From 2a48d73eb794fdd736d1df035c8a31af887cde0a Mon Sep 17 00:00:00 2001 From: Patrick Simianer
Date: Fri, 15 Mar 2013 11:31:18 +0100
Subject: overhauled ruby scripts and examples
---
training/dtrain/examples/parallelized/work/out.0.0 | 61 +++++++++++++++++++++
training/dtrain/examples/parallelized/work/out.0.1 | 62 ++++++++++++++++++++++
training/dtrain/examples/parallelized/work/out.1.0 | 61 +++++++++++++++++++++
training/dtrain/examples/parallelized/work/out.1.1 | 62 ++++++++++++++++++++++
.../dtrain/examples/parallelized/work/shard.0.0.in | 5 ++
.../examples/parallelized/work/shard.0.0.refs | 5 ++
.../dtrain/examples/parallelized/work/shard.1.0.in | 5 ++
.../examples/parallelized/work/shard.1.0.refs | 5 ++
.../dtrain/examples/parallelized/work/weights.0 | 12 +++++
.../dtrain/examples/parallelized/work/weights.0.0 | 12 +++++
.../dtrain/examples/parallelized/work/weights.0.1 | 12 +++++
.../dtrain/examples/parallelized/work/weights.1 | 12 +++++
.../dtrain/examples/parallelized/work/weights.1.0 | 11 ++++
.../dtrain/examples/parallelized/work/weights.1.1 | 12 +++++
14 files changed, 337 insertions(+)
create mode 100644 training/dtrain/examples/parallelized/work/out.0.0
create mode 100644 training/dtrain/examples/parallelized/work/out.0.1
create mode 100644 training/dtrain/examples/parallelized/work/out.1.0
create mode 100644 training/dtrain/examples/parallelized/work/out.1.1
create mode 100644 training/dtrain/examples/parallelized/work/shard.0.0.in
create mode 100644 training/dtrain/examples/parallelized/work/shard.0.0.refs
create mode 100644 training/dtrain/examples/parallelized/work/shard.1.0.in
create mode 100644 training/dtrain/examples/parallelized/work/shard.1.0.refs
create mode 100644 training/dtrain/examples/parallelized/work/weights.0
create mode 100644 training/dtrain/examples/parallelized/work/weights.0.0
create mode 100644 training/dtrain/examples/parallelized/work/weights.0.1
create mode 100644 training/dtrain/examples/parallelized/work/weights.1
create mode 100644 training/dtrain/examples/parallelized/work/weights.1.0
create mode 100644 training/dtrain/examples/parallelized/work/weights.1.1
(limited to 'training/dtrain/examples/parallelized/work')
diff --git a/training/dtrain/examples/parallelized/work/out.0.0 b/training/dtrain/examples/parallelized/work/out.0.0
new file mode 100644
index 00000000..7a00ed0f
--- /dev/null
+++ b/training/dtrain/examples/parallelized/work/out.0.0
@@ -0,0 +1,61 @@
+ cdec cfg 'cdec.ini'
+Loading the LM will be faster if you build a binary file.
+Reading ../example/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 3121929377
+
+dtrain
+Parameters:
+ k 100
+ N 4
+ T 1
+ scorer 'stupid_bleu'
+ sample from 'kbest'
+ filter 'uniq'
+ learning rate 0.0001
+ gamma 0
+ loss margin 1
+ pairs 'XYX'
+ hi lo 0.1
+ pair threshold 0
+ select weights 'last'
+ l1 reg 0 'none'
+ max pairs 4294967295
+ cdec cfg 'cdec.ini'
+ input 'work/shard.0.0.in'
+ refs 'work/shard.0.0.refs'
+ output 'work/weights.0.0'
+(a dot represents 10 inputs)
+Iteration #1 of 1.
+ 5
+WEIGHTS
+ Glue = +0.2663
+ WordPenalty = -0.0079042
+ LanguageModel = +0.44782
+ LanguageModel_OOV = -0.0401
+ PhraseModel_0 = -0.193
+ PhraseModel_1 = +0.71321
+ PhraseModel_2 = +0.85196
+ PhraseModel_3 = -0.43986
+ PhraseModel_4 = -0.44803
+ PhraseModel_5 = -0.0538
+ PhraseModel_6 = -0.1788
+ PassThrough = -0.1477
+ ---
+ 1best avg score: 0.17521 (+0.17521)
+ 1best avg model score: 21.556 (+21.556)
+ avg # pairs: 1671.2
+ avg # rank err: 1118.6
+ avg # margin viol: 552.6
+ non0 feature count: 12
+ avg list sz: 100
+ avg f count: 11.32
+(time 0.37 min, 4.4 s/S)
+
+Writing weights file to 'work/weights.0.0' ...
+done
+
+---
+Best iteration: 1 [SCORE 'stupid_bleu'=0.17521].
+This took 0.36667 min.
diff --git a/training/dtrain/examples/parallelized/work/out.0.1 b/training/dtrain/examples/parallelized/work/out.0.1
new file mode 100644
index 00000000..e2bd6649
--- /dev/null
+++ b/training/dtrain/examples/parallelized/work/out.0.1
@@ -0,0 +1,62 @@
+ cdec cfg 'cdec.ini'
+Loading the LM will be faster if you build a binary file.
+Reading ../example/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 2767202922
+
+dtrain
+Parameters:
+ k 100
+ N 4
+ T 1
+ scorer 'stupid_bleu'
+ sample from 'kbest'
+ filter 'uniq'
+ learning rate 0.0001
+ gamma 0
+ loss margin 1
+ pairs 'XYX'
+ hi lo 0.1
+ pair threshold 0
+ select weights 'last'
+ l1 reg 0 'none'
+ max pairs 4294967295
+ cdec cfg 'cdec.ini'
+ input 'work/shard.0.0.in'
+ refs 'work/shard.0.0.refs'
+ output 'work/weights.0.1'
+ weights in 'work/weights.0'
+(a dot represents 10 inputs)
+Iteration #1 of 1.
+ 5
+WEIGHTS
+ Glue = -0.2699
+ WordPenalty = +0.080605
+ LanguageModel = -0.026572
+ LanguageModel_OOV = -0.30025
+ PhraseModel_0 = -0.32076
+ PhraseModel_1 = +0.67451
+ PhraseModel_2 = +0.92
+ PhraseModel_3 = -0.36402
+ PhraseModel_4 = -0.592
+ PhraseModel_5 = -0.0269
+ PhraseModel_6 = -0.28755
+ PassThrough = -0.33285
+ ---
+ 1best avg score: 0.26638 (+0.26638)
+ 1best avg model score: 53.197 (+53.197)
+ avg # pairs: 2028.6
+ avg # rank err: 998.2
+ avg # margin viol: 918.8
+ non0 feature count: 12
+ avg list sz: 100
+ avg f count: 10.496
+(time 0.32 min, 3.8 s/S)
+
+Writing weights file to 'work/weights.0.1' ...
+done
+
+---
+Best iteration: 1 [SCORE 'stupid_bleu'=0.26638].
+This took 0.31667 min.
diff --git a/training/dtrain/examples/parallelized/work/out.1.0 b/training/dtrain/examples/parallelized/work/out.1.0
new file mode 100644
index 00000000..6e790e38
--- /dev/null
+++ b/training/dtrain/examples/parallelized/work/out.1.0
@@ -0,0 +1,61 @@
+ cdec cfg 'cdec.ini'
+Loading the LM will be faster if you build a binary file.
+Reading ../example/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 1432415010
+
+dtrain
+Parameters:
+ k 100
+ N 4
+ T 1
+ scorer 'stupid_bleu'
+ sample from 'kbest'
+ filter 'uniq'
+ learning rate 0.0001
+ gamma 0
+ loss margin 1
+ pairs 'XYX'
+ hi lo 0.1
+ pair threshold 0
+ select weights 'last'
+ l1 reg 0 'none'
+ max pairs 4294967295
+ cdec cfg 'cdec.ini'
+ input 'work/shard.1.0.in'
+ refs 'work/shard.1.0.refs'
+ output 'work/weights.1.0'
+(a dot represents 10 inputs)
+Iteration #1 of 1.
+ 5
+WEIGHTS
+ Glue = -0.3815
+ WordPenalty = +0.20064
+ LanguageModel = +0.95304
+ LanguageModel_OOV = -0.264
+ PhraseModel_0 = -0.22362
+ PhraseModel_1 = +0.12254
+ PhraseModel_2 = +0.26328
+ PhraseModel_3 = +0.38018
+ PhraseModel_4 = -0.48654
+ PhraseModel_5 = +0
+ PhraseModel_6 = -0.3645
+ PassThrough = -0.2216
+ ---
+ 1best avg score: 0.10863 (+0.10863)
+ 1best avg model score: -4.9841 (-4.9841)
+ avg # pairs: 1345.4
+ avg # rank err: 822.4
+ avg # margin viol: 501
+ non0 feature count: 11
+ avg list sz: 100
+ avg f count: 11.814
+(time 0.45 min, 5.4 s/S)
+
+Writing weights file to 'work/weights.1.0' ...
+done
+
+---
+Best iteration: 1 [SCORE 'stupid_bleu'=0.10863].
+This took 0.45 min.
diff --git a/training/dtrain/examples/parallelized/work/out.1.1 b/training/dtrain/examples/parallelized/work/out.1.1
new file mode 100644
index 00000000..0b984761
--- /dev/null
+++ b/training/dtrain/examples/parallelized/work/out.1.1
@@ -0,0 +1,62 @@
+ cdec cfg 'cdec.ini'
+Loading the LM will be faster if you build a binary file.
+Reading ../example/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 1771918374
+
+dtrain
+Parameters:
+ k 100
+ N 4
+ T 1
+ scorer 'stupid_bleu'
+ sample from 'kbest'
+ filter 'uniq'
+ learning rate 0.0001
+ gamma 0
+ loss margin 1
+ pairs 'XYX'
+ hi lo 0.1
+ pair threshold 0
+ select weights 'last'
+ l1 reg 0 'none'
+ max pairs 4294967295
+ cdec cfg 'cdec.ini'
+ input 'work/shard.1.0.in'
+ refs 'work/shard.1.0.refs'
+ output 'work/weights.1.1'
+ weights in 'work/weights.0'
+(a dot represents 10 inputs)
+Iteration #1 of 1.
+ 5
+WEIGHTS
+ Glue = -0.3178
+ WordPenalty = +0.11092
+ LanguageModel = +0.17269
+ LanguageModel_OOV = -0.13485
+ PhraseModel_0 = -0.45371
+ PhraseModel_1 = +0.38789
+ PhraseModel_2 = +0.75311
+ PhraseModel_3 = -0.38163
+ PhraseModel_4 = -0.58817
+ PhraseModel_5 = -0.0269
+ PhraseModel_6 = -0.27315
+ PassThrough = -0.16745
+ ---
+ 1best avg score: 0.13169 (+0.13169)
+ 1best avg model score: 24.226 (+24.226)
+ avg # pairs: 1951.2
+ avg # rank err: 985.4
+ avg # margin viol: 951
+ non0 feature count: 12
+ avg list sz: 100
+ avg f count: 11.224
+(time 0.42 min, 5 s/S)
+
+Writing weights file to 'work/weights.1.1' ...
+done
+
+---
+Best iteration: 1 [SCORE 'stupid_bleu'=0.13169].
+This took 0.41667 min.
diff --git a/training/dtrain/examples/parallelized/work/shard.0.0.in b/training/dtrain/examples/parallelized/work/shard.0.0.in
new file mode 100644
index 00000000..92f9c78e
--- /dev/null
+++ b/training/dtrain/examples/parallelized/work/shard.0.0.in
@@ -0,0 +1,5 @@
+