OPTION VALUES: Model directory: ./IOB2+0.07/ Training data file: train.tagged Testing data file: test.tagged Unlabeled data file: data.untagged Model file: model.txt Training log file (this one): trainlog.txt Label representation: IOB2 Second-order Markov CRFs Number of labels: 4 Number of training sequences: 886 (one data partition) Number of testing sequences: 43 (one data partition) Number of unlabeled sequences: 0 Number of context predicates: 709326 Number of features: 1351627 Feature rare threshold: 1 Context predicate rare threshold: 1 Using multiple rare thresholds for features: 0 Highlight feature: 0 Number of training iterations: 130 Initial lambda value: 0.0700 Sigma square (for smoothing): 100.0000 Epsilon for L-BFGS convergence: 0.000100 Number of approximated hessian matrixes: 7 Start to train ... Iteration: 1 Log-likelihood = -1662362.257781 Norm (log-likelihood gradient vector) = 434614.415781 Norm (lambda vector) = 81.381646 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20957 20156 96.18 97.98 97.07 b-np 12220 11989 11311 94.34 92.56 93.44 i-np 13660 13505 12766 94.53 93.46 93.99 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.02 94.67 94.84 Avg2. 46451 46451 44233 95.23 95.23 95.23 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 11989 10734 89.53 87.84 88.68 ----- ------ ----- ----- ------- ------- ------------- Avg1. 89.53 87.84 88.68 Avg2. 12220 11989 10734 89.53 87.84 88.68 Current max chunk-based F1: 88.68 (iteration 1) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 2 Log-likelihood = -1272435.329055 Norm (log-likelihood gradient vector) = 332168.866926 Norm (lambda vector) = 81.408526 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 21400 19788 92.47 96.19 94.29 b-np 12220 11174 10175 91.06 83.27 86.99 i-np 13660 13877 12442 89.66 91.08 90.37 ----- ------ ----- ----- ------- ------- ------------- Avg1. 91.06 90.18 90.62 Avg2. 46451 46451 42405 91.29 91.29 91.29 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 11174 9170 82.07 75.04 78.40 ----- ------ ----- ----- ------- ------- ------------- Avg1. 82.07 75.04 78.40 Avg2. 12220 11174 9170 82.07 75.04 78.40 Current max chunk-based F1: 88.68 (iteration 1) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 3 Log-likelihood = -588543.747168 Norm (log-likelihood gradient vector) = 127607.589791 Norm (lambda vector) = 81.657398 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20869 19950 95.60 96.98 96.28 b-np 12220 11087 10495 94.66 85.88 90.06 i-np 13660 14495 12950 89.34 94.80 91.99 ----- ------ ----- ----- ------- ------- ------------- Avg1. 93.20 92.56 92.88 Avg2. 46451 46451 43395 93.42 93.42 93.42 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 11087 9539 86.04 78.06 81.86 ----- ------ ----- ----- ------- ------- ------------- Avg1. 86.04 78.06 81.86 Avg2. 12220 11087 9539 86.04 78.06 81.86 Current max chunk-based F1: 88.68 (iteration 1) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 4 Log-likelihood = -494005.361898 Norm (log-likelihood gradient vector) = 76354.313139 Norm (lambda vector) = 81.740525 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 21138 20176 95.45 98.08 96.75 b-np 12220 11783 11141 94.55 91.17 92.83 i-np 13660 13530 12784 94.49 93.59 94.03 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.83 94.28 94.55 Avg2. 46451 46451 44101 94.94 94.94 94.94 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 11783 10500 89.11 85.92 87.49 ----- ------ ----- ----- ------- ------- ------------- Avg1. 89.11 85.92 87.49 Avg2. 12220 11783 10500 89.11 85.92 87.49 Current max chunk-based F1: 88.68 (iteration 1) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 5 Log-likelihood = -430632.773419 Norm (log-likelihood gradient vector) = 66893.673387 Norm (lambda vector) = 81.858460 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 21012 20199 96.13 98.19 97.15 b-np 12220 11845 11299 95.39 92.46 93.90 i-np 13660 13594 12941 95.20 94.74 94.97 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.57 95.13 95.35 Avg2. 46451 46451 44439 95.67 95.67 95.67 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 11845 10816 91.31 88.51 89.89 ----- ------ ----- ----- ------- ------- ------------- Avg1. 91.31 88.51 89.89 Avg2. 12220 11845 10816 91.31 88.51 89.89 Current max chunk-based F1: 89.89 (iteration 5) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 6 Log-likelihood = -361190.197758 Norm (log-likelihood gradient vector) = 59377.805495 Norm (lambda vector) = 82.132380 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20916 20235 96.74 98.37 97.55 b-np 12220 12101 11529 95.27 94.35 94.81 i-np 13660 13434 12913 96.12 94.53 95.32 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.05 95.75 95.90 Avg2. 46451 46451 44677 96.18 96.18 96.18 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12101 11064 91.43 90.54 90.98 ----- ------ ----- ----- ------- ------- ------------- Avg1. 91.43 90.54 90.98 Avg2. 12220 12101 11064 91.43 90.54 90.98 Current max chunk-based F1: 90.98 (iteration 6) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 7 Log-likelihood = -324991.246938 Norm (log-likelihood gradient vector) = 37053.420449 Norm (lambda vector) = 82.342617 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20850 20268 97.21 98.53 97.86 b-np 12220 12120 11619 95.87 95.08 95.47 i-np 13660 13481 12994 96.39 95.12 95.75 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.49 96.24 96.37 Avg2. 46451 46451 44881 96.62 96.62 96.62 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12120 11190 92.33 91.57 91.95 ----- ------ ----- ----- ------- ------- ------------- Avg1. 92.33 91.57 91.95 Avg2. 12220 12120 11190 92.33 91.57 91.95 Current max chunk-based F1: 91.95 (iteration 7) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 8 Log-likelihood = -294622.277746 Norm (log-likelihood gradient vector) = 30519.729549 Norm (lambda vector) = 82.783826 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20635 20210 97.94 98.25 98.09 b-np 12220 12161 11712 96.31 95.84 96.07 i-np 13660 13655 13143 96.25 96.22 96.23 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.83 96.77 96.80 Avg2. 46451 46451 45065 97.02 97.02 97.02 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12161 11307 92.98 92.53 92.75 ----- ------ ----- ----- ------- ------- ------------- Avg1. 92.98 92.53 92.75 Avg2. 12220 12161 11307 92.98 92.53 92.75 Current max chunk-based F1: 92.75 (iteration 8) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 9 Log-likelihood = -261253.994769 Norm (log-likelihood gradient vector) = 34584.149625 Norm (lambda vector) = 83.666925 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20853 20322 97.45 98.79 98.12 b-np 12220 12145 11714 96.45 95.86 96.15 i-np 13660 13453 13048 96.99 95.52 96.25 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.96 96.72 96.84 Avg2. 46451 46451 45084 97.06 97.06 97.06 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12145 11328 93.27 92.70 92.99 ----- ------ ----- ----- ------- ------- ------------- Avg1. 93.27 92.70 92.99 Avg2. 12220 12145 11328 93.27 92.70 92.99 Current max chunk-based F1: 92.99 (iteration 9) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 10 Log-likelihood = -244569.934206 Norm (log-likelihood gradient vector) = 29848.746679 Norm (lambda vector) = 84.404019 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20787 20315 97.73 98.76 98.24 b-np 12220 12139 11741 96.72 96.08 96.40 i-np 13660 13525 13114 96.96 96.00 96.48 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.14 96.95 97.04 Avg2. 46451 46451 45170 97.24 97.24 97.24 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12139 11365 93.62 93.00 93.31 ----- ------ ----- ----- ------- ------- ------------- Avg1. 93.62 93.00 93.31 Avg2. 12220 12139 11365 93.62 93.00 93.31 Current max chunk-based F1: 93.31 (iteration 10) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 11 Log-likelihood = -234158.750576 Norm (log-likelihood gradient vector) = 19909.038659 Norm (lambda vector) = 84.803857 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20748 20313 97.90 98.75 98.32 b-np 12220 12172 11779 96.77 96.39 96.58 i-np 13660 13531 13140 97.11 96.19 96.65 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.26 97.11 97.19 Avg2. 46451 46451 45232 97.38 97.38 97.38 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12172 11416 93.79 93.42 93.60 ----- ------ ----- ----- ------- ------- ------------- Avg1. 93.79 93.42 93.60 Avg2. 12220 12172 11416 93.79 93.42 93.60 Current max chunk-based F1: 93.60 (iteration 11) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 12 Log-likelihood = -219218.245192 Norm (log-likelihood gradient vector) = 16279.205010 Norm (lambda vector) = 85.480746 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20574 20240 98.38 98.39 98.38 b-np 12220 12068 11740 97.28 96.07 96.67 i-np 13660 13809 13282 96.18 97.23 96.71 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.28 97.23 97.26 Avg2. 46451 46451 45262 97.44 97.44 97.44 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12068 11357 94.11 92.94 93.52 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.11 92.94 93.52 Avg2. 12220 12068 11357 94.11 92.94 93.52 Current max chunk-based F1: 93.60 (iteration 11) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 13 Log-likelihood = -212444.506542 Norm (log-likelihood gradient vector) = 36066.913178 Norm (lambda vector) = 86.299050 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20658 20295 98.24 98.66 98.45 b-np 12220 12153 11797 97.07 96.54 96.80 i-np 13660 13640 13226 96.96 96.82 96.89 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.43 97.34 97.38 Avg2. 46451 46451 45318 97.56 97.56 97.56 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12153 11452 94.23 93.72 93.97 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.23 93.72 93.97 Avg2. 12220 12153 11452 94.23 93.72 93.97 Current max chunk-based F1: 93.97 (iteration 13) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 14 Log-likelihood = -206335.114894 Norm (log-likelihood gradient vector) = 21557.381280 Norm (lambda vector) = 86.631665 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20727 20329 98.08 98.82 98.45 b-np 12220 12207 11831 96.92 96.82 96.87 i-np 13660 13517 13172 97.45 96.43 96.93 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.48 97.36 97.42 Avg2. 46451 46451 45332 97.59 97.59 97.59 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12207 11504 94.24 94.14 94.19 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.24 94.14 94.19 Avg2. 12220 12207 11504 94.24 94.14 94.19 Current max chunk-based F1: 94.19 (iteration 14) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 15 Log-likelihood = -201826.731531 Norm (log-likelihood gradient vector) = 14208.156467 Norm (lambda vector) = 86.902067 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20759 20342 97.99 98.89 98.44 b-np 12220 12214 11841 96.95 96.90 96.92 i-np 13660 13478 13158 97.63 96.33 96.97 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.52 97.37 97.45 Avg2. 46451 46451 45341 97.61 97.61 97.61 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12214 11529 94.39 94.35 94.37 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.39 94.35 94.37 Avg2. 12220 12214 11529 94.39 94.35 94.37 Current max chunk-based F1: 94.37 (iteration 15) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 16 Log-likelihood = -197631.354773 Norm (log-likelihood gradient vector) = 14046.786076 Norm (lambda vector) = 87.267473 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20727 20337 98.12 98.86 98.49 b-np 12220 12182 11844 97.23 96.92 97.07 i-np 13660 13542 13205 97.51 96.67 97.09 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.62 97.48 97.55 Avg2. 46451 46451 45386 97.71 97.71 97.71 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12182 11540 94.73 94.44 94.58 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.73 94.44 94.58 Avg2. 12220 12182 11540 94.73 94.44 94.58 Current max chunk-based F1: 94.58 (iteration 16) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 17 Log-likelihood = -188908.072707 Norm (log-likelihood gradient vector) = 14644.385588 Norm (lambda vector) = 87.974873 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20817 20364 97.82 98.99 98.41 b-np 12220 12358 11916 96.42 97.51 96.96 i-np 13660 13276 13041 98.23 95.47 96.83 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.49 97.32 97.41 Avg2. 46451 46451 45321 97.57 97.57 97.57 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12358 11598 93.85 94.91 94.38 ----- ------ ----- ----- ------- ------- ------------- Avg1. 93.85 94.91 94.38 Avg2. 12220 12358 11598 93.85 94.91 94.38 Current max chunk-based F1: 94.58 (iteration 16) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 18 Log-likelihood = -184254.733531 Norm (log-likelihood gradient vector) = 49667.367123 Norm (lambda vector) = 89.642160 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20702 20331 98.21 98.83 98.52 b-np 12220 12226 11880 97.17 97.22 97.19 i-np 13660 13523 13209 97.68 96.70 97.19 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.69 97.58 97.63 Avg2. 46451 46451 45420 97.78 97.78 97.78 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12226 11589 94.79 94.84 94.81 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.79 94.84 94.81 Avg2. 12220 12226 11589 94.79 94.84 94.81 Current max chunk-based F1: 94.81 (iteration 18) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 19 Log-likelihood = -170057.907088 Norm (log-likelihood gradient vector) = 15874.779562 Norm (lambda vector) = 89.820448 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20646 20304 98.34 98.70 98.52 b-np 12220 12179 11853 97.32 97.00 97.16 i-np 13660 13626 13256 97.28 97.04 97.16 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.65 97.58 97.62 Avg2. 46451 46451 45413 97.77 97.77 97.77 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12179 11553 94.86 94.54 94.70 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.86 94.54 94.70 Avg2. 12220 12179 11553 94.86 94.54 94.70 Current max chunk-based F1: 94.81 (iteration 18) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 20 Log-likelihood = -164119.024612 Norm (log-likelihood gradient vector) = 9747.493302 Norm (lambda vector) = 90.070864 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20601 20287 98.48 98.62 98.55 b-np 12220 12136 11836 97.53 96.86 97.19 i-np 13660 13714 13307 97.03 97.42 97.22 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.68 97.63 97.65 Avg2. 46451 46451 45430 97.80 97.80 97.80 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12136 11539 95.08 94.43 94.75 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.08 94.43 94.75 Avg2. 12220 12136 11539 95.08 94.43 94.75 Current max chunk-based F1: 94.81 (iteration 18) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 21 Log-likelihood = -155640.814128 Norm (log-likelihood gradient vector) = 9006.315813 Norm (lambda vector) = 90.638041 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20606 20290 98.47 98.63 98.55 b-np 12220 12139 11837 97.51 96.87 97.19 i-np 13660 13706 13302 97.05 97.38 97.22 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.68 97.63 97.65 Avg2. 46451 46451 45429 97.80 97.80 97.80 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12139 11539 95.06 94.43 94.74 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.06 94.43 94.74 Avg2. 12220 12139 11539 95.06 94.43 94.74 Current max chunk-based F1: 94.81 (iteration 18) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 22 Log-likelihood = -147771.488415 Norm (log-likelihood gradient vector) = 7718.173519 Norm (lambda vector) = 91.348903 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20355 20107 98.78 97.74 98.26 b-np 12220 11910 11671 97.99 95.51 96.73 i-np 13660 14186 13414 94.56 98.20 96.34 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.11 97.15 97.13 Avg2. 46451 46451 45192 97.29 97.29 97.29 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 11910 11285 94.75 92.35 93.54 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.75 92.35 93.54 Avg2. 12220 11910 11285 94.75 92.35 93.54 Current max chunk-based F1: 94.81 (iteration 18) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 23 Log-likelihood = -142228.250467 Norm (log-likelihood gradient vector) = 41237.085242 Norm (lambda vector) = 93.202366 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20531 20247 98.62 98.42 98.52 b-np 12220 12067 11798 97.77 96.55 97.15 i-np 13660 13853 13357 96.42 97.78 97.10 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.60 97.58 97.59 Avg2. 46451 46451 45402 97.74 97.74 97.74 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12067 11473 95.08 93.89 94.48 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.08 93.89 94.48 Avg2. 12220 12067 11473 95.08 93.89 94.48 Current max chunk-based F1: 94.81 (iteration 18) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 24 Log-likelihood = -142771.628694 Norm (log-likelihood gradient vector) = 16494.263468 Norm (lambda vector) = 92.039783 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20580 20280 98.54 98.59 98.56 b-np 12220 12119 11835 97.66 96.85 97.25 i-np 13660 13752 13325 96.89 97.55 97.22 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.70 97.66 97.68 Avg2. 46451 46451 45440 97.82 97.82 97.82 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12119 11527 95.12 94.33 94.72 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.12 94.33 94.72 Avg2. 12220 12119 11527 95.12 94.33 94.72 Current max chunk-based F1: 94.81 (iteration 18) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 25 Log-likelihood = -135623.437500 Norm (log-likelihood gradient vector) = 7485.223091 Norm (lambda vector) = 93.008258 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20614 20302 98.49 98.69 98.59 b-np 12220 12164 11869 97.57 97.13 97.35 i-np 13660 13673 13299 97.26 97.36 97.31 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.78 97.73 97.75 Avg2. 46451 46451 45470 97.89 97.89 97.89 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12164 11574 95.15 94.71 94.93 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.15 94.71 94.93 Avg2. 12220 12164 11574 95.15 94.71 94.93 Current max chunk-based F1: 94.93 (iteration 25) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 26 Log-likelihood = -129774.239345 Norm (log-likelihood gradient vector) = 7527.549535 Norm (lambda vector) = 94.559102 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20613 20309 98.53 98.73 98.63 b-np 12220 12198 11895 97.52 97.34 97.43 i-np 13660 13640 13289 97.43 97.28 97.36 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.82 97.78 97.80 Avg2. 46451 46451 45493 97.94 97.94 97.94 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12198 11606 95.15 94.98 95.06 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.15 94.98 95.06 Avg2. 12220 12198 11606 95.15 94.98 95.06 Current max chunk-based F1: 95.06 (iteration 26) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 27 Log-likelihood = -124581.323362 Norm (log-likelihood gradient vector) = 6314.972633 Norm (lambda vector) = 95.668768 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20607 20311 98.56 98.74 98.65 b-np 12220 12159 11882 97.72 97.23 97.48 i-np 13660 13685 13323 97.35 97.53 97.44 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.88 97.83 97.86 Avg2. 46451 46451 45516 97.99 97.99 97.99 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12159 11603 95.43 94.95 95.19 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.43 94.95 95.19 Avg2. 12220 12159 11603 95.43 94.95 95.19 Current max chunk-based F1: 95.19 (iteration 27) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 28 Log-likelihood = -121511.919374 Norm (log-likelihood gradient vector) = 6141.287047 Norm (lambda vector) = 97.349949 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20645 20327 98.46 98.81 98.64 b-np 12220 12267 11936 97.30 97.68 97.49 i-np 13660 13539 13238 97.78 96.91 97.34 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.85 97.80 97.82 Avg2. 46451 46451 45501 97.95 97.95 97.95 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12267 11655 95.01 95.38 95.19 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.01 95.38 95.19 Avg2. 12220 12267 11655 95.01 95.38 95.19 Current max chunk-based F1: 95.19 (iteration 28) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 29 Log-likelihood = -120715.274060 Norm (log-likelihood gradient vector) = 16364.302150 Norm (lambda vector) = 98.405673 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20592 20314 98.65 98.75 98.70 b-np 12220 12197 11909 97.64 97.45 97.55 i-np 13660 13662 13315 97.46 97.47 97.47 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.92 97.89 97.90 Avg2. 46451 46451 45538 98.03 98.03 98.03 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12197 11636 95.40 95.22 95.31 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.40 95.22 95.31 Avg2. 12220 12197 11636 95.40 95.22 95.31 Current max chunk-based F1: 95.31 (iteration 29) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 30 Log-likelihood = -117407.699435 Norm (log-likelihood gradient vector) = 6560.419455 Norm (lambda vector) = 98.786140 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20587 20319 98.70 98.77 98.74 b-np 12220 12179 11907 97.77 97.44 97.60 i-np 13660 13685 13339 97.47 97.65 97.56 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.98 97.95 97.97 Avg2. 46451 46451 45565 98.09 98.09 98.09 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12179 11645 95.62 95.29 95.45 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.62 95.29 95.45 Avg2. 12220 12179 11645 95.62 95.29 95.45 Current max chunk-based F1: 95.45 (iteration 30) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 31 Log-likelihood = -117031.604876 Norm (log-likelihood gradient vector) = 7042.237986 Norm (lambda vector) = 98.927932 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20608 20324 98.62 98.80 98.71 b-np 12220 12164 11898 97.81 97.36 97.59 i-np 13660 13679 13327 97.43 97.56 97.49 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.95 97.91 97.93 Avg2. 46451 46451 45549 98.06 98.06 98.06 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12164 11630 95.61 95.17 95.39 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.61 95.17 95.39 Avg2. 12220 12164 11630 95.61 95.17 95.39 Current max chunk-based F1: 95.45 (iteration 30) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 32 Log-likelihood = -115290.487941 Norm (log-likelihood gradient vector) = 6972.280738 Norm (lambda vector) = 99.394178 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20593 20332 98.73 98.84 98.79 b-np 12220 12148 11905 98.00 97.42 97.71 i-np 13660 13710 13362 97.46 97.82 97.64 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.06 98.03 98.05 Avg2. 46451 46451 45599 98.17 98.17 98.17 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12148 11644 95.85 95.29 95.57 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.85 95.29 95.57 Avg2. 12220 12148 11644 95.85 95.29 95.57 Current max chunk-based F1: 95.57 (iteration 32) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 33 Log-likelihood = -111666.654493 Norm (log-likelihood gradient vector) = 6679.347355 Norm (lambda vector) = 100.298265 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20562 20302 98.74 98.69 98.71 b-np 12220 12129 11887 98.00 97.27 97.64 i-np 13660 13760 13354 97.05 97.76 97.40 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.93 97.91 97.92 Avg2. 46451 46451 45543 98.05 98.05 98.05 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12129 11593 95.58 94.87 95.22 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.58 94.87 95.22 Avg2. 12220 12129 11593 95.58 94.87 95.22 Current max chunk-based F1: 95.57 (iteration 32) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 34 Log-likelihood = -109547.874328 Norm (log-likelihood gradient vector) = 23726.093972 Norm (lambda vector) = 102.009070 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20573 20320 98.77 98.78 98.78 b-np 12220 12145 11906 98.03 97.43 97.73 i-np 13660 13733 13369 97.35 97.87 97.61 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.05 98.03 98.04 Avg2. 46451 46451 45595 98.16 98.16 98.16 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12145 11642 95.86 95.27 95.56 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.86 95.27 95.56 Avg2. 12220 12145 11642 95.86 95.27 95.56 Current max chunk-based F1: 95.57 (iteration 32) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 35 Log-likelihood = -108833.718445 Norm (log-likelihood gradient vector) = 11009.962082 Norm (lambda vector) = 101.040245 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20643 20356 98.61 98.95 98.78 b-np 12220 12224 11947 97.73 97.77 97.75 i-np 13660 13584 13297 97.89 97.34 97.61 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.08 98.02 98.05 Avg2. 46451 46451 45600 98.17 98.17 98.17 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12224 11690 95.63 95.66 95.65 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.63 95.66 95.65 Avg2. 12220 12224 11690 95.63 95.66 95.65 Current max chunk-based F1: 95.65 (iteration 35) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 36 Log-likelihood = -105506.039124 Norm (log-likelihood gradient vector) = 6218.890345 Norm (lambda vector) = 101.800032 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20624 20352 98.68 98.94 98.81 b-np 12220 12225 11955 97.79 97.83 97.81 i-np 13660 13602 13314 97.88 97.47 97.67 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.12 98.08 98.10 Avg2. 46451 46451 45621 98.21 98.21 98.21 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12225 11701 95.71 95.75 95.73 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.71 95.75 95.73 Avg2. 12220 12225 11701 95.71 95.75 95.73 Current max chunk-based F1: 95.73 (iteration 36) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 37 Log-likelihood = -103464.506323 Norm (log-likelihood gradient vector) = 5955.554920 Norm (lambda vector) = 102.137506 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20604 20351 98.77 98.93 98.85 b-np 12220 12204 11954 97.95 97.82 97.89 i-np 13660 13643 13348 97.84 97.72 97.78 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.19 98.16 98.17 Avg2. 46451 46451 45653 98.28 98.28 98.28 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12204 11711 95.96 95.83 95.90 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.96 95.83 95.90 Avg2. 12220 12204 11711 95.96 95.83 95.90 Current max chunk-based F1: 95.90 (iteration 37) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 38 Log-likelihood = -100917.013329 Norm (log-likelihood gradient vector) = 4304.336692 Norm (lambda vector) = 102.713181 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20581 20336 98.81 98.86 98.83 b-np 12220 12197 11940 97.89 97.71 97.80 i-np 13660 13673 13353 97.66 97.75 97.71 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.12 98.11 98.11 Avg2. 46451 46451 45629 98.23 98.23 98.23 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12197 11689 95.84 95.65 95.74 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.84 95.65 95.74 Avg2. 12220 12197 11689 95.84 95.65 95.74 Current max chunk-based F1: 95.90 (iteration 37) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 39 Log-likelihood = -96355.340589 Norm (log-likelihood gradient vector) = 4647.451955 Norm (lambda vector) = 104.182296 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20588 20339 98.79 98.87 98.83 b-np 12220 12155 11921 98.07 97.55 97.81 i-np 13660 13708 13367 97.51 97.86 97.68 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.13 98.09 98.11 Avg2. 46451 46451 45627 98.23 98.23 98.23 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12155 11666 95.98 95.47 95.72 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.98 95.47 95.72 Avg2. 12220 12155 11666 95.98 95.47 95.72 Current max chunk-based F1: 95.90 (iteration 37) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 40 Log-likelihood = -95305.328900 Norm (log-likelihood gradient vector) = 18461.393984 Norm (lambda vector) = 105.632684 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20587 20341 98.81 98.88 98.84 b-np 12220 12182 11938 98.00 97.69 97.84 i-np 13660 13682 13359 97.64 97.80 97.72 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.15 98.12 98.14 Avg2. 46451 46451 45638 98.25 98.25 98.25 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12182 11687 95.94 95.64 95.79 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.94 95.64 95.79 Avg2. 12220 12182 11687 95.94 95.64 95.79 Current max chunk-based F1: 95.90 (iteration 37) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 41 Log-likelihood = -94732.930417 Norm (log-likelihood gradient vector) = 7441.154738 Norm (lambda vector) = 104.813296 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20586 20345 98.83 98.90 98.87 b-np 12220 12157 11930 98.13 97.63 97.88 i-np 13660 13708 13380 97.61 97.95 97.78 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.19 98.16 98.17 Avg2. 46451 46451 45655 98.29 98.29 98.29 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12157 11684 96.11 95.61 95.86 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.11 95.61 95.86 Avg2. 12220 12157 11684 96.11 95.61 95.86 Current max chunk-based F1: 95.90 (iteration 37) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 42 Log-likelihood = -92440.825423 Norm (log-likelihood gradient vector) = 4564.280987 Norm (lambda vector) = 105.787343 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20595 20349 98.81 98.92 98.86 b-np 12220 12170 11935 98.07 97.67 97.87 i-np 13660 13686 13372 97.71 97.89 97.80 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.19 98.16 98.18 Avg2. 46451 46451 45656 98.29 98.29 98.29 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12170 11699 96.13 95.74 95.93 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.13 95.74 95.93 Avg2. 12220 12170 11699 96.13 95.74 95.93 Current max chunk-based F1: 95.93 (iteration 42) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 43 Log-likelihood = -90033.191219 Norm (log-likelihood gradient vector) = 3460.727038 Norm (lambda vector) = 106.465656 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20595 20351 98.82 98.93 98.87 b-np 12220 12168 11933 98.07 97.65 97.86 i-np 13660 13688 13377 97.73 97.93 97.83 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.20 98.17 98.19 Avg2. 46451 46451 45661 98.30 98.30 98.30 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12168 11700 96.15 95.74 95.95 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.15 95.74 95.95 Avg2. 12220 12168 11700 96.15 95.74 95.95 Current max chunk-based F1: 95.95 (iteration 43) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 44 Log-likelihood = -85956.390128 Norm (log-likelihood gradient vector) = 3445.073679 Norm (lambda vector) = 107.579742 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20631 20365 98.71 99.00 98.85 b-np 12220 12227 11955 97.78 97.83 97.80 i-np 13660 13593 13322 98.01 97.53 97.77 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.16 98.12 98.14 Avg2. 46451 46451 45642 98.26 98.26 98.26 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12227 11726 95.90 95.96 95.93 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.90 95.96 95.93 Avg2. 12220 12227 11726 95.90 95.96 95.93 Current max chunk-based F1: 95.95 (iteration 43) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 45 Log-likelihood = -81969.354149 Norm (log-likelihood gradient vector) = 9986.230079 Norm (lambda vector) = 108.901896 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20547 20327 98.93 98.81 98.87 b-np 12220 12168 11927 98.02 97.60 97.81 i-np 13660 13736 13400 97.55 98.10 97.82 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.17 98.17 98.17 Avg2. 46451 46451 45654 98.28 98.28 98.28 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12168 11696 96.12 95.71 95.92 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.12 95.71 95.92 Avg2. 12220 12168 11696 96.12 95.71 95.92 Current max chunk-based F1: 95.95 (iteration 43) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 46 Log-likelihood = -78657.021512 Norm (log-likelihood gradient vector) = 5033.613272 Norm (lambda vector) = 109.778587 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20563 20335 98.89 98.85 98.87 b-np 12220 12182 11933 97.96 97.65 97.80 i-np 13660 13706 13387 97.67 98.00 97.84 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.17 98.17 98.17 Avg2. 46451 46451 45655 98.29 98.29 98.29 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12182 11704 96.08 95.78 95.93 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.08 95.78 95.93 Avg2. 12220 12182 11704 96.08 95.78 95.93 Current max chunk-based F1: 95.95 (iteration 43) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 47 Log-likelihood = -78648.604228 Norm (log-likelihood gradient vector) = 3616.791918 Norm (lambda vector) = 109.503748 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20570 20336 98.86 98.86 98.86 b-np 12220 12180 11930 97.95 97.63 97.79 i-np 13660 13701 13382 97.67 97.96 97.82 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.16 98.15 98.16 Avg2. 46451 46451 45648 98.27 98.27 98.27 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12180 11697 96.03 95.72 95.88 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.03 95.72 95.88 Avg2. 12220 12180 11697 96.03 95.72 95.88 Current max chunk-based F1: 95.95 (iteration 43) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 48 Log-likelihood = -78150.237970 Norm (log-likelihood gradient vector) = 3231.463212 Norm (lambda vector) = 109.542439 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20599 20348 98.78 98.92 98.85 b-np 12220 12212 11945 97.81 97.75 97.78 i-np 13660 13640 13351 97.88 97.74 97.81 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.16 98.13 98.15 Avg2. 46451 46451 45644 98.26 98.26 98.26 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12212 11716 95.94 95.88 95.91 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.94 95.88 95.91 Avg2. 12220 12212 11716 95.94 95.88 95.91 Current max chunk-based F1: 95.95 (iteration 43) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 49 Log-likelihood = -76609.402870 Norm (log-likelihood gradient vector) = 3884.344092 Norm (lambda vector) = 110.143737 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20563 20336 98.90 98.86 98.88 b-np 12220 12178 11938 98.03 97.69 97.86 i-np 13660 13710 13395 97.70 98.06 97.88 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.21 98.20 98.21 Avg2. 46451 46451 45669 98.32 98.32 98.32 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12178 11713 96.18 95.85 96.02 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.18 95.85 96.02 Avg2. 12220 12178 11713 96.18 95.85 96.02 Current max chunk-based F1: 96.02 (iteration 49) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 50 Log-likelihood = -73952.843110 Norm (log-likelihood gradient vector) = 3439.998290 Norm (lambda vector) = 111.517565 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20585 20335 98.79 98.85 98.82 b-np 12220 12198 11934 97.84 97.66 97.75 i-np 13660 13668 13359 97.74 97.80 97.77 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.12 98.10 98.11 Avg2. 46451 46451 45628 98.23 98.23 98.23 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12198 11699 95.91 95.74 95.82 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.91 95.74 95.82 Avg2. 12220 12198 11699 95.91 95.74 95.82 Current max chunk-based F1: 96.02 (iteration 49) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 51 Log-likelihood = -71862.964610 Norm (log-likelihood gradient vector) = 9245.322041 Norm (lambda vector) = 112.687346 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20569 20333 98.85 98.84 98.85 b-np 12220 12185 11933 97.93 97.65 97.79 i-np 13660 13697 13381 97.69 97.96 97.83 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.16 98.15 98.15 Avg2. 46451 46451 45647 98.27 98.27 98.27 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12185 11700 96.02 95.74 95.88 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.02 95.74 95.88 Avg2. 12220 12185 11700 96.02 95.74 95.88 Current max chunk-based F1: 96.02 (iteration 49) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 52 Log-likelihood = -70908.859692 Norm (log-likelihood gradient vector) = 3282.190967 Norm (lambda vector) = 112.582421 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20562 20329 98.87 98.82 98.85 b-np 12220 12179 11930 97.96 97.63 97.79 i-np 13660 13710 13384 97.62 97.98 97.80 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.15 98.14 98.15 Avg2. 46451 46451 45643 98.26 98.26 98.26 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12179 11695 96.03 95.70 95.86 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.03 95.70 95.86 Avg2. 12220 12179 11695 96.03 95.70 95.86 Current max chunk-based F1: 96.02 (iteration 49) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 53 Log-likelihood = -70092.740811 Norm (log-likelihood gradient vector) = 2344.344276 Norm (lambda vector) = 112.682523 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20558 20334 98.91 98.85 98.88 b-np 12220 12188 11940 97.97 97.71 97.84 i-np 13660 13705 13391 97.71 98.03 97.87 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.19 98.20 98.20 Avg2. 46451 46451 45665 98.31 98.31 98.31 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12188 11715 96.12 95.87 95.99 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.12 95.87 95.99 Avg2. 12220 12188 11715 96.12 95.87 95.99 Current max chunk-based F1: 96.02 (iteration 49) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 54 Log-likelihood = -68556.699197 Norm (log-likelihood gradient vector) = 3169.911029 Norm (lambda vector) = 113.097427 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20574 20339 98.86 98.87 98.86 b-np 12220 12201 11941 97.87 97.72 97.79 i-np 13660 13676 13372 97.78 97.89 97.83 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.17 98.16 98.16 Avg2. 46451 46451 45652 98.28 98.28 98.28 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12201 11715 96.02 95.87 95.94 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.02 95.87 95.94 Avg2. 12220 12201 11715 96.02 95.87 95.94 Current max chunk-based F1: 96.02 (iteration 49) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 55 Log-likelihood = -66230.248683 Norm (log-likelihood gradient vector) = 4746.278733 Norm (lambda vector) = 114.014061 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20501 20298 99.01 98.67 98.84 b-np 12220 12138 11910 98.12 97.46 97.79 i-np 13660 13812 13426 97.21 98.29 97.74 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.11 98.14 98.13 Avg2. 46451 46451 45634 98.24 98.24 98.24 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12138 11665 96.10 95.46 95.78 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.10 95.46 95.78 Avg2. 12220 12138 11665 96.10 95.46 95.78 Current max chunk-based F1: 96.02 (iteration 49) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 56 Log-likelihood = -63721.095834 Norm (log-likelihood gradient vector) = 10280.051914 Norm (lambda vector) = 115.765594 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20560 20331 98.89 98.83 98.86 b-np 12220 12187 11937 97.95 97.68 97.82 i-np 13660 13704 13384 97.66 97.98 97.82 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.17 98.17 98.17 Avg2. 46451 46451 45652 98.28 98.28 98.28 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12187 11711 96.09 95.83 95.96 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.09 95.83 95.96 Avg2. 12220 12187 11711 96.09 95.83 95.96 Current max chunk-based F1: 96.02 (iteration 49) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 57 Log-likelihood = -63237.437883 Norm (log-likelihood gradient vector) = 3299.810578 Norm (lambda vector) = 115.547991 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20579 20339 98.83 98.87 98.85 b-np 12220 12210 11946 97.84 97.76 97.80 i-np 13660 13662 13360 97.79 97.80 97.80 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.15 98.14 98.15 Avg2. 46451 46451 45645 98.26 98.26 98.26 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12210 11718 95.97 95.89 95.93 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.97 95.89 95.93 Avg2. 12220 12210 11718 95.97 95.89 95.93 Current max chunk-based F1: 96.02 (iteration 49) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 58 Log-likelihood = -63046.808254 Norm (log-likelihood gradient vector) = 2675.501241 Norm (lambda vector) = 115.676040 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20584 20341 98.82 98.88 98.85 b-np 12220 12214 11948 97.82 97.77 97.80 i-np 13660 13653 13356 97.82 97.77 97.80 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.16 98.14 98.15 Avg2. 46451 46451 45645 98.26 98.26 98.26 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12214 11720 95.96 95.91 95.93 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.96 95.91 95.93 Avg2. 12220 12214 11720 95.96 95.91 95.93 Current max chunk-based F1: 96.02 (iteration 49) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 59 Log-likelihood = -62534.932864 Norm (log-likelihood gradient vector) = 3173.809015 Norm (lambda vector) = 116.100497 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20578 20335 98.82 98.85 98.84 b-np 12220 12205 11942 97.85 97.73 97.79 i-np 13660 13668 13358 97.73 97.79 97.76 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.13 98.12 98.13 Avg2. 46451 46451 45635 98.24 98.24 98.24 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12205 11710 95.94 95.83 95.89 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.94 95.83 95.89 Avg2. 12220 12205 11710 95.94 95.83 95.89 Current max chunk-based F1: 96.02 (iteration 49) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 60 Log-likelihood = -61488.748556 Norm (log-likelihood gradient vector) = 3238.747950 Norm (lambda vector) = 116.867979 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20582 20341 98.83 98.88 98.86 b-np 12220 12215 11949 97.82 97.78 97.80 i-np 13660 13654 13360 97.85 97.80 97.83 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.17 98.16 98.16 Avg2. 46451 46451 45650 98.28 98.28 98.28 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12215 11726 96.00 95.96 95.98 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.00 95.96 95.98 Avg2. 12220 12215 11726 96.00 95.96 95.98 Current max chunk-based F1: 96.02 (iteration 49) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 61 Log-likelihood = -60922.478551 Norm (log-likelihood gradient vector) = 7401.774826 Norm (lambda vector) = 118.559339 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20571 20337 98.86 98.86 98.86 b-np 12220 12203 11949 97.92 97.78 97.85 i-np 13660 13677 13375 97.79 97.91 97.85 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.19 98.19 98.19 Avg2. 46451 46451 45661 98.30 98.30 98.30 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12203 11727 96.10 95.97 96.03 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.10 95.97 96.03 Avg2. 12220 12203 11727 96.10 95.97 96.03 Current max chunk-based F1: 96.03 (iteration 61) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 62 Log-likelihood = -60686.714596 Norm (log-likelihood gradient vector) = 6533.855103 Norm (lambda vector) = 119.927380 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20563 20338 98.91 98.87 98.89 b-np 12220 12194 11950 98.00 97.79 97.89 i-np 13660 13694 13388 97.77 98.01 97.89 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.22 98.22 98.22 Avg2. 46451 46451 45676 98.33 98.33 98.33 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12194 11731 96.20 96.00 96.10 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.20 96.00 96.10 Avg2. 12220 12194 11731 96.20 96.00 96.10 Current max chunk-based F1: 96.10 (iteration 62) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 63 Log-likelihood = -59739.725832 Norm (log-likelihood gradient vector) = 2596.140255 Norm (lambda vector) = 119.940299 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20561 20338 98.92 98.87 98.89 b-np 12220 12195 11952 98.01 97.81 97.91 i-np 13660 13695 13390 97.77 98.02 97.90 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.23 98.23 98.23 Avg2. 46451 46451 45680 98.34 98.34 98.34 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12195 11733 96.21 96.01 96.11 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.21 96.01 96.11 Avg2. 12220 12195 11733 96.21 96.01 96.11 Current max chunk-based F1: 96.11 (iteration 63) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 64 Log-likelihood = -59188.539252 Norm (log-likelihood gradient vector) = 2321.749187 Norm (lambda vector) = 120.050386 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20566 20343 98.92 98.89 98.90 b-np 12220 12203 11958 97.99 97.86 97.92 i-np 13660 13682 13387 97.84 98.00 97.92 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.25 98.25 98.25 Avg2. 46451 46451 45688 98.36 98.36 98.36 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12203 11743 96.23 96.10 96.16 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.23 96.10 96.16 Avg2. 12220 12203 11743 96.23 96.10 96.16 Current max chunk-based F1: 96.16 (iteration 64) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 65 Log-likelihood = -58225.912408 Norm (log-likelihood gradient vector) = 2403.808213 Norm (lambda vector) = 120.468953 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20472 20281 99.07 98.59 98.83 b-np 12220 12109 11900 98.27 97.38 97.83 i-np 13660 13870 13455 97.01 98.50 97.75 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.12 98.16 98.14 Avg2. 46451 46451 45636 98.25 98.25 98.25 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12109 11660 96.29 95.42 95.85 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.29 95.42 95.85 Avg2. 12220 12109 11660 96.29 95.42 95.85 Current max chunk-based F1: 96.16 (iteration 64) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 66 Log-likelihood = -57131.905844 Norm (log-likelihood gradient vector) = 12303.581194 Norm (lambda vector) = 121.974649 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20517 20314 99.01 98.75 98.88 b-np 12220 12158 11932 98.14 97.64 97.89 i-np 13660 13776 13430 97.49 98.32 97.90 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.21 98.24 98.23 Avg2. 46451 46451 45676 98.33 98.33 98.33 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12158 11707 96.29 95.80 96.05 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.29 95.80 96.05 Avg2. 12220 12158 11707 96.29 95.80 96.05 Current max chunk-based F1: 96.16 (iteration 64) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 67 Log-likelihood = -57325.077518 Norm (log-likelihood gradient vector) = 6184.104423 Norm (lambda vector) = 121.157183 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20548 20334 98.96 98.85 98.90 b-np 12220 12187 11954 98.09 97.82 97.96 i-np 13660 13716 13410 97.77 98.17 97.97 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.27 98.28 98.28 Avg2. 46451 46451 45698 98.38 98.38 98.38 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12187 11743 96.36 96.10 96.23 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.36 96.10 96.23 Avg2. 12220 12187 11743 96.36 96.10 96.23 Current max chunk-based F1: 96.23 (iteration 67) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 68 Log-likelihood = -55935.792336 Norm (log-likelihood gradient vector) = 3354.748909 Norm (lambda vector) = 121.955269 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20571 20346 98.91 98.91 98.91 b-np 12220 12200 11962 98.05 97.89 97.97 i-np 13660 13680 13392 97.89 98.04 97.97 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.28 98.28 98.28 Avg2. 46451 46451 45700 98.38 98.38 98.38 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12200 11753 96.34 96.18 96.26 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.34 96.18 96.26 Avg2. 12220 12200 11753 96.34 96.18 96.26 Current max chunk-based F1: 96.26 (iteration 68) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 69 Log-likelihood = -54916.595092 Norm (log-likelihood gradient vector) = 2259.873467 Norm (lambda vector) = 122.746661 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20581 20351 98.88 98.93 98.91 b-np 12220 12205 11966 98.04 97.92 97.98 i-np 13660 13665 13383 97.94 97.97 97.95 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.29 98.27 98.28 Avg2. 46451 46451 45700 98.38 98.38 98.38 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12205 11754 96.30 96.19 96.25 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.30 96.19 96.25 Avg2. 12220 12205 11754 96.30 96.19 96.25 Current max chunk-based F1: 96.26 (iteration 68) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 70 Log-likelihood = -53982.474989 Norm (log-likelihood gradient vector) = 2793.242157 Norm (lambda vector) = 123.570194 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20584 20349 98.86 98.92 98.89 b-np 12220 12219 11970 97.96 97.95 97.96 i-np 13660 13648 13369 97.96 97.87 97.91 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.26 98.25 98.25 Avg2. 46451 46451 45688 98.36 98.36 98.36 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12219 11757 96.22 96.21 96.22 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.22 96.21 96.22 Avg2. 12220 12219 11757 96.22 96.21 96.22 Current max chunk-based F1: 96.26 (iteration 68) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 71 Log-likelihood = -52750.914192 Norm (log-likelihood gradient vector) = 3154.908685 Norm (lambda vector) = 124.650656 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20595 20359 98.85 98.97 98.91 b-np 12220 12219 11974 97.99 97.99 97.99 i-np 13660 13637 13365 98.01 97.84 97.92 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.28 98.27 98.28 Avg2. 46451 46451 45698 98.38 98.38 98.38 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12219 11758 96.23 96.22 96.22 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.23 96.22 96.22 Avg2. 12220 12219 11758 96.23 96.22 96.22 Current max chunk-based F1: 96.26 (iteration 68) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 72 Log-likelihood = -50555.881324 Norm (log-likelihood gradient vector) = 4591.111810 Norm (lambda vector) = 126.322169 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20582 20350 98.87 98.93 98.90 b-np 12220 12212 11965 97.98 97.91 97.95 i-np 13660 13657 13369 97.89 97.87 97.88 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.25 98.24 98.24 Avg2. 46451 46451 45684 98.35 98.35 98.35 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12212 11746 96.18 96.12 96.15 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.18 96.12 96.15 Avg2. 12220 12212 11746 96.18 96.12 96.15 Current max chunk-based F1: 96.26 (iteration 68) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 73 Log-likelihood = -48629.093707 Norm (log-likelihood gradient vector) = 4827.025514 Norm (lambda vector) = 127.914344 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20571 20346 98.91 98.91 98.91 b-np 12220 12207 11965 98.02 97.91 97.97 i-np 13660 13673 13380 97.86 97.95 97.90 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.26 98.26 98.26 Avg2. 46451 46451 45691 98.36 98.36 98.36 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12207 11746 96.22 96.12 96.17 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.22 96.12 96.17 Avg2. 12220 12207 11746 96.22 96.12 96.17 Current max chunk-based F1: 96.26 (iteration 68) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 74 Log-likelihood = -48330.958457 Norm (log-likelihood gradient vector) = 2091.011286 Norm (lambda vector) = 127.252950 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20572 20344 98.89 98.90 98.89 b-np 12220 12204 11965 98.04 97.91 97.98 i-np 13660 13675 13380 97.84 97.95 97.90 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.26 98.25 98.26 Avg2. 46451 46451 45689 98.36 98.36 98.36 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12204 11748 96.26 96.14 96.20 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.26 96.14 96.20 Avg2. 12220 12204 11748 96.26 96.14 96.20 Current max chunk-based F1: 96.26 (iteration 68) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 75 Log-likelihood = -48024.660758 Norm (log-likelihood gradient vector) = 2120.395970 Norm (lambda vector) = 126.947488 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20586 20356 98.88 98.95 98.92 b-np 12220 12215 11977 98.05 98.01 98.03 i-np 13660 13650 13376 97.99 97.92 97.96 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.31 98.30 98.30 Avg2. 46451 46451 45709 98.40 98.40 98.40 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12215 11767 96.33 96.29 96.31 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.33 96.29 96.31 Avg2. 12220 12215 11767 96.33 96.29 96.31 Current max chunk-based F1: 96.31 (iteration 75) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 76 Log-likelihood = -47727.331104 Norm (log-likelihood gradient vector) = 2278.567901 Norm (lambda vector) = 126.890558 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20495 20302 99.06 98.69 98.87 b-np 12220 12116 11920 98.38 97.55 97.96 i-np 13660 13840 13449 97.17 98.46 97.81 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.21 98.23 98.22 Avg2. 46451 46451 45671 98.32 98.32 98.32 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12116 11685 96.44 95.62 96.03 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.44 95.62 96.03 Avg2. 12220 12116 11685 96.44 95.62 96.03 Current max chunk-based F1: 96.31 (iteration 75) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 77 Log-likelihood = -47676.472320 Norm (log-likelihood gradient vector) = 10187.407620 Norm (lambda vector) = 127.839026 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20530 20329 99.02 98.82 98.92 b-np 12220 12157 11950 98.30 97.79 98.04 i-np 13660 13764 13431 97.58 98.32 97.95 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.30 98.31 98.31 Avg2. 46451 46451 45710 98.40 98.40 98.40 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12157 11732 96.50 96.01 96.25 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.50 96.01 96.25 Avg2. 12220 12157 11732 96.50 96.01 96.25 Current max chunk-based F1: 96.31 (iteration 75) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 78 Log-likelihood = -47282.482319 Norm (log-likelihood gradient vector) = 4920.536080 Norm (lambda vector) = 127.326523 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20576 20358 98.94 98.96 98.95 b-np 12220 12198 11976 98.18 98.00 98.09 i-np 13660 13677 13398 97.96 98.08 98.02 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.36 98.35 98.36 Avg2. 46451 46451 45732 98.45 98.45 98.45 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12198 11771 96.50 96.33 96.41 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.50 96.33 96.41 Avg2. 12220 12198 11771 96.50 96.33 96.41 Current max chunk-based F1: 96.41 (iteration 78) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 79 Log-likelihood = -46662.340123 Norm (log-likelihood gradient vector) = 2407.216490 Norm (lambda vector) = 127.913131 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20599 20370 98.89 99.02 98.96 b-np 12220 12210 11983 98.14 98.06 98.10 i-np 13660 13642 13376 98.05 97.92 97.99 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.36 98.33 98.35 Avg2. 46451 46451 45729 98.45 98.45 98.45 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12210 11773 96.42 96.34 96.38 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.42 96.34 96.38 Avg2. 12220 12210 11773 96.42 96.34 96.38 Current max chunk-based F1: 96.41 (iteration 78) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 80 Log-likelihood = -45903.067621 Norm (log-likelihood gradient vector) = 2058.297249 Norm (lambda vector) = 129.037358 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20592 20365 98.90 99.00 98.95 b-np 12220 12210 11983 98.14 98.06 98.10 i-np 13660 13649 13379 98.02 97.94 97.98 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.35 98.33 98.34 Avg2. 46451 46451 45727 98.44 98.44 98.44 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12210 11770 96.40 96.32 96.36 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.40 96.32 96.36 Avg2. 12220 12210 11770 96.40 96.32 96.36 Current max chunk-based F1: 96.41 (iteration 78) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 81 Log-likelihood = -45226.150870 Norm (log-likelihood gradient vector) = 2159.808151 Norm (lambda vector) = 129.855766 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20594 20365 98.89 99.00 98.94 b-np 12220 12212 11976 98.07 98.00 98.04 i-np 13660 13645 13376 98.03 97.92 97.97 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.33 98.31 98.32 Avg2. 46451 46451 45717 98.42 98.42 98.42 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12212 11760 96.30 96.24 96.27 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.30 96.24 96.27 Avg2. 12220 12212 11760 96.30 96.24 96.27 Current max chunk-based F1: 96.41 (iteration 78) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 82 Log-likelihood = -43796.670749 Norm (log-likelihood gradient vector) = 1981.379149 Norm (lambda vector) = 131.392793 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20548 20340 98.99 98.88 98.93 b-np 12220 12171 11946 98.15 97.76 97.95 i-np 13660 13732 13409 97.65 98.16 97.90 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.26 98.27 98.26 Avg2. 46451 46451 45695 98.37 98.37 98.37 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12171 11721 96.30 95.92 96.11 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.30 95.92 96.11 Avg2. 12220 12171 11721 96.30 95.92 96.11 Current max chunk-based F1: 96.41 (iteration 78) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 83 Log-likelihood = -44016.553296 Norm (log-likelihood gradient vector) = 14476.524267 Norm (lambda vector) = 133.171301 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20568 20357 98.97 98.96 98.97 b-np 12220 12184 11965 98.20 97.91 98.06 i-np 13660 13699 13407 97.87 98.15 98.01 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.35 98.34 98.34 Avg2. 46451 46451 45729 98.45 98.45 98.45 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12184 11747 96.41 96.13 96.27 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.41 96.13 96.27 Avg2. 12220 12184 11747 96.41 96.13 96.27 Current max chunk-based F1: 96.41 (iteration 78) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 84 Log-likelihood = -42940.201235 Norm (log-likelihood gradient vector) = 7661.784733 Norm (lambda vector) = 132.295915 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20578 20363 98.96 98.99 98.97 b-np 12220 12197 11975 98.18 98.00 98.09 i-np 13660 13676 13400 97.98 98.10 98.04 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.37 98.36 98.37 Avg2. 46451 46451 45738 98.47 98.47 98.47 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12197 11763 96.44 96.26 96.35 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.44 96.26 96.35 Avg2. 12220 12197 11763 96.44 96.26 96.35 Current max chunk-based F1: 96.41 (iteration 78) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 85 Log-likelihood = -43122.475882 Norm (log-likelihood gradient vector) = 3776.885596 Norm (lambda vector) = 131.811625 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20583 20365 98.94 99.00 98.97 b-np 12220 12190 11972 98.21 97.97 98.09 i-np 13660 13678 13401 97.97 98.10 98.04 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.38 98.36 98.37 Avg2. 46451 46451 45738 98.47 98.47 98.47 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12190 11761 96.48 96.24 96.36 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.48 96.24 96.36 Avg2. 12220 12190 11761 96.48 96.24 96.36 Current max chunk-based F1: 96.41 (iteration 78) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 86 Log-likelihood = -42215.807180 Norm (log-likelihood gradient vector) = 2104.819084 Norm (lambda vector) = 132.361507 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20589 20367 98.92 99.01 98.97 b-np 12220 12193 11969 98.16 97.95 98.05 i-np 13660 13669 13394 97.99 98.05 98.02 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.36 98.34 98.35 Avg2. 46451 46451 45730 98.45 98.45 98.45 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12193 11757 96.42 96.21 96.32 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.42 96.21 96.32 Avg2. 12220 12193 11757 96.42 96.21 96.32 Current max chunk-based F1: 96.41 (iteration 78) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 87 Log-likelihood = -41364.428974 Norm (log-likelihood gradient vector) = 1719.865457 Norm (lambda vector) = 132.578641 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20593 20368 98.91 99.01 98.96 b-np 12220 12193 11968 98.15 97.94 98.05 i-np 13660 13665 13393 98.01 98.05 98.03 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.36 98.33 98.34 Avg2. 46451 46451 45729 98.45 98.45 98.45 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12193 11760 96.45 96.24 96.34 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.45 96.24 96.34 Avg2. 12220 12193 11760 96.45 96.24 96.34 Current max chunk-based F1: 96.41 (iteration 78) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 88 Log-likelihood = -40098.240669 Norm (log-likelihood gradient vector) = 2151.374328 Norm (lambda vector) = 132.967471 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20610 20375 98.86 99.05 98.95 b-np 12220 12211 11975 98.07 98.00 98.03 i-np 13660 13630 13377 98.14 97.93 98.04 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.36 98.32 98.34 Avg2. 46451 46451 45727 98.44 98.44 98.44 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12211 11769 96.38 96.31 96.34 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.38 96.31 96.34 Avg2. 12220 12211 11769 96.38 96.31 96.34 Current max chunk-based F1: 96.41 (iteration 78) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 89 Log-likelihood = -38394.665525 Norm (log-likelihood gradient vector) = 2502.891510 Norm (lambda vector) = 133.798029 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20425 20263 99.21 98.50 98.85 b-np 12220 12077 11895 98.49 97.34 97.91 i-np 13660 13949 13496 96.75 98.80 97.77 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.15 98.21 98.18 Avg2. 46451 46451 45654 98.28 98.28 98.28 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12077 11657 96.52 95.39 95.95 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.52 95.39 95.95 Avg2. 12220 12077 11657 96.52 95.39 95.95 Current max chunk-based F1: 96.41 (iteration 78) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 90 Log-likelihood = -38116.542637 Norm (log-likelihood gradient vector) = 14520.134910 Norm (lambda vector) = 135.475145 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20571 20362 98.98 98.98 98.98 b-np 12220 12177 11962 98.23 97.89 98.06 i-np 13660 13703 13425 97.97 98.28 98.13 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.40 98.38 98.39 Avg2. 46451 46451 45749 98.49 98.49 98.49 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12177 11760 96.58 96.24 96.41 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.58 96.24 96.41 Avg2. 12220 12177 11760 96.58 96.24 96.41 Current max chunk-based F1: 96.41 (iteration 78) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 91 Log-likelihood = -37770.973335 Norm (log-likelihood gradient vector) = 3550.792804 Norm (lambda vector) = 134.212258 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20601 20376 98.91 99.05 98.98 b-np 12220 12200 11974 98.15 97.99 98.07 i-np 13660 13650 13398 98.15 98.08 98.12 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.40 98.37 98.39 Avg2. 46451 46451 45748 98.49 98.49 98.49 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12200 11775 96.52 96.36 96.44 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.52 96.36 96.44 Avg2. 12220 12200 11775 96.52 96.36 96.44 Current max chunk-based F1: 96.44 (iteration 91) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 92 Log-likelihood = -36789.284887 Norm (log-likelihood gradient vector) = 1851.144713 Norm (lambda vector) = 134.928715 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20610 20381 98.89 99.08 98.98 b-np 12220 12204 11979 98.16 98.03 98.09 i-np 13660 13637 13390 98.19 98.02 98.11 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.41 98.38 98.39 Avg2. 46451 46451 45750 98.49 98.49 98.49 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12204 11778 96.51 96.38 96.45 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.51 96.38 96.45 Avg2. 12220 12204 11778 96.51 96.38 96.45 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 93 Log-likelihood = -36341.292663 Norm (log-likelihood gradient vector) = 1370.502646 Norm (lambda vector) = 135.424914 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20613 20380 98.87 99.07 98.97 b-np 12220 12204 11977 98.14 98.01 98.08 i-np 13660 13634 13386 98.18 97.99 98.09 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.40 98.36 98.38 Avg2. 46451 46451 45743 98.48 98.48 98.48 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12204 11775 96.48 96.36 96.42 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.48 96.36 96.42 Avg2. 12220 12204 11775 96.48 96.36 96.42 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 94 Log-likelihood = -36078.425357 Norm (log-likelihood gradient vector) = 1738.834297 Norm (lambda vector) = 135.926302 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20608 20377 98.88 99.06 98.97 b-np 12220 12210 11979 98.11 98.03 98.07 i-np 13660 13633 13384 98.17 97.98 98.08 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.39 98.35 98.37 Avg2. 46451 46451 45740 98.47 98.47 98.47 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12210 11775 96.44 96.36 96.40 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.44 96.36 96.40 Avg2. 12220 12210 11775 96.44 96.36 96.40 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 95 Log-likelihood = -35834.073956 Norm (log-likelihood gradient vector) = 1672.126512 Norm (lambda vector) = 136.690346 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20525 20322 99.01 98.79 98.90 b-np 12220 12161 11941 98.19 97.72 97.95 i-np 13660 13765 13427 97.54 98.29 97.92 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.25 98.27 98.26 Avg2. 46451 46451 45690 98.36 98.36 98.36 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12161 11718 96.36 95.89 96.12 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.36 95.89 96.12 Avg2. 12220 12161 11718 96.36 95.89 96.12 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 96 Log-likelihood = -37859.491676 Norm (log-likelihood gradient vector) = 12684.973332 Norm (lambda vector) = 138.651146 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20596 20367 98.89 99.01 98.95 b-np 12220 12205 11977 98.13 98.01 98.07 i-np 13660 13650 13385 98.06 97.99 98.02 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.36 98.34 98.35 Avg2. 46451 46451 45729 98.45 98.45 98.45 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12205 11768 96.42 96.30 96.36 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.42 96.30 96.36 Avg2. 12220 12205 11768 96.42 96.30 96.36 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 97 Log-likelihood = -35738.298118 Norm (log-likelihood gradient vector) = 2949.024494 Norm (lambda vector) = 137.045156 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20587 20361 98.90 98.98 98.94 b-np 12220 12198 11970 98.13 97.95 98.04 i-np 13660 13666 13392 98.00 98.04 98.02 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.34 98.32 98.33 Avg2. 46451 46451 45723 98.43 98.43 98.43 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12198 11761 96.42 96.24 96.33 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.42 96.24 96.33 Avg2. 12220 12198 11761 96.42 96.24 96.33 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 98 Log-likelihood = -35445.662718 Norm (log-likelihood gradient vector) = 2278.659015 Norm (lambda vector) = 138.078188 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20580 20356 98.91 98.95 98.93 b-np 12220 12203 11969 98.08 97.95 98.01 i-np 13660 13668 13389 97.96 98.02 97.99 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.32 98.31 98.31 Avg2. 46451 46451 45714 98.41 98.41 98.41 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12203 11760 96.37 96.24 96.30 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.37 96.24 96.30 Avg2. 12220 12203 11760 96.37 96.24 96.30 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 99 Log-likelihood = -34949.668697 Norm (log-likelihood gradient vector) = 1526.830753 Norm (lambda vector) = 139.522413 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20613 20376 98.85 99.05 98.95 b-np 12220 12212 11974 98.05 97.99 98.02 i-np 13660 13626 13369 98.11 97.87 97.99 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.34 98.30 98.32 Avg2. 46451 46451 45719 98.42 98.42 98.42 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12212 11767 96.36 96.29 96.32 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.36 96.29 96.32 Avg2. 12220 12212 11767 96.36 96.29 96.32 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 100 Log-likelihood = -35099.592735 Norm (log-likelihood gradient vector) = 2630.093804 Norm (lambda vector) = 140.914167 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20586 20361 98.91 98.98 98.94 b-np 12220 12203 11971 98.10 97.96 98.03 i-np 13660 13662 13388 97.99 98.01 98.00 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.33 98.32 98.33 Avg2. 46451 46451 45720 98.43 98.43 98.43 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12203 11763 96.39 96.26 96.33 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.39 96.26 96.33 Avg2. 12220 12203 11763 96.39 96.26 96.33 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 101 Log-likelihood = -34910.854534 Norm (log-likelihood gradient vector) = 1481.271861 Norm (lambda vector) = 139.867636 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20471 20295 99.14 98.66 98.90 b-np 12220 12110 11920 98.43 97.55 97.99 i-np 13660 13870 13471 97.12 98.62 97.86 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.23 98.27 98.25 Avg2. 46451 46451 45686 98.35 98.35 98.35 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12110 11683 96.47 95.61 96.04 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.47 95.61 96.04 Avg2. 12220 12110 11683 96.47 95.61 96.04 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 102 Log-likelihood = -36189.140123 Norm (log-likelihood gradient vector) = 11658.183513 Norm (lambda vector) = 142.722980 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20559 20350 98.98 98.93 98.95 b-np 12220 12178 11962 98.23 97.89 98.06 i-np 13660 13714 13419 97.85 98.24 98.04 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.35 98.35 98.35 Avg2. 46451 46451 45731 98.45 98.45 98.45 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12178 11753 96.51 96.18 96.34 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.51 96.18 96.34 Avg2. 12220 12178 11753 96.51 96.18 96.34 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 103 Log-likelihood = -34772.613838 Norm (log-likelihood gradient vector) = 2260.876826 Norm (lambda vector) = 140.492485 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20578 20357 98.93 98.96 98.94 b-np 12220 12184 11960 98.16 97.87 98.02 i-np 13660 13689 13401 97.90 98.10 98.00 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.33 98.31 98.32 Avg2. 46451 46451 45718 98.42 98.42 98.42 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12184 11750 96.44 96.15 96.30 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.44 96.15 96.30 Avg2. 12220 12184 11750 96.44 96.15 96.30 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 104 Log-likelihood = -35100.444186 Norm (log-likelihood gradient vector) = 1944.049326 Norm (lambda vector) = 141.982553 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20562 20349 98.96 98.92 98.94 b-np 12220 12182 11960 98.18 97.87 98.02 i-np 13660 13707 13411 97.84 98.18 98.01 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.33 98.32 98.33 Avg2. 46451 46451 45720 98.43 98.43 98.43 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12182 11750 96.45 96.15 96.30 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.45 96.15 96.30 Avg2. 12220 12182 11750 96.45 96.15 96.30 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 105 Log-likelihood = -34746.916558 Norm (log-likelihood gradient vector) = 1997.781087 Norm (lambda vector) = 140.822586 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20589 20365 98.91 99.00 98.96 b-np 12220 12199 11969 98.11 97.95 98.03 i-np 13660 13663 13392 98.02 98.04 98.03 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.35 98.33 98.34 Avg2. 46451 46451 45726 98.44 98.44 98.44 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12199 11762 96.42 96.25 96.33 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.42 96.25 96.33 Avg2. 12220 12199 11762 96.42 96.25 96.33 Current max chunk-based F1: 96.45 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 106 Log-likelihood = -34446.192975 Norm (log-likelihood gradient vector) = 1768.079007 Norm (lambda vector) = 142.376415 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20594 20376 98.94 99.05 99.00 b-np 12220 12187 11973 98.24 97.98 98.11 i-np 13660 13670 13407 98.08 98.15 98.11 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.42 98.39 98.41 Avg2. 46451 46451 45756 98.50 98.50 98.50 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12187 11772 96.59 96.33 96.46 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.59 96.33 96.46 Avg2. 12220 12187 11772 96.59 96.33 96.46 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 107 Log-likelihood = -34220.870100 Norm (log-likelihood gradient vector) = 1743.517486 Norm (lambda vector) = 142.901326 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20586 20371 98.96 99.03 98.99 b-np 12220 12205 11981 98.16 98.04 98.10 i-np 13660 13660 13399 98.09 98.09 98.09 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.40 98.39 98.40 Avg2. 46451 46451 45751 98.49 98.49 98.49 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12205 11772 96.45 96.33 96.39 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.45 96.33 96.39 Avg2. 12220 12205 11772 96.45 96.33 96.39 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 108 Log-likelihood = -33455.085768 Norm (log-likelihood gradient vector) = 2270.698420 Norm (lambda vector) = 143.993627 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20591 20374 98.95 99.04 98.99 b-np 12220 12201 11979 98.18 98.03 98.10 i-np 13660 13659 13399 98.10 98.09 98.09 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.41 98.39 98.40 Avg2. 46451 46451 45752 98.50 98.50 98.50 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12201 11772 96.48 96.33 96.41 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.48 96.33 96.41 Avg2. 12220 12201 11772 96.48 96.33 96.41 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 109 Log-likelihood = -32604.671837 Norm (log-likelihood gradient vector) = 1739.493895 Norm (lambda vector) = 144.399191 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20546 20342 99.01 98.89 98.95 b-np 12220 12157 11955 98.34 97.83 98.08 i-np 13660 13748 13430 97.69 98.32 98.00 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.34 98.34 98.34 Avg2. 46451 46451 45727 98.44 98.44 98.44 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12157 11736 96.54 96.04 96.29 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.54 96.04 96.29 Avg2. 12220 12157 11736 96.54 96.04 96.29 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 110 Log-likelihood = -32260.964010 Norm (log-likelihood gradient vector) = 6583.725101 Norm (lambda vector) = 144.847185 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20578 20368 98.98 99.01 99.00 b-np 12220 12184 11973 98.27 97.98 98.12 i-np 13660 13689 13416 98.01 98.21 98.11 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.42 98.40 98.41 Avg2. 46451 46451 45757 98.51 98.51 98.51 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12184 11764 96.55 96.27 96.41 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.55 96.27 96.41 Avg2. 12220 12184 11764 96.55 96.27 96.41 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 111 Log-likelihood = -32185.848466 Norm (log-likelihood gradient vector) = 2632.445733 Norm (lambda vector) = 144.593740 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20577 20364 98.96 98.99 98.98 b-np 12220 12188 11978 98.28 98.02 98.15 i-np 13660 13686 13410 97.98 98.17 98.08 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.41 98.39 98.40 Avg2. 46451 46451 45752 98.50 98.50 98.50 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12188 11771 96.58 96.33 96.45 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.58 96.33 96.45 Avg2. 12220 12188 11771 96.58 96.33 96.45 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 112 Log-likelihood = -31696.149125 Norm (log-likelihood gradient vector) = 1470.373948 Norm (lambda vector) = 144.626130 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20560 20356 99.01 98.95 98.98 b-np 12220 12181 11975 98.31 98.00 98.15 i-np 13660 13710 13422 97.90 98.26 98.08 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.41 98.40 98.40 Avg2. 46451 46451 45753 98.50 98.50 98.50 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12181 11766 96.59 96.28 96.44 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.59 96.28 96.44 Avg2. 12220 12181 11766 96.59 96.28 96.44 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 113 Log-likelihood = -31297.293786 Norm (log-likelihood gradient vector) = 1800.548798 Norm (lambda vector) = 145.070532 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20588 20365 98.92 99.00 98.96 b-np 12220 12207 11982 98.16 98.05 98.10 i-np 13660 13656 13390 98.05 98.02 98.04 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.38 98.36 98.37 Avg2. 46451 46451 45737 98.46 98.46 98.46 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12207 11772 96.44 96.33 96.39 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.44 96.33 96.39 Avg2. 12220 12207 11772 96.44 96.33 96.39 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 114 Log-likelihood = -30898.706273 Norm (log-likelihood gradient vector) = 1880.328747 Norm (lambda vector) = 145.803134 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20571 20359 98.97 98.97 98.97 b-np 12220 12197 11980 98.22 98.04 98.13 i-np 13660 13683 13406 97.98 98.14 98.06 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.39 98.38 98.39 Avg2. 46451 46451 45745 98.48 98.48 98.48 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12197 11771 96.51 96.33 96.42 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.51 96.33 96.42 Avg2. 12220 12197 11771 96.51 96.33 96.42 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 115 Log-likelihood = -30615.616994 Norm (log-likelihood gradient vector) = 1396.438634 Norm (lambda vector) = 146.701938 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20569 20356 98.96 98.95 98.96 b-np 12220 12192 11978 98.24 98.02 98.13 i-np 13660 13690 13410 97.95 98.17 98.06 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.39 98.38 98.38 Avg2. 46451 46451 45744 98.48 98.48 98.48 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12192 11770 96.54 96.32 96.43 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.54 96.32 96.43 Avg2. 12220 12192 11770 96.54 96.32 96.43 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 116 Log-likelihood = -30282.055498 Norm (log-likelihood gradient vector) = 1476.174907 Norm (lambda vector) = 148.150610 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20575 20357 98.94 98.96 98.95 b-np 12220 12196 11975 98.19 98.00 98.09 i-np 13660 13680 13398 97.94 98.08 98.01 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.36 98.35 98.35 Avg2. 46451 46451 45730 98.45 98.45 98.45 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12196 11760 96.43 96.24 96.33 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.43 96.24 96.33 Avg2. 12220 12196 11760 96.43 96.24 96.33 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 117 Log-likelihood = -29743.903395 Norm (log-likelihood gradient vector) = 1252.443195 Norm (lambda vector) = 149.967759 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20587 20359 98.89 98.97 98.93 b-np 12220 12227 11983 98.00 98.06 98.03 i-np 13660 13637 13373 98.06 97.90 97.98 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.32 98.31 98.31 Avg2. 46451 46451 45715 98.42 98.42 98.42 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12227 11766 96.23 96.28 96.26 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.23 96.28 96.26 Avg2. 12220 12227 11766 96.23 96.28 96.26 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 118 Log-likelihood = -28711.330755 Norm (log-likelihood gradient vector) = 2726.020102 Norm (lambda vector) = 154.082894 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20594 20359 98.86 98.97 98.91 b-np 12220 12182 11960 98.18 97.87 98.02 i-np 13660 13675 13390 97.92 98.02 97.97 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.32 98.29 98.30 Avg2. 46451 46451 45709 98.40 98.40 98.40 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12182 11749 96.45 96.15 96.30 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.45 96.15 96.30 Avg2. 12220 12182 11749 96.45 96.15 96.30 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 119 Log-likelihood = -28135.816977 Norm (log-likelihood gradient vector) = 2327.505746 Norm (lambda vector) = 154.438891 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20584 20356 98.89 98.95 98.92 b-np 12220 12199 11971 98.13 97.96 98.05 i-np 13660 13668 13385 97.93 97.99 97.96 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.32 98.30 98.31 Avg2. 46451 46451 45712 98.41 98.41 98.41 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12199 11754 96.35 96.19 96.27 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.35 96.19 96.27 Avg2. 12220 12199 11754 96.35 96.19 96.27 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 120 Log-likelihood = -27859.756525 Norm (log-likelihood gradient vector) = 1170.363820 Norm (lambda vector) = 153.699485 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20583 20357 98.90 98.96 98.93 b-np 12220 12213 11975 98.05 98.00 98.02 i-np 13660 13655 13385 98.02 97.99 98.00 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.33 98.31 98.32 Avg2. 46451 46451 45717 98.42 98.42 98.42 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12213 11759 96.28 96.23 96.26 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.28 96.23 96.26 Avg2. 12220 12213 11759 96.28 96.23 96.26 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 121 Log-likelihood = -27421.117866 Norm (log-likelihood gradient vector) = 1171.891212 Norm (lambda vector) = 153.808164 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20605 20370 98.86 99.02 98.94 b-np 12220 12227 11982 98.00 98.05 98.02 i-np 13660 13619 13369 98.16 97.87 98.02 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.34 98.31 98.33 Avg2. 46451 46451 45721 98.43 98.43 98.43 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12227 11774 96.30 96.35 96.32 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.30 96.35 96.32 Avg2. 12220 12227 11774 96.30 96.35 96.32 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 122 Log-likelihood = -26547.306337 Norm (log-likelihood gradient vector) = 3035.459798 Norm (lambda vector) = 155.231716 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20598 20366 98.87 99.00 98.94 b-np 12220 12215 11980 98.08 98.04 98.06 i-np 13660 13638 13379 98.10 97.94 98.02 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.35 98.33 98.34 Avg2. 46451 46451 45725 98.44 98.44 98.44 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12215 11773 96.38 96.34 96.36 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.38 96.34 96.36 Avg2. 12220 12215 11773 96.38 96.34 96.36 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 123 Log-likelihood = -25868.856593 Norm (log-likelihood gradient vector) = 1417.098735 Norm (lambda vector) = 156.038173 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20593 20363 98.88 98.99 98.94 b-np 12220 12208 11976 98.10 98.00 98.05 i-np 13660 13650 13385 98.06 97.99 98.02 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.35 98.33 98.34 Avg2. 46451 46451 45724 98.43 98.43 98.43 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12208 11770 96.41 96.32 96.36 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.41 96.32 96.36 Avg2. 12220 12208 11770 96.41 96.32 96.36 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 124 Log-likelihood = -25615.322913 Norm (log-likelihood gradient vector) = 1081.503497 Norm (lambda vector) = 156.617397 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 25 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20600 20362 98.84 98.98 98.91 b-np 12220 12208 11973 98.08 97.98 98.03 i-np 13660 13643 13377 98.05 97.93 97.99 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.32 98.30 98.31 Avg2. 46451 46451 45712 98.41 98.41 98.41 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12208 11763 96.35 96.26 96.31 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.35 96.26 96.31 Avg2. 12220 12208 11763 96.35 96.26 96.31 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 125 Log-likelihood = -25274.931497 Norm (log-likelihood gradient vector) = 1443.656288 Norm (lambda vector) = 157.754916 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20550 20337 98.96 98.86 98.91 b-np 12220 12162 11952 98.27 97.81 98.04 i-np 13660 13739 13422 97.69 98.26 97.97 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.31 98.31 98.31 Avg2. 46451 46451 45711 98.41 98.41 98.41 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12162 11738 96.51 96.06 96.28 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.51 96.06 96.28 Avg2. 12220 12162 11738 96.51 96.06 96.28 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 126 Log-likelihood = -25119.378633 Norm (log-likelihood gradient vector) = 4563.367242 Norm (lambda vector) = 158.619747 Log-likelihood and gradient computational time: 26 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20575 20352 98.92 98.94 98.93 b-np 12220 12186 11965 98.19 97.91 98.05 i-np 13660 13690 13402 97.90 98.11 98.00 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.33 98.32 98.33 Avg2. 46451 46451 45719 98.42 98.42 98.42 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12186 11754 96.45 96.19 96.32 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.45 96.19 96.32 Avg2. 12220 12186 11754 96.45 96.19 96.32 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 127 Log-likelihood = -25102.786069 Norm (log-likelihood gradient vector) = 2368.224060 Norm (lambda vector) = 158.193467 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20579 20353 98.90 98.94 98.92 b-np 12220 12190 11966 98.16 97.92 98.04 i-np 13660 13682 13396 97.91 98.07 97.99 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.32 98.31 98.32 Avg2. 46451 46451 45715 98.42 98.42 98.42 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12190 11753 96.42 96.18 96.30 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.42 96.18 96.30 Avg2. 12220 12190 11753 96.42 96.18 96.30 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 128 Log-likelihood = -24930.779350 Norm (log-likelihood gradient vector) = 1809.534360 Norm (lambda vector) = 158.524642 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20598 20371 98.90 99.03 98.96 b-np 12220 12205 11978 98.14 98.02 98.08 i-np 13660 13648 13393 98.13 98.05 98.09 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.39 98.36 98.38 Avg2. 46451 46451 45742 98.47 98.47 98.47 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12205 11772 96.45 96.33 96.39 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.45 96.33 96.39 Avg2. 12220 12205 11772 96.45 96.33 96.39 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 129 Log-likelihood = -24535.412984 Norm (log-likelihood gradient vector) = 1114.510953 Norm (lambda vector) = 159.062938 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20609 20375 98.86 99.05 98.96 b-np 12220 12211 11983 98.13 98.06 98.10 i-np 13660 13631 13384 98.19 97.98 98.08 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.40 98.36 98.38 Avg2. 46451 46451 45742 98.47 98.47 98.47 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12211 11780 96.47 96.40 96.43 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.47 96.40 96.43 Avg2. 12220 12211 11780 96.47 96.40 96.43 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 130 Log-likelihood = -24341.176804 Norm (log-likelihood gradient vector) = 1190.989178 Norm (lambda vector) = 159.360081 Log-likelihood and gradient computational time: 25 seconds Training iteration elapsed: 26 seconds Label-based performance evaluation: Label Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- o 20571 20610 20374 98.85 99.04 98.95 b-np 12220 12204 11978 98.15 98.02 98.08 i-np 13660 13637 13385 98.15 97.99 98.07 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.39 98.35 98.37 Avg2. 46451 46451 45737 98.46 98.46 98.46 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12204 11773 96.47 96.34 96.41 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.47 96.34 96.41 Avg2. 12220 12204 11773 96.47 96.34 96.41 Current max chunk-based F1: 96.46 (iteration 106) Training iteration elapsed (including evaluation time): 26 seconds The training process elapsed: 3369 seconds