diff options
| author | Patrick Simianer <p@simianer.de> | 2015-03-24 19:15:48 +0100 |
|---|---|---|
| committer | Patrick Simianer <p@simianer.de> | 2015-03-24 19:15:48 +0100 |
| commit | 70572bc0aa0338b298e9a8e2829a0a0d134785e4 (patch) | |
| tree | ddcea305027ff3ef1e1aea2e502898de00c718b3 /training/dtrain/examples/parallelized/work/out.0.0 | |
| parent | bca9a8d79e565222898afbe98abf5ce5a1fe801b (diff) | |
dtrain: fix example
Diffstat (limited to 'training/dtrain/examples/parallelized/work/out.0.0')
| -rw-r--r-- | training/dtrain/examples/parallelized/work/out.0.0 | 44 |
1 files changed, 0 insertions, 44 deletions
diff --git a/training/dtrain/examples/parallelized/work/out.0.0 b/training/dtrain/examples/parallelized/work/out.0.0 deleted file mode 100644 index da7c20a4..00000000 --- a/training/dtrain/examples/parallelized/work/out.0.0 +++ /dev/null @@ -1,44 +0,0 @@ -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 -**************************************************************************************************** - Example feature: Shape_S00000_T00000 -dtrain -Parameters: - k 100 - N 4 - T 1 - learning rate 0.0001 - margin 1 - l1 reg 0 - decoder conf 'cdec.ini' - input 'work/shard.0.0' - output 'work/weights.0.0' -(1 dot per processed input) -Iteration #1 of 1. - ... 3 -WEIGHTS - Glue = +0.1984 - WordPenalty = +0.06119 - LanguageModel = +0.6184 - LanguageModel_OOV = -0.2584 - PhraseModel_0 = -0.3803 - PhraseModel_1 = +0.6495 - PhraseModel_2 = +0.9499 - PhraseModel_3 = -0.4945 - PhraseModel_4 = -0.4588 - PhraseModel_5 = +0 - PhraseModel_6 = -0.2935 - PassThrough = -0.2742 - --- - 1best avg score: 22.94 (+22.94) - 1best avg model score: +33.08 - avg # updates: 2169 - non-0 feature count: 441 - avg f count: 143.9 - avg list sz: 100 -(time 0.1667 min, 3 s/S) - ---- -Best iteration: 1 [GOLD = 22.94]. -This took 0.1667 min. |