32.803 (+32.803)
- avg # pairs: 1266.3
- avg # rank err: 857
- avg # margin viol: 386.67
- k-best loss imp: 100%
- non0 feature count: 12
+ 1best avg score: 0.19474 (+0.19474)
+ 1best avg model score: 0.52232
+ avg # pairs: 2513
+ non-0 feature count: 11
avg list sz: 100
- avg f count: 10.853
-(time 0.47 min, 9.3 s/S)
-
-Writing weights file to 'work/weights.0.0' ...
-done
+ avg f count: 11.42
+(time 0.32 min, 6 s/S)
---
-Best iteration: 1 [SCORE 'stupid_bleu'=0.04518].
-This took 0.46667 min.
+Best iteration: 1 [GOLD = 0.19474].
+This took 0.31667 min.