OPTION VALUES: Model directory: ./IOE2+0.03/ 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: IOE2 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: 706357 Number of features: 1350514 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: 0.0300 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 = -2152235.368322 Norm (log-likelihood gradient vector) = 505990.260862 Norm (lambda vector) = 34.863485 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 21310 19969 93.71 97.07 95.36 i-np 13660 13115 12230 93.25 89.53 91.35 e-np 12220 12026 11349 94.37 92.87 93.62 ----- ------ ----- ----- ------- ------- ------------- Avg1. 93.78 93.16 93.47 Avg2. 46451 46451 43548 93.75 93.75 93.75 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12026 9965 82.86 81.55 82.20 ----- ------ ----- ----- ------- ------- ------------- Avg1. 82.86 81.55 82.20 Avg2. 12220 12026 9965 82.86 81.55 82.20 Current max chunk-based F1: 82.20 (iteration 1) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 2 Log-likelihood = -1681010.214854 Norm (log-likelihood gradient vector) = 425284.789216 Norm (lambda vector) = 34.902169 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 19930 18349 92.07 89.20 90.61 i-np 13660 14837 12315 83.00 90.15 86.43 e-np 12220 11684 10622 90.91 86.92 88.87 ----- ------ ----- ----- ------- ------- ------------- Avg1. 88.66 88.76 88.71 Avg2. 46451 46451 41286 88.88 88.88 88.88 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 11686 8259 70.67 67.59 69.10 ----- ------ ----- ----- ------- ------- ------------- Avg1. 70.67 67.59 69.10 Avg2. 12220 11686 8259 70.67 67.59 69.10 Current max chunk-based F1: 82.20 (iteration 1) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 3 Log-likelihood = -651528.297054 Norm (log-likelihood gradient vector) = 255297.747681 Norm (lambda vector) = 35.980825 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 22128 20046 90.59 97.45 93.89 i-np 13660 13801 12613 91.39 92.34 91.86 e-np 12220 10522 10218 97.11 83.62 89.86 ----- ------ ----- ----- ------- ------- ------------- Avg1. 93.03 91.13 92.07 Avg2. 46451 46451 42877 92.31 92.31 92.31 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 10524 8951 85.05 73.25 78.71 ----- ------ ----- ----- ------- ------- ------------- Avg1. 85.05 73.25 78.71 Avg2. 12220 10524 8951 85.05 73.25 78.71 Current max chunk-based F1: 82.20 (iteration 1) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 4 Log-likelihood = -483837.113477 Norm (log-likelihood gradient vector) = 140376.035912 Norm (lambda vector) = 36.027159 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 21108 19994 94.72 97.20 95.94 i-np 13660 13745 12675 92.22 92.79 92.50 e-np 12220 11598 11129 95.96 91.07 93.45 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.30 93.69 93.99 Avg2. 46451 46451 43798 94.29 94.29 94.29 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 11599 9894 85.30 80.97 83.08 ----- ------ ----- ----- ------- ------- ------------- Avg1. 85.30 80.97 83.08 Avg2. 12220 11599 9894 85.30 80.97 83.08 Current max chunk-based F1: 83.08 (iteration 4) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 5 Log-likelihood = -461811.793680 Norm (log-likelihood gradient vector) = 73594.548000 Norm (lambda vector) = 35.955388 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 21127 20089 95.09 97.66 96.35 i-np 13660 13435 12709 94.60 93.04 93.81 e-np 12220 11889 11454 96.34 93.73 95.02 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.34 94.81 95.07 Avg2. 46451 46451 44252 95.27 95.27 95.27 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 11890 10476 88.11 85.73 86.90 ----- ------ ----- ----- ------- ------- ------------- Avg1. 88.11 85.73 86.90 Avg2. 12220 11890 10476 88.11 85.73 86.90 Current max chunk-based F1: 86.90 (iteration 5) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 6 Log-likelihood = -444552.622271 Norm (log-likelihood gradient vector) = 53569.369159 Norm (lambda vector) = 35.972991 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 20959 20155 96.16 97.98 97.06 i-np 13660 13477 12848 95.33 94.06 94.69 e-np 12220 12015 11639 96.87 95.25 96.05 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.12 95.76 95.94 Avg2. 46451 46451 44642 96.11 96.11 96.11 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12015 10795 89.85 88.34 89.09 ----- ------ ----- ----- ------- ------- ------------- Avg1. 89.85 88.34 89.09 Avg2. 12220 12015 10795 89.85 88.34 89.09 Current max chunk-based F1: 89.09 (iteration 6) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 7 Log-likelihood = -407464.197581 Norm (log-likelihood gradient vector) = 47526.575063 Norm (lambda vector) = 36.266231 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 21006 20269 96.49 98.53 97.50 i-np 13660 13231 12791 96.67 93.64 95.13 e-np 12220 12214 11822 96.79 96.74 96.77 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.65 96.30 96.48 Avg2. 46451 46451 44882 96.62 96.62 96.62 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12215 11091 90.80 90.76 90.78 ----- ------ ----- ----- ------- ------- ------------- Avg1. 90.80 90.76 90.78 Avg2. 12220 12215 11091 90.80 90.76 90.78 Current max chunk-based F1: 90.78 (iteration 7) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 8 Log-likelihood = -356728.360056 Norm (log-likelihood gradient vector) = 45662.620973 Norm (lambda vector) = 36.978283 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 19898 19600 98.50 95.28 96.86 i-np 13660 14952 13397 89.60 98.07 93.65 e-np 12220 11601 11433 98.55 93.56 95.99 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.55 95.64 95.59 Avg2. 46451 46451 44430 95.65 95.65 95.65 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 11624 10526 90.55 86.14 88.29 ----- ------ ----- ----- ------- ------- ------------- Avg1. 90.55 86.14 88.29 Avg2. 12220 11624 10526 90.55 86.14 88.29 Current max chunk-based F1: 90.78 (iteration 7) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 9 Log-likelihood = -338794.634711 Norm (log-likelihood gradient vector) = 102026.307433 Norm (lambda vector) = 39.514826 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 20730 20211 97.50 98.25 97.87 i-np 13660 13621 13068 95.94 95.67 95.80 e-np 12220 12100 11819 97.68 96.72 97.20 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.04 96.88 96.96 Avg2. 46451 46451 45098 97.09 97.09 97.09 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12116 11188 92.34 91.55 91.95 ----- ------ ----- ----- ------- ------- ------------- Avg1. 92.34 91.55 91.95 Avg2. 12220 12116 11188 92.34 91.55 91.95 Current max chunk-based F1: 91.95 (iteration 9) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 10 Log-likelihood = -279689.708242 Norm (log-likelihood gradient vector) = 30507.242216 Norm (lambda vector) = 40.365538 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 20870 20296 97.25 98.66 97.95 i-np 13660 13403 12983 96.87 95.04 95.95 e-np 12220 12178 11865 97.43 97.09 97.26 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.18 96.93 97.06 Avg2. 46451 46451 45144 97.19 97.19 97.19 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12195 11274 92.45 92.26 92.35 ----- ------ ----- ----- ------- ------- ------------- Avg1. 92.45 92.26 92.35 Avg2. 12220 12195 11274 92.45 92.26 92.35 Current max chunk-based F1: 92.35 (iteration 10) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 11 Log-likelihood = -268500.826651 Norm (log-likelihood gradient vector) = 19441.214011 Norm (lambda vector) = 41.242493 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 20938 20331 97.10 98.83 97.96 i-np 13660 13291 12929 97.28 94.65 95.94 e-np 12220 12222 11889 97.28 97.29 97.28 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.22 96.92 97.07 Avg2. 46451 46451 45149 97.20 97.20 97.20 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12237 11313 92.45 92.58 92.51 ----- ------ ----- ----- ------- ------- ------------- Avg1. 92.45 92.58 92.51 Avg2. 12220 12237 11313 92.45 92.58 92.51 Current max chunk-based F1: 92.51 (iteration 11) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 12 Log-likelihood = -257329.663503 Norm (log-likelihood gradient vector) = 17390.797013 Norm (lambda vector) = 42.834195 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 20338 97.24 98.87 98.05 i-np 13660 13342 12984 97.32 95.05 96.17 e-np 12220 12193 11883 97.46 97.24 97.35 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.34 97.05 97.20 Avg2. 46451 46451 45205 97.32 97.32 97.32 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12204 11349 92.99 92.87 92.93 ----- ------ ----- ----- ------- ------- ------------- Avg1. 92.99 92.87 92.93 Avg2. 12220 12204 11349 92.99 92.87 92.93 Current max chunk-based F1: 92.93 (iteration 12) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 13 Log-likelihood = -243679.184147 Norm (log-likelihood gradient vector) = 18808.743527 Norm (lambda vector) = 44.973289 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 20869 20356 97.54 98.95 98.24 i-np 13660 13322 13022 97.75 95.33 96.52 e-np 12220 12260 11942 97.41 97.73 97.57 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.57 97.34 97.45 Avg2. 46451 46451 45320 97.57 97.57 97.57 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12270 11455 93.36 93.74 93.55 ----- ------ ----- ----- ------- ------- ------------- Avg1. 93.36 93.74 93.55 Avg2. 12220 12270 11455 93.36 93.74 93.55 Current max chunk-based F1: 93.55 (iteration 13) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 14 Log-likelihood = -232411.536559 Norm (log-likelihood gradient vector) = 19603.065246 Norm (lambda vector) = 49.611015 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 20773 20326 97.85 98.81 98.33 i-np 13660 13483 13124 97.34 96.08 96.70 e-np 12220 12195 11914 97.70 97.50 97.60 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.63 97.46 97.54 Avg2. 46451 46451 45364 97.66 97.66 97.66 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12202 11429 93.66 93.53 93.60 ----- ------ ----- ----- ------- ------- ------------- Avg1. 93.66 93.53 93.60 Avg2. 12220 12202 11429 93.66 93.53 93.60 Current max chunk-based F1: 93.60 (iteration 14) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 15 Log-likelihood = -219500.179965 Norm (log-likelihood gradient vector) = 13364.181165 Norm (lambda vector) = 50.828029 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 20708 20307 98.06 98.72 98.39 i-np 13660 13594 13197 97.08 96.61 96.84 e-np 12220 12149 11897 97.93 97.36 97.64 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.69 97.56 97.63 Avg2. 46451 46451 45401 97.74 97.74 97.74 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12154 11425 94.00 93.49 93.75 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.00 93.49 93.75 Avg2. 12220 12154 11425 94.00 93.49 93.75 Current max chunk-based F1: 93.75 (iteration 15) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 16 Log-likelihood = -210848.444445 Norm (log-likelihood gradient vector) = 13220.638583 Norm (lambda vector) = 51.860313 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 20631 20265 98.23 98.51 98.37 i-np 13660 13704 13250 96.69 97.00 96.84 e-np 12220 12116 11887 98.11 97.27 97.69 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.67 97.60 97.63 Avg2. 46451 46451 45402 97.74 97.74 97.74 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12120 11426 94.27 93.50 93.89 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.27 93.50 93.89 Avg2. 12220 12120 11426 94.27 93.50 93.89 Current max chunk-based F1: 93.89 (iteration 16) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 17 Log-likelihood = -199290.640609 Norm (log-likelihood gradient vector) = 13395.433229 Norm (lambda vector) = 53.107409 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 20629 20280 98.31 98.59 98.45 i-np 13660 13633 13239 97.11 96.92 97.01 e-np 12220 12189 11934 97.91 97.66 97.78 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.78 97.72 97.75 Avg2. 46451 46451 45453 97.85 97.85 97.85 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12190 11509 94.41 94.18 94.30 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.41 94.18 94.30 Avg2. 12220 12190 11509 94.41 94.18 94.30 Current max chunk-based F1: 94.30 (iteration 17) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 18 Log-likelihood = -184040.528329 Norm (log-likelihood gradient vector) = 17348.056985 Norm (lambda vector) = 54.706460 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 20250 98.44 98.44 98.44 i-np 13660 13772 13299 96.57 97.36 96.96 e-np 12220 12108 11889 98.19 97.29 97.74 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.73 97.70 97.71 Avg2. 46451 46451 45438 97.82 97.82 97.82 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12110 11453 94.57 93.72 94.15 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.57 93.72 94.15 Avg2. 12220 12110 11453 94.57 93.72 94.15 Current max chunk-based F1: 94.30 (iteration 17) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 19 Log-likelihood = -175916.379806 Norm (log-likelihood gradient vector) = 11201.598979 Norm (lambda vector) = 55.213165 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 20685 20307 98.17 98.72 98.44 i-np 13660 13571 13202 97.28 96.65 96.96 e-np 12220 12195 11931 97.84 97.64 97.73 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.76 97.67 97.71 Avg2. 46451 46451 45440 97.82 97.82 97.82 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12198 11506 94.33 94.16 94.24 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.33 94.16 94.24 Avg2. 12220 12198 11506 94.33 94.16 94.24 Current max chunk-based F1: 94.30 (iteration 17) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 20 Log-likelihood = -170773.244500 Norm (log-likelihood gradient vector) = 9327.483364 Norm (lambda vector) = 55.964729 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 20666 20297 98.21 98.67 98.44 i-np 13660 13585 13211 97.25 96.71 96.98 e-np 12220 12200 11939 97.86 97.70 97.78 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.77 97.69 97.73 Avg2. 46451 46451 45447 97.84 97.84 97.84 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12203 11510 94.32 94.19 94.26 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.32 94.19 94.26 Avg2. 12220 12203 11510 94.32 94.19 94.26 Current max chunk-based F1: 94.30 (iteration 17) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 21 Log-likelihood = -163998.042499 Norm (log-likelihood gradient vector) = 10961.652390 Norm (lambda vector) = 57.263639 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 20829 20357 97.73 98.96 98.34 i-np 13660 13334 13060 97.95 95.61 96.76 e-np 12220 12288 11980 97.49 98.04 97.76 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.72 97.53 97.63 Avg2. 46451 46451 45397 97.73 97.73 97.73 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12292 11545 93.92 94.48 94.20 ----- ------ ----- ----- ------- ------- ------------- Avg1. 93.92 94.48 94.20 Avg2. 12220 12292 11545 93.92 94.48 94.20 Current max chunk-based F1: 94.30 (iteration 17) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 22 Log-likelihood = -153007.239607 Norm (log-likelihood gradient vector) = 18975.767875 Norm (lambda vector) = 60.136083 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 20692 20319 98.20 98.77 98.49 i-np 13660 13528 13194 97.53 96.59 97.06 e-np 12220 12231 11968 97.85 97.94 97.89 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.86 97.77 97.81 Avg2. 46451 46451 45481 97.91 97.91 97.91 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12233 11557 94.47 94.57 94.52 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.47 94.57 94.52 Avg2. 12220 12233 11557 94.47 94.57 94.52 Current max chunk-based F1: 94.52 (iteration 22) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 23 Log-likelihood = -143493.994286 Norm (log-likelihood gradient vector) = 8573.942402 Norm (lambda vector) = 61.708294 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 20605 20293 98.49 98.65 98.57 i-np 13660 13638 13276 97.35 97.19 97.27 e-np 12220 12208 11973 98.08 97.98 98.03 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.97 97.94 97.95 Avg2. 46451 46451 45542 98.04 98.04 98.04 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12210 11580 94.84 94.76 94.80 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.84 94.76 94.80 Avg2. 12220 12210 11580 94.84 94.76 94.80 Current max chunk-based F1: 94.80 (iteration 23) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 24 Log-likelihood = -137831.231147 Norm (log-likelihood gradient vector) = 6446.205362 Norm (lambda vector) = 62.675999 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 20285 98.58 98.61 98.60 i-np 13660 13688 13310 97.24 97.44 97.34 e-np 12220 12186 11967 98.20 97.93 98.07 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.01 97.99 98.00 Avg2. 46451 46451 45562 98.09 98.09 98.09 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12188 11586 95.06 94.81 94.94 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.06 94.81 94.94 Avg2. 12220 12188 11586 95.06 94.81 94.94 Current max chunk-based F1: 94.94 (iteration 24) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 25 Log-likelihood = -134082.423599 Norm (log-likelihood gradient vector) = 7763.913049 Norm (lambda vector) = 63.550382 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 20306 98.63 98.71 98.67 i-np 13660 13669 13320 97.45 97.51 97.48 e-np 12220 12194 11984 98.28 98.07 98.17 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.12 98.10 98.11 Avg2. 46451 46451 45610 98.19 98.19 98.19 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12195 11627 95.34 95.15 95.24 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.34 95.15 95.24 Avg2. 12220 12195 11627 95.34 95.15 95.24 Current max chunk-based F1: 95.24 (iteration 25) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 26 Log-likelihood = -127514.149899 Norm (log-likelihood gradient vector) = 7461.123530 Norm (lambda vector) = 65.530489 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 20286 19991 98.55 97.18 97.86 i-np 13660 14419 13390 92.86 98.02 95.37 e-np 12220 11746 11611 98.85 95.02 96.90 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.75 96.74 96.75 Avg2. 46451 46451 44992 96.86 96.86 96.86 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 11748 11082 94.33 90.69 92.47 ----- ------ ----- ----- ------- ------- ------------- Avg1. 94.33 90.69 92.47 Avg2. 12220 11748 11082 94.33 90.69 92.47 Current max chunk-based F1: 95.24 (iteration 25) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 27 Log-likelihood = -140850.165164 Norm (log-likelihood gradient vector) = 55629.942364 Norm (lambda vector) = 71.214255 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 20515 20255 98.73 98.46 98.60 i-np 13660 13860 13383 96.56 97.97 97.26 e-np 12220 12076 11911 98.63 97.47 98.05 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.97 97.97 97.97 Avg2. 46451 46451 45549 98.06 98.06 98.06 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12079 11528 95.44 94.34 94.88 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.44 94.34 94.88 Avg2. 12220 12079 11528 95.44 94.34 94.88 Current max chunk-based F1: 95.24 (iteration 25) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 28 Log-likelihood = -124168.188831 Norm (log-likelihood gradient vector) = 16486.144420 Norm (lambda vector) = 67.306883 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 20316 98.59 98.76 98.68 i-np 13660 13673 13320 97.42 97.51 97.46 e-np 12220 12172 11976 98.39 98.00 98.20 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.13 98.09 98.11 Avg2. 46451 46451 45612 98.19 98.19 98.19 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12173 11625 95.50 95.13 95.31 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.50 95.13 95.31 Avg2. 12220 12173 11625 95.50 95.13 95.31 Current max chunk-based F1: 95.31 (iteration 28) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 29 Log-likelihood = -119199.906865 Norm (log-likelihood gradient vector) = 7086.233246 Norm (lambda vector) = 69.218020 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 20646 20333 98.48 98.84 98.66 i-np 13660 13593 13279 97.69 97.21 97.45 e-np 12220 12212 11994 98.21 98.15 98.18 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.13 98.07 98.10 Avg2. 46451 46451 45606 98.18 98.18 98.18 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12213 11646 95.36 95.30 95.33 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.36 95.30 95.33 Avg2. 12220 12213 11646 95.36 95.30 95.33 Current max chunk-based F1: 95.33 (iteration 29) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 30 Log-likelihood = -116388.683189 Norm (log-likelihood gradient vector) = 5183.803578 Norm (lambda vector) = 69.906924 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 20674 20344 98.40 98.90 98.65 i-np 13660 13549 13252 97.81 97.01 97.41 e-np 12220 12228 11999 98.13 98.19 98.16 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.11 98.03 98.07 Avg2. 46451 46451 45595 98.16 98.16 98.16 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12229 11655 95.31 95.38 95.34 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.31 95.38 95.34 Avg2. 12220 12229 11655 95.31 95.38 95.34 Current max chunk-based F1: 95.34 (iteration 30) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 31 Log-likelihood = -111731.632652 Norm (log-likelihood gradient vector) = 5553.680986 Norm (lambda vector) = 71.796795 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 20617 20320 98.56 98.78 98.67 i-np 13660 13625 13289 97.53 97.28 97.41 e-np 12220 12209 11989 98.20 98.11 98.15 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.10 98.06 98.08 Avg2. 46451 46451 45598 98.16 98.16 98.16 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12209 11641 95.35 95.26 95.30 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.35 95.26 95.30 Avg2. 12220 12209 11641 95.35 95.26 95.30 Current max chunk-based F1: 95.34 (iteration 30) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 32 Log-likelihood = -106250.164501 Norm (log-likelihood gradient vector) = 6436.255821 Norm (lambda vector) = 74.687602 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 20688 20367 98.45 99.01 98.73 i-np 13660 13509 13253 98.10 97.02 97.56 e-np 12220 12254 12016 98.06 98.33 98.19 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.20 98.12 98.16 Avg2. 46451 46451 45636 98.25 98.25 98.25 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12254 11690 95.40 95.66 95.53 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.40 95.66 95.53 Avg2. 12220 12254 11690 95.40 95.66 95.53 Current max chunk-based F1: 95.53 (iteration 32) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 33 Log-likelihood = -100676.827029 Norm (log-likelihood gradient vector) = 8644.796514 Norm (lambda vector) = 78.647396 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 20615 20333 98.63 98.84 98.74 i-np 13660 13627 13310 97.67 97.44 97.56 e-np 12220 12209 11992 98.22 98.13 98.18 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.18 98.14 98.16 Avg2. 46451 46451 45635 98.24 98.24 98.24 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12209 11654 95.45 95.37 95.41 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.45 95.37 95.41 Avg2. 12220 12209 11654 95.45 95.37 95.41 Current max chunk-based F1: 95.53 (iteration 32) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 34 Log-likelihood = -98449.286758 Norm (log-likelihood gradient vector) = 3966.931447 Norm (lambda vector) = 78.419962 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 20314 98.73 98.75 98.74 i-np 13660 13691 13341 97.44 97.66 97.55 e-np 12220 12184 11985 98.37 98.08 98.22 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.18 98.16 98.17 Avg2. 46451 46451 45640 98.25 98.25 98.25 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12184 11646 95.58 95.30 95.44 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.58 95.30 95.44 Avg2. 12220 12184 11646 95.58 95.30 95.44 Current max chunk-based F1: 95.53 (iteration 32) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 35 Log-likelihood = -96741.945955 Norm (log-likelihood gradient vector) = 4555.160259 Norm (lambda vector) = 78.788839 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 20549 20305 98.81 98.71 98.76 i-np 13660 13718 13362 97.40 97.82 97.61 e-np 12220 12184 11988 98.39 98.10 98.25 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.20 98.21 98.21 Avg2. 46451 46451 45655 98.29 98.29 98.29 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12184 11657 95.67 95.39 95.53 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.67 95.39 95.53 Avg2. 12220 12184 11657 95.67 95.39 95.53 Current max chunk-based F1: 95.53 (iteration 35) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 36 Log-likelihood = -94706.767210 Norm (log-likelihood gradient vector) = 5563.662724 Norm (lambda vector) = 79.629204 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 20555 20308 98.80 98.72 98.76 i-np 13660 13692 13354 97.53 97.76 97.65 e-np 12220 12204 12002 98.34 98.22 98.28 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.22 98.23 98.23 Avg2. 46451 46451 45664 98.31 98.31 98.31 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12204 11677 95.68 95.56 95.62 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.68 95.56 95.62 Avg2. 12220 12204 11677 95.68 95.56 95.62 Current max chunk-based F1: 95.62 (iteration 36) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 37 Log-likelihood = -91743.670383 Norm (log-likelihood gradient vector) = 4701.928431 Norm (lambda vector) = 81.619021 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 20420 20198 98.91 98.19 98.55 i-np 13660 14028 13424 95.69 98.27 96.97 e-np 12220 12003 11860 98.81 97.05 97.92 ----- ------ ----- ----- ------- ------- ------------- Avg1. 97.81 97.84 97.82 Avg2. 46451 46451 45482 97.91 97.91 97.91 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12003 11461 95.48 93.79 94.63 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.48 93.79 94.63 Avg2. 12220 12003 11461 95.48 93.79 94.63 Current max chunk-based F1: 95.62 (iteration 36) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 38 Log-likelihood = -95757.934887 Norm (log-likelihood gradient vector) = 29608.488766 Norm (lambda vector) = 87.857434 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 20294 98.85 98.65 98.75 i-np 13660 13774 13388 97.20 98.01 97.60 e-np 12220 12146 11975 98.59 98.00 98.29 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.21 98.22 98.22 Avg2. 46451 46451 45657 98.29 98.29 98.29 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12146 11637 95.81 95.23 95.52 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.81 95.23 95.52 Avg2. 12220 12146 11637 95.81 95.23 95.52 Current max chunk-based F1: 95.62 (iteration 36) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 39 Log-likelihood = -89825.879485 Norm (log-likelihood gradient vector) = 11002.724233 Norm (lambda vector) = 83.957119 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 20588 20324 98.72 98.80 98.76 i-np 13660 13660 13335 97.62 97.62 97.62 e-np 12220 12203 12002 98.35 98.22 98.28 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.23 98.21 98.22 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 11681 95.72 95.59 95.66 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.72 95.59 95.66 Avg2. 12220 12203 11681 95.72 95.59 95.66 Current max chunk-based F1: 95.66 (iteration 39) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 40 Log-likelihood = -87650.572674 Norm (log-likelihood gradient vector) = 3601.081674 Norm (lambda vector) = 85.243278 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 20604 20331 98.68 98.83 98.75 i-np 13660 13633 13320 97.70 97.51 97.61 e-np 12220 12214 12006 98.30 98.25 98.27 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.23 98.20 98.21 Avg2. 46451 46451 45657 98.29 98.29 98.29 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12214 11690 95.71 95.66 95.69 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.71 95.66 95.69 Avg2. 12220 12214 11690 95.71 95.66 95.69 Current max chunk-based F1: 95.69 (iteration 40) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 41 Log-likelihood = -86409.821094 Norm (log-likelihood gradient vector) = 3544.787350 Norm (lambda vector) = 86.127723 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 20618 20340 98.65 98.88 98.76 i-np 13660 13604 13307 97.82 97.42 97.62 e-np 12220 12229 12011 98.22 98.29 98.25 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.23 98.19 98.21 Avg2. 46451 46451 45658 98.29 98.29 98.29 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12229 11693 95.62 95.69 95.65 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.62 95.69 95.65 Avg2. 12220 12229 11693 95.62 95.69 95.65 Current max chunk-based F1: 95.69 (iteration 40) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 42 Log-likelihood = -84630.891558 Norm (log-likelihood gradient vector) = 3811.889474 Norm (lambda vector) = 87.326550 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 20632 20351 98.64 98.93 98.78 i-np 13660 13596 13310 97.90 97.44 97.67 e-np 12220 12223 12013 98.28 98.31 98.29 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.27 98.22 98.25 Avg2. 46451 46451 45674 98.33 98.33 98.33 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12223 11703 95.75 95.77 95.76 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.75 95.77 95.76 Avg2. 12220 12223 11703 95.75 95.77 95.76 Current max chunk-based F1: 95.76 (iteration 42) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 43 Log-likelihood = -80649.320517 Norm (log-likelihood gradient vector) = 4919.166504 Norm (lambda vector) = 90.562160 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 20500 20278 98.92 98.58 98.75 i-np 13660 13730 13373 97.40 97.90 97.65 e-np 12220 12221 12006 98.24 98.25 98.24 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.19 98.24 98.21 Avg2. 46451 46451 45657 98.29 98.29 98.29 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12221 11688 95.64 95.65 95.64 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.64 95.65 95.64 Avg2. 12220 12221 11688 95.64 95.65 95.64 Current max chunk-based F1: 95.76 (iteration 42) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 44 Log-likelihood = -76158.782325 Norm (log-likelihood gradient vector) = 11431.655019 Norm (lambda vector) = 97.960423 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 20333 98.79 98.84 98.82 i-np 13660 13650 13345 97.77 97.69 97.73 e-np 12220 12219 12013 98.31 98.31 98.31 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.29 98.28 98.29 Avg2. 46451 46451 45691 98.36 98.36 98.36 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12219 11709 95.83 95.82 95.82 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.83 95.82 95.82 Avg2. 12220 12219 11709 95.83 95.82 95.82 Current max chunk-based F1: 95.82 (iteration 44) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 45 Log-likelihood = -76799.051938 Norm (log-likelihood gradient vector) = 5200.101173 Norm (lambda vector) = 94.050758 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 20608 20343 98.71 98.89 98.80 i-np 13660 13619 13326 97.85 97.55 97.70 e-np 12220 12224 12015 98.29 98.32 98.31 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.28 98.26 98.27 Avg2. 46451 46451 45684 98.35 98.35 98.35 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12224 11709 95.79 95.82 95.80 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.79 95.82 95.80 Avg2. 12220 12224 11709 95.79 95.82 95.80 Current max chunk-based F1: 95.82 (iteration 44) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 46 Log-likelihood = -74006.510666 Norm (log-likelihood gradient vector) = 3200.330163 Norm (lambda vector) = 95.981146 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 20564 20325 98.84 98.80 98.82 i-np 13660 13708 13382 97.62 97.96 97.79 e-np 12220 12179 11997 98.51 98.18 98.34 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.32 98.31 98.32 Avg2. 46451 46451 45704 98.39 98.39 98.39 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12179 11694 96.02 95.70 95.86 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.02 95.70 95.86 Avg2. 12220 12179 11694 96.02 95.70 95.86 Current max chunk-based F1: 95.86 (iteration 46) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 47 Log-likelihood = -71194.693466 Norm (log-likelihood gradient vector) = 3778.409769 Norm (lambda vector) = 97.740833 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 20331 98.77 98.83 98.80 i-np 13660 13669 13357 97.72 97.78 97.75 e-np 12220 12198 12003 98.40 98.22 98.31 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.30 98.28 98.29 Avg2. 46451 46451 45691 98.36 98.36 98.36 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12198 11696 95.88 95.71 95.80 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.88 95.71 95.80 Avg2. 12220 12198 11696 95.88 95.71 95.80 Current max chunk-based F1: 95.86 (iteration 46) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 48 Log-likelihood = -68892.451971 Norm (log-likelihood gradient vector) = 3457.695131 Norm (lambda vector) = 98.855020 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 20323 98.83 98.79 98.81 i-np 13660 13694 13371 97.64 97.88 97.76 e-np 12220 12194 12006 98.46 98.25 98.35 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.31 98.31 98.31 Avg2. 46451 46451 45700 98.38 98.38 98.38 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12194 11703 95.97 95.77 95.87 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.97 95.77 95.87 Avg2. 12220 12194 11703 95.97 95.77 95.87 Current max chunk-based F1: 95.87 (iteration 48) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 49 Log-likelihood = -66743.621648 Norm (log-likelihood gradient vector) = 3454.927375 Norm (lambda vector) = 99.641179 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 20623 20339 98.62 98.87 98.75 i-np 13660 13520 13258 98.06 97.06 97.56 e-np 12220 12308 12046 97.87 98.58 98.22 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.19 98.17 98.18 Avg2. 46451 46451 45643 98.26 98.26 98.26 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12308 11716 95.19 95.88 95.53 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.19 95.88 95.53 Avg2. 12220 12308 11716 95.19 95.88 95.53 Current max chunk-based F1: 95.87 (iteration 48) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 50 Log-likelihood = -65835.042952 Norm (log-likelihood gradient vector) = 9969.086406 Norm (lambda vector) = 102.315988 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 20545 20315 98.88 98.76 98.82 i-np 13660 13684 13370 97.71 97.88 97.79 e-np 12220 12222 12017 98.32 98.34 98.33 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.30 98.32 98.31 Avg2. 46451 46451 45702 98.39 98.39 98.39 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12222 11707 95.79 95.80 95.79 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.79 95.80 95.79 Avg2. 12220 12222 11707 95.79 95.80 95.79 Current max chunk-based F1: 95.87 (iteration 48) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 51 Log-likelihood = -63967.877820 Norm (log-likelihood gradient vector) = 3307.721103 Norm (lambda vector) = 102.159607 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 20555 20319 98.85 98.77 98.81 i-np 13660 13683 13368 97.70 97.86 97.78 e-np 12220 12213 12013 98.36 98.31 98.33 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.30 98.31 98.31 Avg2. 46451 46451 45700 98.38 98.38 98.38 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12213 11706 95.85 95.79 95.82 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.85 95.79 95.82 Avg2. 12220 12213 11706 95.85 95.79 95.82 Current max chunk-based F1: 95.87 (iteration 48) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 52 Log-likelihood = -63341.338083 Norm (log-likelihood gradient vector) = 2428.198695 Norm (lambda vector) = 102.743930 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 20551 20318 98.87 98.77 98.82 i-np 13660 13688 13367 97.65 97.86 97.75 e-np 12220 12212 12010 98.35 98.28 98.31 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.29 98.30 98.30 Avg2. 46451 46451 45695 98.37 98.37 98.37 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12212 11703 95.83 95.77 95.80 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.83 95.77 95.80 Avg2. 12220 12212 11703 95.83 95.77 95.80 Current max chunk-based F1: 95.87 (iteration 48) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 53 Log-likelihood = -61374.522778 Norm (log-likelihood gradient vector) = 2833.095797 Norm (lambda vector) = 105.392998 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 20706 20382 98.44 99.08 98.76 i-np 13660 13516 13272 98.19 97.16 97.67 e-np 12220 12229 12020 98.29 98.36 98.33 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.31 98.20 98.25 Avg2. 46451 46451 45674 98.33 98.33 98.33 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12229 11714 95.79 95.86 95.82 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.79 95.86 95.82 Avg2. 12220 12229 11714 95.79 95.86 95.82 Current max chunk-based F1: 95.87 (iteration 48) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 54 Log-likelihood = -61314.367349 Norm (log-likelihood gradient vector) = 15514.918335 Norm (lambda vector) = 110.914997 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 20331 98.77 98.83 98.80 i-np 13660 13652 13347 97.77 97.71 97.74 e-np 12220 12215 12011 98.33 98.29 98.31 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.29 98.28 98.28 Avg2. 46451 46451 45689 98.36 98.36 98.36 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12215 11707 95.84 95.80 95.82 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.84 95.80 95.82 Avg2. 12220 12215 11707 95.84 95.80 95.82 Current max chunk-based F1: 95.87 (iteration 48) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 55 Log-likelihood = -60006.864770 Norm (log-likelihood gradient vector) = 3584.660013 Norm (lambda vector) = 107.002120 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 20572 20320 98.78 98.78 98.78 i-np 13660 13669 13348 97.65 97.72 97.68 e-np 12220 12210 12003 98.30 98.22 98.26 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.24 98.24 98.24 Avg2. 46451 46451 45671 98.32 98.32 98.32 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12210 11689 95.73 95.65 95.69 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.73 95.65 95.69 Avg2. 12220 12210 11689 95.73 95.65 95.69 Current max chunk-based F1: 95.87 (iteration 48) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 56 Log-likelihood = -58244.207440 Norm (log-likelihood gradient vector) = 2566.381522 Norm (lambda vector) = 109.305177 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 20574 20324 98.78 98.80 98.79 i-np 13660 13653 13341 97.71 97.66 97.69 e-np 12220 12224 12013 98.27 98.31 98.29 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.26 98.26 98.26 Avg2. 46451 46451 45678 98.34 98.34 98.34 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12224 11696 95.68 95.71 95.70 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.68 95.71 95.70 Avg2. 12220 12224 11696 95.68 95.71 95.70 Current max chunk-based F1: 95.87 (iteration 48) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 57 Log-likelihood = -55576.204674 Norm (log-likelihood gradient vector) = 2338.647310 Norm (lambda vector) = 112.761116 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 20555 20319 98.85 98.77 98.81 i-np 13660 13717 13379 97.54 97.94 97.74 e-np 12220 12179 11992 98.46 98.13 98.30 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.28 98.28 98.28 Avg2. 46451 46451 45690 98.36 98.36 98.36 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12180 11683 95.92 95.61 95.76 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.92 95.61 95.76 Avg2. 12220 12180 11683 95.92 95.61 95.76 Current max chunk-based F1: 95.87 (iteration 48) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 58 Log-likelihood = -53228.233638 Norm (log-likelihood gradient vector) = 3905.484525 Norm (lambda vector) = 116.959225 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 20576 20335 98.83 98.85 98.84 i-np 13660 13673 13366 97.75 97.85 97.80 e-np 12220 12202 12009 98.42 98.27 98.35 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.33 98.32 98.33 Avg2. 46451 46451 45710 98.40 98.40 98.40 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12202 11706 95.94 95.79 95.86 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.94 95.79 95.86 Avg2. 12220 12202 11706 95.94 95.79 95.86 Current max chunk-based F1: 95.87 (iteration 48) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 59 Log-likelihood = -52262.030389 Norm (log-likelihood gradient vector) = 2119.270581 Norm (lambda vector) = 117.223609 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 20587 20348 98.84 98.92 98.88 i-np 13660 13640 13359 97.94 97.80 97.87 e-np 12220 12224 12026 98.38 98.41 98.40 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.39 98.37 98.38 Avg2. 46451 46451 45733 98.45 98.45 98.45 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12224 11732 95.98 96.01 95.99 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.98 96.01 95.99 Avg2. 12220 12224 11732 95.98 96.01 95.99 Current max chunk-based F1: 95.99 (iteration 59) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 60 Log-likelihood = -51295.354634 Norm (log-likelihood gradient vector) = 1907.964087 Norm (lambda vector) = 117.450842 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 20619 20360 98.74 98.97 98.86 i-np 13660 13580 13323 98.11 97.53 97.82 e-np 12220 12252 12039 98.26 98.52 98.39 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.37 98.34 98.36 Avg2. 46451 46451 45722 98.43 98.43 98.43 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12252 11740 95.82 96.07 95.95 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.82 96.07 95.95 Avg2. 12220 12252 11740 95.82 96.07 95.95 Current max chunk-based F1: 95.99 (iteration 59) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 61 Log-likelihood = -50133.469482 Norm (log-likelihood gradient vector) = 3783.938366 Norm (lambda vector) = 119.052345 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 20346 98.83 98.91 98.87 i-np 13660 13652 13361 97.87 97.81 97.84 e-np 12220 12213 12030 98.50 98.45 98.47 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.40 98.39 98.39 Avg2. 46451 46451 45737 98.46 98.46 98.46 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12213 11736 96.09 96.04 96.07 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.09 96.04 96.07 Avg2. 12220 12213 11736 96.09 96.04 96.07 Current max chunk-based F1: 96.07 (iteration 61) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 62 Log-likelihood = -48367.002323 Norm (log-likelihood gradient vector) = 3012.956022 Norm (lambda vector) = 121.911796 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 20607 20355 98.78 98.95 98.86 i-np 13660 13613 13340 97.99 97.66 97.83 e-np 12220 12231 12033 98.38 98.47 98.43 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.38 98.36 98.37 Avg2. 46451 46451 45728 98.44 98.44 98.44 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12231 11737 95.96 96.05 96.00 ----- ------ ----- ----- ------- ------- ------------- Avg1. 95.96 96.05 96.00 Avg2. 12220 12231 11737 95.96 96.05 96.00 Current max chunk-based F1: 96.07 (iteration 61) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 63 Log-likelihood = -47283.893013 Norm (log-likelihood gradient vector) = 3282.823303 Norm (lambda vector) = 123.370001 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 20588 20345 98.82 98.90 98.86 i-np 13660 13638 13356 97.93 97.77 97.85 e-np 12220 12225 12032 98.42 98.46 98.44 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.39 98.38 98.39 Avg2. 46451 46451 45733 98.45 98.45 98.45 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12225 11737 96.01 96.05 96.03 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.01 96.05 96.03 Avg2. 12220 12225 11737 96.01 96.05 96.03 Current max chunk-based F1: 96.07 (iteration 61) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 64 Log-likelihood = -46099.209957 Norm (log-likelihood gradient vector) = 2372.490976 Norm (lambda vector) = 124.128590 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 20610 20359 98.78 98.97 98.88 i-np 13660 13627 13351 97.97 97.74 97.86 e-np 12220 12214 12025 98.45 98.40 98.43 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.40 98.37 98.39 Avg2. 46451 46451 45735 98.46 98.46 98.46 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12214 11733 96.06 96.01 96.04 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.06 96.01 96.04 Avg2. 12220 12214 11733 96.06 96.01 96.04 Current max chunk-based F1: 96.07 (iteration 61) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 65 Log-likelihood = -45010.740374 Norm (log-likelihood gradient vector) = 2936.850175 Norm (lambda vector) = 125.130817 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 20539 20317 98.92 98.77 98.84 i-np 13660 13722 13393 97.60 98.05 97.82 e-np 12220 12190 12012 98.54 98.30 98.42 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.35 98.37 98.36 Avg2. 46451 46451 45722 98.43 98.43 98.43 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12190 11713 96.09 95.85 95.97 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.09 95.85 95.97 Avg2. 12220 12190 11713 96.09 95.85 95.97 Current max chunk-based F1: 96.07 (iteration 61) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 66 Log-likelihood = -43729.523970 Norm (log-likelihood gradient vector) = 3378.252600 Norm (lambda vector) = 126.762348 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 20564 20340 98.91 98.88 98.89 i-np 13660 13693 13394 97.82 98.05 97.93 e-np 12220 12194 12021 98.58 98.37 98.48 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.44 98.43 98.43 Avg2. 46451 46451 45755 98.50 98.50 98.50 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12194 11734 96.23 96.02 96.13 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.23 96.02 96.13 Avg2. 12220 12194 11734 96.23 96.02 96.13 Current max chunk-based F1: 96.13 (iteration 66) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 67 Log-likelihood = -43058.920446 Norm (log-likelihood gradient vector) = 2087.658391 Norm (lambda vector) = 127.025039 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 20355 98.88 98.95 98.92 i-np 13660 13661 13384 97.97 97.98 97.98 e-np 12220 12205 12030 98.57 98.45 98.51 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.47 98.46 98.47 Avg2. 46451 46451 45769 98.53 98.53 98.53 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12205 11753 96.30 96.18 96.24 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.30 96.18 96.24 Avg2. 12220 12205 11753 96.30 96.18 96.24 Current max chunk-based F1: 96.24 (iteration 67) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 68 Log-likelihood = -42049.666419 Norm (log-likelihood gradient vector) = 1662.142682 Norm (lambda vector) = 127.570652 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 20605 20366 98.84 99.00 98.92 i-np 13660 13624 13365 98.10 97.84 97.97 e-np 12220 12222 12037 98.49 98.50 98.49 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.45 98.46 Avg2. 46451 46451 45768 98.53 98.53 98.53 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12222 11761 96.23 96.24 96.24 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.23 96.24 96.24 Avg2. 12220 12222 11761 96.23 96.24 96.24 Current max chunk-based F1: 96.24 (iteration 67) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 69 Log-likelihood = -41126.928527 Norm (log-likelihood gradient vector) = 2421.028963 Norm (lambda vector) = 128.467728 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 20349 98.96 98.92 98.94 i-np 13660 13708 13408 97.81 98.16 97.98 e-np 12220 12180 12022 98.70 98.38 98.54 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.49 98.49 98.49 Avg2. 46451 46451 45779 98.55 98.55 98.55 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12180 11753 96.49 96.18 96.34 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.49 96.18 96.34 Avg2. 12220 12180 11753 96.49 96.18 96.34 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 70 Log-likelihood = -39676.321571 Norm (log-likelihood gradient vector) = 2810.286578 Norm (lambda vector) = 130.583912 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 20627 20371 98.76 99.03 98.89 i-np 13660 13576 13333 98.21 97.61 97.91 e-np 12220 12248 12044 98.33 98.56 98.45 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.43 98.40 98.42 Avg2. 46451 46451 45748 98.49 98.49 98.49 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12248 11769 96.09 96.31 96.20 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.09 96.31 96.20 Avg2. 12220 12248 11769 96.09 96.31 96.20 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 71 Log-likelihood = -39165.749626 Norm (log-likelihood gradient vector) = 3847.130202 Norm (lambda vector) = 131.899253 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 20363 98.85 98.99 98.92 i-np 13660 13626 13364 98.08 97.83 97.95 e-np 12220 12226 12036 98.45 98.49 98.47 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.46 98.44 98.45 Avg2. 46451 46451 45763 98.52 98.52 98.52 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12226 11762 96.20 96.25 96.23 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.20 96.25 96.23 Avg2. 12220 12226 11762 96.20 96.25 96.23 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 72 Log-likelihood = -38973.818664 Norm (log-likelihood gradient vector) = 2076.104032 Norm (lambda vector) = 131.561952 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 20344 98.95 98.90 98.92 i-np 13660 13702 13403 97.82 98.12 97.97 e-np 12220 12189 12016 98.58 98.33 98.46 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.45 98.45 98.45 Avg2. 46451 46451 45763 98.52 98.52 98.52 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12189 11740 96.32 96.07 96.19 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.32 96.07 96.19 Avg2. 12220 12189 11740 96.32 96.07 96.19 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 73 Log-likelihood = -38802.540785 Norm (log-likelihood gradient vector) = 1961.500394 Norm (lambda vector) = 131.499847 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 20549 20332 98.94 98.84 98.89 i-np 13660 13727 13403 97.64 98.12 97.88 e-np 12220 12175 12003 98.59 98.22 98.41 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.39 98.39 98.39 Avg2. 46451 46451 45738 98.47 98.47 98.47 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12175 11721 96.27 95.92 96.09 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.27 95.92 96.09 Avg2. 12220 12175 11721 96.27 95.92 96.09 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 74 Log-likelihood = -38592.105703 Norm (log-likelihood gradient vector) = 2345.638462 Norm (lambda vector) = 131.685293 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 20517 20313 99.01 98.75 98.88 i-np 13660 13773 13418 97.42 98.23 97.82 e-np 12220 12161 11990 98.59 98.12 98.36 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.34 98.36 98.35 Avg2. 46451 46451 45721 98.43 98.43 98.43 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12161 11706 96.26 95.79 96.03 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.26 95.79 96.03 Avg2. 12220 12161 11706 96.26 95.79 96.03 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 75 Log-likelihood = -37656.363240 Norm (log-likelihood gradient vector) = 3740.575299 Norm (lambda vector) = 132.990193 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 20322 98.85 98.79 98.82 i-np 13660 13718 13380 97.54 97.95 97.74 e-np 12220 12175 11999 98.55 98.19 98.37 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.31 98.31 98.31 Avg2. 46451 46451 45701 98.39 98.39 98.39 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12175 11711 96.19 95.83 96.01 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.19 95.83 96.01 Avg2. 12220 12175 11711 96.19 95.83 96.01 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 76 Log-likelihood = -37870.854741 Norm (log-likelihood gradient vector) = 5360.625339 Norm (lambda vector) = 133.976999 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 20535 20324 98.97 98.80 98.89 i-np 13660 13746 13409 97.55 98.16 97.85 e-np 12220 12170 12002 98.62 98.22 98.42 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.38 98.39 98.39 Avg2. 46451 46451 45735 98.46 98.46 98.46 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12170 11726 96.35 95.96 96.15 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.35 95.96 96.15 Avg2. 12220 12170 11726 96.35 95.96 96.15 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 77 Log-likelihood = -37239.034058 Norm (log-likelihood gradient vector) = 2306.936764 Norm (lambda vector) = 133.401374 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 20549 20335 98.96 98.85 98.91 i-np 13660 13717 13403 97.71 98.12 97.91 e-np 12220 12185 12015 98.60 98.32 98.46 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.42 98.43 98.43 Avg2. 46451 46451 45753 98.50 98.50 98.50 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12185 11741 96.36 96.08 96.22 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.36 96.08 96.22 Avg2. 12220 12185 11741 96.36 96.08 96.22 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 78 Log-likelihood = -36451.908442 Norm (log-likelihood gradient vector) = 1686.056171 Norm (lambda vector) = 134.691663 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 20607 20352 98.76 98.94 98.85 i-np 13660 13635 13349 97.90 97.72 97.81 e-np 12220 12209 12016 98.42 98.33 98.37 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.36 98.33 98.35 Avg2. 46451 46451 45717 98.42 98.42 98.42 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12209 11737 96.13 96.05 96.09 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.13 96.05 96.09 Avg2. 12220 12209 11737 96.13 96.05 96.09 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 79 Log-likelihood = -35568.363949 Norm (log-likelihood gradient vector) = 2392.452738 Norm (lambda vector) = 135.693765 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 20577 20343 98.86 98.89 98.88 i-np 13660 13666 13376 97.88 97.92 97.90 e-np 12220 12208 12025 98.50 98.40 98.45 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.41 98.41 98.41 Avg2. 46451 46451 45744 98.48 98.48 98.48 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12208 11757 96.31 96.21 96.26 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.31 96.21 96.26 Avg2. 12220 12208 11757 96.31 96.21 96.26 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 80 Log-likelihood = -34732.772169 Norm (log-likelihood gradient vector) = 1777.465793 Norm (lambda vector) = 136.781824 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 20358 98.80 98.96 98.88 i-np 13660 13609 13350 98.10 97.73 97.91 e-np 12220 12237 12038 98.37 98.51 98.44 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.42 98.40 98.41 Avg2. 46451 46451 45746 98.48 98.48 98.48 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12237 11767 96.16 96.29 96.23 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.16 96.29 96.23 Avg2. 12220 12237 11767 96.16 96.29 96.23 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 81 Log-likelihood = -34403.249887 Norm (log-likelihood gradient vector) = 2454.425370 Norm (lambda vector) = 136.804577 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 20588 20353 98.86 98.94 98.90 i-np 13660 13672 13383 97.89 97.97 97.93 e-np 12220 12191 12018 98.58 98.35 98.46 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.44 98.42 98.43 Avg2. 46451 46451 45754 98.50 98.50 98.50 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12191 11743 96.33 96.10 96.21 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.33 96.10 96.21 Avg2. 12220 12191 11743 96.33 96.10 96.21 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 82 Log-likelihood = -34071.346796 Norm (log-likelihood gradient vector) = 2197.852717 Norm (lambda vector) = 136.790180 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 20351 98.87 98.93 98.90 i-np 13660 13668 13380 97.89 97.95 97.92 e-np 12220 12199 12020 98.53 98.36 98.45 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.43 98.41 98.42 Avg2. 46451 46451 45751 98.49 98.49 98.49 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12199 11744 96.27 96.10 96.19 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.27 96.10 96.19 Avg2. 12220 12199 11744 96.27 96.10 96.19 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 83 Log-likelihood = -33920.930609 Norm (log-likelihood gradient vector) = 1553.038293 Norm (lambda vector) = 136.496397 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 20353 98.88 98.94 98.91 i-np 13660 13660 13380 97.95 97.95 97.95 e-np 12220 12207 12025 98.51 98.40 98.46 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.45 98.43 98.44 Avg2. 46451 46451 45758 98.51 98.51 98.51 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12207 11755 96.30 96.19 96.25 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.30 96.19 96.25 Avg2. 12220 12207 11755 96.30 96.19 96.25 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 84 Log-likelihood = -33426.432013 Norm (log-likelihood gradient vector) = 1418.501830 Norm (lambda vector) = 137.040124 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 20579 20346 98.87 98.91 98.89 i-np 13660 13668 13380 97.89 97.95 97.92 e-np 12220 12204 12020 98.49 98.36 98.43 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.42 98.41 98.41 Avg2. 46451 46451 45746 98.48 98.48 98.48 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12204 11749 96.27 96.15 96.21 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.27 96.15 96.21 Avg2. 12220 12204 11749 96.27 96.15 96.21 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 85 Log-likelihood = -32487.133257 Norm (log-likelihood gradient vector) = 2391.642814 Norm (lambda vector) = 138.902114 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 20552 20336 98.95 98.86 98.90 i-np 13660 13700 13395 97.77 98.06 97.92 e-np 12220 12199 12016 98.50 98.33 98.42 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.41 98.42 98.41 Avg2. 46451 46451 45747 98.48 98.48 98.48 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12199 11740 96.24 96.07 96.15 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.24 96.07 96.15 Avg2. 12220 12199 11740 96.24 96.07 96.15 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 86 Log-likelihood = -32066.120981 Norm (log-likelihood gradient vector) = 4399.216155 Norm (lambda vector) = 141.358798 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 20358 98.87 98.96 98.92 i-np 13660 13651 13382 98.03 97.96 98.00 e-np 12220 12209 12029 98.53 98.44 98.48 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.47 98.46 98.46 Avg2. 46451 46451 45769 98.53 98.53 98.53 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12209 11766 96.37 96.28 96.33 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.37 96.28 96.33 Avg2. 12220 12209 11766 96.37 96.28 96.33 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 87 Log-likelihood = -31200.086685 Norm (log-likelihood gradient vector) = 1609.239587 Norm (lambda vector) = 141.621667 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 20608 20363 98.81 98.99 98.90 i-np 13660 13634 13366 98.03 97.85 97.94 e-np 12220 12209 12027 98.51 98.42 98.46 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.45 98.42 98.44 Avg2. 46451 46451 45756 98.50 98.50 98.50 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12209 11760 96.32 96.24 96.28 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.32 96.24 96.28 Avg2. 12220 12209 11760 96.32 96.24 96.28 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 88 Log-likelihood = -30742.871282 Norm (log-likelihood gradient vector) = 1336.473812 Norm (lambda vector) = 141.921577 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 20635 20378 98.75 99.06 98.91 i-np 13660 13597 13349 98.18 97.72 97.95 e-np 12220 12219 12032 98.47 98.46 98.47 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.47 98.42 98.44 Avg2. 46451 46451 45759 98.51 98.51 98.51 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12219 11767 96.30 96.29 96.30 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.30 96.29 96.30 Avg2. 12220 12219 11767 96.30 96.29 96.30 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 89 Log-likelihood = -29994.284008 Norm (log-likelihood gradient vector) = 2159.176973 Norm (lambda vector) = 142.988722 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 20475 20283 99.06 98.60 98.83 i-np 13660 13863 13445 96.98 98.43 97.70 e-np 12220 12113 11965 98.78 97.91 98.34 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.28 98.31 98.29 Avg2. 46451 46451 45693 98.37 98.37 98.37 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12113 11665 96.30 95.46 95.88 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.30 95.46 95.88 Avg2. 12220 12113 11665 96.30 95.46 95.88 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 90 Log-likelihood = -29742.200932 Norm (log-likelihood gradient vector) = 6890.878101 Norm (lambda vector) = 144.294600 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 20567 20341 98.90 98.88 98.89 i-np 13660 13705 13396 97.75 98.07 97.91 e-np 12220 12179 12012 98.63 98.30 98.46 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.43 98.42 98.42 Avg2. 46451 46451 45749 98.49 98.49 98.49 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12179 11742 96.41 96.09 96.25 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.41 96.09 96.25 Avg2. 12220 12179 11742 96.41 96.09 96.25 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 91 Log-likelihood = -29499.971804 Norm (log-likelihood gradient vector) = 2493.372483 Norm (lambda vector) = 143.546703 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 20357 98.88 98.96 98.92 i-np 13660 13654 13382 98.01 97.96 97.99 e-np 12220 12210 12029 98.52 98.44 98.48 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.47 98.45 98.46 Avg2. 46451 46451 45768 98.53 98.53 98.53 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12210 11765 96.36 96.28 96.32 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.36 96.28 96.32 Avg2. 12220 12210 11765 96.36 96.28 96.32 Current max chunk-based F1: 96.34 (iteration 69) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 92 Log-likelihood = -28974.863378 Norm (log-likelihood gradient vector) = 1570.306942 Norm (lambda vector) = 144.263266 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 20590 20363 98.90 98.99 98.94 i-np 13660 13645 13387 98.11 98.00 98.06 e-np 12220 12216 12035 98.52 98.49 98.50 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.51 98.49 98.50 Avg2. 46451 46451 45785 98.57 98.57 98.57 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12216 11778 96.41 96.38 96.40 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.41 96.38 96.40 Avg2. 12220 12216 11778 96.41 96.38 96.40 Current max chunk-based F1: 96.40 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 93 Log-likelihood = -28363.912697 Norm (log-likelihood gradient vector) = 1533.557277 Norm (lambda vector) = 144.891624 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 i-np 13660 13627 13371 98.12 97.88 98.00 e-np 12220 12244 12045 98.37 98.57 98.47 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.47 98.47 98.47 Avg2. 46451 46451 45772 98.54 98.54 98.54 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12244 11784 96.24 96.43 96.34 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.24 96.43 96.34 Avg2. 12220 12244 11784 96.24 96.43 96.34 Current max chunk-based F1: 96.40 (iteration 92) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 94 Log-likelihood = -27503.843648 Norm (log-likelihood gradient vector) = 2563.265341 Norm (lambda vector) = 145.781982 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 20575 20355 98.93 98.95 98.94 i-np 13660 13657 13392 98.06 98.04 98.05 e-np 12220 12219 12037 98.51 98.50 98.51 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.50 98.50 Avg2. 46451 46451 45784 98.56 98.56 98.56 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12219 11780 96.41 96.40 96.40 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.41 96.40 96.40 Avg2. 12220 12219 11780 96.41 96.40 96.40 Current max chunk-based F1: 96.40 (iteration 94) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 95 Log-likelihood = -26845.176827 Norm (log-likelihood gradient vector) = 1349.412924 Norm (lambda vector) = 146.240365 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 20357 98.92 98.96 98.94 i-np 13660 13659 13388 98.02 98.01 98.01 e-np 12220 12212 12032 98.53 98.46 98.49 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.49 98.48 98.48 Avg2. 46451 46451 45777 98.55 98.55 98.55 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12212 11771 96.39 96.33 96.36 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.39 96.33 96.36 Avg2. 12220 12212 11771 96.39 96.33 96.36 Current max chunk-based F1: 96.40 (iteration 94) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 96 Log-likelihood = -26460.104898 Norm (log-likelihood gradient vector) = 1217.588055 Norm (lambda vector) = 146.321463 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 20350 98.96 98.93 98.94 i-np 13660 13694 13405 97.89 98.13 98.01 e-np 12220 12194 12023 98.60 98.39 98.49 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.48 98.48 Avg2. 46451 46451 45778 98.55 98.55 98.55 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12194 11763 96.47 96.26 96.36 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.47 96.26 96.36 Avg2. 12220 12194 11763 96.47 96.26 96.36 Current max chunk-based F1: 96.40 (iteration 94) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 97 Log-likelihood = -26006.090207 Norm (log-likelihood gradient vector) = 1656.249709 Norm (lambda vector) = 146.471795 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 20350 98.79 98.93 98.86 i-np 13660 13664 13368 97.83 97.86 97.85 e-np 12220 12188 12018 98.61 98.35 98.48 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.41 98.38 98.39 Avg2. 46451 46451 45736 98.46 98.46 98.46 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12188 11746 96.37 96.12 96.25 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.37 96.12 96.25 Avg2. 12220 12188 11746 96.37 96.12 96.25 Current max chunk-based F1: 96.40 (iteration 94) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 98 Log-likelihood = -25632.229215 Norm (log-likelihood gradient vector) = 4256.659783 Norm (lambda vector) = 147.500422 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 20344 99.01 98.90 98.95 i-np 13660 13720 13415 97.78 98.21 97.99 e-np 12220 12183 12021 98.67 98.37 98.52 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.49 98.49 Avg2. 46451 46451 45780 98.56 98.56 98.56 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12183 11760 96.53 96.24 96.38 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.53 96.24 96.38 Avg2. 12220 12183 11760 96.53 96.24 96.38 Current max chunk-based F1: 96.40 (iteration 94) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 99 Log-likelihood = -25171.057450 Norm (log-likelihood gradient vector) = 1839.334364 Norm (lambda vector) = 147.486281 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 20564 20351 98.96 98.93 98.95 i-np 13660 13687 13398 97.89 98.08 97.99 e-np 12220 12200 12028 98.59 98.43 98.51 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.48 98.48 Avg2. 46451 46451 45777 98.55 98.55 98.55 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12200 11767 96.45 96.29 96.37 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.45 96.29 96.37 Avg2. 12220 12200 11767 96.45 96.29 96.37 Current max chunk-based F1: 96.40 (iteration 94) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 100 Log-likelihood = -25048.851125 Norm (log-likelihood gradient vector) = 1243.573665 Norm (lambda vector) = 147.583491 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 20358 98.96 98.96 98.96 i-np 13660 13667 13393 98.00 98.05 98.02 e-np 12220 12213 12031 98.51 98.45 98.48 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.49 98.49 98.49 Avg2. 46451 46451 45782 98.56 98.56 98.56 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12213 11769 96.36 96.31 96.34 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.36 96.31 96.34 Avg2. 12220 12213 11769 96.36 96.31 96.34 Current max chunk-based F1: 96.40 (iteration 94) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 101 Log-likelihood = -24826.630427 Norm (log-likelihood gradient vector) = 1371.184187 Norm (lambda vector) = 148.009572 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 20608 20374 98.86 99.04 98.95 i-np 13660 13607 13364 98.21 97.83 98.02 e-np 12220 12236 12044 98.43 98.56 98.50 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.48 98.49 Avg2. 46451 46451 45782 98.56 98.56 98.56 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12236 11786 96.32 96.45 96.39 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.32 96.45 96.39 Avg2. 12220 12236 11786 96.32 96.45 96.39 Current max chunk-based F1: 96.40 (iteration 94) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 102 Log-likelihood = -24482.952070 Norm (log-likelihood gradient vector) = 2729.285259 Norm (lambda vector) = 148.643201 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 20591 20368 98.92 99.01 98.97 i-np 13660 13640 13386 98.14 97.99 98.07 e-np 12220 12220 12037 98.50 98.50 98.50 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.52 98.50 98.51 Avg2. 46451 46451 45791 98.58 98.58 98.58 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12220 11782 96.42 96.42 96.42 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.42 96.42 96.42 Avg2. 12220 12220 11782 96.42 96.42 96.42 Current max chunk-based F1: 96.42 (iteration 102) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 103 Log-likelihood = -24060.389907 Norm (log-likelihood gradient vector) = 1865.564378 Norm (lambda vector) = 149.415254 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 20585 20363 98.92 98.99 98.96 i-np 13660 13641 13383 98.11 97.97 98.04 e-np 12220 12225 12039 98.48 98.52 98.50 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.49 98.50 Avg2. 46451 46451 45785 98.57 98.57 98.57 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12225 11781 96.37 96.41 96.39 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.37 96.41 96.39 Avg2. 12220 12225 11781 96.37 96.41 96.39 Current max chunk-based F1: 96.42 (iteration 102) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 104 Log-likelihood = -23687.456098 Norm (log-likelihood gradient vector) = 1403.322569 Norm (lambda vector) = 150.332304 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 20355 98.92 98.95 98.93 i-np 13660 13676 13390 97.91 98.02 97.97 e-np 12220 12197 12027 98.61 98.42 98.51 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.46 98.47 Avg2. 46451 46451 45772 98.54 98.54 98.54 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12197 11765 96.46 96.28 96.37 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.46 96.28 96.37 Avg2. 12220 12197 11765 96.46 96.28 96.37 Current max chunk-based F1: 96.42 (iteration 102) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 105 Log-likelihood = -23578.227696 Norm (log-likelihood gradient vector) = 1774.618094 Norm (lambda vector) = 150.890742 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 20577 20354 98.92 98.95 98.93 i-np 13660 13676 13390 97.91 98.02 97.97 e-np 12220 12198 12028 98.61 98.43 98.52 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.47 98.47 Avg2. 46451 46451 45772 98.54 98.54 98.54 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12198 11766 96.46 96.28 96.37 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.46 96.28 96.37 Avg2. 12220 12198 11766 96.46 96.28 96.37 Current max chunk-based F1: 96.42 (iteration 102) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 106 Log-likelihood = -23537.939621 Norm (log-likelihood gradient vector) = 1431.396258 Norm (lambda vector) = 151.042840 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 20352 98.90 98.94 98.92 i-np 13660 13673 13390 97.93 98.02 97.98 e-np 12220 12200 12030 98.61 98.45 98.53 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.47 98.47 Avg2. 46451 46451 45772 98.54 98.54 98.54 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12200 11772 96.49 96.33 96.41 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.49 96.33 96.41 Avg2. 12220 12200 11772 96.49 96.33 96.41 Current max chunk-based F1: 96.42 (iteration 102) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 107 Log-likelihood = -23596.007328 Norm (log-likelihood gradient vector) = 1087.552709 Norm (lambda vector) = 151.349093 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 20579 20352 98.90 98.94 98.92 i-np 13660 13674 13387 97.90 98.00 97.95 e-np 12220 12198 12028 98.61 98.43 98.52 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.47 98.46 98.46 Avg2. 46451 46451 45767 98.53 98.53 98.53 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12198 11766 96.46 96.28 96.37 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.46 96.28 96.37 Avg2. 12220 12198 11766 96.46 96.28 96.37 Current max chunk-based F1: 96.42 (iteration 102) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 108 Log-likelihood = -23525.391909 Norm (log-likelihood gradient vector) = 1279.391763 Norm (lambda vector) = 151.112727 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 20566 20352 98.96 98.94 98.95 i-np 13660 13680 13400 97.95 98.10 98.02 e-np 12220 12205 12035 98.61 98.49 98.55 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.51 98.51 98.51 Avg2. 46451 46451 45787 98.57 98.57 98.57 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12205 11780 96.52 96.40 96.46 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.52 96.40 96.46 Avg2. 12220 12205 11780 96.52 96.40 96.46 Current max chunk-based F1: 96.46 (iteration 108) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 109 Log-likelihood = -23691.239855 Norm (log-likelihood gradient vector) = 1397.690431 Norm (lambda vector) = 151.873144 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 20579 20353 98.90 98.94 98.92 i-np 13660 13673 13389 97.92 98.02 97.97 e-np 12220 12199 12029 98.61 98.44 98.52 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.46 98.47 Avg2. 46451 46451 45771 98.54 98.54 98.54 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12199 11769 96.48 96.31 96.39 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.48 96.31 96.39 Avg2. 12220 12199 11769 96.48 96.31 96.39 Current max chunk-based F1: 96.46 (iteration 108) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 110 Log-likelihood = -23502.872726 Norm (log-likelihood gradient vector) = 1110.751351 Norm (lambda vector) = 151.282538 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 20380 98.76 99.07 98.92 i-np 13660 13581 13347 98.28 97.71 97.99 e-np 12220 12235 12051 98.50 98.62 98.56 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.51 98.47 98.49 Avg2. 46451 46451 45778 98.55 98.55 98.55 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12235 11793 96.39 96.51 96.45 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.39 96.51 96.45 Avg2. 12220 12235 11793 96.39 96.51 96.45 Current max chunk-based F1: 96.46 (iteration 108) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 111 Log-likelihood = -24567.440300 Norm (log-likelihood gradient vector) = 5371.185674 Norm (lambda vector) = 152.522648 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 20355 98.89 98.95 98.92 i-np 13660 13663 13384 97.96 97.98 97.97 e-np 12220 12204 12032 98.59 98.46 98.53 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.46 98.47 Avg2. 46451 46451 45771 98.54 98.54 98.54 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12204 11772 96.46 96.33 96.40 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.46 96.33 96.40 Avg2. 12220 12204 11772 96.46 96.33 96.40 Current max chunk-based F1: 96.46 (iteration 108) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 112 Log-likelihood = -23507.217951 Norm (log-likelihood gradient vector) = 1102.946304 Norm (lambda vector) = 151.492045 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 20354 98.89 98.95 98.92 i-np 13660 13666 13384 97.94 97.98 97.96 e-np 12220 12202 12030 98.59 98.45 98.52 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.47 98.46 98.46 Avg2. 46451 46451 45768 98.53 98.53 98.53 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12202 11769 96.45 96.31 96.38 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.45 96.31 96.38 Avg2. 12220 12202 11769 96.45 96.31 96.38 Current max chunk-based F1: 96.46 (iteration 108) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 113 Log-likelihood = -23497.178050 Norm (log-likelihood gradient vector) = 1027.848116 Norm (lambda vector) = 151.331663 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 20355 98.89 98.95 98.92 i-np 13660 13663 13384 97.96 97.98 97.97 e-np 12220 12204 12032 98.59 98.46 98.53 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.46 98.47 Avg2. 46451 46451 45771 98.54 98.54 98.54 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12204 11772 96.46 96.33 96.40 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.46 96.33 96.40 Avg2. 12220 12204 11772 96.46 96.33 96.40 Current max chunk-based F1: 96.46 (iteration 108) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 114 Log-likelihood = -23498.913472 Norm (log-likelihood gradient vector) = 1017.869840 Norm (lambda vector) = 151.437384 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 20350 98.96 98.93 98.94 i-np 13660 13690 13405 97.92 98.13 98.03 e-np 12220 12198 12030 98.62 98.45 98.53 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.50 98.50 Avg2. 46451 46451 45785 98.57 98.57 98.57 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12198 11775 96.53 96.36 96.45 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.53 96.36 96.45 Avg2. 12220 12198 11775 96.53 96.36 96.45 Current max chunk-based F1: 96.46 (iteration 108) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 115 Log-likelihood = -23918.552243 Norm (log-likelihood gradient vector) = 1567.877772 Norm (lambda vector) = 152.442484 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 20580 20355 98.91 98.95 98.93 i-np 13660 13667 13388 97.96 98.01 97.98 e-np 12220 12204 12032 98.59 98.46 98.53 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.49 98.47 98.48 Avg2. 46451 46451 45775 98.54 98.54 98.54 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 108) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 116 Log-likelihood = -23499.480470 Norm (log-likelihood gradient vector) = 923.025234 Norm (lambda vector) = 151.627885 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 20584 20355 98.89 98.95 98.92 i-np 13660 13663 13384 97.96 97.98 97.97 e-np 12220 12204 12032 98.59 98.46 98.53 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.46 98.47 Avg2. 46451 46451 45771 98.54 98.54 98.54 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12204 11772 96.46 96.33 96.40 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.46 96.33 96.40 Avg2. 12220 12204 11772 96.46 96.33 96.40 Current max chunk-based F1: 96.46 (iteration 108) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 117 Log-likelihood = -23495.596586 Norm (log-likelihood gradient vector) = 986.052672 Norm (lambda vector) = 151.480799 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 20355 98.89 98.95 98.92 i-np 13660 13663 13384 97.96 97.98 97.97 e-np 12220 12205 12032 98.58 98.46 98.52 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.46 98.47 Avg2. 46451 46451 45771 98.54 98.54 98.54 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 108) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 118 Log-likelihood = -23495.560842 Norm (log-likelihood gradient vector) = 936.411072 Norm (lambda vector) = 151.577761 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 20676 20399 98.66 99.16 98.91 i-np 13660 13484 13293 98.58 97.31 97.94 e-np 12220 12291 12069 98.19 98.76 98.48 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.41 98.45 Avg2. 46451 46451 45761 98.51 98.51 98.51 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12291 11807 96.06 96.62 96.34 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.06 96.62 96.34 Avg2. 12220 12291 11807 96.06 96.62 96.34 Current max chunk-based F1: 96.46 (iteration 108) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 119 Log-likelihood = -25195.088120 Norm (log-likelihood gradient vector) = 8398.028591 Norm (lambda vector) = 154.429187 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 20597 20362 98.86 98.98 98.92 i-np 13660 13638 13375 98.07 97.91 97.99 e-np 12220 12216 12040 98.56 98.53 98.54 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.47 98.49 Avg2. 46451 46451 45777 98.55 98.55 98.55 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12216 11784 96.46 96.43 96.45 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.46 96.43 96.45 Avg2. 12220 12216 11784 96.46 96.43 96.45 Current max chunk-based F1: 96.46 (iteration 108) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 120 Log-likelihood = -23500.146443 Norm (log-likelihood gradient vector) = 1357.689722 Norm (lambda vector) = 151.996498 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 20355 98.89 98.95 98.92 i-np 13660 13662 13384 97.97 97.98 97.97 e-np 12220 12206 12033 98.58 98.47 98.53 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.47 98.47 Avg2. 46451 46451 45772 98.54 98.54 98.54 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12206 11774 96.46 96.35 96.41 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.46 96.35 96.41 Avg2. 12220 12206 11774 96.46 96.35 96.41 Current max chunk-based F1: 96.46 (iteration 108) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 121 Log-likelihood = -23488.714349 Norm (log-likelihood gradient vector) = 910.686341 Norm (lambda vector) = 151.677842 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 20361 98.87 98.98 98.93 i-np 13660 13647 13381 98.05 97.96 98.00 e-np 12220 12211 12038 98.58 98.51 98.55 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.48 98.49 Avg2. 46451 46451 45780 98.56 98.56 98.56 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12211 11783 96.49 96.42 96.46 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.49 96.42 96.46 Avg2. 12220 12211 11783 96.49 96.42 96.46 Current max chunk-based F1: 96.46 (iteration 121) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 122 Log-likelihood = -23490.600833 Norm (log-likelihood gradient vector) = 1139.707915 Norm (lambda vector) = 151.887819 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 20608 20368 98.84 99.01 98.92 i-np 13660 13613 13363 98.16 97.83 97.99 e-np 12220 12230 12040 98.45 98.53 98.49 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.48 98.46 98.47 Avg2. 46451 46451 45771 98.54 98.54 98.54 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12230 11780 96.32 96.40 96.36 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.32 96.40 96.36 Avg2. 12220 12230 11780 96.32 96.40 96.36 Current max chunk-based F1: 96.46 (iteration 121) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 123 Log-likelihood = -23884.762219 Norm (log-likelihood gradient vector) = 1563.232131 Norm (lambda vector) = 153.438621 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 20361 98.86 98.98 98.92 i-np 13660 13643 13378 98.06 97.94 98.00 e-np 12220 12213 12039 98.58 98.52 98.55 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.48 98.49 Avg2. 46451 46451 45778 98.55 98.55 98.55 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12213 11783 96.48 96.42 96.45 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.48 96.42 96.45 Avg2. 12220 12213 11783 96.48 96.42 96.45 Current max chunk-based F1: 96.46 (iteration 121) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 124 Log-likelihood = -23498.738906 Norm (log-likelihood gradient vector) = 1137.205648 Norm (lambda vector) = 152.168680 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 20361 98.87 98.98 98.93 i-np 13660 13646 13381 98.06 97.96 98.01 e-np 12220 12212 12039 98.58 98.52 98.55 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.49 98.50 Avg2. 46451 46451 45781 98.56 98.56 98.56 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12212 11785 96.50 96.44 96.47 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.50 96.44 96.47 Avg2. 12220 12212 11785 96.50 96.44 96.47 Current max chunk-based F1: 96.47 (iteration 124) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 125 Log-likelihood = -23489.893261 Norm (log-likelihood gradient vector) = 1135.363144 Norm (lambda vector) = 151.947528 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 20361 98.87 98.98 98.92 i-np 13660 13644 13379 98.06 97.94 98.00 e-np 12220 12213 12039 98.58 98.52 98.55 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.48 98.49 Avg2. 46451 46451 45779 98.55 98.55 98.55 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12213 11784 96.49 96.43 96.46 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.49 96.43 96.46 Avg2. 12220 12213 11784 96.49 96.43 96.46 Current max chunk-based F1: 96.47 (iteration 124) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 126 Log-likelihood = -23493.709213 Norm (log-likelihood gradient vector) = 1133.456483 Norm (lambda vector) = 152.093304 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 20361 98.87 98.98 98.93 i-np 13660 13646 13381 98.06 97.96 98.01 e-np 12220 12212 12039 98.58 98.52 98.55 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.49 98.50 Avg2. 46451 46451 45781 98.56 98.56 98.56 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12212 11785 96.50 96.44 96.47 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.50 96.44 96.47 Avg2. 12220 12212 11785 96.50 96.44 96.47 Current max chunk-based F1: 96.47 (iteration 124) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 127 Log-likelihood = -23490.039834 Norm (log-likelihood gradient vector) = 1133.959654 Norm (lambda vector) = 151.977730 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 20361 98.87 98.98 98.93 i-np 13660 13646 13381 98.06 97.96 98.01 e-np 12220 12212 12039 98.58 98.52 98.55 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.49 98.50 Avg2. 46451 46451 45781 98.56 98.56 98.56 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12212 11785 96.50 96.44 96.47 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.50 96.44 96.47 Avg2. 12220 12212 11785 96.50 96.44 96.47 Current max chunk-based F1: 96.47 (iteration 124) Training iteration elapsed (including evaluation time): 25 seconds Iteration: 128 Log-likelihood = -23489.896027 Norm (log-likelihood gradient vector) = 1135.023185 Norm (lambda vector) = 151.953892 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 20593 20361 98.87 98.98 98.93 i-np 13660 13646 13381 98.06 97.96 98.01 e-np 12220 12212 12039 98.58 98.52 98.55 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.49 98.50 Avg2. 46451 46451 45781 98.56 98.56 98.56 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12212 11785 96.50 96.44 96.47 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.50 96.44 96.47 Avg2. 12220 12212 11785 96.50 96.44 96.47 Current max chunk-based F1: 96.47 (iteration 124) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 129 Log-likelihood = -23489.892593 Norm (log-likelihood gradient vector) = 1135.289286 Norm (lambda vector) = 151.948874 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 20361 98.87 98.98 98.93 i-np 13660 13646 13381 98.06 97.96 98.01 e-np 12220 12212 12039 98.58 98.52 98.55 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.49 98.50 Avg2. 46451 46451 45781 98.56 98.56 98.56 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12212 11785 96.50 96.44 96.47 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.50 96.44 96.47 Avg2. 12220 12212 11785 96.50 96.44 96.47 Current max chunk-based F1: 96.47 (iteration 124) Training iteration elapsed (including evaluation time): 26 seconds Iteration: 130 Log-likelihood = -23489.893811 Norm (log-likelihood gradient vector) = 1135.112015 Norm (lambda vector) = 151.952186 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 20361 98.87 98.98 98.93 i-np 13660 13646 13381 98.06 97.96 98.01 e-np 12220 12212 12039 98.58 98.52 98.55 ----- ------ ----- ----- ------- ------- ------------- Avg1. 98.50 98.49 98.50 Avg2. 46451 46451 45781 98.56 98.56 98.56 Chunk-based performance evaluation: Chunk Manual Model Match Pre.(%) Rec.(%) F1-Measure(%) ----- ------ ----- ----- ------- ------- ------------- np 12220 12212 11785 96.50 96.44 96.47 ----- ------ ----- ----- ------- ------- ------------- Avg1. 96.50 96.44 96.47 Avg2. 12220 12212 11785 96.50 96.44 96.47 Current max chunk-based F1: 96.47 (iteration 124) Training iteration elapsed (including evaluation time): 25 seconds The training process elapsed: 3367 seconds