diff --git a/hatt_train.ipynb b/hatt_train.ipynb deleted file mode 100644 index 70c9e3e..0000000 --- a/hatt_train.ipynb +++ /dev/null @@ -1,2817 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": { - "deletable": true, - "editable": true - }, - "source": [ - "The code in this notebook is based on [Richard Liao's implementation of hierarchical attention networks](https://github.com/richliao/textClassifier/blob/master/textClassifierHATT.py) and a related [Google group discussion](https://groups.google.com/forum/#!topic/keras-users/IWK9opMFavQ). The notebook also includes code from [Keras documentation](https://keras.io/) and [blog](https://blog.keras.io/using-pre-trained-word-embeddings-in-a-keras-model.html) as well as this [word2vec tutorial](http://adventuresinmachinelearning.com/gensim-word2vec-tutorial/)." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "deletable": true, - "editable": true - }, - "source": [ - "To enable Theano to run on a single GPU: \n", - "\n", - "* check the following dependencies: \n", - "\n", - " `conda install pygpu`\n", - " \n", - "\n", - "* Replace $HOME/.theanorc with this:\n", - "```\n", - "[global]\n", - "floatX = float32\n", - "device = gpu0\n", - "[lib]\n", - "gpuarray.preallocate=1\n", - "```" - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true, - "scrolled": false - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "WARNING (theano.sandbox.cuda): The cuda backend is deprecated and will be removed in the next release (v0.10). Please switch to the gpuarray backend. You can get more information about how to switch at this URL:\n", - " https://github.com/Theano/Theano/wiki/Converting-to-the-new-gpu-back-end%28gpuarray%29\n", - "\n", - "Using gpu device 0: Tesla K80 (CNMeM is disabled, cuDNN 5110)\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "gpu0\n" - ] - } - ], - "source": [ - "import os \n", - "os.environ['THEANO_FLAGS'] = 'floatX=float32,device=gpu0'\n", - "os.environ['PATH'] = os.environ['PATH'] + ':/usr/local/cuda-8.0/bin'\n", - "import theano\n", - "print(theano.config.device) " - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Using Theano backend.\n" - ] - } - ], - "source": [ - "import numpy as np\n", - "import pandas as pd\n", - "from collections import defaultdict\n", - "import os \n", - "os.environ['KERAS_BACKEND'] = 'theano'\n", - "import subprocess\n", - "import time\n", - "\n", - "from keras.preprocessing.text import Tokenizer, text_to_word_sequence\n", - "from keras.preprocessing.sequence import pad_sequences\n", - "from keras.utils.np_utils import to_categorical\n", - "from keras.optimizers import SGD\n", - "\n", - "from keras.layers import Embedding\n", - "from keras.layers import Dense, Input, Flatten\n", - "from keras.layers import Conv1D, MaxPooling1D, Embedding, Merge, Dropout, LSTM, GRU, Bidirectional, TimeDistributed\n", - "from keras.models import Model\n", - "\n", - "from keras.utils import get_file\n", - "from keras import backend as K\n", - "from keras.engine.topology import Layer, InputSpec\n", - "from keras import initializers, regularizers, optimizers\n", - "from keras.callbacks import History, CSVLogger" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": { - "collapsed": true, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "MAX_SENT_LENGTH = 100\n", - "MAX_SENTS = 30\n", - "MAX_NB_WORDS = 20000\n", - "EMBEDDING_DIM = 200\n", - "MAX_VOCAB_SIZE = 50000" - ] - }, - { - "cell_type": "code", - "execution_count": 35, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "trainFile = '/home/anargyri/.keras/datasets/amazon_reviews_train.csv'\n", - "\n", - "# read\n", - "train_data = pd.read_csv(trainFile, header=None, names=['rating', 'title', 'text'])" - ] - }, - { - "cell_type": "code", - "execution_count": 36, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[nltk_data] Downloading package punkt to /home/anargyri/nltk_data...\n", - "[nltk_data] Package punkt is already up-to-date!\n" - ] - } - ], - "source": [ - "import nltk \n", - "\n", - "nltk.download('punkt')\n", - "\n", - "reviews = []\n", - "labels = []\n", - "texts = []\n", - "\n", - "for idx in range(train_data.shape[0]):\n", - " text = train_data['text'].iloc[idx]\n", - " texts.append(text)\n", - " sentences = nltk.tokenize.sent_tokenize(text)\n", - " reviews.append(sentences)\n", - " labels.append(train_data['rating'].iloc[idx])" - ] - }, - { - "cell_type": "code", - "execution_count": 34, - "metadata": { - "collapsed": true, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "tokenizer = Tokenizer(num_words=MAX_NB_WORDS)\n", - "tokenizer.fit_on_texts(texts)" - ] - }, - { - "cell_type": "code", - "execution_count": 45, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "data = np.zeros((len(texts), MAX_SENTS, MAX_SENT_LENGTH), dtype='int32')\n", - "doc_lst = []\n", - "\n", - "# keep the MAX_NB_WORDS most frequent words and replace the rest with 'UNK'\n", - "# truncate to the first MAX_SENTS sentences per doc and MAX_SENT_LENGTH words per sentence\n", - "\n", - "for i, sentences in enumerate(reviews):\n", - " for j, sent in enumerate(sentences):\n", - " if j < MAX_SENTS:\n", - " wordTokens = text_to_word_sequence(sent)\n", - " k = 0\n", - " words_in_sent = []\n", - " for _, word in enumerate(wordTokens):\n", - " if k < MAX_SENT_LENGTH: \n", - " if (word in tokenizer.word_index) and (tokenizer.word_index[word] < MAX_NB_WORDS):\n", - " data[i, j, k] = tokenizer.word_index[word]\n", - " words_in_sent.append(word)\n", - " else:\n", - " data[i, j, k] = MAX_NB_WORDS\n", - " words_in_sent.append('UNK')\n", - " k = k + 1\n", - " doc_lst.append(words_in_sent)" - ] - }, - { - "cell_type": "code", - "execution_count": 59, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Total 951656 unique tokens.\n", - "Shape of data tensor: (3000000, 30, 100)\n", - "Shape of label tensor: (3000000, 5)\n" - ] - } - ], - "source": [ - "word_index = tokenizer.word_index\n", - "print('Total %s unique tokens.' % len(word_index))\n", - "\n", - "labels = to_categorical(np.asarray(labels))\n", - "x_train = data\n", - "y_train = labels[:,1:]\n", - "\n", - "print('Shape of data tensor:', x_train.shape)\n", - "print('Shape of label tensor:', y_train.shape)" - ] - }, - { - "cell_type": "code", - "execution_count": 8, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Number of reviews by class in training set\n", - "[ 600000. 600000. 600000. 600000. 600000.]\n" - ] - } - ], - "source": [ - "print('Number of reviews by class in training set')\n", - "print(y_train.sum(axis=0))\n", - "n_classes = y_train.shape[1]" - ] - }, - { - "cell_type": "code", - "execution_count": 43, - "metadata": { - "collapsed": true, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "np.save('/data/tmp/x_train', x_train)\n", - "np.save('/data/tmp/y_train', y_train)\n", - "np.save('/data/tmp/reviews', reviews)" - ] - }, - { - "cell_type": "code", - "execution_count": 62, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "# train word2vec on the sentences to initialize the word embedding \n", - "import gensim, logging" - ] - }, - { - "cell_type": "code", - "execution_count": 63, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "2017-08-20 12:50:59,261 : INFO : collecting all words and their counts\n", - "2017-08-20 12:50:59,263 : INFO : PROGRESS: at sentence #0, processed 0 words, keeping 0 word types\n", - "2017-08-20 12:50:59,309 : INFO : PROGRESS: at sentence #10000, processed 164375 words, keeping 9743 word types\n", - "2017-08-20 12:50:59,346 : INFO : PROGRESS: at sentence #20000, processed 329372 words, keeping 12860 word types\n", - "2017-08-20 12:50:59,383 : INFO : PROGRESS: at sentence #30000, processed 493998 words, keeping 14628 word types\n", - "2017-08-20 12:50:59,424 : INFO : PROGRESS: at sentence #40000, processed 658315 words, keeping 15832 word types\n", - "2017-08-20 12:50:59,461 : INFO : PROGRESS: at sentence #50000, processed 821159 words, keeping 16584 word types\n", - "2017-08-20 12:50:59,500 : INFO : PROGRESS: at sentence #60000, processed 983885 words, keeping 17225 word types\n", - "2017-08-20 12:50:59,538 : INFO : PROGRESS: at sentence #70000, processed 1150118 words, keeping 17756 word types\n", - "2017-08-20 12:50:59,576 : INFO : PROGRESS: at sentence #80000, processed 1315784 words, keeping 18112 word types\n", - "2017-08-20 12:50:59,613 : INFO : PROGRESS: at sentence #90000, processed 1483793 words, keeping 18402 word types\n", - "2017-08-20 12:50:59,650 : INFO : PROGRESS: at sentence #100000, processed 1650599 words, keeping 18680 word types\n", - "2017-08-20 12:50:59,704 : INFO : PROGRESS: at sentence #110000, processed 1816834 words, keeping 18870 word types\n", - "2017-08-20 12:50:59,741 : INFO : PROGRESS: at sentence #120000, processed 1980927 words, keeping 19021 word types\n", - "2017-08-20 12:50:59,778 : INFO : PROGRESS: at sentence #130000, processed 2148078 words, keeping 19155 word types\n", - "2017-08-20 12:50:59,814 : INFO : PROGRESS: at sentence #140000, processed 2315585 words, keeping 19262 word types\n", - "2017-08-20 12:50:59,852 : INFO : PROGRESS: at sentence #150000, processed 2483157 words, keeping 19361 word types\n", - "2017-08-20 12:50:59,889 : INFO : PROGRESS: at sentence #160000, processed 2649651 words, keeping 19413 word types\n", - "2017-08-20 12:50:59,925 : INFO : PROGRESS: at sentence #170000, processed 2814302 words, keeping 19480 word types\n", - "2017-08-20 12:50:59,961 : INFO : PROGRESS: at sentence #180000, processed 2980831 words, keeping 19548 word types\n", - "2017-08-20 12:50:59,997 : INFO : PROGRESS: at sentence #190000, processed 3144925 words, keeping 19588 word types\n", - "2017-08-20 12:51:00,042 : INFO : PROGRESS: at sentence #200000, processed 3309585 words, keeping 19631 word types\n", - "2017-08-20 12:51:00,083 : INFO : PROGRESS: at sentence #210000, processed 3473376 words, keeping 19665 word types\n", - "2017-08-20 12:51:00,123 : INFO : PROGRESS: at sentence #220000, processed 3638342 words, keeping 19702 word types\n", - "2017-08-20 12:51:00,161 : INFO : PROGRESS: at sentence #230000, processed 3805399 words, keeping 19732 word types\n", - "2017-08-20 12:51:00,199 : INFO : PROGRESS: at sentence #240000, processed 3971130 words, keeping 19759 word types\n", - "2017-08-20 12:51:00,237 : INFO : PROGRESS: at sentence #250000, processed 4136830 words, keeping 19783 word types\n", - "2017-08-20 12:51:00,276 : INFO : PROGRESS: at sentence #260000, processed 4297199 words, keeping 19807 word types\n", - "2017-08-20 12:51:00,315 : INFO : PROGRESS: at sentence #270000, processed 4467159 words, keeping 19824 word types\n", - "2017-08-20 12:51:00,352 : INFO : PROGRESS: at sentence #280000, processed 4634278 words, keeping 19834 word types\n", - "2017-08-20 12:51:00,390 : INFO : PROGRESS: at sentence #290000, processed 4803392 words, keeping 19852 word types\n", - "2017-08-20 12:51:00,437 : INFO : PROGRESS: at sentence #300000, processed 4967834 words, keeping 19866 word types\n", - "2017-08-20 12:51:00,478 : INFO : PROGRESS: at sentence #310000, processed 5133120 words, keeping 19872 word types\n", - "2017-08-20 12:51:00,515 : INFO : PROGRESS: at sentence #320000, processed 5297864 words, keeping 19886 word types\n", - "2017-08-20 12:51:00,553 : INFO : PROGRESS: at sentence #330000, processed 5462040 words, keeping 19896 word types\n", - "2017-08-20 12:51:00,591 : INFO : PROGRESS: at sentence #340000, processed 5627281 words, keeping 19912 word types\n", - "2017-08-20 12:51:00,634 : INFO : PROGRESS: at sentence #350000, processed 5788197 words, keeping 19927 word types\n", - "2017-08-20 12:51:00,673 : INFO : PROGRESS: at sentence #360000, processed 5950745 words, keeping 19933 word types\n", - "2017-08-20 12:51:00,710 : INFO : PROGRESS: at sentence #370000, processed 6114163 words, keeping 19937 word types\n", - "2017-08-20 12:51:00,747 : INFO : PROGRESS: at sentence #380000, processed 6281076 words, keeping 19940 word types\n", - "2017-08-20 12:51:00,784 : INFO : PROGRESS: at sentence #390000, processed 6444497 words, keeping 19942 word types\n", - "2017-08-20 12:51:00,822 : INFO : PROGRESS: at sentence #400000, processed 6612137 words, keeping 19946 word types\n", - "2017-08-20 12:51:00,861 : INFO : PROGRESS: at sentence #410000, processed 6774953 words, keeping 19952 word types\n", - "2017-08-20 12:51:00,899 : INFO : PROGRESS: at sentence #420000, processed 6941045 words, keeping 19957 word types\n", - "2017-08-20 12:51:00,936 : INFO : PROGRESS: at sentence #430000, processed 7105971 words, keeping 19961 word types\n", - "2017-08-20 12:51:00,974 : INFO : PROGRESS: at sentence #440000, processed 7274371 words, keeping 19961 word types\n", - "2017-08-20 12:51:01,010 : INFO : PROGRESS: at sentence #450000, processed 7436920 words, keeping 19964 word types\n", - "2017-08-20 12:51:01,049 : INFO : PROGRESS: at sentence #460000, processed 7603608 words, keeping 19966 word types\n", - "2017-08-20 12:51:01,087 : INFO : PROGRESS: at sentence #470000, processed 7767626 words, keeping 19969 word types\n", - "2017-08-20 12:51:01,124 : INFO : PROGRESS: at sentence #480000, processed 7933716 words, keeping 19972 word types\n", - "2017-08-20 12:51:01,162 : INFO : PROGRESS: at sentence #490000, processed 8095586 words, keeping 19974 word types\n", - "2017-08-20 12:51:01,199 : INFO : PROGRESS: at sentence #500000, processed 8260356 words, keeping 19976 word types\n", - "2017-08-20 12:51:01,237 : INFO : PROGRESS: at sentence #510000, processed 8423609 words, keeping 19978 word types\n", - "2017-08-20 12:51:01,275 : INFO : PROGRESS: at sentence #520000, processed 8588617 words, keeping 19978 word types\n", - "2017-08-20 12:51:01,312 : INFO : PROGRESS: at sentence #530000, processed 8751836 words, keeping 19979 word types\n", - "2017-08-20 12:51:01,349 : INFO : PROGRESS: at sentence #540000, processed 8915488 words, keeping 19980 word types\n", - "2017-08-20 12:51:01,387 : INFO : PROGRESS: at sentence #550000, processed 9084278 words, keeping 19980 word types\n", - "2017-08-20 12:51:01,425 : INFO : PROGRESS: at sentence #560000, processed 9251207 words, keeping 19980 word types\n", - "2017-08-20 12:51:01,463 : INFO : PROGRESS: at sentence #570000, processed 9417624 words, keeping 19980 word types\n", - "2017-08-20 12:51:01,501 : INFO : PROGRESS: at sentence #580000, processed 9586673 words, keeping 19982 word types\n", - "2017-08-20 12:51:01,537 : INFO : PROGRESS: at sentence #590000, processed 9749149 words, keeping 19983 word types\n", - "2017-08-20 12:51:01,573 : INFO : PROGRESS: at sentence #600000, processed 9910049 words, keeping 19984 word types\n", - "2017-08-20 12:51:01,613 : INFO : PROGRESS: at sentence #610000, processed 10077153 words, keeping 19985 word types\n", - "2017-08-20 12:51:01,652 : INFO : PROGRESS: at sentence #620000, processed 10239427 words, keeping 19986 word types\n", - "2017-08-20 12:51:01,691 : INFO : PROGRESS: at sentence #630000, processed 10407933 words, keeping 19987 word types\n", - "2017-08-20 12:51:01,731 : INFO : PROGRESS: at sentence #640000, processed 10575837 words, keeping 19987 word types\n", - "2017-08-20 12:51:01,769 : INFO : PROGRESS: at sentence #650000, processed 10741603 words, keeping 19987 word types\n", - "2017-08-20 12:51:01,808 : INFO : PROGRESS: at sentence #660000, processed 10908336 words, keeping 19989 word types\n", - "2017-08-20 12:51:01,846 : INFO : PROGRESS: at sentence #670000, processed 11075184 words, keeping 19990 word types\n", - "2017-08-20 12:51:01,882 : INFO : PROGRESS: at sentence #680000, processed 11234190 words, keeping 19990 word types\n", - "2017-08-20 12:51:01,920 : INFO : PROGRESS: at sentence #690000, processed 11401146 words, keeping 19991 word types\n", - "2017-08-20 12:51:01,957 : INFO : PROGRESS: at sentence #700000, processed 11564684 words, keeping 19991 word types\n", - "2017-08-20 12:51:01,995 : INFO : PROGRESS: at sentence #710000, processed 11731995 words, keeping 19993 word types\n", - "2017-08-20 12:51:02,033 : INFO : PROGRESS: at sentence #720000, processed 11900376 words, keeping 19994 word types\n", - "2017-08-20 12:51:02,070 : INFO : PROGRESS: at sentence #730000, processed 12064716 words, keeping 19994 word types\n", - "2017-08-20 12:51:02,107 : INFO : PROGRESS: at sentence #740000, processed 12229536 words, keeping 19994 word types\n", - "2017-08-20 12:51:02,146 : INFO : PROGRESS: at sentence #750000, processed 12399804 words, keeping 19996 word types\n", - "2017-08-20 12:51:02,184 : INFO : PROGRESS: at sentence #760000, processed 12566622 words, keeping 19996 word types\n", - "2017-08-20 12:51:02,223 : INFO : PROGRESS: at sentence #770000, processed 12727491 words, keeping 19996 word types\n", - "2017-08-20 12:51:02,260 : INFO : PROGRESS: at sentence #780000, processed 12893037 words, keeping 19996 word types\n", - "2017-08-20 12:51:02,297 : INFO : PROGRESS: at sentence #790000, processed 13063614 words, keeping 19996 word types\n", - "2017-08-20 12:51:02,334 : INFO : PROGRESS: at sentence #800000, processed 13227813 words, keeping 19997 word types\n", - "2017-08-20 12:51:02,373 : INFO : PROGRESS: at sentence #810000, processed 13396793 words, keeping 19998 word types\n", - "2017-08-20 12:51:02,412 : INFO : PROGRESS: at sentence #820000, processed 13564942 words, keeping 19998 word types\n", - "2017-08-20 12:51:02,449 : INFO : PROGRESS: at sentence #830000, processed 13732072 words, keeping 19998 word types\n", - "2017-08-20 12:51:02,488 : INFO : PROGRESS: at sentence #840000, processed 13902290 words, keeping 19999 word types\n", - "2017-08-20 12:51:02,524 : INFO : PROGRESS: at sentence #850000, processed 14066405 words, keeping 19999 word types\n", - "2017-08-20 12:51:02,562 : INFO : PROGRESS: at sentence #860000, processed 14231472 words, keeping 19999 word types\n", - "2017-08-20 12:51:02,602 : INFO : PROGRESS: at sentence #870000, processed 14400681 words, keeping 19999 word types\n", - "2017-08-20 12:51:02,639 : INFO : PROGRESS: at sentence #880000, processed 14566281 words, keeping 19999 word types\n", - "2017-08-20 12:51:02,675 : INFO : PROGRESS: at sentence #890000, processed 14728042 words, keeping 19999 word types\n", - "2017-08-20 12:51:02,711 : INFO : PROGRESS: at sentence #900000, processed 14889435 words, keeping 19999 word types\n", - "2017-08-20 12:51:02,749 : INFO : PROGRESS: at sentence #910000, processed 15054677 words, keeping 19999 word types\n", - "2017-08-20 12:51:02,788 : INFO : PROGRESS: at sentence #920000, processed 15221359 words, keeping 19999 word types\n", - "2017-08-20 12:51:02,825 : INFO : PROGRESS: at sentence #930000, processed 15388324 words, keeping 19999 word types\n", - "2017-08-20 12:51:02,862 : INFO : PROGRESS: at sentence #940000, processed 15554206 words, keeping 19999 word types\n", - "2017-08-20 12:51:02,898 : INFO : PROGRESS: at sentence #950000, processed 15718324 words, keeping 19999 word types\n", - "2017-08-20 12:51:02,936 : INFO : PROGRESS: at sentence #960000, processed 15885101 words, keeping 19999 word types\n", - "2017-08-20 12:51:02,975 : INFO : PROGRESS: at sentence #970000, processed 16052909 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,014 : INFO : PROGRESS: at sentence #980000, processed 16222802 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,050 : INFO : PROGRESS: at sentence #990000, processed 16384991 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,087 : INFO : PROGRESS: at sentence #1000000, processed 16548292 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,124 : INFO : PROGRESS: at sentence #1010000, processed 16712862 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,163 : INFO : PROGRESS: at sentence #1020000, processed 16879459 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,200 : INFO : PROGRESS: at sentence #1030000, processed 17043081 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,238 : INFO : PROGRESS: at sentence #1040000, processed 17208831 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,275 : INFO : PROGRESS: at sentence #1050000, processed 17372311 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,311 : INFO : PROGRESS: at sentence #1060000, processed 17538886 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,351 : INFO : PROGRESS: at sentence #1070000, processed 17706900 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,388 : INFO : PROGRESS: at sentence #1080000, processed 17871431 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,425 : INFO : PROGRESS: at sentence #1090000, processed 18037110 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,461 : INFO : PROGRESS: at sentence #1100000, processed 18200853 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,497 : INFO : PROGRESS: at sentence #1110000, processed 18364042 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,536 : INFO : PROGRESS: at sentence #1120000, processed 18529719 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,574 : INFO : PROGRESS: at sentence #1130000, processed 18695422 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,611 : INFO : PROGRESS: at sentence #1140000, processed 18861655 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,648 : INFO : PROGRESS: at sentence #1150000, processed 19026666 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,685 : INFO : PROGRESS: at sentence #1160000, processed 19188379 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,722 : INFO : PROGRESS: at sentence #1170000, processed 19355054 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,764 : INFO : PROGRESS: at sentence #1180000, processed 19515495 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,812 : INFO : PROGRESS: at sentence #1190000, processed 19681112 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,850 : INFO : PROGRESS: at sentence #1200000, processed 19846785 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,886 : INFO : PROGRESS: at sentence #1210000, processed 20007314 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,924 : INFO : PROGRESS: at sentence #1220000, processed 20171540 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,962 : INFO : PROGRESS: at sentence #1230000, processed 20335054 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,001 : INFO : PROGRESS: at sentence #1240000, processed 20497983 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,038 : INFO : PROGRESS: at sentence #1250000, processed 20661568 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,075 : INFO : PROGRESS: at sentence #1260000, processed 20827547 words, keeping 19999 word types\n", - "2017-08-20 12:51:03,985 : INFO : PROGRESS: at sentence #1270000, processed 20991590 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,022 : INFO : PROGRESS: at sentence #1280000, processed 21155380 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,060 : INFO : PROGRESS: at sentence #1290000, processed 21323003 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,096 : INFO : PROGRESS: at sentence #1300000, processed 21487306 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,133 : INFO : PROGRESS: at sentence #1310000, processed 21651848 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,170 : INFO : PROGRESS: at sentence #1320000, processed 21817404 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,207 : INFO : PROGRESS: at sentence #1330000, processed 21982248 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,243 : INFO : PROGRESS: at sentence #1340000, processed 22146496 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,281 : INFO : PROGRESS: at sentence #1350000, processed 22312297 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,316 : INFO : PROGRESS: at sentence #1360000, processed 22477011 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,352 : INFO : PROGRESS: at sentence #1370000, processed 22640150 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,390 : INFO : PROGRESS: at sentence #1380000, processed 22804896 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,425 : INFO : PROGRESS: at sentence #1390000, processed 22967092 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,462 : INFO : PROGRESS: at sentence #1400000, processed 23132920 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,498 : INFO : PROGRESS: at sentence #1410000, processed 23296160 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,535 : INFO : PROGRESS: at sentence #1420000, processed 23460311 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,572 : INFO : PROGRESS: at sentence #1430000, processed 23623621 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,608 : INFO : PROGRESS: at sentence #1440000, processed 23786051 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,646 : INFO : PROGRESS: at sentence #1450000, processed 23954244 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,682 : INFO : PROGRESS: at sentence #1460000, processed 24116274 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,718 : INFO : PROGRESS: at sentence #1470000, processed 24281586 words, keeping 19999 word types\n", - "2017-08-20 12:51:04,755 : INFO : PROGRESS: at sentence #1480000, processed 24447707 words, keeping 20000 word types\n", - "2017-08-20 12:51:04,792 : INFO : PROGRESS: at sentence #1490000, processed 24611050 words, keeping 20000 word types\n", - "2017-08-20 12:51:04,829 : INFO : PROGRESS: at sentence #1500000, processed 24777752 words, keeping 20000 word types\n", - "2017-08-20 12:51:04,865 : INFO : PROGRESS: at sentence #1510000, processed 24938761 words, keeping 20000 word types\n", - "2017-08-20 12:51:04,910 : INFO : PROGRESS: at sentence #1520000, processed 25103523 words, keeping 20000 word types\n", - "2017-08-20 12:51:04,957 : INFO : PROGRESS: at sentence #1530000, processed 25267941 words, keeping 20000 word types\n", - "2017-08-20 12:51:04,996 : INFO : PROGRESS: at sentence #1540000, processed 25432487 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,034 : INFO : PROGRESS: at sentence #1550000, processed 25596348 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,074 : INFO : PROGRESS: at sentence #1560000, processed 25760331 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,114 : INFO : PROGRESS: at sentence #1570000, processed 25928914 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,157 : INFO : PROGRESS: at sentence #1580000, processed 26094106 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,195 : INFO : PROGRESS: at sentence #1590000, processed 26256622 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,233 : INFO : PROGRESS: at sentence #1600000, processed 26421402 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,272 : INFO : PROGRESS: at sentence #1610000, processed 26589540 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,325 : INFO : PROGRESS: at sentence #1620000, processed 26750558 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,364 : INFO : PROGRESS: at sentence #1630000, processed 26915451 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,402 : INFO : PROGRESS: at sentence #1640000, processed 27078649 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,440 : INFO : PROGRESS: at sentence #1650000, processed 27242718 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,480 : INFO : PROGRESS: at sentence #1660000, processed 27405246 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,528 : INFO : PROGRESS: at sentence #1670000, processed 27569190 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,567 : INFO : PROGRESS: at sentence #1680000, processed 27735204 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,606 : INFO : PROGRESS: at sentence #1690000, processed 27898649 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,645 : INFO : PROGRESS: at sentence #1700000, processed 28061303 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,707 : INFO : PROGRESS: at sentence #1710000, processed 28218538 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,747 : INFO : PROGRESS: at sentence #1720000, processed 28381193 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,786 : INFO : PROGRESS: at sentence #1730000, processed 28547522 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,826 : INFO : PROGRESS: at sentence #1740000, processed 28715810 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,865 : INFO : PROGRESS: at sentence #1750000, processed 28881533 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,904 : INFO : PROGRESS: at sentence #1760000, processed 29047648 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,944 : INFO : PROGRESS: at sentence #1770000, processed 29209459 words, keeping 20000 word types\n", - "2017-08-20 12:51:05,984 : INFO : PROGRESS: at sentence #1780000, processed 29373575 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,021 : INFO : PROGRESS: at sentence #1790000, processed 29536077 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,060 : INFO : PROGRESS: at sentence #1800000, processed 29698161 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,110 : INFO : PROGRESS: at sentence #1810000, processed 29861186 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,150 : INFO : PROGRESS: at sentence #1820000, processed 30030311 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,189 : INFO : PROGRESS: at sentence #1830000, processed 30193508 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,226 : INFO : PROGRESS: at sentence #1840000, processed 30357869 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,264 : INFO : PROGRESS: at sentence #1850000, processed 30525687 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,302 : INFO : PROGRESS: at sentence #1860000, processed 30689484 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,341 : INFO : PROGRESS: at sentence #1870000, processed 30854631 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,379 : INFO : PROGRESS: at sentence #1880000, processed 31023767 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,416 : INFO : PROGRESS: at sentence #1890000, processed 31190499 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,454 : INFO : PROGRESS: at sentence #1900000, processed 31356871 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,492 : INFO : PROGRESS: at sentence #1910000, processed 31523082 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,529 : INFO : PROGRESS: at sentence #1920000, processed 31687963 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,567 : INFO : PROGRESS: at sentence #1930000, processed 31854031 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,605 : INFO : PROGRESS: at sentence #1940000, processed 32018178 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,643 : INFO : PROGRESS: at sentence #1950000, processed 32182196 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,680 : INFO : PROGRESS: at sentence #1960000, processed 32344528 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,718 : INFO : PROGRESS: at sentence #1970000, processed 32507127 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,756 : INFO : PROGRESS: at sentence #1980000, processed 32672249 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,793 : INFO : PROGRESS: at sentence #1990000, processed 32834849 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,831 : INFO : PROGRESS: at sentence #2000000, processed 32999205 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,871 : INFO : PROGRESS: at sentence #2010000, processed 33168583 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,910 : INFO : PROGRESS: at sentence #2020000, processed 33335543 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,947 : INFO : PROGRESS: at sentence #2030000, processed 33502051 words, keeping 20000 word types\n", - "2017-08-20 12:51:06,986 : INFO : PROGRESS: at sentence #2040000, processed 33666508 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,023 : INFO : PROGRESS: at sentence #2050000, processed 33827699 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,061 : INFO : PROGRESS: at sentence #2060000, processed 33993593 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,100 : INFO : PROGRESS: at sentence #2070000, processed 34157185 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,138 : INFO : PROGRESS: at sentence #2080000, processed 34322108 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,175 : INFO : PROGRESS: at sentence #2090000, processed 34484855 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,218 : INFO : PROGRESS: at sentence #2100000, processed 34651101 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,262 : INFO : PROGRESS: at sentence #2110000, processed 34819441 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,299 : INFO : PROGRESS: at sentence #2120000, processed 34983933 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,337 : INFO : PROGRESS: at sentence #2130000, processed 35151114 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,374 : INFO : PROGRESS: at sentence #2140000, processed 35314999 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,413 : INFO : PROGRESS: at sentence #2150000, processed 35479694 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,450 : INFO : PROGRESS: at sentence #2160000, processed 35642896 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,489 : INFO : PROGRESS: at sentence #2170000, processed 35809606 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,528 : INFO : PROGRESS: at sentence #2180000, processed 35975970 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,565 : INFO : PROGRESS: at sentence #2190000, processed 36141810 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,604 : INFO : PROGRESS: at sentence #2200000, processed 36314797 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,655 : INFO : PROGRESS: at sentence #2210000, processed 36482555 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,692 : INFO : PROGRESS: at sentence #2220000, processed 36646131 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,730 : INFO : PROGRESS: at sentence #2230000, processed 36811317 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,767 : INFO : PROGRESS: at sentence #2240000, processed 36975389 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,805 : INFO : PROGRESS: at sentence #2250000, processed 37139914 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,843 : INFO : PROGRESS: at sentence #2260000, processed 37300601 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,882 : INFO : PROGRESS: at sentence #2270000, processed 37467915 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,918 : INFO : PROGRESS: at sentence #2280000, processed 37631862 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,956 : INFO : PROGRESS: at sentence #2290000, processed 37799423 words, keeping 20000 word types\n", - "2017-08-20 12:51:07,994 : INFO : PROGRESS: at sentence #2300000, processed 37966414 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,034 : INFO : PROGRESS: at sentence #2310000, processed 38132120 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,072 : INFO : PROGRESS: at sentence #2320000, processed 38296000 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,110 : INFO : PROGRESS: at sentence #2330000, processed 38463205 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,146 : INFO : PROGRESS: at sentence #2340000, processed 38624878 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,184 : INFO : PROGRESS: at sentence #2350000, processed 38790253 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,224 : INFO : PROGRESS: at sentence #2360000, processed 38954606 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,264 : INFO : PROGRESS: at sentence #2370000, processed 39118694 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,302 : INFO : PROGRESS: at sentence #2380000, processed 39282718 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,340 : INFO : PROGRESS: at sentence #2390000, processed 39449865 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,378 : INFO : PROGRESS: at sentence #2400000, processed 39617441 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,419 : INFO : PROGRESS: at sentence #2410000, processed 39782408 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,457 : INFO : PROGRESS: at sentence #2420000, processed 39947953 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,495 : INFO : PROGRESS: at sentence #2430000, processed 40112020 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,533 : INFO : PROGRESS: at sentence #2440000, processed 40275868 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,571 : INFO : PROGRESS: at sentence #2450000, processed 40439898 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,624 : INFO : PROGRESS: at sentence #2460000, processed 40605149 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,667 : INFO : PROGRESS: at sentence #2470000, processed 40770079 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,705 : INFO : PROGRESS: at sentence #2480000, processed 40934075 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,746 : INFO : PROGRESS: at sentence #2490000, processed 41097005 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,808 : INFO : PROGRESS: at sentence #2500000, processed 41270037 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,846 : INFO : PROGRESS: at sentence #2510000, processed 41430623 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,883 : INFO : PROGRESS: at sentence #2520000, processed 41597136 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,920 : INFO : PROGRESS: at sentence #2530000, processed 41761498 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,960 : INFO : PROGRESS: at sentence #2540000, processed 41924364 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,998 : INFO : PROGRESS: at sentence #2550000, processed 42090333 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,036 : INFO : PROGRESS: at sentence #2560000, processed 42252482 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,074 : INFO : PROGRESS: at sentence #2570000, processed 42419158 words, keeping 20000 word types\n", - "2017-08-20 12:51:08,983 : INFO : PROGRESS: at sentence #2580000, processed 42585765 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,019 : INFO : PROGRESS: at sentence #2590000, processed 42751808 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,057 : INFO : PROGRESS: at sentence #2600000, processed 42919469 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,096 : INFO : PROGRESS: at sentence #2610000, processed 43086219 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,136 : INFO : PROGRESS: at sentence #2620000, processed 43250683 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,173 : INFO : PROGRESS: at sentence #2630000, processed 43417011 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,209 : INFO : PROGRESS: at sentence #2640000, processed 43580028 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,247 : INFO : PROGRESS: at sentence #2650000, processed 43742541 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,284 : INFO : PROGRESS: at sentence #2660000, processed 43907783 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,322 : INFO : PROGRESS: at sentence #2670000, processed 44073464 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,359 : INFO : PROGRESS: at sentence #2680000, processed 44238399 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,395 : INFO : PROGRESS: at sentence #2690000, processed 44405415 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,432 : INFO : PROGRESS: at sentence #2700000, processed 44570883 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,468 : INFO : PROGRESS: at sentence #2710000, processed 44732084 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,504 : INFO : PROGRESS: at sentence #2720000, processed 44895311 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,542 : INFO : PROGRESS: at sentence #2730000, processed 45061768 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,578 : INFO : PROGRESS: at sentence #2740000, processed 45227170 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,614 : INFO : PROGRESS: at sentence #2750000, processed 45389437 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,650 : INFO : PROGRESS: at sentence #2760000, processed 45556537 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,687 : INFO : PROGRESS: at sentence #2770000, processed 45724295 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,725 : INFO : PROGRESS: at sentence #2780000, processed 45892058 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,762 : INFO : PROGRESS: at sentence #2790000, processed 46059531 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,798 : INFO : PROGRESS: at sentence #2800000, processed 46224158 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,835 : INFO : PROGRESS: at sentence #2810000, processed 46389191 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,871 : INFO : PROGRESS: at sentence #2820000, processed 46555569 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,908 : INFO : PROGRESS: at sentence #2830000, processed 46718538 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,945 : INFO : PROGRESS: at sentence #2840000, processed 46882227 words, keeping 20000 word types\n", - "2017-08-20 12:51:09,981 : INFO : PROGRESS: at sentence #2850000, processed 47042890 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,017 : INFO : PROGRESS: at sentence #2860000, processed 47205940 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,055 : INFO : PROGRESS: at sentence #2870000, processed 47368749 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,092 : INFO : PROGRESS: at sentence #2880000, processed 47532441 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,131 : INFO : PROGRESS: at sentence #2890000, processed 47699181 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,173 : INFO : PROGRESS: at sentence #2900000, processed 47863282 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,211 : INFO : PROGRESS: at sentence #2910000, processed 48033542 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,249 : INFO : PROGRESS: at sentence #2920000, processed 48199516 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,288 : INFO : PROGRESS: at sentence #2930000, processed 48366710 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,328 : INFO : PROGRESS: at sentence #2940000, processed 48530905 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,367 : INFO : PROGRESS: at sentence #2950000, processed 48696779 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,405 : INFO : PROGRESS: at sentence #2960000, processed 48864376 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,443 : INFO : PROGRESS: at sentence #2970000, processed 49030024 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,481 : INFO : PROGRESS: at sentence #2980000, processed 49197892 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,521 : INFO : PROGRESS: at sentence #2990000, processed 49363537 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,559 : INFO : PROGRESS: at sentence #3000000, processed 49527718 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,597 : INFO : PROGRESS: at sentence #3010000, processed 49692793 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,636 : INFO : PROGRESS: at sentence #3020000, processed 49854781 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,676 : INFO : PROGRESS: at sentence #3030000, processed 50020443 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,716 : INFO : PROGRESS: at sentence #3040000, processed 50186627 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,759 : INFO : PROGRESS: at sentence #3050000, processed 50350028 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,798 : INFO : PROGRESS: at sentence #3060000, processed 50514122 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,837 : INFO : PROGRESS: at sentence #3070000, processed 50681118 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,877 : INFO : PROGRESS: at sentence #3080000, processed 50844557 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,916 : INFO : PROGRESS: at sentence #3090000, processed 51010608 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,957 : INFO : PROGRESS: at sentence #3100000, processed 51176649 words, keeping 20000 word types\n", - "2017-08-20 12:51:10,995 : INFO : PROGRESS: at sentence #3110000, processed 51341479 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,032 : INFO : PROGRESS: at sentence #3120000, processed 51505603 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,069 : INFO : PROGRESS: at sentence #3130000, processed 51668590 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,106 : INFO : PROGRESS: at sentence #3140000, processed 51831975 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,145 : INFO : PROGRESS: at sentence #3150000, processed 51997948 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,188 : INFO : PROGRESS: at sentence #3160000, processed 52163961 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,227 : INFO : PROGRESS: at sentence #3170000, processed 52331376 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,265 : INFO : PROGRESS: at sentence #3180000, processed 52495239 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,303 : INFO : PROGRESS: at sentence #3190000, processed 52659321 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,343 : INFO : PROGRESS: at sentence #3200000, processed 52829147 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,383 : INFO : PROGRESS: at sentence #3210000, processed 52994327 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,421 : INFO : PROGRESS: at sentence #3220000, processed 53159376 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,462 : INFO : PROGRESS: at sentence #3230000, processed 53326110 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,504 : INFO : PROGRESS: at sentence #3240000, processed 53492480 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,545 : INFO : PROGRESS: at sentence #3250000, processed 53658333 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,590 : INFO : PROGRESS: at sentence #3260000, processed 53824309 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,631 : INFO : PROGRESS: at sentence #3270000, processed 53990078 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,672 : INFO : PROGRESS: at sentence #3280000, processed 54154779 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,711 : INFO : PROGRESS: at sentence #3290000, processed 54318352 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,751 : INFO : PROGRESS: at sentence #3300000, processed 54482133 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,791 : INFO : PROGRESS: at sentence #3310000, processed 54648753 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,831 : INFO : PROGRESS: at sentence #3320000, processed 54814553 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,870 : INFO : PROGRESS: at sentence #3330000, processed 54979257 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,908 : INFO : PROGRESS: at sentence #3340000, processed 55139069 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,947 : INFO : PROGRESS: at sentence #3350000, processed 55303364 words, keeping 20000 word types\n", - "2017-08-20 12:51:11,987 : INFO : PROGRESS: at sentence #3360000, processed 55470803 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,027 : INFO : PROGRESS: at sentence #3370000, processed 55632669 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,067 : INFO : PROGRESS: at sentence #3380000, processed 55799946 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,105 : INFO : PROGRESS: at sentence #3390000, processed 55961870 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,145 : INFO : PROGRESS: at sentence #3400000, processed 56132142 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,183 : INFO : PROGRESS: at sentence #3410000, processed 56294626 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,226 : INFO : PROGRESS: at sentence #3420000, processed 56457667 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,264 : INFO : PROGRESS: at sentence #3430000, processed 56621137 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,303 : INFO : PROGRESS: at sentence #3440000, processed 56786338 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,341 : INFO : PROGRESS: at sentence #3450000, processed 56949107 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,380 : INFO : PROGRESS: at sentence #3460000, processed 57112968 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,420 : INFO : PROGRESS: at sentence #3470000, processed 57277181 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,459 : INFO : PROGRESS: at sentence #3480000, processed 57441890 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,497 : INFO : PROGRESS: at sentence #3490000, processed 57605456 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,535 : INFO : PROGRESS: at sentence #3500000, processed 57770669 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,573 : INFO : PROGRESS: at sentence #3510000, processed 57935029 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,614 : INFO : PROGRESS: at sentence #3520000, processed 58102105 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,652 : INFO : PROGRESS: at sentence #3530000, processed 58265599 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,691 : INFO : PROGRESS: at sentence #3540000, processed 58433306 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,729 : INFO : PROGRESS: at sentence #3550000, processed 58598485 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,765 : INFO : PROGRESS: at sentence #3560000, processed 58756391 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,804 : INFO : PROGRESS: at sentence #3570000, processed 58923644 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,843 : INFO : PROGRESS: at sentence #3580000, processed 59089614 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,880 : INFO : PROGRESS: at sentence #3590000, processed 59254748 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,918 : INFO : PROGRESS: at sentence #3600000, processed 59421315 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,955 : INFO : PROGRESS: at sentence #3610000, processed 59587934 words, keeping 20000 word types\n", - "2017-08-20 12:51:12,993 : INFO : PROGRESS: at sentence #3620000, processed 59754178 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,032 : INFO : PROGRESS: at sentence #3630000, processed 59919224 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,070 : INFO : PROGRESS: at sentence #3640000, processed 60087238 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,107 : INFO : PROGRESS: at sentence #3650000, processed 60251638 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,144 : INFO : PROGRESS: at sentence #3660000, processed 60417612 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,181 : INFO : PROGRESS: at sentence #3670000, processed 60581175 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,219 : INFO : PROGRESS: at sentence #3680000, processed 60743500 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,261 : INFO : PROGRESS: at sentence #3690000, processed 60907775 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,298 : INFO : PROGRESS: at sentence #3700000, processed 61073515 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,335 : INFO : PROGRESS: at sentence #3710000, processed 61236899 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,372 : INFO : PROGRESS: at sentence #3720000, processed 61402100 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,410 : INFO : PROGRESS: at sentence #3730000, processed 61569383 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,449 : INFO : PROGRESS: at sentence #3740000, processed 61734848 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,487 : INFO : PROGRESS: at sentence #3750000, processed 61902761 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,524 : INFO : PROGRESS: at sentence #3760000, processed 62065833 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,560 : INFO : PROGRESS: at sentence #3770000, processed 62228339 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,598 : INFO : PROGRESS: at sentence #3780000, processed 62391449 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,635 : INFO : PROGRESS: at sentence #3790000, processed 62554113 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,674 : INFO : PROGRESS: at sentence #3800000, processed 62716600 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,711 : INFO : PROGRESS: at sentence #3810000, processed 62881448 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,748 : INFO : PROGRESS: at sentence #3820000, processed 63047322 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,786 : INFO : PROGRESS: at sentence #3830000, processed 63209865 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,822 : INFO : PROGRESS: at sentence #3840000, processed 63374567 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,862 : INFO : PROGRESS: at sentence #3850000, processed 63541175 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,900 : INFO : PROGRESS: at sentence #3860000, processed 63707433 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,938 : INFO : PROGRESS: at sentence #3870000, processed 63873624 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,976 : INFO : PROGRESS: at sentence #3880000, processed 64042916 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,013 : INFO : PROGRESS: at sentence #3890000, processed 64211038 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,051 : INFO : PROGRESS: at sentence #3900000, processed 64375801 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,089 : INFO : PROGRESS: at sentence #3910000, processed 64537956 words, keeping 20000 word types\n", - "2017-08-20 12:51:13,997 : INFO : PROGRESS: at sentence #3920000, processed 64699936 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,034 : INFO : PROGRESS: at sentence #3930000, processed 64864615 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,071 : INFO : PROGRESS: at sentence #3940000, processed 65027181 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,107 : INFO : PROGRESS: at sentence #3950000, processed 65192608 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,149 : INFO : PROGRESS: at sentence #3960000, processed 65357428 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,186 : INFO : PROGRESS: at sentence #3970000, processed 65522925 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,222 : INFO : PROGRESS: at sentence #3980000, processed 65688876 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,257 : INFO : PROGRESS: at sentence #3990000, processed 65848445 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,293 : INFO : PROGRESS: at sentence #4000000, processed 66009390 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,332 : INFO : PROGRESS: at sentence #4010000, processed 66172977 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,369 : INFO : PROGRESS: at sentence #4020000, processed 66339939 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,406 : INFO : PROGRESS: at sentence #4030000, processed 66506663 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,443 : INFO : PROGRESS: at sentence #4040000, processed 66672025 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,478 : INFO : PROGRESS: at sentence #4050000, processed 66832769 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,517 : INFO : PROGRESS: at sentence #4060000, processed 66996948 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,554 : INFO : PROGRESS: at sentence #4070000, processed 67163052 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,591 : INFO : PROGRESS: at sentence #4080000, processed 67329915 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,628 : INFO : PROGRESS: at sentence #4090000, processed 67495274 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,665 : INFO : PROGRESS: at sentence #4100000, processed 67662848 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,701 : INFO : PROGRESS: at sentence #4110000, processed 67826619 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,741 : INFO : PROGRESS: at sentence #4120000, processed 67994609 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,779 : INFO : PROGRESS: at sentence #4130000, processed 68161496 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,816 : INFO : PROGRESS: at sentence #4140000, processed 68333755 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,853 : INFO : PROGRESS: at sentence #4150000, processed 68496259 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,889 : INFO : PROGRESS: at sentence #4160000, processed 68660379 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,926 : INFO : PROGRESS: at sentence #4170000, processed 68822740 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,963 : INFO : PROGRESS: at sentence #4180000, processed 68986993 words, keeping 20000 word types\n", - "2017-08-20 12:51:14,999 : INFO : PROGRESS: at sentence #4190000, processed 69149041 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,036 : INFO : PROGRESS: at sentence #4200000, processed 69312324 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,075 : INFO : PROGRESS: at sentence #4210000, processed 69479900 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,113 : INFO : PROGRESS: at sentence #4220000, processed 69647053 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,161 : INFO : PROGRESS: at sentence #4230000, processed 69813395 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,199 : INFO : PROGRESS: at sentence #4240000, processed 69977540 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,236 : INFO : PROGRESS: at sentence #4250000, processed 70144125 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,274 : INFO : PROGRESS: at sentence #4260000, processed 70308012 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,312 : INFO : PROGRESS: at sentence #4270000, processed 70470080 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,353 : INFO : PROGRESS: at sentence #4280000, processed 70635388 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,390 : INFO : PROGRESS: at sentence #4290000, processed 70798387 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,427 : INFO : PROGRESS: at sentence #4300000, processed 70961349 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,464 : INFO : PROGRESS: at sentence #4310000, processed 71124416 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,503 : INFO : PROGRESS: at sentence #4320000, processed 71293426 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,542 : INFO : PROGRESS: at sentence #4330000, processed 71457932 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,582 : INFO : PROGRESS: at sentence #4340000, processed 71625652 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,619 : INFO : PROGRESS: at sentence #4350000, processed 71788386 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,657 : INFO : PROGRESS: at sentence #4360000, processed 71952742 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,695 : INFO : PROGRESS: at sentence #4370000, processed 72119429 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,731 : INFO : PROGRESS: at sentence #4380000, processed 72278982 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,772 : INFO : PROGRESS: at sentence #4390000, processed 72444773 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,811 : INFO : PROGRESS: at sentence #4400000, processed 72610608 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,848 : INFO : PROGRESS: at sentence #4410000, processed 72776660 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,886 : INFO : PROGRESS: at sentence #4420000, processed 72943109 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,924 : INFO : PROGRESS: at sentence #4430000, processed 73110524 words, keeping 20000 word types\n", - "2017-08-20 12:51:15,964 : INFO : PROGRESS: at sentence #4440000, processed 73276881 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,002 : INFO : PROGRESS: at sentence #4450000, processed 73440365 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,039 : INFO : PROGRESS: at sentence #4460000, processed 73604659 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,077 : INFO : PROGRESS: at sentence #4470000, processed 73769085 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,115 : INFO : PROGRESS: at sentence #4480000, processed 73934623 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,152 : INFO : PROGRESS: at sentence #4490000, processed 74099141 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,193 : INFO : PROGRESS: at sentence #4500000, processed 74264515 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,233 : INFO : PROGRESS: at sentence #4510000, processed 74433524 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,271 : INFO : PROGRESS: at sentence #4520000, processed 74602242 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,309 : INFO : PROGRESS: at sentence #4530000, processed 74770524 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,347 : INFO : PROGRESS: at sentence #4540000, processed 74933229 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,385 : INFO : PROGRESS: at sentence #4550000, processed 75098737 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,423 : INFO : PROGRESS: at sentence #4560000, processed 75265166 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,460 : INFO : PROGRESS: at sentence #4570000, processed 75426360 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,498 : INFO : PROGRESS: at sentence #4580000, processed 75591956 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,535 : INFO : PROGRESS: at sentence #4590000, processed 75754436 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,573 : INFO : PROGRESS: at sentence #4600000, processed 75919498 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,613 : INFO : PROGRESS: at sentence #4610000, processed 76087344 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,650 : INFO : PROGRESS: at sentence #4620000, processed 76251088 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,688 : INFO : PROGRESS: at sentence #4630000, processed 76411734 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,726 : INFO : PROGRESS: at sentence #4640000, processed 76578958 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,763 : INFO : PROGRESS: at sentence #4650000, processed 76741637 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,802 : INFO : PROGRESS: at sentence #4660000, processed 76907193 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,842 : INFO : PROGRESS: at sentence #4670000, processed 77074386 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,878 : INFO : PROGRESS: at sentence #4680000, processed 77232112 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,917 : INFO : PROGRESS: at sentence #4690000, processed 77398599 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,955 : INFO : PROGRESS: at sentence #4700000, processed 77565103 words, keeping 20000 word types\n", - "2017-08-20 12:51:16,994 : INFO : PROGRESS: at sentence #4710000, processed 77730978 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,033 : INFO : PROGRESS: at sentence #4720000, processed 77896686 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,070 : INFO : PROGRESS: at sentence #4730000, processed 78061908 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,109 : INFO : PROGRESS: at sentence #4740000, processed 78229996 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,147 : INFO : PROGRESS: at sentence #4750000, processed 78396082 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,184 : INFO : PROGRESS: at sentence #4760000, processed 78559668 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,226 : INFO : PROGRESS: at sentence #4770000, processed 78728648 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,269 : INFO : PROGRESS: at sentence #4780000, processed 78895381 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,306 : INFO : PROGRESS: at sentence #4790000, processed 79062845 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,344 : INFO : PROGRESS: at sentence #4800000, processed 79229449 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,382 : INFO : PROGRESS: at sentence #4810000, processed 79397005 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,420 : INFO : PROGRESS: at sentence #4820000, processed 79560913 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,458 : INFO : PROGRESS: at sentence #4830000, processed 79723291 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,495 : INFO : PROGRESS: at sentence #4840000, processed 79887385 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,533 : INFO : PROGRESS: at sentence #4850000, processed 80053050 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,570 : INFO : PROGRESS: at sentence #4860000, processed 80218156 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,609 : INFO : PROGRESS: at sentence #4870000, processed 80386004 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,649 : INFO : PROGRESS: at sentence #4880000, processed 80548295 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,688 : INFO : PROGRESS: at sentence #4890000, processed 80714161 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,727 : INFO : PROGRESS: at sentence #4900000, processed 80881129 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,765 : INFO : PROGRESS: at sentence #4910000, processed 81044529 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,803 : INFO : PROGRESS: at sentence #4920000, processed 81210207 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,841 : INFO : PROGRESS: at sentence #4930000, processed 81370670 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,880 : INFO : PROGRESS: at sentence #4940000, processed 81536667 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,917 : INFO : PROGRESS: at sentence #4950000, processed 81698503 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,954 : INFO : PROGRESS: at sentence #4960000, processed 81861586 words, keeping 20000 word types\n", - "2017-08-20 12:51:17,993 : INFO : PROGRESS: at sentence #4970000, processed 82030331 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,032 : INFO : PROGRESS: at sentence #4980000, processed 82196528 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,071 : INFO : PROGRESS: at sentence #4990000, processed 82361569 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,109 : INFO : PROGRESS: at sentence #5000000, processed 82525914 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,148 : INFO : PROGRESS: at sentence #5010000, processed 82686673 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,188 : INFO : PROGRESS: at sentence #5020000, processed 82852670 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,226 : INFO : PROGRESS: at sentence #5030000, processed 83015310 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,272 : INFO : PROGRESS: at sentence #5040000, processed 83181876 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,311 : INFO : PROGRESS: at sentence #5050000, processed 83349596 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,353 : INFO : PROGRESS: at sentence #5060000, processed 83515109 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,392 : INFO : PROGRESS: at sentence #5070000, processed 83681567 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,431 : INFO : PROGRESS: at sentence #5080000, processed 83845717 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,472 : INFO : PROGRESS: at sentence #5090000, processed 84014393 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,512 : INFO : PROGRESS: at sentence #5100000, processed 84181433 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,551 : INFO : PROGRESS: at sentence #5110000, processed 84345817 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,589 : INFO : PROGRESS: at sentence #5120000, processed 84512266 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,628 : INFO : PROGRESS: at sentence #5130000, processed 84677444 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,668 : INFO : PROGRESS: at sentence #5140000, processed 84846175 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,707 : INFO : PROGRESS: at sentence #5150000, processed 85014699 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,746 : INFO : PROGRESS: at sentence #5160000, processed 85178253 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,785 : INFO : PROGRESS: at sentence #5170000, processed 85342509 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,824 : INFO : PROGRESS: at sentence #5180000, processed 85510101 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,862 : INFO : PROGRESS: at sentence #5190000, processed 85674633 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,902 : INFO : PROGRESS: at sentence #5200000, processed 85843370 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,939 : INFO : PROGRESS: at sentence #5210000, processed 86008980 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,976 : INFO : PROGRESS: at sentence #5220000, processed 86173472 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,014 : INFO : PROGRESS: at sentence #5230000, processed 86337885 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,051 : INFO : PROGRESS: at sentence #5240000, processed 86504541 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,090 : INFO : PROGRESS: at sentence #5250000, processed 86670714 words, keeping 20000 word types\n", - "2017-08-20 12:51:18,999 : INFO : PROGRESS: at sentence #5260000, processed 86837638 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,037 : INFO : PROGRESS: at sentence #5270000, processed 87004228 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,074 : INFO : PROGRESS: at sentence #5280000, processed 87169962 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,111 : INFO : PROGRESS: at sentence #5290000, processed 87339024 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,153 : INFO : PROGRESS: at sentence #5300000, processed 87508833 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,190 : INFO : PROGRESS: at sentence #5310000, processed 87674759 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,226 : INFO : PROGRESS: at sentence #5320000, processed 87840187 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,262 : INFO : PROGRESS: at sentence #5330000, processed 88002466 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,299 : INFO : PROGRESS: at sentence #5340000, processed 88168218 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,336 : INFO : PROGRESS: at sentence #5350000, processed 88333373 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,373 : INFO : PROGRESS: at sentence #5360000, processed 88497554 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,407 : INFO : PROGRESS: at sentence #5370000, processed 88646889 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,442 : INFO : PROGRESS: at sentence #5380000, processed 88807484 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,477 : INFO : PROGRESS: at sentence #5390000, processed 88963578 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,516 : INFO : PROGRESS: at sentence #5400000, processed 89137787 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,554 : INFO : PROGRESS: at sentence #5410000, processed 89301607 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,590 : INFO : PROGRESS: at sentence #5420000, processed 89463387 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,626 : INFO : PROGRESS: at sentence #5430000, processed 89628180 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,663 : INFO : PROGRESS: at sentence #5440000, processed 89793064 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,698 : INFO : PROGRESS: at sentence #5450000, processed 89952963 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,734 : INFO : PROGRESS: at sentence #5460000, processed 90115404 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,771 : INFO : PROGRESS: at sentence #5470000, processed 90279090 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,809 : INFO : PROGRESS: at sentence #5480000, processed 90446442 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,845 : INFO : PROGRESS: at sentence #5490000, processed 90612741 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,882 : INFO : PROGRESS: at sentence #5500000, processed 90780458 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,919 : INFO : PROGRESS: at sentence #5510000, processed 90945406 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,958 : INFO : PROGRESS: at sentence #5520000, processed 91116148 words, keeping 20000 word types\n", - "2017-08-20 12:51:19,994 : INFO : PROGRESS: at sentence #5530000, processed 91281768 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,032 : INFO : PROGRESS: at sentence #5540000, processed 91445145 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,072 : INFO : PROGRESS: at sentence #5550000, processed 91609963 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,110 : INFO : PROGRESS: at sentence #5560000, processed 91775608 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,153 : INFO : PROGRESS: at sentence #5570000, processed 91940678 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,191 : INFO : PROGRESS: at sentence #5580000, processed 92103095 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,229 : INFO : PROGRESS: at sentence #5590000, processed 92270556 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,266 : INFO : PROGRESS: at sentence #5600000, processed 92430742 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,304 : INFO : PROGRESS: at sentence #5610000, processed 92594794 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,342 : INFO : PROGRESS: at sentence #5620000, processed 92761932 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,380 : INFO : PROGRESS: at sentence #5630000, processed 92925742 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,418 : INFO : PROGRESS: at sentence #5640000, processed 93088577 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,456 : INFO : PROGRESS: at sentence #5650000, processed 93255544 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,494 : INFO : PROGRESS: at sentence #5660000, processed 93422405 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,532 : INFO : PROGRESS: at sentence #5670000, processed 93587556 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,572 : INFO : PROGRESS: at sentence #5680000, processed 93753757 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,610 : INFO : PROGRESS: at sentence #5690000, processed 93916737 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,647 : INFO : PROGRESS: at sentence #5700000, processed 94079584 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,685 : INFO : PROGRESS: at sentence #5710000, processed 94247023 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,723 : INFO : PROGRESS: at sentence #5720000, processed 94411228 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,760 : INFO : PROGRESS: at sentence #5730000, processed 94574397 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,799 : INFO : PROGRESS: at sentence #5740000, processed 94741781 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,836 : INFO : PROGRESS: at sentence #5750000, processed 94905873 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,875 : INFO : PROGRESS: at sentence #5760000, processed 95072235 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,914 : INFO : PROGRESS: at sentence #5770000, processed 95240072 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,951 : INFO : PROGRESS: at sentence #5780000, processed 95405983 words, keeping 20000 word types\n", - "2017-08-20 12:51:20,990 : INFO : PROGRESS: at sentence #5790000, processed 95573586 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,028 : INFO : PROGRESS: at sentence #5800000, processed 95735266 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,066 : INFO : PROGRESS: at sentence #5810000, processed 95901678 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,103 : INFO : PROGRESS: at sentence #5820000, processed 96063768 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,140 : INFO : PROGRESS: at sentence #5830000, processed 96225429 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,178 : INFO : PROGRESS: at sentence #5840000, processed 96390810 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,219 : INFO : PROGRESS: at sentence #5850000, processed 96553501 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,256 : INFO : PROGRESS: at sentence #5860000, processed 96714628 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,295 : INFO : PROGRESS: at sentence #5870000, processed 96882017 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,333 : INFO : PROGRESS: at sentence #5880000, processed 97046584 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,371 : INFO : PROGRESS: at sentence #5890000, processed 97209607 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,410 : INFO : PROGRESS: at sentence #5900000, processed 97373569 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,448 : INFO : PROGRESS: at sentence #5910000, processed 97536260 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,485 : INFO : PROGRESS: at sentence #5920000, processed 97702259 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,523 : INFO : PROGRESS: at sentence #5930000, processed 97867038 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,560 : INFO : PROGRESS: at sentence #5940000, processed 98029404 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,598 : INFO : PROGRESS: at sentence #5950000, processed 98194596 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,637 : INFO : PROGRESS: at sentence #5960000, processed 98358713 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,674 : INFO : PROGRESS: at sentence #5970000, processed 98521349 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,711 : INFO : PROGRESS: at sentence #5980000, processed 98683449 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,749 : INFO : PROGRESS: at sentence #5990000, processed 98850782 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,787 : INFO : PROGRESS: at sentence #6000000, processed 99017344 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,827 : INFO : PROGRESS: at sentence #6010000, processed 99186431 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,866 : INFO : PROGRESS: at sentence #6020000, processed 99352521 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,904 : INFO : PROGRESS: at sentence #6030000, processed 99517677 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,942 : INFO : PROGRESS: at sentence #6040000, processed 99684431 words, keeping 20000 word types\n", - "2017-08-20 12:51:21,981 : INFO : PROGRESS: at sentence #6050000, processed 99850295 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,019 : INFO : PROGRESS: at sentence #6060000, processed 100014106 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,056 : INFO : PROGRESS: at sentence #6070000, processed 100178270 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,094 : INFO : PROGRESS: at sentence #6080000, processed 100345703 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,132 : INFO : PROGRESS: at sentence #6090000, processed 100510946 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,169 : INFO : PROGRESS: at sentence #6100000, processed 100675742 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,207 : INFO : PROGRESS: at sentence #6110000, processed 100842332 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,249 : INFO : PROGRESS: at sentence #6120000, processed 101007917 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,285 : INFO : PROGRESS: at sentence #6130000, processed 101169809 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,323 : INFO : PROGRESS: at sentence #6140000, processed 101334014 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,360 : INFO : PROGRESS: at sentence #6150000, processed 101500296 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,398 : INFO : PROGRESS: at sentence #6160000, processed 101668372 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,436 : INFO : PROGRESS: at sentence #6170000, processed 101831196 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,474 : INFO : PROGRESS: at sentence #6180000, processed 101995625 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,511 : INFO : PROGRESS: at sentence #6190000, processed 102159576 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,549 : INFO : PROGRESS: at sentence #6200000, processed 102327005 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,586 : INFO : PROGRESS: at sentence #6210000, processed 102490684 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,624 : INFO : PROGRESS: at sentence #6220000, processed 102658684 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,663 : INFO : PROGRESS: at sentence #6230000, processed 102821537 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,700 : INFO : PROGRESS: at sentence #6240000, processed 102985869 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,738 : INFO : PROGRESS: at sentence #6250000, processed 103152388 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,775 : INFO : PROGRESS: at sentence #6260000, processed 103316773 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,813 : INFO : PROGRESS: at sentence #6270000, processed 103482272 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,851 : INFO : PROGRESS: at sentence #6280000, processed 103648177 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,889 : INFO : PROGRESS: at sentence #6290000, processed 103812250 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,926 : INFO : PROGRESS: at sentence #6300000, processed 103974547 words, keeping 20000 word types\n", - "2017-08-20 12:51:22,963 : INFO : PROGRESS: at sentence #6310000, processed 104137720 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,001 : INFO : PROGRESS: at sentence #6320000, processed 104303601 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,039 : INFO : PROGRESS: at sentence #6330000, processed 104474136 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,079 : INFO : PROGRESS: at sentence #6340000, processed 104640992 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,116 : INFO : PROGRESS: at sentence #6350000, processed 104808563 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,154 : INFO : PROGRESS: at sentence #6360000, processed 104975227 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,192 : INFO : PROGRESS: at sentence #6370000, processed 105140483 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,229 : INFO : PROGRESS: at sentence #6380000, processed 105303329 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,270 : INFO : PROGRESS: at sentence #6390000, processed 105467294 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,308 : INFO : PROGRESS: at sentence #6400000, processed 105631295 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,346 : INFO : PROGRESS: at sentence #6410000, processed 105796631 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,383 : INFO : PROGRESS: at sentence #6420000, processed 105960941 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,421 : INFO : PROGRESS: at sentence #6430000, processed 106127406 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,459 : INFO : PROGRESS: at sentence #6440000, processed 106291690 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,499 : INFO : PROGRESS: at sentence #6450000, processed 106456540 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,538 : INFO : PROGRESS: at sentence #6460000, processed 106621690 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,578 : INFO : PROGRESS: at sentence #6470000, processed 106785116 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,618 : INFO : PROGRESS: at sentence #6480000, processed 106953346 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,658 : INFO : PROGRESS: at sentence #6490000, processed 107118875 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,697 : INFO : PROGRESS: at sentence #6500000, processed 107281603 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,735 : INFO : PROGRESS: at sentence #6510000, processed 107446563 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,774 : INFO : PROGRESS: at sentence #6520000, processed 107612564 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,812 : INFO : PROGRESS: at sentence #6530000, processed 107777769 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,849 : INFO : PROGRESS: at sentence #6540000, processed 107941670 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,887 : INFO : PROGRESS: at sentence #6550000, processed 108105702 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,925 : INFO : PROGRESS: at sentence #6560000, processed 108272296 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,964 : INFO : PROGRESS: at sentence #6570000, processed 108438475 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,002 : INFO : PROGRESS: at sentence #6580000, processed 108603431 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,040 : INFO : PROGRESS: at sentence #6590000, processed 108767529 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,078 : INFO : PROGRESS: at sentence #6600000, processed 108933846 words, keeping 20000 word types\n", - "2017-08-20 12:51:23,989 : INFO : PROGRESS: at sentence #6610000, processed 109099318 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,026 : INFO : PROGRESS: at sentence #6620000, processed 109262962 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,062 : INFO : PROGRESS: at sentence #6630000, processed 109423678 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,098 : INFO : PROGRESS: at sentence #6640000, processed 109585659 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,136 : INFO : PROGRESS: at sentence #6650000, processed 109751485 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,179 : INFO : PROGRESS: at sentence #6660000, processed 109919941 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,216 : INFO : PROGRESS: at sentence #6670000, processed 110085349 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,253 : INFO : PROGRESS: at sentence #6680000, processed 110251154 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,291 : INFO : PROGRESS: at sentence #6690000, processed 110416686 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,329 : INFO : PROGRESS: at sentence #6700000, processed 110584323 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,368 : INFO : PROGRESS: at sentence #6710000, processed 110751529 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,406 : INFO : PROGRESS: at sentence #6720000, processed 110913286 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,444 : INFO : PROGRESS: at sentence #6730000, processed 111077592 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,482 : INFO : PROGRESS: at sentence #6740000, processed 111243177 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,520 : INFO : PROGRESS: at sentence #6750000, processed 111406762 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,559 : INFO : PROGRESS: at sentence #6760000, processed 111571729 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,600 : INFO : PROGRESS: at sentence #6770000, processed 111735090 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,638 : INFO : PROGRESS: at sentence #6780000, processed 111898542 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,675 : INFO : PROGRESS: at sentence #6790000, processed 112062867 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,712 : INFO : PROGRESS: at sentence #6800000, processed 112225955 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,752 : INFO : PROGRESS: at sentence #6810000, processed 112391053 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,792 : INFO : PROGRESS: at sentence #6820000, processed 112556850 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,830 : INFO : PROGRESS: at sentence #6830000, processed 112720209 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,867 : INFO : PROGRESS: at sentence #6840000, processed 112882691 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,905 : INFO : PROGRESS: at sentence #6850000, processed 113047362 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,942 : INFO : PROGRESS: at sentence #6860000, processed 113212477 words, keeping 20000 word types\n", - "2017-08-20 12:51:24,982 : INFO : PROGRESS: at sentence #6870000, processed 113381848 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,026 : INFO : PROGRESS: at sentence #6880000, processed 113546261 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,064 : INFO : PROGRESS: at sentence #6890000, processed 113709009 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,102 : INFO : PROGRESS: at sentence #6900000, processed 113870271 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,140 : INFO : PROGRESS: at sentence #6910000, processed 114036844 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,182 : INFO : PROGRESS: at sentence #6920000, processed 114201917 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,221 : INFO : PROGRESS: at sentence #6930000, processed 114368864 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,258 : INFO : PROGRESS: at sentence #6940000, processed 114529669 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,296 : INFO : PROGRESS: at sentence #6950000, processed 114695486 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,334 : INFO : PROGRESS: at sentence #6960000, processed 114860563 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,372 : INFO : PROGRESS: at sentence #6970000, processed 115025009 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,411 : INFO : PROGRESS: at sentence #6980000, processed 115188698 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,449 : INFO : PROGRESS: at sentence #6990000, processed 115353578 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,487 : INFO : PROGRESS: at sentence #7000000, processed 115517610 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,526 : INFO : PROGRESS: at sentence #7010000, processed 115680857 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,564 : INFO : PROGRESS: at sentence #7020000, processed 115844344 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,608 : INFO : PROGRESS: at sentence #7030000, processed 116009261 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,648 : INFO : PROGRESS: at sentence #7040000, processed 116175727 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,689 : INFO : PROGRESS: at sentence #7050000, processed 116339988 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,729 : INFO : PROGRESS: at sentence #7060000, processed 116506386 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,768 : INFO : PROGRESS: at sentence #7070000, processed 116673965 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,809 : INFO : PROGRESS: at sentence #7080000, processed 116838920 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,855 : INFO : PROGRESS: at sentence #7090000, processed 117001468 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,895 : INFO : PROGRESS: at sentence #7100000, processed 117165829 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,933 : INFO : PROGRESS: at sentence #7110000, processed 117327061 words, keeping 20000 word types\n", - "2017-08-20 12:51:25,971 : INFO : PROGRESS: at sentence #7120000, processed 117490285 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,010 : INFO : PROGRESS: at sentence #7130000, processed 117657557 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,049 : INFO : PROGRESS: at sentence #7140000, processed 117821134 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,088 : INFO : PROGRESS: at sentence #7150000, processed 117989961 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,125 : INFO : PROGRESS: at sentence #7160000, processed 118154526 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,162 : INFO : PROGRESS: at sentence #7170000, processed 118319609 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,205 : INFO : PROGRESS: at sentence #7180000, processed 118487374 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,244 : INFO : PROGRESS: at sentence #7190000, processed 118649135 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,281 : INFO : PROGRESS: at sentence #7200000, processed 118812629 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,319 : INFO : PROGRESS: at sentence #7210000, processed 118977046 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,357 : INFO : PROGRESS: at sentence #7220000, processed 119144655 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,395 : INFO : PROGRESS: at sentence #7230000, processed 119311038 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,435 : INFO : PROGRESS: at sentence #7240000, processed 119477103 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,473 : INFO : PROGRESS: at sentence #7250000, processed 119644124 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,512 : INFO : PROGRESS: at sentence #7260000, processed 119808893 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,551 : INFO : PROGRESS: at sentence #7270000, processed 119976564 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,592 : INFO : PROGRESS: at sentence #7280000, processed 120145230 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,633 : INFO : PROGRESS: at sentence #7290000, processed 120311288 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,672 : INFO : PROGRESS: at sentence #7300000, processed 120478547 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,712 : INFO : PROGRESS: at sentence #7310000, processed 120639460 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,751 : INFO : PROGRESS: at sentence #7320000, processed 120803700 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,789 : INFO : PROGRESS: at sentence #7330000, processed 120969232 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,828 : INFO : PROGRESS: at sentence #7340000, processed 121133535 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,867 : INFO : PROGRESS: at sentence #7350000, processed 121297173 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,904 : INFO : PROGRESS: at sentence #7360000, processed 121462597 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,942 : INFO : PROGRESS: at sentence #7370000, processed 121625230 words, keeping 20000 word types\n", - "2017-08-20 12:51:26,979 : INFO : PROGRESS: at sentence #7380000, processed 121789056 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,017 : INFO : PROGRESS: at sentence #7390000, processed 121955123 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,056 : INFO : PROGRESS: at sentence #7400000, processed 122124422 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,093 : INFO : PROGRESS: at sentence #7410000, processed 122288718 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,131 : INFO : PROGRESS: at sentence #7420000, processed 122454814 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,168 : INFO : PROGRESS: at sentence #7430000, processed 122617376 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,206 : INFO : PROGRESS: at sentence #7440000, processed 122783612 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,249 : INFO : PROGRESS: at sentence #7450000, processed 122950355 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,288 : INFO : PROGRESS: at sentence #7460000, processed 123117712 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,325 : INFO : PROGRESS: at sentence #7470000, processed 123279535 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,363 : INFO : PROGRESS: at sentence #7480000, processed 123445949 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,400 : INFO : PROGRESS: at sentence #7490000, processed 123609249 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,437 : INFO : PROGRESS: at sentence #7500000, processed 123773222 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,477 : INFO : PROGRESS: at sentence #7510000, processed 123938300 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,514 : INFO : PROGRESS: at sentence #7520000, processed 124102350 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,552 : INFO : PROGRESS: at sentence #7530000, processed 124265378 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,589 : INFO : PROGRESS: at sentence #7540000, processed 124429079 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,626 : INFO : PROGRESS: at sentence #7550000, processed 124595112 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,665 : INFO : PROGRESS: at sentence #7560000, processed 124761545 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,704 : INFO : PROGRESS: at sentence #7570000, processed 124926298 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,741 : INFO : PROGRESS: at sentence #7580000, processed 125090093 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,780 : INFO : PROGRESS: at sentence #7590000, processed 125255764 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,818 : INFO : PROGRESS: at sentence #7600000, processed 125420067 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,855 : INFO : PROGRESS: at sentence #7610000, processed 125583264 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,895 : INFO : PROGRESS: at sentence #7620000, processed 125750856 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,932 : INFO : PROGRESS: at sentence #7630000, processed 125911977 words, keeping 20000 word types\n", - "2017-08-20 12:51:27,971 : INFO : PROGRESS: at sentence #7640000, processed 126080131 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,007 : INFO : PROGRESS: at sentence #7650000, processed 126242319 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,044 : INFO : PROGRESS: at sentence #7660000, processed 126400608 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,081 : INFO : PROGRESS: at sentence #7670000, processed 126567630 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,120 : INFO : PROGRESS: at sentence #7680000, processed 126734546 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,158 : INFO : PROGRESS: at sentence #7690000, processed 126901975 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,195 : INFO : PROGRESS: at sentence #7700000, processed 127064248 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,232 : INFO : PROGRESS: at sentence #7710000, processed 127228793 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,275 : INFO : PROGRESS: at sentence #7720000, processed 127397553 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,314 : INFO : PROGRESS: at sentence #7730000, processed 127564810 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,350 : INFO : PROGRESS: at sentence #7740000, processed 127724344 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,388 : INFO : PROGRESS: at sentence #7750000, processed 127887264 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,425 : INFO : PROGRESS: at sentence #7760000, processed 128053319 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,462 : INFO : PROGRESS: at sentence #7770000, processed 128217978 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,501 : INFO : PROGRESS: at sentence #7780000, processed 128386890 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,539 : INFO : PROGRESS: at sentence #7790000, processed 128550734 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,577 : INFO : PROGRESS: at sentence #7800000, processed 128717737 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,614 : INFO : PROGRESS: at sentence #7810000, processed 128880603 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,651 : INFO : PROGRESS: at sentence #7820000, processed 129046375 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,688 : INFO : PROGRESS: at sentence #7830000, processed 129208390 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,728 : INFO : PROGRESS: at sentence #7840000, processed 129377087 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,764 : INFO : PROGRESS: at sentence #7850000, processed 129538777 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,802 : INFO : PROGRESS: at sentence #7860000, processed 129703340 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,840 : INFO : PROGRESS: at sentence #7870000, processed 129867647 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,877 : INFO : PROGRESS: at sentence #7880000, processed 130033024 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,916 : INFO : PROGRESS: at sentence #7890000, processed 130195785 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,954 : INFO : PROGRESS: at sentence #7900000, processed 130359688 words, keeping 20000 word types\n", - "2017-08-20 12:51:28,990 : INFO : PROGRESS: at sentence #7910000, processed 130523423 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,028 : INFO : PROGRESS: at sentence #7920000, processed 130690724 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,065 : INFO : PROGRESS: at sentence #7930000, processed 130851133 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,102 : INFO : PROGRESS: at sentence #7940000, processed 131015656 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,010 : INFO : PROGRESS: at sentence #7950000, processed 131179324 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,047 : INFO : PROGRESS: at sentence #7960000, processed 131342535 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,083 : INFO : PROGRESS: at sentence #7970000, processed 131508147 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,119 : INFO : PROGRESS: at sentence #7980000, processed 131670305 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,158 : INFO : PROGRESS: at sentence #7990000, processed 131836639 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,196 : INFO : PROGRESS: at sentence #8000000, processed 132001359 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,233 : INFO : PROGRESS: at sentence #8010000, processed 132166080 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,269 : INFO : PROGRESS: at sentence #8020000, processed 132329883 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,305 : INFO : PROGRESS: at sentence #8030000, processed 132493795 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,342 : INFO : PROGRESS: at sentence #8040000, processed 132660804 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,380 : INFO : PROGRESS: at sentence #8050000, processed 132824613 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,416 : INFO : PROGRESS: at sentence #8060000, processed 132986366 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,452 : INFO : PROGRESS: at sentence #8070000, processed 133151049 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,488 : INFO : PROGRESS: at sentence #8080000, processed 133314230 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,525 : INFO : PROGRESS: at sentence #8090000, processed 133476732 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,562 : INFO : PROGRESS: at sentence #8100000, processed 133641303 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,600 : INFO : PROGRESS: at sentence #8110000, processed 133808004 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,637 : INFO : PROGRESS: at sentence #8120000, processed 133974106 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,673 : INFO : PROGRESS: at sentence #8130000, processed 134135551 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,710 : INFO : PROGRESS: at sentence #8140000, processed 134304070 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,747 : INFO : PROGRESS: at sentence #8150000, processed 134472886 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,785 : INFO : PROGRESS: at sentence #8160000, processed 134641764 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,822 : INFO : PROGRESS: at sentence #8170000, processed 134807263 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,859 : INFO : PROGRESS: at sentence #8180000, processed 134971454 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,895 : INFO : PROGRESS: at sentence #8190000, processed 135132929 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,932 : INFO : PROGRESS: at sentence #8200000, processed 135297817 words, keeping 20000 word types\n", - "2017-08-20 12:51:29,969 : INFO : PROGRESS: at sentence #8210000, processed 135461661 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,007 : INFO : PROGRESS: at sentence #8220000, processed 135626967 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,045 : INFO : PROGRESS: at sentence #8230000, processed 135790331 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,084 : INFO : PROGRESS: at sentence #8240000, processed 135957161 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,122 : INFO : PROGRESS: at sentence #8250000, processed 136125144 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,160 : INFO : PROGRESS: at sentence #8260000, processed 136289567 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,202 : INFO : PROGRESS: at sentence #8270000, processed 136453253 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,241 : INFO : PROGRESS: at sentence #8280000, processed 136619972 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,279 : INFO : PROGRESS: at sentence #8290000, processed 136784876 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,320 : INFO : PROGRESS: at sentence #8300000, processed 136952339 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,359 : INFO : PROGRESS: at sentence #8310000, processed 137119966 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,398 : INFO : PROGRESS: at sentence #8320000, processed 137286703 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,437 : INFO : PROGRESS: at sentence #8330000, processed 137449165 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,479 : INFO : PROGRESS: at sentence #8340000, processed 137613225 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,517 : INFO : PROGRESS: at sentence #8350000, processed 137777268 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,556 : INFO : PROGRESS: at sentence #8360000, processed 137940716 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,593 : INFO : PROGRESS: at sentence #8370000, processed 138102280 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,632 : INFO : PROGRESS: at sentence #8380000, processed 138262707 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,672 : INFO : PROGRESS: at sentence #8390000, processed 138428204 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,711 : INFO : PROGRESS: at sentence #8400000, processed 138592112 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,751 : INFO : PROGRESS: at sentence #8410000, processed 138758350 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,791 : INFO : PROGRESS: at sentence #8420000, processed 138926292 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,831 : INFO : PROGRESS: at sentence #8430000, processed 139091322 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,870 : INFO : PROGRESS: at sentence #8440000, processed 139254732 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,909 : INFO : PROGRESS: at sentence #8450000, processed 139418096 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,949 : INFO : PROGRESS: at sentence #8460000, processed 139580848 words, keeping 20000 word types\n", - "2017-08-20 12:51:30,989 : INFO : PROGRESS: at sentence #8470000, processed 139747536 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,030 : INFO : PROGRESS: at sentence #8480000, processed 139914337 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,069 : INFO : PROGRESS: at sentence #8490000, processed 140071032 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,108 : INFO : PROGRESS: at sentence #8500000, processed 140236505 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,147 : INFO : PROGRESS: at sentence #8510000, processed 140399630 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,186 : INFO : PROGRESS: at sentence #8520000, processed 140562085 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,229 : INFO : PROGRESS: at sentence #8530000, processed 140729473 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,268 : INFO : PROGRESS: at sentence #8540000, processed 140893325 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,306 : INFO : PROGRESS: at sentence #8550000, processed 141050338 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,344 : INFO : PROGRESS: at sentence #8560000, processed 141216561 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,383 : INFO : PROGRESS: at sentence #8570000, processed 141380597 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,421 : INFO : PROGRESS: at sentence #8580000, processed 141542250 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,461 : INFO : PROGRESS: at sentence #8590000, processed 141708277 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,500 : INFO : PROGRESS: at sentence #8600000, processed 141874245 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,538 : INFO : PROGRESS: at sentence #8610000, processed 142038068 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,576 : INFO : PROGRESS: at sentence #8620000, processed 142205228 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,614 : INFO : PROGRESS: at sentence #8630000, processed 142369883 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,651 : INFO : PROGRESS: at sentence #8640000, processed 142532136 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,689 : INFO : PROGRESS: at sentence #8650000, processed 142696007 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,727 : INFO : PROGRESS: at sentence #8660000, processed 142866042 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,766 : INFO : PROGRESS: at sentence #8670000, processed 143031508 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,805 : INFO : PROGRESS: at sentence #8680000, processed 143197425 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,842 : INFO : PROGRESS: at sentence #8690000, processed 143361317 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,880 : INFO : PROGRESS: at sentence #8700000, processed 143525114 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,917 : INFO : PROGRESS: at sentence #8710000, processed 143690914 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,955 : INFO : PROGRESS: at sentence #8720000, processed 143853260 words, keeping 20000 word types\n", - "2017-08-20 12:51:31,992 : INFO : PROGRESS: at sentence #8730000, processed 144019618 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,030 : INFO : PROGRESS: at sentence #8740000, processed 144184065 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,068 : INFO : PROGRESS: at sentence #8750000, processed 144345404 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,106 : INFO : PROGRESS: at sentence #8760000, processed 144508344 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,145 : INFO : PROGRESS: at sentence #8770000, processed 144669874 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,182 : INFO : PROGRESS: at sentence #8780000, processed 144832487 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,220 : INFO : PROGRESS: at sentence #8790000, processed 144994476 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,258 : INFO : PROGRESS: at sentence #8800000, processed 145157403 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,296 : INFO : PROGRESS: at sentence #8810000, processed 145320462 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,333 : INFO : PROGRESS: at sentence #8820000, processed 145484185 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,372 : INFO : PROGRESS: at sentence #8830000, processed 145650826 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,408 : INFO : PROGRESS: at sentence #8840000, processed 145812048 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,446 : INFO : PROGRESS: at sentence #8850000, processed 145979989 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,483 : INFO : PROGRESS: at sentence #8860000, processed 146141452 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,521 : INFO : PROGRESS: at sentence #8870000, processed 146306838 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,559 : INFO : PROGRESS: at sentence #8880000, processed 146473554 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,597 : INFO : PROGRESS: at sentence #8890000, processed 146641298 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,636 : INFO : PROGRESS: at sentence #8900000, processed 146811423 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,673 : INFO : PROGRESS: at sentence #8910000, processed 146976067 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,711 : INFO : PROGRESS: at sentence #8920000, processed 147140154 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,749 : INFO : PROGRESS: at sentence #8930000, processed 147305299 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,786 : INFO : PROGRESS: at sentence #8940000, processed 147471523 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,823 : INFO : PROGRESS: at sentence #8950000, processed 147631964 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,859 : INFO : PROGRESS: at sentence #8960000, processed 147792913 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,898 : INFO : PROGRESS: at sentence #8970000, processed 147960954 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,935 : INFO : PROGRESS: at sentence #8980000, processed 148126479 words, keeping 20000 word types\n", - "2017-08-20 12:51:32,973 : INFO : PROGRESS: at sentence #8990000, processed 148288092 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,010 : INFO : PROGRESS: at sentence #9000000, processed 148449760 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,047 : INFO : PROGRESS: at sentence #9010000, processed 148610540 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,084 : INFO : PROGRESS: at sentence #9020000, processed 148775456 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,121 : INFO : PROGRESS: at sentence #9030000, processed 148940123 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,160 : INFO : PROGRESS: at sentence #9040000, processed 149106837 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,197 : INFO : PROGRESS: at sentence #9050000, processed 149274020 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,235 : INFO : PROGRESS: at sentence #9060000, processed 149439866 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,273 : INFO : PROGRESS: at sentence #9070000, processed 149603171 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,310 : INFO : PROGRESS: at sentence #9080000, processed 149763258 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,348 : INFO : PROGRESS: at sentence #9090000, processed 149930252 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,385 : INFO : PROGRESS: at sentence #9100000, processed 150094134 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,422 : INFO : PROGRESS: at sentence #9110000, processed 150257741 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,459 : INFO : PROGRESS: at sentence #9120000, processed 150419666 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,496 : INFO : PROGRESS: at sentence #9130000, processed 150584173 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,534 : INFO : PROGRESS: at sentence #9140000, processed 150748399 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,571 : INFO : PROGRESS: at sentence #9150000, processed 150911973 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,608 : INFO : PROGRESS: at sentence #9160000, processed 151075393 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,646 : INFO : PROGRESS: at sentence #9170000, processed 151243282 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,683 : INFO : PROGRESS: at sentence #9180000, processed 151408020 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,720 : INFO : PROGRESS: at sentence #9190000, processed 151573708 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,758 : INFO : PROGRESS: at sentence #9200000, processed 151736992 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,794 : INFO : PROGRESS: at sentence #9210000, processed 151901718 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,831 : INFO : PROGRESS: at sentence #9220000, processed 152066070 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,868 : INFO : PROGRESS: at sentence #9230000, processed 152228207 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,905 : INFO : PROGRESS: at sentence #9240000, processed 152392335 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,944 : INFO : PROGRESS: at sentence #9250000, processed 152558896 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,981 : INFO : PROGRESS: at sentence #9260000, processed 152726474 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,017 : INFO : PROGRESS: at sentence #9270000, processed 152887978 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,054 : INFO : PROGRESS: at sentence #9280000, processed 153053607 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,089 : INFO : PROGRESS: at sentence #9290000, processed 153210515 words, keeping 20000 word types\n", - "2017-08-20 12:51:33,998 : INFO : PROGRESS: at sentence #9300000, processed 153377295 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,035 : INFO : PROGRESS: at sentence #9310000, processed 153543253 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,071 : INFO : PROGRESS: at sentence #9320000, processed 153708144 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,110 : INFO : PROGRESS: at sentence #9330000, processed 153870885 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,147 : INFO : PROGRESS: at sentence #9340000, processed 154035280 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,185 : INFO : PROGRESS: at sentence #9350000, processed 154201508 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,223 : INFO : PROGRESS: at sentence #9360000, processed 154365779 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,259 : INFO : PROGRESS: at sentence #9370000, processed 154528170 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,297 : INFO : PROGRESS: at sentence #9380000, processed 154693386 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,333 : INFO : PROGRESS: at sentence #9390000, processed 154854842 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,370 : INFO : PROGRESS: at sentence #9400000, processed 155019474 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,407 : INFO : PROGRESS: at sentence #9410000, processed 155184051 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,444 : INFO : PROGRESS: at sentence #9420000, processed 155349882 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,481 : INFO : PROGRESS: at sentence #9430000, processed 155515298 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,517 : INFO : PROGRESS: at sentence #9440000, processed 155677047 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,553 : INFO : PROGRESS: at sentence #9450000, processed 155840983 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,590 : INFO : PROGRESS: at sentence #9460000, processed 156006291 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,629 : INFO : PROGRESS: at sentence #9470000, processed 156170188 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,678 : INFO : PROGRESS: at sentence #9480000, processed 156335522 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,718 : INFO : PROGRESS: at sentence #9490000, processed 156499642 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,754 : INFO : PROGRESS: at sentence #9500000, processed 156665282 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,791 : INFO : PROGRESS: at sentence #9510000, processed 156831177 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,828 : INFO : PROGRESS: at sentence #9520000, processed 156996631 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,864 : INFO : PROGRESS: at sentence #9530000, processed 157163200 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,901 : INFO : PROGRESS: at sentence #9540000, processed 157326397 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,936 : INFO : PROGRESS: at sentence #9550000, processed 157487021 words, keeping 20000 word types\n", - "2017-08-20 12:51:34,972 : INFO : PROGRESS: at sentence #9560000, processed 157654110 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,012 : INFO : PROGRESS: at sentence #9570000, processed 157820013 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,049 : INFO : PROGRESS: at sentence #9580000, processed 157982375 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,087 : INFO : PROGRESS: at sentence #9590000, processed 158146207 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,126 : INFO : PROGRESS: at sentence #9600000, processed 158312850 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,163 : INFO : PROGRESS: at sentence #9610000, processed 158476461 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,201 : INFO : PROGRESS: at sentence #9620000, processed 158638988 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,239 : INFO : PROGRESS: at sentence #9630000, processed 158803822 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,277 : INFO : PROGRESS: at sentence #9640000, processed 158969474 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,315 : INFO : PROGRESS: at sentence #9650000, processed 159138261 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,353 : INFO : PROGRESS: at sentence #9660000, processed 159304143 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,390 : INFO : PROGRESS: at sentence #9670000, processed 159467875 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,428 : INFO : PROGRESS: at sentence #9680000, processed 159632593 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,467 : INFO : PROGRESS: at sentence #9690000, processed 159799647 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,505 : INFO : PROGRESS: at sentence #9700000, processed 159965778 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,543 : INFO : PROGRESS: at sentence #9710000, processed 160133051 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,581 : INFO : PROGRESS: at sentence #9720000, processed 160296129 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,620 : INFO : PROGRESS: at sentence #9730000, processed 160461238 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,658 : INFO : PROGRESS: at sentence #9740000, processed 160627118 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,696 : INFO : PROGRESS: at sentence #9750000, processed 160793193 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,732 : INFO : PROGRESS: at sentence #9760000, processed 160954183 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,770 : INFO : PROGRESS: at sentence #9770000, processed 161120676 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,808 : INFO : PROGRESS: at sentence #9780000, processed 161285461 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,846 : INFO : PROGRESS: at sentence #9790000, processed 161448823 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,883 : INFO : PROGRESS: at sentence #9800000, processed 161611621 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,921 : INFO : PROGRESS: at sentence #9810000, processed 161774744 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,959 : INFO : PROGRESS: at sentence #9820000, processed 161938733 words, keeping 20000 word types\n", - "2017-08-20 12:51:35,996 : INFO : PROGRESS: at sentence #9830000, processed 162101824 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,033 : INFO : PROGRESS: at sentence #9840000, processed 162265958 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,071 : INFO : PROGRESS: at sentence #9850000, processed 162429779 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,108 : INFO : PROGRESS: at sentence #9860000, processed 162593432 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,146 : INFO : PROGRESS: at sentence #9870000, processed 162756424 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,183 : INFO : PROGRESS: at sentence #9880000, processed 162919482 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,221 : INFO : PROGRESS: at sentence #9890000, processed 163082912 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,259 : INFO : PROGRESS: at sentence #9900000, processed 163248307 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,297 : INFO : PROGRESS: at sentence #9910000, processed 163415729 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,335 : INFO : PROGRESS: at sentence #9920000, processed 163580648 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,372 : INFO : PROGRESS: at sentence #9930000, processed 163744373 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,410 : INFO : PROGRESS: at sentence #9940000, processed 163909233 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,449 : INFO : PROGRESS: at sentence #9950000, processed 164074170 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,488 : INFO : PROGRESS: at sentence #9960000, processed 164239452 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,525 : INFO : PROGRESS: at sentence #9970000, processed 164403113 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,564 : INFO : PROGRESS: at sentence #9980000, processed 164569211 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,603 : INFO : PROGRESS: at sentence #9990000, processed 164737601 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,640 : INFO : PROGRESS: at sentence #10000000, processed 164900837 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,680 : INFO : PROGRESS: at sentence #10010000, processed 165068068 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,719 : INFO : PROGRESS: at sentence #10020000, processed 165235481 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,757 : INFO : PROGRESS: at sentence #10030000, processed 165401391 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,795 : INFO : PROGRESS: at sentence #10040000, processed 165566175 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,833 : INFO : PROGRESS: at sentence #10050000, processed 165731975 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,872 : INFO : PROGRESS: at sentence #10060000, processed 165897260 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,910 : INFO : PROGRESS: at sentence #10070000, processed 166060532 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,948 : INFO : PROGRESS: at sentence #10080000, processed 166221716 words, keeping 20000 word types\n", - "2017-08-20 12:51:36,986 : INFO : PROGRESS: at sentence #10090000, processed 166385628 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,025 : INFO : PROGRESS: at sentence #10100000, processed 166553934 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,064 : INFO : PROGRESS: at sentence #10110000, processed 166720021 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,103 : INFO : PROGRESS: at sentence #10120000, processed 166885212 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,143 : INFO : PROGRESS: at sentence #10130000, processed 167051561 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,182 : INFO : PROGRESS: at sentence #10140000, processed 167216984 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,220 : INFO : PROGRESS: at sentence #10150000, processed 167378900 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,259 : INFO : PROGRESS: at sentence #10160000, processed 167535279 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,298 : INFO : PROGRESS: at sentence #10170000, processed 167698545 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,338 : INFO : PROGRESS: at sentence #10180000, processed 167865171 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,378 : INFO : PROGRESS: at sentence #10190000, processed 168028577 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,416 : INFO : PROGRESS: at sentence #10200000, processed 168188941 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,454 : INFO : PROGRESS: at sentence #10210000, processed 168347997 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,495 : INFO : PROGRESS: at sentence #10220000, processed 168512555 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,534 : INFO : PROGRESS: at sentence #10230000, processed 168675923 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,573 : INFO : PROGRESS: at sentence #10240000, processed 168842845 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,612 : INFO : PROGRESS: at sentence #10250000, processed 169009591 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,650 : INFO : PROGRESS: at sentence #10260000, processed 169174805 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,688 : INFO : PROGRESS: at sentence #10270000, processed 169338118 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,729 : INFO : PROGRESS: at sentence #10280000, processed 169501855 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,767 : INFO : PROGRESS: at sentence #10290000, processed 169664797 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,805 : INFO : PROGRESS: at sentence #10300000, processed 169828863 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,843 : INFO : PROGRESS: at sentence #10310000, processed 169991352 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,880 : INFO : PROGRESS: at sentence #10320000, processed 170154482 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,918 : INFO : PROGRESS: at sentence #10330000, processed 170317630 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,956 : INFO : PROGRESS: at sentence #10340000, processed 170480963 words, keeping 20000 word types\n", - "2017-08-20 12:51:37,994 : INFO : PROGRESS: at sentence #10350000, processed 170648357 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,031 : INFO : PROGRESS: at sentence #10360000, processed 170812489 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,068 : INFO : PROGRESS: at sentence #10370000, processed 170978755 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,104 : INFO : PROGRESS: at sentence #10380000, processed 171139877 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,142 : INFO : PROGRESS: at sentence #10390000, processed 171306150 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,180 : INFO : PROGRESS: at sentence #10400000, processed 171470531 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,217 : INFO : PROGRESS: at sentence #10410000, processed 171634421 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,254 : INFO : PROGRESS: at sentence #10420000, processed 171796989 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,293 : INFO : PROGRESS: at sentence #10430000, processed 171964898 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,331 : INFO : PROGRESS: at sentence #10440000, processed 172128917 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,369 : INFO : PROGRESS: at sentence #10450000, processed 172293978 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,408 : INFO : PROGRESS: at sentence #10460000, processed 172457877 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,445 : INFO : PROGRESS: at sentence #10470000, processed 172623062 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,483 : INFO : PROGRESS: at sentence #10480000, processed 172788911 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,520 : INFO : PROGRESS: at sentence #10490000, processed 172952681 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,560 : INFO : PROGRESS: at sentence #10500000, processed 173119335 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,599 : INFO : PROGRESS: at sentence #10510000, processed 173287707 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,638 : INFO : PROGRESS: at sentence #10520000, processed 173455695 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,678 : INFO : PROGRESS: at sentence #10530000, processed 173622266 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,717 : INFO : PROGRESS: at sentence #10540000, processed 173788892 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,758 : INFO : PROGRESS: at sentence #10550000, processed 173954098 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,795 : INFO : PROGRESS: at sentence #10560000, processed 174115167 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,833 : INFO : PROGRESS: at sentence #10570000, processed 174279187 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,870 : INFO : PROGRESS: at sentence #10580000, processed 174442401 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,909 : INFO : PROGRESS: at sentence #10590000, processed 174610077 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,947 : INFO : PROGRESS: at sentence #10600000, processed 174775998 words, keeping 20000 word types\n", - "2017-08-20 12:51:38,985 : INFO : PROGRESS: at sentence #10610000, processed 174940289 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,021 : INFO : PROGRESS: at sentence #10620000, processed 175099313 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,061 : INFO : PROGRESS: at sentence #10630000, processed 175267385 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,098 : INFO : PROGRESS: at sentence #10640000, processed 175432367 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,006 : INFO : PROGRESS: at sentence #10650000, processed 175598440 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,043 : INFO : PROGRESS: at sentence #10660000, processed 175763041 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,080 : INFO : PROGRESS: at sentence #10670000, processed 175930654 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,116 : INFO : PROGRESS: at sentence #10680000, processed 176095645 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,154 : INFO : PROGRESS: at sentence #10690000, processed 176263848 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,191 : INFO : PROGRESS: at sentence #10700000, processed 176426864 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,228 : INFO : PROGRESS: at sentence #10710000, processed 176594345 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,264 : INFO : PROGRESS: at sentence #10720000, processed 176758819 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,301 : INFO : PROGRESS: at sentence #10730000, processed 176925668 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,338 : INFO : PROGRESS: at sentence #10740000, processed 177093391 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,375 : INFO : PROGRESS: at sentence #10750000, processed 177256672 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,411 : INFO : PROGRESS: at sentence #10760000, processed 177424937 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,449 : INFO : PROGRESS: at sentence #10770000, processed 177587506 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,485 : INFO : PROGRESS: at sentence #10780000, processed 177752386 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,521 : INFO : PROGRESS: at sentence #10790000, processed 177917450 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,557 : INFO : PROGRESS: at sentence #10800000, processed 178084001 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,595 : INFO : PROGRESS: at sentence #10810000, processed 178251869 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,631 : INFO : PROGRESS: at sentence #10820000, processed 178415405 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,668 : INFO : PROGRESS: at sentence #10830000, processed 178580616 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,705 : INFO : PROGRESS: at sentence #10840000, processed 178747159 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,742 : INFO : PROGRESS: at sentence #10850000, processed 178919031 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,778 : INFO : PROGRESS: at sentence #10860000, processed 179083720 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,813 : INFO : PROGRESS: at sentence #10870000, processed 179246844 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,850 : INFO : PROGRESS: at sentence #10880000, processed 179410131 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,889 : INFO : PROGRESS: at sentence #10890000, processed 179577002 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,925 : INFO : PROGRESS: at sentence #10900000, processed 179741325 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,961 : INFO : PROGRESS: at sentence #10910000, processed 179907153 words, keeping 20000 word types\n", - "2017-08-20 12:51:39,997 : INFO : PROGRESS: at sentence #10920000, processed 180069710 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,034 : INFO : PROGRESS: at sentence #10930000, processed 180232635 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,072 : INFO : PROGRESS: at sentence #10940000, processed 180396686 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,108 : INFO : PROGRESS: at sentence #10950000, processed 180557899 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,146 : INFO : PROGRESS: at sentence #10960000, processed 180723242 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,185 : INFO : PROGRESS: at sentence #10970000, processed 180886060 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,222 : INFO : PROGRESS: at sentence #10980000, processed 181048778 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,261 : INFO : PROGRESS: at sentence #10990000, processed 181212733 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,299 : INFO : PROGRESS: at sentence #11000000, processed 181375967 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,336 : INFO : PROGRESS: at sentence #11010000, processed 181537607 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,374 : INFO : PROGRESS: at sentence #11020000, processed 181706700 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,412 : INFO : PROGRESS: at sentence #11030000, processed 181871350 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,451 : INFO : PROGRESS: at sentence #11040000, processed 182036292 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,488 : INFO : PROGRESS: at sentence #11050000, processed 182198478 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,525 : INFO : PROGRESS: at sentence #11060000, processed 182363512 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,563 : INFO : PROGRESS: at sentence #11070000, processed 182528528 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,600 : INFO : PROGRESS: at sentence #11080000, processed 182691146 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,638 : INFO : PROGRESS: at sentence #11090000, processed 182853757 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,679 : INFO : PROGRESS: at sentence #11100000, processed 183022593 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,719 : INFO : PROGRESS: at sentence #11110000, processed 183189068 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,757 : INFO : PROGRESS: at sentence #11120000, processed 183354183 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,797 : INFO : PROGRESS: at sentence #11130000, processed 183521221 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,836 : INFO : PROGRESS: at sentence #11140000, processed 183686672 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,876 : INFO : PROGRESS: at sentence #11150000, processed 183849414 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,913 : INFO : PROGRESS: at sentence #11160000, processed 184009491 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,950 : INFO : PROGRESS: at sentence #11170000, processed 184171101 words, keeping 20000 word types\n", - "2017-08-20 12:51:40,988 : INFO : PROGRESS: at sentence #11180000, processed 184332596 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,025 : INFO : PROGRESS: at sentence #11190000, processed 184495952 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,064 : INFO : PROGRESS: at sentence #11200000, processed 184662292 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,101 : INFO : PROGRESS: at sentence #11210000, processed 184826223 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,138 : INFO : PROGRESS: at sentence #11220000, processed 184987680 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,175 : INFO : PROGRESS: at sentence #11230000, processed 185150838 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,212 : INFO : PROGRESS: at sentence #11240000, processed 185313527 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,250 : INFO : PROGRESS: at sentence #11250000, processed 185476999 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,288 : INFO : PROGRESS: at sentence #11260000, processed 185640391 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,325 : INFO : PROGRESS: at sentence #11270000, processed 185802894 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,362 : INFO : PROGRESS: at sentence #11280000, processed 185969686 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,400 : INFO : PROGRESS: at sentence #11290000, processed 186136409 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,437 : INFO : PROGRESS: at sentence #11300000, processed 186301121 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,474 : INFO : PROGRESS: at sentence #11310000, processed 186461001 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,514 : INFO : PROGRESS: at sentence #11320000, processed 186626742 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,551 : INFO : PROGRESS: at sentence #11330000, processed 186788017 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,588 : INFO : PROGRESS: at sentence #11340000, processed 186951233 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,625 : INFO : PROGRESS: at sentence #11350000, processed 187112054 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,662 : INFO : PROGRESS: at sentence #11360000, processed 187274430 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,701 : INFO : PROGRESS: at sentence #11370000, processed 187439291 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,739 : INFO : PROGRESS: at sentence #11380000, processed 187605714 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,777 : INFO : PROGRESS: at sentence #11390000, processed 187769088 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,815 : INFO : PROGRESS: at sentence #11400000, processed 187932921 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,853 : INFO : PROGRESS: at sentence #11410000, processed 188097957 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,890 : INFO : PROGRESS: at sentence #11420000, processed 188262098 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,928 : INFO : PROGRESS: at sentence #11430000, processed 188429020 words, keeping 20000 word types\n", - "2017-08-20 12:51:41,966 : INFO : PROGRESS: at sentence #11440000, processed 188597861 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,005 : INFO : PROGRESS: at sentence #11450000, processed 188763028 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,042 : INFO : PROGRESS: at sentence #11460000, processed 188929687 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,080 : INFO : PROGRESS: at sentence #11470000, processed 189095375 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,118 : INFO : PROGRESS: at sentence #11480000, processed 189260238 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,154 : INFO : PROGRESS: at sentence #11490000, processed 189423078 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,191 : INFO : PROGRESS: at sentence #11500000, processed 189584600 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,228 : INFO : PROGRESS: at sentence #11510000, processed 189745450 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,267 : INFO : PROGRESS: at sentence #11520000, processed 189913648 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,305 : INFO : PROGRESS: at sentence #11530000, processed 190077420 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,343 : INFO : PROGRESS: at sentence #11540000, processed 190240633 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,380 : INFO : PROGRESS: at sentence #11550000, processed 190404899 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,417 : INFO : PROGRESS: at sentence #11560000, processed 190569487 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,455 : INFO : PROGRESS: at sentence #11570000, processed 190734605 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,492 : INFO : PROGRESS: at sentence #11580000, processed 190900512 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,532 : INFO : PROGRESS: at sentence #11590000, processed 191066890 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,570 : INFO : PROGRESS: at sentence #11600000, processed 191228921 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,608 : INFO : PROGRESS: at sentence #11610000, processed 191394418 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,646 : INFO : PROGRESS: at sentence #11620000, processed 191561057 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,683 : INFO : PROGRESS: at sentence #11630000, processed 191724791 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,721 : INFO : PROGRESS: at sentence #11640000, processed 191892813 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,758 : INFO : PROGRESS: at sentence #11650000, processed 192055406 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,796 : INFO : PROGRESS: at sentence #11660000, processed 192217983 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,833 : INFO : PROGRESS: at sentence #11670000, processed 192382229 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,870 : INFO : PROGRESS: at sentence #11680000, processed 192544276 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,908 : INFO : PROGRESS: at sentence #11690000, processed 192712093 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,947 : INFO : PROGRESS: at sentence #11700000, processed 192874790 words, keeping 20000 word types\n", - "2017-08-20 12:51:42,986 : INFO : PROGRESS: at sentence #11710000, processed 193040090 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,025 : INFO : PROGRESS: at sentence #11720000, processed 193206503 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,063 : INFO : PROGRESS: at sentence #11730000, processed 193372211 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,102 : INFO : PROGRESS: at sentence #11740000, processed 193538765 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,142 : INFO : PROGRESS: at sentence #11750000, processed 193707347 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,180 : INFO : PROGRESS: at sentence #11760000, processed 193872161 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,218 : INFO : PROGRESS: at sentence #11770000, processed 194037547 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,256 : INFO : PROGRESS: at sentence #11780000, processed 194203079 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,296 : INFO : PROGRESS: at sentence #11790000, processed 194369561 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,333 : INFO : PROGRESS: at sentence #11800000, processed 194532345 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,372 : INFO : PROGRESS: at sentence #11810000, processed 194696799 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,410 : INFO : PROGRESS: at sentence #11820000, processed 194862115 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,450 : INFO : PROGRESS: at sentence #11830000, processed 195025929 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,489 : INFO : PROGRESS: at sentence #11840000, processed 195188987 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,528 : INFO : PROGRESS: at sentence #11850000, processed 195354905 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,566 : INFO : PROGRESS: at sentence #11860000, processed 195516024 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,604 : INFO : PROGRESS: at sentence #11870000, processed 195679861 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,642 : INFO : PROGRESS: at sentence #11880000, processed 195842514 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,679 : INFO : PROGRESS: at sentence #11890000, processed 196003134 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,717 : INFO : PROGRESS: at sentence #11900000, processed 196164940 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,758 : INFO : PROGRESS: at sentence #11910000, processed 196330368 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,797 : INFO : PROGRESS: at sentence #11920000, processed 196494059 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,836 : INFO : PROGRESS: at sentence #11930000, processed 196656614 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,876 : INFO : PROGRESS: at sentence #11940000, processed 196822456 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,914 : INFO : PROGRESS: at sentence #11950000, processed 196985266 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,952 : INFO : PROGRESS: at sentence #11960000, processed 197149146 words, keeping 20000 word types\n", - "2017-08-20 12:51:43,991 : INFO : PROGRESS: at sentence #11970000, processed 197313031 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,030 : INFO : PROGRESS: at sentence #11980000, processed 197481141 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,069 : INFO : PROGRESS: at sentence #11990000, processed 197647478 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,107 : INFO : PROGRESS: at sentence #12000000, processed 197816505 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,014 : INFO : PROGRESS: at sentence #12010000, processed 197974014 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,052 : INFO : PROGRESS: at sentence #12020000, processed 198137660 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,089 : INFO : PROGRESS: at sentence #12030000, processed 198301567 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,128 : INFO : PROGRESS: at sentence #12040000, processed 198463220 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,166 : INFO : PROGRESS: at sentence #12050000, processed 198627723 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,204 : INFO : PROGRESS: at sentence #12060000, processed 198789956 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,241 : INFO : PROGRESS: at sentence #12070000, processed 198954727 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,279 : INFO : PROGRESS: at sentence #12080000, processed 199120209 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,315 : INFO : PROGRESS: at sentence #12090000, processed 199284139 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,352 : INFO : PROGRESS: at sentence #12100000, processed 199451306 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,389 : INFO : PROGRESS: at sentence #12110000, processed 199614686 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,426 : INFO : PROGRESS: at sentence #12120000, processed 199780309 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,467 : INFO : PROGRESS: at sentence #12130000, processed 199944761 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,505 : INFO : PROGRESS: at sentence #12140000, processed 200109580 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,541 : INFO : PROGRESS: at sentence #12150000, processed 200271533 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,578 : INFO : PROGRESS: at sentence #12160000, processed 200439759 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,614 : INFO : PROGRESS: at sentence #12170000, processed 200602626 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,653 : INFO : PROGRESS: at sentence #12180000, processed 200769117 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,689 : INFO : PROGRESS: at sentence #12190000, processed 200933448 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,726 : INFO : PROGRESS: at sentence #12200000, processed 201098758 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,764 : INFO : PROGRESS: at sentence #12210000, processed 201265715 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,800 : INFO : PROGRESS: at sentence #12220000, processed 201431072 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,837 : INFO : PROGRESS: at sentence #12230000, processed 201595643 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,874 : INFO : PROGRESS: at sentence #12240000, processed 201757571 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,913 : INFO : PROGRESS: at sentence #12250000, processed 201922685 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,949 : INFO : PROGRESS: at sentence #12260000, processed 202083472 words, keeping 20000 word types\n", - "2017-08-20 12:51:44,985 : INFO : PROGRESS: at sentence #12270000, processed 202246924 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,023 : INFO : PROGRESS: at sentence #12280000, processed 202411275 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,062 : INFO : PROGRESS: at sentence #12290000, processed 202574537 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,101 : INFO : PROGRESS: at sentence #12300000, processed 202736958 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,139 : INFO : PROGRESS: at sentence #12310000, processed 202900489 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,177 : INFO : PROGRESS: at sentence #12320000, processed 203064937 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,217 : INFO : PROGRESS: at sentence #12330000, processed 203232083 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,256 : INFO : PROGRESS: at sentence #12340000, processed 203398421 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,294 : INFO : PROGRESS: at sentence #12350000, processed 203562808 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,332 : INFO : PROGRESS: at sentence #12360000, processed 203728169 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,370 : INFO : PROGRESS: at sentence #12370000, processed 203892639 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,409 : INFO : PROGRESS: at sentence #12380000, processed 204056117 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,447 : INFO : PROGRESS: at sentence #12390000, processed 204218469 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,486 : INFO : PROGRESS: at sentence #12400000, processed 204385562 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,524 : INFO : PROGRESS: at sentence #12410000, processed 204550309 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,561 : INFO : PROGRESS: at sentence #12420000, processed 204713013 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,600 : INFO : PROGRESS: at sentence #12430000, processed 204879756 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,638 : INFO : PROGRESS: at sentence #12440000, processed 205041845 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,677 : INFO : PROGRESS: at sentence #12450000, processed 205207609 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,718 : INFO : PROGRESS: at sentence #12460000, processed 205374390 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,756 : INFO : PROGRESS: at sentence #12470000, processed 205537757 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,793 : INFO : PROGRESS: at sentence #12480000, processed 205697469 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,832 : INFO : PROGRESS: at sentence #12490000, processed 205861356 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,870 : INFO : PROGRESS: at sentence #12500000, processed 206026365 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,909 : INFO : PROGRESS: at sentence #12510000, processed 206188671 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,946 : INFO : PROGRESS: at sentence #12520000, processed 206352548 words, keeping 20000 word types\n", - "2017-08-20 12:51:45,985 : INFO : PROGRESS: at sentence #12530000, processed 206516892 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,023 : INFO : PROGRESS: at sentence #12540000, processed 206681275 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,061 : INFO : PROGRESS: at sentence #12550000, processed 206846946 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,100 : INFO : PROGRESS: at sentence #12560000, processed 207014269 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,138 : INFO : PROGRESS: at sentence #12570000, processed 207180298 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,174 : INFO : PROGRESS: at sentence #12580000, processed 207340004 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,213 : INFO : PROGRESS: at sentence #12590000, processed 207507491 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,252 : INFO : PROGRESS: at sentence #12600000, processed 207672454 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,290 : INFO : PROGRESS: at sentence #12610000, processed 207838211 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,329 : INFO : PROGRESS: at sentence #12620000, processed 208002268 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,366 : INFO : PROGRESS: at sentence #12630000, processed 208166738 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,404 : INFO : PROGRESS: at sentence #12640000, processed 208330289 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,442 : INFO : PROGRESS: at sentence #12650000, processed 208493212 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,479 : INFO : PROGRESS: at sentence #12660000, processed 208657048 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,517 : INFO : PROGRESS: at sentence #12670000, processed 208819533 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,556 : INFO : PROGRESS: at sentence #12680000, processed 208984861 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,594 : INFO : PROGRESS: at sentence #12690000, processed 209150459 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,631 : INFO : PROGRESS: at sentence #12700000, processed 209313830 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,668 : INFO : PROGRESS: at sentence #12710000, processed 209476374 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,706 : INFO : PROGRESS: at sentence #12720000, processed 209641912 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,744 : INFO : PROGRESS: at sentence #12730000, processed 209804250 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,782 : INFO : PROGRESS: at sentence #12740000, processed 209970532 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,820 : INFO : PROGRESS: at sentence #12750000, processed 210135712 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,858 : INFO : PROGRESS: at sentence #12760000, processed 210301163 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,896 : INFO : PROGRESS: at sentence #12770000, processed 210467995 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,934 : INFO : PROGRESS: at sentence #12780000, processed 210630711 words, keeping 20000 word types\n", - "2017-08-20 12:51:46,973 : INFO : PROGRESS: at sentence #12790000, processed 210799004 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,011 : INFO : PROGRESS: at sentence #12800000, processed 210967301 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,049 : INFO : PROGRESS: at sentence #12810000, processed 211134994 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,087 : INFO : PROGRESS: at sentence #12820000, processed 211300523 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,126 : INFO : PROGRESS: at sentence #12830000, processed 211468525 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,164 : INFO : PROGRESS: at sentence #12840000, processed 211634570 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,202 : INFO : PROGRESS: at sentence #12850000, processed 211798506 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,243 : INFO : PROGRESS: at sentence #12860000, processed 211964034 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,282 : INFO : PROGRESS: at sentence #12870000, processed 212125707 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,320 : INFO : PROGRESS: at sentence #12880000, processed 212288762 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,360 : INFO : PROGRESS: at sentence #12890000, processed 212452797 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,397 : INFO : PROGRESS: at sentence #12900000, processed 212616694 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,436 : INFO : PROGRESS: at sentence #12910000, processed 212780880 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,474 : INFO : PROGRESS: at sentence #12920000, processed 212947496 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,512 : INFO : PROGRESS: at sentence #12930000, processed 213113049 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,550 : INFO : PROGRESS: at sentence #12940000, processed 213275993 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,588 : INFO : PROGRESS: at sentence #12950000, processed 213441809 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,625 : INFO : PROGRESS: at sentence #12960000, processed 213604559 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,664 : INFO : PROGRESS: at sentence #12970000, processed 213771462 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,702 : INFO : PROGRESS: at sentence #12980000, processed 213938453 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,739 : INFO : PROGRESS: at sentence #12990000, processed 214102494 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,777 : INFO : PROGRESS: at sentence #13000000, processed 214262813 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,815 : INFO : PROGRESS: at sentence #13010000, processed 214428461 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,852 : INFO : PROGRESS: at sentence #13020000, processed 214591779 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,891 : INFO : PROGRESS: at sentence #13030000, processed 214759312 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,928 : INFO : PROGRESS: at sentence #13040000, processed 214924371 words, keeping 20000 word types\n", - "2017-08-20 12:51:47,966 : INFO : PROGRESS: at sentence #13050000, processed 215088019 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,005 : INFO : PROGRESS: at sentence #13060000, processed 215256109 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,042 : INFO : PROGRESS: at sentence #13070000, processed 215418425 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,079 : INFO : PROGRESS: at sentence #13080000, processed 215584807 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,116 : INFO : PROGRESS: at sentence #13090000, processed 215743892 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,153 : INFO : PROGRESS: at sentence #13100000, processed 215905299 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,190 : INFO : PROGRESS: at sentence #13110000, processed 216067982 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,228 : INFO : PROGRESS: at sentence #13120000, processed 216232242 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,266 : INFO : PROGRESS: at sentence #13130000, processed 216397786 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,305 : INFO : PROGRESS: at sentence #13140000, processed 216562503 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,341 : INFO : PROGRESS: at sentence #13150000, processed 216724098 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,379 : INFO : PROGRESS: at sentence #13160000, processed 216886816 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,417 : INFO : PROGRESS: at sentence #13170000, processed 217052624 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,456 : INFO : PROGRESS: at sentence #13180000, processed 217214673 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,494 : INFO : PROGRESS: at sentence #13190000, processed 217378666 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,532 : INFO : PROGRESS: at sentence #13200000, processed 217542575 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,570 : INFO : PROGRESS: at sentence #13210000, processed 217707763 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,607 : INFO : PROGRESS: at sentence #13220000, processed 217867972 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,644 : INFO : PROGRESS: at sentence #13230000, processed 218032354 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,681 : INFO : PROGRESS: at sentence #13240000, processed 218193783 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,719 : INFO : PROGRESS: at sentence #13250000, processed 218359759 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,756 : INFO : PROGRESS: at sentence #13260000, processed 218522514 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,796 : INFO : PROGRESS: at sentence #13270000, processed 218687905 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,833 : INFO : PROGRESS: at sentence #13280000, processed 218851432 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,870 : INFO : PROGRESS: at sentence #13290000, processed 219014606 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,908 : INFO : PROGRESS: at sentence #13300000, processed 219180740 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,946 : INFO : PROGRESS: at sentence #13310000, processed 219343255 words, keeping 20000 word types\n", - "2017-08-20 12:51:48,984 : INFO : PROGRESS: at sentence #13320000, processed 219508143 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,021 : INFO : PROGRESS: at sentence #13330000, processed 219670425 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,060 : INFO : PROGRESS: at sentence #13340000, processed 219837754 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,097 : INFO : PROGRESS: at sentence #13350000, processed 220000925 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,005 : INFO : PROGRESS: at sentence #13360000, processed 220166893 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,042 : INFO : PROGRESS: at sentence #13370000, processed 220331390 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,079 : INFO : PROGRESS: at sentence #13380000, processed 220496299 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,115 : INFO : PROGRESS: at sentence #13390000, processed 220660949 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,152 : INFO : PROGRESS: at sentence #13400000, processed 220825165 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,191 : INFO : PROGRESS: at sentence #13410000, processed 220990417 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,228 : INFO : PROGRESS: at sentence #13420000, processed 221155327 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,266 : INFO : PROGRESS: at sentence #13430000, processed 221320197 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,304 : INFO : PROGRESS: at sentence #13440000, processed 221485979 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,343 : INFO : PROGRESS: at sentence #13450000, processed 221647707 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,380 : INFO : PROGRESS: at sentence #13460000, processed 221810637 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,418 : INFO : PROGRESS: at sentence #13470000, processed 221976124 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,457 : INFO : PROGRESS: at sentence #13480000, processed 222146061 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,495 : INFO : PROGRESS: at sentence #13490000, processed 222306849 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,533 : INFO : PROGRESS: at sentence #13500000, processed 222472150 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,570 : INFO : PROGRESS: at sentence #13510000, processed 222637852 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,608 : INFO : PROGRESS: at sentence #13520000, processed 222802697 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,646 : INFO : PROGRESS: at sentence #13530000, processed 222968551 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,685 : INFO : PROGRESS: at sentence #13540000, processed 223134957 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,724 : INFO : PROGRESS: at sentence #13550000, processed 223301087 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,762 : INFO : PROGRESS: at sentence #13560000, processed 223464033 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,801 : INFO : PROGRESS: at sentence #13570000, processed 223631134 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,840 : INFO : PROGRESS: at sentence #13580000, processed 223794525 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,878 : INFO : PROGRESS: at sentence #13590000, processed 223956293 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,918 : INFO : PROGRESS: at sentence #13600000, processed 224116760 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,958 : INFO : PROGRESS: at sentence #13610000, processed 224282159 words, keeping 20000 word types\n", - "2017-08-20 12:51:49,997 : INFO : PROGRESS: at sentence #13620000, processed 224445881 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,037 : INFO : PROGRESS: at sentence #13630000, processed 224612461 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,084 : INFO : PROGRESS: at sentence #13640000, processed 224774907 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,123 : INFO : PROGRESS: at sentence #13650000, processed 224938803 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,163 : INFO : PROGRESS: at sentence #13660000, processed 225107628 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,206 : INFO : PROGRESS: at sentence #13670000, processed 225272376 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,244 : INFO : PROGRESS: at sentence #13680000, processed 225432580 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,285 : INFO : PROGRESS: at sentence #13690000, processed 225596471 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,323 : INFO : PROGRESS: at sentence #13700000, processed 225758881 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,365 : INFO : PROGRESS: at sentence #13710000, processed 225921986 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,404 : INFO : PROGRESS: at sentence #13720000, processed 226083689 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,443 : INFO : PROGRESS: at sentence #13730000, processed 226248176 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,481 : INFO : PROGRESS: at sentence #13740000, processed 226410363 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,519 : INFO : PROGRESS: at sentence #13750000, processed 226573000 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,557 : INFO : PROGRESS: at sentence #13760000, processed 226734605 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,594 : INFO : PROGRESS: at sentence #13770000, processed 226896962 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,632 : INFO : PROGRESS: at sentence #13780000, processed 227060387 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,670 : INFO : PROGRESS: at sentence #13790000, processed 227226600 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,709 : INFO : PROGRESS: at sentence #13800000, processed 227393573 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,747 : INFO : PROGRESS: at sentence #13810000, processed 227557035 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,785 : INFO : PROGRESS: at sentence #13820000, processed 227726637 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,824 : INFO : PROGRESS: at sentence #13830000, processed 227891294 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,862 : INFO : PROGRESS: at sentence #13840000, processed 228059009 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,901 : INFO : PROGRESS: at sentence #13850000, processed 228222324 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,940 : INFO : PROGRESS: at sentence #13860000, processed 228387489 words, keeping 20000 word types\n", - "2017-08-20 12:51:50,978 : INFO : PROGRESS: at sentence #13870000, processed 228553033 words, keeping 20000 word types\n", - "2017-08-20 12:51:51,015 : INFO : PROGRESS: at sentence #13880000, processed 228718022 words, keeping 20000 word types\n", - "2017-08-20 12:51:51,052 : INFO : PROGRESS: at sentence #13890000, processed 228880643 words, keeping 20000 word types\n", - "2017-08-20 12:51:51,091 : INFO : PROGRESS: at sentence #13900000, processed 229047418 words, keeping 20000 word types\n", - "2017-08-20 12:51:51,129 : INFO : PROGRESS: at sentence #13910000, processed 229209428 words, keeping 20000 word types\n", - "2017-08-20 12:51:51,166 : INFO : PROGRESS: at sentence #13920000, processed 229373075 words, keeping 20000 word types\n", - "2017-08-20 12:51:51,205 : INFO : PROGRESS: at sentence #13930000, processed 229540585 words, keeping 20000 word types\n", - "2017-08-20 12:51:51,243 : INFO : PROGRESS: at sentence #13940000, processed 229704527 words, keeping 20000 word types\n", - "2017-08-20 12:51:51,281 : INFO : PROGRESS: at sentence #13950000, processed 229868646 words, keeping 20000 word types\n", - "2017-08-20 12:51:51,318 : INFO : collected 20000 word types from a corpus of 230030916 raw words and 13959792 sentences\n", - "2017-08-20 12:51:51,319 : INFO : Loading a fresh vocabulary\n", - "2017-08-20 12:51:51,366 : INFO : min_count=6 retains 20000 unique words (100% of original 20000, drops 0)\n", - "2017-08-20 12:51:51,368 : INFO : min_count=6 leaves 230030916 word corpus (100% of original 230030916, drops 0)\n", - "2017-08-20 12:51:51,420 : INFO : deleting the raw counts dictionary of 20000 items\n", - "2017-08-20 12:51:51,422 : INFO : sample=0.001 downsamples 46 most-common words\n", - "2017-08-20 12:51:51,424 : INFO : downsampling leaves estimated 167110516 word corpus (72.6% of prior 230030916)\n", - "2017-08-20 12:51:51,425 : INFO : estimated required memory for 20000 words and 200 dimensions: 42000000 bytes\n", - "2017-08-20 12:51:51,478 : INFO : resetting layer weights\n", - "2017-08-20 12:51:51,779 : INFO : training model with 12 workers on 20000 vocabulary and 200 features, using sg=1 hs=0 sample=0.001 negative=5 window=5\n", - "2017-08-20 12:51:52,791 : INFO : PROGRESS: at 0.14% examples, 1127028 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:51:53,813 : INFO : PROGRESS: at 0.28% examples, 1172615 words/s, in_qsize 23, out_qsize 1\n", - "2017-08-20 12:51:54,688 : INFO : PROGRESS: at 0.43% examples, 1188164 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:51:55,689 : INFO : PROGRESS: at 0.58% examples, 1199152 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:51:56,690 : INFO : PROGRESS: at 0.68% examples, 1139190 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:51:57,694 : INFO : PROGRESS: at 0.82% examples, 1129864 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:51:58,699 : INFO : PROGRESS: at 0.97% examples, 1152114 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:51:59,571 : INFO : PROGRESS: at 1.13% examples, 1173583 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:00,577 : INFO : PROGRESS: at 1.28% examples, 1184995 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:01,582 : INFO : PROGRESS: at 1.43% examples, 1192603 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:02,585 : INFO : PROGRESS: at 1.58% examples, 1195339 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:03,593 : INFO : PROGRESS: at 1.70% examples, 1178512 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:04,467 : INFO : PROGRESS: at 1.83% examples, 1170722 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:05,472 : INFO : PROGRESS: at 1.97% examples, 1173222 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:52:06,483 : INFO : PROGRESS: at 2.13% examples, 1181555 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:07,485 : INFO : PROGRESS: at 2.27% examples, 1183254 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:08,494 : INFO : PROGRESS: at 2.43% examples, 1190377 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:09,367 : INFO : PROGRESS: at 2.57% examples, 1189943 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:10,368 : INFO : PROGRESS: at 2.69% examples, 1176168 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:11,376 : INFO : PROGRESS: at 2.82% examples, 1173447 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:12,389 : INFO : PROGRESS: at 2.96% examples, 1171099 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:13,389 : INFO : PROGRESS: at 3.11% examples, 1175248 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:52:14,266 : INFO : PROGRESS: at 3.25% examples, 1176414 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:15,277 : INFO : PROGRESS: at 3.41% examples, 1180871 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:52:16,285 : INFO : PROGRESS: at 3.54% examples, 1177349 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:52:17,303 : INFO : PROGRESS: at 3.65% examples, 1168214 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:52:18,308 : INFO : PROGRESS: at 3.80% examples, 1170227 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:52:19,181 : INFO : PROGRESS: at 3.95% examples, 1174133 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:20,184 : INFO : PROGRESS: at 4.11% examples, 1178545 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:21,204 : INFO : PROGRESS: at 4.26% examples, 1179874 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:22,212 : INFO : PROGRESS: at 4.40% examples, 1180137 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:52:23,223 : INFO : PROGRESS: at 4.53% examples, 1176670 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:24,094 : INFO : PROGRESS: at 4.64% examples, 1170008 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:25,095 : INFO : PROGRESS: at 4.80% examples, 1173140 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:26,101 : INFO : PROGRESS: at 4.94% examples, 1173914 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:27,104 : INFO : PROGRESS: at 5.09% examples, 1175009 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:28,111 : INFO : PROGRESS: at 5.24% examples, 1177385 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:29,124 : INFO : PROGRESS: at 5.39% examples, 1179842 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:30,007 : INFO : PROGRESS: at 5.52% examples, 1175599 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:31,014 : INFO : PROGRESS: at 5.64% examples, 1172863 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:32,016 : INFO : PROGRESS: at 5.79% examples, 1173193 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:33,020 : INFO : PROGRESS: at 5.95% examples, 1177251 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:34,020 : INFO : PROGRESS: at 6.08% examples, 1176390 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:34,891 : INFO : PROGRESS: at 6.24% examples, 1179800 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:35,894 : INFO : PROGRESS: at 6.38% examples, 1179349 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:36,907 : INFO : PROGRESS: at 6.49% examples, 1173247 words/s, in_qsize 20, out_qsize 3\n", - "2017-08-20 12:52:37,925 : INFO : PROGRESS: at 6.64% examples, 1173910 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:38,926 : INFO : PROGRESS: at 6.78% examples, 1173780 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:52:39,796 : INFO : PROGRESS: at 6.93% examples, 1176658 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:40,801 : INFO : PROGRESS: at 7.07% examples, 1176793 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:41,805 : INFO : PROGRESS: at 7.22% examples, 1176765 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:42,806 : INFO : PROGRESS: at 7.35% examples, 1175923 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:52:43,841 : INFO : PROGRESS: at 7.47% examples, 1172004 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:44,720 : INFO : PROGRESS: at 7.61% examples, 1171837 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:45,724 : INFO : PROGRESS: at 7.75% examples, 1171830 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:46,735 : INFO : PROGRESS: at 7.90% examples, 1172316 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:47,738 : INFO : PROGRESS: at 8.04% examples, 1173439 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:48,757 : INFO : PROGRESS: at 8.20% examples, 1174960 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:52:49,639 : INFO : PROGRESS: at 8.33% examples, 1173225 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:50,640 : INFO : PROGRESS: at 8.44% examples, 1169548 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:51,649 : INFO : PROGRESS: at 8.59% examples, 1170905 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:52,651 : INFO : PROGRESS: at 8.75% examples, 1172697 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:53,654 : INFO : PROGRESS: at 8.89% examples, 1173363 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:52:54,530 : INFO : PROGRESS: at 9.04% examples, 1174169 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:55,548 : INFO : PROGRESS: at 9.19% examples, 1175089 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:52:56,549 : INFO : PROGRESS: at 9.31% examples, 1172005 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:52:57,551 : INFO : PROGRESS: at 9.42% examples, 1169309 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:58,555 : INFO : PROGRESS: at 9.57% examples, 1170325 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:52:59,431 : INFO : PROGRESS: at 9.73% examples, 1172077 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:00,434 : INFO : PROGRESS: at 9.88% examples, 1173730 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:01,438 : INFO : PROGRESS: at 10.04% examples, 1175328 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:02,439 : INFO : PROGRESS: at 10.19% examples, 1176203 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:03,447 : INFO : PROGRESS: at 10.30% examples, 1173090 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:04,326 : INFO : PROGRESS: at 10.42% examples, 1170737 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:53:05,326 : INFO : PROGRESS: at 10.57% examples, 1171484 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:06,329 : INFO : PROGRESS: at 10.72% examples, 1173095 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:07,355 : INFO : PROGRESS: at 10.86% examples, 1172296 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:08,356 : INFO : PROGRESS: at 11.01% examples, 1173871 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:09,227 : INFO : PROGRESS: at 11.15% examples, 1173380 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:10,239 : INFO : PROGRESS: at 11.27% examples, 1170964 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:11,241 : INFO : PROGRESS: at 11.41% examples, 1170443 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:12,242 : INFO : PROGRESS: at 11.55% examples, 1170500 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:13,245 : INFO : PROGRESS: at 11.70% examples, 1171445 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:14,116 : INFO : PROGRESS: at 11.85% examples, 1172373 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:15,131 : INFO : PROGRESS: at 12.01% examples, 1174161 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:16,141 : INFO : PROGRESS: at 12.13% examples, 1172706 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:17,142 : INFO : PROGRESS: at 12.25% examples, 1169994 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:18,150 : INFO : PROGRESS: at 12.40% examples, 1170774 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:19,156 : INFO : PROGRESS: at 12.55% examples, 1171957 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:20,031 : INFO : PROGRESS: at 12.71% examples, 1173287 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:21,044 : INFO : PROGRESS: at 12.86% examples, 1174179 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:22,058 : INFO : PROGRESS: at 13.01% examples, 1174716 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:23,068 : INFO : PROGRESS: at 13.13% examples, 1173107 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:24,071 : INFO : PROGRESS: at 13.24% examples, 1170496 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:24,945 : INFO : PROGRESS: at 13.40% examples, 1171975 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:25,955 : INFO : PROGRESS: at 13.55% examples, 1172189 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:26,959 : INFO : PROGRESS: at 13.69% examples, 1172415 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:27,961 : INFO : PROGRESS: at 13.83% examples, 1172730 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:28,964 : INFO : PROGRESS: at 13.98% examples, 1172939 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:29,837 : INFO : PROGRESS: at 14.10% examples, 1171731 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:53:30,842 : INFO : PROGRESS: at 14.22% examples, 1169640 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:31,846 : INFO : PROGRESS: at 14.37% examples, 1170123 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:32,848 : INFO : PROGRESS: at 14.51% examples, 1170418 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:33,848 : INFO : PROGRESS: at 14.67% examples, 1171642 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:34,733 : INFO : PROGRESS: at 14.82% examples, 1172392 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:35,739 : INFO : PROGRESS: at 14.96% examples, 1172076 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:36,751 : INFO : PROGRESS: at 15.07% examples, 1170096 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:37,752 : INFO : PROGRESS: at 15.19% examples, 1168528 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:38,759 : INFO : PROGRESS: at 15.34% examples, 1169136 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:39,635 : INFO : PROGRESS: at 15.48% examples, 1168857 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:40,636 : INFO : PROGRESS: at 15.62% examples, 1169359 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:41,637 : INFO : PROGRESS: at 15.76% examples, 1169129 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:42,646 : INFO : PROGRESS: at 15.91% examples, 1169394 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:43,648 : INFO : PROGRESS: at 16.02% examples, 1167338 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:44,517 : INFO : PROGRESS: at 16.15% examples, 1166324 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:45,518 : INFO : PROGRESS: at 16.30% examples, 1167438 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:46,537 : INFO : PROGRESS: at 16.44% examples, 1167139 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:47,549 : INFO : PROGRESS: at 16.59% examples, 1167765 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:48,549 : INFO : PROGRESS: at 16.73% examples, 1167386 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:49,418 : INFO : PROGRESS: at 16.87% examples, 1167738 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:50,423 : INFO : PROGRESS: at 16.98% examples, 1165954 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:51,427 : INFO : PROGRESS: at 17.14% examples, 1166775 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:52,436 : INFO : PROGRESS: at 17.29% examples, 1167286 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:53:53,455 : INFO : PROGRESS: at 17.43% examples, 1167518 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:54,329 : INFO : PROGRESS: at 17.58% examples, 1167978 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:55,334 : INFO : PROGRESS: at 17.72% examples, 1167884 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:56,335 : INFO : PROGRESS: at 17.85% examples, 1167247 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:57,356 : INFO : PROGRESS: at 17.96% examples, 1165387 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:58,362 : INFO : PROGRESS: at 18.11% examples, 1165753 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:53:59,237 : INFO : PROGRESS: at 18.26% examples, 1166274 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:54:00,238 : INFO : PROGRESS: at 18.41% examples, 1167031 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:54:01,244 : INFO : PROGRESS: at 18.56% examples, 1167816 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:02,251 : INFO : PROGRESS: at 18.71% examples, 1167965 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:03,258 : INFO : PROGRESS: at 18.84% examples, 1167437 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:54:04,128 : INFO : PROGRESS: at 18.95% examples, 1165520 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:05,135 : INFO : PROGRESS: at 19.11% examples, 1166470 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:54:06,151 : INFO : PROGRESS: at 19.25% examples, 1166655 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:07,158 : INFO : PROGRESS: at 19.40% examples, 1167336 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:08,168 : INFO : PROGRESS: at 19.55% examples, 1167691 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:09,168 : INFO : PROGRESS: at 19.70% examples, 1167942 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:10,048 : INFO : PROGRESS: at 19.82% examples, 1166819 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:11,058 : INFO : PROGRESS: at 19.93% examples, 1165272 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:12,059 : INFO : PROGRESS: at 20.08% examples, 1165885 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:13,059 : INFO : PROGRESS: at 20.23% examples, 1166515 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:14,063 : INFO : PROGRESS: at 20.39% examples, 1167324 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:14,939 : INFO : PROGRESS: at 20.54% examples, 1167773 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:15,945 : INFO : PROGRESS: at 20.69% examples, 1168604 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:16,946 : INFO : PROGRESS: at 20.81% examples, 1167174 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:17,954 : INFO : PROGRESS: at 20.93% examples, 1166050 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:18,972 : INFO : PROGRESS: at 21.08% examples, 1166637 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:19,846 : INFO : PROGRESS: at 21.23% examples, 1167265 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:20,851 : INFO : PROGRESS: at 21.38% examples, 1167802 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:54:21,868 : INFO : PROGRESS: at 21.52% examples, 1167902 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:22,884 : INFO : PROGRESS: at 21.67% examples, 1168488 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:54:23,888 : INFO : PROGRESS: at 21.79% examples, 1167056 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:24,757 : INFO : PROGRESS: at 21.92% examples, 1166369 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:25,763 : INFO : PROGRESS: at 22.06% examples, 1166481 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:54:26,769 : INFO : PROGRESS: at 22.21% examples, 1166946 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:27,779 : INFO : PROGRESS: at 22.36% examples, 1167526 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:28,781 : INFO : PROGRESS: at 22.50% examples, 1167616 words/s, in_qsize 19, out_qsize 4\n", - "2017-08-20 12:54:29,651 : INFO : PROGRESS: at 22.66% examples, 1168356 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:30,687 : INFO : PROGRESS: at 22.77% examples, 1166719 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:31,689 : INFO : PROGRESS: at 22.90% examples, 1166170 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:32,694 : INFO : PROGRESS: at 23.05% examples, 1166583 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:33,707 : INFO : PROGRESS: at 23.20% examples, 1167248 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:34,578 : INFO : PROGRESS: at 23.35% examples, 1167671 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:35,579 : INFO : PROGRESS: at 23.49% examples, 1167912 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:54:36,587 : INFO : PROGRESS: at 23.64% examples, 1167993 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:37,589 : INFO : PROGRESS: at 23.74% examples, 1166028 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:38,607 : INFO : PROGRESS: at 23.86% examples, 1165212 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:39,477 : INFO : PROGRESS: at 24.01% examples, 1165723 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:40,498 : INFO : PROGRESS: at 24.16% examples, 1166277 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:41,499 : INFO : PROGRESS: at 24.31% examples, 1166609 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:54:42,501 : INFO : PROGRESS: at 24.46% examples, 1166986 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:54:43,505 : INFO : PROGRESS: at 24.60% examples, 1166958 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:44,381 : INFO : PROGRESS: at 24.70% examples, 1165448 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:54:45,381 : INFO : PROGRESS: at 24.84% examples, 1165100 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:46,384 : INFO : PROGRESS: at 24.98% examples, 1165082 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:47,390 : INFO : PROGRESS: at 25.13% examples, 1165776 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:48,395 : INFO : PROGRESS: at 25.28% examples, 1165961 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:54:49,264 : INFO : PROGRESS: at 25.42% examples, 1166334 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:50,265 : INFO : PROGRESS: at 25.56% examples, 1166258 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:51,267 : INFO : PROGRESS: at 25.68% examples, 1165190 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:54:52,268 : INFO : PROGRESS: at 25.82% examples, 1165077 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:53,272 : INFO : PROGRESS: at 25.97% examples, 1165851 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:54,144 : INFO : PROGRESS: at 26.12% examples, 1166040 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:55,145 : INFO : PROGRESS: at 26.28% examples, 1166978 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:56,151 : INFO : PROGRESS: at 26.42% examples, 1167346 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:54:57,152 : INFO : PROGRESS: at 26.55% examples, 1166608 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:58,156 : INFO : PROGRESS: at 26.66% examples, 1165329 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:54:59,160 : INFO : PROGRESS: at 26.80% examples, 1165598 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:00,032 : INFO : PROGRESS: at 26.96% examples, 1166424 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:01,036 : INFO : PROGRESS: at 27.11% examples, 1166896 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:02,042 : INFO : PROGRESS: at 27.27% examples, 1167479 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:03,056 : INFO : PROGRESS: at 27.42% examples, 1167963 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:04,063 : INFO : PROGRESS: at 27.55% examples, 1167597 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:55:04,944 : INFO : PROGRESS: at 27.67% examples, 1166638 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:55:05,959 : INFO : PROGRESS: at 27.82% examples, 1166856 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:06,965 : INFO : PROGRESS: at 27.96% examples, 1167221 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:07,965 : INFO : PROGRESS: at 28.10% examples, 1167155 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:08,968 : INFO : PROGRESS: at 28.25% examples, 1167389 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:09,840 : INFO : PROGRESS: at 28.39% examples, 1167548 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:10,841 : INFO : PROGRESS: at 28.50% examples, 1166382 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:11,845 : INFO : PROGRESS: at 28.62% examples, 1165564 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:12,860 : INFO : PROGRESS: at 28.78% examples, 1166018 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:13,864 : INFO : PROGRESS: at 28.92% examples, 1166035 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:14,733 : INFO : PROGRESS: at 29.07% examples, 1166664 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:15,735 : INFO : PROGRESS: at 29.22% examples, 1167148 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:16,745 : INFO : PROGRESS: at 29.37% examples, 1167263 words/s, in_qsize 24, out_qsize 1\n", - "2017-08-20 12:55:17,775 : INFO : PROGRESS: at 29.48% examples, 1166000 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:18,778 : INFO : PROGRESS: at 29.60% examples, 1165428 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:19,646 : INFO : PROGRESS: at 29.76% examples, 1166252 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:55:20,654 : INFO : PROGRESS: at 29.90% examples, 1166113 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:21,658 : INFO : PROGRESS: at 30.05% examples, 1166575 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:22,659 : INFO : PROGRESS: at 30.20% examples, 1166946 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:23,671 : INFO : PROGRESS: at 30.35% examples, 1167286 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:24,553 : INFO : PROGRESS: at 30.46% examples, 1166110 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:25,558 : INFO : PROGRESS: at 30.60% examples, 1165971 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:26,560 : INFO : PROGRESS: at 30.74% examples, 1166133 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:55:27,566 : INFO : PROGRESS: at 30.88% examples, 1165961 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:28,568 : INFO : PROGRESS: at 31.02% examples, 1166043 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:29,437 : INFO : PROGRESS: at 31.17% examples, 1166229 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:30,444 : INFO : PROGRESS: at 31.30% examples, 1165909 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:31,451 : INFO : PROGRESS: at 31.41% examples, 1164843 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:32,453 : INFO : PROGRESS: at 31.56% examples, 1165075 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:33,456 : INFO : PROGRESS: at 31.71% examples, 1165482 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:34,323 : INFO : PROGRESS: at 31.86% examples, 1165816 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:35,324 : INFO : PROGRESS: at 32.00% examples, 1166046 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:36,333 : INFO : PROGRESS: at 32.15% examples, 1166142 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:37,342 : INFO : PROGRESS: at 32.27% examples, 1165578 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:38,347 : INFO : PROGRESS: at 32.38% examples, 1164406 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:39,218 : INFO : PROGRESS: at 32.53% examples, 1164868 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:40,222 : INFO : PROGRESS: at 32.68% examples, 1165168 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:41,227 : INFO : PROGRESS: at 32.83% examples, 1165431 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:42,240 : INFO : PROGRESS: at 32.97% examples, 1165341 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:43,254 : INFO : PROGRESS: at 33.12% examples, 1165587 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:55:44,128 : INFO : PROGRESS: at 33.23% examples, 1164595 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:55:45,150 : INFO : PROGRESS: at 33.35% examples, 1163789 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:46,158 : INFO : PROGRESS: at 33.50% examples, 1164067 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:47,163 : INFO : PROGRESS: at 33.64% examples, 1164182 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:48,168 : INFO : PROGRESS: at 33.80% examples, 1164717 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:49,172 : INFO : PROGRESS: at 33.94% examples, 1164710 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:50,042 : INFO : PROGRESS: at 34.09% examples, 1164998 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:51,045 : INFO : PROGRESS: at 34.19% examples, 1163870 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:52,062 : INFO : PROGRESS: at 34.33% examples, 1163654 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:53,064 : INFO : PROGRESS: at 34.48% examples, 1164081 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:54,066 : INFO : PROGRESS: at 34.62% examples, 1164127 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:55:54,936 : INFO : PROGRESS: at 34.77% examples, 1164504 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:55,951 : INFO : PROGRESS: at 34.92% examples, 1164476 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:56,956 : INFO : PROGRESS: at 35.04% examples, 1163975 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:57,962 : INFO : PROGRESS: at 35.16% examples, 1163191 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:55:58,969 : INFO : PROGRESS: at 35.30% examples, 1163268 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:55:59,843 : INFO : PROGRESS: at 35.45% examples, 1163604 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:00,850 : INFO : PROGRESS: at 35.59% examples, 1163838 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:01,851 : INFO : PROGRESS: at 35.75% examples, 1164239 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:02,854 : INFO : PROGRESS: at 35.89% examples, 1164406 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:03,855 : INFO : PROGRESS: at 36.02% examples, 1164134 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:04,730 : INFO : PROGRESS: at 36.13% examples, 1163048 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:56:05,732 : INFO : PROGRESS: at 36.29% examples, 1163528 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:06,733 : INFO : PROGRESS: at 36.43% examples, 1163517 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:07,739 : INFO : PROGRESS: at 36.58% examples, 1164007 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:08,742 : INFO : PROGRESS: at 36.73% examples, 1164277 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:09,610 : INFO : PROGRESS: at 36.88% examples, 1164472 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:10,615 : INFO : PROGRESS: at 37.01% examples, 1164188 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:56:11,617 : INFO : PROGRESS: at 37.12% examples, 1163300 words/s, in_qsize 23, out_qsize 1\n", - "2017-08-20 12:56:12,617 : INFO : PROGRESS: at 37.27% examples, 1163505 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:13,625 : INFO : PROGRESS: at 37.40% examples, 1163406 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:14,494 : INFO : PROGRESS: at 37.55% examples, 1163697 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:15,500 : INFO : PROGRESS: at 37.70% examples, 1163985 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:16,514 : INFO : PROGRESS: at 37.85% examples, 1164290 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:17,522 : INFO : PROGRESS: at 37.97% examples, 1163422 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:18,528 : INFO : PROGRESS: at 38.09% examples, 1162916 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:19,406 : INFO : PROGRESS: at 38.23% examples, 1162962 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:20,414 : INFO : PROGRESS: at 38.38% examples, 1163231 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:21,419 : INFO : PROGRESS: at 38.53% examples, 1163520 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:22,419 : INFO : PROGRESS: at 38.67% examples, 1163351 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:23,427 : INFO : PROGRESS: at 38.81% examples, 1163422 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:24,294 : INFO : PROGRESS: at 38.92% examples, 1162477 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:56:25,296 : INFO : PROGRESS: at 39.06% examples, 1162692 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:56:26,296 : INFO : PROGRESS: at 39.21% examples, 1162840 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:27,299 : INFO : PROGRESS: at 39.35% examples, 1162769 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:56:28,304 : INFO : PROGRESS: at 39.48% examples, 1162563 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:29,171 : INFO : PROGRESS: at 39.63% examples, 1162733 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:30,175 : INFO : PROGRESS: at 39.76% examples, 1162428 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:31,194 : INFO : PROGRESS: at 39.87% examples, 1161662 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:56:32,199 : INFO : PROGRESS: at 40.02% examples, 1162062 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:33,203 : INFO : PROGRESS: at 40.16% examples, 1162060 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:34,208 : INFO : PROGRESS: at 40.30% examples, 1162099 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:35,075 : INFO : PROGRESS: at 40.45% examples, 1162213 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:56:36,076 : INFO : PROGRESS: at 40.58% examples, 1161958 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:37,091 : INFO : PROGRESS: at 40.70% examples, 1161495 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:38,092 : INFO : PROGRESS: at 40.82% examples, 1160921 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:39,094 : INFO : PROGRESS: at 40.96% examples, 1160862 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:39,969 : INFO : PROGRESS: at 41.11% examples, 1161117 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:40,972 : INFO : PROGRESS: at 41.25% examples, 1161172 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:41,972 : INFO : PROGRESS: at 41.38% examples, 1161026 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:42,974 : INFO : PROGRESS: at 41.52% examples, 1161085 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:43,982 : INFO : PROGRESS: at 41.63% examples, 1160180 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:44,848 : INFO : PROGRESS: at 41.76% examples, 1160038 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:45,852 : INFO : PROGRESS: at 41.92% examples, 1160462 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:46,864 : INFO : PROGRESS: at 42.06% examples, 1160563 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:47,866 : INFO : PROGRESS: at 42.22% examples, 1161051 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:48,870 : INFO : PROGRESS: at 42.36% examples, 1161093 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:49,744 : INFO : PROGRESS: at 42.49% examples, 1160896 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:50,747 : INFO : PROGRESS: at 42.60% examples, 1160034 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:51,751 : INFO : PROGRESS: at 42.75% examples, 1160253 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:56:52,752 : INFO : PROGRESS: at 42.89% examples, 1160291 words/s, in_qsize 20, out_qsize 3\n", - "2017-08-20 12:56:53,760 : INFO : PROGRESS: at 43.03% examples, 1160424 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:54,626 : INFO : PROGRESS: at 43.19% examples, 1160825 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:55,638 : INFO : PROGRESS: at 43.33% examples, 1160944 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:56:56,647 : INFO : PROGRESS: at 43.45% examples, 1160413 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:57,666 : INFO : PROGRESS: at 43.57% examples, 1159742 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:58,671 : INFO : PROGRESS: at 43.71% examples, 1159736 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:56:59,557 : INFO : PROGRESS: at 43.86% examples, 1159971 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:00,564 : INFO : PROGRESS: at 44.00% examples, 1160151 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:01,572 : INFO : PROGRESS: at 44.15% examples, 1160426 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:02,589 : INFO : PROGRESS: at 44.29% examples, 1160364 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:03,602 : INFO : PROGRESS: at 44.41% examples, 1159710 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:04,471 : INFO : PROGRESS: at 44.53% examples, 1159358 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:57:05,475 : INFO : PROGRESS: at 44.69% examples, 1159731 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:06,484 : INFO : PROGRESS: at 44.83% examples, 1159798 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:07,489 : INFO : PROGRESS: at 44.98% examples, 1159993 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:08,492 : INFO : PROGRESS: at 45.12% examples, 1160093 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:57:09,359 : INFO : PROGRESS: at 45.26% examples, 1160205 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:10,360 : INFO : PROGRESS: at 45.38% examples, 1159717 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:11,367 : INFO : PROGRESS: at 45.50% examples, 1159278 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:12,376 : INFO : PROGRESS: at 45.64% examples, 1159275 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:13,380 : INFO : PROGRESS: at 45.79% examples, 1159329 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:14,245 : INFO : PROGRESS: at 45.94% examples, 1159663 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:57:15,249 : INFO : PROGRESS: at 46.08% examples, 1159661 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:57:16,270 : INFO : PROGRESS: at 46.22% examples, 1159701 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:57:17,275 : INFO : PROGRESS: at 46.32% examples, 1158866 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:57:18,279 : INFO : PROGRESS: at 46.46% examples, 1158859 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:19,280 : INFO : PROGRESS: at 46.62% examples, 1159266 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:57:20,149 : INFO : PROGRESS: at 46.77% examples, 1159668 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:21,150 : INFO : PROGRESS: at 46.92% examples, 1159998 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:22,152 : INFO : PROGRESS: at 47.06% examples, 1159882 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:23,171 : INFO : PROGRESS: at 47.18% examples, 1159403 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:57:24,173 : INFO : PROGRESS: at 47.29% examples, 1158638 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:57:25,042 : INFO : PROGRESS: at 47.43% examples, 1158865 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:26,047 : INFO : PROGRESS: at 47.57% examples, 1158794 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:27,062 : INFO : PROGRESS: at 47.71% examples, 1158686 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:28,086 : INFO : PROGRESS: at 47.85% examples, 1158807 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:57:29,100 : INFO : PROGRESS: at 48.00% examples, 1158912 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:57:29,972 : INFO : PROGRESS: at 48.12% examples, 1158537 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:30,983 : INFO : PROGRESS: at 48.24% examples, 1158050 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:31,994 : INFO : PROGRESS: at 48.40% examples, 1158332 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:32,999 : INFO : PROGRESS: at 48.53% examples, 1158245 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:57:34,005 : INFO : PROGRESS: at 48.68% examples, 1158586 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:34,871 : INFO : PROGRESS: at 48.83% examples, 1158651 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:57:35,876 : INFO : PROGRESS: at 48.97% examples, 1158763 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:36,878 : INFO : PROGRESS: at 49.08% examples, 1158165 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:37,880 : INFO : PROGRESS: at 49.21% examples, 1157968 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:57:38,881 : INFO : PROGRESS: at 49.36% examples, 1158173 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:39,754 : INFO : PROGRESS: at 49.50% examples, 1158192 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:57:40,755 : INFO : PROGRESS: at 49.65% examples, 1158341 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:41,756 : INFO : PROGRESS: at 49.78% examples, 1158348 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:42,761 : INFO : PROGRESS: at 49.92% examples, 1158201 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:43,763 : INFO : PROGRESS: at 50.03% examples, 1157621 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:57:44,631 : INFO : PROGRESS: at 50.18% examples, 1157757 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:45,638 : INFO : PROGRESS: at 50.32% examples, 1157946 words/s, in_qsize 24, out_qsize 1\n", - "2017-08-20 12:57:46,644 : INFO : PROGRESS: at 50.48% examples, 1158268 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:47,652 : INFO : PROGRESS: at 50.62% examples, 1158477 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:48,658 : INFO : PROGRESS: at 50.77% examples, 1158563 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:49,541 : INFO : PROGRESS: at 50.89% examples, 1158201 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:57:50,542 : INFO : PROGRESS: at 51.01% examples, 1157666 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:51,544 : INFO : PROGRESS: at 51.14% examples, 1157546 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:52,552 : INFO : PROGRESS: at 51.28% examples, 1157588 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:53,560 : INFO : PROGRESS: at 51.43% examples, 1157760 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:57:54,425 : INFO : PROGRESS: at 51.57% examples, 1157694 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:55,435 : INFO : PROGRESS: at 51.72% examples, 1158036 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:56,437 : INFO : PROGRESS: at 51.82% examples, 1157209 words/s, in_qsize 22, out_qsize 0\n", - "2017-08-20 12:57:57,442 : INFO : PROGRESS: at 51.95% examples, 1156993 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:58,447 : INFO : PROGRESS: at 52.10% examples, 1157047 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:57:59,319 : INFO : PROGRESS: at 52.25% examples, 1157247 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:00,326 : INFO : PROGRESS: at 52.40% examples, 1157463 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:01,332 : INFO : PROGRESS: at 52.54% examples, 1157570 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:58:02,339 : INFO : PROGRESS: at 52.67% examples, 1157404 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:03,348 : INFO : PROGRESS: at 52.79% examples, 1156946 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:04,220 : INFO : PROGRESS: at 52.93% examples, 1156895 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:05,227 : INFO : PROGRESS: at 53.08% examples, 1157187 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:58:06,231 : INFO : PROGRESS: at 53.22% examples, 1157239 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:07,240 : INFO : PROGRESS: at 53.37% examples, 1157307 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:08,240 : INFO : PROGRESS: at 53.51% examples, 1157371 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:09,240 : INFO : PROGRESS: at 53.64% examples, 1157215 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:10,113 : INFO : PROGRESS: at 53.76% examples, 1156695 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:11,115 : INFO : PROGRESS: at 53.88% examples, 1156492 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:12,116 : INFO : PROGRESS: at 54.02% examples, 1156465 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:13,117 : INFO : PROGRESS: at 54.17% examples, 1156636 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:58:14,123 : INFO : PROGRESS: at 54.31% examples, 1156737 words/s, in_qsize 24, out_qsize 2\n", - "2017-08-20 12:58:14,995 : INFO : PROGRESS: at 54.46% examples, 1156930 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:16,013 : INFO : PROGRESS: at 54.60% examples, 1156784 words/s, in_qsize 22, out_qsize 2\n", - "2017-08-20 12:58:17,020 : INFO : PROGRESS: at 54.71% examples, 1156131 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:18,025 : INFO : PROGRESS: at 54.85% examples, 1156329 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:19,028 : INFO : PROGRESS: at 55.00% examples, 1156369 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:58:19,895 : INFO : PROGRESS: at 55.15% examples, 1156644 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:20,895 : INFO : PROGRESS: at 55.28% examples, 1156618 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:21,898 : INFO : PROGRESS: at 55.43% examples, 1156863 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:22,909 : INFO : PROGRESS: at 55.56% examples, 1156658 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:23,912 : INFO : PROGRESS: at 55.68% examples, 1156134 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:58:24,785 : INFO : PROGRESS: at 55.83% examples, 1156440 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:25,785 : INFO : PROGRESS: at 55.98% examples, 1156590 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:26,786 : INFO : PROGRESS: at 56.12% examples, 1156652 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:27,795 : INFO : PROGRESS: at 56.26% examples, 1156689 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:28,799 : INFO : PROGRESS: at 56.42% examples, 1156958 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:29,663 : INFO : PROGRESS: at 56.52% examples, 1156345 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:30,672 : INFO : PROGRESS: at 56.65% examples, 1156149 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:31,676 : INFO : PROGRESS: at 56.79% examples, 1156114 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:32,706 : INFO : PROGRESS: at 56.93% examples, 1156055 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:33,708 : INFO : PROGRESS: at 57.08% examples, 1156324 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:34,573 : INFO : PROGRESS: at 57.22% examples, 1156333 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:58:35,582 : INFO : PROGRESS: at 57.36% examples, 1156178 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:36,590 : INFO : PROGRESS: at 57.47% examples, 1155657 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:58:37,595 : INFO : PROGRESS: at 57.60% examples, 1155532 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:38,611 : INFO : PROGRESS: at 57.75% examples, 1155590 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:39,479 : INFO : PROGRESS: at 57.90% examples, 1155828 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:40,486 : INFO : PROGRESS: at 58.05% examples, 1156088 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:58:41,486 : INFO : PROGRESS: at 58.17% examples, 1155734 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:42,501 : INFO : PROGRESS: at 58.31% examples, 1155636 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:43,509 : INFO : PROGRESS: at 58.41% examples, 1155022 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:44,375 : INFO : PROGRESS: at 58.55% examples, 1155030 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:45,382 : INFO : PROGRESS: at 58.70% examples, 1155124 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:58:46,395 : INFO : PROGRESS: at 58.84% examples, 1155212 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:47,400 : INFO : PROGRESS: at 58.99% examples, 1155298 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:48,402 : INFO : PROGRESS: at 59.14% examples, 1155557 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:49,266 : INFO : PROGRESS: at 59.28% examples, 1155514 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:50,296 : INFO : PROGRESS: at 59.40% examples, 1155093 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:51,298 : INFO : PROGRESS: at 59.54% examples, 1155136 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:52,300 : INFO : PROGRESS: at 59.68% examples, 1155261 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:58:53,302 : INFO : PROGRESS: at 59.84% examples, 1155533 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:54,309 : INFO : PROGRESS: at 59.97% examples, 1155445 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:55,186 : INFO : PROGRESS: at 60.13% examples, 1155767 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:56,191 : INFO : PROGRESS: at 60.25% examples, 1155493 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:57,193 : INFO : PROGRESS: at 60.36% examples, 1154912 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:58,198 : INFO : PROGRESS: at 60.50% examples, 1154913 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:58:59,206 : INFO : PROGRESS: at 60.64% examples, 1154957 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:00,069 : INFO : PROGRESS: at 60.80% examples, 1155300 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:01,075 : INFO : PROGRESS: at 60.93% examples, 1155264 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:02,075 : INFO : PROGRESS: at 61.08% examples, 1155388 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:03,079 : INFO : PROGRESS: at 61.20% examples, 1155110 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:59:04,079 : INFO : PROGRESS: at 61.31% examples, 1154580 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:04,943 : INFO : PROGRESS: at 61.46% examples, 1154737 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:59:05,950 : INFO : PROGRESS: at 61.60% examples, 1154894 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:06,966 : INFO : PROGRESS: at 61.75% examples, 1154919 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:07,971 : INFO : PROGRESS: at 61.89% examples, 1154986 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:08,978 : INFO : PROGRESS: at 62.04% examples, 1155108 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:59:09,843 : INFO : PROGRESS: at 62.15% examples, 1154566 words/s, in_qsize 19, out_qsize 1\n", - "2017-08-20 12:59:10,849 : INFO : PROGRESS: at 62.27% examples, 1154388 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:11,849 : INFO : PROGRESS: at 62.42% examples, 1154485 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:12,857 : INFO : PROGRESS: at 62.58% examples, 1154804 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:59:13,868 : INFO : PROGRESS: at 62.71% examples, 1154770 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:14,739 : INFO : PROGRESS: at 62.87% examples, 1154999 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:15,774 : INFO : PROGRESS: at 63.02% examples, 1155177 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:16,810 : INFO : PROGRESS: at 63.14% examples, 1154734 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:17,815 : INFO : PROGRESS: at 63.27% examples, 1154574 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:18,818 : INFO : PROGRESS: at 63.40% examples, 1154531 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:19,684 : INFO : PROGRESS: at 63.56% examples, 1154944 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:20,696 : INFO : PROGRESS: at 63.71% examples, 1155043 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:21,698 : INFO : PROGRESS: at 63.86% examples, 1155304 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:59:22,701 : INFO : PROGRESS: at 64.00% examples, 1155389 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:59:23,704 : INFO : PROGRESS: at 64.11% examples, 1154769 words/s, in_qsize 21, out_qsize 0\n", - "2017-08-20 12:59:24,567 : INFO : PROGRESS: at 64.23% examples, 1154581 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:59:25,568 : INFO : PROGRESS: at 64.38% examples, 1154701 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:26,572 : INFO : PROGRESS: at 64.53% examples, 1154921 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:27,573 : INFO : PROGRESS: at 64.66% examples, 1154835 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:28,573 : INFO : PROGRESS: at 64.81% examples, 1155055 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:29,437 : INFO : PROGRESS: at 64.95% examples, 1155070 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:30,455 : INFO : PROGRESS: at 65.06% examples, 1154527 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:31,460 : INFO : PROGRESS: at 65.18% examples, 1154209 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:59:32,460 : INFO : PROGRESS: at 65.33% examples, 1154438 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:33,463 : INFO : PROGRESS: at 65.48% examples, 1154585 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:34,327 : INFO : PROGRESS: at 65.63% examples, 1154793 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:35,329 : INFO : PROGRESS: at 65.79% examples, 1155134 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:36,329 : INFO : PROGRESS: at 65.92% examples, 1154978 words/s, in_qsize 19, out_qsize 4\n", - "2017-08-20 12:59:37,339 : INFO : PROGRESS: at 66.03% examples, 1154562 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:38,343 : INFO : PROGRESS: at 66.17% examples, 1154489 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:39,347 : INFO : PROGRESS: at 66.31% examples, 1154512 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:59:40,219 : INFO : PROGRESS: at 66.45% examples, 1154596 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 12:59:41,221 : INFO : PROGRESS: at 66.59% examples, 1154647 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:42,224 : INFO : PROGRESS: at 66.73% examples, 1154591 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:43,240 : INFO : PROGRESS: at 66.85% examples, 1154241 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:44,244 : INFO : PROGRESS: at 66.96% examples, 1153843 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:45,130 : INFO : PROGRESS: at 67.11% examples, 1153952 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:46,131 : INFO : PROGRESS: at 67.26% examples, 1154102 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 12:59:47,135 : INFO : PROGRESS: at 67.39% examples, 1154093 words/s, in_qsize 20, out_qsize 3\n", - "2017-08-20 12:59:48,141 : INFO : PROGRESS: at 67.54% examples, 1154307 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:49,150 : INFO : PROGRESS: at 67.69% examples, 1154417 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 12:59:50,019 : INFO : PROGRESS: at 67.81% examples, 1154106 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:51,021 : INFO : PROGRESS: at 67.94% examples, 1153908 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:52,030 : INFO : PROGRESS: at 68.09% examples, 1154170 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:53,034 : INFO : PROGRESS: at 68.23% examples, 1154128 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:54,040 : INFO : PROGRESS: at 68.36% examples, 1153995 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:54,905 : INFO : PROGRESS: at 68.51% examples, 1154141 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:55,909 : INFO : PROGRESS: at 68.64% examples, 1154000 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:56,914 : INFO : PROGRESS: at 68.74% examples, 1153418 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:57,926 : INFO : PROGRESS: at 68.87% examples, 1153303 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:58,929 : INFO : PROGRESS: at 69.03% examples, 1153558 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 12:59:59,804 : INFO : PROGRESS: at 69.16% examples, 1153530 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:00,809 : INFO : PROGRESS: at 69.32% examples, 1153779 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:00:01,815 : INFO : PROGRESS: at 69.47% examples, 1154010 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:02,821 : INFO : PROGRESS: at 69.61% examples, 1153986 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:03,841 : INFO : PROGRESS: at 69.73% examples, 1153637 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:04,705 : INFO : PROGRESS: at 69.87% examples, 1153651 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:05,711 : INFO : PROGRESS: at 70.02% examples, 1153823 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:06,720 : INFO : PROGRESS: at 70.16% examples, 1153873 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:07,739 : INFO : PROGRESS: at 70.31% examples, 1154001 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:08,747 : INFO : PROGRESS: at 70.45% examples, 1154079 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:09,634 : INFO : PROGRESS: at 70.58% examples, 1153826 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 13:00:10,639 : INFO : PROGRESS: at 70.69% examples, 1153460 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 13:00:11,648 : INFO : PROGRESS: at 70.83% examples, 1153458 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:12,658 : INFO : PROGRESS: at 70.97% examples, 1153448 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:13,660 : INFO : PROGRESS: at 71.12% examples, 1153620 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:14,524 : INFO : PROGRESS: at 71.27% examples, 1153841 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:15,526 : INFO : PROGRESS: at 71.42% examples, 1153988 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:00:16,530 : INFO : PROGRESS: at 71.54% examples, 1153729 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:17,532 : INFO : PROGRESS: at 71.65% examples, 1153290 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:18,536 : INFO : PROGRESS: at 71.81% examples, 1153535 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:19,405 : INFO : PROGRESS: at 71.96% examples, 1153731 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:20,411 : INFO : PROGRESS: at 72.10% examples, 1153774 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:21,414 : INFO : PROGRESS: at 72.25% examples, 1153977 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:22,417 : INFO : PROGRESS: at 72.39% examples, 1154010 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:23,425 : INFO : PROGRESS: at 72.51% examples, 1153619 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:24,291 : INFO : PROGRESS: at 72.63% examples, 1153362 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:25,297 : INFO : PROGRESS: at 72.79% examples, 1153622 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:26,303 : INFO : PROGRESS: at 72.92% examples, 1153486 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:27,311 : INFO : PROGRESS: at 73.07% examples, 1153632 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:28,328 : INFO : PROGRESS: at 73.21% examples, 1153663 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 13:00:29,338 : INFO : PROGRESS: at 73.36% examples, 1153800 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:30,238 : INFO : PROGRESS: at 73.48% examples, 1153429 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:31,241 : INFO : PROGRESS: at 73.60% examples, 1153222 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:32,245 : INFO : PROGRESS: at 73.75% examples, 1153350 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:33,250 : INFO : PROGRESS: at 73.89% examples, 1153422 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:34,251 : INFO : PROGRESS: at 74.03% examples, 1153391 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:00:35,114 : INFO : PROGRESS: at 74.17% examples, 1153383 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:00:36,117 : INFO : PROGRESS: at 74.30% examples, 1153231 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:37,121 : INFO : PROGRESS: at 74.40% examples, 1152653 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:38,128 : INFO : PROGRESS: at 74.53% examples, 1152650 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:39,138 : INFO : PROGRESS: at 74.68% examples, 1152753 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:40,008 : INFO : PROGRESS: at 74.83% examples, 1152923 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:41,011 : INFO : PROGRESS: at 74.98% examples, 1152999 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:42,014 : INFO : PROGRESS: at 75.12% examples, 1153074 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:43,022 : INFO : PROGRESS: at 75.25% examples, 1152900 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:44,026 : INFO : PROGRESS: at 75.36% examples, 1152485 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:44,891 : INFO : PROGRESS: at 75.50% examples, 1152613 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:45,895 : INFO : PROGRESS: at 75.65% examples, 1152804 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:00:46,900 : INFO : PROGRESS: at 75.80% examples, 1152938 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:47,902 : INFO : PROGRESS: at 75.95% examples, 1153127 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:48,902 : INFO : PROGRESS: at 76.10% examples, 1153258 words/s, in_qsize 22, out_qsize 0\n", - "2017-08-20 13:00:49,783 : INFO : PROGRESS: at 76.24% examples, 1153139 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:50,788 : INFO : PROGRESS: at 76.34% examples, 1152685 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:51,795 : INFO : PROGRESS: at 76.49% examples, 1152763 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:52,797 : INFO : PROGRESS: at 76.62% examples, 1152720 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:53,811 : INFO : PROGRESS: at 76.77% examples, 1152770 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:54,681 : INFO : PROGRESS: at 76.91% examples, 1152817 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:55,688 : INFO : PROGRESS: at 77.06% examples, 1152972 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:56,722 : INFO : PROGRESS: at 77.17% examples, 1152425 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 13:00:57,739 : INFO : PROGRESS: at 77.30% examples, 1152273 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:58,754 : INFO : PROGRESS: at 77.45% examples, 1152424 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:00:59,619 : INFO : PROGRESS: at 77.59% examples, 1152534 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:00,629 : INFO : PROGRESS: at 77.74% examples, 1152697 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:01,632 : INFO : PROGRESS: at 77.89% examples, 1152768 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:02,637 : INFO : PROGRESS: at 78.02% examples, 1152660 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 13:01:03,652 : INFO : PROGRESS: at 78.13% examples, 1152287 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:04,517 : INFO : PROGRESS: at 78.28% examples, 1152409 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 13:01:05,518 : INFO : PROGRESS: at 78.43% examples, 1152572 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:06,520 : INFO : PROGRESS: at 78.57% examples, 1152570 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:07,525 : INFO : PROGRESS: at 78.71% examples, 1152674 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:08,538 : INFO : PROGRESS: at 78.86% examples, 1152729 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:09,406 : INFO : PROGRESS: at 78.99% examples, 1152669 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:10,418 : INFO : PROGRESS: at 79.11% examples, 1152253 words/s, in_qsize 23, out_qsize 3\n", - "2017-08-20 13:01:11,425 : INFO : PROGRESS: at 79.24% examples, 1152254 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:12,429 : INFO : PROGRESS: at 79.39% examples, 1152321 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:01:13,430 : INFO : PROGRESS: at 79.53% examples, 1152399 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:14,302 : INFO : PROGRESS: at 79.69% examples, 1152618 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:15,305 : INFO : PROGRESS: at 79.84% examples, 1152775 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:16,311 : INFO : PROGRESS: at 79.97% examples, 1152652 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 13:01:17,332 : INFO : PROGRESS: at 80.08% examples, 1152210 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:18,334 : INFO : PROGRESS: at 80.21% examples, 1152120 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 13:01:19,336 : INFO : PROGRESS: at 80.35% examples, 1152146 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 13:01:20,199 : INFO : PROGRESS: at 80.50% examples, 1152333 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:21,207 : INFO : PROGRESS: at 80.64% examples, 1152356 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:22,207 : INFO : PROGRESS: at 80.79% examples, 1152482 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:23,212 : INFO : PROGRESS: at 80.92% examples, 1152447 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:24,235 : INFO : PROGRESS: at 81.03% examples, 1151961 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:25,096 : INFO : PROGRESS: at 81.17% examples, 1152049 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 13:01:26,096 : INFO : PROGRESS: at 81.30% examples, 1151972 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:27,098 : INFO : PROGRESS: at 81.45% examples, 1152167 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:28,100 : INFO : PROGRESS: at 81.60% examples, 1152226 words/s, in_qsize 24, out_qsize 2\n", - "2017-08-20 13:01:29,102 : INFO : PROGRESS: at 81.75% examples, 1152447 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:01:29,967 : INFO : PROGRESS: at 81.88% examples, 1152284 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:30,971 : INFO : PROGRESS: at 81.98% examples, 1151802 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:31,974 : INFO : PROGRESS: at 82.14% examples, 1152017 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:32,980 : INFO : PROGRESS: at 82.28% examples, 1152044 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:33,995 : INFO : PROGRESS: at 82.43% examples, 1152204 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:34,862 : INFO : PROGRESS: at 82.58% examples, 1152343 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:35,874 : INFO : PROGRESS: at 82.73% examples, 1152453 words/s, in_qsize 22, out_qsize 3\n", - "2017-08-20 13:01:36,880 : INFO : PROGRESS: at 82.84% examples, 1152174 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:37,881 : INFO : PROGRESS: at 82.96% examples, 1151814 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:38,883 : INFO : PROGRESS: at 83.10% examples, 1151924 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:39,745 : INFO : PROGRESS: at 83.25% examples, 1152102 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:40,747 : INFO : PROGRESS: at 83.40% examples, 1152182 words/s, in_qsize 21, out_qsize 0\n", - "2017-08-20 13:01:41,758 : INFO : PROGRESS: at 83.53% examples, 1152162 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:42,762 : INFO : PROGRESS: at 83.68% examples, 1152244 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:43,768 : INFO : PROGRESS: at 83.80% examples, 1152037 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:44,637 : INFO : PROGRESS: at 83.92% examples, 1151751 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:01:45,640 : INFO : PROGRESS: at 84.06% examples, 1151818 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:46,642 : INFO : PROGRESS: at 84.21% examples, 1151904 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:47,643 : INFO : PROGRESS: at 84.35% examples, 1152001 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 13:01:48,645 : INFO : PROGRESS: at 84.50% examples, 1152188 words/s, in_qsize 24, out_qsize 1\n", - "2017-08-20 13:01:49,516 : INFO : PROGRESS: at 84.65% examples, 1152323 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:50,518 : INFO : PROGRESS: at 84.76% examples, 1151946 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:51,531 : INFO : PROGRESS: at 84.89% examples, 1151776 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:52,533 : INFO : PROGRESS: at 85.02% examples, 1151681 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:53,540 : INFO : PROGRESS: at 85.16% examples, 1151674 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:54,402 : INFO : PROGRESS: at 85.29% examples, 1151663 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:55,403 : INFO : PROGRESS: at 85.45% examples, 1151876 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:01:56,410 : INFO : PROGRESS: at 85.57% examples, 1151725 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:57,410 : INFO : PROGRESS: at 85.69% examples, 1151399 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:58,415 : INFO : PROGRESS: at 85.82% examples, 1151277 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:01:59,417 : INFO : PROGRESS: at 85.96% examples, 1151382 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:02:00,283 : INFO : PROGRESS: at 86.12% examples, 1151645 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:01,294 : INFO : PROGRESS: at 86.27% examples, 1151756 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:02,300 : INFO : PROGRESS: at 86.42% examples, 1151891 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:03,307 : INFO : PROGRESS: at 86.55% examples, 1151855 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:04,320 : INFO : PROGRESS: at 86.66% examples, 1151474 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:05,180 : INFO : PROGRESS: at 86.81% examples, 1151618 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:06,181 : INFO : PROGRESS: at 86.96% examples, 1151762 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:07,190 : INFO : PROGRESS: at 87.11% examples, 1151897 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:08,191 : INFO : PROGRESS: at 87.25% examples, 1151947 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:02:09,192 : INFO : PROGRESS: at 87.40% examples, 1152052 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:10,053 : INFO : PROGRESS: at 87.52% examples, 1151839 words/s, in_qsize 19, out_qsize 4\n", - "2017-08-20 13:02:11,053 : INFO : PROGRESS: at 87.62% examples, 1151360 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:12,055 : INFO : PROGRESS: at 87.74% examples, 1151213 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:13,055 : INFO : PROGRESS: at 87.90% examples, 1151410 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:14,057 : INFO : PROGRESS: at 88.04% examples, 1151423 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:14,919 : INFO : PROGRESS: at 88.20% examples, 1151728 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:15,929 : INFO : PROGRESS: at 88.35% examples, 1151926 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:16,934 : INFO : PROGRESS: at 88.47% examples, 1151673 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:17,959 : INFO : PROGRESS: at 88.58% examples, 1151237 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:02:18,966 : INFO : PROGRESS: at 88.73% examples, 1151378 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:19,830 : INFO : PROGRESS: at 88.88% examples, 1151541 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:20,832 : INFO : PROGRESS: at 89.02% examples, 1151519 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:02:21,839 : INFO : PROGRESS: at 89.16% examples, 1151599 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:02:22,848 : INFO : PROGRESS: at 89.30% examples, 1151607 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:23,855 : INFO : PROGRESS: at 89.42% examples, 1151362 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 13:02:24,717 : INFO : PROGRESS: at 89.53% examples, 1151075 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:25,718 : INFO : PROGRESS: at 89.67% examples, 1151112 words/s, in_qsize 24, out_qsize 1\n", - "2017-08-20 13:02:26,722 : INFO : PROGRESS: at 89.82% examples, 1151244 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:27,726 : INFO : PROGRESS: at 89.96% examples, 1151196 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:28,729 : INFO : PROGRESS: at 90.11% examples, 1151317 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:29,589 : INFO : PROGRESS: at 90.25% examples, 1151363 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 13:02:30,609 : INFO : PROGRESS: at 90.37% examples, 1151187 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:31,613 : INFO : PROGRESS: at 90.49% examples, 1150862 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:32,630 : INFO : PROGRESS: at 90.63% examples, 1150873 words/s, in_qsize 24, out_qsize 2\n", - "2017-08-20 13:02:33,639 : INFO : PROGRESS: at 90.77% examples, 1150895 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:34,500 : INFO : PROGRESS: at 90.91% examples, 1151009 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:35,505 : INFO : PROGRESS: at 91.07% examples, 1151162 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:36,515 : INFO : PROGRESS: at 91.21% examples, 1151257 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:37,521 : INFO : PROGRESS: at 91.34% examples, 1151074 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:38,525 : INFO : PROGRESS: at 91.45% examples, 1150784 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 13:02:39,387 : INFO : PROGRESS: at 91.60% examples, 1150894 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 13:02:40,408 : INFO : PROGRESS: at 91.74% examples, 1150903 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:02:41,411 : INFO : PROGRESS: at 91.88% examples, 1150969 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:42,422 : INFO : PROGRESS: at 92.02% examples, 1150946 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:43,422 : INFO : PROGRESS: at 92.16% examples, 1150970 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:02:44,428 : INFO : PROGRESS: at 92.28% examples, 1150727 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:02:45,289 : INFO : PROGRESS: at 92.41% examples, 1150609 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:46,309 : INFO : PROGRESS: at 92.56% examples, 1150686 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:47,312 : INFO : PROGRESS: at 92.70% examples, 1150771 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:48,319 : INFO : PROGRESS: at 92.85% examples, 1150924 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:49,322 : INFO : PROGRESS: at 93.00% examples, 1151009 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:02:50,183 : INFO : PROGRESS: at 93.15% examples, 1151126 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:51,206 : INFO : PROGRESS: at 93.26% examples, 1150726 words/s, in_qsize 22, out_qsize 2\n", - "2017-08-20 13:02:52,224 : INFO : PROGRESS: at 93.39% examples, 1150663 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:53,254 : INFO : PROGRESS: at 93.54% examples, 1150799 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:54,260 : INFO : PROGRESS: at 93.69% examples, 1150880 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:55,122 : INFO : PROGRESS: at 93.84% examples, 1151069 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:56,138 : INFO : PROGRESS: at 93.98% examples, 1150982 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:57,151 : INFO : PROGRESS: at 94.11% examples, 1150875 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:58,153 : INFO : PROGRESS: at 94.22% examples, 1150546 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:02:59,156 : INFO : PROGRESS: at 94.36% examples, 1150576 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:00,021 : INFO : PROGRESS: at 94.50% examples, 1150660 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:01,024 : INFO : PROGRESS: at 94.65% examples, 1150756 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 13:03:02,027 : INFO : PROGRESS: at 94.79% examples, 1150788 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:03,044 : INFO : PROGRESS: at 94.92% examples, 1150584 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:04,051 : INFO : PROGRESS: at 95.05% examples, 1150546 words/s, in_qsize 24, out_qsize 0\n", - "2017-08-20 13:03:04,922 : INFO : PROGRESS: at 95.17% examples, 1150268 words/s, in_qsize 24, out_qsize 2\n", - "2017-08-20 13:03:05,922 : INFO : PROGRESS: at 95.31% examples, 1150283 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:06,939 : INFO : PROGRESS: at 95.44% examples, 1150167 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:07,945 : INFO : PROGRESS: at 95.58% examples, 1150277 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:08,951 : INFO : PROGRESS: at 95.73% examples, 1150354 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:09,810 : INFO : PROGRESS: at 95.88% examples, 1150565 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:03:10,810 : INFO : PROGRESS: at 96.00% examples, 1150329 words/s, in_qsize 24, out_qsize 2\n", - "2017-08-20 13:03:11,811 : INFO : PROGRESS: at 96.12% examples, 1150061 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:12,814 : INFO : PROGRESS: at 96.27% examples, 1150206 words/s, in_qsize 21, out_qsize 2\n", - "2017-08-20 13:03:13,815 : INFO : PROGRESS: at 96.41% examples, 1150282 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:14,678 : INFO : PROGRESS: at 96.57% examples, 1150445 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:15,684 : INFO : PROGRESS: at 96.71% examples, 1150456 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:16,687 : INFO : PROGRESS: at 96.86% examples, 1150610 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:17,694 : INFO : PROGRESS: at 96.97% examples, 1150344 words/s, in_qsize 22, out_qsize 2\n", - "2017-08-20 13:03:18,708 : INFO : PROGRESS: at 97.10% examples, 1150143 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:19,568 : INFO : PROGRESS: at 97.24% examples, 1150249 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:03:20,579 : INFO : PROGRESS: at 97.39% examples, 1150287 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:03:21,581 : INFO : PROGRESS: at 97.53% examples, 1150357 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:03:22,588 : INFO : PROGRESS: at 97.68% examples, 1150443 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:23,596 : INFO : PROGRESS: at 97.82% examples, 1150424 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:24,457 : INFO : PROGRESS: at 97.92% examples, 1150057 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:25,469 : INFO : PROGRESS: at 98.05% examples, 1149895 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:26,469 : INFO : PROGRESS: at 98.18% examples, 1149828 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:27,472 : INFO : PROGRESS: at 98.33% examples, 1150000 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:28,476 : INFO : PROGRESS: at 98.49% examples, 1150168 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:29,479 : INFO : PROGRESS: at 98.63% examples, 1150219 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:30,344 : INFO : PROGRESS: at 98.77% examples, 1150306 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:31,345 : INFO : PROGRESS: at 98.88% examples, 1149947 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:32,354 : INFO : PROGRESS: at 99.01% examples, 1149846 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:33,361 : INFO : PROGRESS: at 99.16% examples, 1149888 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:34,363 : INFO : PROGRESS: at 99.30% examples, 1149989 words/s, in_qsize 22, out_qsize 1\n", - "2017-08-20 13:03:35,226 : INFO : PROGRESS: at 99.45% examples, 1150147 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:36,227 : INFO : PROGRESS: at 99.60% examples, 1150192 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:37,238 : INFO : PROGRESS: at 99.74% examples, 1150199 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:38,240 : INFO : PROGRESS: at 99.86% examples, 1149987 words/s, in_qsize 23, out_qsize 0\n", - "2017-08-20 13:03:39,242 : INFO : PROGRESS: at 99.98% examples, 1149840 words/s, in_qsize 20, out_qsize 0\n", - "2017-08-20 13:03:39,293 : INFO : worker thread finished; awaiting finish of 11 more threads\n", - "2017-08-20 13:03:39,295 : INFO : worker thread finished; awaiting finish of 10 more threads\n", - "2017-08-20 13:03:39,300 : INFO : worker thread finished; awaiting finish of 9 more threads\n", - "2017-08-20 13:03:39,302 : INFO : worker thread finished; awaiting finish of 8 more threads\n", - "2017-08-20 13:03:39,309 : INFO : worker thread finished; awaiting finish of 7 more threads\n", - "2017-08-20 13:03:39,312 : INFO : worker thread finished; awaiting finish of 6 more threads\n", - "2017-08-20 13:03:39,314 : INFO : worker thread finished; awaiting finish of 5 more threads\n", - "2017-08-20 13:03:39,329 : INFO : worker thread finished; awaiting finish of 4 more threads\n", - "2017-08-20 13:03:39,330 : INFO : worker thread finished; awaiting finish of 3 more threads\n", - "2017-08-20 13:03:39,333 : INFO : worker thread finished; awaiting finish of 2 more threads\n", - "2017-08-20 13:03:39,334 : INFO : worker thread finished; awaiting finish of 1 more threads\n", - "2017-08-20 13:03:39,338 : INFO : worker thread finished; awaiting finish of 0 more threads\n", - "2017-08-20 13:03:39,339 : INFO : training on 1150154580 raw words (835548615 effective words) took 726.6s, 1149884 effective words/s\n" - ] - } - ], - "source": [ - "logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)\n", - "# use skip-gram\n", - "word2vec_model = gensim.models.Word2Vec(doc_lst, min_count=6, size=EMBEDDING_DIM, max_vocab_size=MAX_VOCAB_SIZE, sg=1, workers=os.cpu_count())" - ] - }, - { - "cell_type": "code", - "execution_count": 78, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Total 20000 word vectors.\n" - ] - } - ], - "source": [ - "embeddings_index = {}\n", - "\n", - "for word in word2vec_model.wv.vocab:\n", - " coefs = np.asarray(word2vec_model.wv[word], dtype='float32')\n", - " embeddings_index[word] = coefs\n", - "\n", - "print('Total %s word vectors.' % len(embeddings_index))" - ] - }, - { - "cell_type": "code", - "execution_count": 86, - "metadata": { - "collapsed": true, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "# Initial embedding\n", - "embedding_matrix = np.zeros((MAX_NB_WORDS + 1, EMBEDDING_DIM))\n", - "\n", - "for word, i in word_index.items():\n", - " embedding_vector = embeddings_index.get(word)\n", - " if embedding_vector is not None and i < MAX_NB_WORDS:\n", - " embedding_matrix[i] = embedding_vector\n", - " elif i == MAX_NB_WORDS:\n", - " # index MAX_NB_WORDS in data corresponds to 'UNK'\n", - " embedding_matrix[i] = embeddings_index['UNK']" - ] - }, - { - "cell_type": "code", - "execution_count": 98, - "metadata": { - "collapsed": true, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "np.save('/data/tmp/embedding_matrix', embedding_matrix)" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true, - "scrolled": true - }, - "outputs": [], - "source": [ - "# building Hierachical Attention network\n", - "\n", - "REG_PARAM = 1e-10\n", - "l2_reg = regularizers.l2(REG_PARAM)\n", - "\n", - "embedding_layer = Embedding(MAX_NB_WORDS + 1,\n", - " EMBEDDING_DIM,\n", - " input_length=MAX_SENT_LENGTH,\n", - " trainable=True,\n", - " mask_zero=True,\n", - " embeddings_regularizer=l2_reg,\n", - " weights=[embedding_matrix])" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "CONTEXT_DIM = 100\n", - "\n", - "class AttLayer(Layer):\n", - " def __init__(self, regularizer=None, **kwargs):\n", - " self.regularizer = regularizer\n", - " self.supports_masking = True\n", - " super(AttLayer, self).__init__(**kwargs)\n", - "\n", - " def build(self, input_shape):\n", - " assert len(input_shape) == 3 \n", - " self.W = self.add_weight(name='W', shape=(input_shape[-1], CONTEXT_DIM), initializer='normal', trainable=True, \n", - " regularizer=self.regularizer)\n", - " self.b = self.add_weight(name='b', shape=(CONTEXT_DIM,), initializer='normal', trainable=True, \n", - " regularizer=self.regularizer)\n", - " self.u = self.add_weight(name='u', shape=(CONTEXT_DIM,), initializer='normal', trainable=True, \n", - " regularizer=self.regularizer) \n", - " super(AttLayer, self).build(input_shape) # be sure you call this somewhere!\n", - "\n", - " def call(self, x, mask=None):\n", - " eij = K.dot(K.tanh(K.dot(x, self.W) + self.b), self.u)\n", - " ai = K.exp(eij)\n", - " alphas = ai / K.sum(ai, axis=1).dimshuffle(0, 'x')\n", - " if mask is not None:\n", - " # use only the inputs specified by the mask\n", - " alphas *= mask\n", - " weighted_input = x * alphas.dimshuffle(0, 1, 'x')\n", - " return weighted_input.sum(axis=1)\n", - "\n", - " def compute_output_shape(self, input_shape):\n", - " return (input_shape[0], input_shape[-1])\n", - " \n", - " def get_config(self):\n", - " config = {}\n", - " base_config = super(AttLayer, self).get_config()\n", - " return dict(list(base_config.items()) + list(config.items()))\n", - "\n", - " def compute_mask(self, inputs, mask):\n", - " return None" - ] - }, - { - "cell_type": "code", - "execution_count": 9, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "GPU_IMPL = 2 # for more efficient RNN implementation on GPU\n", - "GRU_UNITS = 50 # dimensionality of GRU output\n", - "\n", - "sentence_input = Input(shape=(MAX_SENT_LENGTH,), dtype='int32')\n", - "embedded_sequences = embedding_layer(sentence_input)\n", - "l_lstm = Bidirectional(GRU(GRU_UNITS, return_sequences=True, kernel_regularizer=l2_reg, implementation=GPU_IMPL))(embedded_sequences)\n", - "l_att = AttLayer(regularizer=l2_reg)(l_lstm) \n", - "sentEncoder = Model(sentence_input, l_att)\n", - "\n", - "review_input = Input(shape=(MAX_SENTS, MAX_SENT_LENGTH), dtype='int32')\n", - "review_encoder = TimeDistributed(sentEncoder)(review_input)\n", - "l_lstm_sent = Bidirectional(GRU(GRU_UNITS, return_sequences=True, kernel_regularizer=l2_reg, implementation=GPU_IMPL))(review_encoder)\n", - "l_att_sent = AttLayer(regularizer=l2_reg)(l_lstm_sent) \n", - "preds = Dense(n_classes, activation='softmax', kernel_regularizer=l2_reg)(l_att_sent)\n", - "model = Model(review_input, preds)" - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "model.compile(loss='categorical_crossentropy',\n", - " optimizer=optimizers.SGD(lr=0.01, momentum=0.9),\n", - " metrics=['acc'])" - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "_________________________________________________________________\n", - "Layer (type) Output Shape Param # \n", - "=================================================================\n", - "input_4 (InputLayer) (None, 30, 100) 0 \n", - "_________________________________________________________________\n", - "time_distributed_2 (TimeDist (None, 30, 100) 4085700 \n", - "_________________________________________________________________\n", - "bidirectional_4 (Bidirection (None, 30, 100) 45300 \n", - "_________________________________________________________________\n", - "att_layer_4 (AttLayer) (None, 100) 10200 \n", - "_________________________________________________________________\n", - "dense_1 (Dense) (None, 5) 505 \n", - "=================================================================\n", - "Total params: 4,141,705\n", - "Trainable params: 4,141,705\n", - "Non-trainable params: 0\n", - "_________________________________________________________________\n" - ] - } - ], - "source": [ - "model.summary()" - ] - }, - { - "cell_type": "code", - "execution_count": 12, - "metadata": { - "collapsed": true, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "history = History()\n", - "csv_logger = CSVLogger('./hatt_model_' + str(REG_PARAM) + '_log',\n", - " separator=',',\n", - " append=True)" - ] - }, - { - "cell_type": "code", - "execution_count": 13, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "# Order training data by the number of sentences in document (as suggested in the [Yang et al.] paper) \n", - "doc_lengths = [len(r) for r in reviews]\n", - "ind = np.argsort(doc_lengths)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "model fitting - Hierachical attention network\n", - "Epoch 1/10\n" - ] - } - ], - "source": [ - "t1 = time.time()\n", - "\n", - "print(\"model fitting - Hierachical attention network\")\n", - "model.fit(x_train[ind,:,:], y_train[ind,:], epochs=10, batch_size=64, shuffle=False, \n", - " callbacks=[history, csv_logger], verbose=2)\n", - "\n", - "t2 = time.time()" - ] - }, - { - "cell_type": "code", - "execution_count": 22, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "# save model\n", - "model.save('./hatt_model_{}.h5'.format(REG_PARAM))" - ] - }, - { - "cell_type": "code", - "execution_count": 23, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [ - "np.savetxt('./hatt_model_{}_time.txt'.format(REG_PARAM), [REG_PARAM, (t2-t1) / 3600])\n", - "with open('./hatt_model_{}_history.txt'.format(REG_PARAM), \"w\") as res_file:\n", - " res_file.write(str(history.history))" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": false, - "deletable": true, - "editable": true - }, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.5.2" - } - }, - "nbformat": 4, - "nbformat_minor": 2 -}