summaryrefslogtreecommitdiff
path: root/training
diff options
context:
space:
mode:
Diffstat (limited to 'training')
-rw-r--r--training/dtrain/examples/standard/expected-output82
1 files changed, 41 insertions, 41 deletions
diff --git a/training/dtrain/examples/standard/expected-output b/training/dtrain/examples/standard/expected-output
index 9a25062b..21f91244 100644
--- a/training/dtrain/examples/standard/expected-output
+++ b/training/dtrain/examples/standard/expected-output
@@ -4,7 +4,7 @@ Reading ./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
-Seeding random number sequence to 1677737427
+Seeding random number sequence to 970626287
dtrain
Parameters:
@@ -34,58 +34,58 @@ Iteration #1 of 2.
. 10
Stopping after 10 input sentences.
WEIGHTS
- Glue = -1155
- WordPenalty = -329.63
- LanguageModel = +3903
- LanguageModel_OOV = -1630
- PhraseModel_0 = +2746.9
- PhraseModel_1 = +1200.3
- PhraseModel_2 = -1004.1
- PhraseModel_3 = +2223.1
- PhraseModel_4 = +551.58
- PhraseModel_5 = +217
- PhraseModel_6 = +1816
- PassThrough = -1603
+ Glue = -614
+ WordPenalty = +1256.8
+ LanguageModel = +5610.5
+ LanguageModel_OOV = -1449
+ PhraseModel_0 = -2107
+ PhraseModel_1 = -4666.1
+ PhraseModel_2 = -2713.5
+ PhraseModel_3 = +4204.3
+ PhraseModel_4 = -1435.8
+ PhraseModel_5 = +916
+ PhraseModel_6 = +190
+ PassThrough = -2527
---
- 1best avg score: 0.19344 (+0.19344)
- 1best avg model score: 81387 (+81387)
- avg # pairs: 616.3 (meaningless)
- avg # rank err: 616.3
+ 1best avg score: 0.17874 (+0.17874)
+ 1best avg model score: 88399 (+88399)
+ avg # pairs: 798.2 (meaningless)
+ avg # rank err: 798.2
avg # margin viol: 0
- non0 feature count: 673
- avg list sz: 90.9
- avg f count: 104.26
-(time 0.38 min, 2.3 s/S)
+ non0 feature count: 887
+ avg list sz: 91.3
+ avg f count: 126.85
+(time 0.33 min, 2 s/S)
Iteration #2 of 2.
. 10
WEIGHTS
- Glue = -994
- WordPenalty = -778.69
- LanguageModel = +2348.9
- LanguageModel_OOV = -1967
- PhraseModel_0 = -412.72
- PhraseModel_1 = +1428.9
- PhraseModel_2 = +1967.4
- PhraseModel_3 = -944.99
- PhraseModel_4 = -239.7
- PhraseModel_5 = +708
- PhraseModel_6 = +645
- PassThrough = -1866
+ Glue = -1025
+ WordPenalty = +1751.5
+ LanguageModel = +10059
+ LanguageModel_OOV = -4490
+ PhraseModel_0 = -2640.7
+ PhraseModel_1 = -3757.4
+ PhraseModel_2 = -1133.1
+ PhraseModel_3 = +1837.3
+ PhraseModel_4 = -3534.3
+ PhraseModel_5 = +2308
+ PhraseModel_6 = +1677
+ PassThrough = -6222
---
- 1best avg score: 0.22395 (+0.03051)
- 1best avg model score: -31388 (-1.1278e+05)
- avg # pairs: 702.3 (meaningless)
- avg # rank err: 702.3
+ 1best avg score: 0.30764 (+0.12891)
+ 1best avg model score: -2.5042e+05 (-3.3882e+05)
+ avg # pairs: 725.9 (meaningless)
+ avg # rank err: 725.9
avg # margin viol: 0
- non0 feature count: 955
+ non0 feature count: 1499
avg list sz: 91.3
- avg f count: 103.45
+ avg f count: 114.34
(time 0.32 min, 1.9 s/S)
Writing weights file to '-' ...
done
---
-Best iteration: 2 [SCORE 'fixed_stupid_bleu'=0.22395].
-This took 0.7 min.
+Best iteration: 2 [SCORE 'fixed_stupid_bleu'=0.30764].
+This took 0.65 min.